diff options
| author | Jonathan Kew <jfkthame@googlemail.com> | 2008-03-04 13:26:36 +0000 |
|---|---|---|
| committer | Jonathan Kew <jfkthame@googlemail.com> | 2008-03-04 13:26:36 +0000 |
| commit | 53790d2a0c50915d8cec71df3e89cd24d887b2fe (patch) | |
| tree | 16f6b4df067eb3c2024e0a7735cb7ccea86b3aba /Build/source/libs/icu-xetex/i18n/unicode | |
| parent | f483a5de9331a257f597282e611ecfb63f5ab118 (diff) | |
update icu-xetex to 3.8.1-based code from xetex repository
git-svn-id: svn://tug.org/texlive/trunk@6842 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Build/source/libs/icu-xetex/i18n/unicode')
51 files changed, 31754 insertions, 0 deletions
diff --git a/Build/source/libs/icu-xetex/i18n/unicode/basictz.h b/Build/source/libs/icu-xetex/i18n/unicode/basictz.h new file mode 100644 index 00000000000..a49effd5b0b --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/basictz.h @@ -0,0 +1,210 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef BASICTZ_H +#define BASICTZ_H + +/** + * \file + * \brief C++ API: ICU TimeZone base class + */ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/timezone.h" +#include "unicode/tzrule.h" +#include "unicode/tztrans.h" + +U_NAMESPACE_BEGIN + +// forward declarations +class UVector; + +/** + * <code>BasicTimeZone</code> is an abstract class extending <code>TimeZone</code>. + * This class provides some additional methods to access time zone transitions and rules. + * All ICU <code>TimeZone</code> concrete subclasses extend this class. + * @draft ICU 3.8 + */ +class U_I18N_API BasicTimeZone: public TimeZone { +public: + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~BasicTimeZone(); + + /** + * Gets the first time zone transition after the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the first transition after the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/ = 0; + + /** + * Gets the most recent time zone transition before the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the most recent transition before the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/ = 0; + + /** + * Checks if the time zone has equivalent transitions in the time range. + * This method returns true when all of transition times, from/to standard + * offsets and DST savings used by this time zone match the other in the + * time range. + * @param tz The <code>BasicTimeZone</code> object to be compared with. + * @param start The start time of the evaluated time range (inclusive) + * @param end The end time of the evaluated time range (inclusive) + * @param ignoreDstAmount + * When true, any transitions with only daylight saving amount + * changes will be ignored, except either of them is zero. + * For example, a transition from rawoffset 3:00/dstsavings 1:00 + * to rawoffset 2:00/dstsavings 2:00 is excluded from the comparison, + * but a transtion from rawoffset 2:00/dstsavings 1:00 to + * rawoffset 3:00/dstsavings 0:00 is included. + * @param ec Output param to filled in with a success or an error. + * @return true if the other time zone has the equivalent transitions in the + * time range. + * @draft ICU 3.8 + */ + virtual UBool hasEquivalentTransitions(/*const*/ BasicTimeZone& tz, UDate start, UDate end, + UBool ignoreDstAmount, UErrorCode& ec) /*const*/; + + /** + * Returns the number of <code>TimeZoneRule</code>s which represents time transitions, + * for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except + * <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value. + * @param status Receives error status code. + * @return The number of <code>TimeZoneRule</code>s representing time transitions. + * @draft ICU 3.8 + */ + virtual int32_t countTransitionRules(UErrorCode& status) /*const*/ = 0; + + /** + * Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code> + * which represent time transitions for this time zone. On successful return, + * the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and + * the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code> + * instances up to the size specified by trscount. The results are referencing the + * rule instance held by this time zone instance. Therefore, after this time zone + * is destructed, they are no longer available. + * @param initial Receives the initial timezone rule + * @param trsrules Receives the timezone transition rules + * @param trscount On input, specify the size of the array 'transitions' receiving + * the timezone transition rules. On output, actual number of + * rules filled in the array will be set. + * @param status Receives error status code. + * @draft ICU 3.8 + */ + virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial, + const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) /*const*/ = 0; + + /** + * Gets the set of time zone rules valid at the specified time. Some known external time zone + * implementations are not capable to handle historic time zone rule changes. Also some + * implementations can only handle certain type of rule definitions. + * If this time zone does not use any daylight saving time within about 1 year from the specified + * time, only the <code>InitialTimeZone</code> is returned. Otherwise, the rule for standard + * time and daylight saving time transitions are returned in addition to the + * <code>InitialTimeZoneRule</code>. The standard and daylight saving time transition rules are + * represented by <code>AnnualTimeZoneRule</code> with <code>DateTimeRule::DOW</code> for its date + * rule and <code>DateTimeRule::WALL_TIME</code> for its time rule. Because daylight saving time + * rule is changing time to time in many time zones and also mapping a transition time rule to + * different type is lossy transformation, the set of rules returned by this method may be valid + * for short period of time. + * The time zone rule objects returned by this method is owned by the caller, so the caller is + * responsible for deleting them after use. + * @param date The date used for extracting time zone rules. + * @param initial Receives the <code>InitialTimeZone</code>, always not NULL. + * @param std Receives the <code>AnnualTimeZoneRule</code> for standard time transitions. + * When this time time zone does not observe daylight saving times around the + * specified date, NULL is set. + * @param dst Receives the <code>AnnualTimeZoneRule</code> for daylight saving time + * transitions. When this time zone does not observer daylight saving times + * around the specified date, NULL is set. + * @param status Receives error status code. + * @draft ICU 3.8 + */ + virtual void getSimpleRulesNear(UDate date, InitialTimeZoneRule*& initial, + AnnualTimeZoneRule*& std, AnnualTimeZoneRule*& dst, UErrorCode& status) /*const*/; + + + /** + * The time type option bit flags used by getOffsetFromLocal + * @internal + */ + enum { + kStandard = 0x01, + kDaylight = 0x03, + kFormer = 0x04, + kLatter = 0x0C + }; + + /** + * Get time zone offsets from local wall time. + * @internal + */ + virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt, int32_t duplicatedTimeOpt, + int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) /*const*/; + +protected: + + /** + * The time type option bit masks used by getOffsetFromLocal + * @internal + */ + enum { + kStdDstMask = kDaylight, + kFormerLatterMask = kLatter + }; + + /** + * Default constructor. + * @draft ICU 3.8 + */ + BasicTimeZone(); + + /** + * Construct a timezone with a given ID. + * @param id a system time zone ID + * @draft ICU 3.8 + */ + BasicTimeZone(const UnicodeString &id); + + /** + * Copy constructor. + * @param source the object to be copied. + * @draft ICU 3.8 + */ + BasicTimeZone(const BasicTimeZone& source); + + /** + * Gets the set of TimeZoneRule instances applicable to the specified time and after. + * @param start The start date used for extracting time zone rules + * @param initial Receives the InitialTimeZone, always not NULL + * @param transitionRules Receives the transition rules, could be NULL + * @param status Receives error status code + */ + void getTimeZoneRulesAfter(UDate start, InitialTimeZoneRule*& initial, UVector*& transitionRules, + UErrorCode& status) /*const*/; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // BASICTZ_H + +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/calendar.h b/Build/source/libs/icu-xetex/i18n/unicode/calendar.h new file mode 100644 index 00000000000..d048a8b8a8a --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/calendar.h @@ -0,0 +1,2161 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2006, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File CALENDAR.H +* +* Modification History: +* +* Date Name Description +* 04/22/97 aliu Expanded and corrected comments and other header +* contents. +* 05/01/97 aliu Made equals(), before(), after() arguments const. +* 05/20/97 aliu Replaced fAreFieldsSet with fAreFieldsInSync and +* fAreAllFieldsSet. +* 07/27/98 stephen Sync up with JDK 1.2 +* 11/15/99 weiv added YEAR_WOY and DOW_LOCAL +* to EDateFields +* 8/19/2002 srl Removed Javaisms +* 11/07/2003 srl Update, clean up documentation. +******************************************************************************** +*/ + +#ifndef CALENDAR_H +#define CALENDAR_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Calendar object + */ +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" +#include "unicode/locid.h" +#include "unicode/timezone.h" +#include "unicode/ucal.h" +#include "unicode/umisc.h" + +U_NAMESPACE_BEGIN + +class ICUServiceFactory; + +/** + * @internal + */ +typedef int32_t UFieldResolutionTable[12][8]; + +/** + * <code>Calendar</code> is an abstract base class for converting between + * a <code>UDate</code> object and a set of integer fields such as + * <code>YEAR</code>, <code>MONTH</code>, <code>DAY</code>, <code>HOUR</code>, + * and so on. (A <code>UDate</code> object represents a specific instant in + * time with millisecond precision. See UDate + * for information about the <code>UDate</code> class.) + * + * <p> + * Subclasses of <code>Calendar</code> interpret a <code>UDate</code> + * according to the rules of a specific calendar system. + * The most commonly used subclass of <code>Calendar</code> is + * <code>GregorianCalendar</code>. Other subclasses could represent + * the various types of lunar calendars in use in many parts of the world. + * + * <p> + * <b>NOTE</b>: (ICU 2.6) The subclass interface should be considered unstable + * - it WILL change. + * + * <p> + * Like other locale-sensitive classes, <code>Calendar</code> provides a + * static method, <code>createInstance</code>, for getting a generally useful + * object of this type. <code>Calendar</code>'s <code>createInstance</code> method + * returns the appropriate <code>Calendar</code> subclass whose + * time fields have been initialized with the current date and time: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * Calendar *rightNow = Calendar::createInstance(errCode); + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <p> + * A <code>Calendar</code> object can produce all the time field values + * needed to implement the date-time formatting for a particular language + * and calendar style (for example, Japanese-Gregorian, Japanese-Traditional). + * + * <p> + * When computing a <code>UDate</code> from time fields, two special circumstances + * may arise: there may be insufficient information to compute the + * <code>UDate</code> (such as only year and month but no day in the month), + * or there may be inconsistent information (such as "Tuesday, July 15, 1996" + * -- July 15, 1996 is actually a Monday). + * + * <p> + * <strong>Insufficient information.</strong> The calendar will use default + * information to specify the missing fields. This may vary by calendar; for + * the Gregorian calendar, the default for a field is the same as that of the + * start of the epoch: i.e., YEAR = 1970, MONTH = JANUARY, DATE = 1, etc. + * + * <p> + * <strong>Inconsistent information.</strong> If fields conflict, the calendar + * will give preference to fields set more recently. For example, when + * determining the day, the calendar will look for one of the following + * combinations of fields. The most recent combination, as determined by the + * most recently set single field, will be used. + * + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * MONTH + DAY_OF_MONTH + * MONTH + WEEK_OF_MONTH + DAY_OF_WEEK + * MONTH + DAY_OF_WEEK_IN_MONTH + DAY_OF_WEEK + * DAY_OF_YEAR + * DAY_OF_WEEK + WEEK_OF_YEAR + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * For the time of day: + * + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * HOUR_OF_DAY + * AM_PM + HOUR + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <p> + * <strong>Note:</strong> for some non-Gregorian calendars, different + * fields may be necessary for complete disambiguation. For example, a full + * specification of the historial Arabic astronomical calendar requires year, + * month, day-of-month <em>and</em> day-of-week in some cases. + * + * <p> + * <strong>Note:</strong> There are certain possible ambiguities in + * interpretation of certain singular times, which are resolved in the + * following ways: + * <ol> + * <li> 24:00:00 "belongs" to the following day. That is, + * 23:59 on Dec 31, 1969 < 24:00 on Jan 1, 1970 < 24:01:00 on Jan 1, 1970 + * + * <li> Although historically not precise, midnight also belongs to "am", + * and noon belongs to "pm", so on the same day, + * 12:00 am (midnight) < 12:01 am, and 12:00 pm (noon) < 12:01 pm + * </ol> + * + * <p> + * The date or time format strings are not part of the definition of a + * calendar, as those must be modifiable or overridable by the user at + * runtime. Use {@link DateFormat} + * to format dates. + * + * <p> + * <code>Calendar</code> provides an API for field "rolling", where fields + * can be incremented or decremented, but wrap around. For example, rolling the + * month up in the date <code>December 12, <b>1996</b></code> results in + * <code>January 12, <b>1996</b></code>. + * + * <p> + * <code>Calendar</code> also provides a date arithmetic function for + * adding the specified (signed) amount of time to a particular time field. + * For example, subtracting 5 days from the date <code>September 12, 1996</code> + * results in <code>September 7, 1996</code>. + * + * @stable ICU 2.0 + */ +class U_I18N_API Calendar : public UObject { +public: + + /** + * Field IDs for date and time. Used to specify date/time fields. ERA is calendar + * specific. Example ranges given are for illustration only; see specific Calendar + * subclasses for actual ranges. + * @deprecated ICU 2.6. Use C enum UCalendarDateFields defined in ucal.h + */ + enum EDateFields { +#ifndef U_HIDE_DEPRECATED_API + ERA, // Example: 0..1 + YEAR, // Example: 1..big number + MONTH, // Example: 0..11 + WEEK_OF_YEAR, // Example: 1..53 + WEEK_OF_MONTH, // Example: 1..4 + DATE, // Example: 1..31 + DAY_OF_YEAR, // Example: 1..365 + DAY_OF_WEEK, // Example: 1..7 + DAY_OF_WEEK_IN_MONTH, // Example: 1..4, may be specified as -1 + AM_PM, // Example: 0..1 + HOUR, // Example: 0..11 + HOUR_OF_DAY, // Example: 0..23 + MINUTE, // Example: 0..59 + SECOND, // Example: 0..59 + MILLISECOND, // Example: 0..999 + ZONE_OFFSET, // Example: -12*U_MILLIS_PER_HOUR..12*U_MILLIS_PER_HOUR + DST_OFFSET, // Example: 0 or U_MILLIS_PER_HOUR + YEAR_WOY, // 'Y' Example: 1..big number - Year of Week of Year + DOW_LOCAL, // 'e' Example: 1..7 - Day of Week / Localized + + FIELD_COUNT = UCAL_FIELD_COUNT // See ucal.h for other fields. +#endif /* U_HIDE_DEPRECATED_API */ + }; + + /** + * Useful constant for days of week. Note: Calendar day-of-week is 1-based. Clients + * who create locale resources for the field of first-day-of-week should be aware of + * this. For instance, in US locale, first-day-of-week is set to 1, i.e., SUNDAY. + * @deprecated ICU 2.6. Use C enum UCalendarDaysOfWeek defined in ucal.h + */ + enum EDaysOfWeek { +#ifndef U_HIDE_DEPRECATED_API + SUNDAY = 1, + MONDAY, + TUESDAY, + WEDNESDAY, + THURSDAY, + FRIDAY, + SATURDAY +#endif /* U_HIDE_DEPRECATED_API */ + }; + + /** + * Useful constants for month. Note: Calendar month is 0-based. + * @deprecated ICU 2.6. Use C enum UCalendarMonths defined in ucal.h + */ + enum EMonths { +#ifndef U_HIDE_DEPRECATED_API + JANUARY, + FEBRUARY, + MARCH, + APRIL, + MAY, + JUNE, + JULY, + AUGUST, + SEPTEMBER, + OCTOBER, + NOVEMBER, + DECEMBER, + UNDECIMBER +#endif /* U_HIDE_DEPRECATED_API */ + }; + + /** + * Useful constants for hour in 12-hour clock. Used in GregorianCalendar. + * @deprecated ICU 2.6. Use C enum UCalendarAMPMs defined in ucal.h + */ + enum EAmpm { +#ifndef U_HIDE_DEPRECATED_API + AM, + PM +#endif /* U_HIDE_DEPRECATED_API */ + }; + + /** + * destructor + * @stable ICU 2.0 + */ + virtual ~Calendar(); + + /** + * Create and return a polymorphic copy of this calendar. + * + * @return a polymorphic copy of this calendar. + * @stable ICU 2.0 + */ + virtual Calendar* clone(void) const = 0; + + /** + * Creates a Calendar using the default timezone and locale. Clients are responsible + * for deleting the object returned. + * + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. U_MISSING_RESOURCE_ERROR will be returned if the resource data + * requests a calendar type which has not been installed. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(UErrorCode& success); + + /** + * Creates a Calendar using the given timezone and the default locale. + * The Calendar takes ownership of zoneToAdopt; the + * client must not delete it. + * + * @param zoneToAdopt The given timezone to be adopted. + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(TimeZone* zoneToAdopt, UErrorCode& success); + + /** + * Creates a Calendar using the given timezone and the default locale. The TimeZone + * is _not_ adopted; the client is still responsible for deleting it. + * + * @param zone The timezone. + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(const TimeZone& zone, UErrorCode& success); + + /** + * Creates a Calendar using the default timezone and the given locale. + * + * @param aLocale The given locale. + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(const Locale& aLocale, UErrorCode& success); + + /** + * Creates a Calendar using the given timezone and given locale. + * The Calendar takes ownership of zoneToAdopt; the + * client must not delete it. + * + * @param zoneToAdopt The given timezone to be adopted. + * @param aLocale The given locale. + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(TimeZone* zoneToAdopt, const Locale& aLocale, UErrorCode& success); + + /** + * Gets a Calendar using the given timezone and given locale. The TimeZone + * is _not_ adopted; the client is still responsible for deleting it. + * + * @param zoneToAdopt The given timezone to be adopted. + * @param aLocale The given locale. + * @param success Indicates the success/failure of Calendar creation. Filled in + * with U_ZERO_ERROR if created successfully, set to a failure result + * otherwise. + * @return A Calendar if created successfully. NULL otherwise. + * @stable ICU 2.0 + */ + static Calendar* U_EXPORT2 createInstance(const TimeZone& zoneToAdopt, const Locale& aLocale, UErrorCode& success); + + /** + * Returns a list of the locales for which Calendars are installed. + * + * @param count Number of locales returned. + * @return An array of Locale objects representing the set of locales for which + * Calendars are installed. The system retains ownership of this list; + * the caller must NOT delete it. Does not include user-registered Calendars. + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + + /** + * Returns the current UTC (GMT) time measured in milliseconds since 0:00:00 on 1/1/70 + * (derived from the system time). + * + * @return The current UTC time in milliseconds. + * @stable ICU 2.0 + */ + static UDate U_EXPORT2 getNow(void); + + /** + * Gets this Calendar's time as milliseconds. May involve recalculation of time due + * to previous calls to set time field values. The time specified is non-local UTC + * (GMT) time. Although this method is const, this object may actually be changed + * (semantically const). + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @return The current time in UTC (GMT) time, or zero if the operation + * failed. + * @stable ICU 2.0 + */ + inline UDate getTime(UErrorCode& status) const { return getTimeInMillis(status); } + + /** + * Sets this Calendar's current time with the given UDate. The time specified should + * be in non-local UTC (GMT) time. + * + * @param date The given UDate in UTC (GMT) time. + * @param status Output param set to success/failure code on exit. If any value + * set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.0 + */ + inline void setTime(UDate date, UErrorCode& status) { setTimeInMillis(date, status); } + + /** + * Compares the equality of two Calendar objects. Objects of different subclasses + * are considered unequal. This comparison is very exacting; two Calendar objects + * must be in exactly the same state to be considered equal. To compare based on the + * represented time, use equals() instead. + * + * @param that The Calendar object to be compared with. + * @return True if the given Calendar is the same as this Calendar; false + * otherwise. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Calendar& that) const; + + /** + * Compares the inequality of two Calendar objects. + * + * @param that The Calendar object to be compared with. + * @return True if the given Calendar is not the same as this Calendar; false + * otherwise. + * @stable ICU 2.0 + */ + UBool operator!=(const Calendar& that) const {return !operator==(that);} + + /** + * Returns TRUE if the given Calendar object is equivalent to this + * one. An equivalent Calendar will behave exactly as this one + * does, but it may be set to a different time. By contrast, for + * the operator==() method to return TRUE, the other Calendar must + * be set to the same time. + * + * @param other the Calendar to be compared with this Calendar + * @stable ICU 2.4 + */ + virtual UBool isEquivalentTo(const Calendar& other) const; + + /** + * Compares the Calendar time, whereas Calendar::operator== compares the equality of + * Calendar objects. + * + * @param when The Calendar to be compared with this Calendar. Although this is a + * const parameter, the object may be modified physically + * (semantically const). + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @return True if the current time of this Calendar is equal to the time of + * Calendar when; false otherwise. + * @stable ICU 2.0 + */ + UBool equals(const Calendar& when, UErrorCode& status) const; + + /** + * Returns true if this Calendar's current time is before "when"'s current time. + * + * @param when The Calendar to be compared with this Calendar. Although this is a + * const parameter, the object may be modified physically + * (semantically const). + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @return True if the current time of this Calendar is before the time of + * Calendar when; false otherwise. + * @stable ICU 2.0 + */ + UBool before(const Calendar& when, UErrorCode& status) const; + + /** + * Returns true if this Calendar's current time is after "when"'s current time. + * + * @param when The Calendar to be compared with this Calendar. Although this is a + * const parameter, the object may be modified physically + * (semantically const). + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @return True if the current time of this Calendar is after the time of + * Calendar when; false otherwise. + * @stable ICU 2.0 + */ + UBool after(const Calendar& when, UErrorCode& status) const; + + /** + * UDate Arithmetic function. Adds the specified (signed) amount of time to the given + * time field, based on the calendar's rules. For example, to subtract 5 days from + * the current time of the calendar, call add(Calendar::DATE, -5). When adding on + * the month or Calendar::MONTH field, other fields like date might conflict and + * need to be changed. For instance, adding 1 month on the date 01/31/96 will result + * in 02/29/96. + * + * @param field Specifies which date field to modify. + * @param amount The amount of time to be added to the field, in the natural unit + * for that field (e.g., days for the day fields, hours for the hour + * field.) + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @deprecated ICU 2.6. use add(UCalendarDateFields field, int32_t amount, UErrorCode& status) instead. + */ + virtual void add(EDateFields field, int32_t amount, UErrorCode& status); + + /** + * UDate Arithmetic function. Adds the specified (signed) amount of time to the given + * time field, based on the calendar's rules. For example, to subtract 5 days from + * the current time of the calendar, call add(Calendar::DATE, -5). When adding on + * the month or Calendar::MONTH field, other fields like date might conflict and + * need to be changed. For instance, adding 1 month on the date 01/31/96 will result + * in 02/29/96. + * + * @param field Specifies which date field to modify. + * @param amount The amount of time to be added to the field, in the natural unit + * for that field (e.g., days for the day fields, hours for the hour + * field.) + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.6. + */ + virtual void add(UCalendarDateFields field, int32_t amount, UErrorCode& status); + + /** + * Time Field Rolling function. Rolls (up/down) a single unit of time on the given + * time field. For example, to roll the current date up by one day, call + * roll(Calendar::DATE, true). When rolling on the year or Calendar::YEAR field, it + * will roll the year value in the range between getMinimum(Calendar::YEAR) and the + * value returned by getMaximum(Calendar::YEAR). When rolling on the month or + * Calendar::MONTH field, other fields like date might conflict and, need to be + * changed. For instance, rolling the month up on the date 01/31/96 will result in + * 02/29/96. Rolling up always means rolling forward in time; e.g., rolling the year + * up on "100 BC" will result in "99 BC", for Gregorian calendar. When rolling on the + * hour-in-day or Calendar::HOUR_OF_DAY field, it will roll the hour value in the range + * between 0 and 23, which is zero-based. + * <P> + * NOTE: Do not use this method -- use roll(EDateFields, int, UErrorCode&) instead. + * + * @param field The time field. + * @param up Indicates if the value of the specified time field is to be rolled + * up or rolled down. Use true if rolling up, false otherwise. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @deprecated ICU 2.6. Use roll(UCalendarDateFields field, UBool up, UErrorCode& status) instead. + */ + inline void roll(EDateFields field, UBool up, UErrorCode& status); + + /** + * Time Field Rolling function. Rolls (up/down) a single unit of time on the given + * time field. For example, to roll the current date up by one day, call + * roll(Calendar::DATE, true). When rolling on the year or Calendar::YEAR field, it + * will roll the year value in the range between getMinimum(Calendar::YEAR) and the + * value returned by getMaximum(Calendar::YEAR). When rolling on the month or + * Calendar::MONTH field, other fields like date might conflict and, need to be + * changed. For instance, rolling the month up on the date 01/31/96 will result in + * 02/29/96. Rolling up always means rolling forward in time; e.g., rolling the year + * up on "100 BC" will result in "99 BC", for Gregorian calendar. When rolling on the + * hour-in-day or Calendar::HOUR_OF_DAY field, it will roll the hour value in the range + * between 0 and 23, which is zero-based. + * <P> + * NOTE: Do not use this method -- use roll(UCalendarDateFields, int, UErrorCode&) instead. + * + * @param field The time field. + * @param up Indicates if the value of the specified time field is to be rolled + * up or rolled down. Use true if rolling up, false otherwise. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.6. + */ + inline void roll(UCalendarDateFields field, UBool up, UErrorCode& status); + + /** + * Time Field Rolling function. Rolls by the given amount on the given + * time field. For example, to roll the current date up by one day, call + * roll(Calendar::DATE, +1, status). When rolling on the month or + * Calendar::MONTH field, other fields like date might conflict and, need to be + * changed. For instance, rolling the month up on the date 01/31/96 will result in + * 02/29/96. Rolling by a positive value always means rolling forward in time; + * e.g., rolling the year by +1 on "100 BC" will result in "99 BC", for Gregorian + * calendar. When rolling on the hour-in-day or Calendar::HOUR_OF_DAY field, it will + * roll the hour value in the range between 0 and 23, which is zero-based. + * <P> + * The only difference between roll() and add() is that roll() does not change + * the value of more significant fields when it reaches the minimum or maximum + * of its range, whereas add() does. + * + * @param field The time field. + * @param amount Indicates amount to roll. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @deprecated ICU 2.6. Use roll(UCalendarDateFields field, int32_t amount, UErrorCode& status) instead. + */ + virtual void roll(EDateFields field, int32_t amount, UErrorCode& status); + + /** + * Time Field Rolling function. Rolls by the given amount on the given + * time field. For example, to roll the current date up by one day, call + * roll(Calendar::DATE, +1, status). When rolling on the month or + * Calendar::MONTH field, other fields like date might conflict and, need to be + * changed. For instance, rolling the month up on the date 01/31/96 will result in + * 02/29/96. Rolling by a positive value always means rolling forward in time; + * e.g., rolling the year by +1 on "100 BC" will result in "99 BC", for Gregorian + * calendar. When rolling on the hour-in-day or Calendar::HOUR_OF_DAY field, it will + * roll the hour value in the range between 0 and 23, which is zero-based. + * <P> + * The only difference between roll() and add() is that roll() does not change + * the value of more significant fields when it reaches the minimum or maximum + * of its range, whereas add() does. + * + * @param field The time field. + * @param amount Indicates amount to roll. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @stable ICU 2.6. + */ + virtual void roll(UCalendarDateFields field, int32_t amount, UErrorCode& status); + + /** + * Return the difference between the given time and the time this + * calendar object is set to. If this calendar is set + * <em>before</em> the given time, the returned value will be + * positive. If this calendar is set <em>after</em> the given + * time, the returned value will be negative. The + * <code>field</code> parameter specifies the units of the return + * value. For example, if <code>fieldDifference(when, + * Calendar::MONTH)</code> returns 3, then this calendar is set to + * 3 months before <code>when</code>, and possibly some addition + * time less than one month. + * + * <p>As a side effect of this call, this calendar is advanced + * toward <code>when</code> by the given amount. That is, calling + * this method has the side effect of calling <code>add(field, + * n)</code>, where <code>n</code> is the return value. + * + * <p>Usage: To use this method, call it first with the largest + * field of interest, then with progressively smaller fields. For + * example: + * + * <pre> + * int y = cal->fieldDifference(when, Calendar::YEAR, err); + * int m = cal->fieldDifference(when, Calendar::MONTH, err); + * int d = cal->fieldDifference(when, Calendar::DATE, err);</pre> + * + * computes the difference between <code>cal</code> and + * <code>when</code> in years, months, and days. + * + * <p>Note: <code>fieldDifference()</code> is + * <em>asymmetrical</em>. That is, in the following code: + * + * <pre> + * cal->setTime(date1, err); + * int m1 = cal->fieldDifference(date2, Calendar::MONTH, err); + * int d1 = cal->fieldDifference(date2, Calendar::DATE, err); + * cal->setTime(date2, err); + * int m2 = cal->fieldDifference(date1, Calendar::MONTH, err); + * int d2 = cal->fieldDifference(date1, Calendar::DATE, err);</pre> + * + * one might expect that <code>m1 == -m2 && d1 == -d2</code>. + * However, this is not generally the case, because of + * irregularities in the underlying calendar system (e.g., the + * Gregorian calendar has a varying number of days per month). + * + * @param when the date to compare this calendar's time to + * @param field the field in which to compute the result + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @return the difference, either positive or negative, between + * this calendar's time and <code>when</code>, in terms of + * <code>field</code>. + * @deprecated ICU 2.6. Use fieldDifference(UDate when, UCalendarDateFields field, UErrorCode& status). + */ + virtual int32_t fieldDifference(UDate when, EDateFields field, UErrorCode& status); + + /** + * Return the difference between the given time and the time this + * calendar object is set to. If this calendar is set + * <em>before</em> the given time, the returned value will be + * positive. If this calendar is set <em>after</em> the given + * time, the returned value will be negative. The + * <code>field</code> parameter specifies the units of the return + * value. For example, if <code>fieldDifference(when, + * Calendar::MONTH)</code> returns 3, then this calendar is set to + * 3 months before <code>when</code>, and possibly some addition + * time less than one month. + * + * <p>As a side effect of this call, this calendar is advanced + * toward <code>when</code> by the given amount. That is, calling + * this method has the side effect of calling <code>add(field, + * n)</code>, where <code>n</code> is the return value. + * + * <p>Usage: To use this method, call it first with the largest + * field of interest, then with progressively smaller fields. For + * example: + * + * <pre> + * int y = cal->fieldDifference(when, Calendar::YEAR, err); + * int m = cal->fieldDifference(when, Calendar::MONTH, err); + * int d = cal->fieldDifference(when, Calendar::DATE, err);</pre> + * + * computes the difference between <code>cal</code> and + * <code>when</code> in years, months, and days. + * + * <p>Note: <code>fieldDifference()</code> is + * <em>asymmetrical</em>. That is, in the following code: + * + * <pre> + * cal->setTime(date1, err); + * int m1 = cal->fieldDifference(date2, Calendar::MONTH, err); + * int d1 = cal->fieldDifference(date2, Calendar::DATE, err); + * cal->setTime(date2, err); + * int m2 = cal->fieldDifference(date1, Calendar::MONTH, err); + * int d2 = cal->fieldDifference(date1, Calendar::DATE, err);</pre> + * + * one might expect that <code>m1 == -m2 && d1 == -d2</code>. + * However, this is not generally the case, because of + * irregularities in the underlying calendar system (e.g., the + * Gregorian calendar has a varying number of days per month). + * + * @param when the date to compare this calendar's time to + * @param field the field in which to compute the result + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @return the difference, either positive or negative, between + * this calendar's time and <code>when</code>, in terms of + * <code>field</code>. + * @stable ICU 2.6. + */ + virtual int32_t fieldDifference(UDate when, UCalendarDateFields field, UErrorCode& status); + + /** + * Sets the calendar's time zone to be the one passed in. The Calendar takes ownership + * of the TimeZone; the caller is no longer responsible for deleting it. If the + * given time zone is NULL, this function has no effect. + * + * @param value The given time zone. + * @stable ICU 2.0 + */ + void adoptTimeZone(TimeZone* value); + + /** + * Sets the calendar's time zone to be the same as the one passed in. The TimeZone + * passed in is _not_ adopted; the client is still responsible for deleting it. + * + * @param zone The given time zone. + * @stable ICU 2.0 + */ + void setTimeZone(const TimeZone& zone); + + /** + * Returns a reference to the time zone owned by this calendar. The returned reference + * is only valid until clients make another call to adoptTimeZone or setTimeZone, + * or this Calendar is destroyed. + * + * @return The time zone object associated with this calendar. + * @stable ICU 2.0 + */ + const TimeZone& getTimeZone(void) const; + + /** + * Returns the time zone owned by this calendar. The caller owns the returned object + * and must delete it when done. After this call, the new time zone associated + * with this Calendar is the default TimeZone as returned by TimeZone::createDefault(). + * + * @return The time zone object which was associated with this calendar. + * @stable ICU 2.0 + */ + TimeZone* orphanTimeZone(void); + + /** + * Queries if the current date for this Calendar is in Daylight Savings Time. + * + * @param status Fill-in parameter which receives the status of this operation. + * @return True if the current date for this Calendar is in Daylight Savings Time, + * false, otherwise. + * @stable ICU 2.0 + */ + virtual UBool inDaylightTime(UErrorCode& status) const = 0; + + /** + * Specifies whether or not date/time interpretation is to be lenient. With lenient + * interpretation, a date such as "February 942, 1996" will be treated as being + * equivalent to the 941st day after February 1, 1996. With strict interpretation, + * such dates will cause an error when computing time from the time field values + * representing the dates. + * + * @param lenient True specifies date/time interpretation to be lenient. + * + * @see DateFormat#setLenient + * @stable ICU 2.0 + */ + void setLenient(UBool lenient); + + /** + * Tells whether date/time interpretation is to be lenient. + * + * @return True tells that date/time interpretation is to be lenient. + * @stable ICU 2.0 + */ + UBool isLenient(void) const; + + /** + * Sets what the first day of the week is; e.g., Sunday in US, Monday in France. + * + * @param value The given first day of the week. + * @deprecated ICU 2.6. Use setFirstDayOfWeek(UCalendarDaysOfWeek value) instead. + */ + void setFirstDayOfWeek(EDaysOfWeek value); + + /** + * Sets what the first day of the week is; e.g., Sunday in US, Monday in France. + * + * @param value The given first day of the week. + * @stable ICU 2.6. + */ + void setFirstDayOfWeek(UCalendarDaysOfWeek value); + + /** + * Gets what the first day of the week is; e.g., Sunday in US, Monday in France. + * + * @return The first day of the week. + * @deprecated ICU 2.6 use the overload with error code + */ + EDaysOfWeek getFirstDayOfWeek(void) const; + + /** + * Gets what the first day of the week is; e.g., Sunday in US, Monday in France. + * + * @param status error code + * @return The first day of the week. + * @stable ICU 2.6 + */ + UCalendarDaysOfWeek getFirstDayOfWeek(UErrorCode &status) const; + + /** + * Sets what the minimal days required in the first week of the year are; For + * example, if the first week is defined as one that contains the first day of the + * first month of a year, call the method with value 1. If it must be a full week, + * use value 7. + * + * @param value The given minimal days required in the first week of the year. + * @stable ICU 2.0 + */ + void setMinimalDaysInFirstWeek(uint8_t value); + + /** + * Gets what the minimal days required in the first week of the year are; e.g., if + * the first week is defined as one that contains the first day of the first month + * of a year, getMinimalDaysInFirstWeek returns 1. If the minimal days required must + * be a full week, getMinimalDaysInFirstWeek returns 7. + * + * @return The minimal days required in the first week of the year. + * @stable ICU 2.0 + */ + uint8_t getMinimalDaysInFirstWeek(void) const; + + /** + * Gets the minimum value for the given time field. e.g., for Gregorian + * DAY_OF_MONTH, 1. + * + * @param field The given time field. + * @return The minimum value for the given time field. + * @deprecated ICU 2.6. Use getMinimum(UCalendarDateFields field) instead. + */ + virtual int32_t getMinimum(EDateFields field) const; + + /** + * Gets the minimum value for the given time field. e.g., for Gregorian + * DAY_OF_MONTH, 1. + * + * @param field The given time field. + * @return The minimum value for the given time field. + * @stable ICU 2.6. + */ + virtual int32_t getMinimum(UCalendarDateFields field) const; + + /** + * Gets the maximum value for the given time field. e.g. for Gregorian DAY_OF_MONTH, + * 31. + * + * @param field The given time field. + * @return The maximum value for the given time field. + * @deprecated ICU 2.6. Use getMaximum(UCalendarDateFields field) instead. + */ + virtual int32_t getMaximum(EDateFields field) const; + + /** + * Gets the maximum value for the given time field. e.g. for Gregorian DAY_OF_MONTH, + * 31. + * + * @param field The given time field. + * @return The maximum value for the given time field. + * @stable ICU 2.6. + */ + virtual int32_t getMaximum(UCalendarDateFields field) const; + + /** + * Gets the highest minimum value for the given field if varies. Otherwise same as + * getMinimum(). For Gregorian, no difference. + * + * @param field The given time field. + * @return The highest minimum value for the given time field. + * @deprecated ICU 2.6. Use getGreatestMinimum(UCalendarDateFields field) instead. + */ + virtual int32_t getGreatestMinimum(EDateFields field) const; + + /** + * Gets the highest minimum value for the given field if varies. Otherwise same as + * getMinimum(). For Gregorian, no difference. + * + * @param field The given time field. + * @return The highest minimum value for the given time field. + * @stable ICU 2.6. + */ + virtual int32_t getGreatestMinimum(UCalendarDateFields field) const; + + /** + * Gets the lowest maximum value for the given field if varies. Otherwise same as + * getMaximum(). e.g., for Gregorian DAY_OF_MONTH, 28. + * + * @param field The given time field. + * @return The lowest maximum value for the given time field. + * @deprecated ICU 2.6. Use getLeastMaximum(UCalendarDateFields field) instead. + */ + virtual int32_t getLeastMaximum(EDateFields field) const; + + /** + * Gets the lowest maximum value for the given field if varies. Otherwise same as + * getMaximum(). e.g., for Gregorian DAY_OF_MONTH, 28. + * + * @param field The given time field. + * @return The lowest maximum value for the given time field. + * @stable ICU 2.6. + */ + virtual int32_t getLeastMaximum(UCalendarDateFields field) const; + + /** + * Return the minimum value that this field could have, given the current date. + * For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum(). + * + * The version of this function on Calendar uses an iterative algorithm to determine the + * actual minimum value for the field. There is almost always a more efficient way to + * accomplish this (in most cases, you can simply return getMinimum()). GregorianCalendar + * overrides this function with a more efficient implementation. + * + * @param field the field to determine the minimum of + * @param status Fill-in parameter which receives the status of this operation. + * @return the minimum of the given field for the current date of this Calendar + * @deprecated ICU 2.6. Use getActualMinimum(UCalendarDateFields field, UErrorCode& status) instead. + */ + int32_t getActualMinimum(EDateFields field, UErrorCode& status) const; + + /** + * Return the minimum value that this field could have, given the current date. + * For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum(). + * + * The version of this function on Calendar uses an iterative algorithm to determine the + * actual minimum value for the field. There is almost always a more efficient way to + * accomplish this (in most cases, you can simply return getMinimum()). GregorianCalendar + * overrides this function with a more efficient implementation. + * + * @param field the field to determine the minimum of + * @param status Fill-in parameter which receives the status of this operation. + * @return the minimum of the given field for the current date of this Calendar + * @stable ICU 2.6. + */ + int32_t getActualMinimum(UCalendarDateFields field, UErrorCode& status) const; + + /** + * Return the maximum value that this field could have, given the current date. + * For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual + * maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar, + * for some years the actual maximum for MONTH is 12, and for others 13. + * + * The version of this function on Calendar uses an iterative algorithm to determine the + * actual maximum value for the field. There is almost always a more efficient way to + * accomplish this (in most cases, you can simply return getMaximum()). GregorianCalendar + * overrides this function with a more efficient implementation. + * + * @param field the field to determine the maximum of + * @param status Fill-in parameter which receives the status of this operation. + * @return the maximum of the given field for the current date of this Calendar + * @deprecated ICU 2.6. Use getActualMaximum(UCalendarDateFields field, UErrorCode& status) instead. + */ + int32_t getActualMaximum(EDateFields field, UErrorCode& status) const; + + /** + * Return the maximum value that this field could have, given the current date. + * For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual + * maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar, + * for some years the actual maximum for MONTH is 12, and for others 13. + * + * The version of this function on Calendar uses an iterative algorithm to determine the + * actual maximum value for the field. There is almost always a more efficient way to + * accomplish this (in most cases, you can simply return getMaximum()). GregorianCalendar + * overrides this function with a more efficient implementation. + * + * @param field the field to determine the maximum of + * @param status Fill-in parameter which receives the status of this operation. + * @return the maximum of the given field for the current date of this Calendar + * @stable ICU 2.6. + */ + int32_t getActualMaximum(UCalendarDateFields field, UErrorCode& status) const; + + /** + * Gets the value for a given time field. Recalculate the current time field values + * if the time value has been changed by a call to setTime(). Return zero for unset + * fields if any fields have been explicitly set by a call to set(). To force a + * recomputation of all fields regardless of the previous state, call complete(). + * This method is semantically const, but may alter the object in memory. + * + * @param field The given time field. + * @param status Fill-in parameter which receives the status of the operation. + * @return The value for the given time field, or zero if the field is unset, + * and set() has been called for any other field. + * @deprecated ICU 2.6. Use get(UCalendarDateFields field, UErrorCode& status) instead. + */ + int32_t get(EDateFields field, UErrorCode& status) const; + + /** + * Gets the value for a given time field. Recalculate the current time field values + * if the time value has been changed by a call to setTime(). Return zero for unset + * fields if any fields have been explicitly set by a call to set(). To force a + * recomputation of all fields regardless of the previous state, call complete(). + * This method is semantically const, but may alter the object in memory. + * + * @param field The given time field. + * @param status Fill-in parameter which receives the status of the operation. + * @return The value for the given time field, or zero if the field is unset, + * and set() has been called for any other field. + * @stable ICU 2.6. + */ + int32_t get(UCalendarDateFields field, UErrorCode& status) const; + + /** + * Determines if the given time field has a value set. This can affect in the + * resolving of time in Calendar. Unset fields have a value of zero, by definition. + * + * @param field The given time field. + * @return True if the given time field has a value set; false otherwise. + * @deprecated ICU 2.6. Use isSet(UCalendarDateFields field) instead. + */ + UBool isSet(EDateFields field) const; + + /** + * Determines if the given time field has a value set. This can affect in the + * resolving of time in Calendar. Unset fields have a value of zero, by definition. + * + * @param field The given time field. + * @return True if the given time field has a value set; false otherwise. + * @stable ICU 2.6. + */ + UBool isSet(UCalendarDateFields field) const; + + /** + * Sets the given time field with the given value. + * + * @param field The given time field. + * @param value The value to be set for the given time field. + * @deprecated ICU 2.6. Use set(UCalendarDateFields field, int32_t value) instead. + */ + void set(EDateFields field, int32_t value); + + /** + * Sets the given time field with the given value. + * + * @param field The given time field. + * @param value The value to be set for the given time field. + * @stable ICU 2.6. + */ + void set(UCalendarDateFields field, int32_t value); + + /** + * Sets the values for the fields YEAR, MONTH, and DATE. Other field values are + * retained; call clear() first if this is not desired. + * + * @param year The value used to set the YEAR time field. + * @param month The value used to set the MONTH time field. Month value is 0-based. + * e.g., 0 for January. + * @param date The value used to set the DATE time field. + * @stable ICU 2.0 + */ + void set(int32_t year, int32_t month, int32_t date); + + /** + * Sets the values for the fields YEAR, MONTH, DATE, HOUR_OF_DAY, and MINUTE. Other + * field values are retained; call clear() first if this is not desired. + * + * @param year The value used to set the YEAR time field. + * @param month The value used to set the MONTH time field. Month value is + * 0-based. E.g., 0 for January. + * @param date The value used to set the DATE time field. + * @param hour The value used to set the HOUR_OF_DAY time field. + * @param minute The value used to set the MINUTE time field. + * @stable ICU 2.0 + */ + void set(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute); + + /** + * Sets the values for the fields YEAR, MONTH, DATE, HOUR_OF_DAY, MINUTE, and SECOND. + * Other field values are retained; call clear() first if this is not desired. + * + * @param year The value used to set the YEAR time field. + * @param month The value used to set the MONTH time field. Month value is + * 0-based. E.g., 0 for January. + * @param date The value used to set the DATE time field. + * @param hour The value used to set the HOUR_OF_DAY time field. + * @param minute The value used to set the MINUTE time field. + * @param second The value used to set the SECOND time field. + * @stable ICU 2.0 + */ + void set(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute, int32_t second); + + /** + * Clears the values of all the time fields, making them both unset and assigning + * them a value of zero. The field values will be determined during the next + * resolving of time into time fields. + * @stable ICU 2.0 + */ + void clear(void); + + /** + * Clears the value in the given time field, both making it unset and assigning it a + * value of zero. This field value will be determined during the next resolving of + * time into time fields. + * + * @param field The time field to be cleared. + * @deprecated ICU 2.6. Use clear(UCalendarDateFields field) instead. + */ + void clear(EDateFields field); + + /** + * Clears the value in the given time field, both making it unset and assigning it a + * value of zero. This field value will be determined during the next resolving of + * time into time fields. + * + * @param field The time field to be cleared. + * @stable ICU 2.6. + */ + void clear(UCalendarDateFields field); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual method. This method is to + * implement a simple version of RTTI, since not all C++ compilers support genuine + * RTTI. Polymorphic operator==() and clone() methods call this method. + * <P> + * Concrete subclasses of Calendar must implement getDynamicClassID() and also a + * static method and data member: + * + * static UClassID getStaticClassID() { return (UClassID)&fgClassID; } + * static char fgClassID; + * + * @return The class ID for this object. All objects of a given class have the + * same class ID. Objects of other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Returns the resource key string used for this calendar type. + * For example, prepending "Eras_" to this string could return "Eras_japanese" + * or "Eras_gregorian". + * + * @returns static string, for example, "gregorian" or "japanese" + * @internal + */ + virtual const char * getType() const = 0; + +protected: + + /** + * Constructs a Calendar with the default time zone as returned by + * TimeZone::createInstance(), and the default locale. + * + * @param success Indicates the status of Calendar object construction. Returns + * U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + Calendar(UErrorCode& success); + + /** + * Copy constructor + * + * @param source Calendar object to be copied from + * @stable ICU 2.0 + */ + Calendar(const Calendar& source); + + /** + * Default assignment operator + * + * @param right Calendar object to be copied + * @stable ICU 2.0 + */ + Calendar& operator=(const Calendar& right); + + /** + * Constructs a Calendar with the given time zone and locale. Clients are no longer + * responsible for deleting the given time zone object after it's adopted. + * + * @param zone The given time zone. + * @param aLocale The given locale. + * @param success Indicates the status of Calendar object construction. Returns + * U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + Calendar(TimeZone* zone, const Locale& aLocale, UErrorCode& success); + + /** + * Constructs a Calendar with the given time zone and locale. + * + * @param zone The given time zone. + * @param aLocale The given locale. + * @param success Indicates the status of Calendar object construction. Returns + * U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + Calendar(const TimeZone& zone, const Locale& aLocale, UErrorCode& success); + + /** + * Converts Calendar's time field values to GMT as milliseconds. + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.0 + */ + virtual void computeTime(UErrorCode& status); + + /** + * Converts GMT as milliseconds to time field values. This allows you to sync up the + * time field values with a new time that is set for the calendar. This method + * does NOT recompute the time first; to recompute the time, then the fields, use + * the method complete(). + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.0 + */ + virtual void computeFields(UErrorCode& status); + + /** + * Gets this Calendar's current time as a long. + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @return the current time as UTC milliseconds from the epoch. + * @stable ICU 2.0 + */ + double getTimeInMillis(UErrorCode& status) const; + + /** + * Sets this Calendar's current time from the given long value. + * @param millis the new time in UTC milliseconds from the epoch. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.0 + */ + void setTimeInMillis( double millis, UErrorCode& status ); + + /** + * Recomputes the current time from currently set fields, and then fills in any + * unset fields in the time field list. + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + * @stable ICU 2.0 + */ + void complete(UErrorCode& status); + + /** + * Gets the value for a given time field. Subclasses can use this function to get + * field values without forcing recomputation of time. + * + * @param field The given time field. + * @return The value for the given time field. + * @deprecated ICU 2.6. Use internalGet(UCalendarDateFields field) instead. + */ + inline int32_t internalGet(EDateFields field) const {return fFields[field];} + + /** + * Gets the value for a given time field. Subclasses can use this function to get + * field values without forcing recomputation of time. If the field's stamp is UNSET, + * the defaultValue is used. + * + * @param field The given time field. + * @param defaultValue a default value used if the field is unset. + * @return The value for the given time field. + * @internal + */ + inline int32_t internalGet(UCalendarDateFields field, int32_t defaultValue) const {return fStamp[field]>kUnset ? fFields[field] : defaultValue;} + + /** + * Gets the value for a given time field. Subclasses can use this function to get + * field values without forcing recomputation of time. + * + * @param field The given time field. + * @return The value for the given time field. + * @internal + */ + inline int32_t internalGet(UCalendarDateFields field) const {return fFields[field];} + + /** + * Sets the value for a given time field. This is a fast internal method for + * subclasses. It does not affect the areFieldsInSync, isTimeSet, or areAllFieldsSet + * flags. + * + * @param field The given time field. + * @param value The value for the given time field. + * @deprecated ICU 2.6. Use internalSet(UCalendarDateFields field, int32_t value) instead. + */ + void internalSet(EDateFields field, int32_t value); + + /** + * Sets the value for a given time field. This is a fast internal method for + * subclasses. It does not affect the areFieldsInSync, isTimeSet, or areAllFieldsSet + * flags. + * + * @param field The given time field. + * @param value The value for the given time field. + * @stable ICU 2.6. + */ + inline void internalSet(UCalendarDateFields field, int32_t value); + + /** + * Prepare this calendar for computing the actual minimum or maximum. + * This method modifies this calendar's fields; it is called on a + * temporary calendar. + * @internal + */ + virtual void prepareGetActual(UCalendarDateFields field, UBool isMinimum, UErrorCode &status); + + /** + * Limit enums. Not in sync with UCalendarLimitType (refers to internal fields). + * @internal + */ + enum ELimitType { + UCAL_LIMIT_MINIMUM = 0, + UCAL_LIMIT_GREATEST_MINIMUM, + UCAL_LIMIT_LEAST_MAXIMUM, + UCAL_LIMIT_MAXIMUM, + UCAL_LIMIT_COUNT + }; + + /** + * Subclass API for defining limits of different types. + * Subclasses must implement this method to return limits for the + * following fields: + * + * <pre>UCAL_ERA + * UCAL_YEAR + * UCAL_MONTH + * UCAL_WEEK_OF_YEAR + * UCAL_WEEK_OF_MONTH + * UCAL_DATE (DAY_OF_MONTH on Java) + * UCAL_DAY_OF_YEAR + * UCAL_DAY_OF_WEEK_IN_MONTH + * UCAL_YEAR_WOY + * UCAL_EXTENDED_YEAR</pre> + * + * @param field one of the above field numbers + * @param limitType one of <code>MINIMUM</code>, <code>GREATEST_MINIMUM</code>, + * <code>LEAST_MAXIMUM</code>, or <code>MAXIMUM</code> + * @internal + */ + virtual int32_t handleGetLimit(UCalendarDateFields field, ELimitType limitType) const = 0; + + /** + * Return a limit for a field. + * @param field the field, from <code>0..UCAL_MAX_FIELD</code> + * @param limitType the type specifier for the limit + * @see #ELimitType + * @internal + */ + virtual int32_t getLimit(UCalendarDateFields field, ELimitType limitType) const; + + + /** + * Return the Julian day number of day before the first day of the + * given month in the given extended year. Subclasses should override + * this method to implement their calendar system. + * @param eyear the extended year + * @param month the zero-based month, or 0 if useMonth is false + * @param useMonth if false, compute the day before the first day of + * the given year, otherwise, compute the day before the first day of + * the given month + * @return the Julian day number of the day before the first + * day of the given month and year + * @internal + */ + virtual int32_t handleComputeMonthStart(int32_t eyear, int32_t month, + UBool useMonth) const = 0; + + /** + * Return the number of days in the given month of the given extended + * year of this calendar system. Subclasses should override this + * method if they can provide a more correct or more efficient + * implementation than the default implementation in Calendar. + * @internal + */ + virtual int32_t handleGetMonthLength(int32_t extendedYear, int32_t month) const ; + + /** + * Return the number of days in the given extended year of this + * calendar system. Subclasses should override this method if they can + * provide a more correct or more efficient implementation than the + * default implementation in Calendar. + * @stable ICU 2.0 + */ + virtual int32_t handleGetYearLength(int32_t eyear) const; + + + /** + * Return the extended year defined by the current fields. This will + * use the UCAL_EXTENDED_YEAR field or the UCAL_YEAR and supra-year fields (such + * as UCAL_ERA) specific to the calendar system, depending on which set of + * fields is newer. + * @return the extended year + * @internal + */ + virtual int32_t handleGetExtendedYear() = 0; + + /** + * Subclasses may override this. This method calls + * handleGetMonthLength() to obtain the calendar-specific month + * length. + * @param bestField which field to use to calculate the date + * @return julian day specified by calendar fields. + * @internal + */ + virtual int32_t handleComputeJulianDay(UCalendarDateFields bestField); + + /** + * Subclasses must override this to convert from week fields + * (YEAR_WOY and WEEK_OF_YEAR) to an extended year in the case + * where YEAR, EXTENDED_YEAR are not set. + * The Calendar implementation assumes yearWoy is in extended gregorian form + * @internal + * @return the extended year, UCAL_EXTENDED_YEAR + */ + virtual int32_t handleGetExtendedYearFromWeekFields(int32_t yearWoy, int32_t woy); + + /** + * Compute the Julian day from fields. Will determine whether to use + * the JULIAN_DAY field directly, or other fields. + * @return the julian day + * @internal + */ + int32_t computeJulianDay(); + + /** + * Compute the milliseconds in the day from the fields. This is a + * value from 0 to 23:59:59.999 inclusive, unless fields are out of + * range, in which case it can be an arbitrary value. This value + * reflects local zone wall time. + * @internal + */ + int32_t computeMillisInDay(); + + /** + * This method can assume EXTENDED_YEAR has been set. + * @param millis milliseconds of the date fields + * @param millisInDay milliseconds of the time fields; may be out + * or range. + * @param ec Output param set to failure code on function return + * when this function fails. + * @internal + */ + int32_t computeZoneOffset(double millis, int32_t millisInDay, UErrorCode &ec); + + + /** + * Determine the best stamp in a range. + * @param start first enum to look at + * @param end last enum to look at + * @param bestSoFar stamp prior to function call + * @return the stamp value of the best stamp + * @internal + */ + int32_t newestStamp(UCalendarDateFields start, UCalendarDateFields end, int32_t bestSoFar) const; + + /** + * Values for field resolution tables + * @see #resolveFields + * @internal + */ + enum { + /** Marker for end of resolve set (row or group). */ + kResolveSTOP = -1, + /** Value to be bitwised "ORed" against resolve table field values for remapping. Example: (UCAL_DATE | kResolveRemap) in 1st column will cause 'UCAL_DATE' to be returned, but will not examine the value of UCAL_DATE. */ + kResolveRemap = 32 + }; + + /** + * Precedence table for Dates + * @see #resolveFields + * @internal + */ + static const UFieldResolutionTable kDatePrecedence[]; + + /** + * Precedence table for Year + * @see #resolveFields + * @internal + */ + static const UFieldResolutionTable kYearPrecedence[]; + + /** + * Precedence table for Day of Week + * @see #resolveFields + * @internal + */ + static const UFieldResolutionTable kDOWPrecedence[]; + + /** + * Given a precedence table, return the newest field combination in + * the table, or UCAL_FIELD_COUNT if none is found. + * + * <p>The precedence table is a 3-dimensional array of integers. It + * may be thought of as an array of groups. Each group is an array of + * lines. Each line is an array of field numbers. Within a line, if + * all fields are set, then the time stamp of the line is taken to be + * the stamp of the most recently set field. If any field of a line is + * unset, then the line fails to match. Within a group, the line with + * the newest time stamp is selected. The first field of the line is + * returned to indicate which line matched. + * + * <p>In some cases, it may be desirable to map a line to field that + * whose stamp is NOT examined. For example, if the best field is + * DAY_OF_WEEK then the DAY_OF_WEEK_IN_MONTH algorithm may be used. In + * order to do this, insert the value <code>kResolveRemap | F</code> at + * the start of the line, where <code>F</code> is the desired return + * field value. This field will NOT be examined; it only determines + * the return value if the other fields in the line are the newest. + * + * <p>If all lines of a group contain at least one unset field, then no + * line will match, and the group as a whole will fail to match. In + * that case, the next group will be processed. If all groups fail to + * match, then UCAL_FIELD_COUNT is returned. + * @internal + */ + UCalendarDateFields resolveFields(const UFieldResolutionTable *precedenceTable); + + + /** + * @internal + */ + virtual const UFieldResolutionTable* getFieldResolutionTable() const; + + /** + * Return the field that is newer, either defaultField, or + * alternateField. If neither is newer or neither is set, return defaultField. + * @internal + */ + UCalendarDateFields newerField(UCalendarDateFields defaultField, UCalendarDateFields alternateField) const; + + +private: + /** + * Helper function for calculating limits by trial and error + * @param field The field being investigated + * @param startValue starting (least max) value of field + * @param endValue ending (greatest max) value of field + * @param status return type + * @internal + */ + int32_t getActualHelper(UCalendarDateFields field, int32_t startValue, int32_t endValue, UErrorCode &status) const; + + +protected: + /** + * The flag which indicates if the current time is set in the calendar. + * @stable ICU 2.0 + */ + UBool fIsTimeSet; + + /** + * True if the fields are in sync with the currently set time of this Calendar. + * If false, then the next attempt to get the value of a field will + * force a recomputation of all fields from the current value of the time + * field. + * <P> + * This should really be named areFieldsInSync, but the old name is retained + * for backward compatibility. + * @stable ICU 2.0 + */ + UBool fAreFieldsSet; + + /** + * True if all of the fields have been set. This is initially false, and set to + * true by computeFields(). + * @stable ICU 2.0 + */ + UBool fAreAllFieldsSet; + + /** + * True if all fields have been virtually set, but have not yet been + * computed. This occurs only in setTimeInMillis(). A calendar set + * to this state will compute all fields from the time if it becomes + * necessary, but otherwise will delay such computation. + * @stable ICU 3.0 + */ + UBool fAreFieldsVirtuallySet; + + /** + * Get the current time without recomputing. + * + * @return the current time without recomputing. + * @stable ICU 2.0 + */ + UDate internalGetTime(void) const { return fTime; } + + /** + * Set the current time without affecting flags or fields. + * + * @param time The time to be set + * @return the current time without recomputing. + * @stable ICU 2.0 + */ + void internalSetTime(UDate time) { fTime = time; } + + /** + * The time fields containing values into which the millis is computed. + * @stable ICU 2.0 + */ + int32_t fFields[UCAL_FIELD_COUNT]; + + /** + * The flags which tell if a specified time field for the calendar is set. + * @deprecated ICU 2.8 use (fStamp[n]!=kUnset) + */ + UBool fIsSet[UCAL_FIELD_COUNT]; + + /** Special values of stamp[] + * @stable ICU 2.0 + */ + enum { + kUnset = 0, + kInternallySet, + kMinimumUserStamp + }; + + /** + * Pseudo-time-stamps which specify when each field was set. There + * are two special values, UNSET and INTERNALLY_SET. Values from + * MINIMUM_USER_SET to Integer.MAX_VALUE are legal user set values. + * @stable ICU 2.0 + */ + int32_t fStamp[UCAL_FIELD_COUNT]; + + /** + * Subclasses may override this method to compute several fields + * specific to each calendar system. These are: + * + * <ul><li>ERA + * <li>YEAR + * <li>MONTH + * <li>DAY_OF_MONTH + * <li>DAY_OF_YEAR + * <li>EXTENDED_YEAR</ul> + * + * Subclasses can refer to the DAY_OF_WEEK and DOW_LOCAL fields, which + * will be set when this method is called. Subclasses can also call + * the getGregorianXxx() methods to obtain Gregorian calendar + * equivalents for the given Julian day. + * + * <p>In addition, subclasses should compute any subclass-specific + * fields, that is, fields from BASE_FIELD_COUNT to + * getFieldCount() - 1. + * + * <p>The default implementation in <code>Calendar</code> implements + * a pure proleptic Gregorian calendar. + * @internal + */ + virtual void handleComputeFields(int32_t julianDay, UErrorCode &status); + + /** + * Return the extended year on the Gregorian calendar as computed by + * <code>computeGregorianFields()</code>. + * @internal + */ + int32_t getGregorianYear() const { + return fGregorianYear; + } + + /** + * Return the month (0-based) on the Gregorian calendar as computed by + * <code>computeGregorianFields()</code>. + * @internal + */ + int32_t getGregorianMonth() const { + return fGregorianMonth; + } + + /** + * Return the day of year (1-based) on the Gregorian calendar as + * computed by <code>computeGregorianFields()</code>. + * @internal + */ + int32_t getGregorianDayOfYear() const { + return fGregorianDayOfYear; + } + + /** + * Return the day of month (1-based) on the Gregorian calendar as + * computed by <code>computeGregorianFields()</code>. + * @internal + */ + int32_t getGregorianDayOfMonth() const { + return fGregorianDayOfMonth; + } + + /** + * Called by computeJulianDay. Returns the default month (0-based) for the year, + * taking year and era into account. Defaults to 0 for Gregorian, which doesn't care. + * @internal + * @internal + */ + virtual int32_t getDefaultMonthInYear() ; + + + /** + * Called by computeJulianDay. Returns the default day (1-based) for the month, + * taking currently-set year and era into account. Defaults to 1 for Gregorian. + * @internal + */ + virtual int32_t getDefaultDayInMonth(int32_t /*month*/); + + //------------------------------------------------------------------------- + // Protected utility methods for use by subclasses. These are very handy + // for implementing add, roll, and computeFields. + //------------------------------------------------------------------------- + + /** + * Adjust the specified field so that it is within + * the allowable range for the date to which this calendar is set. + * For example, in a Gregorian calendar pinning the {@link #UCalendarDateFields DAY_OF_MONTH} + * field for a calendar set to April 31 would cause it to be set + * to April 30. + * <p> + * <b>Subclassing:</b> + * <br> + * This utility method is intended for use by subclasses that need to implement + * their own overrides of {@link #roll roll} and {@link #add add}. + * <p> + * <b>Note:</b> + * <code>pinField</code> is implemented in terms of + * {@link #getActualMinimum getActualMinimum} + * and {@link #getActualMaximum getActualMaximum}. If either of those methods uses + * a slow, iterative algorithm for a particular field, it would be + * unwise to attempt to call <code>pinField</code> for that field. If you + * really do need to do so, you should override this method to do + * something more efficient for that field. + * <p> + * @param field The calendar field whose value should be pinned. + * @param status Output param set to failure code on function return + * when this function fails. + * + * @see #getActualMinimum + * @see #getActualMaximum + * @stable ICU 2.0 + */ + virtual void pinField(UCalendarDateFields field, UErrorCode& status); + + /** + * Return the week number of a day, within a period. This may be the week number in + * a year or the week number in a month. Usually this will be a value >= 1, but if + * some initial days of the period are excluded from week 1, because + * {@link #getMinimalDaysInFirstWeek getMinimalDaysInFirstWeek} is > 1, then + * the week number will be zero for those + * initial days. This method requires the day number and day of week for some + * known date in the period in order to determine the day of week + * on the desired day. + * <p> + * <b>Subclassing:</b> + * <br> + * This method is intended for use by subclasses in implementing their + * {@link #computeTime computeTime} and/or {@link #computeFields computeFields} methods. + * It is often useful in {@link #getActualMinimum getActualMinimum} and + * {@link #getActualMaximum getActualMaximum} as well. + * <p> + * This variant is handy for computing the week number of some other + * day of a period (often the first or last day of the period) when its day + * of the week is not known but the day number and day of week for some other + * day in the period (e.g. the current date) <em>is</em> known. + * <p> + * @param desiredDay The {@link #UCalendarDateFields DAY_OF_YEAR} or + * {@link #UCalendarDateFields DAY_OF_MONTH} whose week number is desired. + * Should be 1 for the first day of the period. + * + * @param dayOfPeriod The {@link #UCalendarDateFields DAY_OF_YEAR} + * or {@link #UCalendarDateFields DAY_OF_MONTH} for a day in the period whose + * {@link #UCalendarDateFields DAY_OF_WEEK} is specified by the + * <code>knownDayOfWeek</code> parameter. + * Should be 1 for first day of period. + * + * @param dayOfWeek The {@link #UCalendarDateFields DAY_OF_WEEK} for the day + * corresponding to the <code>knownDayOfPeriod</code> parameter. + * 1-based with 1=Sunday. + * + * @return The week number (one-based), or zero if the day falls before + * the first week because + * {@link #getMinimalDaysInFirstWeek getMinimalDaysInFirstWeek} + * is more than one. + * + * @stable ICU 2.8 + */ + int32_t weekNumber(int32_t desiredDay, int32_t dayOfPeriod, int32_t dayOfWeek); + + + /** + * Return the week number of a day, within a period. This may be the week number in + * a year, or the week number in a month. Usually this will be a value >= 1, but if + * some initial days of the period are excluded from week 1, because + * {@link #getMinimalDaysInFirstWeek getMinimalDaysInFirstWeek} is > 1, + * then the week number will be zero for those + * initial days. This method requires the day of week for the given date in order to + * determine the result. + * <p> + * <b>Subclassing:</b> + * <br> + * This method is intended for use by subclasses in implementing their + * {@link #computeTime computeTime} and/or {@link #computeFields computeFields} methods. + * It is often useful in {@link #getActualMinimum getActualMinimum} and + * {@link #getActualMaximum getActualMaximum} as well. + * <p> + * @param dayOfPeriod The {@link #UCalendarDateFields DAY_OF_YEAR} or + * {@link #UCalendarDateFields DAY_OF_MONTH} whose week number is desired. + * Should be 1 for the first day of the period. + * + * @param dayOfWeek The {@link #UCalendarDateFields DAY_OF_WEEK} for the day + * corresponding to the <code>dayOfPeriod</code> parameter. + * 1-based with 1=Sunday. + * + * @return The week number (one-based), or zero if the day falls before + * the first week because + * {@link #getMinimalDaysInFirstWeek getMinimalDaysInFirstWeek} + * is more than one. + * @internal + */ + inline int32_t weekNumber(int32_t dayOfPeriod, int32_t dayOfWeek); + + /** + * returns the local DOW, valid range 0..6 + * @internal + */ + int32_t getLocalDOW(); + +private: + + /** + * The next available value for fStamp[] + */ + int32_t fNextStamp;// = MINIMUM_USER_STAMP; + + /** + * The current time set for the calendar. + */ + UDate fTime; + + /** + * @see #setLenient + */ + UBool fLenient; + + /** + * Time zone affects the time calculation done by Calendar. Calendar subclasses use + * the time zone data to produce the local time. + */ + TimeZone* fZone; + + /** + * Both firstDayOfWeek and minimalDaysInFirstWeek are locale-dependent. They are + * used to figure out the week count for a specific date for a given locale. These + * must be set when a Calendar is constructed. For example, in US locale, + * firstDayOfWeek is SUNDAY; minimalDaysInFirstWeek is 1. They are used to figure + * out the week count for a specific date for a given locale. These must be set when + * a Calendar is constructed. + */ + UCalendarDaysOfWeek fFirstDayOfWeek; + uint8_t fMinimalDaysInFirstWeek; + + /** + * Sets firstDayOfWeek and minimalDaysInFirstWeek. Called at Calendar construction + * time. + * + * @param desiredLocale The given locale. + * @param type The calendar type identifier, e.g: gregorian, buddhist, etc. + * @param success Indicates the status of setting the week count data from + * the resource for the given locale. Returns U_ZERO_ERROR if + * constructed successfully. + */ + void setWeekCountData(const Locale& desiredLocale, const char *type, UErrorCode& success); + + /** + * Recompute the time and update the status fields isTimeSet + * and areFieldsSet. Callers should check isTimeSet and only + * call this method if isTimeSet is false. + * + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid or restricted by + * leniency, this will be set to an error status. + */ + void updateTime(UErrorCode& status); + + /** + * The Gregorian year, as computed by computeGregorianFields() and + * returned by getGregorianYear(). + * @see #computeGregorianFields + */ + int32_t fGregorianYear; + + /** + * The Gregorian month, as computed by computeGregorianFields() and + * returned by getGregorianMonth(). + * @see #computeGregorianFields + */ + int32_t fGregorianMonth; + + /** + * The Gregorian day of the year, as computed by + * computeGregorianFields() and returned by getGregorianDayOfYear(). + * @see #computeGregorianFields + */ + int32_t fGregorianDayOfYear; + + /** + * The Gregorian day of the month, as computed by + * computeGregorianFields() and returned by getGregorianDayOfMonth(). + * @see #computeGregorianFields + */ + int32_t fGregorianDayOfMonth; + + /* calculations */ + + /** + * Compute the Gregorian calendar year, month, and day of month from + * the given Julian day. These values are not stored in fields, but in + * member variables gregorianXxx. Also compute the DAY_OF_WEEK and + * DOW_LOCAL fields. + */ + void computeGregorianAndDOWFields(int32_t julianDay, UErrorCode &ec); + + /** + * Compute the Gregorian calendar year, month, and day of month from the + * Julian day. These values are not stored in fields, but in member + * variables gregorianXxx. They are used for time zone computations and by + * subclasses that are Gregorian derivatives. Subclasses may call this + * method to perform a Gregorian calendar millis->fields computation. + * To perform a Gregorian calendar fields->millis computation, call + * computeGregorianMonthStart(). + * @see #computeGregorianMonthStart + */ + void computeGregorianFields(int32_t julianDay, UErrorCode &ec); + + /** + * Compute the fields WEEK_OF_YEAR, YEAR_WOY, WEEK_OF_MONTH, + * DAY_OF_WEEK_IN_MONTH, and DOW_LOCAL from EXTENDED_YEAR, YEAR, + * DAY_OF_WEEK, and DAY_OF_YEAR. The latter fields are computed by the + * subclass based on the calendar system. + * + * <p>The YEAR_WOY field is computed simplistically. It is equal to YEAR + * most of the time, but at the year boundary it may be adjusted to YEAR-1 + * or YEAR+1 to reflect the overlap of a week into an adjacent year. In + * this case, a simple increment or decrement is performed on YEAR, even + * though this may yield an invalid YEAR value. For instance, if the YEAR + * is part of a calendar system with an N-year cycle field CYCLE, then + * incrementing the YEAR may involve incrementing CYCLE and setting YEAR + * back to 0 or 1. This is not handled by this code, and in fact cannot be + * simply handled without having subclasses define an entire parallel set of + * fields for fields larger than or equal to a year. This additional + * complexity is not warranted, since the intention of the YEAR_WOY field is + * to support ISO 8601 notation, so it will typically be used with a + * proleptic Gregorian calendar, which has no field larger than a year. + */ + void computeWeekFields(UErrorCode &ec); + + + /** + * Ensure that each field is within its valid range by calling {@link + * #validateField(int, int&)} on each field that has been set. This method + * should only be called if this calendar is not lenient. + * @see #isLenient + * @see #validateField(int, int&) + * @internal + */ + void validateFields(UErrorCode &status); + + /** + * Validate a single field of this calendar. Subclasses should + * override this method to validate any calendar-specific fields. + * Generic fields can be handled by + * <code>Calendar.validateField()</code>. + * @see #validateField(int, int, int, int&) + * @internal + */ + virtual void validateField(UCalendarDateFields field, UErrorCode &status); + + /** + * Validate a single field of this calendar given its minimum and + * maximum allowed value. If the field is out of range, + * <code>U_ILLEGAL_ARGUMENT_ERROR</code> will be set. Subclasses may + * use this method in their implementation of {@link + * #validateField(int, int&)}. + * @internal + */ + void validateField(UCalendarDateFields field, int32_t min, int32_t max, UErrorCode& status); + + protected: + /** + * Convert a quasi Julian date to the day of the week. The Julian date used here is + * not a true Julian date, since it is measured from midnight, not noon. Return + * value is one-based. + * + * @param julian The given Julian date number. + * @return Day number from 1..7 (SUN..SAT). + * @internal + */ + static uint8_t julianDayToDayOfWeek(double julian); + + private: + char validLocale[ULOC_FULLNAME_CAPACITY]; + char actualLocale[ULOC_FULLNAME_CAPACITY]; + + public: +#if !UCONFIG_NO_SERVICE + /** + * INTERNAL FOR 2.6 -- Registration. + */ + + /** + * Return a StringEnumeration over the locales available at the time of the call, + * including registered locales. + * @return a StringEnumeration over the locales available at the time of the call + * @internal + */ + static StringEnumeration* getAvailableLocales(void); + + /** + * Register a new Calendar factory. The factory will be adopted. + * INTERNAL in 2.6 + * @param toAdopt the factory instance to be adopted + * @param status the in/out status code, no special meanings are assigned + * @return a registry key that can be used to unregister this factory + * @internal + */ + static URegistryKey registerFactory(ICUServiceFactory* toAdopt, UErrorCode& status); + + /** + * Unregister a previously-registered CalendarFactory using the key returned from the + * register call. Key becomes invalid after a successful call and should not be used again. + * The CalendarFactory corresponding to the key will be deleted. + * INTERNAL in 2.6 + * @param key the registry key returned by a previous call to registerFactory + * @param status the in/out status code, no special meanings are assigned + * @return TRUE if the factory for the key was successfully unregistered + * @internal + */ + static UBool unregister(URegistryKey key, UErrorCode& status); + + /** + * Multiple Calendar Implementation + * @internal + */ + friend class CalendarFactory; + + /** + * Multiple Calendar Implementation + * @internal + */ + friend class CalendarService; + + /** + * Multiple Calendar Implementation + * @internal + */ + friend class DefaultCalendarFactory; +#endif /* !UCONFIG_NO_SERVICE */ + + /** + * @internal + * @return TRUE if this calendar has a default century (i.e. 03 -> 2003) + */ + virtual UBool haveDefaultCentury() const = 0; + + /** + * @internal + * @return the start of the default century, as a UDate + */ + virtual UDate defaultCenturyStart() const = 0; + /** + * @internal + * @return the beginning year of the default century, as a year + */ + virtual int32_t defaultCenturyStartYear() const = 0; + + /** Get the locale for this calendar object. You can choose between valid and actual locale. + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale + * @stable ICU 2.8 + */ + Locale getLocale(ULocDataLocaleType type, UErrorCode &status) const; + + /** Get the locale for this calendar object. You can choose between valid and actual locale. + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale + * @internal + */ + const char* getLocaleID(ULocDataLocaleType type, UErrorCode &status) const; + +}; + +// ------------------------------------- + +inline Calendar* +Calendar::createInstance(TimeZone* zone, UErrorCode& errorCode) +{ + // since the Locale isn't specified, use the default locale + return createInstance(zone, Locale::getDefault(), errorCode); +} + +// ------------------------------------- + +inline void +Calendar::roll(UCalendarDateFields field, UBool up, UErrorCode& status) +{ + roll(field, (int32_t)(up ? +1 : -1), status); +} + +inline void +Calendar::roll(EDateFields field, UBool up, UErrorCode& status) +{ + roll((UCalendarDateFields) field, up, status); +} + + +// ------------------------------------- + +/** + * Fast method for subclasses. The caller must maintain fUserSetDSTOffset and + * fUserSetZoneOffset, as well as the isSet[] array. + */ + +inline void +Calendar::internalSet(UCalendarDateFields field, int32_t value) +{ + fFields[field] = value; + fStamp[field] = kInternallySet; + fIsSet[field] = TRUE; // Remove later +} + +inline int32_t Calendar::weekNumber(int32_t dayOfPeriod, int32_t dayOfWeek) +{ + return weekNumber(dayOfPeriod, dayOfPeriod, dayOfWeek); +} + + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _CALENDAR diff --git a/Build/source/libs/icu-xetex/i18n/unicode/choicfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/choicfmt.h new file mode 100644 index 00000000000..409966a4c8f --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/choicfmt.h @@ -0,0 +1,780 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2005, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File CHOICFMT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/20/97 helena Finished first cut of implementation and got rid +* of nextDouble/previousDouble and replaced with +* boolean array. +* 4/10/97 aliu Clean up. Modified to work on AIX. +* 8/6/97 nos Removed overloaded constructor, member var 'buffer'. +* 07/22/98 stephen Removed operator!= (implemented in Format) +******************************************************************************** +*/ + +#ifndef CHOICFMT_H +#define CHOICFMT_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Choice Format. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/unistr.h" +#include "unicode/numfmt.h" +#include "unicode/fieldpos.h" +#include "unicode/format.h" + +U_NAMESPACE_BEGIN + +class MessageFormat; + +/** + * ChoiceFormat converts between ranges of numeric values + * and string names for those ranges. A <code>ChoiceFormat</code> splits + * the real number line <code>-Inf</code> to <code>+Inf</code> into two + * or more contiguous ranges. Each range is mapped to a + * string. <code>ChoiceFormat</code> is generally used in a + * <code>MessageFormat</code> for displaying grammatically correct + * plurals such as "There are 2 files."</p> + * + * <p>There are two methods of defining a <code>ChoiceFormat</code>; both + * are equivalent. The first is by using a string pattern. This is the + * preferred method in most cases. The second method is through direct + * specification of the arrays that make up the + * <code>ChoiceFormat</code>.</p> + * + * <p><strong>Patterns</strong></p> + * + * <p>In most cases, the preferred way to define a + * <code>ChoiceFormat</code> is with a pattern. Here is an example of a + * <code>ChoiceFormat</code> pattern:</p> + * + * \htmlonly<pre> 0≤are no files|1≤is one file|1<are many files</pre>\endhtmlonly + * + * <p>or equivalently,</p> + * + * \htmlonly<pre> 0#are no files|1#is one file|1<are many files</pre>\endhtmlonly + * + * <p>The pattern consists of a number or <em>range specifiers</em> + * separated by vertical bars '|' (U+007C). There is no + * vertical bar after the last range. Each range specifier is of the + * form:</p> + * + * \htmlonly<blockquote><em>Number Separator String</em></blockquote>\endhtmlonly + * + * <p><em>Number</em> is a floating point number that can be parsed by a + * default <code>NumberFormat</code> for the US locale. It gives the + * lower limit of this range. The lower limit is either inclusive or + * exclusive, depending on the <em>separator</em>. The upper limit is + * given by the lower limit of the next range. The Unicode infinity + * sign \htmlonly∞ \endhtmlonly (U+221E) is recognized for positive infinity. It may be preceded by + * '-' (U+002D) to indicate negative infinity.</p> + * + * <p><em>String</em> is the format string for this range, with special + * characters enclosed in single quotes (<code>'The # + * sign'</code>). Single quotes themselves are indicated by two single + * quotes in a row (<code>'o''clock'</code>).</p> + * + * <p><em>Separator</em> is one of the following single characters: + * + * <ul> + * <li>\htmlonly'≤' \endhtmlonly (U+2264) or '#' (U+0023) + * indicates that the lower limit given by <em>Number</em> is + * inclusive. (The two characters are equivalent to ChoiceFormat.) + * This means that the limit value <em>Number</em> belongs to this + * range. Another way of saying this is that the corresponding + * closure is <code>FALSE</code>.</li> + * + * <li>'<' (U+003C) indicates that the lower limit given by + * <em>Number</em> is exclusive. This means that the value + * <em>Number</em> belongs to the prior range.</li> Another way of + * saying this is that the corresponding closure is + * <code>TRUE</code>. + * </ul> + * + * <p>See below for more information about closures.</p> + * + * <p><strong>Arrays</strong></p> + * + * <p>A <code>ChoiceFormat</code> defining <code>n</code> intervals + * (<code>n</code> >= 2) is specified by three arrays of + * <code>n</code> items: + * + * <ul> + * <li><code>double limits[]</code> gives the start of each + * interval. This must be a non-decreasing list of values, none of + * which may be <code>NaN</code>.</li> + * <li><code>UBool closures[]</code> determines whether each limit + * value is contained in the interval below it or in the interval + * above it. If <code>closures[i]</code> is <code>FALSE</code>, then + * <code>limits[i]</code> is a member of interval + * <code>i</code>. Otherwise it is a member of interval + * <code>i+1</code>. If no closures array is specified, this is + * equivalent to having all closures be <code>FALSE</code>. Closures + * allow one to specify half-open, open, or closed intervals.</li> + * <li><code>UnicodeString formats[]</code> gives the string label + * associated with each interval.</li> + * </ul> + * + * <p><strong>Formatting and Parsing</strong></p> + * + * <p>During formatting, a number is converted to a + * string. <code>ChoiceFormat</code> accomplishes this by mapping the + * number to an interval using the following rule. Given a number + * <code>X</code> and and index value <code>j</code> in the range + * <code>0..n-1</code>, where <code>n</code> is the number of ranges:</p> + * + * \htmlonly<blockquote>\endhtmlonly<code>X</code> matches <code>j</code> if and only if + * <code>limit[j] <= X < limit[j+1]</code> + * \htmlonly</blockquote>\endhtmlonly + * + * <p>(This assumes that all closures are <code>FALSE</code>. If some + * closures are <code>TRUE</code> then the relations must be changed to + * <code><=</code> or <code><</code> as appropriate.) If there is + * no match, then either the first or last index is used, depending on + * whether the number is too low or too high. Once a number is mapped to + * an interval <code>j</code>, the string <code>formats[j]</code> is + * output.</p> + * + * <p>During parsing, a string is converted to a + * number. <code>ChoiceFormat</code> finds the element + * <code>formats[j]</code> equal to the string, and returns + * <code>limits[j]</code> as the parsed value.</p> + * + * <p><strong>Notes</strong></p> + * + * <p>The first limit value does not define a range boundary. For + * example, in the pattern \htmlonly"<code>1.0#a|2.0#b</code>"\endhtmlonly, the + * intervals are [-Inf, 2.0) and [2.0, +Inf]. It appears that the first + * interval should be [1.0, 2.0). However, since all values that are too + * small are mapped to range zero, the first interval is effectively + * [-Inf, 2.0). However, the first limit value <em>is</em> used during + * formatting. In this example, <code>parse("a")</code> returns + * 1.0.</p> + * + * <p>There are no gaps between intervals and the entire number line is + * covered. A <code>ChoiceFormat</code> maps <em>all</em> possible + * double values to a finite set of intervals.</p> + * + * <p>The non-number <code>NaN</code> is mapped to interval zero during + * formatting.</p> + * + * <p><strong>Examples</strong></p> + * + * <p>Here is an example of two arrays that map the number + * <code>1..7</code> to the English day of the week abbreviations + * <code>Sun..Sat</code>. No closures array is given; this is the same as + * specifying all closures to be <code>FALSE</code>.</p> + * + * <pre> {1,2,3,4,5,6,7}, + * {"Sun","Mon","Tue","Wed","Thur","Fri","Sat"}</pre> + * + * <p>Here is an example that maps the ranges [-Inf, 1), [1, 1], and (1, + * +Inf] to three strings. That is, the number line is split into three + * ranges: x < 1.0, x = 1.0, and x > 1.0.</p> + * + * <pre> {0, 1, 1}, + * {FALSE, FALSE, TRUE}, + * {"no files", "one file", "many files"}</pre> + * + * <p>Here is a simple example that shows formatting and parsing: </p> + * + * \code + * #include <unicode/choicfmt.h> + * #include <unicode/unistr.h> + * #include <iostream.h> + * + * int main(int argc, char *argv[]) { + * double limits[] = {1,2,3,4,5,6,7}; + * UnicodeString monthNames[] = { + * "Sun","Mon","Tue","Wed","Thu","Fri","Sat"}; + * ChoiceFormat fmt(limits, monthNames, 7); + * UnicodeString str; + * char buf[256]; + * for (double x = 1.0; x <= 8.0; x += 1.0) { + * fmt.format(x, str); + * str.extract(0, str.length(), buf, 256, ""); + * str.truncate(0); + * cout << x << " -> " + * << buf << endl; + * } + * cout << endl; + * return 0; + * } + * \endcode + * + * <p>Here is a more complex example using a <code>ChoiceFormat</code> + * constructed from a pattern together with a + * <code>MessageFormat</code>.</p> + * + * \code + * #include <unicode/choicfmt.h> + * #include <unicode/msgfmt.h> + * #include <unicode/unistr.h> + * #include <iostream.h> + * + * int main(int argc, char *argv[]) { + * UErrorCode status = U_ZERO_ERROR; + * double filelimits[] = {0,1,2}; + * UnicodeString filepart[] = + * {"are no files","is one file","are {0} files"}; + * ChoiceFormat* fileform = new ChoiceFormat(filelimits, filepart, 3 ); + * Format* testFormats[] = + * {fileform, NULL, NumberFormat::createInstance(status)}; + * MessageFormat pattform("There {0} on {1}", status ); + * pattform.adoptFormats(testFormats, 3); + * Formattable testArgs[] = {0L, "Disk A"}; + * FieldPosition fp(0); + * UnicodeString str; + * char buf[256]; + * for (int32_t i = 0; i < 4; ++i) { + * Formattable fInt(i); + * testArgs[0] = fInt; + * pattform.format(testArgs, 2, str, fp, status ); + * str.extract(0, str.length(), buf, ""); + * str.truncate(0); + * cout << "Output for i=" << i << " : " << buf << endl; + * } + * cout << endl; + * return 0; + * } + * \endcode + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API ChoiceFormat: public NumberFormat { +public: + /** + * Construct a new ChoiceFormat with the limits and the corresponding formats + * based on the pattern. + * + * @param pattern Pattern used to construct object. + * @param status Output param to receive success code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + ChoiceFormat(const UnicodeString& pattern, + UErrorCode& status); + + + /** + * Construct a new ChoiceFormat with the given limits and formats. Copy + * the limits and formats instead of adopting them. + * + * @param limits Array of limit values. + * @param formats Array of formats. + * @param count Size of 'limits' and 'formats' arrays. + * @stable ICU 2.0 + */ + + ChoiceFormat(const double* limits, + const UnicodeString* formats, + int32_t count ); + + /** + * Construct a new ChoiceFormat with the given limits and formats. + * Copy the limits and formats (instead of adopting them). By + * default, each limit in the array specifies the inclusive lower + * bound of its range, and the exclusive upper bound of the previous + * range. However, if the isLimitOpen element corresponding to a + * limit is TRUE, then the limit is the exclusive lower bound of its + * range, and the inclusive upper bound of the previous range. + * @param limits Array of limit values + * @param closures Array of booleans specifying whether each + * element of 'limits' is open or closed. If FALSE, then the + * corresponding limit is a member of the range above it. If TRUE, + * then the limit belongs to the range below it. + * @param formats Array of formats + * @param count Size of 'limits', 'closures', and 'formats' arrays + * @stable ICU 2.4 + */ + ChoiceFormat(const double* limits, + const UBool* closures, + const UnicodeString* formats, + int32_t count); + + /** + * Copy constructor. + * + * @param that ChoiceFormat object to be copied from + * @stable ICU 2.0 + */ + ChoiceFormat(const ChoiceFormat& that); + + /** + * Assignment operator. + * + * @param that ChoiceFormat object to be copied + * @stable ICU 2.0 + */ + const ChoiceFormat& operator=(const ChoiceFormat& that); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~ChoiceFormat(); + + /** + * Clone this Format object polymorphically. The caller owns the + * result and should delete it when done. + * + * @return a copy of this object + * @stable ICU 2.0 + */ + virtual Format* clone(void) const; + + /** + * Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * + * @param other ChoiceFormat object to be compared + * @return true if other is the same as this. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const; + + /** + * Sets the pattern. + * @param pattern The pattern to be applied. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Sets the pattern. + * @param pattern The pattern to be applied. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UParseError& parseError, + UErrorCode& status); + /** + * Gets the pattern. + * + * @param pattern Output param which will recieve the pattern + * Previous contents are deleted. + * @return A reference to 'pattern' + * @stable ICU 2.0 + */ + virtual UnicodeString& toPattern(UnicodeString &pattern) const; + +#ifdef U_USE_CHOICE_FORMAT_DEPRECATES + /** + * Set the choices to be used in formatting. The arrays are adopted and + * should not be deleted by the caller. + * + * @param limitsToAdopt Contains the top value that you want + * parsed with that format,and should be in + * ascending sorted order. When formatting X, + * the choice will be the i, where limit[i] + * <= X < limit[i+1]. + * @param formatsToAdopt The format strings you want to use for each limit. + * @param count The size of the above arrays. + * @obsolete ICU 2.6. Use setChoices instead since this API will be removed in that release. + */ + virtual void adoptChoices(double* limitsToAdopt, + UnicodeString* formatsToAdopt, + int32_t count ); + + /** + * Set the choices to be used in formatting. The arrays are adopted + * and should not be deleted by the caller. See class description + * for documenatation of the limits, closures, and formats arrays. + * @param limitsToAdopt Array of limits to adopt + * @param closuresToAdopt Array of limit booleans to adopt + * @param formatsToAdopt Array of format string to adopt + * @param count The size of the above arrays + * @obsolete ICU 2.6. Use setChoices instead since this API will be removed in that release. + */ + virtual void adoptChoices(double* limitsToAdopt, + UBool* closuresToAdopt, + UnicodeString* formatsToAdopt, + int32_t count); +#endif + + /** + * Set the choices to be used in formatting. + * + * @param limitsToCopy Contains the top value that you want + * parsed with that format,and should be in + * ascending sorted order. When formatting X, + * the choice will be the i, where limit[i] + * <= X < limit[i+1]. + * @param formatsToCopy The format strings you want to use for each limit. + * @param count The size of the above arrays. + * @stable ICU 2.0 + */ + virtual void setChoices(const double* limitsToCopy, + const UnicodeString* formatsToCopy, + int32_t count ); + + /** + * Set the choices to be used in formatting. See class description + * for documenatation of the limits, closures, and formats arrays. + * @param limits Array of limits + * @param closures Array of limit booleans + * @param formats Array of format string + * @param count The size of the above arrays + * @stable ICU 2.4 + */ + virtual void setChoices(const double* limits, + const UBool* closures, + const UnicodeString* formats, + int32_t count); + + /** + * Get the limits passed in the constructor. + * + * @param count The size of the limits arrays + * @return the limits. + * @stable ICU 2.0 + */ + virtual const double* getLimits(int32_t& count) const; + + /** + * Get the limit booleans passed in the constructor. The caller + * must not delete the result. + * + * @param count The size of the arrays + * @return the closures + * @stable ICU 2.4 + */ + virtual const UBool* getClosures(int32_t& count) const; + + /** + * Get the formats passed in the constructor. + * + * @param count The size of the arrays + * @return the formats. + * @stable ICU 2.0 + */ + virtual const UnicodeString* getFormats(int32_t& count) const; + + /** + * Format a double or long number using this object's choices. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(double number, + UnicodeString& appendTo, + FieldPosition& pos) const; + /** + * Format a int_32t number using this object's choices. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(int32_t number, + UnicodeString& appendTo, + FieldPosition& pos) const; + + /** + * Format an int64_t number using this object's choices. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.8 + */ + virtual UnicodeString& format(int64_t number, + UnicodeString& appendTo, + FieldPosition& pos) const; + + /** + * Format an array of objects using this object's choices. + * + * @param objs The array of objects to be formatted. + * @param cnt The size of objs. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param success Output param set to success/failure code on + * exit. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable* objs, + int32_t cnt, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& success) const; + /** + * Format an object using this object's choices. + * + * + * @param obj The object to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Output param set to success/failure code on + * exit. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Redeclared NumberFormat method. + * + * @param obj The object to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Output param set to success/failure code on + * exit. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Redeclared NumberFormat method. + * Format a double number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( double number, + UnicodeString& appendTo) const; + + /** + * Redeclared NumberFormat method. + * Format a long number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( int32_t number, + UnicodeString& appendTo) const; + + /** + * Return a long if possible (e.g. within range LONG_MAX, + * LONG_MAX], and with no decimals), otherwise a double. If + * IntegerOnly is set, will stop at a decimal point (or equivalent; + * e.g. for rational numbers "1 2/3", will stop after the 1). + * <P> + * If no object can be parsed, parsePosition is unchanged, and NULL is + * returned. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parsePosition The position to start parsing at on input. + * On output, moved to after the last successfully + * parse character. On parse failure, does not change. + * @see NumberFormat::isParseIntegerOnly + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + ParsePosition& parsePosition) const; + + /** + * Return a long if possible (e.g. within range LONG_MAX, + * LONG_MAX], and with no decimals), otherwise a double. If + * IntegerOnly is set, will stop at a decimal point (or equivalent; + * e.g. for rational numbers "1 2/3", will stop after the 1). + * <P> + * If no object can be parsed, parsePosition is unchanged, and NULL is + * returned. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param status Output param with the formatted string. + * @see NumberFormat::isParseIntegerOnly + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + UErrorCode& status) const; + + +public: + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +private: + // static cache management (thread-safe) + // static NumberFormat* getNumberFormat(UErrorCode &status); // call this function to 'check out' a numberformat from the cache. + // static void releaseNumberFormat(NumberFormat *adopt); // call this function to 'return' the number format to the cache. + + /** + * Converts a string to a double value using a default NumberFormat object + * which is static (shared by all ChoiceFormat instances). + * @param string the string to be converted with. + * @return the converted double number. + */ + static double stod(const UnicodeString& string); + + /** + * Converts a double value to a string using a default NumberFormat object + * which is static (shared by all ChoiceFormat instances). + * @param value the double number to be converted with. + * @param string the result string. + * @return the converted string. + */ + static UnicodeString& dtos(double value, UnicodeString& string); + + ChoiceFormat(); // default constructor not implemented + + /** + * Construct a new ChoiceFormat with the limits and the corresponding formats + * based on the pattern. + * + * @param newPattern Pattern used to construct object. + * @param parseError Struct to recieve information on position + * of error if an error is encountered. + * @param status Output param to receive success code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + ChoiceFormat(const UnicodeString& newPattern, + UParseError& parseError, + UErrorCode& status); + + friend class MessageFormat; + /** + * Each ChoiceFormat divides the range -Inf..+Inf into fCount + * intervals. The intervals are: + * + * 0: fChoiceLimits[0]..fChoiceLimits[1] + * 1: fChoiceLimits[1]..fChoiceLimits[2] + * ... + * fCount-2: fChoiceLimits[fCount-2]..fChoiceLimits[fCount-1] + * fCount-1: fChoiceLimits[fCount-1]..+Inf + * + * Interval 0 is special; during formatting (mapping numbers to + * strings), it also contains all numbers less than + * fChoiceLimits[0], as well as NaN values. + * + * Interval i maps to and from string fChoiceFormats[i]. When + * parsing (mapping strings to numbers), then intervals map to + * their lower limit, that is, interval i maps to fChoiceLimit[i]. + * + * The intervals may be closed, half open, or open. This affects + * formatting but does not affect parsing. Interval i is affected + * by fClosures[i] and fClosures[i+1]. If fClosures[i] + * is FALSE, then the value fChoiceLimits[i] is in interval i. + * That is, intervals i and i are: + * + * i-1: ... x < fChoiceLimits[i] + * i: fChoiceLimits[i] <= x ... + * + * If fClosures[i] is TRUE, then the value fChoiceLimits[i] is + * in interval i-1. That is, intervals i-1 and i are: + * + * i-1: ... x <= fChoiceLimits[i] + * i: fChoiceLimits[i] < x ... + * + * Because of the nature of interval 0, fClosures[0] has no + * effect. + + */ + double* fChoiceLimits; + UBool* fClosures; + UnicodeString* fChoiceFormats; + int32_t fCount; +}; + +inline UnicodeString& +ChoiceFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + // Don't use Format:: - use immediate base class only, + // in case immediate base modifies behavior later. + return NumberFormat::format(obj, appendTo, status); +} + +inline UnicodeString& +ChoiceFormat::format(double number, + UnicodeString& appendTo) const { + return NumberFormat::format(number, appendTo); +} + +inline UnicodeString& +ChoiceFormat::format(int32_t number, + UnicodeString& appendTo) const { + return NumberFormat::format(number, appendTo); +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _CHOICFMT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/coleitr.h b/Build/source/libs/icu-xetex/i18n/unicode/coleitr.h new file mode 100644 index 00000000000..51b5d2887d9 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/coleitr.h @@ -0,0 +1,399 @@ +/* + ****************************************************************************** + * Copyright (C) 1997-2005, International Business Machines + * Corporation and others. All Rights Reserved. + ****************************************************************************** + */ + +/** +* File coleitr.h +* +* +* +* Created by: Helena Shih +* +* Modification History: +* +* Date Name Description +* +* 8/18/97 helena Added internal API documentation. +* 08/03/98 erm Synched with 1.2 version CollationElementIterator.java +* 12/10/99 aliu Ported Thai collation support from Java. +* 01/25/01 swquek Modified into a C++ wrapper calling C APIs (ucoliter.h) +* 02/19/01 swquek Removed CollationElementsIterator() since it is +* private constructor and no calls are made to it +*/ + +#ifndef COLEITR_H +#define COLEITR_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Collation Element Iterator. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/uobject.h" +#include "unicode/tblcoll.h" +#include "unicode/ucoleitr.h" + +/** + * The UCollationElements struct. + * For usage in C programs. + * @stable ICU 2.0 + */ +typedef struct UCollationElements UCollationElements; + +U_NAMESPACE_BEGIN + +/** +* The CollationElementIterator class is used as an iterator to walk through +* each character of an international string. Use the iterator to return the +* ordering priority of the positioned character. The ordering priority of a +* character, which we refer to as a key, defines how a character is collated in +* the given collation object. +* For example, consider the following in Spanish: +* <pre> +* "ca" -> the first key is key('c') and second key is key('a'). +* "cha" -> the first key is key('ch') and second key is key('a').</pre> +* And in German, +* <pre> \htmlonly "æb"-> the first key is key('a'), the second key is key('e'), and +* the third key is key('b'). \endhtmlonly </pre> +* The key of a character, is an integer composed of primary order(short), +* secondary order(char), and tertiary order(char). Java strictly defines the +* size and signedness of its primitive data types. Therefore, the static +* functions primaryOrder(), secondaryOrder(), and tertiaryOrder() return +* int32_t to ensure the correctness of the key value. +* <p>Example of the iterator usage: (without error checking) +* <pre> +* \code +* void CollationElementIterator_Example() +* { +* UnicodeString str = "This is a test"; +* UErrorCode success = U_ZERO_ERROR; +* RuleBasedCollator* rbc = +* (RuleBasedCollator*) RuleBasedCollator::createInstance(success); +* CollationElementIterator* c = +* rbc->createCollationElementIterator( str ); +* int32_t order = c->next(success); +* c->reset(); +* order = c->previous(success); +* delete c; +* delete rbc; +* } +* \endcode +* </pre> +* <p> +* CollationElementIterator::next returns the collation order of the next +* character based on the comparison level of the collator. +* CollationElementIterator::previous returns the collation order of the +* previous character based on the comparison level of the collator. +* The Collation Element Iterator moves only in one direction between calls to +* CollationElementIterator::reset. That is, CollationElementIterator::next() +* and CollationElementIterator::previous can not be inter-used. Whenever +* CollationElementIterator::previous is to be called after +* CollationElementIterator::next() or vice versa, +* CollationElementIterator::reset has to be called first to reset the status, +* shifting pointers to either the end or the start of the string. Hence at the +* next call of CollationElementIterator::previous or +* CollationElementIterator::next(), the first or last collation order will be +* returned. +* If a change of direction is done without a CollationElementIterator::reset(), +* the result is undefined. +* The result of a forward iterate (CollationElementIterator::next) and +* reversed result of the backward iterate (CollationElementIterator::previous) +* on the same string are equivalent, if collation orders with the value +* UCOL_IGNORABLE are ignored. +* Character based on the comparison level of the collator. A collation order +* consists of primary order, secondary order and tertiary order. The data +* type of the collation order is <strong>t_int32</strong>. +* +* Note, CollationElementIterator should not be subclassed. +* @see Collator +* @see RuleBasedCollator +* @version 1.8 Jan 16 2001 +*/ +class U_I18N_API CollationElementIterator : public UObject { +public: + + // CollationElementIterator public data member ------------------------------ + + enum { + /** + * NULLORDER indicates that an error has occured while processing + * @stable ICU 2.0 + */ + NULLORDER = (int32_t)0xffffffff + }; + + // CollationElementIterator public constructor/destructor ------------------- + + /** + * Copy constructor. + * + * @param other the object to be copied from + * @stable ICU 2.0 + */ + CollationElementIterator(const CollationElementIterator& other); + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~CollationElementIterator(); + + // CollationElementIterator public methods ---------------------------------- + + /** + * Returns true if "other" is the same as "this" + * + * @param other the object to be compared + * @return true if "other" is the same as "this" + * @stable ICU 2.0 + */ + UBool operator==(const CollationElementIterator& other) const; + + /** + * Returns true if "other" is not the same as "this". + * + * @param other the object to be compared + * @return true if "other" is not the same as "this" + * @stable ICU 2.0 + */ + UBool operator!=(const CollationElementIterator& other) const; + + /** + * Resets the cursor to the beginning of the string. + * @stable ICU 2.0 + */ + void reset(void); + + /** + * Gets the ordering priority of the next character in the string. + * @param status the error code status. + * @return the next character's ordering. otherwise returns NULLORDER if an + * error has occured or if the end of string has been reached + * @stable ICU 2.0 + */ + int32_t next(UErrorCode& status); + + /** + * Get the ordering priority of the previous collation element in the string. + * @param status the error code status. + * @return the previous element's ordering. otherwise returns NULLORDER if an + * error has occured or if the start of string has been reached + * @stable ICU 2.0 + */ + int32_t previous(UErrorCode& status); + + /** + * Gets the primary order of a collation order. + * @param order the collation order + * @return the primary order of a collation order. + * @stable ICU 2.0 + */ + static inline int32_t primaryOrder(int32_t order); + + /** + * Gets the secondary order of a collation order. + * @param order the collation order + * @return the secondary order of a collation order. + * @stable ICU 2.0 + */ + static inline int32_t secondaryOrder(int32_t order); + + /** + * Gets the tertiary order of a collation order. + * @param order the collation order + * @return the tertiary order of a collation order. + * @stable ICU 2.0 + */ + static inline int32_t tertiaryOrder(int32_t order); + + /** + * Return the maximum length of any expansion sequences that end with the + * specified comparison order. + * @param order a collation order returned by previous or next. + * @return maximum size of the expansion sequences ending with the collation + * element or 1 if collation element does not occur at the end of any + * expansion sequence + * @stable ICU 2.0 + */ + int32_t getMaxExpansion(int32_t order) const; + + /** + * Gets the comparison order in the desired strength. Ignore the other + * differences. + * @param order The order value + * @stable ICU 2.0 + */ + int32_t strengthOrder(int32_t order) const; + + /** + * Sets the source string. + * @param str the source string. + * @param status the error code status. + * @stable ICU 2.0 + */ + void setText(const UnicodeString& str, UErrorCode& status); + + /** + * Sets the source string. + * @param str the source character iterator. + * @param status the error code status. + * @stable ICU 2.0 + */ + void setText(CharacterIterator& str, UErrorCode& status); + + /** + * Checks if a comparison order is ignorable. + * @param order the collation order. + * @return TRUE if a character is ignorable, FALSE otherwise. + * @stable ICU 2.0 + */ + static inline UBool isIgnorable(int32_t order); + + /** + * Gets the offset of the currently processed character in the source string. + * @return the offset of the character. + * @stable ICU 2.0 + */ + int32_t getOffset(void) const; + + /** + * Sets the offset of the currently processed character in the source string. + * @param newOffset the new offset. + * @param status the error code status. + * @return the offset of the character. + * @stable ICU 2.0 + */ + void setOffset(int32_t newOffset, UErrorCode& status); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +protected: + + // CollationElementIterator protected constructors -------------------------- + /** + * @stable ICU 2.0 + */ + friend class RuleBasedCollator; + + /** + * CollationElementIterator constructor. This takes the source string and the + * collation object. The cursor will walk thru the source string based on the + * predefined collation rules. If the source string is empty, NULLORDER will + * be returned on the calls to next(). + * @param sourceText the source string. + * @param order the collation object. + * @param status the error code status. + * @stable ICU 2.0 + */ + CollationElementIterator(const UnicodeString& sourceText, + const RuleBasedCollator* order, UErrorCode& status); + + /** + * CollationElementIterator constructor. This takes the source string and the + * collation object. The cursor will walk thru the source string based on the + * predefined collation rules. If the source string is empty, NULLORDER will + * be returned on the calls to next(). + * @param sourceText the source string. + * @param order the collation object. + * @param status the error code status. + * @stable ICU 2.0 + */ + CollationElementIterator(const CharacterIterator& sourceText, + const RuleBasedCollator* order, UErrorCode& status); + + // CollationElementIterator protected methods ------------------------------- + + /** + * Assignment operator + * + * @param other the object to be copied + * @stable ICU 2.0 + */ + const CollationElementIterator& + operator=(const CollationElementIterator& other); + +private: + CollationElementIterator(); // default constructor not implemented + + // CollationElementIterator private data members ---------------------------- + + /** + * Data wrapper for collation elements + */ + UCollationElements *m_data_; + + /** + * Indicates if m_data_ belongs to this object. + */ + UBool isDataOwned_; + +}; + +// CollationElementIterator inline method defination -------------------------- + +/** +* Get the primary order of a collation order. +* @param order the collation order +* @return the primary order of a collation order. +*/ +inline int32_t CollationElementIterator::primaryOrder(int32_t order) +{ + order &= RuleBasedCollator::PRIMARYORDERMASK; + return (order >> RuleBasedCollator::PRIMARYORDERSHIFT); +} + +/** +* Get the secondary order of a collation order. +* @param order the collation order +* @return the secondary order of a collation order. +*/ +inline int32_t CollationElementIterator::secondaryOrder(int32_t order) +{ + order = order & RuleBasedCollator::SECONDARYORDERMASK; + return (order >> RuleBasedCollator::SECONDARYORDERSHIFT); +} + +/** +* Get the tertiary order of a collation order. +* @param order the collation order +* @return the tertiary order of a collation order. +*/ +inline int32_t CollationElementIterator::tertiaryOrder(int32_t order) +{ + return (order &= RuleBasedCollator::TERTIARYORDERMASK); +} + +inline int32_t CollationElementIterator::getMaxExpansion(int32_t order) const +{ + return ucol_getMaxExpansion(m_data_, (uint32_t)order); +} + +inline UBool CollationElementIterator::isIgnorable(int32_t order) +{ + return (primaryOrder(order) == RuleBasedCollator::PRIMIGNORABLE); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/coll.h b/Build/source/libs/icu-xetex/i18n/unicode/coll.h new file mode 100644 index 00000000000..c3ebca16f23 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/coll.h @@ -0,0 +1,1035 @@ +/* +****************************************************************************** +* Copyright (C) 1996-2007, International Business Machines * +* Corporation and others. All Rights Reserved. * +****************************************************************************** +*/ + +/** +* File coll.h +* +* Created by: Helena Shih +* +* Modification History: +* +* Date Name Description +* 02/5/97 aliu Modified createDefault to load collation data from +* binary files when possible. Added related methods +* createCollationFromFile, chopLocale, createPathName. +* 02/11/97 aliu Added members addToCache, findInCache, and fgCache. +* 02/12/97 aliu Modified to create objects from RuleBasedCollator cache. +* Moved cache out of Collation class. +* 02/13/97 aliu Moved several methods out of this class and into +* RuleBasedCollator, with modifications. Modified +* createDefault() to call new RuleBasedCollator(Locale&) +* constructor. General clean up and documentation. +* 02/20/97 helena Added clone, operator==, operator!=, operator=, copy +* constructor and getDynamicClassID. +* 03/25/97 helena Updated with platform independent data types. +* 05/06/97 helena Added memory allocation error detection. +* 06/20/97 helena Java class name change. +* 09/03/97 helena Added createCollationKeyValues(). +* 02/10/98 damiba Added compare() with length as parameter. +* 04/23/99 stephen Removed EDecompositionMode, merged with +* Normalizer::EMode. +* 11/02/99 helena Collator performance enhancements. Eliminates the +* UnicodeString construction and special case for NO_OP. +* 11/23/99 srl More performance enhancements. Inlining of +* critical accessors. +* 05/15/00 helena Added version information API. +* 01/29/01 synwee Modified into a C++ wrapper which calls C apis +* (ucoll.h). +*/ + +#ifndef COLL_H +#define COLL_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Collation Service. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/uobject.h" +#include "unicode/ucol.h" +#include "unicode/normlzr.h" +#include "unicode/locid.h" +#include "unicode/uniset.h" +#include "unicode/umisc.h" + +U_NAMESPACE_BEGIN + +class StringEnumeration; + +#if !UCONFIG_NO_SERVICE +/** + * @stable ICU 2.6 + */ +class CollatorFactory; +#endif + +/** +* @stable ICU 2.0 +*/ +class CollationKey; + +/** +* The <code>Collator</code> class performs locale-sensitive string +* comparison.<br> +* You use this class to build searching and sorting routines for natural +* language text.<br> +* <em>Important: </em>The ICU collation service has been reimplemented +* in order to achieve better performance and UCA compliance. +* For details, see the +* <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm"> +* collation design document</a>. +* <p> +* <code>Collator</code> is an abstract base class. Subclasses implement +* specific collation strategies. One subclass, +* <code>RuleBasedCollator</code>, is currently provided and is applicable +* to a wide set of languages. Other subclasses may be created to handle more +* specialized needs. +* <p> +* Like other locale-sensitive classes, you can use the static factory method, +* <code>createInstance</code>, to obtain the appropriate +* <code>Collator</code> object for a given locale. You will only need to +* look at the subclasses of <code>Collator</code> if you need to +* understand the details of a particular collation strategy or if you need to +* modify that strategy. +* <p> +* The following example shows how to compare two strings using the +* <code>Collator</code> for the default locale. +* \htmlonly<blockquote>\endhtmlonly +* <pre> +* \code +* // Compare two strings in the default locale +* UErrorCode success = U_ZERO_ERROR; +* Collator* myCollator = Collator::createInstance(success); +* if (myCollator->compare("abc", "ABC") < 0) +* cout << "abc is less than ABC" << endl; +* else +* cout << "abc is greater than or equal to ABC" << endl; +* \endcode +* </pre> +* \htmlonly</blockquote>\endhtmlonly +* <p> +* You can set a <code>Collator</code>'s <em>strength</em> property to +* determine the level of difference considered significant in comparisons. +* Five strengths are provided: <code>PRIMARY</code>, <code>SECONDARY</code>, +* <code>TERTIARY</code>, <code>QUATERNARY</code> and <code>IDENTICAL</code>. +* The exact assignment of strengths to language features is locale dependant. +* For example, in Czech, "e" and "f" are considered primary differences, +* while "e" and "\u00EA" are secondary differences, "e" and "E" are tertiary +* differences and "e" and "e" are identical. The following shows how both case +* and accents could be ignored for US English. +* \htmlonly<blockquote>\endhtmlonly +* <pre> +* \code +* //Get the Collator for US English and set its strength to PRIMARY +* UErrorCode success = U_ZERO_ERROR; +* Collator* usCollator = Collator::createInstance(Locale::US, success); +* usCollator->setStrength(Collator::PRIMARY); +* if (usCollator->compare("abc", "ABC") == 0) +* cout << "'abc' and 'ABC' strings are equivalent with strength PRIMARY" << endl; +* \endcode +* </pre> +* \htmlonly</blockquote>\endhtmlonly +* <p> +* For comparing strings exactly once, the <code>compare</code> method +* provides the best performance. When sorting a list of strings however, it +* is generally necessary to compare each string multiple times. In this case, +* sort keys provide better performance. The <code>getSortKey</code> methods +* convert a string to a series of bytes that can be compared bitwise against +* other sort keys using <code>strcmp()</code>. Sort keys are written as +* zero-terminated byte strings. They consist of several substrings, one for +* each collation strength level, that are delimited by 0x01 bytes. +* If the string code points are appended for UCOL_IDENTICAL, then they are +* processed for correct code point order comparison and may contain 0x01 +* bytes but not zero bytes. +* </p> +* <p> +* An older set of APIs returns a <code>CollationKey</code> object that wraps +* the sort key bytes instead of returning the bytes themselves. +* Its use is deprecated, but it is still available for compatibility with +* Java. +* </p> +* <p> +* <strong>Note:</strong> <code>Collator</code>s with different Locale, +* and CollationStrength settings will return different sort +* orders for the same set of strings. Locales have specific collation rules, +* and the way in which secondary and tertiary differences are taken into +* account, for example, will result in a different sorting order for same +* strings. +* </p> +* @see RuleBasedCollator +* @see CollationKey +* @see CollationElementIterator +* @see Locale +* @see Normalizer +* @version 2.0 11/15/01 +*/ + +class U_I18N_API Collator : public UObject { +public: + + // Collator public enums ----------------------------------------------- + + /** + * Base letter represents a primary difference. Set comparison level to + * PRIMARY to ignore secondary and tertiary differences.<br> + * Use this to set the strength of a Collator object.<br> + * Example of primary difference, "abc" < "abd" + * + * Diacritical differences on the same base letter represent a secondary + * difference. Set comparison level to SECONDARY to ignore tertiary + * differences. Use this to set the strength of a Collator object.<br> + * Example of secondary difference, "ä" >> "a". + * + * Uppercase and lowercase versions of the same character represents a + * tertiary difference. Set comparison level to TERTIARY to include all + * comparison differences. Use this to set the strength of a Collator + * object.<br> + * Example of tertiary difference, "abc" <<< "ABC". + * + * Two characters are considered "identical" when they have the same unicode + * spellings.<br> + * For example, "ä" == "ä". + * + * UCollationStrength is also used to determine the strength of sort keys + * generated from Collator objects. + * @stable ICU 2.0 + */ + enum ECollationStrength + { + PRIMARY = 0, + SECONDARY = 1, + TERTIARY = 2, + QUATERNARY = 3, + IDENTICAL = 15 + }; + + /** + * LESS is returned if source string is compared to be less than target + * string in the compare() method. + * EQUAL is returned if source string is compared to be equal to target + * string in the compare() method. + * GREATER is returned if source string is compared to be greater than + * target string in the compare() method. + * @see Collator#compare + * @deprecated ICU 2.6. Use C enum UCollationResult defined in ucol.h + */ + enum EComparisonResult + { + LESS = -1, + EQUAL = 0, + GREATER = 1 + }; + + // Collator public destructor ----------------------------------------- + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~Collator(); + + // Collator public methods -------------------------------------------- + + /** + * Returns true if "other" is the same as "this" + * @param other Collator object to be compared + * @return true if other is the same as this. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Collator& other) const; + + /** + * Returns true if "other" is not the same as "this". + * @param other Collator object to be compared + * @return true if other is not the same as this. + * @stable ICU 2.0 + */ + virtual UBool operator!=(const Collator& other) const; + + /** + * Makes a shallow copy of the current object. + * @return a copy of this object + * @stable ICU 2.0 + */ + virtual Collator* clone(void) const = 0; + + /** + * Creates the Collator object for the current default locale. + * The default locale is determined by Locale::getDefault. + * The UErrorCode& err parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check the + * value of U_SUCCESS(err). If you wish more detailed information, you can + * check for informational error results which still indicate success. + * U_USING_FALLBACK_ERROR indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_ERROR indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * + * @param err the error code status. + * @return the collation object of the default locale.(for example, en_US) + * @see Locale#getDefault + * @stable ICU 2.0 + */ + static Collator* U_EXPORT2 createInstance(UErrorCode& err); + + /** + * Gets the table-based collation object for the desired locale. The + * resource of the desired locale will be loaded by ResourceLoader. + * Locale::ENGLISH is the base collation table and all other languages are + * built on top of it with additional language-specific modifications. + * The UErrorCode& err parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_ERROR indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_ERROR indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @param loc The locale ID for which to open a collator. + * @param err the error code status. + * @return the created table-based collation object based on the desired + * locale. + * @see Locale + * @see ResourceLoader + * @stable ICU 2.2 + */ + static Collator* U_EXPORT2 createInstance(const Locale& loc, UErrorCode& err); + +#ifdef U_USE_COLLATION_OBSOLETE_2_6 + /** + * Create a Collator with a specific version. + * This is the same as createInstance(loc, err) except that getVersion() of + * the returned object is guaranteed to be the same as the version + * parameter. + * This is designed to be used to open the same collator for a given + * locale even when ICU is updated. + * The same locale and version guarantees the same sort keys and + * comparison results. + * <p> + * Note: this API will be removed in a future release. Use + * <tt>createInstance(const Locale&, UErrorCode&) instead.</tt></p> + * + * @param loc The locale ID for which to open a collator. + * @param version The requested collator version. + * @param err A reference to a UErrorCode, + * must not indicate a failure before calling this function. + * @return A pointer to a Collator, or 0 if an error occurred + * or a collator with the requested version is not available. + * + * @see getVersion + * @obsolete ICU 2.6 + */ + static Collator *createInstance(const Locale &loc, UVersionInfo version, UErrorCode &err); +#endif + + /** + * The comparison function compares the character data stored in two + * different strings. Returns information about whether a string is less + * than, greater than or equal to another string. + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @return Returns a byte value. GREATER if source is greater + * than target; EQUAL if source is equal to target; LESS if source is less + * than target + * @deprecated ICU 2.6 use the overload with UErrorCode & + */ + virtual EComparisonResult compare(const UnicodeString& source, + const UnicodeString& target) const; + + /** + * The comparison function compares the character data stored in two + * different strings. Returns information about whether a string is less + * than, greater than or equal to another string. + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source is greater + * than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less + * than target + * @stable ICU 2.6 + */ + virtual UCollationResult compare(const UnicodeString& source, + const UnicodeString& target, + UErrorCode &status) const = 0; + + /** + * Does the same thing as compare but limits the comparison to a specified + * length + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @param length the length the comparison is limited to + * @return Returns a byte value. GREATER if source (up to the specified + * length) is greater than target; EQUAL if source (up to specified + * length) is equal to target; LESS if source (up to the specified + * length) is less than target. + * @deprecated ICU 2.6 use the overload with UErrorCode & + */ + virtual EComparisonResult compare(const UnicodeString& source, + const UnicodeString& target, + int32_t length) const; + + /** + * Does the same thing as compare but limits the comparison to a specified + * length + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @param length the length the comparison is limited to + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source (up to the specified + * length) is greater than target; UCOL_EQUAL if source (up to specified + * length) is equal to target; UCOL_LESS if source (up to the specified + * length) is less than target. + * @stable ICU 2.6 + */ + virtual UCollationResult compare(const UnicodeString& source, + const UnicodeString& target, + int32_t length, + UErrorCode &status) const = 0; + + /** + * The comparison function compares the character data stored in two + * different string arrays. Returns information about whether a string array + * is less than, greater than or equal to another string array. + * @param source the source string array to be compared with. + * @param sourceLength the length of the source string array. If this value + * is equal to -1, the string array is null-terminated. + * @param target the string that is to be compared with the source string. + * @param targetLength the length of the target string array. If this value + * is equal to -1, the string array is null-terminated. + * @return Returns a byte value. GREATER if source is greater than target; + * EQUAL if source is equal to target; LESS if source is less than + * target + * @deprecated ICU 2.6 use the overload with UErrorCode & + */ + virtual EComparisonResult compare(const UChar* source, int32_t sourceLength, + const UChar* target, int32_t targetLength) + const; + + /** + * The comparison function compares the character data stored in two + * different string arrays. Returns information about whether a string array + * is less than, greater than or equal to another string array. + * @param source the source string array to be compared with. + * @param sourceLength the length of the source string array. If this value + * is equal to -1, the string array is null-terminated. + * @param target the string that is to be compared with the source string. + * @param targetLength the length of the target string array. If this value + * is equal to -1, the string array is null-terminated. + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source is greater + * than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less + * than target + * @stable ICU 2.6 + */ + virtual UCollationResult compare(const UChar* source, int32_t sourceLength, + const UChar* target, int32_t targetLength, + UErrorCode &status) const = 0; + + /** + * Transforms the string into a series of characters that can be compared + * with CollationKey::compareTo. It is not possible to restore the original + * string from the chars in the sort key. The generated sort key handles + * only a limited number of ignorable characters. + * <p>Use CollationKey::equals or CollationKey::compare to compare the + * generated sort keys. + * If the source string is null, a null collation key will be returned. + * @param source the source string to be transformed into a sort key. + * @param key the collation key to be filled in + * @param status the error code status. + * @return the collation key of the string based on the collation rules. + * @see CollationKey#compare + * @deprecated ICU 2.8 Use getSortKey(...) instead + */ + virtual CollationKey& getCollationKey(const UnicodeString& source, + CollationKey& key, + UErrorCode& status) const = 0; + + /** + * Transforms the string into a series of characters that can be compared + * with CollationKey::compareTo. It is not possible to restore the original + * string from the chars in the sort key. The generated sort key handles + * only a limited number of ignorable characters. + * <p>Use CollationKey::equals or CollationKey::compare to compare the + * generated sort keys. + * <p>If the source string is null, a null collation key will be returned. + * @param source the source string to be transformed into a sort key. + * @param sourceLength length of the collation key + * @param key the collation key to be filled in + * @param status the error code status. + * @return the collation key of the string based on the collation rules. + * @see CollationKey#compare + * @deprecated ICU 2.8 Use getSortKey(...) instead + */ + virtual CollationKey& getCollationKey(const UChar*source, + int32_t sourceLength, + CollationKey& key, + UErrorCode& status) const = 0; + /** + * Generates the hash code for the collation object + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const = 0; + + /** + * Gets the locale of the Collator + * + * @param type can be either requested, valid or actual locale. For more + * information see the definition of ULocDataLocaleType in + * uloc.h + * @param status the error code status. + * @return locale where the collation data lives. If the collator + * was instantiated from rules, locale is empty. + * @deprecated ICU 2.8 This API is under consideration for revision + * in ICU 3.0. + */ + virtual const Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const = 0; + + /** + * Convenience method for comparing two strings based on the collation rules. + * @param source the source string to be compared with. + * @param target the target string to be compared with. + * @return true if the first string is greater than the second one, + * according to the collation rules. false, otherwise. + * @see Collator#compare + * @stable ICU 2.0 + */ + UBool greater(const UnicodeString& source, const UnicodeString& target) + const; + + /** + * Convenience method for comparing two strings based on the collation rules. + * @param source the source string to be compared with. + * @param target the target string to be compared with. + * @return true if the first string is greater than or equal to the second + * one, according to the collation rules. false, otherwise. + * @see Collator#compare + * @stable ICU 2.0 + */ + UBool greaterOrEqual(const UnicodeString& source, + const UnicodeString& target) const; + + /** + * Convenience method for comparing two strings based on the collation rules. + * @param source the source string to be compared with. + * @param target the target string to be compared with. + * @return true if the strings are equal according to the collation rules. + * false, otherwise. + * @see Collator#compare + * @stable ICU 2.0 + */ + UBool equals(const UnicodeString& source, const UnicodeString& target) const; + + /** + * Determines the minimum strength that will be use in comparison or + * transformation. + * <p>E.g. with strength == SECONDARY, the tertiary difference is ignored + * <p>E.g. with strength == PRIMARY, the secondary and tertiary difference + * are ignored. + * @return the current comparison level. + * @see Collator#setStrength + * @deprecated ICU 2.6 Use getAttribute(UCOL_STRENGTH...) instead + */ + virtual ECollationStrength getStrength(void) const = 0; + + /** + * Sets the minimum strength to be used in comparison or transformation. + * <p>Example of use: + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * Collator*myCollation = Collator::createInstance(Locale::US, status); + * if (U_FAILURE(status)) return; + * myCollation->setStrength(Collator::PRIMARY); + * // result will be "abc" == "ABC" + * // tertiary differences will be ignored + * Collator::ComparisonResult result = myCollation->compare("abc", "ABC"); + * \endcode + * </pre> + * @see Collator#getStrength + * @param newStrength the new comparison level. + * @deprecated ICU 2.6 Use setAttribute(UCOL_STRENGTH...) instead + */ + virtual void setStrength(ECollationStrength newStrength) = 0; + + /** + * Get name of the object for the desired Locale, in the desired langauge + * @param objectLocale must be from getAvailableLocales + * @param displayLocale specifies the desired locale for output + * @param name the fill-in parameter of the return value + * @return display-able name of the object for the object locale in the + * desired language + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, + const Locale& displayLocale, + UnicodeString& name); + + /** + * Get name of the object for the desired Locale, in the langauge of the + * default locale. + * @param objectLocale must be from getAvailableLocales + * @param name the fill-in parameter of the return value + * @return name of the object for the desired locale in the default language + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, + UnicodeString& name); + + /** + * Get the set of Locales for which Collations are installed. + * + * <p>Note this does not include locales supported by registered collators. + * If collators might have been registered, use the overload of getAvailableLocales + * that returns a StringEnumeration.</p> + * + * @param count the output parameter of number of elements in the locale list + * @return the list of available locales for which collations are installed + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + + /** + * Return a StringEnumeration over the locales available at the time of the call, + * including registered locales. If a severe error occurs (such as out of memory + * condition) this will return null. If there is no locale data, an empty enumeration + * will be returned. + * @return a StringEnumeration over the locales available at the time of the call + * @stable ICU 2.6 + */ + static StringEnumeration* U_EXPORT2 getAvailableLocales(void); + + /** + * Create a string enumerator of all possible keywords that are relevant to + * collation. At this point, the only recognized keyword for this + * service is "collation". + * @param status input-output error code + * @return a string enumeration over locale strings. The caller is + * responsible for closing the result. + * @stable ICU 3.0 + */ + static StringEnumeration* U_EXPORT2 getKeywords(UErrorCode& status); + + /** + * Given a keyword, create a string enumeration of all values + * for that keyword that are currently in use. + * @param keyword a particular keyword as enumerated by + * ucol_getKeywords. If any other keyword is passed in, status is set + * to U_ILLEGAL_ARGUMENT_ERROR. + * @param status input-output error code + * @return a string enumeration over collation keyword values, or NULL + * upon error. The caller is responsible for deleting the result. + * @stable ICU 3.0 + */ + static StringEnumeration* U_EXPORT2 getKeywordValues(const char *keyword, UErrorCode& status); + + /** + * Return the functionally equivalent locale for the given + * requested locale, with respect to given keyword, for the + * collation service. If two locales return the same result, then + * collators instantiated for these locales will behave + * equivalently. The converse is not always true; two collators + * may in fact be equivalent, but return different results, due to + * internal details. The return result has no other meaning than + * that stated above, and implies nothing as to the relationship + * between the two locales. This is intended for use by + * applications who wish to cache collators, or otherwise reuse + * collators when possible. The functional equivalent may change + * over time. For more information, please see the <a + * href="http://icu-project.org/userguide/locale.html#services"> + * Locales and Services</a> section of the ICU User Guide. + * @param keyword a particular keyword as enumerated by + * ucol_getKeywords. + * @param locale the requested locale + * @param isAvailable reference to a fillin parameter that + * indicates whether the requested locale was 'available' to the + * collation service. A locale is defined as 'available' if it + * physically exists within the collation locale data. + * @param status reference to input-output error code + * @return the functionally equivalent collation locale, or the root + * locale upon error. + * @stable ICU 3.0 + */ + static Locale U_EXPORT2 getFunctionalEquivalent(const char* keyword, const Locale& locale, + UBool& isAvailable, UErrorCode& status); + +#if !UCONFIG_NO_SERVICE + /** + * Register a new Collator. The collator will be adopted. + * @param toAdopt the Collator instance to be adopted + * @param locale the locale with which the collator will be associated + * @param status the in/out status code, no special meanings are assigned + * @return a registry key that can be used to unregister this collator + * @stable ICU 2.6 + */ + static URegistryKey U_EXPORT2 registerInstance(Collator* toAdopt, const Locale& locale, UErrorCode& status); + + /** + * Register a new CollatorFactory. The factory will be adopted. + * @param toAdopt the CollatorFactory instance to be adopted + * @param status the in/out status code, no special meanings are assigned + * @return a registry key that can be used to unregister this collator + * @stable ICU 2.6 + */ + static URegistryKey U_EXPORT2 registerFactory(CollatorFactory* toAdopt, UErrorCode& status); + + /** + * Unregister a previously-registered Collator or CollatorFactory + * using the key returned from the register call. Key becomes + * invalid after a successful call and should not be used again. + * The object corresponding to the key will be deleted. + * @param key the registry key returned by a previous call to registerInstance + * @param status the in/out status code, no special meanings are assigned + * @return TRUE if the collator for the key was successfully unregistered + * @stable ICU 2.6 + */ + static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status); +#endif /* UCONFIG_NO_SERVICE */ + + /** + * Gets the version information for a Collator. + * @param info the version # information, the result will be filled in + * @stable ICU 2.0 + */ + virtual void getVersion(UVersionInfo info) const = 0; + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual method. + * This method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * @return The class ID for this object. All objects of a given class have + * the same class ID. Objects of other classes have different class + * IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Universal attribute setter + * @param attr attribute type + * @param value attribute value + * @param status to indicate whether the operation went on smoothly or + * there were errors + * @stable ICU 2.2 + */ + virtual void setAttribute(UColAttribute attr, UColAttributeValue value, + UErrorCode &status) = 0; + + /** + * Universal attribute getter + * @param attr attribute type + * @param status to indicate whether the operation went on smoothly or + * there were errors + * @return attribute value + * @stable ICU 2.2 + */ + virtual UColAttributeValue getAttribute(UColAttribute attr, + UErrorCode &status) = 0; + + /** + * Sets the variable top to a collation element value of a string supplied. + * @param varTop one or more (if contraction) UChars to which the variable top should be set + * @param len length of variable top string. If -1 it is considered to be zero terminated. + * @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br> + * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br> + * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes + * @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined + * @stable ICU 2.0 + */ + virtual uint32_t setVariableTop(const UChar *varTop, int32_t len, UErrorCode &status) = 0; + + /** + * Sets the variable top to a collation element value of a string supplied. + * @param varTop an UnicodeString size 1 or more (if contraction) of UChars to which the variable top should be set + * @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br> + * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br> + * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes + * @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined + * @stable ICU 2.0 + */ + virtual uint32_t setVariableTop(const UnicodeString varTop, UErrorCode &status) = 0; + + /** + * Sets the variable top to a collation element value supplied. Variable top is set to the upper 16 bits. + * Lower 16 bits are ignored. + * @param varTop CE value, as returned by setVariableTop or ucol)getVariableTop + * @param status error code (not changed by function) + * @stable ICU 2.0 + */ + virtual void setVariableTop(const uint32_t varTop, UErrorCode &status) = 0; + + /** + * Gets the variable top value of a Collator. + * Lower 16 bits are undefined and should be ignored. + * @param status error code (not changed by function). If error code is set, the return value is undefined. + * @stable ICU 2.0 + */ + virtual uint32_t getVariableTop(UErrorCode &status) const = 0; + + /** + * Get an UnicodeSet that contains all the characters and sequences + * tailored in this collator. + * @param status error code of the operation + * @return a pointer to a UnicodeSet object containing all the + * code points and sequences that may sort differently than + * in the UCA. The object must be disposed of by using delete + * @stable ICU 2.4 + */ + virtual UnicodeSet *getTailoredSet(UErrorCode &status) const; + + + /** + * Thread safe cloning operation + * @return pointer to the new clone, user should remove it. + * @stable ICU 2.2 + */ + virtual Collator* safeClone(void) = 0; + + /** + * Get the sort key as an array of bytes from an UnicodeString. + * Sort key byte arrays are zero-terminated and can be compared using + * strcmp(). + * @param source string to be processed. + * @param result buffer to store result in. If NULL, number of bytes needed + * will be returned. + * @param resultLength length of the result buffer. If if not enough the + * buffer will be filled to capacity. + * @return Number of bytes needed for storing the sort key + * @stable ICU 2.2 + */ + virtual int32_t getSortKey(const UnicodeString& source, + uint8_t* result, + int32_t resultLength) const = 0; + + /** + * Get the sort key as an array of bytes from an UChar buffer. + * Sort key byte arrays are zero-terminated and can be compared using + * strcmp(). + * @param source string to be processed. + * @param sourceLength length of string to be processed. + * If -1, the string is 0 terminated and length will be decided by the + * function. + * @param result buffer to store result in. If NULL, number of bytes needed + * will be returned. + * @param resultLength length of the result buffer. If if not enough the + * buffer will be filled to capacity. + * @return Number of bytes needed for storing the sort key + * @stable ICU 2.2 + */ + virtual int32_t getSortKey(const UChar*source, int32_t sourceLength, + uint8_t*result, int32_t resultLength) const = 0; + + /** + * Produce a bound for a given sortkey and a number of levels. + * Return value is always the number of bytes needed, regardless of + * whether the result buffer was big enough or even valid.<br> + * Resulting bounds can be used to produce a range of strings that are + * between upper and lower bounds. For example, if bounds are produced + * for a sortkey of string "smith", strings between upper and lower + * bounds with one level would include "Smith", "SMITH", "sMiTh".<br> + * There are two upper bounds that can be produced. If UCOL_BOUND_UPPER + * is produced, strings matched would be as above. However, if bound + * produced using UCOL_BOUND_UPPER_LONG is used, the above example will + * also match "Smithsonian" and similar.<br> + * For more on usage, see example in cintltst/capitst.c in procedure + * TestBounds. + * Sort keys may be compared using <TT>strcmp</TT>. + * @param source The source sortkey. + * @param sourceLength The length of source, or -1 if null-terminated. + * (If an unmodified sortkey is passed, it is always null + * terminated). + * @param boundType Type of bound required. It can be UCOL_BOUND_LOWER, which + * produces a lower inclusive bound, UCOL_BOUND_UPPER, that + * produces upper bound that matches strings of the same length + * or UCOL_BOUND_UPPER_LONG that matches strings that have the + * same starting substring as the source string. + * @param noOfLevels Number of levels required in the resulting bound (for most + * uses, the recommended value is 1). See users guide for + * explanation on number of levels a sortkey can have. + * @param result A pointer to a buffer to receive the resulting sortkey. + * @param resultLength The maximum size of result. + * @param status Used for returning error code if something went wrong. If the + * number of levels requested is higher than the number of levels + * in the source key, a warning (U_SORT_KEY_TOO_SHORT_WARNING) is + * issued. + * @return The size needed to fully store the bound. + * @see ucol_keyHashCode + * @stable ICU 2.1 + */ + static int32_t U_EXPORT2 getBound(const uint8_t *source, + int32_t sourceLength, + UColBoundMode boundType, + uint32_t noOfLevels, + uint8_t *result, + int32_t resultLength, + UErrorCode &status); + + +protected: + + // Collator protected constructors ------------------------------------- + + /** + * Default constructor. + * Constructor is different from the old default Collator constructor. + * The task for determing the default collation strength and normalization + * mode is left to the child class. + * @stable ICU 2.0 + */ + Collator(); + + /** + * Constructor. + * Empty constructor, does not handle the arguments. + * This constructor is done for backward compatibility with 1.7 and 1.8. + * The task for handling the argument collation strength and normalization + * mode is left to the child class. + * @param collationStrength collation strength + * @param decompositionMode + * @deprecated ICU 2.4. Subclasses should use the default constructor + * instead and handle the strength and normalization mode themselves. + */ + Collator(UCollationStrength collationStrength, + UNormalizationMode decompositionMode); + + /** + * Copy constructor. + * @param other Collator object to be copied from + * @stable ICU 2.0 + */ + Collator(const Collator& other); + + // Collator protected methods ----------------------------------------- + + + /** + * Used internally by registraton to define the requested and valid locales. + * @param requestedLocale the requsted locale + * @param validLocale the valid locale + * @internal + */ + virtual void setLocales(const Locale& requestedLocale, const Locale& validLocale); + +public: +#if !UCONFIG_NO_SERVICE + /** + * used only by ucol_open, not for public use + * @internal + */ + static UCollator* createUCollator(const char* loc, UErrorCode* status); +#endif +private: + /** + * Assignment operator. Private for now. + * @internal + */ + Collator& operator=(const Collator& other); + + friend class CFactory; + friend class SimpleCFactory; + friend class ICUCollatorFactory; + friend class ICUCollatorService; + static Collator* makeInstance(const Locale& desiredLocale, + UErrorCode& status); + + // Collator private data members --------------------------------------- + + /* + synwee : removed as attributes to be handled by child class + UCollationStrength strength; + Normalizer::EMode decmp; + */ + /* This is useless information */ +/* static const UVersionInfo fVersion;*/ +}; + +#if !UCONFIG_NO_SERVICE +/** + * A factory, used with registerFactory, the creates multiple collators and provides + * display names for them. A factory supports some number of locales-- these are the + * locales for which it can create collators. The factory can be visible, in which + * case the supported locales will be enumerated by getAvailableLocales, or invisible, + * in which they are not. Invisible locales are still supported, they are just not + * listed by getAvailableLocales. + * <p> + * If standard locale display names are sufficient, Collator instances can + * be registered using registerInstance instead.</p> + * <p> + * Note: if the collators are to be used from C APIs, they must be instances + * of RuleBasedCollator.</p> + * + * @stable ICU 2.6 + */ +class U_I18N_API CollatorFactory : public UObject { +public: + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~CollatorFactory(); + + /** + * Return true if this factory is visible. Default is true. + * If not visible, the locales supported by this factory will not + * be listed by getAvailableLocales. + * @return true if the factory is visible. + * @stable ICU 2.6 + */ + virtual UBool visible(void) const; + + /** + * Return a collator for the provided locale. If the locale + * is not supported, return NULL. + * @param loc the locale identifying the collator to be created. + * @return a new collator if the locale is supported, otherwise NULL. + * @stable ICU 2.6 + */ + virtual Collator* createCollator(const Locale& loc) = 0; + + /** + * Return the name of the collator for the objectLocale, localized for the displayLocale. + * If objectLocale is not supported, or the factory is not visible, set the result string + * to bogus. + * @param objectLocale the locale identifying the collator + * @param displayLocale the locale for which the display name of the collator should be localized + * @param result an output parameter for the display name, set to bogus if not supported. + * @return the display name + * @stable ICU 2.6 + */ + virtual UnicodeString& getDisplayName(const Locale& objectLocale, + const Locale& displayLocale, + UnicodeString& result); + + /** + * Return an array of all the locale names directly supported by this factory. + * The number of names is returned in count. This array is owned by the factory. + * Its contents must never change. + * @param count output parameter for the number of locales supported by the factory + * @param status the in/out error code + * @return a pointer to an array of count UnicodeStrings. + * @stable ICU 2.6 + */ + virtual const UnicodeString * getSupportedIDs(int32_t &count, UErrorCode& status) = 0; +}; +#endif /* UCONFIG_NO_SERVICE */ + +// Collator inline methods ----------------------------------------------- + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/curramt.h b/Build/source/libs/icu-xetex/i18n/unicode/curramt.h new file mode 100644 index 00000000000..c33e6f1f833 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/curramt.h @@ -0,0 +1,130 @@ +/* +********************************************************************** +* Copyright (c) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: April 26, 2004 +* Since: ICU 3.0 +********************************************************************** +*/ +#ifndef __CURRENCYAMOUNT_H__ +#define __CURRENCYAMOUNT_H__ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/measure.h" +#include "unicode/currunit.h" + +/** + * \file + * \brief C++ API: Currency Amount Object. + */ + +U_NAMESPACE_BEGIN + +/** + * + * A currency together with a numeric amount, such as 200 USD. + * + * @author Alan Liu + * @stable ICU 3.0 + */ +class U_I18N_API CurrencyAmount: public Measure { + public: + /** + * Construct an object with the given numeric amount and the given + * ISO currency code. + * @param amount a numeric object; amount.isNumeric() must be TRUE + * @param isoCode the 3-letter ISO 4217 currency code; must not be + * NULL and must have length 3 + * @param ec input-output error code. If the amount or the isoCode + * is invalid, then this will be set to a failing value. + * @stable ICU 3.0 + */ + CurrencyAmount(const Formattable& amount, const UChar* isoCode, + UErrorCode &ec); + + /** + * Construct an object with the given numeric amount and the given + * ISO currency code. + * @param amount the amount of the given currency + * @param isoCode the 3-letter ISO 4217 currency code; must not be + * NULL and must have length 3 + * @param ec input-output error code. If the isoCode is invalid, + * then this will be set to a failing value. + * @stable ICU 3.0 + */ + CurrencyAmount(double amount, const UChar* isoCode, + UErrorCode &ec); + + /** + * Copy constructor + * @stable ICU 3.0 + */ + CurrencyAmount(const CurrencyAmount& other); + + /** + * Assignment operator + * @stable ICU 3.0 + */ + CurrencyAmount& operator=(const CurrencyAmount& other); + + /** + * Return a polymorphic clone of this object. The result will + * have the same class as returned by getDynamicClassID(). + * @stable ICU 3.0 + */ + virtual UObject* clone() const; + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~CurrencyAmount(); + + /** + * Returns a unique class ID for this object POLYMORPHICALLY. + * This method implements a simple form of RTTI used by ICU. + * @return The class ID for this object. All objects of a given + * class have the same class ID. Objects of other classes have + * different class IDs. + * @stable ICU 3.0 + */ + virtual UClassID getDynamicClassID() const; + + /** + * Returns the class ID for this class. This is used to compare to + * the return value of getDynamicClassID(). + * @return The class ID for all objects of this class. + * @stable ICU 3.0 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * Return the currency unit object of this object. + * @stable ICU 3.0 + */ + inline const CurrencyUnit& getCurrency() const; + + /** + * Return the ISO currency code of this object. + * @stable ICU 3.0 + */ + inline const UChar* getISOCurrency() const; +}; + +inline const CurrencyUnit& CurrencyAmount::getCurrency() const { + return (const CurrencyUnit&) getUnit(); +} + +inline const UChar* CurrencyAmount::getISOCurrency() const { + return getCurrency().getISOCurrency(); +} + +U_NAMESPACE_END + +#endif // !UCONFIG_NO_FORMATTING +#endif // __CURRENCYAMOUNT_H__ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/currunit.h b/Build/source/libs/icu-xetex/i18n/unicode/currunit.h new file mode 100644 index 00000000000..ecd94110292 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/currunit.h @@ -0,0 +1,117 @@ +/* +********************************************************************** +* Copyright (c) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: April 26, 2004 +* Since: ICU 3.0 +********************************************************************** +*/ +#ifndef __CURRENCYUNIT_H__ +#define __CURRENCYUNIT_H__ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/measunit.h" + +/** + * \file + * \brief C++ API: Currency Unit Information. + */ + +U_NAMESPACE_BEGIN + +/** + * A unit of currency, such as USD (U.S. dollars) or JPY (Japanese + * yen). This class is a thin wrapper over a UChar string that + * subclasses MeasureUnit, for use with Measure and MeasureFormat. + * + * @author Alan Liu + * @stable ICU 3.0 + */ +class U_I18N_API CurrencyUnit: public MeasureUnit { + public: + /** + * Construct an object with the given ISO currency code. + * @param isoCode the 3-letter ISO 4217 currency code; must not be + * NULL and must have length 3 + * @param ec input-output error code. If the isoCode is invalid, + * then this will be set to a failing value. + * @stable ICU 3.0 + */ + CurrencyUnit(const UChar* isoCode, UErrorCode &ec); + + /** + * Copy constructor + * @stable ICU 3.0 + */ + CurrencyUnit(const CurrencyUnit& other); + + /** + * Assignment operator + * @stable ICU 3.0 + */ + CurrencyUnit& operator=(const CurrencyUnit& other); + + /** + * Return a polymorphic clone of this object. The result will + * have the same class as returned by getDynamicClassID(). + * @stable ICU 3.0 + */ + virtual UObject* clone() const; + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~CurrencyUnit(); + + /** + * Equality operator. Return true if this object is equal + * to the given object. + * @stable ICU 3.0 + */ + UBool operator==(const UObject& other) const; + + /** + * Returns a unique class ID for this object POLYMORPHICALLY. + * This method implements a simple form of RTTI used by ICU. + * @return The class ID for this object. All objects of a given + * class have the same class ID. Objects of other classes have + * different class IDs. + * @stable ICU 3.0 + */ + virtual UClassID getDynamicClassID() const; + + /** + * Returns the class ID for this class. This is used to compare to + * the return value of getDynamicClassID(). + * @return The class ID for all objects of this class. + * @stable ICU 3.0 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * Return the ISO currency code of this object. + * @stable ICU 3.0 + */ + inline const UChar* getISOCurrency() const; + + private: + /** + * The ISO 4217 code of this object. + */ + UChar isoCode[4]; +}; + +inline const UChar* CurrencyUnit::getISOCurrency() const { + return isoCode; +} + +U_NAMESPACE_END + +#endif // !UCONFIG_NO_FORMATTING +#endif // __CURRENCYUNIT_H__ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/datefmt.h b/Build/source/libs/icu-xetex/i18n/unicode/datefmt.h new file mode 100644 index 00000000000..0022a99791b --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/datefmt.h @@ -0,0 +1,672 @@ +/* + ******************************************************************************** + * Copyright (C) 1997-2007, International Business Machines + * Corporation and others. All Rights Reserved. + ******************************************************************************** + * + * File DATEFMT.H + * + * Modification History: + * + * Date Name Description + * 02/19/97 aliu Converted from java. + * 04/01/97 aliu Added support for centuries. + * 07/23/98 stephen JDK 1.2 sync + * 11/15/99 weiv Added support for week of year/day of week formatting + ******************************************************************************** + */ + +#ifndef DATEFMT_H +#define DATEFMT_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/udat.h" +#include "unicode/calendar.h" +#include "unicode/numfmt.h" +#include "unicode/format.h" +#include "unicode/locid.h" + +/** + * \file + * \brief C++ API: Abstract class for converting dates. + */ + +U_NAMESPACE_BEGIN + +class TimeZone; + +/** + * DateFormat is an abstract class for a family of classes that convert dates and + * times from their internal representations to textual form and back again in a + * language-independent manner. Converting from the internal representation (milliseconds + * since midnight, January 1, 1970) to text is known as "formatting," and converting + * from text to millis is known as "parsing." We currently define only one concrete + * subclass of DateFormat: SimpleDateFormat, which can handle pretty much all normal + * date formatting and parsing actions. + * <P> + * DateFormat helps you to format and parse dates for any locale. Your code can + * be completely independent of the locale conventions for months, days of the + * week, or even the calendar format: lunar vs. solar. + * <P> + * To format a date for the current Locale, use one of the static factory + * methods: + * <pre> + * \code + * DateFormat* dfmt = DateFormat::createDateInstance(); + * UDate myDate = Calendar::getNow(); + * UnicodeString myString; + * myString = dfmt->format( myDate, myString ); + * \endcode + * </pre> + * If you are formatting multiple numbers, it is more efficient to get the + * format and use it multiple times so that the system doesn't have to fetch the + * information about the local language and country conventions multiple times. + * <pre> + * \code + * DateFormat* df = DateFormat::createDateInstance(); + * UnicodeString myString; + * UDate myDateArr[] = { 0.0, 100000000.0, 2000000000.0 }; // test values + * for (int32_t i = 0; i < 3; ++i) { + * myString.remove(); + * cout << df->format( myDateArr[i], myString ) << endl; + * } + * \endcode + * </pre> + * To get specific fields of a date, you can use UFieldPosition to + * get specific fields. + * <pre> + * \code + * DateFormat* dfmt = DateFormat::createDateInstance(); + * FieldPosition pos(DateFormat::YEAR_FIELD); + * UnicodeString myString; + * myString = dfmt->format( myDate, myString ); + * cout << myString << endl; + * cout << pos.getBeginIndex() << "," << pos. getEndIndex() << endl; + * \endcode + * </pre> + * To format a date for a different Locale, specify it in the call to + * createDateInstance(). + * <pre> + * \code + * DateFormat* df = + * DateFormat::createDateInstance( DateFormat::SHORT, Locale::getFrance()); + * \endcode + * </pre> + * You can use a DateFormat to parse also. + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * UDate myDate = df->parse(myString, status); + * \endcode + * </pre> + * Use createDateInstance() to produce the normal date format for that country. + * There are other static factory methods available. Use createTimeInstance() + * to produce the normal time format for that country. Use createDateTimeInstance() + * to produce a DateFormat that formats both date and time. You can pass in + * different options to these factory methods to control the length of the + * result; from SHORT to MEDIUM to LONG to FULL. The exact result depends on the + * locale, but generally: + * <ul type=round> + * <li> SHORT is completely numeric, such as 12/13/52 or 3:30pm + * <li> MEDIUM is longer, such as Jan 12, 1952 + * <li> LONG is longer, such as January 12, 1952 or 3:30:32pm + * <li> FULL is pretty completely specified, such as + * Tuesday, April 12, 1952 AD or 3:30:42pm PST. + * </ul> + * You can also set the time zone on the format if you wish. If you want even + * more control over the format or parsing, (or want to give your users more + * control), you can try casting the DateFormat you get from the factory methods + * to a SimpleDateFormat. This will work for the majority of countries; just + * remember to chck getDynamicClassID() before carrying out the cast. + * <P> + * You can also use forms of the parse and format methods with ParsePosition and + * FieldPosition to allow you to + * <ul type=round> + * <li> Progressively parse through pieces of a string. + * <li> Align any particular field, or find out where it is for selection + * on the screen. + * </ul> + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API DateFormat : public Format { +public: + + /** + * Constants for various style patterns. These reflect the order of items in + * the DateTimePatterns resource. There are 4 time patterns, 4 date patterns, + * and then the date-time pattern. Each block of 4 values in the resource occurs + * in the order full, long, medium, short. + * @stable ICU 2.4 + */ + enum EStyle + { + kNone = -1, + + kFull = 0, + kLong = 1, + kMedium = 2, + kShort = 3, + + kDateOffset = kShort + 1, + // kFull + kDateOffset = 4 + // kLong + kDateOffset = 5 + // kMedium + kDateOffset = 6 + // kShort + kDateOffset = 7 + + kDateTime = 8, + + + // relative dates + kRelative = (1 << 7), + + kFullRelative = (kFull | kRelative), + + kLongRelative = kLong | kRelative, + + kMediumRelative = kMedium | kRelative, + + kShortRelative = kShort | kRelative, + + + kDefault = kMedium, + + + + /** + * These constants are provided for backwards compatibility only. + * Please use the C++ style constants defined above. + */ + FULL = kFull, + LONG = kLong, + MEDIUM = kMedium, + SHORT = kShort, + DEFAULT = kDefault, + DATE_OFFSET = kDateOffset, + NONE = kNone, + DATE_TIME = kDateTime + }; + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~DateFormat(); + + /** + * Equality operator. Returns true if the two formats have the same behavior. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format&) const; + + /** + * Format an object to produce a string. This method handles Formattable + * objects with a UDate type. If a the Formattable object type is not a Date, + * then it returns a failing UErrorCode. + * + * @param obj The object to format. Must be a Date. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Output param filled with success/failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Formats a date into a date/time string. This is an abstract method which + * concrete subclasses must implement. + * <P> + * On input, the FieldPosition parameter may have its "field" member filled with + * an enum value specifying a field. On output, the FieldPosition will be filled + * in with the text offsets for that field. + * <P> For example, given a time text + * "1996.07.10 AD at 15:08:56 PDT", if the given fieldPosition.field is + * UDAT_YEAR_FIELD, the offsets fieldPosition.beginIndex and + * statfieldPositionus.getEndIndex will be set to 0 and 4, respectively. + * <P> Notice + * that if the same time field appears more than once in a pattern, the status will + * be set for the first occurence of that time field. For instance, + * formatting a UDate to the time string "1 PM PDT (Pacific Daylight Time)" + * using the pattern "h a z (zzzz)" and the alignment field + * DateFormat::TIMEZONE_FIELD, the offsets fieldPosition.beginIndex and + * fieldPosition.getEndIndex will be set to 5 and 8, respectively, for the first + * occurence of the timezone pattern character 'z'. + * + * @param cal Calendar set to the date and time to be formatted + * into a date/time string. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param fieldPosition On input: an alignment field, if desired (see examples above) + * On output: the offsets of the alignment field (see examples above) + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.1 + */ + virtual UnicodeString& format( Calendar& cal, + UnicodeString& appendTo, + FieldPosition& fieldPosition) const = 0; + + /** + * Formats a UDate into a date/time string. + * <P> + * On input, the FieldPosition parameter may have its "field" member filled with + * an enum value specifying a field. On output, the FieldPosition will be filled + * in with the text offsets for that field. + * <P> For example, given a time text + * "1996.07.10 AD at 15:08:56 PDT", if the given fieldPosition.field is + * UDAT_YEAR_FIELD, the offsets fieldPosition.beginIndex and + * statfieldPositionus.getEndIndex will be set to 0 and 4, respectively. + * <P> Notice + * that if the same time field appears more than once in a pattern, the status will + * be set for the first occurence of that time field. For instance, + * formatting a UDate to the time string "1 PM PDT (Pacific Daylight Time)" + * using the pattern "h a z (zzzz)" and the alignment field + * DateFormat::TIMEZONE_FIELD, the offsets fieldPosition.beginIndex and + * fieldPosition.getEndIndex will be set to 5 and 8, respectively, for the first + * occurence of the timezone pattern character 'z'. + * + * @param date UDate to be formatted into a date/time string. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param fieldPosition On input: an alignment field, if desired (see examples above) + * On output: the offsets of the alignment field (see examples above) + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( UDate date, + UnicodeString& appendTo, + FieldPosition& fieldPosition) const; + + /** + * Formats a UDate into a date/time string. If there is a problem, you won't + * know, using this method. Use the overloaded format() method which takes a + * FieldPosition& to detect formatting problems. + * + * @param date The UDate value to be formatted into a string. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(UDate date, UnicodeString& appendTo) const; + + /** + * Redeclared Format method. + * + * @param obj The object to be formatted into a string. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Output param filled with success/failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Parse a date/time string. + * + * @param text The string to be parsed into a UDate value. + * @param status Output param to be set to success/failure code. If + * 'text' cannot be parsed, it will be set to a failure + * code. + * @result The parsed UDate value, if successful. + * @stable ICU 2.0 + */ + virtual UDate parse( const UnicodeString& text, + UErrorCode& status) const; + + /** + * Parse a date/time string beginning at the given parse position. For + * example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date + * that is equivalent to Date(837039928046). + * <P> + * By default, parsing is lenient: If the input is not in the form used by + * this object's format method but can still be parsed as a date, then the + * parse succeeds. Clients may insist on strict adherence to the format by + * calling setLenient(false). + * + * @see DateFormat::setLenient(boolean) + * + * @param text The date/time string to be parsed + * @param cal a Calendar set to the date and time to be formatted + * into a date/time string. + * @param pos On input, the position at which to start parsing; on + * output, the position at which parsing terminated, or the + * start position if the parse failed. + * @return A valid UDate if the input could be parsed. + * @stable ICU 2.1 + */ + virtual void parse( const UnicodeString& text, + Calendar& cal, + ParsePosition& pos) const = 0; + + /** + * Parse a date/time string beginning at the given parse position. For + * example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date + * that is equivalent to Date(837039928046). + * <P> + * By default, parsing is lenient: If the input is not in the form used by + * this object's format method but can still be parsed as a date, then the + * parse succeeds. Clients may insist on strict adherence to the format by + * calling setLenient(false). + * + * @see DateFormat::setLenient(boolean) + * + * @param text The date/time string to be parsed + * @param pos On input, the position at which to start parsing; on + * output, the position at which parsing terminated, or the + * start position if the parse failed. + * @return A valid UDate if the input could be parsed. + * @stable ICU 2.0 + */ + UDate parse( const UnicodeString& text, + ParsePosition& pos) const; + + /** + * Parse a string to produce an object. This methods handles parsing of + * date/time strings into Formattable objects with UDate types. + * <P> + * Before calling, set parse_pos.index to the offset you want to start + * parsing at in the source. After calling, parse_pos.index is the end of + * the text you parsed. If error occurs, index is unchanged. + * <P> + * When parsing, leading whitespace is discarded (with a successful parse), + * while trailing whitespace is left as is. + * <P> + * See Format::parseObject() for more. + * + * @param source The string to be parsed into an object. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parse_pos The position to start parsing at. Upon return + * this param is set to the position after the + * last character successfully parsed. If the + * source is not parsed successfully, this param + * will remain unchanged. + * @return A newly created Formattable* object, or NULL + * on failure. The caller owns this and should + * delete it when done. + * @stable ICU 2.0 + */ + virtual void parseObject(const UnicodeString& source, + Formattable& result, + ParsePosition& parse_pos) const; + + /** + * Create a default date/time formatter that uses the SHORT style for both + * the date and the time. + * + * @return A date/time formatter which the caller owns. + * @stable ICU 2.0 + */ + static DateFormat* U_EXPORT2 createInstance(void); + + /** + * Creates a time formatter with the given formatting style for the given + * locale. + * + * @param style The given formatting style. For example, + * SHORT for "h:mm a" in the US locale. + * @param aLocale The given locale. + * @return A time formatter which the caller owns. + * @stable ICU 2.0 + */ + static DateFormat* U_EXPORT2 createTimeInstance(EStyle style = kDefault, + const Locale& aLocale = Locale::getDefault()); + + /** + * Creates a date formatter with the given formatting style for the given + * const locale. + * + * @param style The given formatting style. For example, + * SHORT for "M/d/yy" in the US locale. + * @param aLocale The given locale. + * @return A date formatter which the caller owns. + * @stable ICU 2.0 + */ + static DateFormat* U_EXPORT2 createDateInstance(EStyle style = kDefault, + const Locale& aLocale = Locale::getDefault()); + + /** + * Creates a date/time formatter with the given formatting styles for the + * given locale. + * + * @param dateStyle The given formatting style for the date portion of the result. + * For example, SHORT for "M/d/yy" in the US locale. + * @param timeStyle The given formatting style for the time portion of the result. + * For example, SHORT for "h:mm a" in the US locale. + * @param aLocale The given locale. + * @return A date/time formatter which the caller owns. + * @stable ICU 2.0 + */ + static DateFormat* U_EXPORT2 createDateTimeInstance(EStyle dateStyle = kDefault, + EStyle timeStyle = kDefault, + const Locale& aLocale = Locale::getDefault()); + + /** + * Gets the set of locales for which DateFormats are installed. + * @param count Filled in with the number of locales in the list that is returned. + * @return the set of locales for which DateFormats are installed. The caller + * does NOT own this list and must not delete it. + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + + /** + * Returns true if the formatter is set for lenient parsing. + * @stable ICU 2.0 + */ + virtual UBool isLenient(void) const; + + /** + * Specify whether or not date/time parsing is to be lenient. With lenient + * parsing, the parser may use heuristics to interpret inputs that do not + * precisely match this object's format. With strict parsing, inputs must + * match this object's format. + * + * @param lenient True specifies date/time interpretation to be lenient. + * @see Calendar::setLenient + * @stable ICU 2.0 + */ + virtual void setLenient(UBool lenient); + + /** + * Gets the calendar associated with this date/time formatter. + * @return the calendar associated with this date/time formatter. + * @stable ICU 2.0 + */ + virtual const Calendar* getCalendar(void) const; + + /** + * Set the calendar to be used by this date format. Initially, the default + * calendar for the specified or default locale is used. The caller should + * not delete the Calendar object after it is adopted by this call. + * Adopting a new calendar will change to the default symbols. + * + * @param calendarToAdopt Calendar object to be adopted. + * @stable ICU 2.0 + */ + virtual void adoptCalendar(Calendar* calendarToAdopt); + + /** + * Set the calendar to be used by this date format. Initially, the default + * calendar for the specified or default locale is used. + * + * @param newCalendar Calendar object to be set. + * @stable ICU 2.0 + */ + virtual void setCalendar(const Calendar& newCalendar); + + + /** + * Gets the number formatter which this date/time formatter uses to format + * and parse the numeric portions of the pattern. + * @return the number formatter which this date/time formatter uses. + * @stable ICU 2.0 + */ + virtual const NumberFormat* getNumberFormat(void) const; + + /** + * Allows you to set the number formatter. The caller should + * not delete the NumberFormat object after it is adopted by this call. + * @param formatToAdopt NumberFormat object to be adopted. + * @stable ICU 2.0 + */ + virtual void adoptNumberFormat(NumberFormat* formatToAdopt); + + /** + * Allows you to set the number formatter. + * @param newNumberFormat NumberFormat object to be set. + * @stable ICU 2.0 + */ + virtual void setNumberFormat(const NumberFormat& newNumberFormat); + + /** + * Returns a reference to the TimeZone used by this DateFormat's calendar. + * @return the time zone associated with the calendar of DateFormat. + * @stable ICU 2.0 + */ + virtual const TimeZone& getTimeZone(void) const; + + /** + * Sets the time zone for the calendar of this DateFormat object. The caller + * no longer owns the TimeZone object and should not delete it after this call. + * @param zoneToAdopt the TimeZone to be adopted. + * @stable ICU 2.0 + */ + virtual void adoptTimeZone(TimeZone* zoneToAdopt); + + /** + * Sets the time zone for the calendar of this DateFormat object. + * @param zone the new time zone. + * @stable ICU 2.0 + */ + virtual void setTimeZone(const TimeZone& zone); + +protected: + /** + * Default constructor. Creates a DateFormat with no Calendar or NumberFormat + * associated with it. This constructor depends on the subclasses to fill in + * the calendar and numberFormat fields. + * @stable ICU 2.0 + */ + DateFormat(); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + DateFormat(const DateFormat&); + + /** + * Default assignment operator. + * @stable ICU 2.0 + */ + DateFormat& operator=(const DateFormat&); + + /** + * The calendar that DateFormat uses to produce the time field values needed + * to implement date/time formatting. Subclasses should generally initialize + * this to the default calendar for the locale associated with this DateFormat. + * @stable ICU 2.4 + */ + Calendar* fCalendar; + + /** + * The number formatter that DateFormat uses to format numbers in dates and + * times. Subclasses should generally initialize this to the default number + * format for the locale associated with this DateFormat. + * @stable ICU 2.4 + */ + NumberFormat* fNumberFormat; + +private: + /** + * Gets the date/time formatter with the given formatting styles for the + * given locale. + * @param dateStyle the given date formatting style. + * @param timeStyle the given time formatting style. + * @param inLocale the given locale. + * @return a date/time formatter, or 0 on failure. + */ + static DateFormat* U_EXPORT2 create(EStyle timeStyle, EStyle dateStyle, const Locale&); + +public: + /** + * Field selector for FieldPosition for DateFormat fields. + * @obsolete ICU 3.4 use UDateFormatField instead, since this API will be + * removed in that release + */ + enum EField + { + // Obsolete; use UDateFormatField instead + kEraField = UDAT_ERA_FIELD, + kYearField = UDAT_YEAR_FIELD, + kMonthField = UDAT_MONTH_FIELD, + kDateField = UDAT_DATE_FIELD, + kHourOfDay1Field = UDAT_HOUR_OF_DAY1_FIELD, + kHourOfDay0Field = UDAT_HOUR_OF_DAY0_FIELD, + kMinuteField = UDAT_MINUTE_FIELD, + kSecondField = UDAT_SECOND_FIELD, + kMillisecondField = UDAT_FRACTIONAL_SECOND_FIELD, + kDayOfWeekField = UDAT_DAY_OF_WEEK_FIELD, + kDayOfYearField = UDAT_DAY_OF_YEAR_FIELD, + kDayOfWeekInMonthField = UDAT_DAY_OF_WEEK_IN_MONTH_FIELD, + kWeekOfYearField = UDAT_WEEK_OF_YEAR_FIELD, + kWeekOfMonthField = UDAT_WEEK_OF_MONTH_FIELD, + kAmPmField = UDAT_AM_PM_FIELD, + kHour1Field = UDAT_HOUR1_FIELD, + kHour0Field = UDAT_HOUR0_FIELD, + kTimezoneField = UDAT_TIMEZONE_FIELD, + kYearWOYField = UDAT_YEAR_WOY_FIELD, + kDOWLocalField = UDAT_DOW_LOCAL_FIELD, + kExtendedYearField = UDAT_EXTENDED_YEAR_FIELD, + kJulianDayField = UDAT_JULIAN_DAY_FIELD, + kMillisecondsInDayField = UDAT_MILLISECONDS_IN_DAY_FIELD, + + // Obsolete; use UDateFormatField instead + ERA_FIELD = UDAT_ERA_FIELD, + YEAR_FIELD = UDAT_YEAR_FIELD, + MONTH_FIELD = UDAT_MONTH_FIELD, + DATE_FIELD = UDAT_DATE_FIELD, + HOUR_OF_DAY1_FIELD = UDAT_HOUR_OF_DAY1_FIELD, + HOUR_OF_DAY0_FIELD = UDAT_HOUR_OF_DAY0_FIELD, + MINUTE_FIELD = UDAT_MINUTE_FIELD, + SECOND_FIELD = UDAT_SECOND_FIELD, + MILLISECOND_FIELD = UDAT_FRACTIONAL_SECOND_FIELD, + DAY_OF_WEEK_FIELD = UDAT_DAY_OF_WEEK_FIELD, + DAY_OF_YEAR_FIELD = UDAT_DAY_OF_YEAR_FIELD, + DAY_OF_WEEK_IN_MONTH_FIELD = UDAT_DAY_OF_WEEK_IN_MONTH_FIELD, + WEEK_OF_YEAR_FIELD = UDAT_WEEK_OF_YEAR_FIELD, + WEEK_OF_MONTH_FIELD = UDAT_WEEK_OF_MONTH_FIELD, + AM_PM_FIELD = UDAT_AM_PM_FIELD, + HOUR1_FIELD = UDAT_HOUR1_FIELD, + HOUR0_FIELD = UDAT_HOUR0_FIELD, + TIMEZONE_FIELD = UDAT_TIMEZONE_FIELD + }; +}; + +inline UnicodeString& +DateFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + return Format::format(obj, appendTo, status); +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _DATEFMT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/dcfmtsym.h b/Build/source/libs/icu-xetex/i18n/unicode/dcfmtsym.h new file mode 100644 index 00000000000..bc5547d4cdd --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/dcfmtsym.h @@ -0,0 +1,370 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2007, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File DCFMTSYM.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/18/97 clhuang Updated per C++ implementation. +* 03/27/97 helena Updated to pass the simple test after code review. +* 08/26/97 aliu Added currency/intl currency symbol support. +* 07/22/98 stephen Changed to match C++ style +* currencySymbol -> fCurrencySymbol +* Constants changed from CAPS to kCaps +* 06/24/99 helena Integrated Alan's NF enhancements and Java2 bug fixes +* 09/22/00 grhoten Marked deprecation tags with a pointer to replacement +* functions. +******************************************************************************** +*/ + +#ifndef DCFMTSYM_H +#define DCFMTSYM_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" +#include "unicode/locid.h" + +/** + * \file + * \brief C++ API: Symbols for formatting numbers. + */ + + +U_NAMESPACE_BEGIN + +/** + * This class represents the set of symbols needed by DecimalFormat + * to format numbers. DecimalFormat creates for itself an instance of + * DecimalFormatSymbols from its locale data. If you need to change any + * of these symbols, you can get the DecimalFormatSymbols object from + * your DecimalFormat and modify it. + * <P> + * Here are the special characters used in the parts of the + * subpattern, with notes on their usage. + * <pre> + * \code + * Symbol Meaning + * 0 a digit + * # a digit, zero shows as absent + * . placeholder for decimal separator + * , placeholder for grouping separator. + * ; separates formats. + * - default negative prefix. + * % divide by 100 and show as percentage + * X any other characters can be used in the prefix or suffix + * ' used to quote special characters in a prefix or suffix. + * \endcode + * </pre> + * [Notes] + * <P> + * If there is no explicit negative subpattern, - is prefixed to the + * positive form. That is, "0.00" alone is equivalent to "0.00;-0.00". + * <P> + * The grouping separator is commonly used for thousands, but in some + * countries for ten-thousands. The interval is a constant number of + * digits between the grouping characters, such as 100,000,000 or 1,0000,0000. + * If you supply a pattern with multiple grouping characters, the interval + * between the last one and the end of the integer is the one that is + * used. So "#,##,###,####" == "######,####" == "##,####,####". + * <P> + * This class only handles localized digits where the 10 digits are + * contiguous in Unicode, from 0 to 9. Other digits sets (such as + * superscripts) would need a different subclass. + */ +class U_I18N_API DecimalFormatSymbols : public UObject { +public: + /** + * Constants for specifying a number format symbol. + * @stable ICU 2.0 + */ + enum ENumberFormatSymbol { + /** The decimal separator */ + kDecimalSeparatorSymbol, + /** The grouping separator */ + kGroupingSeparatorSymbol, + /** The pattern separator */ + kPatternSeparatorSymbol, + /** The percent sign */ + kPercentSymbol, + /** Zero*/ + kZeroDigitSymbol, + /** Character representing a digit in the pattern */ + kDigitSymbol, + /** The minus sign */ + kMinusSignSymbol, + /** The plus sign */ + kPlusSignSymbol, + /** The currency symbol */ + kCurrencySymbol, + /** The international currency symbol */ + kIntlCurrencySymbol, + /** The monetary separator */ + kMonetarySeparatorSymbol, + /** The exponential symbol */ + kExponentialSymbol, + /** Per mill symbol - replaces kPermillSymbol */ + kPerMillSymbol, + /** Escape padding character */ + kPadEscapeSymbol, + /** Infinity symbol */ + kInfinitySymbol, + /** Nan symbol */ + kNaNSymbol, + /** Significant digit symbol + * @stable ICU 3.0 */ + kSignificantDigitSymbol, + /** The monetary grouping separator + * @stable ICU 3.6 + */ + kMonetaryGroupingSeparatorSymbol, + /** count symbol constants */ + kFormatSymbolCount + }; + + /** + * Create a DecimalFormatSymbols object for the given locale. + * + * @param locale The locale to get symbols for. + * @param status Input/output parameter, set to success or + * failure code upon return. + * @stable ICU 2.0 + */ + DecimalFormatSymbols(const Locale& locale, UErrorCode& status); + + /** + * Create a DecimalFormatSymbols object for the default locale. + * This constructor will not fail. If the resource file data is + * not available, it will use hard-coded last-resort data and + * set status to U_USING_FALLBACK_ERROR. + * + * @param status Input/output parameter, set to success or + * failure code upon return. + * @stable ICU 2.0 + */ + DecimalFormatSymbols( UErrorCode& status); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + DecimalFormatSymbols(const DecimalFormatSymbols&); + + /** + * Assignment operator. + * @stable ICU 2.0 + */ + DecimalFormatSymbols& operator=(const DecimalFormatSymbols&); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~DecimalFormatSymbols(); + + /** + * Return true if another object is semantically equal to this one. + * + * @param other the object to be compared with. + * @return true if another object is semantically equal to this one. + * @stable ICU 2.0 + */ + UBool operator==(const DecimalFormatSymbols& other) const; + + /** + * Return true if another object is semantically unequal to this one. + * + * @param other the object to be compared with. + * @return true if another object is semantically unequal to this one. + * @stable ICU 2.0 + */ + UBool operator!=(const DecimalFormatSymbols& other) const { return !operator==(other); } + + /** + * Get one of the format symbols by its enum constant. + * Each symbol is stored as a string so that graphemes + * (characters with modifyer letters) can be used. + * + * @param symbol Constant to indicate a number format symbol. + * @return the format symbols by the param 'symbol' + * @stable ICU 2.0 + */ + inline UnicodeString getSymbol(ENumberFormatSymbol symbol) const; + + /** + * Set one of the format symbols by its enum constant. + * Each symbol is stored as a string so that graphemes + * (characters with modifyer letters) can be used. + * + * @param symbol Constant to indicate a number format symbol. + * @param value value of the format sybmol + * @stable ICU 2.0 + */ + void setSymbol(ENumberFormatSymbol symbol, const UnicodeString &value); + + /** + * Returns the locale for which this object was constructed. + * @stable ICU 2.6 + */ + inline Locale getLocale() const; + + /** + * Returns the locale for this object. Two flavors are available: + * valid and actual locale. + * @stable ICU 2.8 + */ + Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + DecimalFormatSymbols(); // default constructor not implemented + + /** + * Initializes the symbols from the LocaleElements resource bundle. + * Note: The organization of LocaleElements badly needs to be + * cleaned up. + * + * @param locale The locale to get symbols for. + * @param success Input/output parameter, set to success or + * failure code upon return. + * @param useLastResortData determine if use last resort data + */ + void initialize(const Locale& locale, UErrorCode& success, UBool useLastResortData = FALSE); + + /** + * Initialize the symbols from the given array of UnicodeStrings. + * The array must be of the correct size. + * + * @param numberElements the number format symbols + * @param numberElementsLength length of numberElements + */ + void initialize(const UChar** numberElements, int32_t *numberElementsStrLen, int32_t numberElementsLength); + + /** + * Initialize the symbols with default values. + */ + void initialize(); + + void setCurrencyForSymbols(); + +public: + /** + * _Internal_ function - more efficient version of getSymbol, + * returning a const reference to one of the symbol strings. + * The returned reference becomes invalid when the symbol is changed + * or when the DecimalFormatSymbols are destroyed. + * ### TODO markus 2002oct11: Consider proposing getConstSymbol() to be really public. + * + * @param symbol Constant to indicate a number format symbol. + * @return the format symbol by the param 'symbol' + * @internal + */ + inline const UnicodeString &getConstSymbol(ENumberFormatSymbol symbol) const; + + /** + * Returns that pattern stored in currecy info. Internal API for use by NumberFormat API. + * @internal + */ + inline const UChar* getCurrencyPattern(void) const; + +private: + /** + * Private symbol strings. + * They are either loaded from a resource bundle or otherwise owned. + * setSymbol() clones the symbol string. + * Readonly aliases can only come from a resource bundle, so that we can always + * use fastCopyFrom() with them. + * + * If DecimalFormatSymbols becomes subclassable and the status of fSymbols changes + * from private to protected, + * or when fSymbols can be set any other way that allows them to be readonly aliases + * to non-resource bundle strings, + * then regular UnicodeString copies must be used instead of fastCopyFrom(). + * + * @internal + */ + UnicodeString fSymbols[kFormatSymbolCount]; + + /** + * Non-symbol variable for getConstSymbol(). Always empty. + * @internal + */ + UnicodeString fNoSymbol; + + Locale locale; + + char actualLocale[ULOC_FULLNAME_CAPACITY]; + char validLocale[ULOC_FULLNAME_CAPACITY]; + const UChar* currPattern; +}; + +// ------------------------------------- + +inline UnicodeString +DecimalFormatSymbols::getSymbol(ENumberFormatSymbol symbol) const { + const UnicodeString *strPtr; + if(symbol < kFormatSymbolCount) { + strPtr = &fSymbols[symbol]; + } else { + strPtr = &fNoSymbol; + } + return *strPtr; +} + +inline const UnicodeString & +DecimalFormatSymbols::getConstSymbol(ENumberFormatSymbol symbol) const { + const UnicodeString *strPtr; + if(symbol < kFormatSymbolCount) { + strPtr = &fSymbols[symbol]; + } else { + strPtr = &fNoSymbol; + } + return *strPtr; +} + +// ------------------------------------- + +inline void +DecimalFormatSymbols::setSymbol(ENumberFormatSymbol symbol, const UnicodeString &value) { + if(symbol<kFormatSymbolCount) { + fSymbols[symbol]=value; + } +} + +// ------------------------------------- + +inline Locale +DecimalFormatSymbols::getLocale() const { + return locale; +} + +inline const UChar* +DecimalFormatSymbols::getCurrencyPattern() const { + return currPattern; +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _DCFMTSYM +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/decimfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/decimfmt.h new file mode 100644 index 00000000000..296906fb7d7 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/decimfmt.h @@ -0,0 +1,1902 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2006, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File DECIMFMT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/20/97 clhuang Updated per C++ implementation. +* 04/03/97 aliu Rewrote parsing and formatting completely, and +* cleaned up and debugged. Actually works now. +* 04/17/97 aliu Changed DigitCount to int per code review. +* 07/10/97 helena Made ParsePosition a class and get rid of the function +* hiding problems. +* 09/09/97 aliu Ported over support for exponential formats. +* 07/20/98 stephen Changed documentation +******************************************************************************** +*/ + +#ifndef DECIMFMT_H +#define DECIMFMT_H + +#include "unicode/utypes.h" +/** + * \file + * \brief C++ API: Formats decimal numbers. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/dcfmtsym.h" +#include "unicode/numfmt.h" +#include "unicode/locid.h" + +U_NAMESPACE_BEGIN + +class DigitList; +class ChoiceFormat; + +/** + * DecimalFormat is a concrete subclass of NumberFormat that formats decimal + * numbers. It has a variety of features designed to make it possible to parse + * and format numbers in any locale, including support for Western, Arabic, or + * Indic digits. It also supports different flavors of numbers, including + * integers ("123"), fixed-point numbers ("123.4"), scientific notation + * ("1.23E4"), percentages ("12%"), and currency amounts ("$123"). All of these + * flavors can be easily localized. + * + * <p>To obtain a NumberFormat for a specific locale (including the default + * locale) call one of NumberFormat's factory methods such as + * createInstance(). Do not call the DecimalFormat constructors directly, unless + * you know what you are doing, since the NumberFormat factory methods may + * return subclasses other than DecimalFormat. + * + * <p><strong>Example Usage</strong> + * + * \code + * // Normally we would have a GUI with a menu for this + * int32_t locCount; + * const Locale* locales = NumberFormat::getAvailableLocales(locCount); + * + * double myNumber = -1234.56; + * UErrorCode success = U_ZERO_ERROR; + * NumberFormat* form; + * + * // Print out a number with the localized number, currency and percent + * // format for each locale. + * UnicodeString countryName; + * UnicodeString displayName; + * UnicodeString str; + * UnicodeString pattern; + * Formattable fmtable; + * for (int32_t j = 0; j < 3; ++j) { + * cout << endl << "FORMAT " << j << endl; + * for (int32_t i = 0; i < locCount; ++i) { + * if (locales[i].getCountry(countryName).size() == 0) { + * // skip language-only + * continue; + * } + * switch (j) { + * case 0: + * form = NumberFormat::createInstance(locales[i], success ); break; + * case 1: + * form = NumberFormat::createCurrencyInstance(locales[i], success ); break; + * default: + * form = NumberFormat::createPercentInstance(locales[i], success ); break; + * } + * if (form) { + * str.remove(); + * pattern = ((DecimalFormat*)form)->toPattern(pattern); + * cout << locales[i].getDisplayName(displayName) << ": " << pattern; + * cout << " -> " << form->format(myNumber,str) << endl; + * form->parse(form->format(myNumber,str), fmtable, success); + * delete form; + * } + * } + * } + * \endcode + * + * <p><strong>Patterns</strong> + * + * <p>A DecimalFormat consists of a <em>pattern</em> and a set of + * <em>symbols</em>. The pattern may be set directly using + * applyPattern(), or indirectly using other API methods which + * manipulate aspects of the pattern, such as the minimum number of integer + * digits. The symbols are stored in a DecimalFormatSymbols + * object. When using the NumberFormat factory methods, the + * pattern and symbols are read from ICU's locale data. + * + * <p><strong>Special Pattern Characters</strong> + * + * <p>Many characters in a pattern are taken literally; they are matched during + * parsing and output unchanged during formatting. Special characters, on the + * other hand, stand for other characters, strings, or classes of characters. + * For example, the '#' character is replaced by a localized digit. Often the + * replacement character is the same as the pattern character; in the U.S. locale, + * the ',' grouping character is replaced by ','. However, the replacement is + * still happening, and if the symbols are modified, the grouping character + * changes. Some special characters affect the behavior of the formatter by + * their presence; for example, if the percent character is seen, then the + * value is multiplied by 100 before being displayed. + * + * <p>To insert a special character in a pattern as a literal, that is, without + * any special meaning, the character must be quoted. There are some exceptions to + * this which are noted below. + * + * <p>The characters listed here are used in non-localized patterns. Localized + * patterns use the corresponding characters taken from this formatter's + * DecimalFormatSymbols object instead, and these characters lose + * their special status. Two exceptions are the currency sign and quote, which + * are not localized. + * + * <table border=0 cellspacing=3 cellpadding=0> + * <tr bgcolor="#ccccff"> + * <td align=left><strong>Symbol</strong> + * <td align=left><strong>Location</strong> + * <td align=left><strong>Localized?</strong> + * <td align=left><strong>Meaning</strong> + * <tr valign=top> + * <td><code>0</code> + * <td>Number + * <td>Yes + * <td>Digit + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>1-9</code> + * <td>Number + * <td>Yes + * <td>'1' through '9' indicate rounding. + * <tr valign=top> + * <td><code>\htmlonly@\endhtmlonly</code> <!--doxygen doesn't like @--> + * <td>Number + * <td>No + * <td>Significant digit + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>#</code> + * <td>Number + * <td>Yes + * <td>Digit, zero shows as absent + * <tr valign=top> + * <td><code>.</code> + * <td>Number + * <td>Yes + * <td>Decimal separator or monetary decimal separator + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>-</code> + * <td>Number + * <td>Yes + * <td>Minus sign + * <tr valign=top> + * <td><code>,</code> + * <td>Number + * <td>Yes + * <td>Grouping separator + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>E</code> + * <td>Number + * <td>Yes + * <td>Separates mantissa and exponent in scientific notation. + * <em>Need not be quoted in prefix or suffix.</em> + * <tr valign=top> + * <td><code>+</code> + * <td>Exponent + * <td>Yes + * <td>Prefix positive exponents with localized plus sign. + * <em>Need not be quoted in prefix or suffix.</em> + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>;</code> + * <td>Subpattern boundary + * <td>Yes + * <td>Separates positive and negative subpatterns + * <tr valign=top> + * <td><code>\%</code> + * <td>Prefix or suffix + * <td>Yes + * <td>Multiply by 100 and show as percentage + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>\\u2030</code> + * <td>Prefix or suffix + * <td>Yes + * <td>Multiply by 1000 and show as per mille + * <tr valign=top> + * <td><code>\htmlonly¤\endhtmlonly</code> (<code>\\u00A4</code>) + * <td>Prefix or suffix + * <td>No + * <td>Currency sign, replaced by currency symbol. If + * doubled, replaced by international currency symbol. + * If present in a pattern, the monetary decimal separator + * is used instead of the decimal separator. + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>'</code> + * <td>Prefix or suffix + * <td>No + * <td>Used to quote special characters in a prefix or suffix, + * for example, <code>"'#'#"</code> formats 123 to + * <code>"#123"</code>. To create a single quote + * itself, use two in a row: <code>"# o''clock"</code>. + * <tr valign=top> + * <td><code>*</code> + * <td>Prefix or suffix boundary + * <td>Yes + * <td>Pad escape, precedes pad character + * </table> + * + * <p>A DecimalFormat pattern contains a postive and negative + * subpattern, for example, "#,##0.00;(#,##0.00)". Each subpattern has a + * prefix, a numeric part, and a suffix. If there is no explicit negative + * subpattern, the negative subpattern is the localized minus sign prefixed to the + * positive subpattern. That is, "0.00" alone is equivalent to "0.00;-0.00". If there + * is an explicit negative subpattern, it serves only to specify the negative + * prefix and suffix; the number of digits, minimal digits, and other + * characteristics are ignored in the negative subpattern. That means that + * "#,##0.0#;(#)" has precisely the same result as "#,##0.0#;(#,##0.0#)". + * + * <p>The prefixes, suffixes, and various symbols used for infinity, digits, + * thousands separators, decimal separators, etc. may be set to arbitrary + * values, and they will appear properly during formatting. However, care must + * be taken that the symbols and strings do not conflict, or parsing will be + * unreliable. For example, either the positive and negative prefixes or the + * suffixes must be distinct for parse() to be able + * to distinguish positive from negative values. Another example is that the + * decimal separator and thousands separator should be distinct characters, or + * parsing will be impossible. + * + * <p>The <em>grouping separator</em> is a character that separates clusters of + * integer digits to make large numbers more legible. It commonly used for + * thousands, but in some locales it separates ten-thousands. The <em>grouping + * size</em> is the number of digits between the grouping separators, such as 3 + * for "100,000,000" or 4 for "1 0000 0000". There are actually two different + * grouping sizes: One used for the least significant integer digits, the + * <em>primary grouping size</em>, and one used for all others, the + * <em>secondary grouping size</em>. In most locales these are the same, but + * sometimes they are different. For example, if the primary grouping interval + * is 3, and the secondary is 2, then this corresponds to the pattern + * "#,##,##0", and the number 123456789 is formatted as "12,34,56,789". If a + * pattern contains multiple grouping separators, the interval between the last + * one and the end of the integer defines the primary grouping size, and the + * interval between the last two defines the secondary grouping size. All others + * are ignored, so "#,##,###,####" == "###,###,####" == "##,#,###,####". + * + * <p>Illegal patterns, such as "#.#.#" or "#.###,###", will cause + * DecimalFormat to set a failing UErrorCode. + * + * <p><strong>Pattern BNF</strong> + * + * <pre> + * pattern := subpattern (';' subpattern)? + * subpattern := prefix? number exponent? suffix? + * number := (integer ('.' fraction)?) | sigDigits + * prefix := '\\u0000'..'\\uFFFD' - specialCharacters + * suffix := '\\u0000'..'\\uFFFD' - specialCharacters + * integer := '#'* '0'* '0' + * fraction := '0'* '#'* + * sigDigits := '#'* '@' '@'* '#'* + * exponent := 'E' '+'? '0'* '0' + * padSpec := '*' padChar + * padChar := '\\u0000'..'\\uFFFD' - quote + * + * Notation: + * X* 0 or more instances of X + * X? 0 or 1 instances of X + * X|Y either X or Y + * C..D any character from C up to D, inclusive + * S-T characters in S, except those in T + * </pre> + * The first subpattern is for positive numbers. The second (optional) + * subpattern is for negative numbers. + * + * <p>Not indicated in the BNF syntax above: + * + * <ul><li>The grouping separator ',' can occur inside the integer and + * sigDigits elements, between any two pattern characters of that + * element, as long as the integer or sigDigits element is not + * followed by the exponent element. + * + * <li>Two grouping intervals are recognized: That between the + * decimal point and the first grouping symbol, and that + * between the first and second grouping symbols. These + * intervals are identical in most locales, but in some + * locales they differ. For example, the pattern + * "#,##,###" formats the number 123456789 as + * "12,34,56,789".</li> + * + * <li>The pad specifier <code>padSpec</code> may appear before the prefix, + * after the prefix, before the suffix, after the suffix, or not at all. + * + * <li>In place of '0', the digits '1' through '9' may be used to + * indicate a rounding increment. + * </ul> + * + * <p><strong>Parsing</strong> + * + * <p>DecimalFormat parses all Unicode characters that represent + * decimal digits, as defined by u_charDigitValue(). In addition, + * DecimalFormat also recognizes as digits the ten consecutive + * characters starting with the localized zero digit defined in the + * DecimalFormatSymbols object. During formatting, the + * DecimalFormatSymbols-based digits are output. + * + * <p>During parsing, grouping separators are ignored. + * + * <p>If parse(UnicodeString&,Formattable&,ParsePosition&) + * fails to parse a string, it leaves the parse position unchanged. + * The convenience method parse(UnicodeString&,Formattable&,UErrorCode&) + * indicates parse failure by setting a failing + * UErrorCode. + * + * <p><strong>Formatting</strong> + * + * <p>Formatting is guided by several parameters, all of which can be + * specified either using a pattern or using the API. The following + * description applies to formats that do not use <a href="#sci">scientific + * notation</a> or <a href="#sigdig">significant digits</a>. + * + * <ul><li>If the number of actual integer digits exceeds the + * <em>maximum integer digits</em>, then only the least significant + * digits are shown. For example, 1997 is formatted as "97" if the + * maximum integer digits is set to 2. + * + * <li>If the number of actual integer digits is less than the + * <em>minimum integer digits</em>, then leading zeros are added. For + * example, 1997 is formatted as "01997" if the minimum integer digits + * is set to 5. + * + * <li>If the number of actual fraction digits exceeds the <em>maximum + * fraction digits</em>, then half-even rounding it performed to the + * maximum fraction digits. For example, 0.125 is formatted as "0.12" + * if the maximum fraction digits is 2. This behavior can be changed + * by specifying a rounding increment and a rounding mode. + * + * <li>If the number of actual fraction digits is less than the + * <em>minimum fraction digits</em>, then trailing zeros are added. + * For example, 0.125 is formatted as "0.1250" if the mimimum fraction + * digits is set to 4. + * + * <li>Trailing fractional zeros are not displayed if they occur + * <em>j</em> positions after the decimal, where <em>j</em> is less + * than the maximum fraction digits. For example, 0.10004 is + * formatted as "0.1" if the maximum fraction digits is four or less. + * </ul> + * + * <p><strong>Special Values</strong> + * + * <p><code>NaN</code> is represented as a single character, typically + * <code>\\uFFFD</code>. This character is determined by the + * DecimalFormatSymbols object. This is the only value for which + * the prefixes and suffixes are not used. + * + * <p>Infinity is represented as a single character, typically + * <code>\\u221E</code>, with the positive or negative prefixes and suffixes + * applied. The infinity character is determined by the + * DecimalFormatSymbols object. + * + * <a name="sci"><strong>Scientific Notation</strong></a> + * + * <p>Numbers in scientific notation are expressed as the product of a mantissa + * and a power of ten, for example, 1234 can be expressed as 1.234 x 10<sup>3</sup>. The + * mantissa is typically in the half-open interval [1.0, 10.0) or sometimes [0.0, 1.0), + * but it need not be. DecimalFormat supports arbitrary mantissas. + * DecimalFormat can be instructed to use scientific + * notation through the API or through the pattern. In a pattern, the exponent + * character immediately followed by one or more digit characters indicates + * scientific notation. Example: "0.###E0" formats the number 1234 as + * "1.234E3". + * + * <ul> + * <li>The number of digit characters after the exponent character gives the + * minimum exponent digit count. There is no maximum. Negative exponents are + * formatted using the localized minus sign, <em>not</em> the prefix and suffix + * from the pattern. This allows patterns such as "0.###E0 m/s". To prefix + * positive exponents with a localized plus sign, specify '+' between the + * exponent and the digits: "0.###E+0" will produce formats "1E+1", "1E+0", + * "1E-1", etc. (In localized patterns, use the localized plus sign rather than + * '+'.) + * + * <li>The minimum number of integer digits is achieved by adjusting the + * exponent. Example: 0.00123 formatted with "00.###E0" yields "12.3E-4". This + * only happens if there is no maximum number of integer digits. If there is a + * maximum, then the minimum number of integer digits is fixed at one. + * + * <li>The maximum number of integer digits, if present, specifies the exponent + * grouping. The most common use of this is to generate <em>engineering + * notation</em>, in which the exponent is a multiple of three, e.g., + * "##0.###E0". The number 12345 is formatted using "##0.####E0" as "12.345E3". + * + * <li>When using scientific notation, the formatter controls the + * digit counts using significant digits logic. The maximum number of + * significant digits limits the total number of integer and fraction + * digits that will be shown in the mantissa; it does not affect + * parsing. For example, 12345 formatted with "##0.##E0" is "12.3E3". + * See the section on significant digits for more details. + * + * <li>The number of significant digits shown is determined as + * follows: If areSignificantDigitsUsed() returns false, then the + * minimum number of significant digits shown is one, and the maximum + * number of significant digits shown is the sum of the <em>minimum + * integer</em> and <em>maximum fraction</em> digits, and is + * unaffected by the maximum integer digits. If this sum is zero, + * then all significant digits are shown. If + * areSignificantDigitsUsed() returns true, then the significant digit + * counts are specified by getMinimumSignificantDigits() and + * getMaximumSignificantDigits(). In this case, the number of + * integer digits is fixed at one, and there is no exponent grouping. + * + * <li>Exponential patterns may not contain grouping separators. + * </ul> + * + * <a name="sigdig"><strong>Significant Digits</strong></a> + * + * <code>DecimalFormat</code> has two ways of controlling how many + * digits are shows: (a) significant digits counts, or (b) integer and + * fraction digit counts. Integer and fraction digit counts are + * described above. When a formatter is using significant digits + * counts, the number of integer and fraction digits is not specified + * directly, and the formatter settings for these counts are ignored. + * Instead, the formatter uses however many integer and fraction + * digits are required to display the specified number of significant + * digits. Examples: + * + * <table border=0 cellspacing=3 cellpadding=0> + * <tr bgcolor="#ccccff"> + * <td align=left>Pattern + * <td align=left>Minimum significant digits + * <td align=left>Maximum significant digits + * <td align=left>Number + * <td align=left>Output of format() + * <tr valign=top> + * <td><code>\@\@\@</code> + * <td>3 + * <td>3 + * <td>12345 + * <td><code>12300</code> + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>\@\@\@</code> + * <td>3 + * <td>3 + * <td>0.12345 + * <td><code>0.123</code> + * <tr valign=top> + * <td><code>\@\@##</code> + * <td>2 + * <td>4 + * <td>3.14159 + * <td><code>3.142</code> + * <tr valign=top bgcolor="#eeeeff"> + * <td><code>\@\@##</code> + * <td>2 + * <td>4 + * <td>1.23004 + * <td><code>1.23</code> + * </table> + * + * <ul> + * <li>Significant digit counts may be expressed using patterns that + * specify a minimum and maximum number of significant digits. These + * are indicated by the <code>'@'</code> and <code>'#'</code> + * characters. The minimum number of significant digits is the number + * of <code>'@'</code> characters. The maximum number of significant + * digits is the number of <code>'@'</code> characters plus the number + * of <code>'#'</code> characters following on the right. For + * example, the pattern <code>"@@@"</code> indicates exactly 3 + * significant digits. The pattern <code>"@##"</code> indicates from + * 1 to 3 significant digits. Trailing zero digits to the right of + * the decimal separator are suppressed after the minimum number of + * significant digits have been shown. For example, the pattern + * <code>"@##"</code> formats the number 0.1203 as + * <code>"0.12"</code>. + * + * <li>If a pattern uses significant digits, it may not contain a + * decimal separator, nor the <code>'0'</code> pattern character. + * Patterns such as <code>"@00"</code> or <code>"@.###"</code> are + * disallowed. + * + * <li>Any number of <code>'#'</code> characters may be prepended to + * the left of the leftmost <code>'@'</code> character. These have no + * effect on the minimum and maximum significant digits counts, but + * may be used to position grouping separators. For example, + * <code>"#,#@#"</code> indicates a minimum of one significant digits, + * a maximum of two significant digits, and a grouping size of three. + * + * <li>In order to enable significant digits formatting, use a pattern + * containing the <code>'@'</code> pattern character. Alternatively, + * call setSignificantDigitsUsed(TRUE). + * + * <li>In order to disable significant digits formatting, use a + * pattern that does not contain the <code>'@'</code> pattern + * character. Alternatively, call setSignificantDigitsUsed(FALSE). + * + * <li>The number of significant digits has no effect on parsing. + * + * <li>Significant digits may be used together with exponential notation. Such + * patterns are equivalent to a normal exponential pattern with a minimum and + * maximum integer digit count of one, a minimum fraction digit count of + * <code>getMinimumSignificantDigits() - 1</code>, and a maximum fraction digit + * count of <code>getMaximumSignificantDigits() - 1</code>. For example, the + * pattern <code>"@@###E0"</code> is equivalent to <code>"0.0###E0"</code>. + * + * <li>If signficant digits are in use, then the integer and fraction + * digit counts, as set via the API, are ignored. If significant + * digits are not in use, then the signficant digit counts, as set via + * the API, are ignored. + * + * </ul> + * + * <p><strong>Padding</strong> + * + * <p>DecimalFormat supports padding the result of + * format() to a specific width. Padding may be specified either + * through the API or through the pattern syntax. In a pattern the pad escape + * character, followed by a single pad character, causes padding to be parsed + * and formatted. The pad escape character is '*' in unlocalized patterns, and + * can be localized using DecimalFormatSymbols::setSymbol() with a + * DecimalFormatSymbols::kPadEscapeSymbol + * selector. For example, <code>"$*x#,##0.00"</code> formats 123 to + * <code>"$xx123.00"</code>, and 1234 to <code>"$1,234.00"</code>. + * + * <ul> + * <li>When padding is in effect, the width of the positive subpattern, + * including prefix and suffix, determines the format width. For example, in + * the pattern <code>"* #0 o''clock"</code>, the format width is 10. + * + * <li>The width is counted in 16-bit code units (UChars). + * + * <li>Some parameters which usually do not matter have meaning when padding is + * used, because the pattern width is significant with padding. In the pattern + * "* ##,##,#,##0.##", the format width is 14. The initial characters "##,##," + * do not affect the grouping size or maximum integer digits, but they do affect + * the format width. + * + * <li>Padding may be inserted at one of four locations: before the prefix, + * after the prefix, before the suffix, or after the suffix. If padding is + * specified in any other location, applyPattern() + * sets a failing UErrorCode. If there is no prefix, + * before the prefix and after the prefix are equivalent, likewise for the + * suffix. + * + * <li>When specified in a pattern, the 32-bit code point immediately + * following the pad escape is the pad character. This may be any character, + * including a special pattern character. That is, the pad escape + * <em>escapes</em> the following character. If there is no character after + * the pad escape, then the pattern is illegal. + * + * </ul> + * + * <p><strong>Rounding</strong> + * + * <p>DecimalFormat supports rounding to a specific increment. For + * example, 1230 rounded to the nearest 50 is 1250. 1.234 rounded to the + * nearest 0.65 is 1.3. The rounding increment may be specified through the API + * or in a pattern. To specify a rounding increment in a pattern, include the + * increment in the pattern itself. "#,#50" specifies a rounding increment of + * 50. "#,##0.05" specifies a rounding increment of 0.05. + * + * <ul> + * <li>Rounding only affects the string produced by formatting. It does + * not affect parsing or change any numerical values. + * + * <li>A <em>rounding mode</em> determines how values are rounded; see + * DecimalFormat::ERoundingMode. Rounding increments specified in + * patterns use the default mode, DecimalFormat::kRoundHalfEven. + * + * <li>Some locales use rounding in their currency formats to reflect the + * smallest currency denomination. + * + * <li>In a pattern, digits '1' through '9' specify rounding, but otherwise + * behave identically to digit '0'. + * </ul> + * + * <p><strong>Synchronization</strong> + * + * <p>DecimalFormat objects are not synchronized. Multiple + * threads should not access one formatter concurrently. + * + * <p><strong>Subclassing</strong> + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API DecimalFormat: public NumberFormat { +public: + /** + * Rounding mode. + * @stable ICU 2.4 + */ + enum ERoundingMode { + kRoundCeiling, /**< Round towards positive infinity */ + kRoundFloor, /**< Round towards negative infinity */ + kRoundDown, /**< Round towards zero */ + kRoundUp, /**< Round away from zero */ + kRoundHalfEven, /**< Round towards the nearest integer, or + towards the nearest even integer if equidistant */ + kRoundHalfDown, /**< Round towards the nearest integer, or + towards zero if equidistant */ + kRoundHalfUp /**< Round towards the nearest integer, or + away from zero if equidistant */ + // We don't support ROUND_UNNECESSARY + }; + + /** + * Pad position. + * @stable ICU 2.4 + */ + enum EPadPosition { + kPadBeforePrefix, + kPadAfterPrefix, + kPadBeforeSuffix, + kPadAfterSuffix + }; + + /** + * Create a DecimalFormat using the default pattern and symbols + * for the default locale. This is a convenient way to obtain a + * DecimalFormat when internationalization is not the main concern. + * <P> + * To obtain standard formats for a given locale, use the factory methods + * on NumberFormat such as createInstance. These factories will + * return the most appropriate sub-class of NumberFormat for a given + * locale. + * @param status Output param set to success/failure code. If the + * pattern is invalid this will be set to a failure code. + * @stable ICU 2.0 + */ + DecimalFormat(UErrorCode& status); + + /** + * Create a DecimalFormat from the given pattern and the symbols + * for the default locale. This is a convenient way to obtain a + * DecimalFormat when internationalization is not the main concern. + * <P> + * To obtain standard formats for a given locale, use the factory methods + * on NumberFormat such as createInstance. These factories will + * return the most appropriate sub-class of NumberFormat for a given + * locale. + * @param pattern A non-localized pattern string. + * @param status Output param set to success/failure code. If the + * pattern is invalid this will be set to a failure code. + * @stable ICU 2.0 + */ + DecimalFormat(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Create a DecimalFormat from the given pattern and symbols. + * Use this constructor when you need to completely customize the + * behavior of the format. + * <P> + * To obtain standard formats for a given + * locale, use the factory methods on NumberFormat such as + * createInstance or createCurrencyInstance. If you need only minor adjustments + * to a standard format, you can modify the format returned by + * a NumberFormat factory method. + * + * @param pattern a non-localized pattern string + * @param symbolsToAdopt the set of symbols to be used. The caller should not + * delete this object after making this call. + * @param status Output param set to success/failure code. If the + * pattern is invalid this will be set to a failure code. + * @stable ICU 2.0 + */ + DecimalFormat( const UnicodeString& pattern, + DecimalFormatSymbols* symbolsToAdopt, + UErrorCode& status); + + /** + * Create a DecimalFormat from the given pattern and symbols. + * Use this constructor when you need to completely customize the + * behavior of the format. + * <P> + * To obtain standard formats for a given + * locale, use the factory methods on NumberFormat such as + * createInstance or createCurrencyInstance. If you need only minor adjustments + * to a standard format, you can modify the format returned by + * a NumberFormat factory method. + * + * @param pattern a non-localized pattern string + * @param symbolsToAdopt the set of symbols to be used. The caller should not + * delete this object after making this call. + * @param parseError Output param to receive errors occured during parsing + * @param status Output param set to success/failure code. If the + * pattern is invalid this will be set to a failure code. + * @stable ICU 2.0 + */ + DecimalFormat( const UnicodeString& pattern, + DecimalFormatSymbols* symbolsToAdopt, + UParseError& parseError, + UErrorCode& status); + /** + * Create a DecimalFormat from the given pattern and symbols. + * Use this constructor when you need to completely customize the + * behavior of the format. + * <P> + * To obtain standard formats for a given + * locale, use the factory methods on NumberFormat such as + * createInstance or createCurrencyInstance. If you need only minor adjustments + * to a standard format, you can modify the format returned by + * a NumberFormat factory method. + * + * @param pattern a non-localized pattern string + * @param symbols the set of symbols to be used + * @param status Output param set to success/failure code. If the + * pattern is invalid this will be set to a failure code. + * @stable ICU 2.0 + */ + DecimalFormat( const UnicodeString& pattern, + const DecimalFormatSymbols& symbols, + UErrorCode& status); + + /** + * Copy constructor. + * + * @param source the DecimalFormat object to be copied from. + * @stable ICU 2.0 + */ + DecimalFormat(const DecimalFormat& source); + + /** + * Assignment operator. + * + * @param rhs the DecimalFormat object to be copied. + * @stable ICU 2.0 + */ + DecimalFormat& operator=(const DecimalFormat& rhs); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~DecimalFormat(); + + /** + * Clone this Format object polymorphically. The caller owns the + * result and should delete it when done. + * + * @return a polymorphic copy of this DecimalFormat. + * @stable ICU 2.0 + */ + virtual Format* clone(void) const; + + /** + * Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * + * @param other the object to be compared with. + * @return true if the given Format objects are semantically equal. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const; + + /** + * Format a double or long number using base-10 representation. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(double number, + UnicodeString& appendTo, + FieldPosition& pos) const; + /** + * Format a long number using base-10 representation. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(int32_t number, + UnicodeString& appendTo, + FieldPosition& pos) const; + /** + * Format an int64 number using base-10 representation. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.8 + */ + virtual UnicodeString& format(int64_t number, + UnicodeString& appendTo, + FieldPosition& pos) const; + + /** + * Format a Formattable using base-10 representation. + * + * @param obj The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Error code indicating success or failure. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Redeclared NumberFormat method. + * Formats an object to produce a string. + * + * @param obj The object to format. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Output parameter filled in with success or failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Redeclared NumberFormat method. + * Format a double number. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(double number, + UnicodeString& appendTo) const; + + /** + * Redeclared NumberFormat method. + * Format a long number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(int32_t number, + UnicodeString& appendTo) const; + + /** + * Redeclared NumberFormat method. + * Format an int64 number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.8 + */ + UnicodeString& format(int64_t number, + UnicodeString& appendTo) const; + /** + * Parse the given string using this object's choices. The method + * does string comparisons to try to find an optimal match. + * If no object can be parsed, index is unchanged, and NULL is + * returned. The result is returned as the most parsimonious + * type of Formattable that will accomodate all of the + * necessary precision. For example, if the result is exactly 12, + * it will be returned as a long. However, if it is 1.5, it will + * be returned as a double. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parsePosition The position to start parsing at on input. + * On output, moved to after the last successfully + * parse character. On parse failure, does not change. + * @see Formattable + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + ParsePosition& parsePosition) const; + + // Declare here again to get rid of function hiding problems. + /** + * Parse the given string using this object's choices. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * @param status Output parameter filled in with success or failure status. + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + UErrorCode& status) const; + + /** + * Parses text from the given string as a currency amount. Unlike + * the parse() method, this method will attempt to parse a generic + * currency name, searching for a match of this object's locale's + * currency display names, or for a 3-letter ISO currency code. + * This method will fail if this format is not a currency format, + * that is, if it does not contain the currency pattern symbol + * (U+00A4) in its prefix or suffix. + * + * @param text the string to parse + * @param result output parameter to receive result. This will have + * its currency set to the parsed ISO currency code. + * @param pos input-output position; on input, the position within + * text to match; must have 0 <= pos.getIndex() < text.length(); + * on output, the position after the last matched character. If + * the parse fails, the position in unchanged upon output. + * @return a reference to result + * @internal + */ + virtual Formattable& parseCurrency(const UnicodeString& text, + Formattable& result, + ParsePosition& pos) const; + + /** + * Returns the decimal format symbols, which is generally not changed + * by the programmer or user. + * @return desired DecimalFormatSymbols + * @see DecimalFormatSymbols + * @stable ICU 2.0 + */ + virtual const DecimalFormatSymbols* getDecimalFormatSymbols(void) const; + + /** + * Sets the decimal format symbols, which is generally not changed + * by the programmer or user. + * @param symbolsToAdopt DecimalFormatSymbols to be adopted. + * @stable ICU 2.0 + */ + virtual void adoptDecimalFormatSymbols(DecimalFormatSymbols* symbolsToAdopt); + + /** + * Sets the decimal format symbols, which is generally not changed + * by the programmer or user. + * @param symbols DecimalFormatSymbols. + * @stable ICU 2.0 + */ + virtual void setDecimalFormatSymbols(const DecimalFormatSymbols& symbols); + + + /** + * Get the positive prefix. + * + * @param result Output param which will receive the positive prefix. + * @return A reference to 'result'. + * Examples: +123, $123, sFr123 + * @stable ICU 2.0 + */ + UnicodeString& getPositivePrefix(UnicodeString& result) const; + + /** + * Set the positive prefix. + * + * @param newValue the new value of the the positive prefix to be set. + * Examples: +123, $123, sFr123 + * @stable ICU 2.0 + */ + virtual void setPositivePrefix(const UnicodeString& newValue); + + /** + * Get the negative prefix. + * + * @param result Output param which will receive the negative prefix. + * @return A reference to 'result'. + * Examples: -123, ($123) (with negative suffix), sFr-123 + * @stable ICU 2.0 + */ + UnicodeString& getNegativePrefix(UnicodeString& result) const; + + /** + * Set the negative prefix. + * + * @param newValue the new value of the the negative prefix to be set. + * Examples: -123, ($123) (with negative suffix), sFr-123 + * @stable ICU 2.0 + */ + virtual void setNegativePrefix(const UnicodeString& newValue); + + /** + * Get the positive suffix. + * + * @param result Output param which will receive the positive suffix. + * @return A reference to 'result'. + * Example: 123% + * @stable ICU 2.0 + */ + UnicodeString& getPositiveSuffix(UnicodeString& result) const; + + /** + * Set the positive suffix. + * + * @param newValue the new value of the positive suffix to be set. + * Example: 123% + * @stable ICU 2.0 + */ + virtual void setPositiveSuffix(const UnicodeString& newValue); + + /** + * Get the negative suffix. + * + * @param result Output param which will receive the negative suffix. + * @return A reference to 'result'. + * Examples: -123%, ($123) (with positive suffixes) + * @stable ICU 2.0 + */ + UnicodeString& getNegativeSuffix(UnicodeString& result) const; + + /** + * Set the negative suffix. + * + * @param newValue the new value of the negative suffix to be set. + * Examples: 123% + * @stable ICU 2.0 + */ + virtual void setNegativeSuffix(const UnicodeString& newValue); + + /** + * Get the multiplier for use in percent, permill, etc. + * For a percentage, set the suffixes to have "%" and the multiplier to be 100. + * (For Arabic, use arabic percent symbol). + * For a permill, set the suffixes to have "\\u2031" and the multiplier to be 1000. + * + * @return the multiplier for use in percent, permill, etc. + * Examples: with 100, 1.23 -> "123", and "123" -> 1.23 + * @stable ICU 2.0 + */ + int32_t getMultiplier(void) const; + + /** + * Set the multiplier for use in percent, permill, etc. + * For a percentage, set the suffixes to have "%" and the multiplier to be 100. + * (For Arabic, use arabic percent symbol). + * For a permill, set the suffixes to have "\\u2031" and the multiplier to be 1000. + * + * @param newValue the new value of the multiplier for use in percent, permill, etc. + * Examples: with 100, 1.23 -> "123", and "123" -> 1.23 + * @stable ICU 2.0 + */ + virtual void setMultiplier(int32_t newValue); + + /** + * Get the rounding increment. + * @return A positive rounding increment, or 0.0 if rounding + * is not in effect. + * @see #setRoundingIncrement + * @see #getRoundingMode + * @see #setRoundingMode + * @stable ICU 2.0 + */ + virtual double getRoundingIncrement(void) const; + + /** + * Set the rounding increment. This method also controls whether + * rounding is enabled. + * @param newValue A positive rounding increment, or 0.0 to disable rounding. + * Negative increments are equivalent to 0.0. + * @see #getRoundingIncrement + * @see #getRoundingMode + * @see #setRoundingMode + * @stable ICU 2.0 + */ + virtual void setRoundingIncrement(double newValue); + + /** + * Get the rounding mode. + * @return A rounding mode + * @see #setRoundingIncrement + * @see #getRoundingIncrement + * @see #setRoundingMode + * @stable ICU 2.0 + */ + virtual ERoundingMode getRoundingMode(void) const; + + /** + * Set the rounding mode. This has no effect unless the rounding + * increment is greater than zero. + * @param roundingMode A rounding mode + * @see #setRoundingIncrement + * @see #getRoundingIncrement + * @see #getRoundingMode + * @stable ICU 2.0 + */ + virtual void setRoundingMode(ERoundingMode roundingMode); + + /** + * Get the width to which the output of format() is padded. + * The width is counted in 16-bit code units. + * @return the format width, or zero if no padding is in effect + * @see #setFormatWidth + * @see #getPadCharacterString + * @see #setPadCharacter + * @see #getPadPosition + * @see #setPadPosition + * @stable ICU 2.0 + */ + virtual int32_t getFormatWidth(void) const; + + /** + * Set the width to which the output of format() is padded. + * The width is counted in 16-bit code units. + * This method also controls whether padding is enabled. + * @param width the width to which to pad the result of + * format(), or zero to disable padding. A negative + * width is equivalent to 0. + * @see #getFormatWidth + * @see #getPadCharacterString + * @see #setPadCharacter + * @see #getPadPosition + * @see #setPadPosition + * @stable ICU 2.0 + */ + virtual void setFormatWidth(int32_t width); + + /** + * Get the pad character used to pad to the format width. The + * default is ' '. + * @return a string containing the pad character. This will always + * have a length of one 32-bit code point. + * @see #setFormatWidth + * @see #getFormatWidth + * @see #setPadCharacter + * @see #getPadPosition + * @see #setPadPosition + * @stable ICU 2.0 + */ + virtual UnicodeString getPadCharacterString() const; + + /** + * Set the character used to pad to the format width. If padding + * is not enabled, then this will take effect if padding is later + * enabled. + * @param padChar a string containing the pad charcter. If the string + * has length 0, then the pad characer is set to ' '. Otherwise + * padChar.char32At(0) will be used as the pad character. + * @see #setFormatWidth + * @see #getFormatWidth + * @see #getPadCharacterString + * @see #getPadPosition + * @see #setPadPosition + * @stable ICU 2.0 + */ + virtual void setPadCharacter(const UnicodeString &padChar); + + /** + * Get the position at which padding will take place. This is the location + * at which padding will be inserted if the result of format() + * is shorter than the format width. + * @return the pad position, one of kPadBeforePrefix, + * kPadAfterPrefix, kPadBeforeSuffix, or + * kPadAfterSuffix. + * @see #setFormatWidth + * @see #getFormatWidth + * @see #setPadCharacter + * @see #getPadCharacterString + * @see #setPadPosition + * @see #kPadBeforePrefix + * @see #kPadAfterPrefix + * @see #kPadBeforeSuffix + * @see #kPadAfterSuffix + * @stable ICU 2.0 + */ + virtual EPadPosition getPadPosition(void) const; + + /** + * Set the position at which padding will take place. This is the location + * at which padding will be inserted if the result of format() + * is shorter than the format width. This has no effect unless padding is + * enabled. + * @param padPos the pad position, one of kPadBeforePrefix, + * kPadAfterPrefix, kPadBeforeSuffix, or + * kPadAfterSuffix. + * @see #setFormatWidth + * @see #getFormatWidth + * @see #setPadCharacter + * @see #getPadCharacterString + * @see #getPadPosition + * @see #kPadBeforePrefix + * @see #kPadAfterPrefix + * @see #kPadBeforeSuffix + * @see #kPadAfterSuffix + * @stable ICU 2.0 + */ + virtual void setPadPosition(EPadPosition padPos); + + /** + * Return whether or not scientific notation is used. + * @return TRUE if this object formats and parses scientific notation + * @see #setScientificNotation + * @see #getMinimumExponentDigits + * @see #setMinimumExponentDigits + * @see #isExponentSignAlwaysShown + * @see #setExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual UBool isScientificNotation(void); + + /** + * Set whether or not scientific notation is used. When scientific notation + * is used, the effective maximum number of integer digits is <= 8. If the + * maximum number of integer digits is set to more than 8, the effective + * maximum will be 1. This allows this call to generate a 'default' scientific + * number format without additional changes. + * @param useScientific TRUE if this object formats and parses scientific + * notation + * @see #isScientificNotation + * @see #getMinimumExponentDigits + * @see #setMinimumExponentDigits + * @see #isExponentSignAlwaysShown + * @see #setExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual void setScientificNotation(UBool useScientific); + + /** + * Return the minimum exponent digits that will be shown. + * @return the minimum exponent digits that will be shown + * @see #setScientificNotation + * @see #isScientificNotation + * @see #setMinimumExponentDigits + * @see #isExponentSignAlwaysShown + * @see #setExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual int8_t getMinimumExponentDigits(void) const; + + /** + * Set the minimum exponent digits that will be shown. This has no + * effect unless scientific notation is in use. + * @param minExpDig a value >= 1 indicating the fewest exponent digits + * that will be shown. Values less than 1 will be treated as 1. + * @see #setScientificNotation + * @see #isScientificNotation + * @see #getMinimumExponentDigits + * @see #isExponentSignAlwaysShown + * @see #setExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual void setMinimumExponentDigits(int8_t minExpDig); + + /** + * Return whether the exponent sign is always shown. + * @return TRUE if the exponent is always prefixed with either the + * localized minus sign or the localized plus sign, false if only negative + * exponents are prefixed with the localized minus sign. + * @see #setScientificNotation + * @see #isScientificNotation + * @see #setMinimumExponentDigits + * @see #getMinimumExponentDigits + * @see #setExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual UBool isExponentSignAlwaysShown(void); + + /** + * Set whether the exponent sign is always shown. This has no effect + * unless scientific notation is in use. + * @param expSignAlways TRUE if the exponent is always prefixed with either + * the localized minus sign or the localized plus sign, false if only + * negative exponents are prefixed with the localized minus sign. + * @see #setScientificNotation + * @see #isScientificNotation + * @see #setMinimumExponentDigits + * @see #getMinimumExponentDigits + * @see #isExponentSignAlwaysShown + * @stable ICU 2.0 + */ + virtual void setExponentSignAlwaysShown(UBool expSignAlways); + + /** + * Return the grouping size. Grouping size is the number of digits between + * grouping separators in the integer portion of a number. For example, + * in the number "123,456.78", the grouping size is 3. + * + * @return the grouping size. + * @see setGroupingSize + * @see NumberFormat::isGroupingUsed + * @see DecimalFormatSymbols::getGroupingSeparator + * @stable ICU 2.0 + */ + int32_t getGroupingSize(void) const; + + /** + * Set the grouping size. Grouping size is the number of digits between + * grouping separators in the integer portion of a number. For example, + * in the number "123,456.78", the grouping size is 3. + * + * @param newValue the new value of the grouping size. + * @see getGroupingSize + * @see NumberFormat::setGroupingUsed + * @see DecimalFormatSymbols::setGroupingSeparator + * @stable ICU 2.0 + */ + virtual void setGroupingSize(int32_t newValue); + + /** + * Return the secondary grouping size. In some locales one + * grouping interval is used for the least significant integer + * digits (the primary grouping size), and another is used for all + * others (the secondary grouping size). A formatter supporting a + * secondary grouping size will return a positive integer unequal + * to the primary grouping size returned by + * getGroupingSize(). For example, if the primary + * grouping size is 4, and the secondary grouping size is 2, then + * the number 123456789 formats as "1,23,45,6789", and the pattern + * appears as "#,##,###0". + * @return the secondary grouping size, or a value less than + * one if there is none + * @see setSecondaryGroupingSize + * @see NumberFormat::isGroupingUsed + * @see DecimalFormatSymbols::getGroupingSeparator + * @stable ICU 2.4 + */ + int32_t getSecondaryGroupingSize(void) const; + + /** + * Set the secondary grouping size. If set to a value less than 1, + * then secondary grouping is turned off, and the primary grouping + * size is used for all intervals, not just the least significant. + * + * @param newValue the new value of the secondary grouping size. + * @see getSecondaryGroupingSize + * @see NumberFormat#setGroupingUsed + * @see DecimalFormatSymbols::setGroupingSeparator + * @stable ICU 2.4 + */ + virtual void setSecondaryGroupingSize(int32_t newValue); + + /** + * Allows you to get the behavior of the decimal separator with integers. + * (The decimal separator will always appear with decimals.) + * + * @return TRUE if the decimal separator always appear with decimals. + * Example: Decimal ON: 12345 -> 12345.; OFF: 12345 -> 12345 + * @stable ICU 2.0 + */ + UBool isDecimalSeparatorAlwaysShown(void) const; + + /** + * Allows you to set the behavior of the decimal separator with integers. + * (The decimal separator will always appear with decimals.) + * + * @param newValue set TRUE if the decimal separator will always appear with decimals. + * Example: Decimal ON: 12345 -> 12345.; OFF: 12345 -> 12345 + * @stable ICU 2.0 + */ + virtual void setDecimalSeparatorAlwaysShown(UBool newValue); + + /** + * Synthesizes a pattern string that represents the current state + * of this Format object. + * + * @param result Output param which will receive the pattern. + * Previous contents are deleted. + * @return A reference to 'result'. + * @see applyPattern + * @stable ICU 2.0 + */ + virtual UnicodeString& toPattern(UnicodeString& result) const; + + /** + * Synthesizes a localized pattern string that represents the current + * state of this Format object. + * + * @param result Output param which will receive the localized pattern. + * Previous contents are deleted. + * @return A reference to 'result'. + * @see applyPattern + * @stable ICU 2.0 + */ + virtual UnicodeString& toLocalizedPattern(UnicodeString& result) const; + + /** + * Apply the given pattern to this Format object. A pattern is a + * short-hand specification for the various formatting properties. + * These properties can also be changed individually through the + * various setter methods. + * <P> + * There is no limit to integer digits are set + * by this routine, since that is the typical end-user desire; + * use setMaximumInteger if you want to set a real value. + * For negative numbers, use a second pattern, separated by a semicolon + * <pre> + * . Example "#,#00.0#" -> 1,234.56 + * </pre> + * This means a minimum of 2 integer digits, 1 fraction digit, and + * a maximum of 2 fraction digits. + * <pre> + * . Example: "#,#00.0#;(#,#00.0#)" for negatives in parantheses. + * </pre> + * In negative patterns, the minimum and maximum counts are ignored; + * these are presumed to be set in the positive pattern. + * + * @param pattern The pattern to be applied. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UParseError& parseError, + UErrorCode& status); + /** + * Sets the pattern. + * @param pattern The pattern to be applied. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Apply the given pattern to this Format object. The pattern + * is assumed to be in a localized notation. A pattern is a + * short-hand specification for the various formatting properties. + * These properties can also be changed individually through the + * various setter methods. + * <P> + * There is no limit to integer digits are set + * by this routine, since that is the typical end-user desire; + * use setMaximumInteger if you want to set a real value. + * For negative numbers, use a second pattern, separated by a semicolon + * <pre> + * . Example "#,#00.0#" -> 1,234.56 + * </pre> + * This means a minimum of 2 integer digits, 1 fraction digit, and + * a maximum of 2 fraction digits. + * + * Example: "#,#00.0#;(#,#00.0#)" for negatives in parantheses. + * + * In negative patterns, the minimum and maximum counts are ignored; + * these are presumed to be set in the positive pattern. + * + * @param pattern The localized pattern to be applied. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyLocalizedPattern(const UnicodeString& pattern, + UParseError& parseError, + UErrorCode& status); + + /** + * Apply the given pattern to this Format object. + * + * @param pattern The localized pattern to be applied. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyLocalizedPattern(const UnicodeString& pattern, + UErrorCode& status); + + + /** + * Sets the maximum number of digits allowed in the integer portion of a + * number. This override limits the integer digit count to 309. + * + * @param newValue the new value of the maximum number of digits + * allowed in the integer portion of a number. + * @see NumberFormat#setMaximumIntegerDigits + * @stable ICU 2.0 + */ + virtual void setMaximumIntegerDigits(int32_t newValue); + + /** + * Sets the minimum number of digits allowed in the integer portion of a + * number. This override limits the integer digit count to 309. + * + * @param newValue the new value of the minimum number of digits + * allowed in the integer portion of a number. + * @see NumberFormat#setMinimumIntegerDigits + * @stable ICU 2.0 + */ + virtual void setMinimumIntegerDigits(int32_t newValue); + + /** + * Sets the maximum number of digits allowed in the fraction portion of a + * number. This override limits the fraction digit count to 340. + * + * @param newValue the new value of the maximum number of digits + * allowed in the fraction portion of a number. + * @see NumberFormat#setMaximumFractionDigits + * @stable ICU 2.0 + */ + virtual void setMaximumFractionDigits(int32_t newValue); + + /** + * Sets the minimum number of digits allowed in the fraction portion of a + * number. This override limits the fraction digit count to 340. + * + * @param newValue the new value of the minimum number of digits + * allowed in the fraction portion of a number. + * @see NumberFormat#setMinimumFractionDigits + * @stable ICU 2.0 + */ + virtual void setMinimumFractionDigits(int32_t newValue); + + /** + * Returns the minimum number of significant digits that will be + * displayed. This value has no effect unless areSignificantDigitsUsed() + * returns true. + * @return the fewest significant digits that will be shown + * @stable ICU 3.0 + */ + int32_t getMinimumSignificantDigits() const; + + /** + * Returns the maximum number of significant digits that will be + * displayed. This value has no effect unless areSignificantDigitsUsed() + * returns true. + * @return the most significant digits that will be shown + * @stable ICU 3.0 + */ + int32_t getMaximumSignificantDigits() const; + + /** + * Sets the minimum number of significant digits that will be + * displayed. If <code>min</code> is less than one then it is set + * to one. If the maximum significant digits count is less than + * <code>min</code>, then it is set to <code>min</code>. This + * value has no effect unless areSignificantDigits() returns true. + * @param min the fewest significant digits to be shown + * @stable ICU 3.0 + */ + void setMinimumSignificantDigits(int32_t min); + + /** + * Sets the maximum number of significant digits that will be + * displayed. If <code>max</code> is less than one then it is set + * to one. If the minimum significant digits count is greater + * than <code>max</code>, then it is set to <code>max</code>. + * This value has no effect unless areSignificantDigits() returns + * true. + * @param max the most significant digits to be shown + * @stable ICU 3.0 + */ + void setMaximumSignificantDigits(int32_t max); + + /** + * Returns true if significant digits are in use, or false if + * integer and fraction digit counts are in use. + * @return true if significant digits are in use + * @stable ICU 3.0 + */ + UBool areSignificantDigitsUsed() const; + + /** + * Sets whether significant digits are in use, or integer and + * fraction digit counts are in use. + * @param useSignificantDigits true to use significant digits, or + * false to use integer and fraction digit counts + * @stable ICU 3.0 + */ + void setSignificantDigitsUsed(UBool useSignificantDigits); + + public: + /** + * Sets the currency used to display currency + * amounts. This takes effect immediately, if this format is a + * currency format. If this format is not a currency format, then + * the currency is used if and when this object becomes a + * currency format through the application of a new pattern. + * @param theCurrency a 3-letter ISO code indicating new currency + * to use. It need not be null-terminated. May be the empty + * string or NULL to indicate no currency. + * @param ec input-output error code + * @stable ICU 3.0 + */ + virtual void setCurrency(const UChar* theCurrency, UErrorCode& ec); + + /** + * Sets the currency used to display currency amounts. See + * setCurrency(const UChar*, UErrorCode&). + * @deprecated ICU 3.0. Use setCurrency(const UChar*, UErrorCode&). + */ + virtual void setCurrency(const UChar* theCurrency); + + /** + * The resource tags we use to retrieve decimal format data from + * locale resource bundles. + * @deprecated ICU 3.4. This string has no public purpose. Please don't use it. + */ + static const char fgNumberPatterns[]; + +public: + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + +private: + DecimalFormat(); // default constructor not implemented + + int32_t precision(UBool isIntegral) const; + + /** + * Do real work of constructing a new DecimalFormat. + */ + void construct(UErrorCode& status, + UParseError& parseErr, + const UnicodeString* pattern = 0, + DecimalFormatSymbols* symbolsToAdopt = 0 + ); + + /** + * Does the real work of generating a pattern. + * + * @param result Output param which will receive the pattern. + * Previous contents are deleted. + * @param localized TRUE return localized pattern. + * @return A reference to 'result'. + */ + UnicodeString& toPattern(UnicodeString& result, UBool localized) const; + + /** + * Does the real work of applying a pattern. + * @param pattern The pattern to be applied. + * @param localized If true, the pattern is localized; else false. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + */ + void applyPattern(const UnicodeString& pattern, + UBool localized, + UParseError& parseError, + UErrorCode& status); + /** + * Do the work of formatting a number, either a double or a long. + * + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param fieldPosition On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param digits the digits to be formatted. + * @param isInteger if TRUE format the digits as Integer. + * @return Reference to 'appendTo' parameter. + */ + UnicodeString& subformat(UnicodeString& appendTo, + FieldPosition& fieldPosition, + DigitList& digits, + UBool isInteger) const; + + void parse(const UnicodeString& text, + Formattable& result, + ParsePosition& pos, + UBool parseCurrency) const; + + enum { + fgStatusInfinite, + fgStatusLength // Leave last in list. + } StatusFlags; + + UBool subparse(const UnicodeString& text, ParsePosition& parsePosition, + DigitList& digits, UBool* status, + UChar* currency) const; + + int32_t skipPadding(const UnicodeString& text, int32_t position) const; + + int32_t compareAffix(const UnicodeString& input, + int32_t pos, + UBool isNegative, + UBool isPrefix, + UChar* currency) const; + + static int32_t compareSimpleAffix(const UnicodeString& affix, + const UnicodeString& input, + int32_t pos); + + static int32_t skipRuleWhiteSpace(const UnicodeString& text, int32_t pos); + + static int32_t skipUWhiteSpace(const UnicodeString& text, int32_t pos); + + int32_t compareComplexAffix(const UnicodeString& affixPat, + const UnicodeString& input, + int32_t pos, + UChar* currency) const; + + static int32_t match(const UnicodeString& text, int32_t pos, UChar32 ch); + + static int32_t match(const UnicodeString& text, int32_t pos, const UnicodeString& str); + + /** + * Get a decimal format symbol. + * Returns a const reference to the symbol string. + * @internal + */ + inline const UnicodeString &getConstSymbol(DecimalFormatSymbols::ENumberFormatSymbol symbol) const; + + int32_t appendAffix(UnicodeString& buf, double number, + UBool isNegative, UBool isPrefix) const; + + /** + * Append an affix to the given UnicodeString, using quotes if + * there are special characters. Single quotes themselves must be + * escaped in either case. + */ + void appendAffixPattern(UnicodeString& appendTo, const UnicodeString& affix, + UBool localized) const; + + void appendAffixPattern(UnicodeString& appendTo, + const UnicodeString* affixPattern, + const UnicodeString& expAffix, UBool localized) const; + + void expandAffix(const UnicodeString& pattern, + UnicodeString& affix, + double number, + UBool doFormat) const; + + void expandAffixes(); + + static double round(double a, ERoundingMode mode, UBool isNegative); + + void addPadding(UnicodeString& appendTo, + FieldPosition& fieldPosition, + int32_t prefixLen, int32_t suffixLen) const; + + UBool isGroupingPosition(int32_t pos) const; + + void setCurrencyForSymbols(); + + /** + * Constants. + */ + //static const int8_t fgMaxDigit; // The largest digit, in this case 9 + + /*transient*/ //DigitList* fDigitList; + + UnicodeString fPositivePrefix; + UnicodeString fPositiveSuffix; + UnicodeString fNegativePrefix; + UnicodeString fNegativeSuffix; + UnicodeString* fPosPrefixPattern; + UnicodeString* fPosSuffixPattern; + UnicodeString* fNegPrefixPattern; + UnicodeString* fNegSuffixPattern; + + /** + * Formatter for ChoiceFormat-based currency names. If this field + * is not null, then delegate to it to format currency symbols. + * @since ICU 2.6 + */ + ChoiceFormat* fCurrencyChoice; + + int32_t fMultiplier; + int32_t fGroupingSize; + int32_t fGroupingSize2; + UBool fDecimalSeparatorAlwaysShown; + /*transient*/ UBool fIsCurrencyFormat; + DecimalFormatSymbols* fSymbols; + + UBool fUseSignificantDigits; + int32_t fMinSignificantDigits; + int32_t fMaxSignificantDigits; + + UBool fUseExponentialNotation; + int8_t fMinExponentDigits; + UBool fExponentSignAlwaysShown; + + /* If fRoundingIncrement is NULL, there is no rounding. Otherwise, round to + * fRoundingIncrement.getDouble(). Since this operation may be expensive, + * we cache the result in fRoundingDouble. All methods that update + * fRoundingIncrement also update fRoundingDouble. */ + DigitList* fRoundingIncrement; + /*transient*/ double fRoundingDouble; + ERoundingMode fRoundingMode; + + UChar32 fPad; + int32_t fFormatWidth; + EPadPosition fPadPosition; + +protected: + + /** + * Returns the currency in effect for this formatter. Subclasses + * should override this method as needed. Unlike getCurrency(), + * this method should never return "". + * @result output parameter for null-terminated result, which must + * have a capacity of at least 4 + * @internal + */ + virtual void getEffectiveCurrency(UChar* result, UErrorCode& ec) const; + + /** number of integer digits + * @stable ICU 2.4 + */ + static const int32_t kDoubleIntegerDigits; + /** number of fraction digits + * @stable ICU 2.4 + */ + static const int32_t kDoubleFractionDigits; + + /** + * When someone turns on scientific mode, we assume that more than this + * number of digits is due to flipping from some other mode that didn't + * restrict the maximum, and so we force 1 integer digit. We don't bother + * to track and see if someone is using exponential notation with more than + * this number, it wouldn't make sense anyway, and this is just to make sure + * that someone turning on scientific mode with default settings doesn't + * end up with lots of zeroes. + * @stable ICU 2.8 + */ + static const int32_t kMaxScientificIntegerDigits; +}; + +inline UnicodeString& +DecimalFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + // Don't use Format:: - use immediate base class only, + // in case immediate base modifies behavior later. + return NumberFormat::format(obj, appendTo, status); +} + +inline UnicodeString& +DecimalFormat::format(double number, + UnicodeString& appendTo) const { + FieldPosition pos(0); + return format(number, appendTo, pos); +} + +inline UnicodeString& +DecimalFormat::format(int32_t number, + UnicodeString& appendTo) const { + FieldPosition pos(0); + return format((int64_t)number, appendTo, pos); +} + +inline const UnicodeString & +DecimalFormat::getConstSymbol(DecimalFormatSymbols::ENumberFormatSymbol symbol) const { + return fSymbols->getConstSymbol(symbol); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _DECIMFMT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/dtfmtsym.h b/Build/source/libs/icu-xetex/i18n/unicode/dtfmtsym.h new file mode 100644 index 00000000000..5bc73fef829 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/dtfmtsym.h @@ -0,0 +1,698 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2007, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File DTFMTSYM.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 07/21/98 stephen Added getZoneIndex() +* Changed to match C++ conventions +******************************************************************************** +*/ + +#ifndef DTFMTSYM_H +#define DTFMTSYM_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/calendar.h" +#include "unicode/uobject.h" +#include "unicode/locid.h" +#include "unicode/ures.h" + +/** + * \file + * \brief C++ API: Symbols for formatting dates. + */ + +U_NAMESPACE_BEGIN + +/* forward declaration */ +class SimpleDateFormat; +class Hashtable; +class ZoneStringFormat; +class SafeZoneStringFormatPtr; + +/** + * DateFormatSymbols is a public class for encapsulating localizable date-time + * formatting data -- including timezone data. DateFormatSymbols is used by + * DateFormat and SimpleDateFormat. + * <P> + * Rather than first creating a DateFormatSymbols to get a date-time formatter + * by using a SimpleDateFormat constructor, clients are encouraged to create a + * date-time formatter using the getTimeInstance(), getDateInstance(), or + * getDateTimeInstance() method in DateFormat. Each of these methods can return a + * date/time formatter initialized with a default format pattern along with the + * date-time formatting data for a given or default locale. After a formatter is + * created, clients may modify the format pattern using the setPattern function + * as so desired. For more information on using these formatter factory + * functions, see DateFormat. + * <P> + * If clients decide to create a date-time formatter with a particular format + * pattern and locale, they can do so with new SimpleDateFormat(aPattern, + * new DateFormatSymbols(aLocale)). This will load the appropriate date-time + * formatting data from the locale. + * <P> + * DateFormatSymbols objects are clonable. When clients obtain a + * DateFormatSymbols object, they can feel free to modify the date-time + * formatting data as necessary. For instance, clients can + * replace the localized date-time format pattern characters with the ones that + * they feel easy to remember. Or they can change the representative cities + * originally picked by default to using their favorite ones. + * <P> + * DateFormatSymbols are not expected to be subclassed. Data for a calendar is + * loaded out of resource bundles. The 'type' parameter indicates the type of + * calendar, for example, "gregorian" or "japanese". If the type is not gregorian + * (or NULL, or an empty string) then the type is appended to the resource name, + * for example, 'Eras_japanese' instead of 'Eras'. If the resource 'Eras_japanese' did + * not exist (even in root), then this class will fall back to just 'Eras', that is, + * Gregorian data. Therefore, the calendar implementor MUST ensure that the root + * locale at least contains any resources that are to be particularized for the + * calendar type. + */ +class U_I18N_API DateFormatSymbols : public UObject { +public: + /** + * Construct a DateFormatSymbols object by loading format data from + * resources for the default locale, in the default calendar (Gregorian). + * <P> + * NOTE: This constructor will never fail; if it cannot get resource + * data for the default locale, it will return a last-resort object + * based on hard-coded strings. + * + * @param status Status code. Failure + * results if the resources for the default cannot be + * found or cannot be loaded + * @stable ICU 2.0 + */ + DateFormatSymbols(UErrorCode& status); + + /** + * Construct a DateFormatSymbols object by loading format data from + * resources for the given locale, in the default calendar (Gregorian). + * + * @param locale Locale to load format data from. + * @param status Status code. Failure + * results if the resources for the locale cannot be + * found or cannot be loaded + * @stable ICU 2.0 + */ + DateFormatSymbols(const Locale& locale, + UErrorCode& status); + + /** + * Construct a DateFormatSymbols object by loading format data from + * resources for the default locale, in the default calendar (Gregorian). + * <P> + * NOTE: This constructor will never fail; if it cannot get resource + * data for the default locale, it will return a last-resort object + * based on hard-coded strings. + * + * @param type Type of calendar (as returned by Calendar::getType). + * Will be used to access the correct set of strings. + * (NULL or empty string defaults to "gregorian".) + * @param status Status code. Failure + * results if the resources for the default cannot be + * found or cannot be loaded + * @internal + */ + DateFormatSymbols(const char *type, UErrorCode& status); + + /** + * Construct a DateFormatSymbols object by loading format data from + * resources for the given locale, in the default calendar (Gregorian). + * + * @param locale Locale to load format data from. + * @param type Type of calendar (as returned by Calendar::getType). + * Will be used to access the correct set of strings. + * (NULL or empty string defaults to "gregorian".) + * @param status Status code. Failure + * results if the resources for the locale cannot be + * found or cannot be loaded + * @internal + */ + DateFormatSymbols(const Locale& locale, + const char *type, + UErrorCode& status); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + DateFormatSymbols(const DateFormatSymbols&); + + /** + * Assignment operator. + * @stable ICU 2.0 + */ + DateFormatSymbols& operator=(const DateFormatSymbols&); + + /** + * Destructor. This is nonvirtual because this class is not designed to be + * subclassed. + * @stable ICU 2.0 + */ + virtual ~DateFormatSymbols(); + + /** + * Return true if another object is semantically equal to this one. + * + * @param other the DateFormatSymbols object to be compared with. + * @return true if other is semantically equal to this. + * @stable ICU 2.0 + */ + UBool operator==(const DateFormatSymbols& other) const; + + /** + * Return true if another object is semantically unequal to this one. + * + * @param other the DateFormatSymbols object to be compared with. + * @return true if other is semantically unequal to this. + * @stable ICU 2.0 + */ + UBool operator!=(const DateFormatSymbols& other) const { return !operator==(other); } + + /** + * Gets era strings. For example: "AD" and "BC". + * + * @param count Filled in with length of the array. + * @return the era strings. + * @stable ICU 2.0 + */ + const UnicodeString* getEras(int32_t& count) const; + + /** + * Sets era strings. For example: "AD" and "BC". + * @param eras Array of era strings (DateFormatSymbols retains ownership.) + * @param count Filled in with length of the array. + * @stable ICU 2.0 + */ + void setEras(const UnicodeString* eras, int32_t count); + + /** + * Gets era name strings. For example: "Anno Domini" and "Before Christ". + * + * @param count Filled in with length of the array. + * @return the era name strings. + * @stable ICU 3.4 + */ + const UnicodeString* getEraNames(int32_t& count) const; + + /** + * Sets era name strings. For example: "Anno Domini" and "Before Christ". + * @param eraNames Array of era name strings (DateFormatSymbols retains ownership.) + * @param count Filled in with length of the array. + * @stable ICU 3.6 + */ + void setEraNames(const UnicodeString* eraNames, int32_t count); + + /** + * Gets month strings. For example: "January", "February", etc. + * @param count Filled in with length of the array. + * @return the month strings. (DateFormatSymbols retains ownership.) + * @stable ICU 2.0 + */ + const UnicodeString* getMonths(int32_t& count) const; + + /** + * Sets month strings. For example: "January", "February", etc. + * + * @param months the new month strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @stable ICU 2.0 + */ + void setMonths(const UnicodeString* months, int32_t count); + + /** + * Gets short month strings. For example: "Jan", "Feb", etc. + * + * @param count Filled in with length of the array. + * @return the short month strings. (DateFormatSymbols retains ownership.) + * @stable ICU 2.0 + */ + const UnicodeString* getShortMonths(int32_t& count) const; + + /** + * Sets short month strings. For example: "Jan", "Feb", etc. + * @param count Filled in with length of the array. + * @param shortMonths the new short month strings. (not adopted; caller retains ownership) + * @stable ICU 2.0 + */ + void setShortMonths(const UnicodeString* shortMonths, int32_t count); + + /** + * Selector for date formatting context + * @stable ICU 3.6 + */ + enum DtContextType { + FORMAT, + STANDALONE, + DT_CONTEXT_COUNT + }; + + /** + * Selector for date formatting width + * @stable ICU 3.6 + */ + enum DtWidthType { + ABBREVIATED, + WIDE, + NARROW, + DT_WIDTH_COUNT + }; + + /** + * Gets month strings by width and context. For example: "January", "February", etc. + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW. + * @return the month strings. (DateFormatSymbols retains ownership.) + * @stable ICU 3.4 + */ + const UnicodeString* getMonths(int32_t& count, DtContextType context, DtWidthType width) const; + + /** + * Sets month strings by width and context. For example: "January", "February", etc. + * + * @param months The new month strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW. + * @stable ICU 3.6 + */ + void setMonths(const UnicodeString* months, int32_t count, DtContextType context, DtWidthType width); + + /** + * Gets weekday strings. For example: "Sunday", "Monday", etc. + * @param count Filled in with length of the array. + * @return the weekday strings. (DateFormatSymbols retains ownership.) + * @stable ICU 2.0 + */ + const UnicodeString* getWeekdays(int32_t& count) const; + + + /** + * Sets weekday strings. For example: "Sunday", "Monday", etc. + * @param weekdays the new weekday strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @stable ICU 2.0 + */ + void setWeekdays(const UnicodeString* weekdays, int32_t count); + + /** + * Gets short weekday strings. For example: "Sun", "Mon", etc. + * @param count Filled in with length of the array. + * @return the short weekday strings. (DateFormatSymbols retains ownership.) + * @stable ICU 2.0 + */ + const UnicodeString* getShortWeekdays(int32_t& count) const; + + /** + * Sets short weekday strings. For example: "Sun", "Mon", etc. + * @param shortWeekdays the new short weekday strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @stable ICU 2.0 + */ + void setShortWeekdays(const UnicodeString* shortWeekdays, int32_t count); + + /** + * Gets weekday strings by width and context. For example: "Sunday", "Monday", etc. + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW + * @return the month strings. (DateFormatSymbols retains ownership.) + * @stable ICU 3.4 + */ + const UnicodeString* getWeekdays(int32_t& count, DtContextType context, DtWidthType width) const; + + /** + * Sets weekday strings by width and context. For example: "Sunday", "Monday", etc. + * @param weekdays The new weekday strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW + * @stable ICU 3.6 + */ + void setWeekdays(const UnicodeString* weekdays, int32_t count, DtContextType context, DtWidthType width); + + /** + * Gets quarter strings by width and context. For example: "1st Quarter", "2nd Quarter", etc. + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE or ABBREVIATED. There + * are no NARROW quarters. + * @return the quarter strings. (DateFormatSymbols retains ownership.) + * @stable ICU 3.6 + */ + const UnicodeString* getQuarters(int32_t& count, DtContextType context, DtWidthType width) const; + + /** + * Sets quarter strings by width and context. For example: "1st Quarter", "2nd Quarter", etc. + * + * @param quarters The new quarter strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @param context The formatting context, either FORMAT or STANDALONE + * @param width The width of returned strings, either WIDE or ABBREVIATED. There + * are no NARROW quarters. + * @stable ICU 3.6 + */ + void setQuarters(const UnicodeString* quarters, int32_t count, DtContextType context, DtWidthType width); + + /** + * Gets AM/PM strings. For example: "AM" and "PM". + * @param count Filled in with length of the array. + * @return the weekday strings. (DateFormatSymbols retains ownership.) + * @stable ICU 2.0 + */ + const UnicodeString* getAmPmStrings(int32_t& count) const; + + /** + * Sets ampm strings. For example: "AM" and "PM". + * @param ampms the new ampm strings. (not adopted; caller retains ownership) + * @param count Filled in with length of the array. + * @stable ICU 2.0 + */ + void setAmPmStrings(const UnicodeString* ampms, int32_t count); + + /** + * Gets timezone strings. These strings are stored in a 2-dimensional array. + * @param rowCount Output param to receive number of rows. + * @param columnCount Output param to receive number of columns. + * @return The timezone strings as a 2-d array. (DateFormatSymbols retains ownership.) + * @deprecated ICU 3.6 + */ + const UnicodeString** getZoneStrings(int32_t& rowCount, int32_t& columnCount) const; + + /** + * Sets timezone strings. These strings are stored in a 2-dimensional array. + * @param strings The timezone strings as a 2-d array to be copied. (not adopted; caller retains ownership) + * @param rowCount The number of rows (count of first index). + * @param columnCount The number of columns (count of second index). + * @stable ICU 2.0 + */ + void setZoneStrings(const UnicodeString* const* strings, int32_t rowCount, int32_t columnCount); + + /** + * Get the non-localized date-time pattern characters. + * @return the non-localized date-time pattern characters + * @stable ICU 2.0 + */ + static const UChar * U_EXPORT2 getPatternUChars(void); + + /** + * Gets localized date-time pattern characters. For example: 'u', 't', etc. + * <p> + * Note: ICU no longer provides localized date-time pattern characters for a locale + * starting ICU 3.8. This method returns the non-localized date-time pattern + * characters unless user defined localized data is set by setLocalPatternChars. + * @param result Output param which will receive the localized date-time pattern characters. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getLocalPatternChars(UnicodeString& result) const; + + /** + * Sets localized date-time pattern characters. For example: 'u', 't', etc. + * @param newLocalPatternChars the new localized date-time + * pattern characters. + * @stable ICU 2.0 + */ + void setLocalPatternChars(const UnicodeString& newLocalPatternChars); + + /** + * Returns the locale for this object. Two flavors are available: + * valid and actual locale. + * @stable ICU 2.8 + */ + Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + + friend class SimpleDateFormat; + friend class DateFormatSymbolsSingleSetter; // see udat.cpp + + /** + * Era strings. For example: "AD" and "BC". + */ + UnicodeString* fEras; + int32_t fErasCount; + + /** + * Era name strings. For example: "Anno Domini" and "Before Christ". + */ + UnicodeString* fEraNames; + int32_t fEraNamesCount; + + /** + * Month strings. For example: "January", "February", etc. + */ + UnicodeString* fMonths; + int32_t fMonthsCount; + + /** + * Short month strings. For example: "Jan", "Feb", etc. + */ + UnicodeString* fShortMonths; + int32_t fShortMonthsCount; + + /** + * Narrow month strings. For example: "J", "F", etc. + */ + UnicodeString* fNarrowMonths; + int32_t fNarrowMonthsCount; + + /** + * Standalone Month strings. For example: "January", "February", etc. + */ + UnicodeString* fStandaloneMonths; + int32_t fStandaloneMonthsCount; + + /** + * Standalone Short month strings. For example: "Jan", "Feb", etc. + */ + UnicodeString* fStandaloneShortMonths; + int32_t fStandaloneShortMonthsCount; + + /** + * Standalone Narrow month strings. For example: "J", "F", etc. + */ + UnicodeString* fStandaloneNarrowMonths; + int32_t fStandaloneNarrowMonthsCount; + + /** + * Weekday strings. For example: "Sunday", "Monday", etc. + */ + UnicodeString* fWeekdays; + int32_t fWeekdaysCount; + + /** + * Short weekday strings. For example: "Sun", "Mon", etc. + */ + UnicodeString* fShortWeekdays; + int32_t fShortWeekdaysCount; + + /** + * Narrow weekday strings. For example: "Sun", "Mon", etc. + */ + UnicodeString* fNarrowWeekdays; + int32_t fNarrowWeekdaysCount; + + /** + * Standalone Weekday strings. For example: "Sunday", "Monday", etc. + */ + UnicodeString* fStandaloneWeekdays; + int32_t fStandaloneWeekdaysCount; + + /** + * Standalone Short weekday strings. For example: "Sun", "Mon", etc. + */ + UnicodeString* fStandaloneShortWeekdays; + int32_t fStandaloneShortWeekdaysCount; + + /** + * Standalone Narrow weekday strings. For example: "Sun", "Mon", etc. + */ + UnicodeString* fStandaloneNarrowWeekdays; + int32_t fStandaloneNarrowWeekdaysCount; + + /** + * Ampm strings. For example: "AM" and "PM". + */ + UnicodeString* fAmPms; + int32_t fAmPmsCount; + + /** + * Quarter strings. For example: "1st quarter", "2nd quarter", etc. + */ + UnicodeString *fQuarters; + int32_t fQuartersCount; + + /** + * Short quarters. For example: "Q1", "Q2", etc. + */ + UnicodeString *fShortQuarters; + int32_t fShortQuartersCount; + + /** + * Standalone quarter strings. For example: "1st quarter", "2nd quarter", etc. + */ + UnicodeString *fStandaloneQuarters; + int32_t fStandaloneQuartersCount; + + /** + * Standalone short quarter strings. For example: "Q1", "Q2", etc. + */ + UnicodeString *fStandaloneShortQuarters; + int32_t fStandaloneShortQuartersCount; + + /** + * The format data of all the timezones in this locale. + */ + UnicodeString **fZoneStrings; // Zone string array set by setZoneStrings + UnicodeString **fLocaleZoneStrings; // Zone string array created by the locale + int32_t fZoneStringsRowCount; + int32_t fZoneStringsColCount; + + const ZoneStringFormat *fZoneStringFormat; + ZoneStringFormat *fZSFLocal; // Local ZoneStringFormat instance + SafeZoneStringFormatPtr *fZSFCachePtr; // Cached ZoneStringFormat + Locale fZSFLocale; // Locale used for getting ZoneStringFormat + + /** + * Pattern string used for localized time zone GMT format. For example, "GMT{0}" + */ + UnicodeString fGmtFormat; + + /** + * Pattern strings used for formatting zone offset in a localized time zone GMT string. + */ + UnicodeString *fGmtHourFormats; + int32_t fGmtHourFormatsCount; + + enum GMTHourType { + GMT_NEGATIVE_HMS = 0, + GMT_NEGATIVE_HM, + GMT_POSITIVE_HMS, + GMT_POSITIVE_HM, + GMT_HOUR_COUNT + }; + + /** + * Localized date-time pattern characters. For example: use 'u' as 'y'. + */ + UnicodeString fLocalPatternChars; + +private: + /** valid/actual locale information + * these are always ICU locales, so the length should not be a problem + */ + char validLocale[ULOC_FULLNAME_CAPACITY]; + char actualLocale[ULOC_FULLNAME_CAPACITY]; + + DateFormatSymbols(); // default constructor not implemented + + /** + * Called by the constructors to actually load data from the resources + * + * @param locale The locale to get symbols for. + * @param type Calendar Type (as from Calendar::getType()) + * @param status Input/output parameter, set to success or + * failure code upon return. + * @param useLastResortData determine if use last resort data + */ + void initializeData(const Locale&, const char *type, UErrorCode& status, UBool useLastResortData = FALSE); + + /** + * Copy or alias an array in another object, as appropriate. + * + * @param dstArray the copy destination array. + * @param dstCount fill in with the lenth of 'dstArray'. + * @param srcArray the source array to be copied. + * @param srcCount the length of items to be copied from the 'srcArray'. + */ + static void assignArray(UnicodeString*& dstArray, + int32_t& dstCount, + const UnicodeString* srcArray, + int32_t srcCount); + + /** + * Return true if the given arrays' contents are equal, or if the arrays are + * identical (pointers are equal). + * + * @param array1 one array to be compared with. + * @param array2 another array to be compared with. + * @param count the length of items to be copied. + * @return true if the given arrays' contents are equal, or if the arrays are + * identical (pointers are equal). + */ + static UBool arrayCompare(const UnicodeString* array1, + const UnicodeString* array2, + int32_t count); + + /** + * Create a copy, in fZoneStrings, of the given zone strings array. The + * member variables fZoneStringsRowCount and fZoneStringsColCount should be + * set already by the caller. + */ + void createZoneStrings(const UnicodeString *const * otherStrings); + + /** + * Delete all the storage owned by this object. + */ + void dispose(void); + + /** + * Copy all of the other's data to this. + * @param other the object to be copied. + */ + void copyData(const DateFormatSymbols& other); + + + /** + * Returns a ZoneStringFormat, used only by SimpleDateFormat for now. + */ + const ZoneStringFormat* getZoneStringFormat(void) const; + + /** + * Create a ZoneStringFormat by locale if not yet availble + */ + void initZoneStringFormat(void); + + /** + * Create zone strings array by locale if not yet available + */ + void initZoneStringsArray(void); + + /** + * Delete just the zone strings. + */ + void disposeZoneStrings(void); +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _DTFMTSYM +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/dtptngen.h b/Build/source/libs/icu-xetex/i18n/unicode/dtptngen.h new file mode 100644 index 00000000000..09f6b84590c --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/dtptngen.h @@ -0,0 +1,416 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and +* others. All Rights Reserved. +******************************************************************************* +* +* File DTPTNGEN.H +* +******************************************************************************* +*/ + +#ifndef __DTPTNGEN_H__ +#define __DTPTNGEN_H__ + +#include "unicode/datefmt.h" +#include "unicode/locid.h" +#include "unicode/udat.h" +#include "unicode/udatpg.h" + +U_NAMESPACE_BEGIN + +class Hashtable; +class FormatParser; +class DateTimeMatcher; +class DistanceInfo; +class PatternMap; + +/** + * This class provides flexible generation of date format patterns, like "yy-MM-dd". + * The user can build up the generator by adding successive patterns. Once that + * is done, a query can be made using a "skeleton", which is a pattern which just + * includes the desired fields and lengths. The generator will return the "best fit" + * pattern corresponding to that skeleton. + * <p>The main method people will use is getBestPattern(String skeleton), + * since normally this class is pre-built with data from a particular locale. + * However, generators can be built directly from other data as well. + * <p><i>Issue: may be useful to also have a function that returns the list of + * fields in a pattern, in order, since we have that internally. + * That would be useful for getting the UI order of field elements.</i> + * @draft ICU 3.8 +**/ +class U_I18N_API DateTimePatternGenerator : public UObject { +public: + /** + * Construct a flexible generator according to default locale. + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @draft ICU 3.8 + */ + static DateTimePatternGenerator* U_EXPORT2 createInstance(UErrorCode& status); + + /** + * Construct a flexible generator according to data for a given locale. + * @param uLocale + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @draft ICU 3.8 + */ + static DateTimePatternGenerator* U_EXPORT2 createInstance(const Locale& uLocale, UErrorCode& status); + + /** + * Create an empty generator, to be constructed with addPattern(...) etc. + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @draft ICU 3.8 + */ + static DateTimePatternGenerator* U_EXPORT2 createEmptyInstance(UErrorCode& status); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~DateTimePatternGenerator(); + + /** + * Clone DateTimePatternGenerator object. Clients are responsible for + * deleting the DateTimePatternGenerator object cloned. + * @draft ICU 3.8 + */ + DateTimePatternGenerator* clone() const; + + /** + * Return true if another object is semantically equal to this one. + * + * @param other the DateTimePatternGenerator object to be compared with. + * @return true if other is semantically equal to this. + * @draft ICU 3.8 + */ + UBool operator==(const DateTimePatternGenerator& other) const; + + /** + * Return true if another object is semantically unequal to this one. + * + * @param other the DateTimePatternGenerator object to be compared with. + * @return true if other is semantically unequal to this. + * @draft ICU 3.8 + */ + UBool operator!=(const DateTimePatternGenerator& other) const; + + /** + * Utility to return a unique skeleton from a given pattern. For example, + * both "MMM-dd" and "dd/MMM" produce the skeleton "MMMdd". + * + * @param pattern Input pattern, such as "dd/MMM" + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return skeleton such as "MMMdd" + * @draft ICU 3.8 + */ + UnicodeString getSkeleton(const UnicodeString& pattern, UErrorCode& status); + + /** + * Utility to return a unique base skeleton from a given pattern. This is + * the same as the skeleton, except that differences in length are minimized + * so as to only preserve the difference between string and numeric form. So + * for example, both "MMM-dd" and "d/MMM" produce the skeleton "MMMd" + * (notice the single d). + * + * @param pattern Input pattern, such as "dd/MMM" + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return base skeleton, such as "Md" + * @draft ICU 3.8 + */ + UnicodeString getBaseSkeleton(const UnicodeString& pattern, UErrorCode& status); + + /** + * Adds a pattern to the generator. If the pattern has the same skeleton as + * an existing pattern, and the override parameter is set, then the previous + * value is overriden. Otherwise, the previous value is retained. In either + * case, the conflicting status is set and previous vale is stored in + * conflicting pattern. + * <p> + * Note that single-field patterns (like "MMM") are automatically added, and + * don't need to be added explicitly! + * + * @param pattern Input pattern, such as "dd/MMM" + * @param override When existing values are to be overridden use true, + * otherwise use false. + * @param conflictingPattern Previous pattern with the same skeleton. + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return conflicting status. The value could be UDATPG_NO_CONFLICT, + * UDATPG_BASE_CONFLICT or UDATPG_CONFLICT. + * @draft ICU 3.8 + */ + UDateTimePatternConflict addPattern(const UnicodeString& pattern, + UBool override, + UnicodeString& conflictingPattern, + UErrorCode& status); + + /** + * An AppendItem format is a pattern used to append a field if there is no + * good match. For example, suppose that the input skeleton is "GyyyyMMMd", + * and there is no matching pattern internally, but there is a pattern + * matching "yyyyMMMd", say "d-MM-yyyy". Then that pattern is used, plus the + * G. The way these two are conjoined is by using the AppendItemFormat for G + * (era). So if that value is, say "{0}, {1}" then the final resulting + * pattern is "d-MM-yyyy, G". + * <p> + * There are actually three available variables: {0} is the pattern so far, + * {1} is the element we are adding, and {2} is the name of the element. + * <p> + * This reflects the way that the CLDR data is organized. + * + * @param field such as UDATPG_ERA_FIELD. + * @param value pattern, such as "{0}, {1}" + * @draft ICU 3.8 + */ + void setAppendItemFormat(UDateTimePatternField field, const UnicodeString& value); + + /** + * Getter corresponding to setAppendItemFormat. Values below 0 or at or + * above UDATPG_FIELD_COUNT are illegal arguments. + * + * @param field such as UDATPG_ERA_FIELD. + * @return append pattern for field + * @draft ICU 3.8 + */ + const UnicodeString& getAppendItemFormat(UDateTimePatternField field) const; + + /** + * Sets the names of field, eg "era" in English for ERA. These are only + * used if the corresponding AppendItemFormat is used, and if it contains a + * {2} variable. + * <p> + * This reflects the way that the CLDR data is organized. + * + * @param field such as UDATPG_ERA_FIELD. + * @param value name of the field + * @draft ICU 3.8 + */ + void setAppendItemName(UDateTimePatternField field, const UnicodeString& value); + + /** + * Getter corresponding to setAppendItemNames. Values below 0 or at or above + * UDATPG_FIELD_COUNT are illegal arguments. + * + * @param field such as UDATPG_ERA_FIELD. + * @return name for field + * @draft ICU 3.8 + */ + const UnicodeString& getAppendItemName(UDateTimePatternField field) const; + + /** + * The date time format is a message format pattern used to compose date and + * time patterns. The default value is "{0} {1}", where {0} will be replaced + * by the date pattern and {1} will be replaced by the time pattern. + * <p> + * This is used when the input skeleton contains both date and time fields, + * but there is not a close match among the added patterns. For example, + * suppose that this object was created by adding "dd-MMM" and "hh:mm", and + * its datetimeFormat is the default "{0} {1}". Then if the input skeleton + * is "MMMdhmm", there is not an exact match, so the input skeleton is + * broken up into two components "MMMd" and "hmm". There are close matches + * for those two skeletons, so the result is put together with this pattern, + * resulting in "d-MMM h:mm". + * + * @param dateTimeFormat + * message format pattern, here {0} will be replaced by the date + * pattern and {1} will be replaced by the time pattern. + * @draft ICU 3.8 + */ + void setDateTimeFormat(const UnicodeString& dateTimeFormat); + + /** + * Getter corresponding to setDateTimeFormat. + * @return DateTimeFormat. + * @draft ICU 3.8 + */ + const UnicodeString& getDateTimeFormat() const; + + /** + * Return the best pattern matching the input skeleton. It is guaranteed to + * have all of the fields in the skeleton. + * + * @param skeleton + * The skeleton is a pattern containing only the variable fields. + * For example, "MMMdd" and "mmhh" are skeletons. + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return bestPattern + * The best pattern found from the given skeleton. + * @draft ICU 3.8 + */ + UnicodeString getBestPattern(const UnicodeString& skeleton, UErrorCode& status); + + + /** + * Adjusts the field types (width and subtype) of a pattern to match what is + * in a skeleton. That is, if you supply a pattern like "d-M H:m", and a + * skeleton of "MMMMddhhmm", then the input pattern is adjusted to be + * "dd-MMMM hh:mm". This is used internally to get the best match for the + * input skeleton, but can also be used externally. + * + * @param pattern Input pattern + * @param skeleton + * The skeleton is a pattern containing only the variable fields. + * For example, "MMMdd" and "mmhh" are skeletons. + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return pattern adjusted to match the skeleton fields widths and subtypes. + * @draft ICU 3.8 + */ + UnicodeString replaceFieldTypes(const UnicodeString& pattern, + const UnicodeString& skeleton, + UErrorCode& status); + + /** + * Return a list of all the skeletons (in canonical form) from this class. + * + * Call getPatternForSkeleton() to get the corresponding pattern. + * + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return StringEnumeration with the skeletons. + * The caller must delete the object. + * @draft ICU 3.8 + */ + StringEnumeration* getSkeletons(UErrorCode& status) const; + + /** + * Get the pattern corresponding to a given skeleton. + * @param skeleton + * @return pattern corresponding to a given skeleton. + * @draft ICU 3.8 + */ + const UnicodeString& getPatternForSkeleton(const UnicodeString& skeleton) const; + + /** + * Return a list of all the base skeletons (in canonical form) from this class. + * + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return a StringEnumeration with the base skeletons. + * The caller must delete the object. + * @draft ICU 3.8 + */ + StringEnumeration* getBaseSkeletons(UErrorCode& status) const; + + /** + * Return a list of redundant patterns are those which if removed, make no + * difference in the resulting getBestPattern values. This method returns a + * list of them, to help check the consistency of the patterns used to build + * this generator. + * + * @param status Output param set to success/failure code on exit, + * which must not indicate a failure before the function call. + * @return a StringEnumeration with the redundant pattern. + * The caller must delete the object. + * @internal ICU 3.8 + */ + StringEnumeration* getRedundants(UErrorCode& status); + + /** + * The decimal value is used in formatting fractions of seconds. If the + * skeleton contains fractional seconds, then this is used with the + * fractional seconds. For example, suppose that the input pattern is + * "hhmmssSSSS", and the best matching pattern internally is "H:mm:ss", and + * the decimal string is ",". Then the resulting pattern is modified to be + * "H:mm:ss,SSSS" + * + * @param decimal + * @draft ICU 3.8 + */ + void setDecimal(const UnicodeString& decimal); + + /** + * Getter corresponding to setDecimal. + * @return UnicodeString corresponding to the decimal point + * @draft ICU 3.8 + */ + const UnicodeString& getDecimal() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +private: + /** + * Constructor. + * @draft ICU 3.8 + */ + DateTimePatternGenerator(UErrorCode & status); + + /** + * Constructor. + * @draft ICU 3.8 + */ + DateTimePatternGenerator(const Locale& locale, UErrorCode & status); + + /** + * Copy constructor. + * @param other DateTimePatternGenerator to copy + * @draft ICU 3.8 + */ + DateTimePatternGenerator(const DateTimePatternGenerator& other); + + /** + * Default assignment operator. + * @param other DateTimePatternGenerator to copy + * @draft ICU 3.8 + */ + DateTimePatternGenerator& operator=(const DateTimePatternGenerator& other); + + Locale pLocale; // pattern locale + FormatParser *fp; + DateTimeMatcher* dtMatcher; + DistanceInfo *distanceInfo; + PatternMap *patternMap; + UnicodeString appendItemFormats[UDATPG_FIELD_COUNT]; + UnicodeString appendItemNames[UDATPG_FIELD_COUNT]; + UnicodeString dateTimeFormat; + UnicodeString decimal; + DateTimeMatcher *skipMatcher; + Hashtable *fAvailableFormatKeyHash; + UnicodeString hackPattern; + UErrorCode fStatus; + UnicodeString emptyString; + + void initData(const Locale &locale); + void addCanonicalItems(); + void addICUPatterns(const Locale& locale, UErrorCode& status); + void hackTimes(const UnicodeString& hackPattern, UErrorCode& status); + void addCLDRData(const Locale& locale); + void initHashtable(UErrorCode& status); + void setDateTimeFromCalendar(const Locale& locale, UErrorCode& status); + void setDecimalSymbols(const Locale& locale, UErrorCode& status); + UDateTimePatternField getAppendFormatNumber(const char* field) const; + UDateTimePatternField getAppendNameNumber(const char* field) const; + void getAppendName(UDateTimePatternField field, UnicodeString& value); + int32_t getCanonicalIndex(const UnicodeString& field); + const UnicodeString* getBestRaw(DateTimeMatcher& source, int32_t includeMask, DistanceInfo* missingFields); + UnicodeString adjustFieldTypes(const UnicodeString& pattern, UBool fixFractionalSeconds); + UnicodeString getBestAppending(int32_t missingFields); + int32_t getTopBitNumber(int32_t foundMask); + void setAvailableFormat(const UnicodeString &key, UErrorCode& status); + UBool isAvailableFormatSet(const UnicodeString &key) const; + void copyHashtable(Hashtable *other); + UBool isCanonicalItem(const UnicodeString& item) const; + UErrorCode getStatus() const { return fStatus; } ; +} ;// end class DateTimePatternGenerator + +U_NAMESPACE_END + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/dtrule.h b/Build/source/libs/icu-xetex/i18n/unicode/dtrule.h new file mode 100644 index 00000000000..7bdacd06aea --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/dtrule.h @@ -0,0 +1,250 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef DTRULE_H +#define DTRULE_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Rule for specifying date and time in an year + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN +/** + * <code>DateTimeRule</code> is a class representing a time in a year by + * a rule specified by month, day of month, day of week and + * time in the day. + * + * @draft ICU 3.8 + */ +class U_I18N_API DateTimeRule : public UObject { +public: + + /** + * Date rule type constants. + * @draft ICU 3.8 + */ + enum DateRuleType { + DOM = 0, /**< The exact day of month, + for example, March 11. */ + DOW, /**< The Nth occurence of the day of week, + for example, 2nd Sunday in March. */ + DOW_GEQ_DOM, /**< The first occurence of the day of week on or after the day of monnth, + for example, first Sunday on or after March 8. */ + DOW_LEQ_DOM /**< The last occurence of the day of week on or before the day of month, + for example, first Sunday on or before March 14. */ + }; + + /** + * Time rule type constants. + * @draft ICU 3.8 + */ + enum TimeRuleType { + WALL_TIME = 0, /**< The local wall clock time */ + STANDARD_TIME, /**< The local standard time */ + UTC_TIME /**< The UTC time */ + }; + + /** + * Constructs a <code>DateTimeRule</code> by the day of month and + * the time rule. The date rule type for an instance created by + * this constructor is <code>DOM</code>. + * + * @param month The rule month, for example, <code>Calendar::JANUARY</code> + * @param dayOfMonth The day of month, 1-based. + * @param millisInDay The milliseconds in the rule date. + * @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code> + * or <code>UTC_TIME</code>. + * @draft ICU 3.8 + */ + DateTimeRule(int32_t month, int32_t dayOfMonth, + int32_t millisInDay, TimeRuleType timeType); + + /** + * Constructs a <code>DateTimeRule</code> by the day of week and its oridinal + * number and the time rule. The date rule type for an instance created + * by this constructor is <code>DOW</code>. + * + * @param month The rule month, for example, <code>Calendar::JANUARY</code>. + * @param weekInMonth The ordinal number of the day of week. Negative number + * may be used for specifying a rule date counted from the + * end of the rule month. + * @param dayOfWeek The day of week, for example, <code>Calendar::SUNDAY</code>. + * @param millisInDay The milliseconds in the rule date. + * @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code> + * or <code>UTC_TIME</code>. + * @draft ICU 3.8 + */ + DateTimeRule(int32_t month, int32_t weekInMonth, int32_t dayOfWeek, + int32_t millisInDay, TimeRuleType timeType); + + /** + * Constructs a <code>DateTimeRule</code> by the first/last day of week + * on or after/before the day of month and the time rule. The date rule + * type for an instance created by this constructor is either + * <code>DOM_GEQ_DOM</code> or <code>DOM_LEQ_DOM</code>. + * + * @param month The rule month, for example, <code>Calendar::JANUARY</code> + * @param dayOfMonth The day of month, 1-based. + * @param dayOfWeek The day of week, for example, <code>Calendar::SUNDAY</code>. + * @param after true if the rule date is on or after the day of month. + * @param millisInDay The milliseconds in the rule date. + * @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code> + * or <code>UTC_TIME</code>. + * @draft ICU 3.8 + */ + DateTimeRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, UBool after, + int32_t millisInDay, TimeRuleType timeType); + + /** + * Copy constructor. + * @param source The DateTimeRule object to be copied. + * @draft ICU 3.8 + */ + DateTimeRule(const DateTimeRule& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + ~DateTimeRule(); + + /** + * Clone this DateTimeRule object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + DateTimeRule* clone(void) const; + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + DateTimeRule& operator=(const DateTimeRule& right); + + /** + * Return true if the given DateTimeRule objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given DateTimeRule objects are semantically equal. + * @draft ICU 3.8 + */ + UBool operator==(const DateTimeRule& that) const; + + /** + * Return true if the given DateTimeRule objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given DateTimeRule objects are semantically unequal. + * @draft ICU 3.8 + */ + UBool operator!=(const DateTimeRule& that) const; + + /** + * Gets the date rule type, such as <code>DOM</code> + * @return The date rule type. + * @draft ICU 3.8 + */ + DateRuleType getDateRuleType(void) const; + + /** + * Gets the time rule type + * @return The time rule type, either <code>WALL_TIME</code> or <code>STANDARD_TIME</code> + * or <code>UTC_TIME</code>. + * @draft ICU 3.8 + */ + TimeRuleType getTimeRuleType(void) const; + + /** + * Gets the rule month. + * @return The rule month. + * @draft ICU 3.8 + */ + int32_t getRuleMonth(void) const; + + /** + * Gets the rule day of month. When the date rule type + * is <code>DOW</code>, the value is always 0. + * @return The rule day of month + * @draft ICU 3.8 + */ + int32_t getRuleDayOfMonth(void) const; + + /** + * Gets the rule day of week. When the date rule type + * is <code>DOM</code>, the value is always 0. + * @return The rule day of week. + * @draft ICU 3.8 + */ + int32_t getRuleDayOfWeek(void) const; + + /** + * Gets the ordinal number of the occurence of the day of week + * in the month. When the date rule type is not <code>DOW</code>, + * the value is always 0. + * @return The rule day of week ordinal number in the month. + * @draft ICU 3.8 + */ + int32_t getRuleWeekInMonth(void) const; + + /** + * Gets the rule time in the rule day. + * @return The time in the rule day in milliseconds. + * @draft ICU 3.8 + */ + int32_t getRuleMillisInDay(void) const; + +private: + int32_t fMonth; + int32_t fDayOfMonth; + int32_t fDayOfWeek; + int32_t fWeekInMonth; + int32_t fMillisInDay; + DateRuleType fDateRuleType; + TimeRuleType fTimeRuleType; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // DTRULE_H +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/fieldpos.h b/Build/source/libs/icu-xetex/i18n/unicode/fieldpos.h new file mode 100644 index 00000000000..38a9576e782 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/fieldpos.h @@ -0,0 +1,291 @@ +/* + ******************************************************************************** + * Copyright (C) 1997-2006, International Business Machines + * Corporation and others. All Rights Reserved. + ******************************************************************************** + * + * File FIELDPOS.H + * + * Modification History: + * + * Date Name Description + * 02/25/97 aliu Converted from java. + * 03/17/97 clhuang Updated per Format implementation. + * 07/17/98 stephen Added default/copy ctors, and operators =, ==, != + ******************************************************************************** + */ + +// ***************************************************************************** +// This file was generated from the java source file FieldPosition.java +// ***************************************************************************** + +#ifndef FIELDPOS_H +#define FIELDPOS_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: FieldPosition identifies the fields in a formatted output. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN + +/** + * <code>FieldPosition</code> is a simple class used by <code>Format</code> + * and its subclasses to identify fields in formatted output. Fields are + * identified by constants, whose names typically end with <code>_FIELD</code>, + * defined in the various subclasses of <code>Format</code>. See + * <code>ERA_FIELD</code> and its friends in <code>DateFormat</code> for + * an example. + * + * <p> + * <code>FieldPosition</code> keeps track of the position of the + * field within the formatted output with two indices: the index + * of the first character of the field and the index of the last + * character of the field. + * + * <p> + * One version of the <code>format</code> method in the various + * <code>Format</code> classes requires a <code>FieldPosition</code> + * object as an argument. You use this <code>format</code> method + * to perform partial formatting or to get information about the + * formatted output (such as the position of a field). + * + * The FieldPosition class is not suitable for subclassing. + * + * <p> + * Below is an example of using <code>FieldPosition</code> to aid + * alignment of an array of formatted floating-point numbers on + * their decimal points: + * <pre> + * \code + * double doubleNum[] = {123456789.0, -12345678.9, 1234567.89, -123456.789, + * 12345.6789, -1234.56789, 123.456789, -12.3456789, 1.23456789}; + * int dNumSize = (int)(sizeof(doubleNum)/sizeof(double)); + * + * UErrorCode status = U_ZERO_ERROR; + * DecimalFormat* fmt = (DecimalFormat*) NumberFormat::createInstance(status); + * fmt->setDecimalSeparatorAlwaysShown(true); + * + * const int tempLen = 20; + * char temp[tempLen]; + * + * for (int i=0; i<dNumSize; i++) { + * FieldPosition pos(NumberFormat::INTEGER_FIELD); + * UnicodeString buf; + * char fmtText[tempLen]; + * ToCharString(fmt->format(doubleNum[i], buf, pos), fmtText); + * for (int j=0; j<tempLen; j++) temp[j] = ' '; // clear with spaces + * temp[__min(tempLen, tempLen-pos.getEndIndex())] = '\0'; + * cout << temp << fmtText << endl; + * } + * delete fmt; + * \endcode + * </pre> + * <p> + * The code will generate the following output: + * <pre> + * \code + * 123,456,789.000 + * -12,345,678.900 + * 1,234,567.880 + * -123,456.789 + * 12,345.678 + * -1,234.567 + * 123.456 + * -12.345 + * 1.234 + * \endcode + * </pre> + */ +class U_I18N_API FieldPosition : public UObject { +public: + /** + * DONT_CARE may be specified as the field to indicate that the + * caller doesn't need to specify a field. Do not subclass. + */ + enum { DONT_CARE = -1 }; + + /** + * Creates a FieldPosition object with a non-specified field. + * @stable ICU 2.0 + */ + FieldPosition() + : UObject(), fField(DONT_CARE), fBeginIndex(0), fEndIndex(0) {} + + /** + * Creates a FieldPosition object for the given field. Fields are + * identified by constants, whose names typically end with _FIELD, + * in the various subclasses of Format. + * + * @see NumberFormat#INTEGER_FIELD + * @see NumberFormat#FRACTION_FIELD + * @see DateFormat#YEAR_FIELD + * @see DateFormat#MONTH_FIELD + * @stable ICU 2.0 + */ + FieldPosition(int32_t field) + : UObject(), fField(field), fBeginIndex(0), fEndIndex(0) {} + + /** + * Copy constructor + * @param copy the object to be copied from. + * @stable ICU 2.0 + */ + FieldPosition(const FieldPosition& copy) + : UObject(copy), fField(copy.fField), fBeginIndex(copy.fBeginIndex), fEndIndex(copy.fEndIndex) {} + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~FieldPosition(); + + /** + * Assignment operator + * @param copy the object to be copied from. + * @stable ICU 2.0 + */ + FieldPosition& operator=(const FieldPosition& copy); + + /** + * Equality operator. + * @param that the object to be compared with. + * @return TRUE if the two field positions are equal, FALSE otherwise. + * @stable ICU 2.0 + */ + UBool operator==(const FieldPosition& that) const; + + /** + * Equality operator. + * @param that the object to be compared with. + * @return TRUE if the two field positions are not equal, FALSE otherwise. + * @stable ICU 2.0 + */ + UBool operator!=(const FieldPosition& that) const; + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + FieldPosition *clone() const; + + /** + * Retrieve the field identifier. + * @return the field identifier. + * @stable ICU 2.0 + */ + int32_t getField(void) const { return fField; } + + /** + * Retrieve the index of the first character in the requested field. + * @return the index of the first character in the requested field. + * @stable ICU 2.0 + */ + int32_t getBeginIndex(void) const { return fBeginIndex; } + + /** + * Retrieve the index of the character following the last character in the + * requested field. + * @return the index of the character following the last character in the + * requested field. + * @stable ICU 2.0 + */ + int32_t getEndIndex(void) const { return fEndIndex; } + + /** + * Set the field. + * @param f the new value of the field. + * @stable ICU 2.0 + */ + void setField(int32_t f) { fField = f; } + + /** + * Set the begin index. For use by subclasses of Format. + * @param bi the new value of the begin index + * @stable ICU 2.0 + */ + void setBeginIndex(int32_t bi) { fBeginIndex = bi; } + + /** + * Set the end index. For use by subclasses of Format. + * @param ei the new value of the end index + * @stable ICU 2.0 + */ + void setEndIndex(int32_t ei) { fEndIndex = ei; } + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + /** + * Input: Desired field to determine start and end offsets for. + * The meaning depends on the subclass of Format. + */ + int32_t fField; + + /** + * Output: Start offset of field in text. + * If the field does not occur in the text, 0 is returned. + */ + int32_t fBeginIndex; + + /** + * Output: End offset of field in text. + * If the field does not occur in the text, 0 is returned. + */ + int32_t fEndIndex; +}; + +inline FieldPosition& +FieldPosition::operator=(const FieldPosition& copy) +{ + fField = copy.fField; + fEndIndex = copy.fEndIndex; + fBeginIndex = copy.fBeginIndex; + return *this; +} + +inline UBool +FieldPosition::operator==(const FieldPosition& copy) const +{ + return (fField == copy.fField && + fEndIndex == copy.fEndIndex && + fBeginIndex == copy.fBeginIndex); +} + +inline UBool +FieldPosition::operator!=(const FieldPosition& copy) const +{ + return !operator==(copy); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _FIELDPOS +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/fmtable.h b/Build/source/libs/icu-xetex/i18n/unicode/fmtable.h new file mode 100644 index 00000000000..94ee32843f5 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/fmtable.h @@ -0,0 +1,591 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2006, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File FMTABLE.H +* +* Modification History: +* +* Date Name Description +* 02/29/97 aliu Creation. +******************************************************************************** +*/ +#ifndef FMTABLE_H +#define FMTABLE_H + +#include "unicode/utypes.h" +#include "unicode/unistr.h" +/** + * \file + * \brief C++ API: Formattable is a thin wrapper for primitive numeric types. + */ + +#if !UCONFIG_NO_FORMATTING + +U_NAMESPACE_BEGIN + +/** + * Formattable objects can be passed to the Format class or + * its subclasses for formatting. Formattable is a thin wrapper + * class which interconverts between the primitive numeric types + * (double, long, etc.) as well as UDate and UnicodeString. + * + * <p>Internally, a Formattable object is a union of primitive types. + * As such, it can only store one flavor of data at a time. To + * determine what flavor of data it contains, use the getType method. + * + * <p>As of ICU 3.0, Formattable may also wrap a UObject pointer, + * which it owns. This allows an instance of any ICU class to be + * encapsulated in a Formattable. For legacy reasons and for + * efficiency, primitive numeric types are still stored directly + * within a Formattable. + * + * <p>The Formattable class is not suitable for subclassing. + */ +class U_I18N_API Formattable : public UObject { +public: + /** + * This enum is only used to let callers distinguish between + * the Formattable(UDate) constructor and the Formattable(double) + * constructor; the compiler cannot distinguish the signatures, + * since UDate is currently typedefed to be either double or long. + * If UDate is changed later to be a bonafide class + * or struct, then we no longer need this enum. + * @stable ICU 2.4 + */ + enum ISDATE { kIsDate }; + + /** + * Default constructor + * @stable ICU 2.4 + */ + Formattable(); // Type kLong, value 0 + + /** + * Creates a Formattable object with a UDate instance. + * @param d the UDate instance. + * @param flag the flag to indicate this is a date. Always set it to kIsDate + * @stable ICU 2.0 + */ + Formattable(UDate d, ISDATE flag); + + /** + * Creates a Formattable object with a double number. + * @param d the double number. + * @stable ICU 2.0 + */ + Formattable(double d); + + /** + * Creates a Formattable object with a long number. + * @param l the long number. + * @stable ICU 2.0 + */ + Formattable(int32_t l); + + /** + * Creates a Formattable object with an int64_t number + * @param ll the int64_t number. + * @stable ICU 2.8 + */ + Formattable(int64_t ll); + +#if !UCONFIG_NO_CONVERSION + /** + * Creates a Formattable object with a char string pointer. + * Assumes that the char string is null terminated. + * @param strToCopy the char string. + * @stable ICU 2.0 + */ + Formattable(const char* strToCopy); +#endif + + /** + * Creates a Formattable object with a UnicodeString object to copy from. + * @param strToCopy the UnicodeString string. + * @stable ICU 2.0 + */ + Formattable(const UnicodeString& strToCopy); + + /** + * Creates a Formattable object with a UnicodeString object to adopt from. + * @param strToAdopt the UnicodeString string. + * @stable ICU 2.0 + */ + Formattable(UnicodeString* strToAdopt); + + /** + * Creates a Formattable object with an array of Formattable objects. + * @param arrayToCopy the Formattable object array. + * @param count the array count. + * @stable ICU 2.0 + */ + Formattable(const Formattable* arrayToCopy, int32_t count); + + /** + * Creates a Formattable object that adopts the given UObject. + * @param objectToAdopt the UObject to set this object to + * @stable ICU 3.0 + */ + Formattable(UObject* objectToAdopt); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + Formattable(const Formattable&); + + /** + * Assignment operator. + * @param rhs The Formattable object to copy into this object. + * @stable ICU 2.0 + */ + Formattable& operator=(const Formattable &rhs); + + /** + * Equality comparison. + * @param other the object to be compared with. + * @return TRUE if other are equal to this, FALSE otherwise. + * @stable ICU 2.0 + */ + UBool operator==(const Formattable &other) const; + + /** + * Equality operator. + * @param other the object to be compared with. + * @return TRUE if other are unequal to this, FALSE otherwise. + * @stable ICU 2.0 + */ + UBool operator!=(const Formattable& other) const + { return !operator==(other); } + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~Formattable(); + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + Formattable *clone() const; + + /** + * Selector for flavor of data type contained within a + * Formattable object. Formattable is a union of several + * different types, and at any time contains exactly one type. + * @stable ICU 2.4 + */ + enum Type { + /** + * Selector indicating a UDate value. Use getDate to retrieve + * the value. + * @stable ICU 2.4 + */ + kDate, + + /** + * Selector indicating a double value. Use getDouble to + * retrieve the value. + * @stable ICU 2.4 + */ + kDouble, + + /** + * Selector indicating a 32-bit integer value. Use getLong to + * retrieve the value. + * @stable ICU 2.4 + */ + kLong, + + /** + * Selector indicating a UnicodeString value. Use getString + * to retrieve the value. + * @stable ICU 2.4 + */ + kString, + + /** + * Selector indicating an array of Formattables. Use getArray + * to retrieve the value. + * @stable ICU 2.4 + */ + kArray, + + /** + * Selector indicating a 64-bit integer value. Use getInt64 + * to retrieve the value. + * @stable ICU 2.8 + */ + kInt64, + + /** + * Selector indicating a UObject value. Use getObject to + * retrieve the value. + * @stable ICU 3.0 + */ + kObject + }; + + /** + * Gets the data type of this Formattable object. + * @return the data type of this Formattable object. + * @stable ICU 2.0 + */ + Type getType(void) const; + + /** + * Returns TRUE if the data type of this Formattable object + * is kDouble, kLong, or kInt64. + * @return TRUE if this is a pure numeric object + * @stable ICU 3.0 + */ + UBool isNumeric() const; + + /** + * Gets the double value of this object. If this object is not of type + * kDouble then the result is undefined. + * @return the double value of this object. + * @stable ICU 2.0 + */ + double getDouble(void) const { return fValue.fDouble; } + + /** + * Gets the double value of this object. If this object is of type + * long or int64 then a casting conversion is peformed, with + * possible loss of precision. If the type is kObject and the + * object is a Measure, then the result of + * getNumber().getDouble(status) is returned. If this object is + * neither a numeric type nor a Measure, then 0 is returned and + * the status is set to U_INVALID_FORMAT_ERROR. + * @param status the error code + * @return the double value of this object. + * @stable ICU 3.0 + */ + double getDouble(UErrorCode& status) const; + + /** + * Gets the long value of this object. If this object is not of type + * kLong then the result is undefined. + * @return the long value of this object. + * @stable ICU 2.0 + */ + int32_t getLong(void) const { return (int32_t)fValue.fInt64; } + + /** + * Gets the long value of this object. If the magnitude is too + * large to fit in a long, then the maximum or minimum long value, + * as appropriate, is returned and the status is set to + * U_INVALID_FORMAT_ERROR. If this object is of type kInt64 and + * it fits within a long, then no precision is lost. If it is of + * type kDouble, then a casting conversion is peformed, with + * truncation of any fractional part. If the type is kObject and + * the object is a Measure, then the result of + * getNumber().getLong(status) is returned. If this object is + * neither a numeric type nor a Measure, then 0 is returned and + * the status is set to U_INVALID_FORMAT_ERROR. + * @param status the error code + * @return the long value of this object. + * @stable ICU 3.0 + */ + int32_t getLong(UErrorCode& status) const; + + /** + * Gets the int64 value of this object. If this object is not of type + * kInt64 then the result is undefined. + * @return the int64 value of this object. + * @stable ICU 2.8 + */ + int64_t getInt64(void) const { return fValue.fInt64; } + + /** + * Gets the int64 value of this object. If this object is of type + * kDouble and the magnitude is too large to fit in an int64, then + * the maximum or minimum int64 value, as appropriate, is returned + * and the status is set to U_INVALID_FORMAT_ERROR. If the + * magnitude fits in an int64, then a casting conversion is + * peformed, with truncation of any fractional part. If the type + * is kObject and the object is a Measure, then the result of + * getNumber().getDouble(status) is returned. If this object is + * neither a numeric type nor a Measure, then 0 is returned and + * the status is set to U_INVALID_FORMAT_ERROR. + * @param status the error code + * @return the int64 value of this object. + * @stable ICU 3.0 + */ + int64_t getInt64(UErrorCode& status) const; + + /** + * Gets the Date value of this object. If this object is not of type + * kDate then the result is undefined. + * @return the Date value of this object. + * @stable ICU 2.0 + */ + UDate getDate() const { return fValue.fDate; } + + /** + * Gets the Date value of this object. If the type is not a date, + * status is set to U_INVALID_FORMAT_ERROR and the return value is + * undefined. + * @param status the error code. + * @return the Date value of this object. + * @stable ICU 3.0 + */ + UDate getDate(UErrorCode& status) const; + + /** + * Gets the string value of this object. If this object is not of type + * kString then the result is undefined. + * @param result Output param to receive the Date value of this object. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getString(UnicodeString& result) const + { result=*fValue.fString; return result; } + + /** + * Gets the string value of this object. If the type is not a + * string, status is set to U_INVALID_FORMAT_ERROR and a bogus + * string is returned. + * @param result Output param to receive the Date value of this object. + * @param status the error code. + * @return A reference to 'result'. + * @stable ICU 3.0 + */ + UnicodeString& getString(UnicodeString& result, UErrorCode& status) const; + + /** + * Gets a const reference to the string value of this object. If + * this object is not of type kString then the result is + * undefined. + * @return a const reference to the string value of this object. + * @stable ICU 2.0 + */ + inline const UnicodeString& getString(void) const; + + /** + * Gets a const reference to the string value of this object. If + * the type is not a string, status is set to + * U_INVALID_FORMAT_ERROR and the result is a bogus string. + * @param status the error code. + * @return a const reference to the string value of this object. + * @stable ICU 3.0 + */ + const UnicodeString& getString(UErrorCode& status) const; + + /** + * Gets a reference to the string value of this object. If this + * object is not of type kString then the result is undefined. + * @return a reference to the string value of this object. + * @stable ICU 2.0 + */ + inline UnicodeString& getString(void); + + /** + * Gets a reference to the string value of this object. If the + * type is not a string, status is set to U_INVALID_FORMAT_ERROR + * and the result is a bogus string. + * @param status the error code. + * @return a reference to the string value of this object. + * @stable ICU 3.0 + */ + UnicodeString& getString(UErrorCode& status); + + /** + * Gets the array value and count of this object. If this object + * is not of type kArray then the result is undefined. + * @param count fill-in with the count of this object. + * @return the array value of this object. + * @stable ICU 2.0 + */ + const Formattable* getArray(int32_t& count) const + { count=fValue.fArrayAndCount.fCount; return fValue.fArrayAndCount.fArray; } + + /** + * Gets the array value and count of this object. If the type is + * not an array, status is set to U_INVALID_FORMAT_ERROR, count is + * set to 0, and the result is NULL. + * @param count fill-in with the count of this object. + * @param status the error code. + * @return the array value of this object. + * @stable ICU 3.0 + */ + const Formattable* getArray(int32_t& count, UErrorCode& status) const; + + /** + * Accesses the specified element in the array value of this + * Formattable object. If this object is not of type kArray then + * the result is undefined. + * @param index the specified index. + * @return the accessed element in the array. + * @stable ICU 2.0 + */ + Formattable& operator[](int32_t index) { return fValue.fArrayAndCount.fArray[index]; } + + /** + * Returns a pointer to the UObject contained within this + * formattable, or NULL if this object does not contain a UObject. + * @return a UObject pointer, or NULL + * @stable ICU 3.0 + */ + const UObject* getObject() const; + + /** + * Sets the double value of this object and changes the type to + * kDouble. + * @param d the new double value to be set. + * @stable ICU 2.0 + */ + void setDouble(double d); + + /** + * Sets the long value of this object and changes the type to + * kLong. + * @param l the new long value to be set. + * @stable ICU 2.0 + */ + void setLong(int32_t l); + + /** + * Sets the int64 value of this object and changes the type to + * kInt64. + * @param ll the new int64 value to be set. + * @stable ICU 2.8 + */ + void setInt64(int64_t ll); + + /** + * Sets the Date value of this object and changes the type to + * kDate. + * @param d the new Date value to be set. + * @stable ICU 2.0 + */ + void setDate(UDate d); + + /** + * Sets the string value of this object and changes the type to + * kString. + * @param stringToCopy the new string value to be set. + * @stable ICU 2.0 + */ + void setString(const UnicodeString& stringToCopy); + + /** + * Sets the array value and count of this object and changes the + * type to kArray. + * @param array the array value. + * @param count the number of array elements to be copied. + * @stable ICU 2.0 + */ + void setArray(const Formattable* array, int32_t count); + + /** + * Sets and adopts the string value and count of this object and + * changes the type to kArray. + * @param stringToAdopt the new string value to be adopted. + * @stable ICU 2.0 + */ + void adoptString(UnicodeString* stringToAdopt); + + /** + * Sets and adopts the array value and count of this object and + * changes the type to kArray. + * @stable ICU 2.0 + */ + void adoptArray(Formattable* array, int32_t count); + + /** + * Sets and adopts the UObject value of this object and changes + * the type to kObject. After this call, the caller must not + * delete the given object. + * @param objectToAdopt the UObject value to be adopted + * @stable ICU 3.0 + */ + void adoptObject(UObject* objectToAdopt); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * Deprecated variant of getLong(UErrorCode&). + * @param status the error code + * @return the long value of this object. + * @deprecated ICU 3.0 use getLong(UErrorCode&) instead + */ + inline int32_t getLong(UErrorCode* status) const; + +private: + /** + * Cleans up the memory for unwanted values. For example, the adopted + * string or array objects. + */ + void dispose(void); + + UnicodeString* getBogus() const; + + union { + UObject* fObject; + UnicodeString* fString; + double fDouble; + int64_t fInt64; + UDate fDate; + struct { + Formattable* fArray; + int32_t fCount; + } fArrayAndCount; + } fValue; + + Type fType; + UnicodeString fBogus; // Bogus string when it's needed. +}; + +inline UDate Formattable::getDate(UErrorCode& status) const { + if (fType != kDate) { + if (U_SUCCESS(status)) { + status = U_INVALID_FORMAT_ERROR; + } + return 0; + } + return fValue.fDate; +} + +inline const UnicodeString& Formattable::getString(void) const { + return *fValue.fString; +} + +inline UnicodeString& Formattable::getString(void) { + return *fValue.fString; +} + +inline int32_t Formattable::getLong(UErrorCode* status) const { + return getLong(*status); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif //_FMTABLE +//eof + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/format.h b/Build/source/libs/icu-xetex/i18n/unicode/format.h new file mode 100644 index 00000000000..7f17b52f00a --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/format.h @@ -0,0 +1,296 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2006, International Business Machines Corporation and others. +* All Rights Reserved. +******************************************************************************** +* +* File FORMAT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/17/97 clhuang Updated per C++ implementation. +* 03/27/97 helena Updated to pass the simple test after code review. +******************************************************************************** +*/ +// ***************************************************************************** +// This file was generated from the java source file Format.java +// ***************************************************************************** + +#ifndef FORMAT_H +#define FORMAT_H + + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Base class for all formats. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/unistr.h" +#include "unicode/fmtable.h" +#include "unicode/fieldpos.h" +#include "unicode/parsepos.h" +#include "unicode/parseerr.h" +#include "unicode/locid.h" + +U_NAMESPACE_BEGIN + +/** + * Base class for all formats. This is an abstract base class which + * specifies the protocol for classes which convert other objects or + * values, such as numeric values and dates, and their string + * representations. In some cases these representations may be + * localized or contain localized characters or strings. For example, + * a numeric formatter such as DecimalFormat may convert a numeric + * value such as 12345 to the string "$12,345". It may also parse + * the string back into a numeric value. A date and time formatter + * like SimpleDateFormat may represent a specific date, encoded + * numerically, as a string such as "Wednesday, February 26, 1997 AD". + * <P> + * Many of the concrete subclasses of Format employ the notion of + * a pattern. A pattern is a string representation of the rules which + * govern the interconversion between values and strings. For example, + * a DecimalFormat object may be associated with the pattern + * "$#,##0.00;($#,##0.00)", which is a common US English format for + * currency values, yielding strings such as "$1,234.45" for 1234.45, + * and "($987.65)" for 987.6543. The specific syntax of a pattern + * is defined by each subclass. + * <P> + * Even though many subclasses use patterns, the notion of a pattern + * is not inherent to Format classes in general, and is not part of + * the explicit base class protocol. + * <P> + * Two complex formatting classes bear mentioning. These are + * MessageFormat and ChoiceFormat. ChoiceFormat is a subclass of + * NumberFormat which allows the user to format different number ranges + * as strings. For instance, 0 may be represented as "no files", 1 as + * "one file", and any number greater than 1 as "many files". + * MessageFormat is a formatter which utilizes other Format objects to + * format a string containing with multiple values. For instance, + * A MessageFormat object might produce the string "There are no files + * on the disk MyDisk on February 27, 1997." given the arguments 0, + * "MyDisk", and the date value of 2/27/97. See the ChoiceFormat + * and MessageFormat headers for further information. + * <P> + * If formatting is unsuccessful, a failing UErrorCode is returned when + * the Format cannot format the type of object, otherwise if there is + * something illformed about the the Unicode replacement character + * 0xFFFD is returned. + * <P> + * If there is no match when parsing, a parse failure UErrorCode is + * retured for methods which take no ParsePosition. For the method + * that takes a ParsePosition, the index parameter is left unchanged. + * <P> + * <em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API Format : public UObject { +public: + + /** Destructor + * @stable ICU 2.4 + */ + virtual ~Format(); + + /** + * Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * @param other the object to be compared with. + * @return Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const = 0; + + /** + * Return true if the given Format objects are not semantically + * equal. + * @param other the object to be compared with. + * @return Return true if the given Format objects are not semantically. + * @stable ICU 2.0 + */ + UBool operator!=(const Format& other) const { return !operator==(other); } + + /** + * Clone this object polymorphically. The caller is responsible + * for deleting the result when done. + * @return A copy of the object + * @stable ICU 2.0 + */ + virtual Format* clone() const = 0; + + /** + * Formats an object to produce a string. + * + * @param obj The object to format. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Output parameter filled in with success or failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Format an object to produce a string. This is a pure virtual method which + * subclasses must implement. This method allows polymorphic formatting + * of Formattable objects. If a subclass of Format receives a Formattable + * object type it doesn't handle (e.g., if a numeric Formattable is passed + * to a DateFormat object) then it returns a failing UErrorCode. + * + * @param obj The object to format. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Output param filled with success/failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const = 0; + + /** + * Parse a string to produce an object. This is a pure virtual + * method which subclasses must implement. This method allows + * polymorphic parsing of strings into Formattable objects. + * <P> + * Before calling, set parse_pos.index to the offset you want to + * start parsing at in the source. After calling, parse_pos.index + * is the end of the text you parsed. If error occurs, index is + * unchanged. + * <P> + * When parsing, leading whitespace is discarded (with successful + * parse), while trailing whitespace is left as is. + * <P> + * Example: + * <P> + * Parsing "_12_xy" (where _ represents a space) for a number, + * with index == 0 will result in the number 12, with + * parse_pos.index updated to 3 (just before the second space). + * Parsing a second time will result in a failing UErrorCode since + * "xy" is not a number, and leave index at 3. + * <P> + * Subclasses will typically supply specific parse methods that + * return different types of values. Since methods can't overload + * on return types, these will typically be named "parse", while + * this polymorphic method will always be called parseObject. Any + * parse method that does not take a parse_pos should set status + * to an error value when no text in the required format is at the + * start position. + * + * @param source The string to be parsed into an object. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parse_pos The position to start parsing at. Upon return + * this param is set to the position after the + * last character successfully parsed. If the + * source is not parsed successfully, this param + * will remain unchanged. + * @stable ICU 2.0 + */ + virtual void parseObject(const UnicodeString& source, + Formattable& result, + ParsePosition& parse_pos) const = 0; + + /** + * Parses a string to produce an object. This is a convenience method + * which calls the pure virtual parseObject() method, and returns a + * failure UErrorCode if the ParsePosition indicates failure. + * + * @param source The string to be parsed into an object. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param status Output param to be filled with success/failure + * result code. + * @stable ICU 2.0 + */ + void parseObject(const UnicodeString& source, + Formattable& result, + UErrorCode& status) const; + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual method. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * Concrete subclasses of Format must implement getDynamicClassID() + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID() const = 0; + + /** Get the locale for this format object. You can choose between valid and actual locale. + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale + * @stable ICU 2.8 + */ + Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; + + /** Get the locale for this format object. You can choose between valid and actual locale. + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale + * @internal + */ + const char* getLocaleID(ULocDataLocaleType type, UErrorCode &status) const; + + protected: + /** @stable ICU 2.8 */ + void setLocaleIDs(const char* valid, const char* actual); + +protected: + /** + * Default constructor for subclass use only. Does nothing. + * @stable ICU 2.0 + */ + Format(); + + /** + * @stable ICU 2.0 + */ + Format(const Format&); // Does nothing; for subclasses only + + /** + * @stable ICU 2.0 + */ + Format& operator=(const Format&); // Does nothing; for subclasses + + + /** + * Simple function for initializing a UParseError from a UnicodeString. + * + * @param pattern The pattern to copy into the parseError + * @param pos The position in pattern where the error occured + * @param parseError The UParseError object to fill in + * @stable ICU 2.4 + */ + static void syntaxError(const UnicodeString& pattern, + int32_t pos, + UParseError& parseError); + + private: + char actualLocale[ULOC_FULLNAME_CAPACITY]; + char validLocale[ULOC_FULLNAME_CAPACITY]; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _FORMAT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/gregocal.h b/Build/source/libs/icu-xetex/i18n/unicode/gregocal.h new file mode 100644 index 00000000000..f2d1b0b17d5 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/gregocal.h @@ -0,0 +1,823 @@ +/* +* Copyright (C) 1997-2006, International Business Machines Corporation and others. +* All Rights Reserved. +******************************************************************************** +* +* File GREGOCAL.H +* +* Modification History: +* +* Date Name Description +* 04/22/97 aliu Overhauled header. +* 07/28/98 stephen Sync with JDK 1.2 +* 09/04/98 stephen Re-sync with JDK 8/31 putback +* 09/14/98 stephen Changed type of kOneDay, kOneWeek to double. +* Fixed bug in roll() +* 10/15/99 aliu Fixed j31, incorrect WEEK_OF_YEAR computation. +* Added documentation of WEEK_OF_YEAR computation. +* 10/15/99 aliu Fixed j32, cannot set date to Feb 29 2000 AD. +* {JDK bug 4210209 4209272} +* 11/07/2003 srl Update, clean up documentation. +******************************************************************************** +*/ + +#ifndef GREGOCAL_H +#define GREGOCAL_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/calendar.h" + +/** + * \file + * \brief C++ API: Concrete class which provides the standard calendar. + */ + +U_NAMESPACE_BEGIN + +/** + * Concrete class which provides the standard calendar used by most of the world. + * <P> + * The standard (Gregorian) calendar has 2 eras, BC and AD. + * <P> + * This implementation handles a single discontinuity, which corresponds by default to + * the date the Gregorian calendar was originally instituted (October 15, 1582). Not all + * countries adopted the Gregorian calendar then, so this cutover date may be changed by + * the caller. + * <P> + * Prior to the institution of the Gregorian Calendar, New Year's Day was March 25. To + * avoid confusion, this Calendar always uses January 1. A manual adjustment may be made + * if desired for dates that are prior to the Gregorian changeover and which fall + * between January 1 and March 24. + * + * <p>Values calculated for the <code>WEEK_OF_YEAR</code> field range from 1 to + * 53. Week 1 for a year is the first week that contains at least + * <code>getMinimalDaysInFirstWeek()</code> days from that year. It thus + * depends on the values of <code>getMinimalDaysInFirstWeek()</code>, + * <code>getFirstDayOfWeek()</code>, and the day of the week of January 1. + * Weeks between week 1 of one year and week 1 of the following year are + * numbered sequentially from 2 to 52 or 53 (as needed). + * + * <p>For example, January 1, 1998 was a Thursday. If + * <code>getFirstDayOfWeek()</code> is <code>MONDAY</code> and + * <code>getMinimalDaysInFirstWeek()</code> is 4 (these are the values + * reflecting ISO 8601 and many national standards), then week 1 of 1998 starts + * on December 29, 1997, and ends on January 4, 1998. If, however, + * <code>getFirstDayOfWeek()</code> is <code>SUNDAY</code>, then week 1 of 1998 + * starts on January 4, 1998, and ends on January 10, 1998; the first three days + * of 1998 then are part of week 53 of 1997. + * + * <p>Example for using GregorianCalendar: + * <pre> + * \code + * // get the supported ids for GMT-08:00 (Pacific Standard Time) + * UErrorCode success = U_ZERO_ERROR; + * const StringEnumeration *ids = TimeZone::createEnumeration(-8 * 60 * 60 * 1000); + * // if no ids were returned, something is wrong. get out. + * if (ids == 0 || ids->count(success) == 0) { + * return; + * } + * + * // begin output + * cout << "Current Time" << endl; + * + * // create a Pacific Standard Time time zone + * SimpleTimeZone* pdt = new SimpleTimeZone(-8 * 60 * 60 * 1000, ids->unext(NULL, success))); + * + * // set up rules for daylight savings time + * pdt->setStartRule(Calendar::APRIL, 1, Calendar::SUNDAY, 2 * 60 * 60 * 1000); + * pdt->setEndRule(Calendar::OCTOBER, -1, Calendar::SUNDAY, 2 * 60 * 60 * 1000); + * + * // create a GregorianCalendar with the Pacific Daylight time zone + * // and the current date and time + * Calendar* calendar = new GregorianCalendar( pdt, success ); + * + * // print out a bunch of interesting things + * cout << "ERA: " << calendar->get( Calendar::ERA, success ) << endl; + * cout << "YEAR: " << calendar->get( Calendar::YEAR, success ) << endl; + * cout << "MONTH: " << calendar->get( Calendar::MONTH, success ) << endl; + * cout << "WEEK_OF_YEAR: " << calendar->get( Calendar::WEEK_OF_YEAR, success ) << endl; + * cout << "WEEK_OF_MONTH: " << calendar->get( Calendar::WEEK_OF_MONTH, success ) << endl; + * cout << "DATE: " << calendar->get( Calendar::DATE, success ) << endl; + * cout << "DAY_OF_MONTH: " << calendar->get( Calendar::DAY_OF_MONTH, success ) << endl; + * cout << "DAY_OF_YEAR: " << calendar->get( Calendar::DAY_OF_YEAR, success ) << endl; + * cout << "DAY_OF_WEEK: " << calendar->get( Calendar::DAY_OF_WEEK, success ) << endl; + * cout << "DAY_OF_WEEK_IN_MONTH: " << calendar->get( Calendar::DAY_OF_WEEK_IN_MONTH, success ) << endl; + * cout << "AM_PM: " << calendar->get( Calendar::AM_PM, success ) << endl; + * cout << "HOUR: " << calendar->get( Calendar::HOUR, success ) << endl; + * cout << "HOUR_OF_DAY: " << calendar->get( Calendar::HOUR_OF_DAY, success ) << endl; + * cout << "MINUTE: " << calendar->get( Calendar::MINUTE, success ) << endl; + * cout << "SECOND: " << calendar->get( Calendar::SECOND, success ) << endl; + * cout << "MILLISECOND: " << calendar->get( Calendar::MILLISECOND, success ) << endl; + * cout << "ZONE_OFFSET: " << (calendar->get( Calendar::ZONE_OFFSET, success )/(60*60*1000)) << endl; + * cout << "DST_OFFSET: " << (calendar->get( Calendar::DST_OFFSET, success )/(60*60*1000)) << endl; + * + * cout << "Current Time, with hour reset to 3" << endl; + * calendar->clear(Calendar::HOUR_OF_DAY); // so doesn't override + * calendar->set(Calendar::HOUR, 3); + * cout << "ERA: " << calendar->get( Calendar::ERA, success ) << endl; + * cout << "YEAR: " << calendar->get( Calendar::YEAR, success ) << endl; + * cout << "MONTH: " << calendar->get( Calendar::MONTH, success ) << endl; + * cout << "WEEK_OF_YEAR: " << calendar->get( Calendar::WEEK_OF_YEAR, success ) << endl; + * cout << "WEEK_OF_MONTH: " << calendar->get( Calendar::WEEK_OF_MONTH, success ) << endl; + * cout << "DATE: " << calendar->get( Calendar::DATE, success ) << endl; + * cout << "DAY_OF_MONTH: " << calendar->get( Calendar::DAY_OF_MONTH, success ) << endl; + * cout << "DAY_OF_YEAR: " << calendar->get( Calendar::DAY_OF_YEAR, success ) << endl; + * cout << "DAY_OF_WEEK: " << calendar->get( Calendar::DAY_OF_WEEK, success ) << endl; + * cout << "DAY_OF_WEEK_IN_MONTH: " << calendar->get( Calendar::DAY_OF_WEEK_IN_MONTH, success ) << endl; + * cout << "AM_PM: " << calendar->get( Calendar::AM_PM, success ) << endl; + * cout << "HOUR: " << calendar->get( Calendar::HOUR, success ) << endl; + * cout << "HOUR_OF_DAY: " << calendar->get( Calendar::HOUR_OF_DAY, success ) << endl; + * cout << "MINUTE: " << calendar->get( Calendar::MINUTE, success ) << endl; + * cout << "SECOND: " << calendar->get( Calendar::SECOND, success ) << endl; + * cout << "MILLISECOND: " << calendar->get( Calendar::MILLISECOND, success ) << endl; + * cout << "ZONE_OFFSET: " << (calendar->get( Calendar::ZONE_OFFSET, success )/(60*60*1000)) << endl; // in hours + * cout << "DST_OFFSET: " << (calendar->get( Calendar::DST_OFFSET, success )/(60*60*1000)) << endl; // in hours + * + * if (U_FAILURE(success)) { + * cout << "An error occured. success=" << u_errorName(success) << endl; + * } + * + * delete ids; + * delete calendar; // also deletes pdt + * \endcode + * </pre> + * @stable ICU 2.0 + */ +class U_I18N_API GregorianCalendar: public Calendar { +public: + + /** + * Useful constants for GregorianCalendar and TimeZone. + * @stable ICU 2.0 + */ + enum EEras { + BC, + AD + }; + + /** + * Constructs a default GregorianCalendar using the current time in the default time + * zone with the default locale. + * + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(UErrorCode& success); + + /** + * Constructs a GregorianCalendar based on the current time in the given time zone + * with the default locale. Clients are no longer responsible for deleting the given + * time zone object after it's adopted. + * + * @param zoneToAdopt The given timezone. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(TimeZone* zoneToAdopt, UErrorCode& success); + + /** + * Constructs a GregorianCalendar based on the current time in the given time zone + * with the default locale. + * + * @param zone The given timezone. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(const TimeZone& zone, UErrorCode& success); + + /** + * Constructs a GregorianCalendar based on the current time in the default time zone + * with the given locale. + * + * @param aLocale The given locale. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(const Locale& aLocale, UErrorCode& success); + + /** + * Constructs a GregorianCalendar based on the current time in the given time zone + * with the given locale. Clients are no longer responsible for deleting the given + * time zone object after it's adopted. + * + * @param zoneToAdopt The given timezone. + * @param aLocale The given locale. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(TimeZone* zoneToAdopt, const Locale& aLocale, UErrorCode& success); + + /** + * Constructs a GregorianCalendar based on the current time in the given time zone + * with the given locale. + * + * @param zone The given timezone. + * @param aLocale The given locale. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(const TimeZone& zone, const Locale& aLocale, UErrorCode& success); + + /** + * Constructs a GregorianCalendar with the given AD date set in the default time + * zone with the default locale. + * + * @param year The value used to set the YEAR time field in the calendar. + * @param month The value used to set the MONTH time field in the calendar. Month + * value is 0-based. e.g., 0 for January. + * @param date The value used to set the DATE time field in the calendar. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(int32_t year, int32_t month, int32_t date, UErrorCode& success); + + /** + * Constructs a GregorianCalendar with the given AD date and time set for the + * default time zone with the default locale. + * + * @param year The value used to set the YEAR time field in the calendar. + * @param month The value used to set the MONTH time field in the calendar. Month + * value is 0-based. e.g., 0 for January. + * @param date The value used to set the DATE time field in the calendar. + * @param hour The value used to set the HOUR_OF_DAY time field in the calendar. + * @param minute The value used to set the MINUTE time field in the calendar. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute, UErrorCode& success); + + /** + * Constructs a GregorianCalendar with the given AD date and time set for the + * default time zone with the default locale. + * + * @param year The value used to set the YEAR time field in the calendar. + * @param month The value used to set the MONTH time field in the calendar. Month + * value is 0-based. e.g., 0 for January. + * @param date The value used to set the DATE time field in the calendar. + * @param hour The value used to set the HOUR_OF_DAY time field in the calendar. + * @param minute The value used to set the MINUTE time field in the calendar. + * @param second The value used to set the SECOND time field in the calendar. + * @param success Indicates the status of GregorianCalendar object construction. + * Returns U_ZERO_ERROR if constructed successfully. + * @stable ICU 2.0 + */ + GregorianCalendar(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute, int32_t second, UErrorCode& success); + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~GregorianCalendar(); + + /** + * Copy constructor + * @param source the object to be copied. + * @stable ICU 2.0 + */ + GregorianCalendar(const GregorianCalendar& source); + + /** + * Default assignment operator + * @param right the object to be copied. + * @stable ICU 2.0 + */ + GregorianCalendar& operator=(const GregorianCalendar& right); + + /** + * Create and return a polymorphic copy of this calendar. + * @return return a polymorphic copy of this calendar. + * @stable ICU 2.0 + */ + virtual Calendar* clone(void) const; + + /** + * Sets the GregorianCalendar change date. This is the point when the switch from + * Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October + * 15, 1582. Previous to this time and date will be Julian dates. + * + * @param date The given Gregorian cutover date. + * @param success Output param set to success/failure code on exit. + * @stable ICU 2.0 + */ + void setGregorianChange(UDate date, UErrorCode& success); + + /** + * Gets the Gregorian Calendar change date. This is the point when the switch from + * Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October + * 15, 1582. Previous to this time and date will be Julian dates. + * + * @return The Gregorian cutover time for this calendar. + * @stable ICU 2.0 + */ + UDate getGregorianChange(void) const; + + /** + * Return true if the given year is a leap year. Determination of whether a year is + * a leap year is actually very complicated. We do something crude and mostly + * correct here, but for a real determination you need a lot of contextual + * information. For example, in Sweden, the change from Julian to Gregorian happened + * in a complex way resulting in missed leap years and double leap years between + * 1700 and 1753. Another example is that after the start of the Julian calendar in + * 45 B.C., the leap years did not regularize until 8 A.D. This method ignores these + * quirks, and pays attention only to the Julian onset date and the Gregorian + * cutover (which can be changed). + * + * @param year The given year. + * @return True if the given year is a leap year; false otherwise. + * @stable ICU 2.0 + */ + UBool isLeapYear(int32_t year) const; + + /** + * Returns TRUE if the given Calendar object is equivalent to this + * one. Calendar override. + * + * @param other the Calendar to be compared with this Calendar + * @stable ICU 2.4 + */ + virtual UBool isEquivalentTo(const Calendar& other) const; + + /** + * (Overrides Calendar) Rolls up or down by the given amount in the specified field. + * For more information, see the documentation for Calendar::roll(). + * + * @param field The time field. + * @param amount Indicates amount to roll. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @deprecated ICU 2.6. Use roll(UCalendarDateFields field, int32_t amount, UErrorCode& status) instead. + */ + virtual void roll(EDateFields field, int32_t amount, UErrorCode& status); + + /** + * (Overrides Calendar) Rolls up or down by the given amount in the specified field. + * For more information, see the documentation for Calendar::roll(). + * + * @param field The time field. + * @param amount Indicates amount to roll. + * @param status Output param set to success/failure code on exit. If any value + * previously set in the time field is invalid, this will be set to + * an error status. + * @stable ICU 2.6. + */ + virtual void roll(UCalendarDateFields field, int32_t amount, UErrorCode& status); + + /** + * Return the minimum value that this field could have, given the current date. + * For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum(). + * @param field the time field. + * @return the minimum value that this field could have, given the current date. + * @deprecated ICU 2.6. Use getActualMinimum(UCalendarDateFields field) instead. + */ + int32_t getActualMinimum(EDateFields field) const; + + /** + * Return the minimum value that this field could have, given the current date. + * For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum(). + * @param field the time field. + * @param status + * @return the minimum value that this field could have, given the current date. + * @deprecated ICU 2.6. Use getActualMinimum(UCalendarDateFields field) instead. (Added to ICU 3.0 for signature consistency) + */ + int32_t getActualMinimum(EDateFields field, UErrorCode& status) const; + + /** + * Return the minimum value that this field could have, given the current date. + * For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum(). + * @param field the time field. + * @param status error result. + * @return the minimum value that this field could have, given the current date. + * @stable ICU 3.0 + */ + int32_t getActualMinimum(UCalendarDateFields field, UErrorCode &status) const; + + /** + * Return the maximum value that this field could have, given the current date. + * For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual + * maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar, + * for some years the actual maximum for MONTH is 12, and for others 13. + * @param field the time field. + * @return the maximum value that this field could have, given the current date. + * @deprecated ICU 2.6. Use getActualMaximum(UCalendarDateFields field) instead. + */ + int32_t getActualMaximum(EDateFields field) const; + + /** + * Return the maximum value that this field could have, given the current date. + * For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual + * maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar, + * for some years the actual maximum for MONTH is 12, and for others 13. + * @param field the time field. + * @param status returns any errors that may result from this function call. + * @return the maximum value that this field could have, given the current date. + * @stable ICU 2.6 + */ + virtual int32_t getActualMaximum(UCalendarDateFields field, UErrorCode& status) const; + + /** + * (Overrides Calendar) Return true if the current date for this Calendar is in + * Daylight Savings Time. Recognizes DST_OFFSET, if it is set. + * + * @param status Fill-in parameter which receives the status of this operation. + * @return True if the current date for this Calendar is in Daylight Savings Time, + * false, otherwise. + * @stable ICU 2.0 + */ + virtual UBool inDaylightTime(UErrorCode& status) const; + +public: + + /** + * Override Calendar Returns a unique class ID POLYMORPHICALLY. Pure virtual + * override. This method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() methods call + * this method. + * + * @return The class ID for this object. All objects of a given class have the + * same class ID. Objects of other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Return the class ID for this class. This is useful only for comparing to a return + * value from getDynamicClassID(). For example: + * + * Base* polymorphic_pointer = createPolymorphicObject(); + * if (polymorphic_pointer->getDynamicClassID() == + * Derived::getStaticClassID()) ... + * + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Get the calendar type, "gregorian", for use in DateFormatSymbols. + * + * @return calendar type + * @internal + */ + virtual const char * getType() const; + +protected: + + /** + * (Overrides Calendar) Converts GMT as milliseconds to time field values. + * @param status Fill-in parameter which receives the status of this operation. + * @stable ICU 2.0 + */ + + private: + GregorianCalendar(); // default constructor not implemented + + protected: + /** + * Return the ERA. We need a special method for this because the + * default ERA is AD, but a zero (unset) ERA is BC. + * @return the ERA. + * @internal + */ + virtual int32_t internalGetEra() const; + + /** + * Return the Julian day number of day before the first day of the + * given month in the given extended year. Subclasses should override + * this method to implement their calendar system. + * @param eyear the extended year + * @param month the zero-based month, or 0 if useMonth is false + * @param useMonth if false, compute the day before the first day of + * the given year, otherwise, compute the day before the first day of + * the given month + * @return the Julian day number of the day before the first + * day of the given month and year + * @internal + */ + virtual int32_t handleComputeMonthStart(int32_t eyear, int32_t month, + UBool useMonth) const; + + /** + * Subclasses may override this. This method calls + * handleGetMonthLength() to obtain the calendar-specific month + * length. + * @param bestField which field to use to calculate the date + * @return julian day specified by calendar fields. + * @internal + */ + virtual int32_t handleComputeJulianDay(UCalendarDateFields bestField) ; + + /** + * Return the number of days in the given month of the given extended + * year of this calendar system. Subclasses should override this + * method if they can provide a more correct or more efficient + * implementation than the default implementation in Calendar. + * @internal + */ + virtual int32_t handleGetMonthLength(int32_t extendedYear, int32_t month) const; + + /** + * Return the number of days in the given extended year of this + * calendar system. Subclasses should override this method if they can + * provide a more correct or more efficient implementation than the + * default implementation in Calendar. + * @stable ICU 2.0 + */ + virtual int32_t handleGetYearLength(int32_t eyear) const; + + /** + * return the length of the given month. + * @param month the given month. + * @return the length of the given month. + * @internal + */ + virtual int32_t monthLength(int32_t month) const; + + /** + * return the length of the month according to the given year. + * @param month the given month. + * @param year the given year. + * @return the length of the month + * @internal + */ + virtual int32_t monthLength(int32_t month, int32_t year) const; + + /** + * return the length of the given year. + * @param year the given year. + * @return the length of the given year. + * @internal + */ + int32_t yearLength(int32_t year) const; + + /** + * return the length of the year field. + * @return the length of the year field + * @internal + */ + int32_t yearLength(void) const; + + /** + * After adjustments such as add(MONTH), add(YEAR), we don't want the + * month to jump around. E.g., we don't want Jan 31 + 1 month to go to Mar + * 3, we want it to go to Feb 28. Adjustments which might run into this + * problem call this method to retain the proper month. + * @internal + */ + void pinDayOfMonth(void); + + /** + * Return the day number with respect to the epoch. January 1, 1970 (Gregorian) + * is day zero. + * @param status Fill-in parameter which receives the status of this operation. + * @return the day number with respect to the epoch. + * @internal + */ + virtual UDate getEpochDay(UErrorCode& status); + + /** + * Subclass API for defining limits of different types. + * Subclasses must implement this method to return limits for the + * following fields: + * + * <pre>UCAL_ERA + * UCAL_YEAR + * UCAL_MONTH + * UCAL_WEEK_OF_YEAR + * UCAL_WEEK_OF_MONTH + * UCAL_DATE (DAY_OF_MONTH on Java) + * UCAL_DAY_OF_YEAR + * UCAL_DAY_OF_WEEK_IN_MONTH + * UCAL_YEAR_WOY + * UCAL_EXTENDED_YEAR</pre> + * + * @param field one of the above field numbers + * @param limitType one of <code>MINIMUM</code>, <code>GREATEST_MINIMUM</code>, + * <code>LEAST_MAXIMUM</code>, or <code>MAXIMUM</code> + * @internal + */ + virtual int32_t handleGetLimit(UCalendarDateFields field, ELimitType limitType) const; + + /** + * Return the extended year defined by the current fields. This will + * use the UCAL_EXTENDED_YEAR field or the UCAL_YEAR and supra-year fields (such + * as UCAL_ERA) specific to the calendar system, depending on which set of + * fields is newer. + * @return the extended year + * @internal + */ + virtual int32_t handleGetExtendedYear(); + + /** + * Subclasses may override this to convert from week fields + * (YEAR_WOY and WEEK_OF_YEAR) to an extended year in the case + * where YEAR, EXTENDED_YEAR are not set. + * The Gregorian implementation assumes a yearWoy in gregorian format, according to the current era. + * @return the extended year, UCAL_EXTENDED_YEAR + * @internal + */ + virtual int32_t handleGetExtendedYearFromWeekFields(int32_t yearWoy, int32_t woy); + + + /** + * Subclasses may override this method to compute several fields + * specific to each calendar system. These are: + * + * <ul><li>ERA + * <li>YEAR + * <li>MONTH + * <li>DAY_OF_MONTH + * <li>DAY_OF_YEAR + * <li>EXTENDED_YEAR</ul> + * + * <p>The GregorianCalendar implementation implements + * a calendar with the specified Julian/Gregorian cutover date. + * @internal + */ + virtual void handleComputeFields(int32_t julianDay, UErrorCode &status); + + private: + /** + * Compute the julian day number of the given year. + * @param isGregorian if true, using Gregorian calendar, otherwise using Julian calendar + * @param year the given year. + * @param isLeap true if the year is a leap year. + * @return + */ + static double computeJulianDayOfYear(UBool isGregorian, int32_t year, + UBool& isLeap); + + /** + * Validates the values of the set time fields. True if they're all valid. + * @return True if the set time fields are all valid. + */ + UBool validateFields(void) const; + + /** + * Validates the value of the given time field. True if it's valid. + */ + UBool boundsCheck(int32_t value, UCalendarDateFields field) const; + + /** + * Return the pseudo-time-stamp for two fields, given their + * individual pseudo-time-stamps. If either of the fields + * is unset, then the aggregate is unset. Otherwise, the + * aggregate is the later of the two stamps. + * @param stamp_a One given field. + * @param stamp_b Another given field. + * @return the pseudo-time-stamp for two fields + */ + int32_t aggregateStamp(int32_t stamp_a, int32_t stamp_b); + + /** + * The point at which the Gregorian calendar rules are used, measured in + * milliseconds from the standard epoch. Default is October 15, 1582 + * (Gregorian) 00:00:00 UTC, that is, October 4, 1582 (Julian) is followed + * by October 15, 1582 (Gregorian). This corresponds to Julian day number + * 2299161. This is measured from the standard epoch, not in Julian Days. + * @internal + */ + UDate fGregorianCutover; + + /** + * Julian day number of the Gregorian cutover + */ + int32_t fCutoverJulianDay; + + /** + * Midnight, local time (using this Calendar's TimeZone) at or before the + * gregorianCutover. This is a pure date value with no time of day or + * timezone component. + */ + UDate fNormalizedGregorianCutover;// = gregorianCutover; + + /** + * The year of the gregorianCutover, with 0 representing + * 1 BC, -1 representing 2 BC, etc. + */ + int32_t fGregorianCutoverYear;// = 1582; + + /** + * The year of the gregorianCutover, with 0 representing + * 1 BC, -1 representing 2 BC, etc. + */ + int32_t fGregorianCutoverJulianDay;// = 2299161; + + /** + * Converts time as milliseconds to Julian date. The Julian date used here is not a + * true Julian date, since it is measured from midnight, not noon. + * + * @param millis The given milliseconds. + * @return The Julian date number. + */ + static double millisToJulianDay(UDate millis); + + /** + * Converts Julian date to time as milliseconds. The Julian date used here is not a + * true Julian date, since it is measured from midnight, not noon. + * + * @param julian The given Julian date number. + * @return Time as milliseconds. + */ + static UDate julianDayToMillis(double julian); + + /** + * Used by handleComputeJulianDay() and handleComputeMonthStart(). + * Temporary field indicating whether the calendar is currently Gregorian as opposed to Julian. + */ + UBool fIsGregorian; + + /** + * Used by handleComputeJulianDay() and handleComputeMonthStart(). + * Temporary field indicating that the sense of the gregorian cutover should be inverted + * to handle certain calculations on and around the cutover date. + */ + UBool fInvertGregorian; + + + public: // internal implementation + + /** + * @internal + * @return TRUE if this calendar has the notion of a default century + */ + virtual UBool haveDefaultCentury() const; + + /** + * @internal + * @return the start of the default century + */ + virtual UDate defaultCenturyStart() const; + + /** + * @internal + * @return the beginning year of the default century + */ + virtual int32_t defaultCenturyStartYear() const; + + private: + /** + * The system maintains a static default century start date. This is initialized + * the first time it is used. Before then, it is set to SYSTEM_DEFAULT_CENTURY to + * indicate an uninitialized state. Once the system default century date and year + * are set, they do not change. + */ + static UDate fgSystemDefaultCenturyStart; + + /** + * See documentation for systemDefaultCenturyStart. + */ + static int32_t fgSystemDefaultCenturyStartYear; + + /** + * Default value that indicates the defaultCenturyStartYear is unitialized + */ + static const int32_t fgSystemDefaultCenturyYear; + + /** + * Default value that indicates the UDate of the beginning of the system default century + */ + static const UDate fgSystemDefaultCentury; + + /** + * Returns the beginning date of the 100-year window that dates with 2-digit years + * are considered to fall within. + * @return the beginning date of the 100-year window that dates with 2-digit years + * are considered to fall within. + */ + UDate internalGetDefaultCenturyStart(void) const; + + /** + * Returns the first year of the 100-year window that dates with 2-digit years + * are considered to fall within. + * @return the first year of the 100-year window that dates with 2-digit years + * are considered to fall within. + */ + int32_t internalGetDefaultCenturyStartYear(void) const; + + /** + * Initializes the 100-year window that dates with 2-digit years are considered + * to fall within so that its start date is 80 years before the current time. + */ + static void initializeSystemDefaultCentury(void); + +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _GREGOCAL +//eof + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/measfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/measfmt.h new file mode 100644 index 00000000000..a5af55e9d53 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/measfmt.h @@ -0,0 +1,77 @@ +/* +********************************************************************** +* Copyright (c) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: April 20, 2004 +* Since: ICU 3.0 +********************************************************************** +*/ +#ifndef MEASUREFORMAT_H +#define MEASUREFORMAT_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/format.h" + +/** + * \file + * \brief C++ API: Formatter for measure objects. + */ + +U_NAMESPACE_BEGIN + +/** + * + * A formatter for measure objects. This is an abstract base class. + * + * <p>To format or parse a measure object, first create a formatter + * object using a MeasureFormat factory method. Then use that + * object's format and parse methods. + * + * <p>This is an abstract class. + * + * @see Format + * @author Alan Liu + * @stable ICU 3.0 + */ +class U_I18N_API MeasureFormat : public Format { + + public: + + /** + * Return a formatter for CurrencyAmount objects in the given + * locale. + * @param locale desired locale + * @param ec input-output error code + * @return a formatter object, or NULL upon error + * @stable ICU 3.0 + */ + static MeasureFormat* U_EXPORT2 createCurrencyFormat(const Locale& locale, + UErrorCode& ec); + + /** + * Return a formatter for CurrencyAmount objects in the default + * locale. + * @param ec input-output error code + * @return a formatter object, or NULL upon error + * @stable ICU 3.0 + */ + static MeasureFormat* U_EXPORT2 createCurrencyFormat(UErrorCode& ec); + + protected: + + /** + * Default constructor. + * @stable ICU 3.0 + */ + MeasureFormat(); +}; + +U_NAMESPACE_END + +#endif // #if !UCONFIG_NO_FORMATTING +#endif // #ifndef MEASUREFORMAT_H diff --git a/Build/source/libs/icu-xetex/i18n/unicode/measunit.h b/Build/source/libs/icu-xetex/i18n/unicode/measunit.h new file mode 100644 index 00000000000..9a210e65957 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/measunit.h @@ -0,0 +1,71 @@ +/* +********************************************************************** +* Copyright (c) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: April 26, 2004 +* Since: ICU 3.0 +********************************************************************** +*/ +#ifndef __MEASUREUNIT_H__ +#define __MEASUREUNIT_H__ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/fmtable.h" + +/** + * \file + * \brief C++ API: A unit for measuring a quantity. + */ + +U_NAMESPACE_BEGIN + +/** + * A unit such as length, mass, volume, currency, etc. A unit is + * coupled with a numeric amount to produce a Measure. + * + * <p>This is an abstract class. + * + * @author Alan Liu + * @stable ICU 3.0 + */ +class U_I18N_API MeasureUnit: public UObject { + public: + /** + * Return a polymorphic clone of this object. The result will + * have the same class as returned by getDynamicClassID(). + * @stable ICU 3.0 + */ + virtual UObject* clone() const = 0; + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~MeasureUnit(); + + /** + * Equality operator. Return true if this object is equal + * to the given object. + * @stable ICU 3.0 + */ + virtual UBool operator==(const UObject& other) const = 0; + + protected: + /** + * Default constructor. + * @stable ICU 3.0 + */ + MeasureUnit(); +}; + +U_NAMESPACE_END + +// NOTE: There is no measunit.cpp. For implementation, see measure.cpp. [alan] + +#endif // !UCONFIG_NO_FORMATTING +#endif // __MEASUREUNIT_H__ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/measure.h b/Build/source/libs/icu-xetex/i18n/unicode/measure.h new file mode 100644 index 00000000000..6b7a0497b47 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/measure.h @@ -0,0 +1,137 @@ +/* +********************************************************************** +* Copyright (c) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: April 26, 2004 +* Since: ICU 3.0 +********************************************************************** +*/ +#ifndef __MEASURE_H__ +#define __MEASURE_H__ + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: MeasureUnit object. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/fmtable.h" + +U_NAMESPACE_BEGIN + +class MeasureUnit; + +/** + * An amount of a specified unit, consisting of a number and a Unit. + * For example, a length measure consists of a number and a length + * unit, such as feet or meters. This is an abstract class. + * Subclasses specify a concrete Unit type. + * + * <p>Measure objects are parsed and formatted by subclasses of + * MeasureFormat. + * + * <p>Measure objects are immutable. + * + * <p>This is an abstract class. + * + * @author Alan Liu + * @stable ICU 3.0 + */ +class U_I18N_API Measure: public UObject { + public: + /** + * Construct an object with the given numeric amount and the given + * unit. After this call, the caller must not delete the given + * unit object. + * @param number a numeric object; amount.isNumeric() must be TRUE + * @param adoptedUnit the unit object, which must not be NULL + * @param ec input-output error code. If the amount or the unit + * is invalid, then this will be set to a failing value. + * @stable ICU 3.0 + */ + Measure(const Formattable& number, MeasureUnit* adoptedUnit, + UErrorCode& ec); + + /** + * Copy constructor + * @stable ICU 3.0 + */ + Measure(const Measure& other); + + /** + * Assignment operator + * @stable ICU 3.0 + */ + Measure& operator=(const Measure& other); + + /** + * Return a polymorphic clone of this object. The result will + * have the same class as returned by getDynamicClassID(). + * @stable ICU 3.0 + */ + virtual UObject* clone() const = 0; + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~Measure(); + + /** + * Equality operator. Return true if this object is equal + * to the given object. + * @stable ICU 3.0 + */ + UBool operator==(const UObject& other) const; + + /** + * Return a reference to the numeric value of this object. The + * numeric value may be of any numeric type supported by + * Formattable. + * @stable ICU 3.0 + */ + inline const Formattable& getNumber() const; + + /** + * Return a reference to the unit of this object. + * @stable ICU 3.0 + */ + inline const MeasureUnit& getUnit() const; + + protected: + /** + * Default constructor. + * @stable ICU 3.0 + */ + Measure(); + + private: + /** + * The numeric value of this object, e.g. 2.54 or 100. + */ + Formattable number; + + /** + * The unit of this object, e.g., "millimeter" or "JPY". This is + * owned by this object. + */ + MeasureUnit* unit; +}; + +inline const Formattable& Measure::getNumber() const { + return number; +} + +inline const MeasureUnit& Measure::getUnit() const { + return *unit; +} + +U_NAMESPACE_END + +#endif // !UCONFIG_NO_FORMATTING +#endif // __MEASURE_H__ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/msgfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/msgfmt.h new file mode 100644 index 00000000000..815cabbb944 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/msgfmt.h @@ -0,0 +1,829 @@ +/* +* Copyright (C) 1997-2006, International Business Machines Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File MSGFMT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/20/97 helena Finished first cut of implementation. +* 07/22/98 stephen Removed operator!= (defined in Format) +* 08/19/2002 srl Removing Javaisms +******************************************************************************** +*/ + +#ifndef MSGFMT_H +#define MSGFMT_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Formats messages in a language-neutral way. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/format.h" +#include "unicode/locid.h" +#include "unicode/parseerr.h" + +U_NAMESPACE_BEGIN + +class NumberFormat; +class DateFormat; + +/** + * + * A MessageFormat produces concatenated messages in a + * language-neutral way. It should be used for all string + * concatenations that are visible to end users. + * <P> + * A MessageFormat contains an array of <EM>subformats</EM> arranged + * within a <EM>template string</EM>. Together, the subformats and + * template string determine how the MessageFormat will operate during + * formatting and parsing. + * <P> + * Typically, both the subformats and the template string are + * specified at once in a <EM>pattern</EM>. By using different + * patterns for different locales, messages may be localized. + * <P> + * During formatting, the MessageFormat takes an array of arguments + * and produces a user-readable string. Each argument is a + * Formattable object; they may be passed in in an array, or as a + * single Formattable object which itself contains an array. Each + * argument is matched up with its corresponding subformat, which then + * formats it into a string. The resultant strings are then assembled + * within the string template of the MessageFormat to produce the + * final output string. + * <P> + * During parsing, an input string is matched against the string + * template of the MessageFormat to produce an array of Formattable + * objects. Plain text of the template string is matched directly + * against intput text. At each position in the template string where + * a subformat is located, the subformat is called to parse the + * corresponding segment of input text to produce an output argument. + * In this way, an array of arguments is created which together + * constitute the parse result. + * <P> + * Parsing may fail or produce unexpected results in a number of + * circumstances. + * <UL> + * <LI>If one of the arguments does not occur in the pattern, it + * will be returned as a default Formattable. + * <LI>If the format of an argument is loses information, such as with + * a choice format where a large number formats to "many", then the + * parse may not correspond to the originally formatted argument. + * <LI>MessageFormat does not handle ChoiceFormat recursion during + * parsing; such parses will fail. + * <LI>Parsing will not always find a match (or the correct match) if + * some part of the parse is ambiguous. For example, if the pattern + * "{1},{2}" is used with the string arguments {"a,b", "c"}, it will + * format as "a,b,c". When the result is parsed, it will return {"a", + * "b,c"}. + * <LI>If a single argument is formatted more than once in the string, + * then the rightmost subformat in the pattern string will produce the + * parse result; prior subformats with the same argument index will + * have no effect. + * </UL> + * Here are some examples of usage: + * <P> + * Example 1: + * <pre> + * \code + * UErrorCode success = U_ZERO_ERROR; + * GregorianCalendar cal(success); + * Formattable arguments[] = { + * 7L, + * Formattable( (Date) cal.getTime(success), Formattable::kIsDate), + * "a disturbance in the Force" + * }; + * + * UnicodeString result; + * MessageFormat::format( + * "At {1,time} on {1,date}, there was {2} on planet {0,number}.", + * arguments, 3, result, success ); + * + * cout << "result: " << result << endl; + * //<output>: At 4:34:20 PM on 23-Mar-98, there was a disturbance + * // in the Force on planet 7. + * \endcode + * </pre> + * Typically, the message format will come from resources, and the + * arguments will be dynamically set at runtime. + * <P> + * Example 2: + * <pre> + * \code + * success = U_ZERO_ERROR; + * Formattable testArgs[] = {3L, "MyDisk"}; + * + * MessageFormat form( + * "The disk \"{1}\" contains {0} file(s).", success ); + * + * UnicodeString string; + * FieldPosition fpos = 0; + * cout << "format: " << form.format(testArgs, 2, string, fpos, success ) << endl; + * + * // output, with different testArgs: + * // output: The disk "MyDisk" contains 0 file(s). + * // output: The disk "MyDisk" contains 1 file(s). + * // output: The disk "MyDisk" contains 1,273 file(s). + * \endcode + * </pre> + * + * The pattern is of the following form. Legend: + * <pre> + * \code + * {optional item} + * (group that may be repeated)* + * \endcode + * </pre> + * Do not confuse optional items with items inside quotes braces, such + * as this: "{". Quoted braces are literals. + * <pre> + * \code + * messageFormatPattern := string ( "{" messageFormatElement "}" string )* + * + * messageFormatElement := argumentIndex { "," elementFormat } + * + * elementFormat := "time" { "," datetimeStyle } + * | "date" { "," datetimeStyle } + * | "number" { "," numberStyle } + * | "choice" "," choiceStyle + * + * datetimeStyle := "short" + * | "medium" + * | "long" + * | "full" + * | dateFormatPattern + * + * numberStyle := "currency" + * | "percent" + * | "integer" + * | numberFormatPattern + * + * choiceStyle := choiceFormatPattern + * \endcode + * </pre> + * If there is no elementFormat, then the argument must be a string, + * which is substituted. If there is no dateTimeStyle or numberStyle, + * then the default format is used (e.g. NumberFormat::createInstance(), + * DateFormat::createTimeInstance(DateFormat::kDefault, ...) or DateFormat::createDateInstance(DateFormat::kDefault, ...). For + * a ChoiceFormat, the pattern must always be specified, since there + * is no default. + * <P> + * In strings, single quotes can be used to quote syntax characters. + * A literal single quote is represented by '', both within and outside + * of single-quoted segments. Inside a + * messageFormatElement, quotes are <EM>not</EM> removed. For example, + * {1,number,$'#',##} will produce a number format with the pound-sign + * quoted, with a result such as: "$#31,45". + * <P> + * If a pattern is used, then unquoted braces in the pattern, if any, + * must match: that is, "ab {0} de" and "ab '}' de" are ok, but "ab + * {0'}' de" and "ab } de" are not. + * <p> + * <dl><dt><b>Warning:</b><dd>The rules for using quotes within message + * format patterns unfortunately have shown to be somewhat confusing. + * In particular, it isn't always obvious to localizers whether single + * quotes need to be doubled or not. Make sure to inform localizers about + * the rules, and tell them (for example, by using comments in resource + * bundle source files) which strings will be processed by MessageFormat. + * Note that localizers may need to use single quotes in translated + * strings where the original version doesn't have them. + * <br>Note also that the simplest way to avoid the problem is to + * use the real apostrophe (single quote) character U+2019 (') for + * human-readable text, and to use the ASCII apostrophe (U+0027 ' ) + * only in program syntax, like quoting in MessageFormat. + * See the annotations for U+0027 Apostrophe in The Unicode Standard.</p> + * </dl> + * <P> + * The argumentIndex is a non-negative integer, which corresponds to the + * index of the arguments presented in an array to be formatted. The + * first argument has argumentIndex 0. + * <P> + * It is acceptable to have unused arguments in the array. With missing + * arguments or arguments that are not of the right class for the + * specified format, a failing UErrorCode result is set. + * <P> + * For more sophisticated patterns, you can use a ChoiceFormat to get + * output: + * <pre> + * \code + * UErrorCode success = U_ZERO_ERROR; + * MessageFormat* form("The disk \"{1}\" contains {0}.", success); + * double filelimits[] = {0,1,2}; + * UnicodeString filepart[] = {"no files","one file","{0,number} files"}; + * ChoiceFormat* fileform = new ChoiceFormat(filelimits, filepart, 3); + * form.setFormat(1, *fileform); // NOT zero, see below + * + * Formattable testArgs[] = {1273L, "MyDisk"}; + * + * UnicodeString string; + * FieldPosition fpos = 0; + * cout << form.format(testArgs, 2, string, fpos, success) << endl; + * + * // output, with different testArgs + * // output: The disk "MyDisk" contains no files. + * // output: The disk "MyDisk" contains one file. + * // output: The disk "MyDisk" contains 1,273 files. + * \endcode + * </pre> + * You can either do this programmatically, as in the above example, + * or by using a pattern (see ChoiceFormat for more information) as in: + * <pre> + * \code + * form.applyPattern( + * "There {0,choice,0#are no files|1#is one file|1<are {0,number,integer} files}."); + * \endcode + * </pre> + * <P> + * <EM>Note:</EM> As we see above, the string produced by a ChoiceFormat in + * MessageFormat is treated specially; occurences of '{' are used to + * indicated subformats, and cause recursion. If you create both a + * MessageFormat and ChoiceFormat programmatically (instead of using + * the string patterns), then be careful not to produce a format that + * recurses on itself, which will cause an infinite loop. + * <P> + * <EM>Note:</EM> Subformats are numbered by their order in the pattern. + * This is <EM>not</EM> the same as the argumentIndex. + * <pre> + * \code + * For example: with "abc{2}def{3}ghi{0}...", + * + * format0 affects the first variable {2} + * format1 affects the second variable {3} + * format2 affects the second variable {0} + * \endcode + * </pre> + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API MessageFormat : public Format { +public: + /** + * Enum type for kMaxFormat. + * @obsolete ICU 3.0. The 10-argument limit was removed as of ICU 2.6, + * rendering this enum type obsolete. + */ + enum EFormatNumber { + /** + * The maximum number of arguments. + * @obsolete ICU 3.0. The 10-argument limit was removed as of ICU 2.6, + * rendering this constant obsolete. + */ + kMaxFormat = 10 + }; + + /** + * Constructs a new MessageFormat using the given pattern and the + * default locale. + * + * @param pattern Pattern used to construct object. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + MessageFormat(const UnicodeString& pattern, + UErrorCode &status); + + /** + * Constructs a new MessageFormat using the given pattern and locale. + * @param pattern Pattern used to construct object. + * @param newLocale The locale to use for formatting dates and numbers. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + MessageFormat(const UnicodeString& pattern, + const Locale& newLocale, + UErrorCode& status); + /** + * Constructs a new MessageFormat using the given pattern and locale. + * @param pattern Pattern used to construct object. + * @param newLocale The locale to use for formatting dates and numbers. + * @param parseError Struct to recieve information on position + * of error within the pattern. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + MessageFormat(const UnicodeString& pattern, + const Locale& newLocale, + UParseError& parseError, + UErrorCode& status); + /** + * Constructs a new MessageFormat from an existing one. + * @stable ICU 2.0 + */ + MessageFormat(const MessageFormat&); + + /** + * Assignment operator. + * @stable ICU 2.0 + */ + const MessageFormat& operator=(const MessageFormat&); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~MessageFormat(); + + /** + * Clones this Format object polymorphically. The caller owns the + * result and should delete it when done. + * @stable ICU 2.0 + */ + virtual Format* clone(void) const; + + /** + * Returns true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * @param other the object to be compared with. + * @return true if the given Format objects are semantically equal. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const; + + /** + * Sets the locale. This locale is used for fetching default number or date + * format information. + * @param theLocale the new locale value to be set. + * @stable ICU 2.0 + */ + virtual void setLocale(const Locale& theLocale); + + /** + * Gets the locale. This locale is used for fetching default number or date + * format information. + * @return the locale of the object. + * @stable ICU 2.0 + */ + virtual const Locale& getLocale(void) const; + + /** + * Applies the given pattern string to this message format. + * + * @param pattern The pattern to be applied. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UErrorCode& status); + /** + * Applies the given pattern string to this message format. + * + * @param pattern The pattern to be applied. + * @param parseError Struct to recieve information on position + * of error within pattern. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern, + UParseError& parseError, + UErrorCode& status); + + /** + * Returns a pattern that can be used to recreate this object. + * + * @param appendTo Output parameter to receive the pattern. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& toPattern(UnicodeString& appendTo) const; + + /** + * Sets subformats. + * See the class description about format numbering. + * The caller should not delete the Format objects after this call. + * <EM>The array formatsToAdopt is not itself adopted.</EM> Its + * ownership is retained by the caller. If the call fails because + * memory cannot be allocated, then the formats will be deleted + * by this method, and this object will remain unchanged. + * + * @stable ICU 2.0 + * @param formatsToAdopt the format to be adopted. + * @param count the size of the array. + */ + virtual void adoptFormats(Format** formatsToAdopt, int32_t count); + + /** + * Sets subformats. + * See the class description about format numbering. + * Each item in the array is cloned into the internal array. + * If the call fails because memory cannot be allocated, then this + * object will remain unchanged. + * + * @stable ICU 2.0 + * @param newFormats the new format to be set. + * @param cnt the size of the array. + */ + virtual void setFormats(const Format** newFormats,int32_t cnt); + + + /** + * Sets one subformat. + * See the class description about format numbering. + * The caller should not delete the Format object after this call. + * If the number is over the number of formats already set, + * the item will be deleted and ignored. + * @stable ICU 2.0 + * @param formatNumber index of the subformat. + * @param formatToAdopt the format to be adopted. + */ + virtual void adoptFormat(int32_t formatNumber, Format* formatToAdopt); + + /** + * Sets one subformat. + * See the class description about format numbering. + * If the number is over the number of formats already set, + * the item will be ignored. + * @param formatNumber index of the subformat. + * @param format the format to be set. + * @stable ICU 2.0 + */ + virtual void setFormat(int32_t formatNumber, const Format& format); + + /** + * Gets an array of subformats of this object. The returned array + * should not be deleted by the caller, nor should the pointers + * within the array. The array and its contents remain valid only + * until the next call to any method of this class is made with + * this object. See the class description about format numbering. + * @param count output parameter to receive the size of the array + * @return an array of count Format* objects, or NULL if out of + * memory. Any or all of the array elements may be NULL. + * @stable ICU 2.0 + */ + virtual const Format** getFormats(int32_t& count) const; + + /** + * Formats the given array of arguments into a user-readable string. + * Does not take ownership of the Formattable* array or its contents. + * + * @param source An array of objects to be formatted. + * @param count The number of elements of 'source'. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param ignore Not used; inherited from base class API. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( const Formattable* source, + int32_t count, + UnicodeString& appendTo, + FieldPosition& ignore, + UErrorCode& status) const; + + /** + * Formats the given array of arguments into a user-readable string + * using the given pattern. + * + * @param pattern The pattern. + * @param arguments An array of objects to be formatted. + * @param count The number of elements of 'source'. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + static UnicodeString& format( const UnicodeString& pattern, + const Formattable* arguments, + int32_t count, + UnicodeString& appendTo, + UErrorCode& status); + + /** + * Formats the given array of arguments into a user-readable + * string. The array must be stored within a single Formattable + * object of type kArray. If the Formattable object type is not of + * type kArray, then returns a failing UErrorCode. + * + * @param obj A Formattable of type kArray containing + * arguments to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Formats the given array of arguments into a user-readable + * string. The array must be stored within a single Formattable + * object of type kArray. If the Formattable object type is not of + * type kArray, then returns a failing UErrorCode. + * + * @param obj The object to format + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Parses the given string into an array of output arguments. + * + * @param source String to be parsed. + * @param pos On input, starting position for parse. On output, + * final position after parse. Unchanged if parse + * fails. + * @param count Output parameter to receive the number of arguments + * parsed. + * @return an array of parsed arguments. The caller owns both + * the array and its contents. + * @stable ICU 2.0 + */ + virtual Formattable* parse( const UnicodeString& source, + ParsePosition& pos, + int32_t& count) const; + + /** + * Parses the given string into an array of output arguments. + * + * @param source String to be parsed. + * @param count Output param to receive size of returned array. + * @param status Input/output error code. If the + * pattern cannot be parsed, set to failure code. + * @return an array of parsed arguments. The caller owns both + * the array and its contents. + * @stable ICU 2.0 + */ + virtual Formattable* parse( const UnicodeString& source, + int32_t& count, + UErrorCode& status) const; + + /** + * Parses the given string into an array of output arguments + * stored within a single Formattable of type kArray. + * + * @param source The string to be parsed into an object. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param pos On input, starting position for parse. On output, + * final position after parse. Unchanged if parse + * fails. + * @stable ICU 2.0 + */ + virtual void parseObject(const UnicodeString& source, + Formattable& result, + ParsePosition& pos) const; + + /** + * Convert an 'apostrophe-friendly' pattern into a standard + * pattern. Standard patterns treat all apostrophes as + * quotes, which is problematic in some languages, e.g. + * French, where apostrophe is commonly used. This utility + * assumes that only an unpaired apostrophe immediately before + * a brace is a true quote. Other unpaired apostrophes are paired, + * and the resulting standard pattern string is returned. + * + * <p><b>Note</b> it is not guaranteed that the returned pattern + * is indeed a valid pattern. The only effect is to convert + * between patterns having different quoting semantics. + * + * @param pattern the 'apostrophe-friendly' patttern to convert + * @param status Input/output error code. If the pattern + * cannot be parsed, the failure code is set. + * @return the standard equivalent of the original pattern + * @stable ICU 3.4 + */ + static UnicodeString autoQuoteApostrophe(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +private: + + Locale fLocale; + UnicodeString fPattern; + Format** formatAliases; // see getFormats + int32_t formatAliasesCapacity; + + MessageFormat(); // default constructor not implemented + + /* + * A structure representing one subformat of this MessageFormat. + * Each subformat has a Format object, an offset into the plain + * pattern text fPattern, and an argument number. The argument + * number corresponds to the array of arguments to be formatted. + * @internal + */ + class Subformat { + public: + /** + * @internal + */ + Format* format; // formatter + /** + * @internal + */ + int32_t offset; // offset into fPattern + /** + * @internal + */ + int32_t arg; // 0-based argument number + + /** + * Clone that.format and assign it to this.format + * Do NOT delete this.format + * @internal + */ + Subformat& operator=(const Subformat& that) { + format = that.format ? that.format->clone() : NULL; + offset = that.offset; + arg = that.arg; + return *this; + } + + /** + * @internal + */ + UBool operator==(const Subformat& that) const { + // Do cheap comparisons first + return offset == that.offset && + arg == that.arg && + ((format == that.format) || // handles NULL + (*format == *that.format)); + } + + /** + * @internal + */ + UBool operator!=(const Subformat& that) const { + return !operator==(that); + } + }; + + /** + * A MessageFormat contains an array of subformats. This array + * needs to grow dynamically if the MessageFormat is modified. + */ + Subformat* subformats; + int32_t subformatCount; + int32_t subformatCapacity; + + /** + * A MessageFormat formats an array of arguments. Each argument + * has an expected type, based on the pattern. For example, if + * the pattern contains the subformat "{3,number,integer}", then + * we expect argument 3 to have type Formattable::kLong. This + * array needs to grow dynamically if the MessageFormat is + * modified. + */ + Formattable::Type* argTypes; + int32_t argTypeCount; + int32_t argTypeCapacity; + + // Variable-size array management + UBool allocateSubformats(int32_t capacity); + UBool allocateArgTypes(int32_t capacity); + + /** + * Default Format objects used when no format is specified and a + * numeric or date argument is formatted. These are volatile + * cache objects maintained only for performance. They do not + * participate in operator=(), copy constructor(), nor + * operator==(). + */ + NumberFormat* defaultNumberFormat; + DateFormat* defaultDateFormat; + + /** + * Method to retrieve default formats (or NULL on failure). + * These are semantically const, but may modify *this. + */ + const NumberFormat* getDefaultNumberFormat(UErrorCode&) const; + const DateFormat* getDefaultDateFormat(UErrorCode&) const; + + /** + * Finds the word s, in the keyword list and returns the located index. + * @param s the keyword to be searched for. + * @param list the list of keywords to be searched with. + * @return the index of the list which matches the keyword s. + */ + static int32_t findKeyword( const UnicodeString& s, + const UChar * const *list); + + /** + * Formats the array of arguments and copies the result into the + * result buffer, updates the field position. + * + * @param arguments The formattable objects array. + * @param cnt The array count. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Field position status. + * @param recursionProtection + * Initially zero. Bits 0..9 are used to indicate + * that a parameter has already been seen, to + * avoid recursion. Currently unused. + * @param success The error code status. + * @return Reference to 'appendTo' parameter. + */ + UnicodeString& format( const Formattable* arguments, + int32_t cnt, + UnicodeString& appendTo, + FieldPosition& status, + int32_t recursionProtection, + UErrorCode& success) const; + + void makeFormat(int32_t offsetNumber, + UnicodeString* segments, + UParseError& parseError, + UErrorCode& success); + + /** + * Convenience method that ought to be in NumberFormat + */ + NumberFormat* createIntegerFormat(const Locale& locale, UErrorCode& status) const; + + /** + * Checks the range of the source text to quote the special + * characters, { and ' and copy to target buffer. + * @param source + * @param start the text offset to start the process of in the source string + * @param end the text offset to end the process of in the source string + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + */ + static void copyAndFixQuotes(const UnicodeString& appendTo, int32_t start, int32_t end, UnicodeString& target); + + /** + * Returns array of argument types in the parsed pattern + * for use in C API. Only for the use of umsg_vformat(). Not + * for public consumption. + * @param listCount Output parameter to receive the size of array + * @return The array of formattable types in the pattern + * @internal + */ + const Formattable::Type* getArgTypeList(int32_t& listCount) const { + listCount = argTypeCount; + return argTypes; + } + + friend class MessageFormatAdapter; // getFormatTypeList() access +}; + +inline UnicodeString& +MessageFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + return Format::format(obj, appendTo, status); +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _MSGFMT +//eof + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/numfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/numfmt.h new file mode 100644 index 00000000000..b27ed470819 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/numfmt.h @@ -0,0 +1,861 @@ +/* +******************************************************************************** +* Copyright (C) 1997-2006, International Business Machines Corporation and others. +* All Rights Reserved. +******************************************************************************** +* +* File NUMFMT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 03/18/97 clhuang Updated per C++ implementation. +* 04/17/97 aliu Changed DigitCount to int per code review. +* 07/20/98 stephen JDK 1.2 sync up. Added scientific support. +* Changed naming conventions to match C++ guidelines +* Derecated Java style constants (eg, INTEGER_FIELD) +******************************************************************************** +*/ + +#ifndef NUMFMT_H +#define NUMFMT_H + + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Abstract base class for all number formats. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/unistr.h" +#include "unicode/format.h" +#include "unicode/unum.h" // UNumberFormatStyle +#include "unicode/locid.h" + +U_NAMESPACE_BEGIN + +#if !UCONFIG_NO_SERVICE +class NumberFormatFactory; +class StringEnumeration; +#endif + +/** + * + * Abstract base class for all number formats. Provides interface for + * formatting and parsing a number. Also provides methods for + * determining which locales have number formats, and what their names + * are. + * <P> + * NumberFormat helps you to format and parse numbers for any locale. + * Your code can be completely independent of the locale conventions + * for decimal points, thousands-separators, or even the particular + * decimal digits used, or whether the number format is even decimal. + * <P> + * To format a number for the current Locale, use one of the static + * factory methods: + * <pre> + * \code + * double myNumber = 7.0; + * UnicodeString myString; + * UErrorCode success = U_ZERO_ERROR; + * NumberFormat* nf = NumberFormat::createInstance(success) + * nf->format(myNumber, myString); + * cout << " Example 1: " << myString << endl; + * \endcode + * </pre> + * If you are formatting multiple numbers, it is more efficient to get + * the format and use it multiple times so that the system doesn't + * have to fetch the information about the local language and country + * conventions multiple times. + * <pre> + * \code + * UnicodeString myString; + * UErrorCode success = U_ZERO_ERROR; + * nf = NumberFormat::createInstance( success ); + * int32_t a[] = { 123, 3333, -1234567 }; + * const int32_t a_len = sizeof(a) / sizeof(a[0]); + * myString.remove(); + * for (int32_t i = 0; i < a_len; i++) { + * nf->format(a[i], myString); + * myString += " ; "; + * } + * cout << " Example 2: " << myString << endl; + * \endcode + * </pre> + * To format a number for a different Locale, specify it in the + * call to createInstance(). + * <pre> + * \code + * nf = NumberFormat::createInstance( Locale::FRENCH, success ); + * \endcode + * </pre> + * You can use a NumberFormat to parse also. + * <pre> + * \code + * UErrorCode success; + * Formattable result(-999); // initialized with error code + * nf->parse(myString, result, success); + * \endcode + * </pre> + * Use createInstance to get the normal number format for that country. + * There are other static factory methods available. Use getCurrency + * to get the currency number format for that country. Use getPercent + * to get a format for displaying percentages. With this format, a + * fraction from 0.53 is displayed as 53%. + * <P> + * You can also control the display of numbers with such methods as + * getMinimumFractionDigits. If you want even more control over the + * format or parsing, or want to give your users more control, you can + * try casting the NumberFormat you get from the factory methods to a + * DecimalNumberFormat. This will work for the vast majority of + * countries; just remember to put it in a try block in case you + * encounter an unusual one. + * <P> + * You can also use forms of the parse and format methods with + * ParsePosition and FieldPosition to allow you to: + * <ul type=round> + * <li>(a) progressively parse through pieces of a string. + * <li>(b) align the decimal point and other areas. + * </ul> + * For example, you can align numbers in two ways. + * <P> + * If you are using a monospaced font with spacing for alignment, you + * can pass the FieldPosition in your format call, with field = + * INTEGER_FIELD. On output, getEndIndex will be set to the offset + * between the last character of the integer and the decimal. Add + * (desiredSpaceCount - getEndIndex) spaces at the front of the + * string. + * <P> + * If you are using proportional fonts, instead of padding with + * spaces, measure the width of the string in pixels from the start to + * getEndIndex. Then move the pen by (desiredPixelWidth - + * widthToAlignmentPoint) before drawing the text. It also works + * where there is no decimal, but possibly additional characters at + * the end, e.g. with parentheses in negative numbers: "(12)" for -12. + * <p> + * <em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + * + * @stable ICU 2.0 + */ +class U_I18N_API NumberFormat : public Format { +public: + + /** + * Alignment Field constants used to construct a FieldPosition object. + * Signifies that the position of the integer part or fraction part of + * a formatted number should be returned. + * + * @see FieldPosition + * @stable ICU 2.0 + */ + enum EAlignmentFields { + kIntegerField, + kFractionField, + + + /** + * These constants are provided for backwards compatibility only. + * Please use the C++ style constants defined above. + * @stable ICU 2.0 + */ + INTEGER_FIELD = kIntegerField, + FRACTION_FIELD = kFractionField + }; + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~NumberFormat(); + + /** + * Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * @return true if the given Format objects are semantically equal. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const; + + /** + * Format an object to produce a string. This method handles + * Formattable objects with numeric types. If the Formattable + * object type is not a numeric type, then it returns a failing + * UErrorCode. + * + * @param obj The object to format. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @param status Output param filled with success/failure status. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Parse a string to produce an object. This methods handles + * parsing of numeric strings into Formattable objects with numeric + * types. + * <P> + * Before calling, set parse_pos.index to the offset you want to + * start parsing at in the source. After calling, parse_pos.index + * indicates the position after the successfully parsed text. If + * an error occurs, parse_pos.index is unchanged. + * <P> + * When parsing, leading whitespace is discarded (with successful + * parse), while trailing whitespace is left as is. + * <P> + * See Format::parseObject() for more. + * + * @param source The string to be parsed into an object. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parse_pos The position to start parsing at. Upon return + * this param is set to the position after the + * last character successfully parsed. If the + * source is not parsed successfully, this param + * will remain unchanged. + * @return A newly created Formattable* object, or NULL + * on failure. The caller owns this and should + * delete it when done. + * @stable ICU 2.0 + */ + virtual void parseObject(const UnicodeString& source, + Formattable& result, + ParsePosition& parse_pos) const; + + /** + * Format a double number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( double number, + UnicodeString& appendTo) const; + + /** + * Format a long number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format( int32_t number, + UnicodeString& appendTo) const; + + /** + * Format an int64 number. These methods call the NumberFormat + * pure virtual format() methods with the default FieldPosition. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.8 + */ + UnicodeString& format( int64_t number, + UnicodeString& appendTo) const; + + /** + * Format a double number. Concrete subclasses must implement + * these pure virtual methods. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(double number, + UnicodeString& appendTo, + FieldPosition& pos) const = 0; + /** + * Format a long number. Concrete subclasses must implement + * these pure virtual methods. + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(int32_t number, + UnicodeString& appendTo, + FieldPosition& pos) const = 0; + + /** + * Format an int64 number. (Not abstract to retain compatibility + * with earlier releases, however subclasses should override this + * method as it just delegates to format(int32_t number...); + * + * @param number The value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos On input: an alignment field, if desired. + * On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.8 + */ + virtual UnicodeString& format(int64_t number, + UnicodeString& appendTo, + FieldPosition& pos) const; + /** + * Redeclared Format method. + * @param obj The object to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Output parameter set to a failure error code + * when a failure occurs. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Return a long if possible (e.g. within range LONG_MAX, + * LONG_MAX], and with no decimals), otherwise a double. If + * IntegerOnly is set, will stop at a decimal point (or equivalent; + * e.g. for rational numbers "1 2/3", will stop after the 1). + * <P> + * If no object can be parsed, index is unchanged, and NULL is + * returned. + * <P> + * This is a pure virtual which concrete subclasses must implement. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param parsePosition The position to start parsing at on input. + * On output, moved to after the last successfully + * parse character. On parse failure, does not change. + * @return A Formattable object of numeric type. The caller + * owns this an must delete it. NULL on failure. + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + ParsePosition& parsePosition) const = 0; + + /** + * Parse a string as a numeric value, and return a Formattable + * numeric object. This method parses integers only if IntegerOnly + * is set. + * + * @param text The text to be parsed. + * @param result Formattable to be set to the parse result. + * If parse fails, return contents are undefined. + * @param status Output parameter set to a failure error code + * when a failure occurs. + * @return A Formattable object of numeric type. The caller + * owns this an must delete it. NULL on failure. + * @see NumberFormat::isParseIntegerOnly + * @stable ICU 2.0 + */ + virtual void parse( const UnicodeString& text, + Formattable& result, + UErrorCode& status) const; + + /** + * Parses text from the given string as a currency amount. Unlike + * the parse() method, this method will attempt to parse a generic + * currency name, searching for a match of this object's locale's + * currency display names, or for a 3-letter ISO currency code. + * This method will fail if this format is not a currency format, + * that is, if it does not contain the currency pattern symbol + * (U+00A4) in its prefix or suffix. + * + * @param text the string to parse + * @param result output parameter to receive result. This will have + * its currency set to the parsed ISO currency code. + * @param pos input-output position; on input, the position within + * text to match; must have 0 <= pos.getIndex() < text.length(); + * on output, the position after the last matched character. If + * the parse fails, the position in unchanged upon output. + * @return a reference to result + * @internal + */ + virtual Formattable& parseCurrency(const UnicodeString& text, + Formattable& result, + ParsePosition& pos) const; + + /** + * Return true if this format will parse numbers as integers + * only. For example in the English locale, with ParseIntegerOnly + * true, the string "1234." would be parsed as the integer value + * 1234 and parsing would stop at the "." character. Of course, + * the exact format accepted by the parse operation is locale + * dependant and determined by sub-classes of NumberFormat. + * @return true if this format will parse numbers as integers + * only. + * @stable ICU 2.0 + */ + UBool isParseIntegerOnly(void) const; + + /** + * Sets whether or not numbers should be parsed as integers only. + * @param value set True, this format will parse numbers as integers + * only. + * @see isParseIntegerOnly + * @stable ICU 2.0 + */ + virtual void setParseIntegerOnly(UBool value); + + /** + * Returns the default number format for the current default + * locale. The default format is one of the styles provided by + * the other factory methods: getNumberInstance, + * getCurrencyInstance or getPercentInstance. Exactly which one + * is locale dependant. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createInstance(UErrorCode&); + + /** + * Returns the default number format for the specified locale. + * The default format is one of the styles provided by the other + * factory methods: getNumberInstance, getCurrencyInstance or + * getPercentInstance. Exactly which one is locale dependant. + * @param inLocale the given locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createInstance(const Locale& inLocale, + UErrorCode&); + + /** + * Returns a currency format for the current default locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createCurrencyInstance(UErrorCode&); + + /** + * Returns a currency format for the specified locale. + * @param inLocale the given locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createCurrencyInstance(const Locale& inLocale, + UErrorCode&); + + /** + * Returns a percentage format for the current default locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createPercentInstance(UErrorCode&); + + /** + * Returns a percentage format for the specified locale. + * @param inLocale the given locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createPercentInstance(const Locale& inLocale, + UErrorCode&); + + /** + * Returns a scientific format for the current default locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createScientificInstance(UErrorCode&); + + /** + * Returns a scientific format for the specified locale. + * @param inLocale the given locale. + * @stable ICU 2.0 + */ + static NumberFormat* U_EXPORT2 createScientificInstance(const Locale& inLocale, + UErrorCode&); + + /** + * Get the set of Locales for which NumberFormats are installed. + * @param count Output param to receive the size of the locales + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + +#if !UCONFIG_NO_SERVICE + /** + * Register a new NumberFormatFactory. The factory will be adopted. + * @param toAdopt the NumberFormatFactory instance to be adopted + * @param status the in/out status code, no special meanings are assigned + * @return a registry key that can be used to unregister this factory + * @stable ICU 2.6 + */ + static URegistryKey U_EXPORT2 registerFactory(NumberFormatFactory* toAdopt, UErrorCode& status); + + /** + * Unregister a previously-registered NumberFormatFactory using the key returned from the + * register call. Key becomes invalid after a successful call and should not be used again. + * The NumberFormatFactory corresponding to the key will be deleted. + * @param key the registry key returned by a previous call to registerFactory + * @param status the in/out status code, no special meanings are assigned + * @return TRUE if the factory for the key was successfully unregistered + * @stable ICU 2.6 + */ + static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status); + + /** + * Return a StringEnumeration over the locales available at the time of the call, + * including registered locales. + * @return a StringEnumeration over the locales available at the time of the call + * @stable ICU 2.6 + */ + static StringEnumeration* U_EXPORT2 getAvailableLocales(void); +#endif /* UCONFIG_NO_SERVICE */ + + /** + * Returns true if grouping is used in this format. For example, + * in the English locale, with grouping on, the number 1234567 + * might be formatted as "1,234,567". The grouping separator as + * well as the size of each group is locale dependant and is + * determined by sub-classes of NumberFormat. + * @see setGroupingUsed + * @stable ICU 2.0 + */ + UBool isGroupingUsed(void) const; + + /** + * Set whether or not grouping will be used in this format. + * @param newValue True, grouping will be used in this format. + * @see getGroupingUsed + * @stable ICU 2.0 + */ + virtual void setGroupingUsed(UBool newValue); + + /** + * Returns the maximum number of digits allowed in the integer portion of a + * number. + * @return the maximum number of digits allowed in the integer portion of a + * number. + * @see setMaximumIntegerDigits + * @stable ICU 2.0 + */ + int32_t getMaximumIntegerDigits(void) const; + + /** + * Sets the maximum number of digits allowed in the integer portion of a + * number. maximumIntegerDigits must be >= minimumIntegerDigits. If the + * new value for maximumIntegerDigits is less than the current value + * of minimumIntegerDigits, then minimumIntegerDigits will also be set to + * the new value. + * + * @param newValue the new value for the maximum number of digits + * allowed in the integer portion of a number. + * @see getMaximumIntegerDigits + * @stable ICU 2.0 + */ + virtual void setMaximumIntegerDigits(int32_t newValue); + + /** + * Returns the minimum number of digits allowed in the integer portion of a + * number. + * @return the minimum number of digits allowed in the integer portion of a + * number. + * @see setMinimumIntegerDigits + * @stable ICU 2.0 + */ + int32_t getMinimumIntegerDigits(void) const; + + /** + * Sets the minimum number of digits allowed in the integer portion of a + * number. minimumIntegerDigits must be <= maximumIntegerDigits. If the + * new value for minimumIntegerDigits exceeds the current value + * of maximumIntegerDigits, then maximumIntegerDigits will also be set to + * the new value. + * @param newValue the new value to be set. + * @see getMinimumIntegerDigits + * @stable ICU 2.0 + */ + virtual void setMinimumIntegerDigits(int32_t newValue); + + /** + * Returns the maximum number of digits allowed in the fraction portion of a + * number. + * @return the maximum number of digits allowed in the fraction portion of a + * number. + * @see setMaximumFractionDigits + * @stable ICU 2.0 + */ + int32_t getMaximumFractionDigits(void) const; + + /** + * Sets the maximum number of digits allowed in the fraction portion of a + * number. maximumFractionDigits must be >= minimumFractionDigits. If the + * new value for maximumFractionDigits is less than the current value + * of minimumFractionDigits, then minimumFractionDigits will also be set to + * the new value. + * @param newValue the new value to be set. + * @see getMaximumFractionDigits + * @stable ICU 2.0 + */ + virtual void setMaximumFractionDigits(int32_t newValue); + + /** + * Returns the minimum number of digits allowed in the fraction portion of a + * number. + * @return the minimum number of digits allowed in the fraction portion of a + * number. + * @see setMinimumFractionDigits + * @stable ICU 2.0 + */ + int32_t getMinimumFractionDigits(void) const; + + /** + * Sets the minimum number of digits allowed in the fraction portion of a + * number. minimumFractionDigits must be <= maximumFractionDigits. If the + * new value for minimumFractionDigits exceeds the current value + * of maximumFractionDigits, then maximumIntegerDigits will also be set to + * the new value + * @param newValue the new value to be set. + * @see getMinimumFractionDigits + * @stable ICU 2.0 + */ + virtual void setMinimumFractionDigits(int32_t newValue); + + /** + * Sets the currency used to display currency + * amounts. This takes effect immediately, if this format is a + * currency format. If this format is not a currency format, then + * the currency is used if and when this object becomes a + * currency format. + * @param theCurrency a 3-letter ISO code indicating new currency + * to use. It need not be null-terminated. May be the empty + * string or NULL to indicate no currency. + * @param ec input-output error code + * @stable ICU 3.0 + */ + virtual void setCurrency(const UChar* theCurrency, UErrorCode& ec); + + /** + * Gets the currency used to display currency + * amounts. This may be an empty string for some subclasses. + * @return a 3-letter null-terminated ISO code indicating + * the currency in use, or a pointer to the empty string. + * @stable ICU 2.6 + */ + const UChar* getCurrency() const; + +public: + + /** + * Return the class ID for this class. This is useful for + * comparing to a return value from getDynamicClassID(). Note that, + * because NumberFormat is an abstract base class, no fully constructed object + * will have the class ID returned by NumberFormat::getStaticClassID(). + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * <P> + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + +protected: + + /** + * Default constructor for subclass use only. + * @stable ICU 2.0 + */ + NumberFormat(); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + NumberFormat(const NumberFormat&); + + /** + * Assignment operator. + * @stable ICU 2.0 + */ + NumberFormat& operator=(const NumberFormat&); + + /** + * Returns the currency in effect for this formatter. Subclasses + * should override this method as needed. Unlike getCurrency(), + * this method should never return "". + * @result output parameter for null-terminated result, which must + * have a capacity of at least 4 + * @internal + */ + virtual void getEffectiveCurrency(UChar* result, UErrorCode& ec) const; + +private: + + enum EStyles { + kNumberStyle, + kCurrencyStyle, + kPercentStyle, + kScientificStyle, + kStyleCount // ALWAYS LAST ENUM: number of styles + }; + + /** + * Creates the specified decimal format style of the desired locale. + * Hook for service registration, uses makeInstance directly if no services + * registered. + * @param desiredLocale the given locale. + * @param choice the given style. + * @param success Output param filled with success/failure status. + * @return A new NumberFormat instance. + */ + static NumberFormat* U_EXPORT2 createInstance(const Locale& desiredLocale, EStyles choice, UErrorCode& success); + + /** + * Creates the specified decimal format style of the desired locale. + * @param desiredLocale the given locale. + * @param choice the given style. + * @param success Output param filled with success/failure status. + * @return A new NumberFormat instance. + */ + static NumberFormat* makeInstance(const Locale& desiredLocale, EStyles choice, UErrorCode& success); + + UBool fGroupingUsed; + int32_t fMaxIntegerDigits; + int32_t fMinIntegerDigits; + int32_t fMaxFractionDigits; + int32_t fMinFractionDigits; + UBool fParseIntegerOnly; + + // ISO currency code + UChar fCurrency[4]; + + friend class ICUNumberFormatFactory; // access to makeInstance, EStyles + friend class ICUNumberFormatService; +}; + +#if !UCONFIG_NO_SERVICE +/** + * A NumberFormatFactory is used to register new number formats. The factory + * should be able to create any of the predefined formats for each locale it + * supports. When registered, the locales it supports extend or override the + * locale already supported by ICU. + * + * @stable ICU 2.6 + */ +class U_I18N_API NumberFormatFactory : public UObject { +public: + + /** + * Destructor + * @stable ICU 3.0 + */ + virtual ~NumberFormatFactory(); + + /** + * Return true if this factory will be visible. Default is true. + * If not visible, the locales supported by this factory will not + * be listed by getAvailableLocales. + * @stable ICU 2.6 + */ + virtual UBool visible(void) const = 0; + + /** + * Return the locale names directly supported by this factory. The number of names + * is returned in count; + * @stable ICU 2.6 + */ + virtual const UnicodeString * getSupportedIDs(int32_t &count, UErrorCode& status) const = 0; + + /** + * Return a number format of the appropriate type. If the locale + * is not supported, return null. If the locale is supported, but + * the type is not provided by this service, return null. Otherwise + * return an appropriate instance of NumberFormat. + * @stable ICU 2.6 + */ + virtual NumberFormat* createFormat(const Locale& loc, UNumberFormatStyle formatType) = 0; +}; + +/** + * A NumberFormatFactory that supports a single locale. It can be visible or invisible. + * @stable ICU 2.6 + */ +class U_I18N_API SimpleNumberFormatFactory : public NumberFormatFactory { +protected: + /** + * True if the locale supported by this factory is visible. + * @stable ICU 2.6 + */ + const UBool _visible; + + /** + * The locale supported by this factory, as a UnicodeString. + * @stable ICU 2.6 + */ + UnicodeString _id; + +public: + /** + * @stable ICU 2.6 + */ + SimpleNumberFormatFactory(const Locale& locale, UBool visible = TRUE); + + /** + * @stable ICU 3.0 + */ + virtual ~SimpleNumberFormatFactory(); + + /** + * @stable ICU 2.6 + */ + virtual UBool visible(void) const; + + /** + * @stable ICU 2.6 + */ + virtual const UnicodeString * getSupportedIDs(int32_t &count, UErrorCode& status) const; +}; +#endif /* #if !UCONFIG_NO_SERVICE */ + +// ------------------------------------- + +inline UBool +NumberFormat::isParseIntegerOnly() const +{ + return fParseIntegerOnly; +} + +inline UnicodeString& +NumberFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + return Format::format(obj, appendTo, status); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _NUMFMT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/rbnf.h b/Build/source/libs/icu-xetex/i18n/unicode/rbnf.h new file mode 100644 index 00000000000..030565eb284 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/rbnf.h @@ -0,0 +1,1049 @@ +/* +******************************************************************************* +* Copyright (C) 1997-2006, International Business Machines Corporation and others. +* All Rights Reserved. +******************************************************************************* +*/ + +#ifndef RBNF_H +#define RBNF_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Rule Based Number Format + */ + +/** + * \def U_HAVE_RBNF + * This will be 0 if RBNF support is not included in ICU + * and 1 if it is. + * + * @stable ICU 2.4 + */ +#if UCONFIG_NO_FORMATTING +#define U_HAVE_RBNF 0 +#else +#define U_HAVE_RBNF 1 + +#include "unicode/coll.h" +#include "unicode/dcfmtsym.h" +#include "unicode/fmtable.h" +#include "unicode/locid.h" +#include "unicode/numfmt.h" +#include "unicode/unistr.h" +#include "unicode/strenum.h" + +U_NAMESPACE_BEGIN + +class NFRuleSet; +class LocalizationInfo; + +/** + * Tags for the predefined rulesets. + * + * @stable ICU 2.2 + */ +enum URBNFRuleSetTag { + URBNF_SPELLOUT, + URBNF_ORDINAL, + URBNF_DURATION, + URBNF_COUNT +}; + +#if UCONFIG_NO_COLLATION +class Collator; +#endif + +/** + * The RuleBasedNumberFormat class formats numbers according to a set of rules. This number formatter is + * typically used for spelling out numeric values in words (e.g., 25,3476 as + * "twenty-five thousand three hundred seventy-six" or "vingt-cinq mille trois + * cents soixante-seize" or + * "fünfundzwanzigtausenddreihundertsechsundsiebzig"), but can also be used for + * other complicated formatting tasks, such as formatting a number of seconds as hours, + * minutes and seconds (e.g., 3,730 as "1:02:10"). + * + * <p>The resources contain three predefined formatters for each locale: spellout, which + * spells out a value in words (123 is "one hundred twenty-three"); ordinal, which + * appends an ordinal suffix to the end of a numeral (123 is "123rd"); and + * duration, which shows a duration in seconds as hours, minutes, and seconds (123 is + * "2:03"). The client can also define more specialized <tt>RuleBasedNumberFormat</tt>s + * by supplying programmer-defined rule sets.</p> + * + * <p>The behavior of a <tt>RuleBasedNumberFormat</tt> is specified by a textual description + * that is either passed to the constructor as a <tt>String</tt> or loaded from a resource + * bundle. In its simplest form, the description consists of a semicolon-delimited list of <em>rules.</em> + * Each rule has a string of output text and a value or range of values it is applicable to. + * In a typical spellout rule set, the first twenty rules are the words for the numbers from + * 0 to 19:</p> + * + * <pre>zero; one; two; three; four; five; six; seven; eight; nine; + * ten; eleven; twelve; thirteen; fourteen; fifteen; sixteen; seventeen; eighteen; nineteen;</pre> + * + * <p>For larger numbers, we can use the preceding set of rules to format the ones place, and + * we only have to supply the words for the multiples of 10:</p> + * + * <pre> 20: twenty[->>]; + * 30: thirty[->>]; + * 40: forty[->>]; + * 50: fifty[->>]; + * 60: sixty[->>]; + * 70: seventy[->>]; + * 80: eighty[->>]; + * 90: ninety[->>];</pre> + * + * <p>In these rules, the <em>base value</em> is spelled out explicitly and set off from the + * rule's output text with a colon. The rules are in a sorted list, and a rule is applicable + * to all numbers from its own base value to one less than the next rule's base value. The + * ">>" token is called a <em>substitution</em> and tells the fomatter to + * isolate the number's ones digit, format it using this same set of rules, and place the + * result at the position of the ">>" token. Text in brackets is omitted if + * the number being formatted is an even multiple of 10 (the hyphen is a literal hyphen; 24 + * is "twenty-four," not "twenty four").</p> + * + * <p>For even larger numbers, we can actually look up several parts of the number in the + * list:</p> + * + * <pre>100: << hundred[ >>];</pre> + * + * <p>The "<<" represents a new kind of substitution. The << isolates + * the hundreds digit (and any digits to its left), formats it using this same rule set, and + * places the result where the "<<" was. Notice also that the meaning of + * >> has changed: it now refers to both the tens and the ones digits. The meaning of + * both substitutions depends on the rule's base value. The base value determines the rule's <em>divisor,</em> + * which is the highest power of 10 that is less than or equal to the base value (the user + * can change this). To fill in the substitutions, the formatter divides the number being + * formatted by the divisor. The integral quotient is used to fill in the << + * substitution, and the remainder is used to fill in the >> substitution. The meaning + * of the brackets changes similarly: text in brackets is omitted if the value being + * formatted is an even multiple of the rule's divisor. The rules are applied recursively, so + * if a substitution is filled in with text that includes another substitution, that + * substitution is also filled in.</p> + * + * <p>This rule covers values up to 999, at which point we add another rule:</p> + * + * <pre>1000: << thousand[ >>];</pre> + * + * <p>Again, the meanings of the brackets and substitution tokens shift because the rule's + * base value is a higher power of 10, changing the rule's divisor. This rule can actually be + * used all the way up to 999,999. This allows us to finish out the rules as follows:</p> + * + * <pre> 1,000,000: << million[ >>]; + * 1,000,000,000: << billion[ >>]; + * 1,000,000,000,000: << trillion[ >>]; + * 1,000,000,000,000,000: OUT OF RANGE!;</pre> + * + * <p>Commas, periods, and spaces can be used in the base values to improve legibility and + * are ignored by the rule parser. The last rule in the list is customarily treated as an + * "overflow rule," applying to everything from its base value on up, and often (as + * in this example) being used to print out an error message or default representation. + * Notice also that the size of the major groupings in large numbers is controlled by the + * spacing of the rules: because in English we group numbers by thousand, the higher rules + * are separated from each other by a factor of 1,000.</p> + * + * <p>To see how these rules actually work in practice, consider the following example: + * Formatting 25,430 with this rule set would work like this:</p> + * + * <table border="0" width="100%"> + * <tr> + * <td><strong><< thousand >></strong></td> + * <td>[the rule whose base value is 1,000 is applicable to 25,340]</td> + * </tr> + * <tr> + * <td><strong>twenty->></strong> thousand >></td> + * <td>[25,340 over 1,000 is 25. The rule for 20 applies.]</td> + * </tr> + * <tr> + * <td>twenty-<strong>five</strong> thousand >></td> + * <td>[25 mod 10 is 5. The rule for 5 is "five."</td> + * </tr> + * <tr> + * <td>twenty-five thousand <strong><< hundred >></strong></td> + * <td>[25,340 mod 1,000 is 340. The rule for 100 applies.]</td> + * </tr> + * <tr> + * <td>twenty-five thousand <strong>three</strong> hundred >></td> + * <td>[340 over 100 is 3. The rule for 3 is "three."]</td> + * </tr> + * <tr> + * <td>twenty-five thousand three hundred <strong>forty</strong></td> + * <td>[340 mod 100 is 40. The rule for 40 applies. Since 40 divides + * evenly by 10, the hyphen and substitution in the brackets are omitted.]</td> + * </tr> + * </table> + * + * <p>The above syntax suffices only to format positive integers. To format negative numbers, + * we add a special rule:</p> + * + * <pre>-x: minus >>;</pre> + * + * <p>This is called a <em>negative-number rule,</em> and is identified by "-x" + * where the base value would be. This rule is used to format all negative numbers. the + * >> token here means "find the number's absolute value, format it with these + * rules, and put the result here."</p> + * + * <p>We also add a special rule called a <em>fraction rule </em>for numbers with fractional + * parts:</p> + * + * <pre>x.x: << point >>;</pre> + * + * <p>This rule is used for all positive non-integers (negative non-integers pass through the + * negative-number rule first and then through this rule). Here, the << token refers to + * the number's integral part, and the >> to the number's fractional part. The + * fractional part is formatted as a series of single-digit numbers (e.g., 123.456 would be + * formatted as "one hundred twenty-three point four five six").</p> + * + * <p>To see how this rule syntax is applied to various languages, examine the resource data.</p> + * + * <p>There is actually much more flexibility built into the rule language than the + * description above shows. A formatter may own multiple rule sets, which can be selected by + * the caller, and which can use each other to fill in their substitutions. Substitutions can + * also be filled in with digits, using a DecimalFormat object. There is syntax that can be + * used to alter a rule's divisor in various ways. And there is provision for much more + * flexible fraction handling. A complete description of the rule syntax follows:</p> + * + * <hr> + * + * <p>The description of a <tt>RuleBasedNumberFormat</tt>'s behavior consists of one or more <em>rule + * sets.</em> Each rule set consists of a name, a colon, and a list of <em>rules.</em> A rule + * set name must begin with a % sign. Rule sets with names that begin with a single % sign + * are <em>public:</em> the caller can specify that they be used to format and parse numbers. + * Rule sets with names that begin with %% are <em>private:</em> they exist only for the use + * of other rule sets. If a formatter only has one rule set, the name may be omitted.</p> + * + * <p>The user can also specify a special "rule set" named <tt>%%lenient-parse</tt>. + * The body of <tt>%%lenient-parse</tt> isn't a set of number-formatting rules, but a <tt>RuleBasedCollator</tt> + * description which is used to define equivalences for lenient parsing. For more information + * on the syntax, see <tt>RuleBasedCollator</tt>. For more information on lenient parsing, + * see <tt>setLenientParse()</tt>. <em>Note:</em> symbols that have syntactic meaning + * in collation rules, such as '&', have no particular meaning when appearing outside + * of the <tt>lenient-parse</tt> rule set.</p> + * + * <p>The body of a rule set consists of an ordered, semicolon-delimited list of <em>rules.</em> + * Internally, every rule has a base value, a divisor, rule text, and zero, one, or two <em>substitutions.</em> + * These parameters are controlled by the description syntax, which consists of a <em>rule + * descriptor,</em> a colon, and a <em>rule body.</em></p> + * + * <p>A rule descriptor can take one of the following forms (text in <em>italics</em> is the + * name of a token):</p> + * + * <table border="0" width="100%"> + * <tr> + * <td><em>bv</em>:</td> + * <td><em>bv</em> specifies the rule's base value. <em>bv</em> is a decimal + * number expressed using ASCII digits. <em>bv</em> may contain spaces, period, and commas, + * which are ignored. The rule's divisor is the highest power of 10 less than or equal to + * the base value.</td> + * </tr> + * <tr> + * <td><em>bv</em>/<em>rad</em>:</td> + * <td><em>bv</em> specifies the rule's base value. The rule's divisor is the + * highest power of <em>rad</em> less than or equal to the base value.</td> + * </tr> + * <tr> + * <td><em>bv</em>>:</td> + * <td><em>bv</em> specifies the rule's base value. To calculate the divisor, + * let the radix be 10, and the exponent be the highest exponent of the radix that yields a + * result less than or equal to the base value. Every > character after the base value + * decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix + * raised to the power of the exponent; otherwise, the divisor is 1.</td> + * </tr> + * <tr> + * <td><em>bv</em>/<em>rad</em>>:</td> + * <td><em>bv</em> specifies the rule's base value. To calculate the divisor, + * let the radix be <em>rad</em>, and the exponent be the highest exponent of the radix that + * yields a result less than or equal to the base value. Every > character after the radix + * decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix + * raised to the power of the exponent; otherwise, the divisor is 1.</td> + * </tr> + * <tr> + * <td>-x:</td> + * <td>The rule is a negative-number rule.</td> + * </tr> + * <tr> + * <td>x.x:</td> + * <td>The rule is an <em>improper fraction rule.</em></td> + * </tr> + * <tr> + * <td>0.x:</td> + * <td>The rule is a <em>proper fraction rule.</em></td> + * </tr> + * <tr> + * <td>x.0:</td> + * <td>The rule is a <em>master rule.</em></td> + * </tr> + * <tr> + * <td><em>nothing</em></td> + * <td>If the rule's rule descriptor is left out, the base value is one plus the + * preceding rule's base value (or zero if this is the first rule in the list) in a normal + * rule set. In a fraction rule set, the base value is the same as the preceding rule's + * base value.</td> + * </tr> + * </table> + * + * <p>A rule set may be either a regular rule set or a <em>fraction rule set,</em> depending + * on whether it is used to format a number's integral part (or the whole number) or a + * number's fractional part. Using a rule set to format a rule's fractional part makes it a + * fraction rule set.</p> + * + * <p>Which rule is used to format a number is defined according to one of the following + * algorithms: If the rule set is a regular rule set, do the following: + * + * <ul> + * <li>If the rule set includes a master rule (and the number was passed in as a <tt>double</tt>), + * use the master rule. (If the number being formatted was passed in as a <tt>long</tt>, + * the master rule is ignored.)</li> + * <li>If the number is negative, use the negative-number rule.</li> + * <li>If the number has a fractional part and is greater than 1, use the improper fraction + * rule.</li> + * <li>If the number has a fractional part and is between 0 and 1, use the proper fraction + * rule.</li> + * <li>Binary-search the rule list for the rule with the highest base value less than or equal + * to the number. If that rule has two substitutions, its base value is not an even multiple + * of its divisor, and the number <em>is</em> an even multiple of the rule's divisor, use the + * rule that precedes it in the rule list. Otherwise, use the rule itself.</li> + * </ul> + * + * <p>If the rule set is a fraction rule set, do the following: + * + * <ul> + * <li>Ignore negative-number and fraction rules.</li> + * <li>For each rule in the list, multiply the number being formatted (which will always be + * between 0 and 1) by the rule's base value. Keep track of the distance between the result + * the nearest integer.</li> + * <li>Use the rule that produced the result closest to zero in the above calculation. In the + * event of a tie or a direct hit, use the first matching rule encountered. (The idea here is + * to try each rule's base value as a possible denominator of a fraction. Whichever + * denominator produces the fraction closest in value to the number being formatted wins.) If + * the rule following the matching rule has the same base value, use it if the numerator of + * the fraction is anything other than 1; if the numerator is 1, use the original matching + * rule. (This is to allow singular and plural forms of the rule text without a lot of extra + * hassle.)</li> + * </ul> + * + * <p>A rule's body consists of a string of characters terminated by a semicolon. The rule + * may include zero, one, or two <em>substitution tokens,</em> and a range of text in + * brackets. The brackets denote optional text (and may also include one or both + * substitutions). The exact meanings of the substitution tokens, and under what conditions + * optional text is omitted, depend on the syntax of the substitution token and the context. + * The rest of the text in a rule body is literal text that is output when the rule matches + * the number being formatted.</p> + * + * <p>A substitution token begins and ends with a <em>token character.</em> The token + * character and the context together specify a mathematical operation to be performed on the + * number being formatted. An optional <em>substitution descriptor </em>specifies how the + * value resulting from that operation is used to fill in the substitution. The position of + * the substitution token in the rule body specifies the location of the resultant text in + * the original rule text.</p> + * + * <p>The meanings of the substitution token characters are as follows:</p> + * + * <table border="0" width="100%"> + * <tr> + * <td>>></td> + * <td>in normal rule</td> + * <td>Divide the number by the rule's divisor and format the remainder</td> + * </tr> + * <tr> + * <td></td> + * <td>in negative-number rule</td> + * <td>Find the absolute value of the number and format the result</td> + * </tr> + * <tr> + * <td></td> + * <td>in fraction or master rule</td> + * <td>Isolate the number's fractional part and format it.</td> + * </tr> + * <tr> + * <td></td> + * <td>in rule in fraction rule set</td> + * <td>Not allowed.</td> + * </tr> + * <tr> + * <td>>>></td> + * <td>in normal rule</td> + * <td>Divide the number by the rule's divisor and format the remainder, + * but bypass the normal rule-selection process and just use the + * rule that precedes this one in this rule list.</td> + * </tr> + * <tr> + * <td></td> + * <td>in all other rules</td> + * <td>Not allowed.</td> + * </tr> + * <tr> + * <td><<</td> + * <td>in normal rule</td> + * <td>Divide the number by the rule's divisor and format the quotient</td> + * </tr> + * <tr> + * <td></td> + * <td>in negative-number rule</td> + * <td>Not allowed.</td> + * </tr> + * <tr> + * <td></td> + * <td>in fraction or master rule</td> + * <td>Isolate the number's integral part and format it.</td> + * </tr> + * <tr> + * <td></td> + * <td>in rule in fraction rule set</td> + * <td>Multiply the number by the rule's base value and format the result.</td> + * </tr> + * <tr> + * <td>==</td> + * <td>in all rule sets</td> + * <td>Format the number unchanged</td> + * </tr> + * <tr> + * <td>[]</td> + * <td>in normal rule</td> + * <td>Omit the optional text if the number is an even multiple of the rule's divisor</td> + * </tr> + * <tr> + * <td></td> + * <td>in negative-number rule</td> + * <td>Not allowed.</td> + * </tr> + * <tr> + * <td></td> + * <td>in improper-fraction rule</td> + * <td>Omit the optional text if the number is between 0 and 1 (same as specifying both an + * x.x rule and a 0.x rule)</td> + * </tr> + * <tr> + * <td></td> + * <td>in master rule</td> + * <td>Omit the optional text if the number is an integer (same as specifying both an x.x + * rule and an x.0 rule)</td> + * </tr> + * <tr> + * <td></td> + * <td>in proper-fraction rule</td> + * <td>Not allowed.</td> + * </tr> + * <tr> + * <td></td> + * <td>in rule in fraction rule set</td> + * <td>Omit the optional text if multiplying the number by the rule's base value yields 1.</td> + * </tr> + * </table> + * + * <p>The substitution descriptor (i.e., the text between the token characters) may take one + * of three forms:</p> + * + * <table border="0" width="100%"> + * <tr> + * <td>a rule set name</td> + * <td>Perform the mathematical operation on the number, and format the result using the + * named rule set.</td> + * </tr> + * <tr> + * <td>a DecimalFormat pattern</td> + * <td>Perform the mathematical operation on the number, and format the result using a + * DecimalFormat with the specified pattern. The pattern must begin with 0 or #.</td> + * </tr> + * <tr> + * <td>nothing</td> + * <td>Perform the mathematical operation on the number, and format the result using the rule + * set containing the current rule, except: + * <ul> + * <li>You can't have an empty substitution descriptor with a == substitution.</li> + * <li>If you omit the substitution descriptor in a >> substitution in a fraction rule, + * format the result one digit at a time using the rule set containing the current rule.</li> + * <li>If you omit the substitution descriptor in a << substitution in a rule in a + * fraction rule set, format the result using the default rule set for this formatter.</li> + * </ul> + * </td> + * </tr> + * </table> + * + * <p>Whitespace is ignored between a rule set name and a rule set body, between a rule + * descriptor and a rule body, or between rules. If a rule body begins with an apostrophe, + * the apostrophe is ignored, but all text after it becomes significant (this is how you can + * have a rule's rule text begin with whitespace). There is no escape function: the semicolon + * is not allowed in rule set names or in rule text, and the colon is not allowed in rule set + * names. The characters beginning a substitution token are always treated as the beginning + * of a substitution token.</p> + * + * <p>See the resource data and the demo program for annotated examples of real rule sets + * using these features.</p> + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + * + * <p><b>Localizations</b></p> + * <p>Constructors are available that allow the specification of localizations for the + * public rule sets (and also allow more control over what public rule sets are available). + * Localization data is represented as a textual description. The description represents + * an array of arrays of string. The first element is an array of the public rule set names, + * each of these must be one of the public rule set names that appear in the rules. Only + * names in this array will be treated as public rule set names by the API. Each subsequent + * element is an array of localizations of these names. The first element of one of these + * subarrays is the locale name, and the remaining elements are localizations of the + * public rule set names, in the same order as they were listed in the first arrray.</p> + * <p>In the syntax, angle brackets '<', '>' are used to delimit the arrays, and comma ',' is used + * to separate elements of an array. Whitespace is ignored, unless quoted.</p> + * <p>For example:<pre> + * < < %foo, %bar, %baz >, + * < en, Foo, Bar, Baz >, + * < fr, 'le Foo', 'le Bar', 'le Baz' > + * < zh, \\u7532, \\u4e59, \\u4e19 > > + * </pre></p> + * @author Richard Gillam + * @see NumberFormat + * @see DecimalFormat + * @stable ICU 2.0 + */ +class U_I18N_API RuleBasedNumberFormat : public NumberFormat { +public: + + //----------------------------------------------------------------------- + // constructors + //----------------------------------------------------------------------- + + /** + * Creates a RuleBasedNumberFormat that behaves according to the description + * passed in. The formatter uses the default locale. + * @param rules A description of the formatter's desired behavior. + * See the class documentation for a complete explanation of the description + * syntax. + * @param perror The parse error if an error was encountered. + * @param status The status indicating whether the constructor succeeded. + * @stable ICU 3.2 + */ + RuleBasedNumberFormat(const UnicodeString& rules, UParseError& perror, UErrorCode& status); + + /** + * Creates a RuleBasedNumberFormat that behaves according to the description + * passed in. The formatter uses the default locale. + * <p> + * The localizations data provides information about the public + * rule sets and their localized display names for different + * locales. The first element in the list is an array of the names + * of the public rule sets. The first element in this array is + * the initial default ruleset. The remaining elements in the + * list are arrays of localizations of the names of the public + * rule sets. Each of these is one longer than the initial array, + * with the first String being the ULocale ID, and the remaining + * Strings being the localizations of the rule set names, in the + * same order as the initial array. Arrays are NULL-terminated. + * @param rules A description of the formatter's desired behavior. + * See the class documentation for a complete explanation of the description + * syntax. + * @param localizations the localization information. + * names in the description. These will be copied by the constructor. + * @param perror The parse error if an error was encountered. + * @param status The status indicating whether the constructor succeeded. + * @stable ICU 3.2 + */ + RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations, + UParseError& perror, UErrorCode& status); + + /** + * Creates a RuleBasedNumberFormat that behaves according to the rules + * passed in. The formatter uses the specified locale to determine the + * characters to use when formatting numerals, and to define equivalences + * for lenient parsing. + * @param rules The formatter rules. + * See the class documentation for a complete explanation of the rule + * syntax. + * @param locale A locale that governs which characters are used for + * formatting values in numerals and which characters are equivalent in + * lenient parsing. + * @param perror The parse error if an error was encountered. + * @param status The status indicating whether the constructor succeeded. + * @stable ICU 2.0 + */ + RuleBasedNumberFormat(const UnicodeString& rules, const Locale& locale, + UParseError& perror, UErrorCode& status); + + /** + * Creates a RuleBasedNumberFormat that behaves according to the description + * passed in. The formatter uses the default locale. + * <p> + * The localizations data provides information about the public + * rule sets and their localized display names for different + * locales. The first element in the list is an array of the names + * of the public rule sets. The first element in this array is + * the initial default ruleset. The remaining elements in the + * list are arrays of localizations of the names of the public + * rule sets. Each of these is one longer than the initial array, + * with the first String being the ULocale ID, and the remaining + * Strings being the localizations of the rule set names, in the + * same order as the initial array. Arrays are NULL-terminated. + * @param rules A description of the formatter's desired behavior. + * See the class documentation for a complete explanation of the description + * syntax. + * @param localizations a list of localizations for the rule set + * names in the description. These will be copied by the constructor. + * @param locale A locale that governs which characters are used for + * formatting values in numerals and which characters are equivalent in + * lenient parsing. + * @param perror The parse error if an error was encountered. + * @param status The status indicating whether the constructor succeeded. + * @stable ICU 3.2 + */ + RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations, + const Locale& locale, UParseError& perror, UErrorCode& status); + + /** + * Creates a RuleBasedNumberFormat from a predefined ruleset. The selector + * code choosed among three possible predefined formats: spellout, ordinal, + * and duration. + * @param tag A selector code specifying which kind of formatter to create for that + * locale. There are three legal values: URBNF_SPELLOUT, which creates a formatter that + * spells out a value in words in the desired language, URBNF_ORDINAL, which attaches + * an ordinal suffix from the desired language to the end of a number (e.g. "123rd"), + * and URBNF_DURATION, which formats a duration in seconds as hours, minutes, and seconds. + * @param locale The locale for the formatter. + * @param status The status indicating whether the constructor succeeded. + * @stable ICU 2.0 + */ + RuleBasedNumberFormat(URBNFRuleSetTag tag, const Locale& locale, UErrorCode& status); + + //----------------------------------------------------------------------- + // boilerplate + //----------------------------------------------------------------------- + + /** + * Copy constructor + * @param rhs the object to be copied from. + * @stable ICU 2.6 + */ + RuleBasedNumberFormat(const RuleBasedNumberFormat& rhs); + + /** + * Assignment operator + * @param rhs the object to be copied from. + * @stable ICU 2.6 + */ + RuleBasedNumberFormat& operator=(const RuleBasedNumberFormat& rhs); + + /** + * Release memory allocated for a RuleBasedNumberFormat when you are finished with it. + * @stable ICU 2.6 + */ + virtual ~RuleBasedNumberFormat(); + + /** + * Clone this object polymorphically. The caller is responsible + * for deleting the result when done. + * @return A copy of the object. + * @stable ICU 2.6 + */ + virtual Format* clone(void) const; + + /** + * Return true if the given Format objects are semantically equal. + * Objects of different subclasses are considered unequal. + * @param other the object to be compared with. + * @return true if the given Format objects are semantically equal. + * @stable ICU 2.6 + */ + virtual UBool operator==(const Format& other) const; + +//----------------------------------------------------------------------- +// public API functions +//----------------------------------------------------------------------- + + /** + * return the rules that were provided to the RuleBasedNumberFormat. + * @return the result String that was passed in + * @stable ICU 2.0 + */ + virtual UnicodeString getRules() const; + + /** + * Return the number of public rule set names. + * @return the number of public rule set names. + * @stable ICU 2.0 + */ + virtual int32_t getNumberOfRuleSetNames() const; + + /** + * Return the name of the index'th public ruleSet. If index is not valid, + * the function returns null. + * @param index the index of the ruleset + * @return the name of the index'th public ruleSet. + * @stable ICU 2.0 + */ + virtual UnicodeString getRuleSetName(int32_t index) const; + + /** + * Return the number of locales for which we have localized rule set display names. + * @return the number of locales for which we have localized rule set display names. + * @stable ICU 3.2 + */ + virtual int32_t getNumberOfRuleSetDisplayNameLocales(void) const; + + /** + * Return the index'th display name locale. + * @param index the index of the locale + * @param status set to a failure code when this function fails + * @return the locale + * @see #getNumberOfRuleSetDisplayNameLocales + * @stable ICU 3.2 + */ + virtual Locale getRuleSetDisplayNameLocale(int32_t index, UErrorCode& status) const; + + /** + * Return the rule set display names for the provided locale. These are in the same order + * as those returned by getRuleSetName. The locale is matched against the locales for + * which there is display name data, using normal fallback rules. If no locale matches, + * the default display names are returned. (These are the internal rule set names minus + * the leading '%'.) + * @param index the index of the rule set + * @param locale the locale (returned by getRuleSetDisplayNameLocales) for which the localized + * display name is desired + * @return the display name for the given index, which might be bogus if there is an error + * @see #getRuleSetName + * @stable ICU 3.2 + */ + virtual UnicodeString getRuleSetDisplayName(int32_t index, + const Locale& locale = Locale::getDefault()); + + /** + * Return the rule set display name for the provided rule set and locale. + * The locale is matched against the locales for which there is display name data, using + * normal fallback rules. If no locale matches, the default display name is returned. + * @return the display name for the rule set + * @stable ICU 3.2 + * @see #getRuleSetDisplayName + */ + virtual UnicodeString getRuleSetDisplayName(const UnicodeString& ruleSetName, + const Locale& locale = Locale::getDefault()); + + /** + * Formats the specified 32-bit number using the default ruleset. + * @param number The number to format. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @return A textual representation of the number. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(int32_t number, + UnicodeString& toAppendTo, + FieldPosition& pos) const; + + /** + * Formats the specified 64-bit number using the default ruleset. + * @param number The number to format. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @return A textual representation of the number. + * @stable ICU 2.1 + */ + virtual UnicodeString& format(int64_t number, + UnicodeString& toAppendTo, + FieldPosition& pos) const; + /** + * Formats the specified number using the default ruleset. + * @param number The number to format. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @return A textual representation of the number. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(double number, + UnicodeString& toAppendTo, + FieldPosition& pos) const; + + /** + * Formats the specified number using the named ruleset. + * @param number The number to format. + * @param ruleSetName The name of the rule set to format the number with. + * This must be the name of a valid public rule set for this formatter. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @param status the status + * @return A textual representation of the number. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(int32_t number, + const UnicodeString& ruleSetName, + UnicodeString& toAppendTo, + FieldPosition& pos, + UErrorCode& status) const; + /** + * Formats the specified 64-bit number using the named ruleset. + * @param number The number to format. + * @param ruleSetName The name of the rule set to format the number with. + * This must be the name of a valid public rule set for this formatter. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @param status the status + * @return A textual representation of the number. + * @stable ICU 2.1 + */ + virtual UnicodeString& format(int64_t number, + const UnicodeString& ruleSetName, + UnicodeString& toAppendTo, + FieldPosition& pos, + UErrorCode& status) const; + /** + * Formats the specified number using the named ruleset. + * @param number The number to format. + * @param ruleSetName The name of the rule set to format the number with. + * This must be the name of a valid public rule set for this formatter. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @param status the status + * @return A textual representation of the number. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(double number, + const UnicodeString& ruleSetName, + UnicodeString& toAppendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Formats the specified number using the default ruleset. + * @param obj The number to format. + * @param toAppendTo the string that will hold the (appended) result + * @param pos the fieldposition + * @param status the status + * @return A textual representation of the number. + * @stable ICU 2.0 + */ + virtual UnicodeString& format(const Formattable& obj, + UnicodeString& toAppendTo, + FieldPosition& pos, + UErrorCode& status) const; + /** + * Redeclared Format method. + * @param obj the object to be formatted. + * @param result Output param which will receive the formatted string. + * @param status Output param set to success/failure code + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& result, + UErrorCode& status) const; + + /** + * Redeclared NumberFormat method. + * @param number the double value to be formatted. + * @param output Output param which will receive the formatted string. + * @return A reference to 'output'. + * @stable ICU 2.0 + */ + UnicodeString& format(double number, + UnicodeString& output) const; + + /** + * Redeclared NumberFormat method. + * @param number the long value to be formatted. + * @param output Output param which will receive the formatted string. + * @return A reference to 'output'. + * @stable ICU 2.0 + */ + UnicodeString& format(int32_t number, + UnicodeString& output) const; + + /** + * Parses the specfied string, beginning at the specified position, according + * to this formatter's rules. This will match the string against all of the + * formatter's public rule sets and return the value corresponding to the longest + * parseable substring. This function's behavior is affected by the lenient + * parse mode. + * @param text The string to parse + * @param result the result of the parse, either a double or a long. + * @param parsePosition On entry, contains the position of the first character + * in "text" to examine. On exit, has been updated to contain the position + * of the first character in "text" that wasn't consumed by the parse. + * @see #setLenient + * @stable ICU 2.0 + */ + virtual void parse(const UnicodeString& text, + Formattable& result, + ParsePosition& parsePosition) const; + + + /** + * Redeclared Format method. + * @param text The string to parse + * @param result the result of the parse, either a double or a long. + * @param status Output param set to failure code when a problem occurs. + * @stable ICU 2.0 + */ + virtual inline void parse(const UnicodeString& text, + Formattable& result, + UErrorCode& status) const; + +#if !UCONFIG_NO_COLLATION + + /** + * Turns lenient parse mode on and off. + * + * When in lenient parse mode, the formatter uses a Collator for parsing the text. + * Only primary differences are treated as significant. This means that case + * differences, accent differences, alternate spellings of the same letter + * (e.g., ae and a-umlaut in German), ignorable characters, etc. are ignored in + * matching the text. In many cases, numerals will be accepted in place of words + * or phrases as well. + * + * For example, all of the following will correctly parse as 255 in English in + * lenient-parse mode: + * <br>"two hundred fifty-five" + * <br>"two hundred fifty five" + * <br>"TWO HUNDRED FIFTY-FIVE" + * <br>"twohundredfiftyfive" + * <br>"2 hundred fifty-5" + * + * The Collator used is determined by the locale that was + * passed to this object on construction. The description passed to this object + * on construction may supply additional collation rules that are appended to the + * end of the default collator for the locale, enabling additional equivalences + * (such as adding more ignorable characters or permitting spelled-out version of + * symbols; see the demo program for examples). + * + * It's important to emphasize that even strict parsing is relatively lenient: it + * will accept some text that it won't produce as output. In English, for example, + * it will correctly parse "two hundred zero" and "fifteen hundred". + * + * @param enabled If true, turns lenient-parse mode on; if false, turns it off. + * @see RuleBasedCollator + * @stable ICU 2.0 + */ + virtual void setLenient(UBool enabled); + + /** + * Returns true if lenient-parse mode is turned on. Lenient parsing is off + * by default. + * @return true if lenient-parse mode is turned on. + * @see #setLenient + * @stable ICU 2.0 + */ + virtual inline UBool isLenient(void) const; + +#endif + + /** + * Override the default rule set to use. If ruleSetName is null, reset + * to the initial default rule set. If the rule set is not a public rule set name, + * U_ILLEGAL_ARGUMENT_ERROR is returned in status. + * @param ruleSetName the name of the rule set, or null to reset the initial default. + * @param status set to failure code when a problem occurs. + * @stable ICU 2.6 + */ + virtual void setDefaultRuleSet(const UnicodeString& ruleSetName, UErrorCode& status); + + /** + * Return the name of the current default rule set. If the current rule set is + * not public, returns a bogus (and empty) UnicodeString. + * @return the name of the current default rule set + * @stable ICU 3.0 + */ + virtual UnicodeString getDefaultRuleSetName() const; + +public: + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.8 + */ + virtual UClassID getDynamicClassID(void) const; + +private: + RuleBasedNumberFormat(); // default constructor not implemented + + // this will ref the localizations if they are not NULL + // caller must deref to get adoption + RuleBasedNumberFormat(const UnicodeString& description, LocalizationInfo* localizations, + const Locale& locale, UParseError& perror, UErrorCode& status); + + void init(const UnicodeString& rules, LocalizationInfo* localizations, UParseError& perror, UErrorCode& status); + void dispose(); + void stripWhitespace(UnicodeString& src); + void initDefaultRuleSet(); + void format(double number, NFRuleSet& ruleSet); + NFRuleSet* findRuleSet(const UnicodeString& name, UErrorCode& status) const; + + /* friend access */ + friend class NFSubstitution; + friend class NFRule; + friend class FractionalPartSubstitution; + + inline NFRuleSet * getDefaultRuleSet() const; + Collator * getCollator() const; + DecimalFormatSymbols * getDecimalFormatSymbols() const; + +private: + NFRuleSet **ruleSets; + NFRuleSet *defaultRuleSet; + Locale locale; + Collator* collator; + DecimalFormatSymbols* decimalFormatSymbols; + UBool lenient; + UnicodeString* lenientParseRules; + LocalizationInfo* localizations; +}; + +// --------------- + +inline UnicodeString& +RuleBasedNumberFormat::format(const Formattable& obj, + UnicodeString& result, + UErrorCode& status) const +{ + // Don't use Format:: - use immediate base class only, + // in case immediate base modifies behavior later. + // dlf - the above comment is bogus, if there were a reason to modify + // it, it would be virtual, and there's no reason because it is + // a one-line macro in NumberFormat anyway, just like this one. + return NumberFormat::format(obj, result, status); +} + +inline UnicodeString& +RuleBasedNumberFormat::format(double number, UnicodeString& output) const { + FieldPosition pos(0); + return format(number, output, pos); +} + +inline UnicodeString& +RuleBasedNumberFormat::format(int32_t number, UnicodeString& output) const { + FieldPosition pos(0); + return format(number, output, pos); +} + +inline void +RuleBasedNumberFormat::parse(const UnicodeString& text, Formattable& result, UErrorCode& status) const +{ + NumberFormat::parse(text, result, status); +} + +#if !UCONFIG_NO_COLLATION + +inline UBool +RuleBasedNumberFormat::isLenient(void) const { + return lenient; +} + +#endif + +inline NFRuleSet* +RuleBasedNumberFormat::getDefaultRuleSet() const { + return defaultRuleSet; +} + +U_NAMESPACE_END + +/* U_HAVE_RBNF */ +#endif + +/* RBNF_H */ +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/rbtz.h b/Build/source/libs/icu-xetex/i18n/unicode/rbtz.h new file mode 100644 index 00000000000..d7f342d5f9e --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/rbtz.h @@ -0,0 +1,355 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef RBTZ_H +#define RBTZ_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Rule based customizable time zone + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/basictz.h" +#include "unicode/unistr.h" + +U_NAMESPACE_BEGIN + +// forward declaration +class UVector; +struct Transition; + +class U_I18N_API RuleBasedTimeZone : public BasicTimeZone { +public: + /** + * Constructs a <code>RuleBasedTimeZone</code> object with the ID and the + * <code>InitialTimeZoneRule</code>. The input <code>InitialTimeZoneRule</code> + * is adopted by this <code>RuleBasedTimeZone</code>, thus the caller must not + * delete it. + * @param id The time zone ID. + * @param initialRule The initial time zone rule. + * @draft ICU 3.8 + */ + RuleBasedTimeZone(const UnicodeString& id, InitialTimeZoneRule* initialRule); + + /** + * Copy constructor. + * @param source The RuleBasedTimeZone object to be copied. + * @draft ICU 3.8 + */ + RuleBasedTimeZone(const RuleBasedTimeZone& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~RuleBasedTimeZone(); + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + RuleBasedTimeZone& operator=(const RuleBasedTimeZone& right); + + /** + * Return true if the given <code>TimeZone</code> objects are + * semantically equal. Objects of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZone</code> objects are + *semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZone& that) const; + + /** + * Return true if the given <code>TimeZone</code> objects are + * semantically unequal. Objects of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZone</code> objects are + * semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZone& that) const; + + /** + * Adds the <code>TimeZoneRule</code> which represents time transitions. + * The <code>TimeZoneRule</code> must have start times, that is, the result + * of isTransitionRule() must be true. Otherwise, U_ILLEGAL_ARGUMENT_ERROR + * is set to the error code. + * The input <code>TimeZoneRule</code> is adopted by this + * <code>RuleBasedTimeZone</code> on successful completion of this method, + * thus, the caller must not delete it when no error is returned. + * After all rules are added, the caller must call complete() method to + * make this <code>RuleBasedTimeZone</code> ready to handle common time + * zone functions. + * @param rule The <code>TimeZoneRule</code>. + * @param status Output param to filled in with a success or an error. + * @draft ICU 3.8 + */ + void addTransitionRule(TimeZoneRule* rule, UErrorCode& status); + + /** + * Makes the <code>TimeZoneRule</code> ready to handle actual timezone + * calcuation APIs. This method collects time zone rules specified + * by the caller via the constructor and addTransitionRule() and + * builds internal structure for making the object ready to support + * time zone APIs such as getOffset(), getNextTransition() and others. + * @param status Output param to filled in with a success or an error. + * @draft ICU 3.8 + */ + void complete(UErrorCode& status); + + /** + * Clones TimeZone objects polymorphically. Clients are responsible for deleting + * the TimeZone object cloned. + * + * @return A new copy of this TimeZone object. + * @draft ICU 3.8 + */ + virtual TimeZone* clone(void) const; + + /** + * Returns the TimeZone's adjusted GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time in this time zone, taking daylight savings time into + * account) as of a particular reference date. The reference date is used to determine + * whether daylight savings time is in effect and needs to be figured into the offset + * that is returned (in other words, what is the adjusted GMT offset in this time zone + * at this particular date and time?). For the time zones produced by createTimeZone(), + * the reference data is specified according to the Gregorian calendar, and the date + * and time fields are local standard time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, local standard time + * @param status Output param to filled in with a success or an error. + * @return The offset in milliseconds to add to GMT to get local time. + * @draft ICU 3.8 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, UErrorCode& status) const; + + /** + * Gets the time zone offset, for current date, modified in case of + * daylight savings. This is the offset to add *to* UTC to get local time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, local standard time + * @param monthLength The length of the given month in days. + * @param status Output param to filled in with a success or an error. + * @return The offset in milliseconds to add to GMT to get local time. + * @draft ICU 3.8 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, + int32_t monthLength, UErrorCode& status) const; + + /** + * Returns the time zone raw and GMT offset for the given moment + * in time. Upon return, local-millis = GMT-millis + rawOffset + + * dstOffset. All computations are performed in the proleptic + * Gregorian calendar. The default implementation in the TimeZone + * class delegates to the 8-argument getOffset(). + * + * @param date moment in time for which to return offsets, in + * units of milliseconds from January 1, 1970 0:00 GMT, either GMT + * time or local wall time, depending on `local'. + * @param local if true, `date' is local wall time; otherwise it + * is in GMT time. + * @param rawOffset output parameter to receive the raw offset, that + * is, the offset not including DST adjustments + * @param dstOffset output parameter to receive the DST offset, + * that is, the offset to be added to `rawOffset' to obtain the + * total offset between local and GMT time. If DST is not in + * effect, this value is zero; otherwise it is a positive value, + * typically one hour. + * @param ec input-output error code + * @draft ICU 3.8 + */ + virtual void getOffset(UDate date, UBool local, int32_t& rawOffset, + int32_t& dstOffset, UErrorCode& ec) const; + + /** + * Sets the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @param offsetMillis The new raw GMT offset for this time zone. + * @draft ICU 3.8 + */ + virtual void setRawOffset(int32_t offsetMillis); + + /** + * Returns the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @return The TimeZone's raw GMT offset. + * @draft ICU 3.8 + */ + virtual int32_t getRawOffset(void) const; + + /** + * Queries if this time zone uses daylight savings time. + * @return true if this time zone uses daylight savings time, + * false, otherwise. + * @draft ICU 3.8 + */ + virtual UBool useDaylightTime(void) const; + + /** + * Queries if the given date is in daylight savings time in + * this time zone. + * This method is wasteful since it creates a new GregorianCalendar and + * deletes it each time it is called. This is a deprecated method + * and provided only for Java compatibility. + * + * @param date the given UDate. + * @param status Output param filled in with success/error code. + * @return true if the given date is in daylight savings time, + * false, otherwise. + * @deprecated ICU 2.4. Use Calendar::inDaylightTime() instead. + */ + virtual UBool inDaylightTime(UDate date, UErrorCode& status) const; + + /** + * Returns true if this zone has the same rule and offset as another zone. + * That is, if this zone differs only in ID, if at all. + * @param other the <code>TimeZone</code> object to be compared with + * @return true if the given zone is the same as this one, + * with the possible exception of the ID + * @draft ICU 3.8 + */ + virtual UBool hasSameRules(const TimeZone& other) const; + + /** + * Gets the first time zone transition after the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the first transition after the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Gets the most recent time zone transition before the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the most recent transition before the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Returns the number of <code>TimeZoneRule</code>s which represents time transitions, + * for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except + * <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value. + * @param status Receives error status code. + * @return The number of <code>TimeZoneRule</code>s representing time transitions. + * @draft ICU 3.8 + */ + virtual int32_t countTransitionRules(UErrorCode& status) /*const*/; + + /** + * Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code> + * which represent time transitions for this time zone. On successful return, + * the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and + * the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code> + * instances up to the size specified by trscount. The results are referencing the + * rule instance held by this time zone instance. Therefore, after this time zone + * is destructed, they are no longer available. + * @param initial Receives the initial timezone rule + * @param trsrules Receives the timezone transition rules + * @param trscount On input, specify the size of the array 'transitions' receiving + * the timezone transition rules. On output, actual number of + * rules filled in the array will be set. + * @param status Receives error status code. + * @draft ICU 3.8 + */ + virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial, + const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) /*const*/; + + /** + * Get time zone offsets from local wall time. + * @internal + */ + virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt, int32_t duplicatedTimeOpt, + int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) /*const*/; + +private: + void deleteRules(void); + void deleteTransitions(void); + UVector* copyRules(UVector* source); + TimeZoneRule* findRuleInFinal(UDate date, UBool local, + int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const; + UBool findNext(UDate base, UBool inclusive, UDate& time, TimeZoneRule*& from, TimeZoneRule*& to) const; + UBool findPrev(UDate base, UBool inclusive, UDate& time, TimeZoneRule*& from, TimeZoneRule*& to) const; + int32_t getLocalDelta(int32_t rawBefore, int32_t dstBefore, int32_t rawAfter, int32_t dstAfter, + int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const; + UDate getTransitionTime(Transition* transition, UBool local, + int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const; + void getOffsetInternal(UDate date, UBool local, int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt, + int32_t& rawOffset, int32_t& dstOffset, UErrorCode& ec) const; + + InitialTimeZoneRule *fInitialRule; + UVector *fHistoricRules; + UVector *fFinalRules; + UVector *fHistoricTransitions; + UBool fUpToDate; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // RBTZ_H + +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/regex.h b/Build/source/libs/icu-xetex/i18n/unicode/regex.h new file mode 100644 index 00000000000..ce24ef5f89b --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/regex.h @@ -0,0 +1,950 @@ +/* +********************************************************************** +* Copyright (C) 2002-2007, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* file name: regex.h +* encoding: US-ASCII +* indentation:4 +* +* created on: 2002oct22 +* created by: Andy Heninger +* +* ICU Regular Expressions, API for C++ +*/ + +#ifndef REGEX_H +#define REGEX_H + +//#define REGEX_DEBUG + +/** + * \file + * \brief C++ API: Regular Expressions + * + * <h2>Regular Expression API</h2> + * + * <p>The ICU API for processing regular expressions consists of two classes, + * <code>RegexPattern</code> and <code>RegexMatcher</code>. + * <code>RegexPattern</code> objects represent a pre-processed, or compiled + * regular expression. They are created from a regular expression pattern string, + * and can be used to create <code>RegexMatcher</code> objects for the pattern.</p> + * + * <p>Class <code>RegexMatcher</code> bundles together a regular expression + * pattern and a target string to which the search pattern will be applied. + * <code>RegexMatcher</code> includes API for doing plain find or search + * operations, for search and replace operations, and for obtaining detailed + * information about bounds of a match. </p> + * + * <p>Note that by constructing <code>RegexMatcher</code> objects directly from regular + * expression pattern strings application code can be simplified and the explicit + * need for <code>RegexPattern</code> objects can usually be eliminated. + * </p> + */ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_REGULAR_EXPRESSIONS + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/parseerr.h" + +#include "unicode/uregex.h" + +U_NAMESPACE_BEGIN + + +// Forward Declarations... + +class RegexMatcher; +class RegexPattern; +class UVector; +class UVector32; +class UnicodeSet; +struct REStackFrame; +struct Regex8BitSet; +class RuleBasedBreakIterator; +class RegexCImpl; + + + + +/** + * RBBIPatternDump Debug function, displays the compiled form of a pattern. + * @internal + */ +#ifdef REGEX_DEBUG +U_INTERNAL void U_EXPORT2 + RegexPatternDump(const RegexPattern *pat); +#else + #define RegexPatternDump(pat) +#endif + + + +/** + * Class <code>RegexPattern</code> represents a compiled regular expression. It includes + * factory methods for creating a RegexPattern object from the source (string) form + * of a regular expression, methods for creating RegexMatchers that allow the pattern + * to be applied to input text, and a few convenience methods for simple common + * uses of regular expressions. + * + * <p>Class RegexPattern is not intended to be subclassed.</p> + * + * @stable ICU 2.4 + */ +class U_I18N_API RegexPattern: public UObject { +public: + + /** + * default constructor. Create a RegexPattern object that refers to no actual + * pattern. Not normally needed; RegexPattern objects are usually + * created using the factory method <code>compile()</code>. + * + * @stable ICU 2.4 + */ + RegexPattern(); + + /** + * Copy Constructor. Create a new RegexPattern object that is equivalent + * to the source object. + * @param source the pattern object to be copied. + * @stable ICU 2.4 + */ + RegexPattern(const RegexPattern &source); + + /** + * Destructor. Note that a RegexPattern object must persist so long as any + * RegexMatcher objects that were created from the RegexPattern are active. + * @stable ICU 2.4 + */ + virtual ~RegexPattern(); + + /** + * Comparison operator. Two RegexPattern objects are considered equal if they + * were constructed from identical source patterns using the same match flag + * settings. + * @param that a RegexPattern object to compare with "this". + * @return TRUE if the objects are equivalent. + * @stable ICU 2.4 + */ + UBool operator==(const RegexPattern& that) const; + + /** + * Comparison operator. Two RegexPattern objects are considered equal if they + * were constructed from identical source patterns using the same match flag + * settings. + * @param that a RegexPattern object to compare with "this". + * @return TRUE if the objects are different. + * @stable ICU 2.4 + */ + inline UBool operator!=(const RegexPattern& that) const {return ! operator ==(that);}; + + /** + * Assignment operator. After assignment, this RegexPattern will behave identically + * to the source object. + * @stable ICU 2.4 + */ + RegexPattern &operator =(const RegexPattern &source); + + /** + * Create an exact copy of this RegexPattern object. Since RegexPattern is not + * intended to be subclasses, <code>clone()</code> and the copy construction are + * equivalent operations. + * @return the copy of this RegexPattern + * @stable ICU 2.4 + */ + virtual RegexPattern *clone() const; + + + /** + * Compiles the regular expression in string form into a RegexPattern + * object. These compile methods, rather than the constructors, are the usual + * way that RegexPattern objects are created. + * + * <p>Note that RegexPattern objects must not be deleted while RegexMatcher + * objects created from the pattern are active. RegexMatchers keep a pointer + * back to their pattern, so premature deletion of the pattern is a + * catastrophic error.</p> + * + * <p>All pattern match mode flags are set to their default values.</p> + * + * <p>Note that it is often more convenient to construct a RegexMatcher directly + * from a pattern string rather than separately compiling the pattern and + * then creating a RegexMatcher object from the pattern.</p> + * + * @param regex The regular expression to be compiled. + * @param pe Receives the position (line and column nubers) of any error + * within the regular expression.) + * @param status A reference to a UErrorCode to receive any errors. + * @return A regexPattern object for the compiled pattern. + * + * @stable ICU 2.4 + */ + static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex, + UParseError &pe, + UErrorCode &status); + + /** + * Compiles the regular expression in string form into a RegexPattern + * object using the specified match mode flags. These compile methods, + * rather than the constructors, are the usual way that RegexPattern objects + * are created. + * + * <p>Note that RegexPattern objects must not be deleted while RegexMatcher + * objects created from the pattern are active. RegexMatchers keep a pointer + * back to their pattern, so premature deletion of the pattern is a + * catastrophic error.</p> + * + * <p>Note that it is often more convenient to construct a RegexMatcher directly + * from a pattern string instead of than separately compiling the pattern and + * then creating a RegexMatcher object from the pattern.</p> + * + * @param regex The regular expression to be compiled. + * @param flags The match mode flags to be used. + * @param pe Receives the position (line and column nubers) of any error + * within the regular expression.) + * @param status A reference to a UErrorCode to receive any errors. + * @return A regexPattern object for the compiled pattern. + * + * @stable ICU 2.4 + */ + static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex, + uint32_t flags, + UParseError &pe, + UErrorCode &status); + + + /** + * Compiles the regular expression in string form into a RegexPattern + * object using the specified match mode flags. These compile methods, + * rather than the constructors, are the usual way that RegexPattern objects + * are created. + * + * <p>Note that RegexPattern objects must not be deleted while RegexMatcher + * objects created from the pattern are active. RegexMatchers keep a pointer + * back to their pattern, so premature deletion of the pattern is a + * catastrophic error.</p> + * + * <p>Note that it is often more convenient to construct a RegexMatcher directly + * from a pattern string instead of than separately compiling the pattern and + * then creating a RegexMatcher object from the pattern.</p> + * + * @param regex The regular expression to be compiled. + * @param flags The match mode flags to be used. + * @param status A reference to a UErrorCode to receive any errors. + * @return A regexPattern object for the compiled pattern. + * + * @stable ICU 2.6 + */ + static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex, + uint32_t flags, + UErrorCode &status); + + + /** + * Get the match mode flags that were used when compiling this pattern. + * @return the match mode flags + * @stable ICU 2.4 + */ + virtual uint32_t flags() const; + + /** + * Creates a RegexMatcher that will match the given input against this pattern. The + * RegexMatcher can then be used to perform match, find or replace operations + * on the input. Note that a RegexPattern object must not be deleted while + * RegexMatchers created from it still exist and might possibly be used again. + * <p> + * The matcher will retain a reference to the supplied input string, and all regexp + * pattern matching operations happen directly on this original string. It is + * critical that the string not be altered or deleted before use by the regular + * expression operations is complete. + * + * @param input The input string to which the regular expression will be applied. + * @param status A reference to a UErrorCode to receive any errors. + * @return A RegexMatcher object for this pattern and input. + * + * @stable ICU 2.4 + */ + virtual RegexMatcher *matcher(const UnicodeString &input, + UErrorCode &status) const; + +private: + /** + * Cause a compilation error if an application accidently attempts to + * create a matcher with a (UChar *) string as input rather than + * a UnicodeString. Avoids a dangling reference to a temporary string. + * <p> + * To efficiently work with UChar *strings, wrap the data in a UnicodeString + * using one of the aliasing constructors, such as + * <code>UnicodeString(UBool isTerminated, const UChar *text, int32_t textLength);</code> + * + * @internal + */ + RegexMatcher *matcher(const UChar *input, + UErrorCode &status) const; +public: + + + /** + * Creates a RegexMatcher that will match against this pattern. The + * RegexMatcher can be used to perform match, find or replace operations. + * Note that a RegexPattern object must not be deleted while + * RegexMatchers created from it still exist and might possibly be used again. + * + * @param status A reference to a UErrorCode to receive any errors. + * @return A RegexMatcher object for this pattern and input. + * + * @stable ICU 2.6 + */ + virtual RegexMatcher *matcher(UErrorCode &status) const; + + + /** + * Test whether a string matches a regular expression. This convenience function + * both compiles the reguluar expression and applies it in a single operation. + * Note that if the same pattern needs to be applied repeatedly, this method will be + * less efficient than creating and reusing a RegexMatcher object. + * + * @param regex The regular expression + * @param input The string data to be matched + * @param pe Receives the position of any syntax errors within the regular expression + * @param status A reference to a UErrorCode to receive any errors. + * @return True if the regular expression exactly matches the full input string. + * + * @stable ICU 2.4 + */ + static UBool U_EXPORT2 matches(const UnicodeString ®ex, + const UnicodeString &input, + UParseError &pe, + UErrorCode &status); + + + /** + * Returns the regular expression from which this pattern was compiled. + * @stable ICU 2.4 + */ + virtual UnicodeString pattern() const; + + + /** + * Split a string into fields. Somewhat like split() from Perl. + * The pattern matches identify delimiters that separate the input + * into fields. The input data between the matches becomes the + * fields themselves. + * <p> + * For the best performance on split() operations, + * <code>RegexMatcher::split</code> is perferable to this function + * + * @param input The string to be split into fields. The field delimiters + * match the pattern (in the "this" object) + * @param dest An array of UnicodeStrings to receive the results of the split. + * This is an array of actual UnicodeString objects, not an + * array of pointers to strings. Local (stack based) arrays can + * work well here. + * @param destCapacity The number of elements in the destination array. + * If the number of fields found is less than destCapacity, the + * extra strings in the destination array are not altered. + * If the number of destination strings is less than the number + * of fields, the trailing part of the input string, including any + * field delimiters, is placed in the last destination string. + * @param status A reference to a UErrorCode to receive any errors. + * @return The number of fields into which the input string was split. + * @stable ICU 2.4 + */ + virtual int32_t split(const UnicodeString &input, + UnicodeString dest[], + int32_t destCapacity, + UErrorCode &status) const; + + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.4 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.4 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + // + // Implementation Data + // + UnicodeString fPattern; // The original pattern string. + uint32_t fFlags; // The flags used when compiling the pattern. + // + UVector32 *fCompiledPat; // The compiled pattern p-code. + UnicodeString fLiteralText; // Any literal string data from the pattern, + // after un-escaping, for use during the match. + + UVector *fSets; // Any UnicodeSets referenced from the pattern. + Regex8BitSet *fSets8; // (and fast sets for latin-1 range.) + + + UErrorCode fDeferredStatus; // status if some prior error has left this + // RegexPattern in an unusable state. + + int32_t fMinMatchLen; // Minimum Match Length. All matches will have length + // >= this value. For some patterns, this calculated + // value may be less than the true shortest + // possible match. + + int32_t fFrameSize; // Size of a state stack frame in the + // execution engine. + + int32_t fDataSize; // The size of the data needed by the pattern that + // does not go on the state stack, but has just + // a single copy per matcher. + + UVector32 *fGroupMap; // Map from capture group number to position of + // the group's variables in the matcher stack frame. + + int32_t fMaxCaptureDigits; + + UnicodeSet **fStaticSets; // Ptr to static (shared) sets for predefined + // regex character classes, e.g. Word. + + Regex8BitSet *fStaticSets8; // Ptr to the static (shared) latin-1 only + // sets for predefined regex classes. + + int32_t fStartType; // Info on how a match must start. + int32_t fInitialStringIdx; // + int32_t fInitialStringLen; + UnicodeSet *fInitialChars; + UChar32 fInitialChar; + Regex8BitSet *fInitialChars8; + + friend class RegexCompile; + friend class RegexMatcher; + friend class RegexCImpl; + + // + // Implementation Methods + // + void init(); // Common initialization, for use by constructors. + void zap(); // Common cleanup +#ifdef REGEX_DEBUG + void dumpOp(int32_t index) const; + friend void U_EXPORT2 RegexPatternDump(const RegexPattern *); +#endif + +}; + + + +/** + * class RegexMatcher bundles together a reular expression pattern and + * input text to which the expression can be applied. It includes methods + * for testing for matches, and for find and replace operations. + * + * <p>Class RegexMatcher is not intended to be subclassed.</p> + * + * @stable ICU 2.4 + */ +class U_I18N_API RegexMatcher: public UObject { +public: + + /** + * Construct a RegexMatcher for a regular expression. + * This is a convenience method that avoids the need to explicitly create + * a RegexPattern object. Note that if several RegexMatchers need to be + * created for the same expression, it will be more efficient to + * separately create and cache a RegexPattern object, and use + * its matcher() method to create the RegexMatcher objects. + * + * @param regexp The Regular Expression to be compiled. + * @param flags Regular expression options, such as case insensitive matching. + * @see UREGEX_CASE_INSENSITIVE + * @param status Any errors are reported by setting this UErrorCode variable. + * @stable ICU 2.6 + */ + RegexMatcher(const UnicodeString ®exp, uint32_t flags, UErrorCode &status); + + /** + * Construct a RegexMatcher for a regular expression. + * This is a convenience method that avoids the need to explicitly create + * a RegexPattern object. Note that if several RegexMatchers need to be + * created for the same expression, it will be more efficient to + * separately create and cache a RegexPattern object, and use + * its matcher() method to create the RegexMatcher objects. + * <p> + * The matcher will retain a reference to the supplied input string, and all regexp + * pattern matching operations happen directly on the original string. It is + * critical that the string not be altered or deleted before use by the regular + * expression operations is complete. + * + * @param regexp The Regular Expression to be compiled. + * @param input The string to match. The matcher retains a reference to the + * caller's string; mo copy is made. + * @param flags Regular expression options, such as case insensitive matching. + * @see UREGEX_CASE_INSENSITIVE + * @param status Any errors are reported by setting this UErrorCode variable. + * @stable ICU 2.6 + */ + RegexMatcher(const UnicodeString ®exp, const UnicodeString &input, + uint32_t flags, UErrorCode &status); + +private: + /** + * Cause a compilation error if an application accidently attempts to + * create a matcher with a (UChar *) string as input rather than + * a UnicodeString. Avoids a dangling reference to a temporary string. + * <p> + * To efficiently work with UChar *strings, wrap the data in a UnicodeString + * using one of the aliasing constructors, such as + * <code>UnicodeString(UBool isTerminated, const UChar *text, int32_t textLength);</code> + * + * @internal + */ + RegexMatcher(const UnicodeString ®exp, const UChar *input, + uint32_t flags, UErrorCode &status); +public: + + + /** + * Destructor. + * + * @stable ICU 2.4 + */ + virtual ~RegexMatcher(); + + + /** + * Attempts to match the entire input string against the pattern. + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if there is a match + * @stable ICU 2.4 + */ + virtual UBool matches(UErrorCode &status); + + /** + * Attempts to match the input string, beginning at startIndex, against the pattern. + * The match must extend to the end of the input string. + * @param startIndex The input string index at which to begin matching. + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if there is a match + * @stable ICU 2.8 + */ + virtual UBool matches(int32_t startIndex, UErrorCode &status); + + + + + /** + * Attempts to match the input string, starting from the beginning, against the pattern. + * Like the matches() method, this function always starts at the beginning of the input string; + * unlike that function, it does not require that the entire input string be matched. + * + * <p>If the match succeeds then more information can be obtained via the <code>start()</code>, + * <code>end()</code>, and <code>group()</code> functions.</p> + * + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if there is a match at the start of the input string. + * @stable ICU 2.4 + */ + virtual UBool lookingAt(UErrorCode &status); + + + /** + * Attempts to match the input string, starting from the specified index, against the pattern. + * The match may be of any length, and is not required to extend to the end + * of the input string. Contrast with match(). + * + * <p>If the match succeeds then more information can be obtained via the <code>start()</code>, + * <code>end()</code>, and <code>group()</code> functions.</p> + * + * @param startIndex The input string index at which to begin matching. + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if there is a match. + * @stable ICU 2.8 + */ + virtual UBool lookingAt(int32_t startIndex, UErrorCode &status); + + /** + * Find the next pattern match in the input string. + * The find begins searching the input at the location following the end of + * the previous match, or at the start of the string if there is no previous match. + * If a match is found, <code>start(), end()</code> and <code>group()</code> + * will provide more information regarding the match. + * <p>Note that if the input string is changed by the application, + * use find(startPos, status) instead of find(), because the saved starting + * position may not be valid with the altered input string.</p> + * @return TRUE if a match is found. + * @stable ICU 2.4 + */ + virtual UBool find(); + + + /** + * Resets this RegexMatcher and then attempts to find the next substring of the + * input string that matches the pattern, starting at the specified index. + * + * @param start the position in the input string to begin the search + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if a match is found. + * @stable ICU 2.4 + */ + virtual UBool find(int32_t start, UErrorCode &status); + + + /** + * Returns a string containing the text matched by the previous match. + * If the pattern can match an empty string, an empty string may be returned. + * @param status A reference to a UErrorCode to receive any errors. + * Possible errors are U_REGEX_INVALID_STATE if no match + * has been attempted or the last match failed. + * @return a string containing the matched input text. + * @stable ICU 2.4 + */ + virtual UnicodeString group(UErrorCode &status) const; + + + /** + * Returns a string containing the text captured by the given group + * during the previous match operation. Group(0) is the entire match. + * + * @param groupNum the capture group number + * @param status A reference to a UErrorCode to receive any errors. + * Possible errors are U_REGEX_INVALID_STATE if no match + * has been attempted or the last match failed and + * U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number. + * @return the captured text + * @stable ICU 2.4 + */ + virtual UnicodeString group(int32_t groupNum, UErrorCode &status) const; + + + /** + * Returns the number of capturing groups in this matcher's pattern. + * @return the number of capture groups + * @stable ICU 2.4 + */ + virtual int32_t groupCount() const; + + + /** + * Returns the index in the input string of the start of the text matched + * during the previous match operation. + * @param status a reference to a UErrorCode to receive any errors. + * @return The position in the input string of the start of the last match. + * @stable ICU 2.4 + */ + virtual int32_t start(UErrorCode &status) const; + + + /** + * Returns the index in the input string of the start of the text matched by the + * specified capture group during the previous match operation. Return -1 if + * the capture group exists in the pattern, but was not part of the last match. + * + * @param group the capture group number + * @param status A reference to a UErrorCode to receive any errors. Possible + * errors are U_REGEX_INVALID_STATE if no match has been + * attempted or the last match failed, and + * U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number + * @return the start position of substring matched by the specified group. + * @stable ICU 2.4 + */ + virtual int32_t start(int32_t group, UErrorCode &status) const; + + + /** + * Returns the index in the input string of the first character following the + * text matched during the previous match operation. + * @param status A reference to a UErrorCode to receive any errors. Possible + * errors are U_REGEX_INVALID_STATE if no match has been + * attempted or the last match failed. + * @return the index of the last character matched, plus one. + * @stable ICU 2.4 + */ + virtual int32_t end(UErrorCode &status) const; + + + /** + * Returns the index in the input string of the character following the + * text matched by the specified capture group during the previous match operation. + * @param group the capture group number + * @param status A reference to a UErrorCode to receive any errors. Possible + * errors are U_REGEX_INVALID_STATE if no match has been + * attempted or the last match failed and + * U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number + * @return the index of the first character following the text + * captured by the specifed group during the previous match operation. + * Return -1 if the capture group exists in the pattern but was not part of the match. + * @stable ICU 2.4 + */ + virtual int32_t end(int32_t group, UErrorCode &status) const; + + + /** + * Resets this matcher. The effect is to remove any memory of previous matches, + * and to cause subsequent find() operations to begin at the beginning of + * the input string. + * + * @return this RegexMatcher. + * @stable ICU 2.4 + */ + virtual RegexMatcher &reset(); + + + /** + * Resets this matcher, and set the current input position. + * The effect is to remove any memory of previous matches, + * and to cause subsequent find() operations to begin at + * the specified position in the input string. + * + * @return this RegexMatcher. + * @stable ICU 2.8 + */ + virtual RegexMatcher &reset(int32_t index, UErrorCode &status); + + + /** + * Resets this matcher with a new input string. This allows instances of RegexMatcher + * to be reused, which is more efficient than creating a new RegexMatcher for + * each input string to be processed. + * @param input The new string on which subsequent pattern matches will operate. + * The matcher retains a reference to the callers string, and operates + * directly on that. Ownership of the string remains with the caller. + * Because no copy of the string is made, it is essential that the + * caller not delete the string until after regexp operations on it + * are done. + * @return this RegexMatcher. + * @stable ICU 2.4 + */ + virtual RegexMatcher &reset(const UnicodeString &input); + +private: + /** + * Cause a compilation error if an application accidently attempts to + * reset a matcher with a (UChar *) string as input rather than + * a UnicodeString. Avoids a dangling reference to a temporary string. + * <p> + * To efficiently work with UChar *strings, wrap the data in a UnicodeString + * using one of the aliasing constructors, such as + * <code>UnicodeString(UBool isTerminated, const UChar *text, int32_t textLength);</code> + * + * @internal + */ + RegexMatcher &reset(const UChar *input); +public: + + /** + * Returns the input string being matched. The returned string is not a copy, + * but the live input string. It should not be altered or deleted. + * @return the input string + * @stable ICU 2.4 + */ + virtual const UnicodeString &input() const; + + + /** + * Returns the pattern that is interpreted by this matcher. + * @return the RegexPattern for this RegexMatcher + * @stable ICU 2.4 + */ + virtual const RegexPattern &pattern() const; + + + /** + * Replaces every substring of the input that matches the pattern + * with the given replacement string. This is a convenience function that + * provides a complete find-and-replace-all operation. + * + * This method first resets this matcher. It then scans the input string + * looking for matches of the pattern. Input that is not part of any + * match is left unchanged; each match is replaced in the result by the + * replacement string. The replacement string may contain references to + * capture groups. + * + * @param replacement a string containing the replacement text. + * @param status a reference to a UErrorCode to receive any errors. + * @return a string containing the results of the find and replace. + * @stable ICU 2.4 + */ + virtual UnicodeString replaceAll(const UnicodeString &replacement, UErrorCode &status); + + + /** + * Replaces the first substring of the input that matches + * the pattern with the replacement string. This is a convenience + * function that provides a complete find-and-replace operation. + * + * <p>This function first resets this RegexMatcher. It then scans the input string + * looking for a match of the pattern. Input that is not part + * of the match is appended directly to the result string; the match is replaced + * in the result by the replacement string. The replacement string may contain + * references to captured groups.</p> + * + * <p>The state of the matcher (the position at which a subsequent find() + * would begin) after completing a replaceFirst() is not specified. The + * RegexMatcher should be reset before doing additional find() operations.</p> + * + * @param replacement a string containing the replacement text. + * @param status a reference to a UErrorCode to receive any errors. + * @return a string containing the results of the find and replace. + * @stable ICU 2.4 + */ + virtual UnicodeString replaceFirst(const UnicodeString &replacement, UErrorCode &status); + + /** + * Implements a replace operation intended to be used as part of an + * incremental find-and-replace. + * + * <p>The input string, starting from the end of the previous replacement and ending at + * the start of the current match, is appended to the destination string. Then the + * replacement string is appended to the output string, + * including handling any substitutions of captured text.</p> + * + * <p>For simple, prepackaged, non-incremental find-and-replace + * operations, see replaceFirst() or replaceAll().</p> + * + * @param dest A UnicodeString to which the results of the find-and-replace are appended. + * @param replacement A UnicodeString that provides the text to be substituted for + * the input text that matched the regexp pattern. The replacement + * text may contain references to captured text from the + * input. + * @param status A reference to a UErrorCode to receive any errors. Possible + * errors are U_REGEX_INVALID_STATE if no match has been + * attempted or the last match failed, and U_INDEX_OUTOFBOUNDS_ERROR + * if the replacement text specifies a capture group that + * does not exist in the pattern. + * + * @return this RegexMatcher + * @stable ICU 2.4 + * + */ + virtual RegexMatcher &appendReplacement(UnicodeString &dest, + const UnicodeString &replacement, UErrorCode &status); + + + /** + * As the final step in a find-and-replace operation, append the remainder + * of the input string, starting at the position following the last appendReplacement(), + * to the destination string. <code>appendTail()</code> is intended to be invoked after one + * or more invocations of the <code>RegexMatcher::appendReplacement()</code>. + * + * @param dest A UnicodeString to which the results of the find-and-replace are appended. + * @return the destination string. + * @stable ICU 2.4 + */ + virtual UnicodeString &appendTail(UnicodeString &dest); + + + + /** + * Split a string into fields. Somewhat like split() from Perl. + * The pattern matches identify delimiters that separate the input + * into fields. The input data between the matches becomes the + * fields themselves. + * <p> + * + * @param input The string to be split into fields. The field delimiters + * match the pattern (in the "this" object). This matcher + * will be reset to this input string. + * @param dest An array of UnicodeStrings to receive the results of the split. + * This is an array of actual UnicodeString objects, not an + * array of pointers to strings. Local (stack based) arrays can + * work well here. + * @param destCapacity The number of elements in the destination array. + * If the number of fields found is less than destCapacity, the + * extra strings in the destination array are not altered. + * If the number of destination strings is less than the number + * of fields, the trailing part of the input string, including any + * field delimiters, is placed in the last destination string. + * @param status A reference to a UErrorCode to receive any errors. + * @return The number of fields into which the input string was split. + * @stable ICU 2.6 + */ + virtual int32_t split(const UnicodeString &input, + UnicodeString dest[], + int32_t destCapacity, + UErrorCode &status); + + + + /** + * setTrace Debug function, enable/disable tracing of the matching engine. + * For internal ICU development use only. DO NO USE!!!! + * @internal + */ + void setTrace(UBool state); + + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + +private: + // Constructors and other object boilerplate are private. + // Instances of RegexMatcher can not be assigned, copied, cloned, etc. + RegexMatcher(); // default constructor not implemented + RegexMatcher(const RegexPattern *pat); + RegexMatcher(const RegexMatcher &other); + RegexMatcher &operator =(const RegexMatcher &rhs); + friend class RegexPattern; + friend class RegexCImpl; + + // + // MatchAt This is the internal interface to the match engine itself. + // Match status comes back in matcher member variables. + // + void MatchAt(int32_t startIdx, UErrorCode &status); + inline void backTrack(int32_t &inputIdx, int32_t &patIdx); + UBool isWordBoundary(int32_t pos); // perform Perl-like \b test + UBool isUWordBoundary(int32_t pos); // perform RBBI based \b test + REStackFrame *resetStack(); + inline REStackFrame *StateSave(REStackFrame *fp, int32_t savePatIdx, + int32_t frameSize, UErrorCode &status); + + + const RegexPattern *fPattern; + RegexPattern *fPatternOwned; // Non-NULL if this matcher owns the pattern, and + // should delete it when through. + const UnicodeString *fInput; + + UBool fMatch; // True if the last match was successful. + int32_t fMatchStart; // Position of the start of the most recent match + int32_t fMatchEnd; // First position after the end of the most recent match + int32_t fLastMatchEnd; // First position after the end of the previous match, + // or -1 if there was no previous match. + int32_t fLastReplaceEnd; // First position after the end of the previous appendReplacement(); + + UVector32 *fStack; + REStackFrame *fFrame; // After finding a match, the last active stack + // frame, which will contain the capture group results. + // NOT valid while match engine is running. + + int32_t *fData; // Data area for use by the compiled pattern. + int32_t fSmallData[8]; // Use this for data if it's enough. + + UBool fTraceDebug; // Set true for debug tracing of match engine. + + UErrorCode fDeferredStatus; // Save error state if that cannot be immediately + // reported, or that permanently disables this matcher. + + RuleBasedBreakIterator *fWordBreakItr; + + +}; + +U_NAMESPACE_END +#endif // UCONFIG_NO_REGULAR_EXPRESSIONS +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/search.h b/Build/source/libs/icu-xetex/i18n/unicode/search.h new file mode 100644 index 00000000000..a2fb2a8c7a0 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/search.h @@ -0,0 +1,569 @@ +/* +********************************************************************** +* Copyright (C) 2001-2005 IBM and others. All rights reserved. +********************************************************************** +* Date Name Description +* 03/22/2000 helena Creation. +********************************************************************** +*/ + +#ifndef SEARCH_H +#define SEARCH_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: SearchIterator object. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/chariter.h" +#include "unicode/brkiter.h" +#include "unicode/usearch.h" + +/** +* @stable ICU 2.0 +*/ +struct USearch; +/** +* @stable ICU 2.0 +*/ +typedef struct USearch USearch; + +U_NAMESPACE_BEGIN + +/** + * + * <tt>SearchIterator</tt> is an abstract base class that provides + * methods to search for a pattern within a text string. Instances of + * <tt>SearchIterator</tt> maintain a current position and scans over the + * target text, returning the indices the pattern is matched and the length + * of each match. + * <p> + * <tt>SearchIterator</tt> defines a protocol for text searching. + * Subclasses provide concrete implementations of various search algorithms. + * For example, <tt>StringSearch</tt> implements language-sensitive pattern + * matching based on the comparison rules defined in a + * <tt>RuleBasedCollator</tt> object. + * <p> + * Other options for searching includes using a BreakIterator to restrict + * the points at which matches are detected. + * <p> + * <tt>SearchIterator</tt> provides an API that is similar to that of + * other text iteration classes such as <tt>BreakIterator</tt>. Using + * this class, it is easy to scan through text looking for all occurances of + * a given pattern. The following example uses a <tt>StringSearch</tt> + * object to find all instances of "fox" in the target string. Any other + * subclass of <tt>SearchIterator</tt> can be used in an identical + * manner. + * <pre><code> + * UnicodeString target("The quick brown fox jumped over the lazy fox"); + * UnicodeString pattern("fox"); + * + * SearchIterator *iter = new StringSearch(pattern, target); + * UErrorCode error = U_ZERO_ERROR; + * for (int pos = iter->first(error); pos != USEARCH_DONE; + * pos = iter->next(error)) { + * printf("Found match at %d pos, length is %d\n", pos, + * iter.getMatchLength()); + * } + * </code></pre> + * + * @see StringSearch + * @see RuleBasedCollator + */ +class U_I18N_API SearchIterator : public UObject { + +public: + + // public constructors and destructors ------------------------------- + + /** + * Copy constructor that creates a SearchIterator instance with the same + * behavior, and iterating over the same text. + * @param other the SearchIterator instance to be copied. + * @stable ICU 2.0 + */ + SearchIterator(const SearchIterator &other); + + /** + * Destructor. Cleans up the search iterator data struct. + * @stable ICU 2.0 + */ + virtual ~SearchIterator(); + + // public get and set methods ---------------------------------------- + + /** + * Sets the index to point to the given position, and clears any state + * that's affected. + * <p> + * This method takes the argument index and sets the position in the text + * string accordingly without checking if the index is pointing to a + * valid starting point to begin searching. + * @param position within the text to be set. If position is less + * than or greater than the text range for searching, + * an U_INDEX_OUTOFBOUNDS_ERROR will be returned + * @param status for errors if it occurs + * @stable ICU 2.0 + */ + virtual void setOffset(int32_t position, UErrorCode &status) = 0; + + /** + * Return the current index in the text being searched. + * If the iteration has gone past the end of the text + * (or past the beginning for a backwards search), USEARCH_DONE + * is returned. + * @return current index in the text being searched. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(void) const = 0; + + /** + * Sets the text searching attributes located in the enum + * USearchAttribute with values from the enum USearchAttributeValue. + * USEARCH_DEFAULT can be used for all attributes for resetting. + * @param attribute text attribute (enum USearchAttribute) to be set + * @param value text attribute value + * @param status for errors if it occurs + * @stable ICU 2.0 + */ + void setAttribute(USearchAttribute attribute, + USearchAttributeValue value, + UErrorCode &status); + + /** + * Gets the text searching attributes + * @param attribute text attribute (enum USearchAttribute) to be retrieve + * @return text attribute value + * @stable ICU 2.0 + */ + USearchAttributeValue getAttribute(USearchAttribute attribute) const; + + /** + * Returns the index to the match in the text string that was searched. + * This call returns a valid result only after a successful call to + * <tt>first</tt>, <tt>next</tt>, <tt>previous</tt>, or <tt>last</tt>. + * Just after construction, or after a searching method returns + * <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>. + * <p> + * Use getMatchedLength to get the matched string length. + * @return index of a substring within the text string that is being + * searched. + * @see #first + * @see #next + * @see #previous + * @see #last + * @stable ICU 2.0 + */ + int32_t getMatchedStart(void) const; + + /** + * Returns the length of text in the string which matches the search + * pattern. This call returns a valid result only after a successful call + * to <tt>first</tt>, <tt>next</tt>, <tt>previous</tt>, or <tt>last</tt>. + * Just after construction, or after a searching method returns + * <tt>USEARCH_DONE</tt>, this method will return 0. + * @return The length of the match in the target text, or 0 if there + * is no match currently. + * @see #first + * @see #next + * @see #previous + * @see #last + * @stable ICU 2.0 + */ + int32_t getMatchedLength(void) const; + + /** + * Returns the text that was matched by the most recent call to + * <tt>first</tt>, <tt>next</tt>, <tt>previous</tt>, or <tt>last</tt>. + * If the iterator is not pointing at a valid match (e.g. just after + * construction or after <tt>USEARCH_DONE</tt> has been returned, + * returns an empty string. + * @param result stores the matched string or an empty string if a match + * is not found. + * @see #first + * @see #next + * @see #previous + * @see #last + * @stable ICU 2.0 + */ + void getMatchedText(UnicodeString &result) const; + + /** + * Set the BreakIterator that will be used to restrict the points + * at which matches are detected. The user is responsible for deleting + * the breakiterator. + * @param breakiter A BreakIterator that will be used to restrict the + * points at which matches are detected. If a match is + * found, but the match's start or end index is not a + * boundary as determined by the <tt>BreakIterator</tt>, + * the match will be rejected and another will be searched + * for. If this parameter is <tt>NULL</tt>, no break + * detection is attempted. + * @param status for errors if it occurs + * @see BreakIterator + * @stable ICU 2.0 + */ + void setBreakIterator(BreakIterator *breakiter, UErrorCode &status); + + /** + * Returns the BreakIterator that is used to restrict the points at + * which matches are detected. This will be the same object that was + * passed to the constructor or to <tt>setBreakIterator</tt>. + * Note that <tt>NULL</tt> is a legal value; it means that break + * detection should not be attempted. + * @return BreakIterator used to restrict matchings. + * @see #setBreakIterator + * @stable ICU 2.0 + */ + const BreakIterator * getBreakIterator(void) const; + + /** + * Set the string text to be searched. Text iteration will hence begin at + * the start of the text string. This method is useful if you want to + * re-use an iterator to search for the same pattern within a different + * body of text. The user is responsible for deleting the text. + * @param text string to be searched. + * @param status for errors. If the text length is 0, + * an U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + virtual void setText(const UnicodeString &text, UErrorCode &status); + + /** + * Set the string text to be searched. Text iteration will hence begin at + * the start of the text string. This method is useful if you want to + * re-use an iterator to search for the same pattern within a different + * body of text. + * <p> + * Note: No parsing of the text within the <tt>CharacterIterator</tt> + * will be done during searching for this version. The block of text + * in <tt>CharacterIterator</tt> will be used as it is. + * The user is responsible for deleting the text. + * @param text string iterator to be searched. + * @param status for errors if any. If the text length is 0 then an + * U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + virtual void setText(CharacterIterator &text, UErrorCode &status); + + /** + * Return the string text to be searched. + * @return text string to be searched. + * @stable ICU 2.0 + */ + const UnicodeString & getText(void) const; + + // operator overloading ---------------------------------------------- + + /** + * Equality operator. + * @param that SearchIterator instance to be compared. + * @return TRUE if both BreakIterators are of the same class, have the + * same behavior, terates over the same text and have the same + * attributes. FALSE otherwise. + * @stable ICU 2.0 + */ + virtual UBool operator==(const SearchIterator &that) const; + + /** + * Not-equal operator. + * @param that SearchIterator instance to be compared. + * @return FALSE if operator== returns TRUE, and vice versa. + * @stable ICU 2.0 + */ + UBool operator!=(const SearchIterator &that) const; + + // public methods ---------------------------------------------------- + + /** + * Returns a copy of SearchIterator with the same behavior, and + * iterating over the same text, as this one. Note that all data will be + * replicated, except for the text string to be searched. + * @return cloned object + * @stable ICU 2.0 + */ + virtual SearchIterator* safeClone(void) const = 0; + + /** + * Returns the first index at which the string text matches the search + * pattern. The iterator is adjusted so that its current index (as + * returned by <tt>getOffset</tt>) is the match position if one + * was found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the iterator will be adjusted to the index USEARCH_DONE + * @param status for errors if it occurs + * @return The character index of the first match, or + * <tt>USEARCH_DONE</tt> if there are no matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t first(UErrorCode &status); + + /** + * Returns the first index greater than <tt>position</tt> at which the + * string text matches the search pattern. The iterator is adjusted so + * that its current index (as returned by <tt>getOffset</tt>) is the + * match position if one was found. If a match is not found, + * <tt>USEARCH_DONE</tt> will be returned and the iterator will be + * adjusted to the index USEARCH_DONE + * @param position where search if to start from. If position is less + * than or greater than the text range for searching, + * an U_INDEX_OUTOFBOUNDS_ERROR will be returned + * @param status for errors if it occurs + * @return The character index of the first match following + * <tt>position</tt>, or <tt>USEARCH_DONE</tt> if there are no + * matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t following(int32_t position, UErrorCode &status); + + /** + * Returns the last index in the target text at which it matches the + * search pattern. The iterator is adjusted so that its current index + * (as returned by <tt>getOffset</tt>) is the match position if one was + * found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the iterator will be adjusted to the index USEARCH_DONE. + * @param status for errors if it occurs + * @return The index of the first match, or <tt>USEARCH_DONE</tt> if + * there are no matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t last(UErrorCode &status); + + /** + * Returns the first index less than <tt>position</tt> at which the string + * text matches the search pattern. The iterator is adjusted so that its + * current index (as returned by <tt>getOffset</tt>) is the match + * position if one was found. If a match is not found, + * <tt>USEARCH_DONE</tt> will be returned and the iterator will be + * adjusted to the index USEARCH_DONE + * @param position where search is to start from. If position is less + * than or greater than the text range for searching, + * an U_INDEX_OUTOFBOUNDS_ERROR will be returned + * @param status for errors if it occurs + * @return The character index of the first match preceding + * <tt>position</tt>, or <tt>USEARCH_DONE</tt> if there are + * no matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t preceding(int32_t position, UErrorCode &status); + + /** + * Returns the index of the next point at which the text matches the + * search pattern, starting from the current position + * The iterator is adjusted so that its current index (as returned by + * <tt>getOffset</tt>) is the match position if one was found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the iterator will be adjusted to a position after the end of the text + * string. + * @param status for errors if it occurs + * @return The index of the next match after the current position, + * or <tt>USEARCH_DONE</tt> if there are no more matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t next(UErrorCode &status); + + /** + * Returns the index of the previous point at which the string text + * matches the search pattern, starting at the current position. + * The iterator is adjusted so that its current index (as returned by + * <tt>getOffset</tt>) is the match position if one was found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the iterator will be adjusted to the index USEARCH_DONE + * @param status for errors if it occurs + * @return The index of the previous match before the current position, + * or <tt>USEARCH_DONE</tt> if there are no more matches. + * @see #getOffset + * @stable ICU 2.0 + */ + int32_t previous(UErrorCode &status); + + /** + * Resets the iteration. + * Search will begin at the start of the text string if a forward + * iteration is initiated before a backwards iteration. Otherwise if a + * backwards iteration is initiated before a forwards iteration, the + * search will begin at the end of the text string. + * @stable ICU 2.0 + */ + virtual void reset(); + +protected: + // protected data members --------------------------------------------- + + /** + * C search data struct + * @stable ICU 2.0 + */ + USearch *m_search_; + + /** + * Break iterator. + * Currently the C++ breakiterator does not have getRules etc to reproduce + * another in C. Hence we keep the original around and do the verification + * at the end of the match. The user is responsible for deleting this + * break iterator. + * @stable ICU 2.0 + */ + BreakIterator *m_breakiterator_; + + /** + * Unicode string version of the search text + * @stable ICU 2.0 + */ + UnicodeString m_text_; + + // protected constructors and destructors ----------------------------- + + /** + * Default constructor. + * Initializes data to the default values. + * @stable ICU 2.0 + */ + SearchIterator(); + + /** + * Constructor for use by subclasses. + * @param text The target text to be searched. + * @param breakiter A {@link BreakIterator} that is used to restrict the + * points at which matches are detected. If + * <tt>handleNext</tt> or <tt>handlePrev</tt> finds a + * match, but the match's start or end index is not a + * boundary as determined by the <tt>BreakIterator</tt>, + * the match is rejected and <tt>handleNext</tt> or + * <tt>handlePrev</tt> is called again. If this parameter + * is <tt>NULL</tt>, no break detection is attempted. + * @see #handleNext + * @see #handlePrev + * @stable ICU 2.0 + */ + SearchIterator(const UnicodeString &text, + BreakIterator *breakiter = NULL); + + /** + * Constructor for use by subclasses. + * <p> + * Note: No parsing of the text within the <tt>CharacterIterator</tt> + * will be done during searching for this version. The block of text + * in <tt>CharacterIterator</tt> will be used as it is. + * @param text The target text to be searched. + * @param breakiter A {@link BreakIterator} that is used to restrict the + * points at which matches are detected. If + * <tt>handleNext</tt> or <tt>handlePrev</tt> finds a + * match, but the match's start or end index is not a + * boundary as determined by the <tt>BreakIterator</tt>, + * the match is rejected and <tt>handleNext</tt> or + * <tt>handlePrev</tt> is called again. If this parameter + * is <tt>NULL</tt>, no break detection is attempted. + * @see #handleNext + * @see #handlePrev + * @stable ICU 2.0 + */ + SearchIterator(CharacterIterator &text, BreakIterator *breakiter = NULL); + + // protected methods -------------------------------------------------- + + /** + * Assignment operator. Sets this iterator to have the same behavior, + * and iterate over the same text, as the one passed in. + * @param that instance to be copied. + * @stable ICU 2.0 + */ + SearchIterator & operator=(const SearchIterator &that); + + /** + * Abstract method which subclasses override to provide the mechanism + * for finding the next match in the target text. This allows different + * subclasses to provide different search algorithms. + * <p> + * If a match is found, the implementation should return the index at + * which the match starts and should call + * <tt>setMatchLength</tt> with the number of characters + * in the target text that make up the match. If no match is found, the + * method should return USEARCH_DONE. + * <p> + * @param position The index in the target text at which the search + * should start. + * @param status for error codes if it occurs. + * @return index at which the match starts, else if match is not found + * USEARCH_DONE is returned + * @see #setMatchLength + * @stable ICU 2.0 + */ + virtual int32_t handleNext(int32_t position, UErrorCode &status) + = 0; + + /** + * Abstract method which subclasses override to provide the mechanism for + * finding the previous match in the target text. This allows different + * subclasses to provide different search algorithms. + * <p> + * If a match is found, the implementation should return the index at + * which the match starts and should call + * <tt>setMatchLength</tt> with the number of characters + * in the target text that make up the match. If no match is found, the + * method should return USEARCH_DONE. + * <p> + * @param position The index in the target text at which the search + * should start. + * @param status for error codes if it occurs. + * @return index at which the match starts, else if match is not found + * USEARCH_DONE is returned + * @see #setMatchLength + * @stable ICU 2.0 + */ + virtual int32_t handlePrev(int32_t position, UErrorCode &status) + = 0; + + /** + * Sets the length of the currently matched string in the text string to + * be searched. + * Subclasses' <tt>handleNext</tt> and <tt>handlePrev</tt> + * methods should call this when they find a match in the target text. + * @param length length of the matched text. + * @see #handleNext + * @see #handlePrev + * @stable ICU 2.0 + */ + virtual void setMatchLength(int32_t length); + + /** + * Sets the offset of the currently matched string in the text string to + * be searched. + * Subclasses' <tt>handleNext</tt> and <tt>handlePrev</tt> + * methods should call this when they find a match in the target text. + * @param position start offset of the matched text. + * @see #handleNext + * @see #handlePrev + * @stable ICU 2.0 + */ + virtual void setMatchStart(int32_t position); + + /** + * sets match not found + * @stable ICU 2.0 + */ + void setMatchNotFound(); +}; + +inline UBool SearchIterator::operator!=(const SearchIterator &that) const +{ + return !operator==(that); +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/simpletz.h b/Build/source/libs/icu-xetex/i18n/unicode/simpletz.h new file mode 100644 index 00000000000..08fdd208761 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/simpletz.h @@ -0,0 +1,927 @@ +/* + ******************************************************************************** + * Copyright (C) 1997-2007, International Business Machines * + * Corporation and others. All Rights Reserved. * + ******************************************************************************** + * + * File SIMPLETZ.H + * + * Modification History: + * + * Date Name Description + * 04/21/97 aliu Overhauled header. + * 08/10/98 stephen JDK 1.2 sync + * Added setStartRule() / setEndRule() overloads + * Added hasSameRules() + * 09/02/98 stephen Added getOffset(monthLen) + * Changed getOffset() to take UErrorCode + * 07/09/99 stephen Removed millisPerHour (unused, for HP compiler) + * 12/02/99 aliu Added TimeMode and constructor and setStart/EndRule + * methods that take TimeMode. Added to docs. + ******************************************************************************** + */ + +#ifndef SIMPLETZ_H +#define SIMPLETZ_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: SimpleTimeZone is a concrete subclass of TimeZone. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/basictz.h" + +U_NAMESPACE_BEGIN + +// forward declaration +class InitialTimeZoneRule; +class TimeZoneTransition; +class AnnualTimeZoneRule; + +/** + * <code>SimpleTimeZone</code> is a concrete subclass of <code>TimeZone</code> + * that represents a time zone for use with a Gregorian calendar. This + * class does not handle historical changes. + * <P> + * When specifying daylight-savings-time begin and end dates, use a negative value for + * <code>dayOfWeekInMonth</code> to indicate that <code>SimpleTimeZone</code> should + * count from the end of the month backwards. For example, in the U.S., Daylight Savings + * Time ends at the last (dayOfWeekInMonth = -1) Sunday in October, at 2 AM in standard + * time. + * + * @see Calendar + * @see GregorianCalendar + * @see TimeZone + * @author D. Goldsmith, Mark Davis, Chen-Lieh Huang, Alan Liu + */ +class U_I18N_API SimpleTimeZone: public BasicTimeZone { +public: + + /** + * TimeMode is used, together with a millisecond offset after + * midnight, to specify a rule transition time. Most rules + * transition at a local wall time, that is, according to the + * current time in effect, either standard, or DST. However, some + * rules transition at local standard time, and some at a specific + * UTC time. Although it might seem that all times could be + * converted to wall time, thus eliminating the need for this + * parameter, this is not the case. + * @stable ICU 2.0 + */ + enum TimeMode { + WALL_TIME = 0, + STANDARD_TIME, + UTC_TIME + }; + + /** + * Copy constructor + * @param source the object to be copied. + * @stable ICU 2.0 + */ + SimpleTimeZone(const SimpleTimeZone& source); + + /** + * Default assignment operator + * @param right the object to be copied. + * @stable ICU 2.0 + */ + SimpleTimeZone& operator=(const SimpleTimeZone& right); + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~SimpleTimeZone(); + + /** + * Returns true if the two TimeZone objects are equal; that is, they have + * the same ID, raw GMT offset, and DST rules. + * + * @param that The SimpleTimeZone object to be compared with. + * @return True if the given time zone is equal to this time zone; false + * otherwise. + * @stable ICU 2.0 + */ + virtual UBool operator==(const TimeZone& that) const; + + /** + * Constructs a SimpleTimeZone with the given raw GMT offset and time zone ID, + * and which doesn't observe daylight savings time. Normally you should use + * TimeZone::createInstance() to create a TimeZone instead of creating a + * SimpleTimeZone directly with this constructor. + * + * @param rawOffsetGMT The given base time zone offset to GMT. + * @param ID The timezone ID which is obtained from + * TimeZone.getAvailableIDs. + * @stable ICU 2.0 + */ + SimpleTimeZone(int32_t rawOffsetGMT, const UnicodeString& ID); + + /** + * Construct a SimpleTimeZone with the given raw GMT offset, time zone ID, + * and times to start and end daylight savings time. To create a TimeZone that + * doesn't observe daylight savings time, don't use this constructor; use + * SimpleTimeZone(rawOffset, ID) instead. Normally, you should use + * TimeZone.createInstance() to create a TimeZone instead of creating a + * SimpleTimeZone directly with this constructor. + * <P> + * Various types of daylight-savings time rules can be specfied by using different + * values for startDay and startDayOfWeek and endDay and endDayOfWeek. For a + * complete explanation of how these parameters work, see the documentation for + * setStartRule(). + * + * @param rawOffsetGMT The new SimpleTimeZone's raw GMT offset + * @param ID The new SimpleTimeZone's time zone ID. + * @param savingsStartMonth The daylight savings starting month. Month is + * 0-based. eg, 0 for January. + * @param savingsStartDayOfWeekInMonth The daylight savings starting + * day-of-week-in-month. See setStartRule() for a + * complete explanation. + * @param savingsStartDayOfWeek The daylight savings starting day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsStartTime The daylight savings starting time, expressed as the + * number of milliseconds after midnight. + * @param savingsEndMonth The daylight savings ending month. Month is + * 0-based. eg, 0 for January. + * @param savingsEndDayOfWeekInMonth The daylight savings ending day-of-week-in-month. + * See setStartRule() for a complete explanation. + * @param savingsEndDayOfWeek The daylight savings ending day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsEndTime The daylight savings ending time, expressed as the + * number of milliseconds after midnight. + * @param status An UErrorCode to receive the status. + * @stable ICU 2.0 + */ + SimpleTimeZone(int32_t rawOffsetGMT, const UnicodeString& ID, + int8_t savingsStartMonth, int8_t savingsStartDayOfWeekInMonth, + int8_t savingsStartDayOfWeek, int32_t savingsStartTime, + int8_t savingsEndMonth, int8_t savingsEndDayOfWeekInMonth, + int8_t savingsEndDayOfWeek, int32_t savingsEndTime, + UErrorCode& status); + /** + * Construct a SimpleTimeZone with the given raw GMT offset, time zone ID, + * and times to start and end daylight savings time. To create a TimeZone that + * doesn't observe daylight savings time, don't use this constructor; use + * SimpleTimeZone(rawOffset, ID) instead. Normally, you should use + * TimeZone.createInstance() to create a TimeZone instead of creating a + * SimpleTimeZone directly with this constructor. + * <P> + * Various types of daylight-savings time rules can be specfied by using different + * values for startDay and startDayOfWeek and endDay and endDayOfWeek. For a + * complete explanation of how these parameters work, see the documentation for + * setStartRule(). + * + * @param rawOffsetGMT The new SimpleTimeZone's raw GMT offset + * @param ID The new SimpleTimeZone's time zone ID. + * @param savingsStartMonth The daylight savings starting month. Month is + * 0-based. eg, 0 for January. + * @param savingsStartDayOfWeekInMonth The daylight savings starting + * day-of-week-in-month. See setStartRule() for a + * complete explanation. + * @param savingsStartDayOfWeek The daylight savings starting day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsStartTime The daylight savings starting time, expressed as the + * number of milliseconds after midnight. + * @param savingsEndMonth The daylight savings ending month. Month is + * 0-based. eg, 0 for January. + * @param savingsEndDayOfWeekInMonth The daylight savings ending day-of-week-in-month. + * See setStartRule() for a complete explanation. + * @param savingsEndDayOfWeek The daylight savings ending day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsEndTime The daylight savings ending time, expressed as the + * number of milliseconds after midnight. + * @param savingsDST The number of milliseconds added to standard time + * to get DST time. Default is one hour. + * @param status An UErrorCode to receive the status. + * @stable ICU 2.0 + */ + SimpleTimeZone(int32_t rawOffsetGMT, const UnicodeString& ID, + int8_t savingsStartMonth, int8_t savingsStartDayOfWeekInMonth, + int8_t savingsStartDayOfWeek, int32_t savingsStartTime, + int8_t savingsEndMonth, int8_t savingsEndDayOfWeekInMonth, + int8_t savingsEndDayOfWeek, int32_t savingsEndTime, + int32_t savingsDST, UErrorCode& status); + + /** + * Construct a SimpleTimeZone with the given raw GMT offset, time zone ID, + * and times to start and end daylight savings time. To create a TimeZone that + * doesn't observe daylight savings time, don't use this constructor; use + * SimpleTimeZone(rawOffset, ID) instead. Normally, you should use + * TimeZone.createInstance() to create a TimeZone instead of creating a + * SimpleTimeZone directly with this constructor. + * <P> + * Various types of daylight-savings time rules can be specfied by using different + * values for startDay and startDayOfWeek and endDay and endDayOfWeek. For a + * complete explanation of how these parameters work, see the documentation for + * setStartRule(). + * + * @param rawOffsetGMT The new SimpleTimeZone's raw GMT offset + * @param ID The new SimpleTimeZone's time zone ID. + * @param savingsStartMonth The daylight savings starting month. Month is + * 0-based. eg, 0 for January. + * @param savingsStartDayOfWeekInMonth The daylight savings starting + * day-of-week-in-month. See setStartRule() for a + * complete explanation. + * @param savingsStartDayOfWeek The daylight savings starting day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsStartTime The daylight savings starting time, expressed as the + * number of milliseconds after midnight. + * @param savingsStartTimeMode Whether the start time is local wall time, local + * standard time, or UTC time. Default is local wall time. + * @param savingsEndMonth The daylight savings ending month. Month is + * 0-based. eg, 0 for January. + * @param savingsEndDayOfWeekInMonth The daylight savings ending day-of-week-in-month. + * See setStartRule() for a complete explanation. + * @param savingsEndDayOfWeek The daylight savings ending day-of-week. + * See setStartRule() for a complete explanation. + * @param savingsEndTime The daylight savings ending time, expressed as the + * number of milliseconds after midnight. + * @param savingsEndTimeMode Whether the end time is local wall time, local + * standard time, or UTC time. Default is local wall time. + * @param savingsDST The number of milliseconds added to standard time + * to get DST time. Default is one hour. + * @param status An UErrorCode to receive the status. + * @stable ICU 2.0 + */ + SimpleTimeZone(int32_t rawOffsetGMT, const UnicodeString& ID, + int8_t savingsStartMonth, int8_t savingsStartDayOfWeekInMonth, + int8_t savingsStartDayOfWeek, int32_t savingsStartTime, + TimeMode savingsStartTimeMode, + int8_t savingsEndMonth, int8_t savingsEndDayOfWeekInMonth, + int8_t savingsEndDayOfWeek, int32_t savingsEndTime, TimeMode savingsEndTimeMode, + int32_t savingsDST, UErrorCode& status); + + /** + * Sets the daylight savings starting year, that is, the year this time zone began + * observing its specified daylight savings time rules. The time zone is considered + * not to observe daylight savings time prior to that year; SimpleTimeZone doesn't + * support historical daylight-savings-time rules. + * @param year the daylight savings starting year. + * @stable ICU 2.0 + */ + void setStartYear(int32_t year); + + /** + * Sets the daylight savings starting rule. For example, in the U.S., Daylight Savings + * Time starts at the first Sunday in April, at 2 AM in standard time. + * Therefore, you can set the start rule by calling: + * setStartRule(TimeFields.APRIL, 1, TimeFields.SUNDAY, 2*60*60*1000); + * The dayOfWeekInMonth and dayOfWeek parameters together specify how to calculate + * the exact starting date. Their exact meaning depend on their respective signs, + * allowing various types of rules to be constructed, as follows: + * <ul> + * <li>If both dayOfWeekInMonth and dayOfWeek are positive, they specify the + * day of week in the month (e.g., (2, WEDNESDAY) is the second Wednesday + * of the month).</li> + * <li>If dayOfWeek is positive and dayOfWeekInMonth is negative, they specify + * the day of week in the month counting backward from the end of the month. + * (e.g., (-1, MONDAY) is the last Monday in the month)</li> + * <li>If dayOfWeek is zero and dayOfWeekInMonth is positive, dayOfWeekInMonth + * specifies the day of the month, regardless of what day of the week it is. + * (e.g., (10, 0) is the tenth day of the month)</li> + * <li>If dayOfWeek is zero and dayOfWeekInMonth is negative, dayOfWeekInMonth + * specifies the day of the month counting backward from the end of the + * month, regardless of what day of the week it is (e.g., (-2, 0) is the + * next-to-last day of the month).</li> + * <li>If dayOfWeek is negative and dayOfWeekInMonth is positive, they specify the + * first specified day of the week on or after the specfied day of the month. + * (e.g., (15, -SUNDAY) is the first Sunday after the 15th of the month + * [or the 15th itself if the 15th is a Sunday].)</li> + * <li>If dayOfWeek and DayOfWeekInMonth are both negative, they specify the + * last specified day of the week on or before the specified day of the month. + * (e.g., (-20, -TUESDAY) is the last Tuesday before the 20th of the month + * [or the 20th itself if the 20th is a Tuesday].)</li> + * </ul> + * @param month the daylight savings starting month. Month is 0-based. + * eg, 0 for January. + * @param dayOfWeekInMonth the daylight savings starting + * day-of-week-in-month. Please see the member description for an example. + * @param dayOfWeek the daylight savings starting day-of-week. Please see + * the member description for an example. + * @param time the daylight savings starting time. Please see the member + * description for an example. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfWeekInMonth, int32_t dayOfWeek, + int32_t time, UErrorCode& status); + /** + * Sets the daylight savings starting rule. For example, in the U.S., Daylight Savings + * Time starts at the first Sunday in April, at 2 AM in standard time. + * Therefore, you can set the start rule by calling: + * setStartRule(TimeFields.APRIL, 1, TimeFields.SUNDAY, 2*60*60*1000); + * The dayOfWeekInMonth and dayOfWeek parameters together specify how to calculate + * the exact starting date. Their exact meaning depend on their respective signs, + * allowing various types of rules to be constructed, as follows: + * <ul> + * <li>If both dayOfWeekInMonth and dayOfWeek are positive, they specify the + * day of week in the month (e.g., (2, WEDNESDAY) is the second Wednesday + * of the month).</li> + * <li>If dayOfWeek is positive and dayOfWeekInMonth is negative, they specify + * the day of week in the month counting backward from the end of the month. + * (e.g., (-1, MONDAY) is the last Monday in the month)</li> + * <li>If dayOfWeek is zero and dayOfWeekInMonth is positive, dayOfWeekInMonth + * specifies the day of the month, regardless of what day of the week it is. + * (e.g., (10, 0) is the tenth day of the month)</li> + * <li>If dayOfWeek is zero and dayOfWeekInMonth is negative, dayOfWeekInMonth + * specifies the day of the month counting backward from the end of the + * month, regardless of what day of the week it is (e.g., (-2, 0) is the + * next-to-last day of the month).</li> + * <li>If dayOfWeek is negative and dayOfWeekInMonth is positive, they specify the + * first specified day of the week on or after the specfied day of the month. + * (e.g., (15, -SUNDAY) is the first Sunday after the 15th of the month + * [or the 15th itself if the 15th is a Sunday].)</li> + * <li>If dayOfWeek and DayOfWeekInMonth are both negative, they specify the + * last specified day of the week on or before the specified day of the month. + * (e.g., (-20, -TUESDAY) is the last Tuesday before the 20th of the month + * [or the 20th itself if the 20th is a Tuesday].)</li> + * </ul> + * @param month the daylight savings starting month. Month is 0-based. + * eg, 0 for January. + * @param dayOfWeekInMonth the daylight savings starting + * day-of-week-in-month. Please see the member description for an example. + * @param dayOfWeek the daylight savings starting day-of-week. Please see + * the member description for an example. + * @param time the daylight savings starting time. Please see the member + * description for an example. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfWeekInMonth, int32_t dayOfWeek, + int32_t time, TimeMode mode, UErrorCode& status); + + /** + * Sets the DST start rule to a fixed date within a month. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth The date in that month (1-based). + * @param time The time of that day (number of millis after midnight) + * when DST takes effect in local wall time, which is + * standard time in this case. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfMonth, int32_t time, + UErrorCode& status); + /** + * Sets the DST start rule to a fixed date within a month. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth The date in that month (1-based). + * @param time The time of that day (number of millis after midnight) + * when DST takes effect in local wall time, which is + * standard time in this case. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfMonth, int32_t time, + TimeMode mode, UErrorCode& status); + + /** + * Sets the DST start rule to a weekday before or after a give date within + * a month, e.g., the first Monday on or after the 8th. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth A date within that month (1-based). + * @param dayOfWeek The day of the week on which this rule occurs. + * @param time The time of that day (number of millis after midnight) + * when DST takes effect in local wall time, which is + * standard time in this case. + * @param after If true, this rule selects the first dayOfWeek on + * or after dayOfMonth. If false, this rule selects + * the last dayOfWeek on or before dayOfMonth. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + int32_t time, UBool after, UErrorCode& status); + /** + * Sets the DST start rule to a weekday before or after a give date within + * a month, e.g., the first Monday on or after the 8th. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth A date within that month (1-based). + * @param dayOfWeek The day of the week on which this rule occurs. + * @param time The time of that day (number of millis after midnight) + * when DST takes effect in local wall time, which is + * standard time in this case. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param after If true, this rule selects the first dayOfWeek on + * or after dayOfMonth. If false, this rule selects + * the last dayOfWeek on or before dayOfMonth. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setStartRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + int32_t time, TimeMode mode, UBool after, UErrorCode& status); + + /** + * Sets the daylight savings ending rule. For example, in the U.S., Daylight + * Savings Time ends at the last (-1) Sunday in October, at 2 AM in standard time. + * Therefore, you can set the end rule by calling: + * <pre> + * . setEndRule(TimeFields.OCTOBER, -1, TimeFields.SUNDAY, 2*60*60*1000); + * </pre> + * Various other types of rules can be specified by manipulating the dayOfWeek + * and dayOfWeekInMonth parameters. For complete details, see the documentation + * for setStartRule(). + * + * @param month the daylight savings ending month. Month is 0-based. + * eg, 0 for January. + * @param dayOfWeekInMonth the daylight savings ending + * day-of-week-in-month. See setStartRule() for a complete explanation. + * @param dayOfWeek the daylight savings ending day-of-week. See setStartRule() + * for a complete explanation. + * @param time the daylight savings ending time. Please see the member + * description for an example. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfWeekInMonth, int32_t dayOfWeek, + int32_t time, UErrorCode& status); + + /** + * Sets the daylight savings ending rule. For example, in the U.S., Daylight + * Savings Time ends at the last (-1) Sunday in October, at 2 AM in standard time. + * Therefore, you can set the end rule by calling: + * <pre> + * . setEndRule(TimeFields.OCTOBER, -1, TimeFields.SUNDAY, 2*60*60*1000); + * </pre> + * Various other types of rules can be specified by manipulating the dayOfWeek + * and dayOfWeekInMonth parameters. For complete details, see the documentation + * for setStartRule(). + * + * @param month the daylight savings ending month. Month is 0-based. + * eg, 0 for January. + * @param dayOfWeekInMonth the daylight savings ending + * day-of-week-in-month. See setStartRule() for a complete explanation. + * @param dayOfWeek the daylight savings ending day-of-week. See setStartRule() + * for a complete explanation. + * @param time the daylight savings ending time. Please see the member + * description for an example. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfWeekInMonth, int32_t dayOfWeek, + int32_t time, TimeMode mode, UErrorCode& status); + + /** + * Sets the DST end rule to a fixed date within a month. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth The date in that month (1-based). + * @param time The time of that day (number of millis after midnight) + * when DST ends in local wall time, which is daylight + * time in this case. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfMonth, int32_t time, UErrorCode& status); + + /** + * Sets the DST end rule to a fixed date within a month. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth The date in that month (1-based). + * @param time The time of that day (number of millis after midnight) + * when DST ends in local wall time, which is daylight + * time in this case. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfMonth, int32_t time, + TimeMode mode, UErrorCode& status); + + /** + * Sets the DST end rule to a weekday before or after a give date within + * a month, e.g., the first Monday on or after the 8th. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth A date within that month (1-based). + * @param dayOfWeek The day of the week on which this rule occurs. + * @param time The time of that day (number of millis after midnight) + * when DST ends in local wall time, which is daylight + * time in this case. + * @param after If true, this rule selects the first dayOfWeek on + * or after dayOfMonth. If false, this rule selects + * the last dayOfWeek on or before dayOfMonth. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + int32_t time, UBool after, UErrorCode& status); + + /** + * Sets the DST end rule to a weekday before or after a give date within + * a month, e.g., the first Monday on or after the 8th. + * + * @param month The month in which this rule occurs (0-based). + * @param dayOfMonth A date within that month (1-based). + * @param dayOfWeek The day of the week on which this rule occurs. + * @param time The time of that day (number of millis after midnight) + * when DST ends in local wall time, which is daylight + * time in this case. + * @param mode whether the time is local wall time, local standard time, + * or UTC time. Default is local wall time. + * @param after If true, this rule selects the first dayOfWeek on + * or after dayOfMonth. If false, this rule selects + * the last dayOfWeek on or before dayOfMonth. + * @param status An UErrorCode + * @stable ICU 2.0 + */ + void setEndRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + int32_t time, TimeMode mode, UBool after, UErrorCode& status); + + /** + * Returns the TimeZone's adjusted GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time in this time zone, taking daylight savings time into + * account) as of a particular reference date. The reference date is used to determine + * whether daylight savings time is in effect and needs to be figured into the offset + * that is returned (in other words, what is the adjusted GMT offset in this time zone + * at this particular date and time?). For the time zones produced by createTimeZone(), + * the reference data is specified according to the Gregorian calendar, and the date + * and time fields are in GMT, NOT local time. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, UTT (NOT local time). + * @param status An UErrorCode to receive the status. + * @return The offset in milliseconds to add to GMT to get local time. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, UErrorCode& status) const; + + /** + * Gets the time zone offset, for current date, modified in case of + * daylight savings. This is the offset to add *to* UTC to get local time. + * @param era the era of the given date. + * @param year the year in the given date. + * @param month the month in the given date. + * Month is 0-based. e.g., 0 for January. + * @param day the day-in-month of the given date. + * @param dayOfWeek the day-of-week of the given date. + * @param milliseconds the millis in day in <em>standard</em> local time. + * @param monthLength the length of the given month in days. + * @param status An UErrorCode to receive the status. + * @return the offset to add *to* GMT to get local time. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t milliseconds, + int32_t monthLength, UErrorCode& status) const; + /** + * Gets the time zone offset, for current date, modified in case of + * daylight savings. This is the offset to add *to* UTC to get local time. + * @param era the era of the given date. + * @param year the year in the given date. + * @param month the month in the given date. + * Month is 0-based. e.g., 0 for January. + * @param day the day-in-month of the given date. + * @param dayOfWeek the day-of-week of the given date. + * @param milliseconds the millis in day in <em>standard</em> local time. + * @param monthLength the length of the given month in days. + * @param prevMonthLength length of the previous month in days. + * @param status An UErrorCode to receive the status. + * @return the offset to add *to* GMT to get local time. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t milliseconds, + int32_t monthLength, int32_t prevMonthLength, + UErrorCode& status) const; + + /** + * Redeclared TimeZone method. This implementation simply calls + * the base class method, which otherwise would be hidden. + * @stable ICU 2.8 + */ + virtual void getOffset(UDate date, UBool local, int32_t& rawOffset, + int32_t& dstOffset, UErrorCode& ec) const; + + /** + * Get time zone offsets from local wall time. + * @internal + */ + virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt, int32_t duplicatedTimeOpt, + int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) /*const*/; + + /** + * Returns the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @return The TimeZone's raw GMT offset. + * @stable ICU 2.0 + */ + virtual int32_t getRawOffset(void) const; + + /** + * Sets the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @param offsetMillis The new raw GMT offset for this time zone. + * @stable ICU 2.0 + */ + virtual void setRawOffset(int32_t offsetMillis); + + /** + * Sets the amount of time in ms that the clock is advanced during DST. + * @param millisSavedDuringDST the number of milliseconds the time is + * advanced with respect to standard time when the daylight savings rules + * are in effect. A positive number, typically one hour (3600000). + * @param status An UErrorCode to receive the status. + * @stable ICU 2.0 + */ + void setDSTSavings(int32_t millisSavedDuringDST, UErrorCode& status); + + /** + * Returns the amount of time in ms that the clock is advanced during DST. + * @return the number of milliseconds the time is + * advanced with respect to standard time when the daylight savings rules + * are in effect. A positive number, typically one hour (3600000). + * @stable ICU 2.0 + */ + virtual int32_t getDSTSavings(void) const; + + /** + * Queries if this TimeZone uses Daylight Savings Time. + * + * @return True if this TimeZone uses Daylight Savings Time; false otherwise. + * @stable ICU 2.0 + */ + virtual UBool useDaylightTime(void) const; + + /** + * Returns true if the given date is within the period when daylight savings time + * is in effect; false otherwise. If the TimeZone doesn't observe daylight savings + * time, this functions always returns false. + * This method is wasteful since it creates a new GregorianCalendar and + * deletes it each time it is called. This is a deprecated method + * and provided only for Java compatibility. + * + * @param date The date to test. + * @param status An UErrorCode to receive the status. + * @return true if the given date is in Daylight Savings Time; + * false otherwise. + * @deprecated ICU 2.4. Use Calendar::inDaylightTime() instead. + */ + virtual UBool inDaylightTime(UDate date, UErrorCode& status) const; + + /** + * Return true if this zone has the same rules and offset as another zone. + * @param other the TimeZone object to be compared with + * @return true if the given zone has the same rules and offset as this one + * @stable ICU 2.0 + */ + UBool hasSameRules(const TimeZone& other) const; + + /** + * Clones TimeZone objects polymorphically. Clients are responsible for deleting + * the TimeZone object cloned. + * + * @return A new copy of this TimeZone object. + * @stable ICU 2.0 + */ + virtual TimeZone* clone(void) const; + + /** + * Gets the first time zone transition after the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the first transition after the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Gets the most recent time zone transition before the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the most recent transition before the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Returns the number of <code>TimeZoneRule</code>s which represents time transitions, + * for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except + * <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value. + * @param status Receives error status code. + * @return The number of <code>TimeZoneRule</code>s representing time transitions. + * @draft ICU 3.8 + */ + virtual int32_t countTransitionRules(UErrorCode& status) /*const*/; + + /** + * Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code> + * which represent time transitions for this time zone. On successful return, + * the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and + * the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code> + * instances up to the size specified by trscount. The results are referencing the + * rule instance held by this time zone instance. Therefore, after this time zone + * is destructed, they are no longer available. + * @param initial Receives the initial timezone rule + * @param trsrules Receives the timezone transition rules + * @param trscount On input, specify the size of the array 'transitions' receiving + * the timezone transition rules. On output, actual number of + * rules filled in the array will be set. + * @param status Receives error status code. + * @draft ICU 3.8 + */ + virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial, + const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) /*const*/; + + +public: + + /** + * Override TimeZone Returns a unique class ID POLYMORPHICALLY. Pure virtual + * override. This method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() methods call + * this method. + * + * @return The class ID for this object. All objects of a given class have the + * same class ID. Objects of other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Return the class ID for this class. This is useful only for comparing to a return + * value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +private: + /** + * Constants specifying values of startMode and endMode. + */ + enum EMode + { + DOM_MODE = 1, + DOW_IN_MONTH_MODE, + DOW_GE_DOM_MODE, + DOW_LE_DOM_MODE + }; + + SimpleTimeZone(); // default constructor not implemented + + /** + * Internal construction method. + * @param rawOffsetGMT The new SimpleTimeZone's raw GMT offset + * @param startMonth the month DST starts + * @param startDay the day DST starts + * @param startDayOfWeek the DOW DST starts + * @param startTime the time DST starts + * @param startTimeMode Whether the start time is local wall time, local + * standard time, or UTC time. Default is local wall time. + * @param endMonth the month DST ends + * @param endDay the day DST ends + * @param endDayOfWeek the DOW DST ends + * @param endTime the time DST ends + * @param endTimeMode Whether the end time is local wall time, local + * standard time, or UTC time. Default is local wall time. + * @param savingsDST The number of milliseconds added to standard time + * to get DST time. Default is one hour. + * @param status An UErrorCode to receive the status. + */ + void construct(int32_t rawOffsetGMT, + int8_t startMonth, int8_t startDay, int8_t startDayOfWeek, + int32_t startTime, TimeMode startTimeMode, + int8_t endMonth, int8_t endDay, int8_t endDayOfWeek, + int32_t endTime, TimeMode endTimeMode, + int32_t dstSavings, UErrorCode& status); + + /** + * Compare a given date in the year to a rule. Return 1, 0, or -1, depending + * on whether the date is after, equal to, or before the rule date. The + * millis are compared directly against the ruleMillis, so any + * standard-daylight adjustments must be handled by the caller. + * + * @return 1 if the date is after the rule date, -1 if the date is before + * the rule date, or 0 if the date is equal to the rule date. + */ + static int32_t compareToRule(int8_t month, int8_t monthLen, int8_t prevMonthLen, + int8_t dayOfMonth, + int8_t dayOfWeek, int32_t millis, int32_t millisDelta, + EMode ruleMode, int8_t ruleMonth, int8_t ruleDayOfWeek, + int8_t ruleDay, int32_t ruleMillis); + + /** + * Given a set of encoded rules in startDay and startDayOfMonth, decode + * them and set the startMode appropriately. Do the same for endDay and + * endDayOfMonth. + * <P> + * Upon entry, the day of week variables may be zero or + * negative, in order to indicate special modes. The day of month + * variables may also be negative. + * <P> + * Upon exit, the mode variables will be + * set, and the day of week and day of month variables will be positive. + * <P> + * This method also recognizes a startDay or endDay of zero as indicating + * no DST. + */ + void decodeRules(UErrorCode& status); + void decodeStartRule(UErrorCode& status); + void decodeEndRule(UErrorCode& status); + + int8_t startMonth, startDay, startDayOfWeek; // the month, day, DOW, and time DST starts + int32_t startTime; + TimeMode startTimeMode, endTimeMode; // Mode for startTime, endTime; see TimeMode + int8_t endMonth, endDay, endDayOfWeek; // the month, day, DOW, and time DST ends + int32_t endTime; + int32_t startYear; // the year these DST rules took effect + int32_t rawOffset; // the TimeZone's raw GMT offset + UBool useDaylight; // flag indicating whether this TimeZone uses DST + static const int8_t STATICMONTHLENGTH[12]; // lengths of the months + EMode startMode, endMode; // flags indicating what kind of rules the DST rules are + + /** + * A positive value indicating the amount of time saved during DST in ms. + * Typically one hour; sometimes 30 minutes. + */ + int32_t dstSavings; + + /* Private for BasicTimeZone implementation */ + void initTransitionRules(UErrorCode& status); + void clearTransitionRules(void); + void deleteTransitionRules(void); + UBool transitionRulesInitialized; + InitialTimeZoneRule* initialRule; + TimeZoneTransition* firstTransition; + AnnualTimeZoneRule* stdRule; + AnnualTimeZoneRule* dstRule; +}; + +inline void SimpleTimeZone::setStartRule(int32_t month, int32_t dayOfWeekInMonth, + int32_t dayOfWeek, + int32_t time, UErrorCode& status) { + setStartRule(month, dayOfWeekInMonth, dayOfWeek, time, WALL_TIME, status); +} + +inline void SimpleTimeZone::setStartRule(int32_t month, int32_t dayOfMonth, + int32_t time, + UErrorCode& status) { + setStartRule(month, dayOfMonth, time, WALL_TIME, status); +} + +inline void SimpleTimeZone::setStartRule(int32_t month, int32_t dayOfMonth, + int32_t dayOfWeek, + int32_t time, UBool after, UErrorCode& status) { + setStartRule(month, dayOfMonth, dayOfWeek, time, WALL_TIME, after, status); +} + +inline void SimpleTimeZone::setEndRule(int32_t month, int32_t dayOfWeekInMonth, + int32_t dayOfWeek, + int32_t time, UErrorCode& status) { + setEndRule(month, dayOfWeekInMonth, dayOfWeek, time, WALL_TIME, status); +} + +inline void SimpleTimeZone::setEndRule(int32_t month, int32_t dayOfMonth, + int32_t time, UErrorCode& status) { + setEndRule(month, dayOfMonth, time, WALL_TIME, status); +} + +inline void SimpleTimeZone::setEndRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + int32_t time, UBool after, UErrorCode& status) { + setEndRule(month, dayOfMonth, dayOfWeek, time, WALL_TIME, after, status); +} + +inline void +SimpleTimeZone::getOffset(UDate date, UBool local, int32_t& rawOffsetRef, + int32_t& dstOffsetRef, UErrorCode& ec) const { + TimeZone::getOffset(date, local, rawOffsetRef, dstOffsetRef, ec); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _SIMPLETZ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/smpdtfmt.h b/Build/source/libs/icu-xetex/i18n/unicode/smpdtfmt.h new file mode 100644 index 00000000000..2fb7c8eb0cf --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/smpdtfmt.h @@ -0,0 +1,904 @@ +/* +* Copyright (C) 1997-2006, International Business Machines Corporation and others. All Rights Reserved. +******************************************************************************* +* +* File SMPDTFMT.H +* +* Modification History: +* +* Date Name Description +* 02/19/97 aliu Converted from java. +* 07/09/97 helena Make ParsePosition into a class. +* 07/21/98 stephen Added GMT_PLUS, GMT_MINUS +* Changed setTwoDigitStartDate to set2DigitYearStart +* Changed getTwoDigitStartDate to get2DigitYearStart +* Removed subParseLong +* Removed getZoneIndex (added in DateFormatSymbols) +* 06/14/99 stephen Removed fgTimeZoneDataSuffix +* 10/14/99 aliu Updated class doc to describe 2-digit year parsing +* {j28 4182066}. +******************************************************************************* +*/ + +#ifndef SMPDTFMT_H +#define SMPDTFMT_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Format and parse dates in a language-independent manner. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/datefmt.h" + +U_NAMESPACE_BEGIN + +class DateFormatSymbols; +class DateFormat; +class MessageFormat; + +/** + * + * SimpleDateFormat is a concrete class for formatting and parsing dates in a + * language-independent manner. It allows for formatting (millis -> text), + * parsing (text -> millis), and normalization. Formats/Parses a date or time, + * which is the standard milliseconds since 24:00 GMT, Jan 1, 1970. + * <P> + * Clients are encouraged to create a date-time formatter using DateFormat::getInstance(), + * getDateInstance(), getDateInstance(), or getDateTimeInstance() rather than + * explicitly constructing an instance of SimpleDateFormat. This way, the client + * is guaranteed to get an appropriate formatting pattern for whatever locale the + * program is running in. However, if the client needs something more unusual than + * the default patterns in the locales, he can construct a SimpleDateFormat directly + * and give it an appropriate pattern (or use one of the factory methods on DateFormat + * and modify the pattern after the fact with toPattern() and applyPattern(). + * <P> + * Date/Time format syntax: + * <P> + * The date/time format is specified by means of a string time pattern. In this + * pattern, all ASCII letters are reserved as pattern letters, which are defined + * as the following: + * <pre> + * \code + * Symbol Meaning Presentation Example + * ------ ------- ------------ ------- + * G era designator (Text) AD + * y year (Number) 1996 + * Y year (week of year) (Number) 1997 + * u extended year (Number) 4601 + * M month in year (Text & Number) July & 07 + * d day in month (Number) 10 + * h hour in am/pm (1~12) (Number) 12 + * H hour in day (0~23) (Number) 0 + * m minute in hour (Number) 30 + * s second in minute (Number) 55 + * S fractional second (Number) 978 + * E day of week (Text) Tuesday + * e day of week (local 1~7) (Number) 2 + * D day in year (Number) 189 + * F day of week in month (Number) 2 (2nd Wed in July) + * w week in year (Number) 27 + * W week in month (Number) 2 + * a am/pm marker (Text) PM + * k hour in day (1~24) (Number) 24 + * K hour in am/pm (0~11) (Number) 0 + * z time zone (Time) Pacific Standard Time + * Z time zone (RFC 822) (Number) -0800 + * v time zone (generic) (Text) Pacific Time + * g Julian day (Number) 2451334 + * A milliseconds in day (Number) 69540000 + * ' escape for text (Delimiter) 'Date=' + * '' single quote (Literal) 'o''clock' + * \endcode + * </pre> + * The count of pattern letters determine the format. + * <P> + * (Text): 4 or more, use full form, <4, use short or abbreviated form if it + * exists. (e.g., "EEEE" produces "Monday", "EEE" produces "Mon") + * <P> + * (Number): the minimum number of digits. Shorter numbers are zero-padded to + * this amount (e.g. if "m" produces "6", "mm" produces "06"). Year is handled + * specially; that is, if the count of 'y' is 2, the Year will be truncated to 2 digits. + * (e.g., if "yyyy" produces "1997", "yy" produces "97".) + * Unlike other fields, fractional seconds are padded on the right with zero. + * <P> + * (Text & Number): 3 or over, use text, otherwise use number. (e.g., "M" produces "1", + * "MM" produces "01", "MMM" produces "Jan", and "MMMM" produces "January".) + * <P> + * Any characters in the pattern that are not in the ranges of ['a'..'z'] and + * ['A'..'Z'] will be treated as quoted text. For instance, characters + * like ':', '.', ' ', '#' and '@' will appear in the resulting time text + * even they are not embraced within single quotes. + * <P> + * A pattern containing any invalid pattern letter will result in a failing + * UErrorCode result during formatting or parsing. + * <P> + * Examples using the US locale: + * <pre> + * \code + * Format Pattern Result + * -------------- ------- + * "yyyy.MM.dd G 'at' HH:mm:ss vvvv" ->> 1996.07.10 AD at 15:08:56 Pacific Time + * "EEE, MMM d, ''yy" ->> Wed, July 10, '96 + * "h:mm a" ->> 12:08 PM + * "hh 'o''clock' a, zzzz" ->> 12 o'clock PM, Pacific Daylight Time + * "K:mm a, vvv" ->> 0:00 PM, PT + * "yyyyy.MMMMM.dd GGG hh:mm aaa" ->> 1996.July.10 AD 12:08 PM + * \endcode + * </pre> + * Code Sample: + * <pre> + * \code + * UErrorCode success = U_ZERO_ERROR; + * SimpleTimeZone* pdt = new SimpleTimeZone(-8 * 60 * 60 * 1000, "PST"); + * pdt->setStartRule( Calendar::APRIL, 1, Calendar::SUNDAY, 2*60*60*1000); + * pdt->setEndRule( Calendar::OCTOBER, -1, Calendar::SUNDAY, 2*60*60*1000); + * + * // Format the current time. + * SimpleDateFormat* formatter + * = new SimpleDateFormat ("yyyy.MM.dd G 'at' hh:mm:ss a zzz", success ); + * GregorianCalendar cal(success); + * UDate currentTime_1 = cal.getTime(success); + * FieldPosition fp(0); + * UnicodeString dateString; + * formatter->format( currentTime_1, dateString, fp ); + * cout << "result: " << dateString << endl; + * + * // Parse the previous string back into a Date. + * ParsePosition pp(0); + * UDate currentTime_2 = formatter->parse(dateString, pp ); + * \endcode + * </pre> + * In the above example, the time value "currentTime_2" obtained from parsing + * will be equal to currentTime_1. However, they may not be equal if the am/pm + * marker 'a' is left out from the format pattern while the "hour in am/pm" + * pattern symbol is used. This information loss can happen when formatting the + * time in PM. + * + * <p> + * When parsing a date string using the abbreviated year pattern ("y" or "yy"), + * SimpleDateFormat must interpret the abbreviated year + * relative to some century. It does this by adjusting dates to be + * within 80 years before and 20 years after the time the SimpleDateFormat + * instance is created. For example, using a pattern of "MM/dd/yy" and a + * SimpleDateFormat instance created on Jan 1, 1997, the string + * "01/11/12" would be interpreted as Jan 11, 2012 while the string "05/04/64" + * would be interpreted as May 4, 1964. + * During parsing, only strings consisting of exactly two digits, as defined by + * <code>Unicode::isDigit()</code>, will be parsed into the default century. + * Any other numeric string, such as a one digit string, a three or more digit + * string, or a two digit string that isn't all digits (for example, "-1"), is + * interpreted literally. So "01/02/3" or "01/02/003" are parsed, using the + * same pattern, as Jan 2, 3 AD. Likewise, "01/02/-3" is parsed as Jan 2, 4 BC. + * + * <p> + * If the year pattern has more than two 'y' characters, the year is + * interpreted literally, regardless of the number of digits. So using the + * pattern "MM/dd/yyyy", "01/11/12" parses to Jan 11, 12 A.D. + * + * <p> + * When numeric fields abut one another directly, with no intervening delimiter + * characters, they constitute a run of abutting numeric fields. Such runs are + * parsed specially. For example, the format "HHmmss" parses the input text + * "123456" to 12:34:56, parses the input text "12345" to 1:23:45, and fails to + * parse "1234". In other words, the leftmost field of the run is flexible, + * while the others keep a fixed width. If the parse fails anywhere in the run, + * then the leftmost field is shortened by one character, and the entire run is + * parsed again. This is repeated until either the parse succeeds or the + * leftmost field is one character in length. If the parse still fails at that + * point, the parse of the run fails. + * + * <P> + * For time zones that have no names, SimpleDateFormat uses strings GMT+hours:minutes or + * GMT-hours:minutes. + * <P> + * The calendar defines what is the first day of the week, the first week of the + * year, whether hours are zero based or not (0 vs 12 or 24), and the timezone. + * There is one common number format to handle all the numbers; the digit count + * is handled programmatically according to the pattern. + * + * <p><em>User subclasses are not supported.</em> While clients may write + * subclasses, such code will not necessarily work and will not be + * guaranteed to work stably from release to release. + */ +class U_I18N_API SimpleDateFormat: public DateFormat { +public: + /** + * Construct a SimpleDateFormat using the default pattern for the default + * locale. + * <P> + * [Note:] Not all locales support SimpleDateFormat; for full generality, + * use the factory methods in the DateFormat class. + * @param status Output param set to success/failure code. + * @stable ICU 2.0 + */ + SimpleDateFormat(UErrorCode& status); + + /** + * Construct a SimpleDateFormat using the given pattern and the default locale. + * The locale is used to obtain the symbols used in formatting (e.g., the + * names of the months), but not to provide the pattern. + * <P> + * [Note:] Not all locales support SimpleDateFormat; for full generality, + * use the factory methods in the DateFormat class. + * @param pattern the pattern for the format. + * @param status Output param set to success/failure code. + * @stable ICU 2.0 + */ + SimpleDateFormat(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Construct a SimpleDateFormat using the given pattern and locale. + * The locale is used to obtain the symbols used in formatting (e.g., the + * names of the months), but not to provide the pattern. + * <P> + * [Note:] Not all locales support SimpleDateFormat; for full generality, + * use the factory methods in the DateFormat class. + * @param pattern the pattern for the format. + * @param locale the given locale. + * @param status Output param set to success/failure code. + * @stable ICU 2.0 + */ + SimpleDateFormat(const UnicodeString& pattern, + const Locale& locale, + UErrorCode& status); + + /** + * Construct a SimpleDateFormat using the given pattern and locale-specific + * symbol data. The formatter takes ownership of the DateFormatSymbols object; + * the caller is no longer responsible for deleting it. + * @param pattern the given pattern for the format. + * @param formatDataToAdopt the symbols to be adopted. + * @param status Output param set to success/faulure code. + * @stable ICU 2.0 + */ + SimpleDateFormat(const UnicodeString& pattern, + DateFormatSymbols* formatDataToAdopt, + UErrorCode& status); + + /** + * Construct a SimpleDateFormat using the given pattern and locale-specific + * symbol data. The DateFormatSymbols object is NOT adopted; the caller + * remains responsible for deleting it. + * @param pattern the given pattern for the format. + * @param formatData the formatting symbols to be use. + * @param status Output param set to success/faulure code. + * @stable ICU 2.0 + */ + SimpleDateFormat(const UnicodeString& pattern, + const DateFormatSymbols& formatData, + UErrorCode& status); + + /** + * Copy constructor. + * @stable ICU 2.0 + */ + SimpleDateFormat(const SimpleDateFormat&); + + /** + * Assignment operator. + * @stable ICU 2.0 + */ + SimpleDateFormat& operator=(const SimpleDateFormat&); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~SimpleDateFormat(); + + /** + * Clone this Format object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @stable ICU 2.0 + */ + virtual Format* clone(void) const; + + /** + * Return true if the given Format objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param other the object to be compared with. + * @return true if the given Format objects are semantically equal. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Format& other) const; + + /** + * Format a date or time, which is the standard millis since 24:00 GMT, Jan + * 1, 1970. Overrides DateFormat pure virtual method. + * <P> + * Example: using the US locale: "yyyy.MM.dd e 'at' HH:mm:ss zzz" ->> + * 1996.07.10 AD at 15:08:56 PDT + * + * @param cal Calendar set to the date and time to be formatted + * into a date/time string. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos The formatting position. On input: an alignment field, + * if desired. On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.1 + */ + virtual UnicodeString& format( Calendar& cal, + UnicodeString& appendTo, + FieldPosition& pos) const; + + /** + * Format a date or time, which is the standard millis since 24:00 GMT, Jan + * 1, 1970. Overrides DateFormat pure virtual method. + * <P> + * Example: using the US locale: "yyyy.MM.dd e 'at' HH:mm:ss zzz" ->> + * 1996.07.10 AD at 15:08:56 PDT + * + * @param obj A Formattable containing the date-time value to be formatted + * into a date-time string. If the type of the Formattable + * is a numeric type, it is treated as if it were an + * instance of Date. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param pos The formatting position. On input: an alignment field, + * if desired. On output: the offsets of the alignment field. + * @param status Output param set to success/faulure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + virtual UnicodeString& format( const Formattable& obj, + UnicodeString& appendTo, + FieldPosition& pos, + UErrorCode& status) const; + + /** + * Redeclared DateFormat method. + * @param date the Date value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param fieldPosition The formatting position. On input: an alignment field, + * if desired. On output: the offsets of the alignment field. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.1 + */ + UnicodeString& format(UDate date, + UnicodeString& appendTo, + FieldPosition& fieldPosition) const; + + /** + * Redeclared DateFormat method. + * @param obj Object to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param status Input/output success/failure code. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const; + + /** + * Redeclared DateFormat method. + * @param date Date value to be formatted. + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @return Reference to 'appendTo' parameter. + * @stable ICU 2.0 + */ + UnicodeString& format(UDate date, UnicodeString& appendTo) const; + + /** + * Parse a date/time string beginning at the given parse position. For + * example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date + * that is equivalent to Date(837039928046). + * <P> + * By default, parsing is lenient: If the input is not in the form used by + * this object's format method but can still be parsed as a date, then the + * parse succeeds. Clients may insist on strict adherence to the format by + * calling setLenient(false). + * + * @param text The date/time string to be parsed + * @param cal a Calendar set to the date and time to be formatted + * into a date/time string. + * @param pos On input, the position at which to start parsing; on + * output, the position at which parsing terminated, or the + * start position if the parse failed. + * @return A valid UDate if the input could be parsed. + * @stable ICU 2.1 + */ + virtual void parse( const UnicodeString& text, + Calendar& cal, + ParsePosition& pos) const; + + /** + * Parse a date/time string starting at the given parse position. For + * example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date + * that is equivalent to Date(837039928046). + * <P> + * By default, parsing is lenient: If the input is not in the form used by + * this object's format method but can still be parsed as a date, then the + * parse succeeds. Clients may insist on strict adherence to the format by + * calling setLenient(false). + * + * @see DateFormat::setLenient(boolean) + * + * @param text The date/time string to be parsed + * @param pos On input, the position at which to start parsing; on + * output, the position at which parsing terminated, or the + * start position if the parse failed. + * @return A valid UDate if the input could be parsed. + * @stable ICU 2.0 + */ + UDate parse( const UnicodeString& text, + ParsePosition& pos) const; + + + /** + * Parse a date/time string. For example, a time text "07/10/96 4:5 PM, PDT" + * will be parsed into a UDate that is equivalent to Date(837039928046). + * Parsing begins at the beginning of the string and proceeds as far as + * possible. Assuming no parse errors were encountered, this function + * doesn't return any information about how much of the string was consumed + * by the parsing. If you need that information, use the version of + * parse() that takes a ParsePosition. + * + * @param text The date/time string to be parsed + * @param status Filled in with U_ZERO_ERROR if the parse was successful, and with + * an error value if there was a parse error. + * @return A valid UDate if the input could be parsed. + * @stable ICU 2.0 + */ + virtual UDate parse( const UnicodeString& text, + UErrorCode& status) const; + + /** + * Set the start UDate used to interpret two-digit year strings. + * When dates are parsed having 2-digit year strings, they are placed within + * a assumed range of 100 years starting on the two digit start date. For + * example, the string "24-Jan-17" may be in the year 1817, 1917, 2017, or + * some other year. SimpleDateFormat chooses a year so that the resultant + * date is on or after the two digit start date and within 100 years of the + * two digit start date. + * <P> + * By default, the two digit start date is set to 80 years before the current + * time at which a SimpleDateFormat object is created. + * @param d start UDate used to interpret two-digit year strings. + * @param status Filled in with U_ZERO_ERROR if the parse was successful, and with + * an error value if there was a parse error. + * @stable ICU 2.0 + */ + virtual void set2DigitYearStart(UDate d, UErrorCode& status); + + /** + * Get the start UDate used to interpret two-digit year strings. + * When dates are parsed having 2-digit year strings, they are placed within + * a assumed range of 100 years starting on the two digit start date. For + * example, the string "24-Jan-17" may be in the year 1817, 1917, 2017, or + * some other year. SimpleDateFormat chooses a year so that the resultant + * date is on or after the two digit start date and within 100 years of the + * two digit start date. + * <P> + * By default, the two digit start date is set to 80 years before the current + * time at which a SimpleDateFormat object is created. + * @param status Filled in with U_ZERO_ERROR if the parse was successful, and with + * an error value if there was a parse error. + * @stable ICU 2.0 + */ + UDate get2DigitYearStart(UErrorCode& status) const; + + /** + * Return a pattern string describing this date format. + * @param result Output param to receive the pattern. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + virtual UnicodeString& toPattern(UnicodeString& result) const; + + /** + * Return a localized pattern string describing this date format. + * In most cases, this will return the same thing as toPattern(), + * but a locale can specify characters to use in pattern descriptions + * in place of the ones described in this class's class documentation. + * (Presumably, letters that would be more mnemonic in that locale's + * language.) This function would produce a pattern using those + * letters. + * + * @param result Receives the localized pattern. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + virtual UnicodeString& toLocalizedPattern(UnicodeString& result, + UErrorCode& status) const; + + /** + * Apply the given unlocalized pattern string to this date format. + * (i.e., after this call, this formatter will format dates according to + * the new pattern) + * + * @param pattern The pattern to be applied. + * @stable ICU 2.0 + */ + virtual void applyPattern(const UnicodeString& pattern); + + /** + * Apply the given localized pattern string to this date format. + * (see toLocalizedPattern() for more information on localized patterns.) + * + * @param pattern The localized pattern to be applied. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ + virtual void applyLocalizedPattern(const UnicodeString& pattern, + UErrorCode& status); + + /** + * Gets the date/time formatting symbols (this is an object carrying + * the various strings and other symbols used in formatting: e.g., month + * names and abbreviations, time zone names, AM/PM strings, etc.) + * @return a copy of the date-time formatting data associated + * with this date-time formatter. + * @stable ICU 2.0 + */ + virtual const DateFormatSymbols* getDateFormatSymbols(void) const; + + /** + * Set the date/time formatting symbols. The caller no longer owns the + * DateFormatSymbols object and should not delete it after making this call. + * @param newFormatSymbols the given date-time formatting symbols to copy. + * @stable ICU 2.0 + */ + virtual void adoptDateFormatSymbols(DateFormatSymbols* newFormatSymbols); + + /** + * Set the date/time formatting data. + * @param newFormatSymbols the given date-time formatting symbols to copy. + * @stable ICU 2.0 + */ + virtual void setDateFormatSymbols(const DateFormatSymbols& newFormatSymbols); + + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Set the calendar to be used by this date format. Initially, the default + * calendar for the specified or default locale is used. The caller should + * not delete the Calendar object after it is adopted by this call. + * Adopting a new calendar will change to the default symbols. + * + * @param calendarToAdopt Calendar object to be adopted. + * @stable ICU 2.0 + */ + virtual void adoptCalendar(Calendar* calendarToAdopt); + +private: + friend class DateFormat; + + void initializeDefaultCentury(void); + + SimpleDateFormat(); // default constructor not implemented + + /** + * Used by the DateFormat factory methods to construct a SimpleDateFormat. + * @param timeStyle the time style. + * @param dateStyle the date style. + * @param locale the given locale. + * @param status Output param set to success/failure code on + * exit. + */ + SimpleDateFormat(EStyle timeStyle, EStyle dateStyle, const Locale& locale, UErrorCode& status); + + /** + * Construct a SimpleDateFormat for the given locale. If no resource data + * is available, create an object of last resort, using hard-coded strings. + * This is an internal method, called by DateFormat. It should never fail. + * @param locale the given locale. + * @param status Output param set to success/failure code on + * exit. + */ + SimpleDateFormat(const Locale& locale, UErrorCode& status); // Use default pattern + + /** + * Called by format() to format a single field. + * + * @param appendTo Output parameter to receive result. + * Result is appended to existing contents. + * @param ch The format character we encountered in the pattern. + * @param count Number of characters in the current pattern symbol (e.g., + * "yyyy" in the pattern would result in a call to this function + * with ch equal to 'y' and count equal to 4) + * @param pos The FieldPosition being filled in by the format() call. If + * this function is formatting the field specfied by pos, it + * will fill in pos with the beginning and ending offsets of the + * field. + * @param status Receives a status code, which will be U_ZERO_ERROR if the operation + * succeeds. + */ + void subFormat( UnicodeString &appendTo, + UChar ch, + int32_t count, + FieldPosition& pos, + Calendar& cal, + UErrorCode& status) const; // in case of illegal argument + + /** + * Used by subFormat() to format a numeric value. + * Appends to toAppendTo a string representation of "value" + * having a number of digits between "minDigits" and + * "maxDigits". Uses the DateFormat's NumberFormat. + * + * @param appendTo Output parameter to receive result. + * Formatted number is appended to existing contents. + * @param value Value to format. + * @param minDigits Minimum number of digits the result should have + * @param maxDigits Maximum number of digits the result should have + */ + void zeroPaddingNumber( UnicodeString &appendTo, + int32_t value, + int32_t minDigits, + int32_t maxDigits) const; + + /** + * Return true if the given format character, occuring count + * times, represents a numeric field. + */ + static UBool isNumeric(UChar formatChar, int32_t count); + + /** + * initializes fCalendar from parameters. Returns fCalendar as a convenience. + * @param adoptZone Zone to be adopted, or NULL for TimeZone::createDefault(). + * @param locale Locale of the calendar + * @param status Error code + * @return the newly constructed fCalendar + */ + Calendar *initializeCalendar(TimeZone* adoptZone, const Locale& locale, UErrorCode& status); + + /** + * initializes fSymbols from parameters. + * @param locale Locale of the symbols + * @param calendar Alias to Calendar that will be used. + * @param status Error code + */ + void initializeSymbols(const Locale& locale, Calendar* calendar, UErrorCode& status); + + /** + * Called by several of the constructors to load pattern data and formatting symbols + * out of a resource bundle and initialize the locale based on it. + * @param timeStyle The time style, as passed to DateFormat::createDateInstance(). + * @param dateStyle The date style, as passed to DateFormat::createTimeInstance(). + * @param locale The locale to load the patterns from. + * @param status Filled in with an error code if loading the data from the + * resources fails. + */ + void construct(EStyle timeStyle, EStyle dateStyle, const Locale& locale, UErrorCode& status); + + /** + * Called by construct() and the various constructors to set up the SimpleDateFormat's + * Calendar and NumberFormat objects. + * @param locale The locale for which we want a Calendar and a NumberFormat. + * @param statuc Filled in with an error code if creating either subobject fails. + */ + void initialize(const Locale& locale, UErrorCode& status); + + /** + * Private code-size reduction function used by subParse. + * @param text the time text being parsed. + * @param start where to start parsing. + * @param field the date field being parsed. + * @param stringArray the string array to parsed. + * @param stringArrayCount the size of the array. + * @param cal a Calendar set to the date and time to be formatted + * into a date/time string. + * @return the new start position if matching succeeded; a negative number + * indicating matching failure, otherwise. + */ + int32_t matchString(const UnicodeString& text, int32_t start, UCalendarDateFields field, + const UnicodeString* stringArray, int32_t stringArrayCount, Calendar& cal) const; + + /** + * Private code-size reduction function used by subParse. + * @param text the time text being parsed. + * @param start where to start parsing. + * @param field the date field being parsed. + * @param stringArray the string array to parsed. + * @param stringArrayCount the size of the array. + * @param cal a Calendar set to the date and time to be formatted + * into a date/time string. + * @return the new start position if matching succeeded; a negative number + * indicating matching failure, otherwise. + */ + int32_t matchQuarterString(const UnicodeString& text, int32_t start, UCalendarDateFields field, + const UnicodeString* stringArray, int32_t stringArrayCount, Calendar& cal) const; + + /** + * Private member function that converts the parsed date strings into + * timeFields. Returns -start (for ParsePosition) if failed. + * @param text the time text to be parsed. + * @param start where to start parsing. + * @param ch the pattern character for the date field text to be parsed. + * @param count the count of a pattern character. + * @param obeyCount if true then the count is strictly obeyed. + * @param ambiguousYear If true then the two-digit year == the default start year. + * @param cal a Calendar set to the date and time to be formatted + * into a date/time string. + * @return the new start position if matching succeeded; a negative number + * indicating matching failure, otherwise. + */ + int32_t subParse(const UnicodeString& text, int32_t& start, UChar ch, int32_t count, + UBool obeyCount, UBool allowNegative, UBool ambiguousYear[], Calendar& cal) const; + + void parseInt(const UnicodeString& text, + Formattable& number, + ParsePosition& pos, + UBool allowNegative) const; + + void parseInt(const UnicodeString& text, + Formattable& number, + int32_t maxDigits, + ParsePosition& pos, + UBool allowNegative) const; + + /** + * Translate a pattern, mapping each character in the from string to the + * corresponding character in the to string. Return an error if the original + * pattern contains an unmapped character, or if a quote is unmatched. + * Quoted (single quotes only) material is not translated. + * @param originalPattern the original pattern. + * @param translatedPattern Output param to receive the translited pattern. + * @param from the characters to be translited from. + * @param to the characters to be translited to. + * @param status Receives a status code, which will be U_ZERO_ERROR + * if the operation succeeds. + */ + static void translatePattern(const UnicodeString& originalPattern, + UnicodeString& translatedPattern, + const UnicodeString& from, + const UnicodeString& to, + UErrorCode& status); + + /** + * Sets the starting date of the 100-year window that dates with 2-digit years + * are considered to fall within. + * @param startDate the start date + * @param status Receives a status code, which will be U_ZERO_ERROR + * if the operation succeeds. + */ + void parseAmbiguousDatesAsAfter(UDate startDate, UErrorCode& status); + + /** + * Private methods for formatting/parsing GMT string + */ + void appendGMT(UnicodeString &appendTo, Calendar& cal, UErrorCode& status) const; + void formatGMTDefault(UnicodeString &appendTo, int32_t offset) const; + int32_t parseGMT(const UnicodeString &text, ParsePosition &pos) const; + int32_t parseGMTDefault(const UnicodeString &text, ParsePosition &pos) const; + UBool isDefaultGMTFormat() const; + + void formatRFC822TZ(UnicodeString &appendTo, int32_t offset) const; + + /** + * Initialize MessageFormat instances used for GMT formatting/parsing + */ + void initGMTFormatters(UErrorCode &status); + + /** + * Used to map pattern characters to Calendar field identifiers. + */ + static const UCalendarDateFields fgPatternIndexToCalendarField[]; + + /** + * Map index into pattern character string to DateFormat field number + */ + static const UDateFormatField fgPatternIndexToDateFormatField[]; + + /** + * The formatting pattern for this formatter. + */ + UnicodeString fPattern; + + /** + * The original locale used (for reloading symbols) + */ + Locale fLocale; + + /** + * A pointer to an object containing the strings to use in formatting (e.g., + * month and day names, AM and PM strings, time zone names, etc.) + */ + DateFormatSymbols* fSymbols; // Owned + + /** + * If dates have ambiguous years, we map them into the century starting + * at defaultCenturyStart, which may be any date. If defaultCenturyStart is + * set to SYSTEM_DEFAULT_CENTURY, which it is by default, then the system + * values are used. The instance values defaultCenturyStart and + * defaultCenturyStartYear are only used if explicitly set by the user + * through the API method parseAmbiguousDatesAsAfter(). + */ + UDate fDefaultCenturyStart; + + /** + * See documentation for defaultCenturyStart. + */ + /*transient*/ int32_t fDefaultCenturyStartYear; + + enum ParsedTZType { + TZTYPE_UNK, + TZTYPE_STD, + TZTYPE_DST + }; + + ParsedTZType tztype; // here to avoid api change + + /* + * MessageFormat instances used for localized GMT format + */ + MessageFormat **fGMTFormatters; + + UBool fHaveDefaultCentury; +}; + +inline UDate +SimpleDateFormat::get2DigitYearStart(UErrorCode& /*status*/) const +{ + return fDefaultCenturyStart; +} + +inline UnicodeString& +SimpleDateFormat::format(const Formattable& obj, + UnicodeString& appendTo, + UErrorCode& status) const { + // Don't use Format:: - use immediate base class only, + // in case immediate base modifies behavior later. + return DateFormat::format(obj, appendTo, status); +} + +inline UnicodeString& +SimpleDateFormat::format(UDate date, + UnicodeString& appendTo, + FieldPosition& fieldPosition) const { + // Don't use Format:: - use immediate base class only, + // in case immediate base modifies behavior later. + return DateFormat::format(date, appendTo, fieldPosition); +} + +inline UnicodeString& +SimpleDateFormat::format(UDate date, UnicodeString& appendTo) const { + return DateFormat::format(date, appendTo); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // _SMPDTFMT +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/sortkey.h b/Build/source/libs/icu-xetex/i18n/unicode/sortkey.h new file mode 100644 index 00000000000..ef202dd9ba4 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/sortkey.h @@ -0,0 +1,324 @@ +/* + ***************************************************************************** + * Copyright (C) 1996-2006, International Business Machines Corporation and others. + * All Rights Reserved. + ***************************************************************************** + * + * File sortkey.h + * + * Created by: Helena Shih + * + * Modification History: + * + * Date Name Description + * + * 6/20/97 helena Java class name change. + * 8/18/97 helena Added internal API documentation. + * 6/26/98 erm Changed to use byte arrays and memcmp. + ***************************************************************************** + */ + +#ifndef SORTKEY_H +#define SORTKEY_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Keys for comparing strings multiple times. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/coll.h" + +U_NAMESPACE_BEGIN + +/* forward declaration */ +class RuleBasedCollator; + +/** + * + * Collation keys are generated by the Collator class. Use the CollationKey objects + * instead of Collator to compare strings multiple times. A CollationKey + * preprocesses the comparison information from the Collator object to + * make the comparison faster. If you are not going to comparing strings + * multiple times, then using the Collator object is generally faster, + * since it only processes as much of the string as needed to make a + * comparison. + * <p> For example (with strength == tertiary) + * <p>When comparing "Abernathy" to "Baggins-Smythworthy", Collator + * only needs to process a couple of characters, while a comparison + * with CollationKeys will process all of the characters. On the other hand, + * if you are doing a sort of a number of fields, it is much faster to use + * CollationKeys, since you will be comparing strings multiple times. + * <p>Typical use of CollationKeys are in databases, where you store a CollationKey + * in a hidden field, and use it for sorting or indexing. + * + * <p>Example of use: + * <pre> + * \code + * UErrorCode success = U_ZERO_ERROR; + * Collator* myCollator = Collator::createInstance(success); + * CollationKey* keys = new CollationKey [3]; + * myCollator->getCollationKey("Tom", keys[0], success ); + * myCollator->getCollationKey("Dick", keys[1], success ); + * myCollator->getCollationKey("Harry", keys[2], success ); + * + * // Inside body of sort routine, compare keys this way: + * CollationKey tmp; + * if(keys[0].compareTo( keys[1] ) > 0 ) { + * tmp = keys[0]; keys[0] = keys[1]; keys[1] = tmp; + * } + * //... + * \endcode + * </pre> + * <p>Because Collator::compare()'s algorithm is complex, it is faster to sort + * long lists of words by retrieving collation keys with Collator::getCollationKey(). + * You can then cache the collation keys and compare them using CollationKey::compareTo(). + * <p> + * <strong>Note:</strong> <code>Collator</code>s with different Locale, + * CollationStrength and DecompositionMode settings will return different + * CollationKeys for the same set of strings. Locales have specific + * collation rules, and the way in which secondary and tertiary differences + * are taken into account, for example, will result in different CollationKeys + * for same strings. + * <p> + + * @see Collator + * @see RuleBasedCollator + * @version 1.3 12/18/96 + * @author Helena Shih + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ +class U_I18N_API CollationKey : public UObject { +public: + /** + * This creates an empty collation key based on the null string. An empty + * collation key contains no sorting information. When comparing two empty + * collation keys, the result is Collator::EQUAL. Comparing empty collation key + * with non-empty collation key is always Collator::LESS. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + CollationKey(); + + + /** + * Creates a collation key based on the collation key values. + * @param values the collation key values + * @param count number of collation key values, including trailing nulls. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + CollationKey(const uint8_t* values, + int32_t count); + + /** + * Copy constructor. + * @param other the object to be copied. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + CollationKey(const CollationKey& other); + + /** + * Sort key destructor. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + virtual ~CollationKey(); + + /** + * Assignment operator + * @param other the object to be copied. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + const CollationKey& operator=(const CollationKey& other); + + /** + * Compare if two collation keys are the same. + * @param source the collation key to compare to. + * @return Returns true if two collation keys are equal, false otherwise. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + UBool operator==(const CollationKey& source) const; + + /** + * Compare if two collation keys are not the same. + * @param source the collation key to compare to. + * @return Returns TRUE if two collation keys are different, FALSE otherwise. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + UBool operator!=(const CollationKey& source) const; + + + /** + * Test to see if the key is in an invalid state. The key will be in an + * invalid state if it couldn't allocate memory for some operation. + * @return Returns TRUE if the key is in an invalid, FALSE otherwise. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + UBool isBogus(void) const; + + /** + * Returns a pointer to the collation key values. The storage is owned + * by the collation key and the pointer will become invalid if the key + * is deleted. + * @param count the output parameter of number of collation key values, + * including any trailing nulls. + * @return a pointer to the collation key values. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + const uint8_t* getByteArray(int32_t& count) const; + +#ifdef U_USE_COLLATION_KEY_DEPRECATES + /** + * Extracts the collation key values into a new array. The caller owns + * this storage and should free it. + * @param count the output parameter of number of collation key values, + * including any trailing nulls. + * @obsolete ICU 2.6. Use getByteArray instead since this API will be removed in that release. + */ + uint8_t* toByteArray(int32_t& count) const; +#endif + + /** + * Convenience method which does a string(bit-wise) comparison of the + * two collation keys. + * @param target target collation key to be compared with + * @return Returns Collator::LESS if sourceKey < targetKey, + * Collator::GREATER if sourceKey > targetKey and Collator::EQUAL + * otherwise. + * @deprecated ICU 2.6 use the overload with error code + */ + Collator::EComparisonResult compareTo(const CollationKey& target) const; + + /** + * Convenience method which does a string(bit-wise) comparison of the + * two collation keys. + * @param target target collation key to be compared with + * @param status error code + * @return Returns UCOL_LESS if sourceKey < targetKey, + * UCOL_GREATER if sourceKey > targetKey and UCOL_EQUAL + * otherwise. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + UCollationResult compareTo(const CollationKey& target, UErrorCode &status) const; + + /** + * Creates an integer that is unique to the collation key. NOTE: this + * is not the same as String.hashCode. + * <p>Example of use: + * <pre> + * . UErrorCode status = U_ZERO_ERROR; + * . Collator *myCollation = Collator::createInstance(Locale::US, status); + * . if (U_FAILURE(status)) return; + * . CollationKey key1, key2; + * . UErrorCode status1 = U_ZERO_ERROR, status2 = U_ZERO_ERROR; + * . myCollation->getCollationKey("abc", key1, status1); + * . if (U_FAILURE(status1)) { delete myCollation; return; } + * . myCollation->getCollationKey("ABC", key2, status2); + * . if (U_FAILURE(status2)) { delete myCollation; return; } + * . // key1.hashCode() != key2.hashCode() + * </pre> + * @return the hash value based on the string's collation order. + * @see UnicodeString#hashCode + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + int32_t hashCode(void) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * @deprecated ICU 2.8 Use Collator::getSortKey(...) instead + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + /** + * Returns an array of the collation key values as 16-bit integers. + * The caller owns the storage and must delete it. + * @param values Output param of the collation key values. + * @param count output parameter of the number of collation key values + * @return a pointer to an array of 16-bit collation key values. + */ + void adopt(uint8_t *values, int32_t count); + + /* + * Creates a collation key with a string. + */ + + /** + * If this CollationKey has capacity less than newSize, + * its internal capacity will be increased to newSize. + * @param newSize minimum size this CollationKey has to have + * @return this CollationKey + */ + CollationKey& ensureCapacity(int32_t newSize); + /** + * Set the CollationKey to a "bogus" or invalid state + * @return this CollationKey + */ + CollationKey& setToBogus(void); + /** + * Resets this CollationKey to an empty state + * @return this CollationKey + */ + CollationKey& reset(void); + + /** + * Allow private access to RuleBasedCollator + */ + friend class RuleBasedCollator; + /** + * Bogus status + */ + UBool fBogus; + /** + * Size of fBytes used to store the sortkey. i.e. up till the + * null-termination. + */ + int32_t fCount; + /** + * Full size of the fBytes + */ + int32_t fCapacity; + /** + * Unique hash value of this CollationKey + */ + int32_t fHashCode; + /** + * Array to store the sortkey + */ + uint8_t* fBytes; + +}; + +inline UBool +CollationKey::operator!=(const CollationKey& other) const +{ + return !(*this == other); +} + +inline UBool +CollationKey::isBogus() const +{ + return fBogus; +} + +inline const uint8_t* +CollationKey::getByteArray(int32_t &count) const +{ + count = fCount; + return fBytes; +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/stsearch.h b/Build/source/libs/icu-xetex/i18n/unicode/stsearch.h new file mode 100644 index 00000000000..a3e1bd79263 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/stsearch.h @@ -0,0 +1,518 @@ +/* +********************************************************************** +* Copyright (C) 2001-2007 IBM and others. All rights reserved. +********************************************************************** +* Date Name Description +* 03/22/2000 helena Creation. +********************************************************************** +*/ + +#ifndef STSEARCH_H +#define STSEARCH_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Service for searching text based on RuleBasedCollator. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/tblcoll.h" +#include "unicode/coleitr.h" +#include "unicode/search.h" + +U_NAMESPACE_BEGIN + +/** + * + * <tt>StringSearch</tt> is a <tt>SearchIterator</tt> that provides + * language-sensitive text searching based on the comparison rules defined + * in a {@link RuleBasedCollator} object. + * StringSearch ensures that language eccentricity can be + * handled, e.g. for the German collator, characters ß and SS will be matched + * if case is chosen to be ignored. + * See the <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm"> + * "ICU Collation Design Document"</a> for more information. + * <p> + * The algorithm implemented is a modified form of the Boyer Moore's search. + * For more information see + * <a href="http://icu-project.org/docs/papers/efficient_text_searching_in_java.html"> + * "Efficient Text Searching in Java"</a>, published in <i>Java Report</i> + * in February, 1999, for further information on the algorithm. + * <p> + * There are 2 match options for selection:<br> + * Let S' be the sub-string of a text string S between the offsets start and + * end <start, end>. + * <br> + * A pattern string P matches a text string S at the offsets <start, end> + * if + * <pre> + * option 1. Some canonical equivalent of P matches some canonical equivalent + * of S' + * option 2. P matches S' and if P starts or ends with a combining mark, + * there exists no non-ignorable combining mark before or after S? + * in S respectively. + * </pre> + * Option 2. will be the default. + * <p> + * This search has APIs similar to that of other text iteration mechanisms + * such as the break iterators in <tt>BreakIterator</tt>. Using these + * APIs, it is easy to scan through text looking for all occurances of + * a given pattern. This search iterator allows changing of direction by + * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>. + * Though a direction change can occur without calling <tt>reset</tt> first, + * this operation comes with some speed penalty. + * Match results in the forward direction will match the result matches in + * the backwards direction in the reverse order + * <p> + * <tt>SearchIterator</tt> provides APIs to specify the starting position + * within the text string to be searched, e.g. <tt>setOffset</tt>, + * <tt>preceding</tt> and <tt>following</tt>. Since the + * starting position will be set as it is specified, please take note that + * there are some danger points which the search may render incorrect + * results: + * <ul> + * <li> The midst of a substring that requires normalization. + * <li> If the following match is to be found, the position should not be the + * second character which requires to be swapped with the preceding + * character. Vice versa, if the preceding match is to be found, + * position to search from should not be the first character which + * requires to be swapped with the next character. E.g certain Thai and + * Lao characters require swapping. + * <li> If a following pattern match is to be found, any position within a + * contracting sequence except the first will fail. Vice versa if a + * preceding pattern match is to be found, a invalid starting point + * would be any character within a contracting sequence except the last. + * </ul> + * <p> + * A breakiterator can be used if only matches at logical breaks are desired. + * Using a breakiterator will only give you results that exactly matches the + * boundaries given by the breakiterator. For instance the pattern "e" will + * not be found in the string "\u00e9" if a character break iterator is used. + * <p> + * Options are provided to handle overlapping matches. + * E.g. In English, overlapping matches produces the result 0 and 2 + * for the pattern "abab" in the text "ababab", where else mutually + * exclusive matches only produce the result of 0. + * <p> + * Though collator attributes will be taken into consideration while + * performing matches, there are no APIs here for setting and getting the + * attributes. These attributes can be set by getting the collator + * from <tt>getCollator</tt> and using the APIs in <tt>coll.h</tt>. + * Lastly to update StringSearch to the new collator attributes, + * reset() has to be called. + * <p> + * Restriction: <br> + * Currently there are no composite characters that consists of a + * character with combining class > 0 before a character with combining + * class == 0. However, if such a character exists in the future, + * StringSearch does not guarantee the results for option 1. + * <p> + * Consult the <tt>SearchIterator</tt> documentation for information on + * and examples of how to use instances of this class to implement text + * searching. + * <pre><code> + * UnicodeString target("The quick brown fox jumps over the lazy dog."); + * UnicodeString pattern("fox"); + * + * UErrorCode error = U_ZERO_ERROR; + * StringSearch iter(pattern, target, Locale::getUS(), NULL, status); + * for (int pos = iter.first(error); + * pos != USEARCH_DONE; + * pos = iter.next(error)) + * { + * printf("Found match at %d pos, length is %d\n", pos, + * iter.getMatchLength()); + * } + * </code></pre> + * <p> + * Note, StringSearch is not to be subclassed. + * </p> + * @see SearchIterator + * @see RuleBasedCollator + * @since ICU 2.0 + */ + +class U_I18N_API StringSearch : public SearchIterator +{ +public: + + // public constructors and destructors -------------------------------- + + /** + * Creating a <tt>StringSearch</tt> instance using the argument locale + * language rule set. A collator will be created in the process, which + * will be owned by this instance and will be deleted during + * destruction + * @param pattern The text for which this object will search. + * @param text The text in which to search for the pattern. + * @param locale A locale which defines the language-sensitive + * comparison rules used to determine whether text in the + * pattern and target matches. + * @param breakiter A <tt>BreakIterator</tt> object used to constrain + * the matches that are found. Matches whose start and end + * indices in the target text are not boundaries as + * determined by the <tt>BreakIterator</tt> are + * ignored. If this behavior is not desired, + * <tt>NULL</tt> can be passed in instead. + * @param status for errors if any. If pattern or text is NULL, or if + * either the length of pattern or text is 0 then an + * U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + StringSearch(const UnicodeString &pattern, const UnicodeString &text, + const Locale &locale, + BreakIterator *breakiter, + UErrorCode &status); + + /** + * Creating a <tt>StringSearch</tt> instance using the argument collator + * language rule set. Note, user retains the ownership of this collator, + * it does not get destroyed during this instance's destruction. + * @param pattern The text for which this object will search. + * @param text The text in which to search for the pattern. + * @param coll A <tt>RuleBasedCollator</tt> object which defines + * the language-sensitive comparison rules used to + * determine whether text in the pattern and target + * matches. User is responsible for the clearing of this + * object. + * @param breakiter A <tt>BreakIterator</tt> object used to constrain + * the matches that are found. Matches whose start and end + * indices in the target text are not boundaries as + * determined by the <tt>BreakIterator</tt> are + * ignored. If this behavior is not desired, + * <tt>NULL</tt> can be passed in instead. + * @param status for errors if any. If either the length of pattern or + * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + StringSearch(const UnicodeString &pattern, + const UnicodeString &text, + RuleBasedCollator *coll, + BreakIterator *breakiter, + UErrorCode &status); + + /** + * Creating a <tt>StringSearch</tt> instance using the argument locale + * language rule set. A collator will be created in the process, which + * will be owned by this instance and will be deleted during + * destruction + * <p> + * Note: No parsing of the text within the <tt>CharacterIterator</tt> + * will be done during searching for this version. The block of text + * in <tt>CharacterIterator</tt> will be used as it is. + * @param pattern The text for which this object will search. + * @param text The text iterator in which to search for the pattern. + * @param locale A locale which defines the language-sensitive + * comparison rules used to determine whether text in the + * pattern and target matches. User is responsible for + * the clearing of this object. + * @param breakiter A <tt>BreakIterator</tt> object used to constrain + * the matches that are found. Matches whose start and end + * indices in the target text are not boundaries as + * determined by the <tt>BreakIterator</tt> are + * ignored. If this behavior is not desired, + * <tt>NULL</tt> can be passed in instead. + * @param status for errors if any. If either the length of pattern or + * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + StringSearch(const UnicodeString &pattern, CharacterIterator &text, + const Locale &locale, + BreakIterator *breakiter, + UErrorCode &status); + + /** + * Creating a <tt>StringSearch</tt> instance using the argument collator + * language rule set. Note, user retains the ownership of this collator, + * it does not get destroyed during this instance's destruction. + * <p> + * Note: No parsing of the text within the <tt>CharacterIterator</tt> + * will be done during searching for this version. The block of text + * in <tt>CharacterIterator</tt> will be used as it is. + * @param pattern The text for which this object will search. + * @param text The text in which to search for the pattern. + * @param coll A <tt>RuleBasedCollator</tt> object which defines + * the language-sensitive comparison rules used to + * determine whether text in the pattern and target + * matches. User is responsible for the clearing of this + * object. + * @param breakiter A <tt>BreakIterator</tt> object used to constrain + * the matches that are found. Matches whose start and end + * indices in the target text are not boundaries as + * determined by the <tt>BreakIterator</tt> are + * ignored. If this behavior is not desired, + * <tt>NULL</tt> can be passed in instead. + * @param status for errors if any. If either the length of pattern or + * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + StringSearch(const UnicodeString &pattern, CharacterIterator &text, + RuleBasedCollator *coll, + BreakIterator *breakiter, + UErrorCode &status); + + /** + * Copy constructor that creates a StringSearch instance with the same + * behavior, and iterating over the same text. + * @param that StringSearch instance to be copied. + * @stable ICU 2.0 + */ + StringSearch(const StringSearch &that); + + /** + * Destructor. Cleans up the search iterator data struct. + * If a collator is created in the constructor, it will be destroyed here. + * @stable ICU 2.0 + */ + virtual ~StringSearch(void); + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + StringSearch *clone() const; + + // operator overloading --------------------------------------------- + + /** + * Assignment operator. Sets this iterator to have the same behavior, + * and iterate over the same text, as the one passed in. + * @param that instance to be copied. + * @stable ICU 2.0 + */ + StringSearch & operator=(const StringSearch &that); + + /** + * Equality operator. + * @param that instance to be compared. + * @return TRUE if both instances have the same attributes, + * breakiterators, collators and iterate over the same text + * while looking for the same pattern. + * @stable ICU 2.0 + */ + virtual UBool operator==(const SearchIterator &that) const; + + // public get and set methods ---------------------------------------- + + /** + * Sets the index to point to the given position, and clears any state + * that's affected. + * <p> + * This method takes the argument index and sets the position in the text + * string accordingly without checking if the index is pointing to a + * valid starting point to begin searching. + * @param position within the text to be set. If position is less + * than or greater than the text range for searching, + * an U_INDEX_OUTOFBOUNDS_ERROR will be returned + * @param status for errors if it occurs + * @stable ICU 2.0 + */ + virtual void setOffset(int32_t position, UErrorCode &status); + + /** + * Return the current index in the text being searched. + * If the iteration has gone past the end of the text + * (or past the beginning for a backwards search), USEARCH_DONE + * is returned. + * @return current index in the text being searched. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(void) const; + + /** + * Set the target text to be searched. + * Text iteration will hence begin at the start of the text string. + * This method is + * useful if you want to re-use an iterator to search for the same + * pattern within a different body of text. + * @param text text string to be searched + * @param status for errors if any. If the text length is 0 then an + * U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + virtual void setText(const UnicodeString &text, UErrorCode &status); + + /** + * Set the target text to be searched. + * Text iteration will hence begin at the start of the text string. + * This method is + * useful if you want to re-use an iterator to search for the same + * pattern within a different body of text. + * Note: No parsing of the text within the <tt>CharacterIterator</tt> + * will be done during searching for this version. The block of text + * in <tt>CharacterIterator</tt> will be used as it is. + * @param text text string to be searched + * @param status for errors if any. If the text length is 0 then an + * U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + virtual void setText(CharacterIterator &text, UErrorCode &status); + + /** + * Gets the collator used for the language rules. + * <p> + * Caller may modify but <b>must not</b> delete the <tt>RuleBasedCollator</tt>! + * Modifications to this collator will affect the original collator passed in to + * the <tt>StringSearch></tt> constructor or to setCollator, if any. + * @return collator used for string search + * @stable ICU 2.0 + */ + RuleBasedCollator * getCollator() const; + + /** + * Sets the collator used for the language rules. User retains the + * ownership of this collator, thus the responsibility of deletion lies + * with the user. This method causes internal data such as Boyer-Moore + * shift tables to be recalculated, but the iterator's position is + * unchanged. + * @param coll collator + * @param status for errors if any + * @stable ICU 2.0 + */ + void setCollator(RuleBasedCollator *coll, UErrorCode &status); + + /** + * Sets the pattern used for matching. + * Internal data like the Boyer Moore table will be recalculated, but + * the iterator's position is unchanged. + * @param pattern search pattern to be found + * @param status for errors if any. If the pattern length is 0 then an + * U_ILLEGAL_ARGUMENT_ERROR is returned. + * @stable ICU 2.0 + */ + void setPattern(const UnicodeString &pattern, UErrorCode &status); + + /** + * Gets the search pattern. + * @return pattern used for matching + * @stable ICU 2.0 + */ + const UnicodeString & getPattern() const; + + // public methods ---------------------------------------------------- + + /** + * Reset the iteration. + * Search will begin at the start of the text string if a forward + * iteration is initiated before a backwards iteration. Otherwise if + * a backwards iteration is initiated before a forwards iteration, the + * search will begin at the end of the text string. + * @stable ICU 2.0 + */ + virtual void reset(); + + /** + * Returns a copy of StringSearch with the same behavior, and + * iterating over the same text, as this one. Note that all data will be + * replicated, except for the user-specified collator and the + * breakiterator. + * @return cloned object + * @stable ICU 2.0 + */ + virtual SearchIterator * safeClone(void) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +protected: + + // protected method ------------------------------------------------- + + /** + * Search forward for matching text, starting at a given location. + * Clients should not call this method directly; instead they should + * call {@link SearchIterator#next }. + * <p> + * If a match is found, this method returns the index at which the match + * starts and calls {@link SearchIterator#setMatchLength } with the number + * of characters in the target text that make up the match. If no match + * is found, the method returns <tt>USEARCH_DONE</tt>. + * <p> + * The <tt>StringSearch</tt> is adjusted so that its current index + * (as returned by {@link #getOffset }) is the match position if one was + * found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE. + * @param position The index in the target text at which the search + * starts + * @param status for errors if any occurs + * @return The index at which the matched text in the target starts, or + * USEARCH_DONE if no match was found. + * @stable ICU 2.0 + */ + virtual int32_t handleNext(int32_t position, UErrorCode &status); + + /** + * Search backward for matching text, starting at a given location. + * Clients should not call this method directly; instead they should call + * <tt>SearchIterator.previous()</tt>, which this method overrides. + * <p> + * If a match is found, this method returns the index at which the match + * starts and calls {@link SearchIterator#setMatchLength } with the number + * of characters in the target text that make up the match. If no match + * is found, the method returns <tt>USEARCH_DONE</tt>. + * <p> + * The <tt>StringSearch</tt> is adjusted so that its current index + * (as returned by {@link #getOffset }) is the match position if one was + * found. + * If a match is not found, <tt>USEARCH_DONE</tt> will be returned and + * the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE. + * @param position The index in the target text at which the search + * starts. + * @param status for errors if any occurs + * @return The index at which the matched text in the target starts, or + * USEARCH_DONE if no match was found. + * @stable ICU 2.0 + */ + virtual int32_t handlePrev(int32_t position, UErrorCode &status); + +private : + StringSearch(); // default constructor not implemented + + // private data members ---------------------------------------------- + + /** + * RuleBasedCollator, contains exactly the same UCollator * in m_strsrch_ + * @stable ICU 2.0 + */ + RuleBasedCollator m_collator_; + /** + * Pattern text + * @stable ICU 2.0 + */ + UnicodeString m_pattern_; + /** + * String search struct data + * @stable ICU 2.0 + */ + UStringSearch *m_strsrch_; + +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/tblcoll.h b/Build/source/libs/icu-xetex/i18n/unicode/tblcoll.h new file mode 100644 index 00000000000..ab7d9eae21b --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/tblcoll.h @@ -0,0 +1,924 @@ +/* +****************************************************************************** +* Copyright (C) 1996-2007, International Business Machines Corporation and +* others. All Rights Reserved. +****************************************************************************** +*/ + +/** +* File tblcoll.h +* +* Created by: Helena Shih +* +* Modification History: +* +* Date Name Description +* 2/5/97 aliu Added streamIn and streamOut methods. Added +* constructor which reads RuleBasedCollator object from +* a binary file. Added writeToFile method which streams +* RuleBasedCollator out to a binary file. The streamIn +* and streamOut methods use istream and ostream objects +* in binary mode. +* 2/12/97 aliu Modified to use TableCollationData sub-object to +* hold invariant data. +* 2/13/97 aliu Moved several methods into this class from Collation. +* Added a private RuleBasedCollator(Locale&) constructor, +* to be used by Collator::createDefault(). General +* clean up. +* 2/20/97 helena Added clone, operator==, operator!=, operator=, and copy +* constructor and getDynamicClassID. +* 3/5/97 aliu Modified constructFromFile() to add parameter +* specifying whether or not binary loading is to be +* attempted. This is required for dynamic rule loading. +* 05/07/97 helena Added memory allocation error detection. +* 6/17/97 helena Added IDENTICAL strength for compare, changed getRules to +* use MergeCollation::getPattern. +* 6/20/97 helena Java class name change. +* 8/18/97 helena Added internal API documentation. +* 09/03/97 helena Added createCollationKeyValues(). +* 02/10/98 damiba Added compare with "length" parameter +* 08/05/98 erm Synched with 1.2 version of RuleBasedCollator.java +* 04/23/99 stephen Removed EDecompositionMode, merged with +* Normalizer::EMode +* 06/14/99 stephen Removed kResourceBundleSuffix +* 11/02/99 helena Collator performance enhancements. Eliminates the +* UnicodeString construction and special case for NO_OP. +* 11/23/99 srl More performance enhancements. Updates to NormalizerIterator +* internal state management. +* 12/15/99 aliu Update to support Thai collation. Move NormalizerIterator +* to implementation file. +* 01/29/01 synwee Modified into a C++ wrapper which calls C API +* (ucol.h) +*/ + +#ifndef TBLCOLL_H +#define TBLCOLL_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: RuleBasedCollator class provides the simple implementation of Collator. + */ + +#if !UCONFIG_NO_COLLATION + +#include "unicode/coll.h" +#include "unicode/ucol.h" +#include "unicode/sortkey.h" +#include "unicode/normlzr.h" + +U_NAMESPACE_BEGIN + +/** +* @stable ICU 2.0 +*/ +class StringSearch; +/** +* @stable ICU 2.0 +*/ +class CollationElementIterator; + +/** + * The RuleBasedCollator class provides the simple implementation of + * Collator, using data-driven tables. The user can create a customized + * table-based collation. + * <P> + * <em>Important: </em>The ICU collation service has been reimplemented + * in order to achieve better performance and UCA compliance. + * For details, see the + * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm"> + * collation design document</a>. + * <p> + * RuleBasedCollator is a thin C++ wrapper over the C implementation. + * <p> + * For more information about the collation service see + * <a href="http://icu-project.org/userguide/Collate_Intro.html">the users guide</a>. + * <p> + * Collation service provides correct sorting orders for most locales supported in ICU. + * If specific data for a locale is not available, the orders eventually falls back + * to the <a href="http://www.unicode.org/unicode/reports/tr10/">UCA sort order</a>. + * <p> + * Sort ordering may be customized by providing your own set of rules. For more on + * this subject see the <a href="http://icu-project.org/userguide/Collate_Customization.html"> + * Collation customization</a> section of the users guide. + * <p> + * Note, RuleBasedCollator is not to be subclassed. + * @see Collator + * @version 2.0 11/15/2001 + */ +class U_I18N_API RuleBasedCollator : public Collator +{ +public: + + // constructor ------------------------------------------------------------- + + /** + * RuleBasedCollator constructor. This takes the table rules and builds a + * collation table out of them. Please see RuleBasedCollator class + * description for more details on the collation rule syntax. + * @param rules the collation rules to build the collation table from. + * @param status reporting a success or an error. + * @see Locale + * @stable ICU 2.0 + */ + RuleBasedCollator(const UnicodeString& rules, UErrorCode& status); + + /** + * RuleBasedCollator constructor. This takes the table rules and builds a + * collation table out of them. Please see RuleBasedCollator class + * description for more details on the collation rule syntax. + * @param rules the collation rules to build the collation table from. + * @param collationStrength default strength for comparison + * @param status reporting a success or an error. + * @see Locale + * @stable ICU 2.0 + */ + RuleBasedCollator(const UnicodeString& rules, + ECollationStrength collationStrength, + UErrorCode& status); + + /** + * RuleBasedCollator constructor. This takes the table rules and builds a + * collation table out of them. Please see RuleBasedCollator class + * description for more details on the collation rule syntax. + * @param rules the collation rules to build the collation table from. + * @param decompositionMode the normalisation mode + * @param status reporting a success or an error. + * @see Locale + * @stable ICU 2.0 + */ + RuleBasedCollator(const UnicodeString& rules, + UColAttributeValue decompositionMode, + UErrorCode& status); + + /** + * RuleBasedCollator constructor. This takes the table rules and builds a + * collation table out of them. Please see RuleBasedCollator class + * description for more details on the collation rule syntax. + * @param rules the collation rules to build the collation table from. + * @param collationStrength default strength for comparison + * @param decompositionMode the normalisation mode + * @param status reporting a success or an error. + * @see Locale + * @stable ICU 2.0 + */ + RuleBasedCollator(const UnicodeString& rules, + ECollationStrength collationStrength, + UColAttributeValue decompositionMode, + UErrorCode& status); + + /** + * Copy constructor. + * @param other the RuleBasedCollator object to be copied + * @see Locale + * @stable ICU 2.0 + */ + RuleBasedCollator(const RuleBasedCollator& other); + + + /** Opens a collator from a collator binary image created using + * cloneBinary. Binary image used in instantiation of the + * collator remains owned by the user and should stay around for + * the lifetime of the collator. The API also takes a base collator + * which usualy should be UCA. + * @param bin binary image owned by the user and required through the + * lifetime of the collator + * @param length size of the image. If negative, the API will try to + * figure out the length of the image + * @param base fallback collator, usually UCA. Base is required to be + * present through the lifetime of the collator. Currently + * it cannot be NULL. + * @param status for catching errors + * @return newly created collator + * @see cloneBinary + * @stable ICU 3.4 + */ + RuleBasedCollator(const uint8_t *bin, int32_t length, + const RuleBasedCollator *base, + UErrorCode &status); + // destructor -------------------------------------------------------------- + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~RuleBasedCollator(); + + // public methods ---------------------------------------------------------- + + /** + * Assignment operator. + * @param other other RuleBasedCollator object to compare with. + * @stable ICU 2.0 + */ + RuleBasedCollator& operator=(const RuleBasedCollator& other); + + /** + * Returns true if argument is the same as this object. + * @param other Collator object to be compared. + * @return true if arguments is the same as this object. + * @stable ICU 2.0 + */ + virtual UBool operator==(const Collator& other) const; + + /** + * Returns true if argument is not the same as this object. + * @param other Collator object to be compared + * @return returns true if argument is not the same as this object. + * @stable ICU 2.0 + */ + virtual UBool operator!=(const Collator& other) const; + + /** + * Makes a deep copy of the object. + * The caller owns the returned object. + * @return the cloned object. + * @stable ICU 2.0 + */ + virtual Collator* clone(void) const; + + /** + * Creates a collation element iterator for the source string. The caller of + * this method is responsible for the memory management of the return + * pointer. + * @param source the string over which the CollationElementIterator will + * iterate. + * @return the collation element iterator of the source string using this as + * the based Collator. + * @stable ICU 2.2 + */ + virtual CollationElementIterator* createCollationElementIterator( + const UnicodeString& source) const; + + /** + * Creates a collation element iterator for the source. The caller of this + * method is responsible for the memory management of the returned pointer. + * @param source the CharacterIterator which produces the characters over + * which the CollationElementItgerator will iterate. + * @return the collation element iterator of the source using this as the + * based Collator. + * @stable ICU 2.2 + */ + virtual CollationElementIterator* createCollationElementIterator( + const CharacterIterator& source) const; + + /** + * Compares a range of character data stored in two different strings based + * on the collation rules. Returns information about whether a string is + * less than, greater than or equal to another string in a language. + * This can be overriden in a subclass. + * @param source the source string. + * @param target the target string to be compared with the source string. + * @return the comparison result. GREATER if the source string is greater + * than the target string, LESS if the source is less than the + * target. Otherwise, returns EQUAL. + * @deprecated ICU 2.6 Use overload with UErrorCode& + */ + virtual EComparisonResult compare(const UnicodeString& source, + const UnicodeString& target) const; + + + /** + * The comparison function compares the character data stored in two + * different strings. Returns information about whether a string is less + * than, greater than or equal to another string. + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source is greater + * than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less + * than target + * @stable ICU 2.6 + **/ + virtual UCollationResult compare(const UnicodeString& source, + const UnicodeString& target, + UErrorCode &status) const; + + /** + * Compares a range of character data stored in two different strings based + * on the collation rules up to the specified length. Returns information + * about whether a string is less than, greater than or equal to another + * string in a language. This can be overriden in a subclass. + * @param source the source string. + * @param target the target string to be compared with the source string. + * @param length compares up to the specified length + * @return the comparison result. GREATER if the source string is greater + * than the target string, LESS if the source is less than the + * target. Otherwise, returns EQUAL. + * @deprecated ICU 2.6 Use overload with UErrorCode& + */ + virtual EComparisonResult compare(const UnicodeString& source, + const UnicodeString& target, + int32_t length) const; + + /** + * Does the same thing as compare but limits the comparison to a specified + * length + * @param source the source string to be compared with. + * @param target the string that is to be compared with the source string. + * @param length the length the comparison is limited to + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source (up to the specified + * length) is greater than target; UCOL_EQUAL if source (up to specified + * length) is equal to target; UCOL_LESS if source (up to the specified + * length) is less than target. + * @stable ICU 2.6 + */ + virtual UCollationResult compare(const UnicodeString& source, + const UnicodeString& target, + int32_t length, + UErrorCode &status) const; + + /** + * The comparison function compares the character data stored in two + * different string arrays. Returns information about whether a string array + * is less than, greater than or equal to another string array. + * <p>Example of use: + * <pre> + * . UChar ABC[] = {0x41, 0x42, 0x43, 0}; // = "ABC" + * . UChar abc[] = {0x61, 0x62, 0x63, 0}; // = "abc" + * . UErrorCode status = U_ZERO_ERROR; + * . Collator *myCollation = + * . Collator::createInstance(Locale::US, status); + * . if (U_FAILURE(status)) return; + * . myCollation->setStrength(Collator::PRIMARY); + * . // result would be Collator::EQUAL ("abc" == "ABC") + * . // (no primary difference between "abc" and "ABC") + * . Collator::EComparisonResult result = + * . myCollation->compare(abc, 3, ABC, 3); + * . myCollation->setStrength(Collator::TERTIARY); + * . // result would be Collator::LESS ("abc" <<< "ABC") + * . // (with tertiary difference between "abc" and "ABC") + * . result = myCollation->compare(abc, 3, ABC, 3); + * </pre> + * @param source the source string array to be compared with. + * @param sourceLength the length of the source string array. If this value + * is equal to -1, the string array is null-terminated. + * @param target the string that is to be compared with the source string. + * @param targetLength the length of the target string array. If this value + * is equal to -1, the string array is null-terminated. + * @return Returns a byte value. GREATER if source is greater than target; + * EQUAL if source is equal to target; LESS if source is less than + * target + * @deprecated ICU 2.6 Use overload with UErrorCode& + */ + virtual EComparisonResult compare(const UChar* source, int32_t sourceLength, + const UChar* target, int32_t targetLength) + const; + + /** + * The comparison function compares the character data stored in two + * different string arrays. Returns information about whether a string array + * is less than, greater than or equal to another string array. + * @param source the source string array to be compared with. + * @param sourceLength the length of the source string array. If this value + * is equal to -1, the string array is null-terminated. + * @param target the string that is to be compared with the source string. + * @param targetLength the length of the target string array. If this value + * is equal to -1, the string array is null-terminated. + * @param status possible error code + * @return Returns an enum value. UCOL_GREATER if source is greater + * than target; UCOL_EQUAL if source is equal to target; UCOL_LESS if source is less + * than target + * @stable ICU 2.6 + */ + virtual UCollationResult compare(const UChar* source, int32_t sourceLength, + const UChar* target, int32_t targetLength, + UErrorCode &status) const; + + /** + * Transforms a specified region of the string into a series of characters + * that can be compared with CollationKey.compare. Use a CollationKey when + * you need to do repeated comparisions on the same string. For a single + * comparison the compare method will be faster. + * @param source the source string. + * @param key the transformed key of the source string. + * @param status the error code status. + * @return the transformed key. + * @see CollationKey + * @deprecated ICU 2.8 Use getSortKey(...) instead + */ + virtual CollationKey& getCollationKey(const UnicodeString& source, + CollationKey& key, + UErrorCode& status) const; + + /** + * Transforms a specified region of the string into a series of characters + * that can be compared with CollationKey.compare. Use a CollationKey when + * you need to do repeated comparisions on the same string. For a single + * comparison the compare method will be faster. + * @param source the source string. + * @param sourceLength the length of the source string. + * @param key the transformed key of the source string. + * @param status the error code status. + * @return the transformed key. + * @see CollationKey + * @deprecated ICU 2.8 Use getSortKey(...) instead + */ + virtual CollationKey& getCollationKey(const UChar *source, + int32_t sourceLength, + CollationKey& key, + UErrorCode& status) const; + + /** + * Generates the hash code for the rule-based collation object. + * @return the hash code. + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const; + + /** + * Gets the locale of the Collator + * @param type can be either requested, valid or actual locale. For more + * information see the definition of ULocDataLocaleType in + * uloc.h + * @param status the error code status. + * @return locale where the collation data lives. If the collator + * was instantiated from rules, locale is empty. + * @deprecated ICU 2.8 likely to change in ICU 3.0, based on feedback + */ + virtual const Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; + + /** + * Gets the table-based rules for the collation object. + * @return returns the collation rules that the table collation object was + * created from. + * @stable ICU 2.0 + */ + const UnicodeString& getRules(void) const; + + /** + * Gets the version information for a Collator. + * @param info the version # information, the result will be filled in + * @stable ICU 2.0 + */ + virtual void getVersion(UVersionInfo info) const; + + /** + * Return the maximum length of any expansion sequences that end with the + * specified comparison order. + * @param order a collation order returned by previous or next. + * @return maximum size of the expansion sequences ending with the collation + * element or 1 if collation element does not occur at the end of + * any expansion sequence + * @see CollationElementIterator#getMaxExpansion + * @stable ICU 2.0 + */ + int32_t getMaxExpansion(int32_t order) const; + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * @return The class ID for this object. All objects of a given class have + * the same class ID. Objects of other classes have different class + * IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Returns the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * Base* polymorphic_pointer = createPolymorphicObject(); + * if (polymorphic_pointer->getDynamicClassID() == + * Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns the binary format of the class's rules. The format is that of + * .col files. + * @param length Returns the length of the data, in bytes + * @param status the error code status. + * @return memory, owned by the caller, of size 'length' bytes. + * @stable ICU 2.2 + */ + uint8_t *cloneRuleData(int32_t &length, UErrorCode &status); + + + /** Creates a binary image of a collator. This binary image can be stored and + * later used to instantiate a collator using ucol_openBinary. + * This API supports preflighting. + * @param buffer a fill-in buffer to receive the binary image + * @param capacity capacity of the destination buffer + * @param status for catching errors + * @return size of the image + * @see ucol_openBinary + * @stable ICU 3.4 + */ + int32_t cloneBinary(uint8_t *buffer, int32_t capacity, UErrorCode &status); + + /** + * Returns current rules. Delta defines whether full rules are returned or + * just the tailoring. + * @param delta one of UCOL_TAILORING_ONLY, UCOL_FULL_RULES. + * @param buffer UnicodeString to store the result rules + * @stable ICU 2.2 + */ + void getRules(UColRuleOption delta, UnicodeString &buffer); + + /** + * Universal attribute setter + * @param attr attribute type + * @param value attribute value + * @param status to indicate whether the operation went on smoothly or there were errors + * @stable ICU 2.2 + */ + virtual void setAttribute(UColAttribute attr, UColAttributeValue value, + UErrorCode &status); + + /** + * Universal attribute getter. + * @param attr attribute type + * @param status to indicate whether the operation went on smoothly or there were errors + * @return attribute value + * @stable ICU 2.2 + */ + virtual UColAttributeValue getAttribute(UColAttribute attr, + UErrorCode &status); + + /** + * Sets the variable top to a collation element value of a string supplied. + * @param varTop one or more (if contraction) UChars to which the variable top should be set + * @param len length of variable top string. If -1 it is considered to be zero terminated. + * @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br> + * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br> + * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes + * @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined + * @stable ICU 2.0 + */ + virtual uint32_t setVariableTop(const UChar *varTop, int32_t len, UErrorCode &status); + + /** + * Sets the variable top to a collation element value of a string supplied. + * @param varTop an UnicodeString size 1 or more (if contraction) of UChars to which the variable top should be set + * @param status error code. If error code is set, the return value is undefined. Errors set by this function are: <br> + * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such a contraction<br> + * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes + * @return a 32 bit value containing the value of the variable top in upper 16 bits. Lower 16 bits are undefined + * @stable ICU 2.0 + */ + virtual uint32_t setVariableTop(const UnicodeString varTop, UErrorCode &status); + + /** + * Sets the variable top to a collation element value supplied. Variable top is set to the upper 16 bits. + * Lower 16 bits are ignored. + * @param varTop CE value, as returned by setVariableTop or ucol)getVariableTop + * @param status error code (not changed by function) + * @stable ICU 2.0 + */ + virtual void setVariableTop(const uint32_t varTop, UErrorCode &status); + + /** + * Gets the variable top value of a Collator. + * Lower 16 bits are undefined and should be ignored. + * @param status error code (not changed by function). If error code is set, the return value is undefined. + * @stable ICU 2.0 + */ + virtual uint32_t getVariableTop(UErrorCode &status) const; + + /** + * Get an UnicodeSet that contains all the characters and sequences tailored in + * this collator. + * @param status error code of the operation + * @return a pointer to a UnicodeSet object containing all the + * code points and sequences that may sort differently than + * in the UCA. The object must be disposed of by using delete + * @stable ICU 2.4 + */ + virtual UnicodeSet *getTailoredSet(UErrorCode &status) const; + + /** + * Thread safe cloning operation. + * @return pointer to the new clone, user should remove it. + * @stable ICU 2.2 + */ + virtual Collator* safeClone(void); + + /** + * Get the sort key as an array of bytes from an UnicodeString. + * @param source string to be processed. + * @param result buffer to store result in. If NULL, number of bytes needed + * will be returned. + * @param resultLength length of the result buffer. If if not enough the + * buffer will be filled to capacity. + * @return Number of bytes needed for storing the sort key + * @stable ICU 2.0 + */ + virtual int32_t getSortKey(const UnicodeString& source, uint8_t *result, + int32_t resultLength) const; + + /** + * Get the sort key as an array of bytes from an UChar buffer. + * @param source string to be processed. + * @param sourceLength length of string to be processed. If -1, the string + * is 0 terminated and length will be decided by the function. + * @param result buffer to store result in. If NULL, number of bytes needed + * will be returned. + * @param resultLength length of the result buffer. If if not enough the + * buffer will be filled to capacity. + * @return Number of bytes needed for storing the sort key + * @stable ICU 2.2 + */ + virtual int32_t getSortKey(const UChar *source, int32_t sourceLength, + uint8_t *result, int32_t resultLength) const; + + /** + * Determines the minimum strength that will be use in comparison or + * transformation. + * <p>E.g. with strength == SECONDARY, the tertiary difference is ignored + * <p>E.g. with strength == PRIMARY, the secondary and tertiary difference + * are ignored. + * @return the current comparison level. + * @see RuleBasedCollator#setStrength + * @deprecated ICU 2.6 Use getAttribute(UCOL_STRENGTH...) instead + */ + virtual ECollationStrength getStrength(void) const; + + /** + * Sets the minimum strength to be used in comparison or transformation. + * @see RuleBasedCollator#getStrength + * @param newStrength the new comparison level. + * @deprecated ICU 2.6 Use setAttribute(UCOL_STRENGTH...) instead + */ + virtual void setStrength(ECollationStrength newStrength); + +private: + + // private static constants ----------------------------------------------- + + enum { + /* need look up in .commit() */ + CHARINDEX = 0x70000000, + /* Expand index follows */ + EXPANDCHARINDEX = 0x7E000000, + /* contract indexes follows */ + CONTRACTCHARINDEX = 0x7F000000, + /* unmapped character values */ + UNMAPPED = 0xFFFFFFFF, + /* primary strength increment */ + PRIMARYORDERINCREMENT = 0x00010000, + /* secondary strength increment */ + SECONDARYORDERINCREMENT = 0x00000100, + /* tertiary strength increment */ + TERTIARYORDERINCREMENT = 0x00000001, + /* mask off anything but primary order */ + PRIMARYORDERMASK = 0xffff0000, + /* mask off anything but secondary order */ + SECONDARYORDERMASK = 0x0000ff00, + /* mask off anything but tertiary order */ + TERTIARYORDERMASK = 0x000000ff, + /* mask off ignorable char order */ + IGNORABLEMASK = 0x0000ffff, + /* use only the primary difference */ + PRIMARYDIFFERENCEONLY = 0xffff0000, + /* use only the primary and secondary difference */ + SECONDARYDIFFERENCEONLY = 0xffffff00, + /* primary order shift */ + PRIMARYORDERSHIFT = 16, + /* secondary order shift */ + SECONDARYORDERSHIFT = 8, + /* starting value for collation elements */ + COLELEMENTSTART = 0x02020202, + /* testing mask for primary low element */ + PRIMARYLOWZEROMASK = 0x00FF0000, + /* reseting value for secondaries and tertiaries */ + RESETSECONDARYTERTIARY = 0x00000202, + /* reseting value for tertiaries */ + RESETTERTIARY = 0x00000002, + + PRIMIGNORABLE = 0x0202 + }; + + // private data members --------------------------------------------------- + + UBool dataIsOwned; + + UBool isWriteThroughAlias; + + /** + * c struct for collation. All initialisation for it has to be done through + * setUCollator(). + */ + UCollator *ucollator; + + /** + * Rule UnicodeString + */ + UnicodeString urulestring; + + // friend classes -------------------------------------------------------- + + /** + * Used to iterate over collation elements in a character source. + */ + friend class CollationElementIterator; + + /** + * Collator ONLY needs access to RuleBasedCollator(const Locale&, + * UErrorCode&) + */ + friend class Collator; + + /** + * Searching over collation elements in a character source + */ + friend class StringSearch; + + // private constructors -------------------------------------------------- + + /** + * Default constructor + */ + RuleBasedCollator(); + + /** + * RuleBasedCollator constructor. This constructor takes a locale. The + * only caller of this class should be Collator::createInstance(). If + * createInstance() happens to know that the requested locale's collation is + * implemented as a RuleBasedCollator, it can then call this constructor. + * OTHERWISE IT SHOULDN'T, since this constructor ALWAYS RETURNS A VALID + * COLLATION TABLE. It does this by falling back to defaults. + * @param desiredLocale locale used + * @param status error code status + */ + RuleBasedCollator(const Locale& desiredLocale, UErrorCode& status); + + /** + * common constructor implementation + * + * @param rules the collation rules to build the collation table from. + * @param collationStrength default strength for comparison + * @param decompositionMode the normalisation mode + * @param status reporting a success or an error. + */ + void + construct(const UnicodeString& rules, + UColAttributeValue collationStrength, + UColAttributeValue decompositionMode, + UErrorCode& status); + + // private methods ------------------------------------------------------- + + /** + * Creates the c struct for ucollator + * @param locale desired locale + * @param status error status + */ + void setUCollator(const Locale& locale, UErrorCode& status); + + /** + * Creates the c struct for ucollator + * @param locale desired locale name + * @param status error status + */ + void setUCollator(const char* locale, UErrorCode& status); + + /** + * Creates the c struct for ucollator. This used internally by StringSearch. + * Hence the responsibility of cleaning up the ucollator is not done by + * this RuleBasedCollator. The isDataOwned flag is set to FALSE. + * @param collator new ucollator data + * @param rules corresponding collation rules + */ + void setUCollator(UCollator *collator); + +public: + /** + * Get UCollator data struct. Used only by StringSearch & intltest. + * @return UCollator data struct + * @internal + */ + const UCollator * getUCollator(); + +protected: + /** + * Used internally by registraton to define the requested and valid locales. + * @param requestedLocale the requsted locale + * @param validLocale the valid locale + * @internal + */ + virtual void setLocales(const Locale& requestedLocale, const Locale& validLocale); + +private: + + // if not owned and not a write through alias, copy the ucollator + void checkOwned(void); + + // utility to init rule string used by checkOwned and construct + void setRuleStringFromCollator(); + + /** + * Converts C's UCollationResult to EComparisonResult + * @param result member of the enum UComparisonResult + * @return EComparisonResult equivalent of UCollationResult + * @deprecated ICU 2.6. We will not need it. + */ + Collator::EComparisonResult getEComparisonResult( + const UCollationResult &result) const; + + /** + * Converts C's UCollationStrength to ECollationStrength + * @param strength member of the enum UCollationStrength + * @return ECollationStrength equivalent of UCollationStrength + */ + Collator::ECollationStrength getECollationStrength( + const UCollationStrength &strength) const; + + /** + * Converts C++'s ECollationStrength to UCollationStrength + * @param strength member of the enum ECollationStrength + * @return UCollationStrength equivalent of ECollationStrength + */ + UCollationStrength getUCollationStrength( + const Collator::ECollationStrength &strength) const; +}; + +// inline method implementation --------------------------------------------- + +inline void RuleBasedCollator::setUCollator(const Locale &locale, + UErrorCode &status) +{ + setUCollator(locale.getName(), status); +} + + +inline void RuleBasedCollator::setUCollator(UCollator *collator) +{ + + if (ucollator && dataIsOwned) { + ucol_close(ucollator); + } + ucollator = collator; + dataIsOwned = FALSE; + isWriteThroughAlias = TRUE; + setRuleStringFromCollator(); +} + +inline const UCollator * RuleBasedCollator::getUCollator() +{ + return ucollator; +} + +inline Collator::EComparisonResult RuleBasedCollator::getEComparisonResult( + const UCollationResult &result) const +{ + switch (result) + { + case UCOL_LESS : + return Collator::LESS; + case UCOL_EQUAL : + return Collator::EQUAL; + default : + return Collator::GREATER; + } +} + +inline Collator::ECollationStrength RuleBasedCollator::getECollationStrength( + const UCollationStrength &strength) const +{ + switch (strength) + { + case UCOL_PRIMARY : + return Collator::PRIMARY; + case UCOL_SECONDARY : + return Collator::SECONDARY; + case UCOL_TERTIARY : + return Collator::TERTIARY; + case UCOL_QUATERNARY : + return Collator::QUATERNARY; + default : + return Collator::IDENTICAL; + } +} + +inline UCollationStrength RuleBasedCollator::getUCollationStrength( + const Collator::ECollationStrength &strength) const +{ + switch (strength) + { + case Collator::PRIMARY : + return UCOL_PRIMARY; + case Collator::SECONDARY : + return UCOL_SECONDARY; + case Collator::TERTIARY : + return UCOL_TERTIARY; + case Collator::QUATERNARY : + return UCOL_QUATERNARY; + default : + return UCOL_IDENTICAL; + } +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/timezone.h b/Build/source/libs/icu-xetex/i18n/unicode/timezone.h new file mode 100644 index 00000000000..e771cb90855 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/timezone.h @@ -0,0 +1,726 @@ +/************************************************************************* +* Copyright (c) 1997-2007, International Business Machines Corporation +* and others. All Rights Reserved. +************************************************************************** +* +* File TIMEZONE.H +* +* Modification History: +* +* Date Name Description +* 04/21/97 aliu Overhauled header. +* 07/09/97 helena Changed createInstance to createDefault. +* 08/06/97 aliu Removed dependency on internal header for Hashtable. +* 08/10/98 stephen Changed getDisplayName() API conventions to match +* 08/19/98 stephen Changed createTimeZone() to never return 0 +* 09/02/98 stephen Sync to JDK 1.2 8/31 +* - Added getOffset(... monthlen ...) +* - Added hasSameRules() +* 09/15/98 stephen Added getStaticClassID +* 12/03/99 aliu Moved data out of static table into icudata.dll. +* Hashtable replaced by new static data structures. +* 12/14/99 aliu Made GMT public. +* 08/15/01 grhoten Made GMT private and added the getGMT() function +************************************************************************** +*/ + +#ifndef TIMEZONE_H +#define TIMEZONE_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: TimeZone object + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/ures.h" + +U_NAMESPACE_BEGIN + +class StringEnumeration; + +/** + * + * <code>TimeZone</code> represents a time zone offset, and also figures out daylight + * savings. + * + * <p> + * Typically, you get a <code>TimeZone</code> using <code>createDefault</code> + * which creates a <code>TimeZone</code> based on the time zone where the program + * is running. For example, for a program running in Japan, <code>createDefault</code> + * creates a <code>TimeZone</code> object based on Japanese Standard Time. + * + * <p> + * You can also get a <code>TimeZone</code> using <code>createTimeZone</code> along + * with a time zone ID. For instance, the time zone ID for the Pacific + * Standard Time zone is "PST". So, you can get a PST <code>TimeZone</code> object + * with: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * TimeZone *tz = TimeZone::createTimeZone("PST"); + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * You can use <code>getAvailableIDs</code> method to iterate through + * all the supported time zone IDs. You can then choose a + * supported ID to get a <code>TimeZone</code>. + * If the time zone you want is not represented by one of the + * supported IDs, then you can create a custom time zone ID with + * the following syntax: + * + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * GMT[+|-]hh[[:]mm] + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * For example, you might specify GMT+14:00 as a custom + * time zone ID. The <code>TimeZone</code> that is returned + * when you specify a custom time zone ID does not include + * daylight savings time. + * + * TimeZone is an abstract class representing a time zone. A TimeZone is needed for + * Calendar to produce local time for a particular time zone. A TimeZone comprises + * three basic pieces of information: + * <ul> + * <li>A time zone offset; that, is the number of milliseconds to add or subtract + * from a time expressed in terms of GMT to convert it to the same time in that + * time zone (without taking daylight savings time into account).</li> + * <li>Logic necessary to take daylight savings time into account if daylight savings + * time is observed in that time zone (e.g., the days and hours on which daylight + * savings time begins and ends).</li> + * <li>An ID. This is a text string that uniquely identifies the time zone.</li> + * </ul> + * + * (Only the ID is actually implemented in TimeZone; subclasses of TimeZone may handle + * daylight savings time and GMT offset in different ways. Currently we only have one + * TimeZone subclass: SimpleTimeZone.) + * <P> + * The TimeZone class contains a static list containing a TimeZone object for every + * combination of GMT offset and daylight-savings time rules currently in use in the + * world, each with a unique ID. Each ID consists of a region (usually a continent or + * ocean) and a city in that region, separated by a slash, (for example, Pacific + * Standard Time is "America/Los_Angeles.") Because older versions of this class used + * three- or four-letter abbreviations instead, there is also a table that maps the older + * abbreviations to the newer ones (for example, "PST" maps to "America/LosAngeles"). + * Anywhere the API requires an ID, you can use either form. + * <P> + * To create a new TimeZone, you call the factory function TimeZone::createTimeZone() + * and pass it a time zone ID. You can use the createEnumeration() function to + * obtain a list of all the time zone IDs recognized by createTimeZone(). + * <P> + * You can also use TimeZone::createDefault() to create a TimeZone. This function uses + * platform-specific APIs to produce a TimeZone for the time zone corresponding to + * the client's computer's physical location. For example, if you're in Japan (assuming + * your machine is set up correctly), TimeZone::createDefault() will return a TimeZone + * for Japanese Standard Time ("Asia/Tokyo"). + */ +class U_I18N_API TimeZone : public UObject { +public: + /** + * @stable ICU 2.0 + */ + virtual ~TimeZone(); + + /** + * The GMT time zone has a raw offset of zero and does not use daylight + * savings time. This is a commonly used time zone. + * @return the GMT time zone. + * @stable ICU 2.0 + */ + static const TimeZone* U_EXPORT2 getGMT(void); + + /** + * Creates a <code>TimeZone</code> for the given ID. + * @param ID the ID for a <code>TimeZone</code>, either an abbreviation such as + * "PST", a full name such as "America/Los_Angeles", or a custom ID + * such as "GMT-8:00". + * @return the specified <code>TimeZone</code>, or the GMT zone if the given ID + * cannot be understood. Return result guaranteed to be non-null. If you + * require that the specific zone asked for be returned, check the ID of the + * return result. + * @stable ICU 2.0 + */ + static TimeZone* U_EXPORT2 createTimeZone(const UnicodeString& ID); + + /** + * Returns an enumeration over all recognized time zone IDs. (i.e., + * all strings that createTimeZone() accepts) + * + * @return an enumeration object, owned by the caller. + * @stable ICU 2.4 + */ + static StringEnumeration* U_EXPORT2 createEnumeration(); + + /** + * Returns an enumeration over time zone IDs with a given raw + * offset from GMT. There may be several times zones with the + * same GMT offset that differ in the way they handle daylight + * savings time. For example, the state of Arizona doesn't + * observe daylight savings time. If you ask for the time zone + * IDs corresponding to GMT-7:00, you'll get back an enumeration + * over two time zone IDs: "America/Denver," which corresponds to + * Mountain Standard Time in the winter and Mountain Daylight Time + * in the summer, and "America/Phoenix", which corresponds to + * Mountain Standard Time year-round, even in the summer. + * + * @param rawOffset an offset from GMT in milliseconds, ignoring + * the effect of daylight savings time, if any + * @return an enumeration object, owned by the caller + * @stable ICU 2.4 + */ + static StringEnumeration* U_EXPORT2 createEnumeration(int32_t rawOffset); + + /** + * Returns an enumeration over time zone IDs associated with the + * given country. Some zones are affiliated with no country + * (e.g., "UTC"); these may also be retrieved, as a group. + * + * @param country The ISO 3166 two-letter country code, or NULL to + * retrieve zones not affiliated with any country. + * @return an enumeration object, owned by the caller + * @stable ICU 2.4 + */ + static StringEnumeration* U_EXPORT2 createEnumeration(const char* country); + +#ifdef U_USE_TIMEZONE_OBSOLETE_2_8 + /** + * Returns a list of time zone IDs, one for each time zone with a given GMT offset. + * The return value is a list because there may be several times zones with the same + * GMT offset that differ in the way they handle daylight savings time. For example, + * the state of Arizona doesn't observe Daylight Savings time. So if you ask for + * the time zone IDs corresponding to GMT-7:00, you'll get back two time zone IDs: + * "America/Denver," which corresponds to Mountain Standard Time in the winter and + * Mountain Daylight Time in the summer, and "America/Phoenix", which corresponds to + * Mountain Standard Time year-round, even in the summer. + * <P> + * The caller owns the list that is returned, but does not own the strings contained + * in that list. Delete the array with uprv_free(), but DON'T delete the elements in the array. + * + * <p>NOTE: uprv_free() is declared in the private header source/common/cmemory.h. + * + * @param rawOffset An offset from GMT in milliseconds. + * @param numIDs Receives the number of items in the array that is returned. + * @return An array of UnicodeString pointers, where each UnicodeString is + * a time zone ID for a time zone with the given GMT offset. If + * there is no timezone that matches the GMT offset + * specified, NULL is returned. + * @obsolete ICU 2.8. Use createEnumeration(int32_t) instead since this API will be removed in that release. + */ + static const UnicodeString** createAvailableIDs(int32_t rawOffset, int32_t& numIDs); + + /** + * Returns a list of time zone IDs associated with the given + * country. Some zones are affiliated with no country (e.g., + * "UTC"); these may also be retrieved, as a group. + * + * <P>The caller owns the list that is returned, but does not own + * the strings contained in that list. Delete the array with uprv_free(), but + * <b>DON'T</b> delete the elements in the array. + * + * <p>NOTE: uprv_free() is declared in the private header source/common/cmemory.h. + * + * @param country The ISO 3166 two-letter country code, or NULL to + * retrieve zones not affiliated with any country. + * @param numIDs Receives the number of items in the array that is + * returned. + * @return An array of UnicodeString pointers, where each + * UnicodeString is a time zone ID for a time zone with the given + * country. If there is no timezone that matches the country + * specified, NULL is returned. + * @obsolete ICU 2.8. Use createEnumeration(const char*) instead since this API will be removed in that release. + */ + static const UnicodeString** createAvailableIDs(const char* country, + int32_t& numIDs); + + /** + * Returns a list of all time zone IDs supported by the TimeZone class (i.e., all + * IDs that it's legal to pass to createTimeZone()). The caller owns the list that + * is returned, but does not own the strings contained in that list. Delete the array with uprv_free(), + * but DON'T delete the elements in the array. + * + * <p>NOTE: uprv_free() is declared in the private header source/common/cmemory.h. + * + * @param numIDs Receives the number of zone IDs returned. + * @return An array of UnicodeString pointers, where each is a time zone ID + * supported by the TimeZone class. + * @obsolete ICU 2.8. Use createEnumeration(void) instead since this API will be removed in that release. + */ + static const UnicodeString** createAvailableIDs(int32_t& numIDs); +#endif + + /** + * Returns the number of IDs in the equivalency group that + * includes the given ID. An equivalency group contains zones + * that have the same GMT offset and rules. + * + * <p>The returned count includes the given ID; it is always >= 1. + * The given ID must be a system time zone. If it is not, returns + * zero. + * @param id a system time zone ID + * @return the number of zones in the equivalency group containing + * 'id', or zero if 'id' is not a valid system ID + * @see #getEquivalentID + * @stable ICU 2.0 + */ + static int32_t U_EXPORT2 countEquivalentIDs(const UnicodeString& id); + + /** + * Returns an ID in the equivalency group that + * includes the given ID. An equivalency group contains zones + * that have the same GMT offset and rules. + * + * <p>The given index must be in the range 0..n-1, where n is the + * value returned by <code>countEquivalentIDs(id)</code>. For + * some value of 'index', the returned value will be equal to the + * given id. If the given id is not a valid system time zone, or + * if 'index' is out of range, then returns an empty string. + * @param id a system time zone ID + * @param index a value from 0 to n-1, where n is the value + * returned by <code>countEquivalentIDs(id)</code> + * @return the ID of the index-th zone in the equivalency group + * containing 'id', or an empty string if 'id' is not a valid + * system ID or 'index' is out of range + * @see #countEquivalentIDs + * @stable ICU 2.0 + */ + static const UnicodeString U_EXPORT2 getEquivalentID(const UnicodeString& id, + int32_t index); + + /** + * Creates a new copy of the default TimeZone for this host. Unless the default time + * zone has already been set using adoptDefault() or setDefault(), the default is + * determined by querying the system using methods in TPlatformUtilities. If the + * system routines fail, or if they specify a TimeZone or TimeZone offset which is not + * recognized, the TimeZone indicated by the ID kLastResortID is instantiated + * and made the default. + * + * @return A default TimeZone. Clients are responsible for deleting the time zone + * object returned. + * @stable ICU 2.0 + */ + static TimeZone* U_EXPORT2 createDefault(void); + + /** + * Sets the default time zone (i.e., what's returned by createDefault()) to be the + * specified time zone. If NULL is specified for the time zone, the default time + * zone is set to the default host time zone. This call adopts the TimeZone object + * passed in; the clent is no longer responsible for deleting it. + * + * @param zone A pointer to the new TimeZone object to use as the default. + * @stable ICU 2.0 + */ + static void U_EXPORT2 adoptDefault(TimeZone* zone); + + /** + * Same as adoptDefault(), except that the TimeZone object passed in is NOT adopted; + * the caller remains responsible for deleting it. + * + * @param zone The given timezone. + * @system + */ + static void U_EXPORT2 setDefault(const TimeZone& zone); + + /** + * Returns the timezone data version currently used by ICU. + * @param status Output param to filled in with a success or an error. + * @return the version string, such as "2007f" + * @draft ICU 3.8 + */ + static const char* U_EXPORT2 getTZDataVersion(UErrorCode& status); + + /** + * Returns true if the two TimeZones are equal. (The TimeZone version only compares + * IDs, but subclasses are expected to also compare the fields they add.) + * + * @param that The TimeZone object to be compared with. + * @return True if the given TimeZone is equal to this TimeZone; false + * otherwise. + * @stable ICU 2.0 + */ + virtual UBool operator==(const TimeZone& that) const; + + /** + * Returns true if the two TimeZones are NOT equal; that is, if operator==() returns + * false. + * + * @param that The TimeZone object to be compared with. + * @return True if the given TimeZone is not equal to this TimeZone; false + * otherwise. + * @stable ICU 2.0 + */ + UBool operator!=(const TimeZone& that) const {return !operator==(that);} + + /** + * Returns the TimeZone's adjusted GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time in this time zone, taking daylight savings time into + * account) as of a particular reference date. The reference date is used to determine + * whether daylight savings time is in effect and needs to be figured into the offset + * that is returned (in other words, what is the adjusted GMT offset in this time zone + * at this particular date and time?). For the time zones produced by createTimeZone(), + * the reference data is specified according to the Gregorian calendar, and the date + * and time fields are local standard time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, local standard time + * @param status Output param to filled in with a success or an error. + * @return The offset in milliseconds to add to GMT to get local time. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, UErrorCode& status) const = 0; + + /** + * Gets the time zone offset, for current date, modified in case of + * daylight savings. This is the offset to add *to* UTC to get local time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era the era of the given date. + * @param year the year in the given date. + * @param month the month in the given date. + * Month is 0-based. e.g., 0 for January. + * @param day the day-in-month of the given date. + * @param dayOfWeek the day-of-week of the given date. + * @param milliseconds the millis in day in <em>standard</em> local time. + * @param monthLength the length of the given month in days. + * @param status Output param to filled in with a success or an error. + * @return the offset to add *to* GMT to get local time. + * @stable ICU 2.0 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t milliseconds, + int32_t monthLength, UErrorCode& status) const = 0; + + /** + * Returns the time zone raw and GMT offset for the given moment + * in time. Upon return, local-millis = GMT-millis + rawOffset + + * dstOffset. All computations are performed in the proleptic + * Gregorian calendar. The default implementation in the TimeZone + * class delegates to the 8-argument getOffset(). + * + * @param date moment in time for which to return offsets, in + * units of milliseconds from January 1, 1970 0:00 GMT, either GMT + * time or local wall time, depending on `local'. + * @param local if true, `date' is local wall time; otherwise it + * is in GMT time. + * @param rawOffset output parameter to receive the raw offset, that + * is, the offset not including DST adjustments + * @param dstOffset output parameter to receive the DST offset, + * that is, the offset to be added to `rawOffset' to obtain the + * total offset between local and GMT time. If DST is not in + * effect, this value is zero; otherwise it is a positive value, + * typically one hour. + * @param ec input-output error code + * + * @stable ICU 2.8 + */ + virtual void getOffset(UDate date, UBool local, int32_t& rawOffset, + int32_t& dstOffset, UErrorCode& ec) const; + + /** + * Sets the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @param offsetMillis The new raw GMT offset for this time zone. + * @stable ICU 2.0 + */ + virtual void setRawOffset(int32_t offsetMillis) = 0; + + /** + * Returns the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @return The TimeZone's raw GMT offset. + * @stable ICU 2.0 + */ + virtual int32_t getRawOffset(void) const = 0; + + /** + * Fills in "ID" with the TimeZone's ID. + * + * @param ID Receives this TimeZone's ID. + * @return A reference to 'ID' + * @stable ICU 2.0 + */ + UnicodeString& getID(UnicodeString& ID) const; + + /** + * Sets the TimeZone's ID to the specified value. This doesn't affect any other + * fields (for example, if you say< + * blockquote><pre> + * . TimeZone* foo = TimeZone::createTimeZone("America/New_York"); + * . foo.setID("America/Los_Angeles"); + * </pre>\htmlonly</blockquote>\endhtmlonly + * the time zone's GMT offset and daylight-savings rules don't change to those for + * Los Angeles. They're still those for New York. Only the ID has changed.) + * + * @param ID The new timezone ID. + * @stable ICU 2.0 + */ + void setID(const UnicodeString& ID); + + /** + * Enum for use with getDisplayName + * @stable ICU 2.4 + */ + enum EDisplayType { + /** + * Selector for short display name + * @stable ICU 2.4 + */ + SHORT = 1, + /** + * Selector for long display name + * @stable ICU 2.4 + */ + LONG + }; + + /** + * Returns a name of this time zone suitable for presentation to the user + * in the default locale. + * This method returns the long name, not including daylight savings. + * If the display name is not available for the locale, + * then this method returns a string in the format + * <code>GMT[+-]hh:mm</code>. + * @param result the human-readable name of this time zone in the default locale. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName(UnicodeString& result) const; + + /** + * Returns a name of this time zone suitable for presentation to the user + * in the specified locale. + * This method returns the long name, not including daylight savings. + * If the display name is not available for the locale, + * then this method returns a string in the format + * <code>GMT[+-]hh:mm</code>. + * @param locale the locale in which to supply the display name. + * @param result the human-readable name of this time zone in the given locale + * or in the default locale if the given locale is not recognized. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName(const Locale& locale, UnicodeString& result) const; + + /** + * Returns a name of this time zone suitable for presentation to the user + * in the default locale. + * If the display name is not available for the locale, + * then this method returns a string in the format + * <code>GMT[+-]hh:mm</code>. + * @param daylight if true, return the daylight savings name. + * @param style either <code>LONG</code> or <code>SHORT</code> + * @param result the human-readable name of this time zone in the default locale. + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName(UBool daylight, EDisplayType style, UnicodeString& result) const; + + /** + * Returns a name of this time zone suitable for presentation to the user + * in the specified locale. + * If the display name is not available for the locale, + * then this method returns a string in the format + * <code>GMT[+-]hh:mm</code>. + * @param daylight if true, return the daylight savings name. + * @param style either <code>LONG</code> or <code>SHORT</code> + * @param locale the locale in which to supply the display name. + * @param result the human-readable name of this time zone in the given locale + * or in the default locale if the given locale is not recognized. + * @return A refence to 'result'. + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName(UBool daylight, EDisplayType style, const Locale& locale, UnicodeString& result) const; + + /** + * Queries if this time zone uses daylight savings time. + * @return true if this time zone uses daylight savings time, + * false, otherwise. + * @stable ICU 2.0 + */ + virtual UBool useDaylightTime(void) const = 0; + + /** + * Queries if the given date is in daylight savings time in + * this time zone. + * This method is wasteful since it creates a new GregorianCalendar and + * deletes it each time it is called. This is a deprecated method + * and provided only for Java compatibility. + * + * @param date the given UDate. + * @param status Output param filled in with success/error code. + * @return true if the given date is in daylight savings time, + * false, otherwise. + * @deprecated ICU 2.4. Use Calendar::inDaylightTime() instead. + */ + virtual UBool inDaylightTime(UDate date, UErrorCode& status) const = 0; + + /** + * Returns true if this zone has the same rule and offset as another zone. + * That is, if this zone differs only in ID, if at all. + * @param other the <code>TimeZone</code> object to be compared with + * @return true if the given zone is the same as this one, + * with the possible exception of the ID + * @stable ICU 2.0 + */ + virtual UBool hasSameRules(const TimeZone& other) const; + + /** + * Clones TimeZone objects polymorphically. Clients are responsible for deleting + * the TimeZone object cloned. + * + * @return A new copy of this TimeZone object. + * @stable ICU 2.0 + */ + virtual TimeZone* clone(void) const = 0; + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. This method is to + * implement a simple version of RTTI, since not all C++ compilers support genuine + * RTTI. Polymorphic operator==() and clone() methods call this method. + * <P> + * Concrete subclasses of TimeZone must use the UOBJECT_DEFINE_RTTI_IMPLEMENTATION + * macro from uobject.h in their implementation to provide correct RTTI information. + * @return The class ID for this object. All objects of a given class have the + * same class ID. Objects of other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Returns the amount of time to be added to local standard time + * to get local wall clock time. + * <p> + * The default implementation always returns 3600000 milliseconds + * (i.e., one hour) if this time zone observes Daylight Saving + * Time. Otherwise, 0 (zero) is returned. + * <p> + * If an underlying TimeZone implementation subclass supports + * historical Daylight Saving Time changes, this method returns + * the known latest daylight saving value. + * + * @return the amount of saving time in milliseconds + * @stable ICU 3.6 + */ + virtual int32_t getDSTSavings() const; + +protected: + + /** + * Default constructor. ID is initialized to the empty string. + * @stable ICU 2.0 + */ + TimeZone(); + + /** + * Construct a timezone with a given ID. + * @param id a system time zone ID + * @stable ICU 2.0 + */ + TimeZone(const UnicodeString &id); + + /** + * Copy constructor. + * @param source the object to be copied. + * @stable ICU 2.0 + */ + TimeZone(const TimeZone& source); + + /** + * Default assignment operator. + * @param right the object to be copied. + * @stable ICU 2.0 + */ + TimeZone& operator=(const TimeZone& right); + + /** + * Utility function. For internally loading rule data. + * @param top Top resource bundle for tz data + * @param ruleid ID of rule to load + * @param oldbundle Old bundle to reuse or NULL + * @param status Status parameter + * @return either a new bundle or *oldbundle + * @internal + */ + static UResourceBundle* loadRule(const UResourceBundle* top, const UnicodeString& ruleid, UResourceBundle* oldbundle, UErrorCode&status); + +private: + friend class ZoneMeta; + + /** + * Get a canonical Olson zone ID for the given ID. If the given ID is not valid, + * this method returns empty string as the result. If the given ID is a link, then the + * referenced ID (canonical ID) is returned. + */ + static UnicodeString& getOlsonCanonicalID(const UnicodeString &id, UnicodeString &canonical); + + static TimeZone* createCustomTimeZone(const UnicodeString&); // Creates a time zone based on the string. + + /** + * Responsible for setting up DEFAULT_ZONE. Uses routines in TPlatformUtilities + * (i.e., platform-specific calls) to get the current system time zone. Failing + * that, uses the platform-specific default time zone. Failing that, uses GMT. + */ + static void initDefault(void); + + // See source file for documentation + /** + * Lookup the given name in our system zone table. If found, + * instantiate a new zone of that name and return it. If not + * found, return 0. + * @param name tthe given name of a system time zone. + * @return the timezone indicated by the 'name'. + */ + static TimeZone* createSystemTimeZone(const UnicodeString& name); + + UnicodeString fID; // this time zone's ID +}; + + +// ------------------------------------- + +inline UnicodeString& +TimeZone::getID(UnicodeString& ID) const +{ + ID = fID; + return ID; +} + +// ------------------------------------- + +inline void +TimeZone::setID(const UnicodeString& ID) +{ + fID = ID; +} +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif //_TIMEZONE +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/translit.h b/Build/source/libs/icu-xetex/i18n/unicode/translit.h new file mode 100644 index 00000000000..1dcbb9a884d --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/translit.h @@ -0,0 +1,1323 @@ +/* +********************************************************************** +* Copyright (C) 1999-2007, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 11/17/99 aliu Creation. +********************************************************************** +*/ +#ifndef TRANSLIT_H +#define TRANSLIT_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Tranforms text from one format to another. + */ + +#if !UCONFIG_NO_TRANSLITERATION + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/parseerr.h" +#include "unicode/utrans.h" // UTransPosition, UTransDirection +#include "unicode/strenum.h" + +U_NAMESPACE_BEGIN + +class UnicodeFilter; +class UnicodeSet; +class CompoundTransliterator; +class TransliteratorParser; +class NormalizationTransliterator; +class TransliteratorIDParser; + +/** + * + * <code>Transliterator</code> is an abstract class that + * transliterates text from one format to another. The most common + * kind of transliterator is a script, or alphabet, transliterator. + * For example, a Russian to Latin transliterator changes Russian text + * written in Cyrillic characters to phonetically equivalent Latin + * characters. It does not <em>translate</em> Russian to English! + * Transliteration, unlike translation, operates on characters, without + * reference to the meanings of words and sentences. + * + * <p>Although script conversion is its most common use, a + * transliterator can actually perform a more general class of tasks. + * In fact, <code>Transliterator</code> defines a very general API + * which specifies only that a segment of the input text is replaced + * by new text. The particulars of this conversion are determined + * entirely by subclasses of <code>Transliterator</code>. + * + * <p><b>Transliterators are stateless</b> + * + * <p><code>Transliterator</code> objects are <em>stateless</em>; they + * retain no information between calls to + * <code>transliterate()</code>. (However, this does <em>not</em> + * mean that threads may share transliterators without synchronizing + * them. Transliterators are not immutable, so they must be + * synchronized when shared between threads.) This1 might seem to + * limit the complexity of the transliteration operation. In + * practice, subclasses perform complex transliterations by delaying + * the replacement of text until it is known that no other + * replacements are possible. In other words, although the + * <code>Transliterator</code> objects are stateless, the source text + * itself embodies all the needed information, and delayed operation + * allows arbitrary complexity. + * + * <p><b>Batch transliteration</b> + * + * <p>The simplest way to perform transliteration is all at once, on a + * string of existing text. This is referred to as <em>batch</em> + * transliteration. For example, given a string <code>input</code> + * and a transliterator <code>t</code>, the call + * + * \htmlonly<blockquote>\endhtmlonly<code>String result = t.transliterate(input); + * </code>\htmlonly</blockquote>\endhtmlonly + * + * will transliterate it and return the result. Other methods allow + * the client to specify a substring to be transliterated and to use + * {@link Replaceable } objects instead of strings, in order to + * preserve out-of-band information (such as text styles). + * + * <p><b>Keyboard transliteration</b> + * + * <p>Somewhat more involved is <em>keyboard</em>, or incremental + * transliteration. This is the transliteration of text that is + * arriving from some source (typically the user's keyboard) one + * character at a time, or in some other piecemeal fashion. + * + * <p>In keyboard transliteration, a <code>Replaceable</code> buffer + * stores the text. As text is inserted, as much as possible is + * transliterated on the fly. This means a GUI that displays the + * contents of the buffer may show text being modified as each new + * character arrives. + * + * <p>Consider the simple <code>RuleBasedTransliterator</code>: + * + * \htmlonly<blockquote>\endhtmlonly<code> + * th>{theta}<br> + * t>{tau} + * </code>\htmlonly</blockquote>\endhtmlonly + * + * When the user types 't', nothing will happen, since the + * transliterator is waiting to see if the next character is 'h'. To + * remedy this, we introduce the notion of a cursor, marked by a '|' + * in the output string: + * + * \htmlonly<blockquote>\endhtmlonly<code> + * t>|{tau}<br> + * {tau}h>{theta} + * </code>\htmlonly</blockquote>\endhtmlonly + * + * Now when the user types 't', tau appears, and if the next character + * is 'h', the tau changes to a theta. This is accomplished by + * maintaining a cursor position (independent of the insertion point, + * and invisible in the GUI) across calls to + * <code>transliterate()</code>. Typically, the cursor will + * be coincident with the insertion point, but in a case like the one + * above, it will precede the insertion point. + * + * <p>Keyboard transliteration methods maintain a set of three indices + * that are updated with each call to + * <code>transliterate()</code>, including the cursor, start, + * and limit. Since these indices are changed by the method, they are + * passed in an <code>int[]</code> array. The <code>START</code> index + * marks the beginning of the substring that the transliterator will + * look at. It is advanced as text becomes committed (but it is not + * the committed index; that's the <code>CURSOR</code>). The + * <code>CURSOR</code> index, described above, marks the point at + * which the transliterator last stopped, either because it reached + * the end, or because it required more characters to disambiguate + * between possible inputs. The <code>CURSOR</code> can also be + * explicitly set by rules in a <code>RuleBasedTransliterator</code>. + * Any characters before the <code>CURSOR</code> index are frozen; + * future keyboard transliteration calls within this input sequence + * will not change them. New text is inserted at the + * <code>LIMIT</code> index, which marks the end of the substring that + * the transliterator looks at. + * + * <p>Because keyboard transliteration assumes that more characters + * are to arrive, it is conservative in its operation. It only + * transliterates when it can do so unambiguously. Otherwise it waits + * for more characters to arrive. When the client code knows that no + * more characters are forthcoming, perhaps because the user has + * performed some input termination operation, then it should call + * <code>finishTransliteration()</code> to complete any + * pending transliterations. + * + * <p><b>Inverses</b> + * + * <p>Pairs of transliterators may be inverses of one another. For + * example, if transliterator <b>A</b> transliterates characters by + * incrementing their Unicode value (so "abc" -> "def"), and + * transliterator <b>B</b> decrements character values, then <b>A</b> + * is an inverse of <b>B</b> and vice versa. If we compose <b>A</b> + * with <b>B</b> in a compound transliterator, the result is the + * indentity transliterator, that is, a transliterator that does not + * change its input text. + * + * The <code>Transliterator</code> method <code>getInverse()</code> + * returns a transliterator's inverse, if one exists, or + * <code>null</code> otherwise. However, the result of + * <code>getInverse()</code> usually will <em>not</em> be a true + * mathematical inverse. This is because true inverse transliterators + * are difficult to formulate. For example, consider two + * transliterators: <b>AB</b>, which transliterates the character 'A' + * to 'B', and <b>BA</b>, which transliterates 'B' to 'A'. It might + * seem that these are exact inverses, since + * + * \htmlonly<blockquote>\endhtmlonly"A" x <b>AB</b> -> "B"<br> + * "B" x <b>BA</b> -> "A"\htmlonly</blockquote>\endhtmlonly + * + * where 'x' represents transliteration. However, + * + * \htmlonly<blockquote>\endhtmlonly"ABCD" x <b>AB</b> -> "BBCD"<br> + * "BBCD" x <b>BA</b> -> "AACD"\htmlonly</blockquote>\endhtmlonly + * + * so <b>AB</b> composed with <b>BA</b> is not the + * identity. Nonetheless, <b>BA</b> may be usefully considered to be + * <b>AB</b>'s inverse, and it is on this basis that + * <b>AB</b><code>.getInverse()</code> could legitimately return + * <b>BA</b>. + * + * <p><b>IDs and display names</b> + * + * <p>A transliterator is designated by a short identifier string or + * <em>ID</em>. IDs follow the format <em>source-destination</em>, + * where <em>source</em> describes the entity being replaced, and + * <em>destination</em> describes the entity replacing + * <em>source</em>. The entities may be the names of scripts, + * particular sequences of characters, or whatever else it is that the + * transliterator converts to or from. For example, a transliterator + * from Russian to Latin might be named "Russian-Latin". A + * transliterator from keyboard escape sequences to Latin-1 characters + * might be named "KeyboardEscape-Latin1". By convention, system + * entity names are in English, with the initial letters of words + * capitalized; user entity names may follow any format so long as + * they do not contain dashes. + * + * <p>In addition to programmatic IDs, transliterator objects have + * display names for presentation in user interfaces, returned by + * {@link #getDisplayName }. + * + * <p><b>Factory methods and registration</b> + * + * <p>In general, client code should use the factory method + * {@link #createInstance } to obtain an instance of a + * transliterator given its ID. Valid IDs may be enumerated using + * <code>getAvailableIDs()</code>. Since transliterators are mutable, + * multiple calls to {@link #createInstance } with the same ID will + * return distinct objects. + * + * <p>In addition to the system transliterators registered at startup, + * user transliterators may be registered by calling + * <code>registerInstance()</code> at run time. A registered instance + * acts a template; future calls to {@link #createInstance } with the ID + * of the registered object return clones of that object. Thus any + * object passed to <tt>registerInstance()</tt> must implement + * <tt>clone()</tt> propertly. To register a transliterator subclass + * without instantiating it (until it is needed), users may call + * {@link #registerFactory }. In this case, the objects are + * instantiated by invoking the zero-argument public constructor of + * the class. + * + * <p><b>Subclassing</b> + * + * Subclasses must implement the abstract method + * <code>handleTransliterate()</code>. <p>Subclasses should override + * the <code>transliterate()</code> method taking a + * <code>Replaceable</code> and the <code>transliterate()</code> + * method taking a <code>String</code> and <code>StringBuffer</code> + * if the performance of these methods can be improved over the + * performance obtained by the default implementations in this class. + * + * @author Alan Liu + * @stable ICU 2.0 + */ +class U_I18N_API Transliterator : public UObject { + +private: + + /** + * Programmatic name, e.g., "Latin-Arabic". + */ + UnicodeString ID; + + /** + * This transliterator's filter. Any character for which + * <tt>filter.contains()</tt> returns <tt>false</tt> will not be + * altered by this transliterator. If <tt>filter</tt> is + * <tt>null</tt> then no filtering is applied. + */ + UnicodeFilter* filter; + + int32_t maximumContextLength; + + public: + + /** + * A context integer or pointer for a factory function, passed by + * value. + * @stable ICU 2.4 + */ + union Token { + /** + * This token, interpreted as a 32-bit integer. + * @stable ICU 2.4 + */ + int32_t integer; + /** + * This token, interpreted as a native pointer. + * @stable ICU 2.4 + */ + void* pointer; + }; + + /** + * Return a token containing an integer. + * @return a token containing an integer. + * @internal + */ + inline static Token integerToken(int32_t); + + /** + * Return a token containing a pointer. + * @return a token containing a pointer. + * @internal + */ + inline static Token pointerToken(void*); + + /** + * A function that creates and returns a Transliterator. When + * invoked, it will be passed the ID string that is being + * instantiated, together with the context pointer that was passed + * in when the factory function was first registered. Many + * factory functions will ignore both parameters, however, + * functions that are registered to more than one ID may use the + * ID or the context parameter to parameterize the transliterator + * they create. + * @param ID the string identifier for this transliterator + * @param context a context pointer that will be stored and + * later passed to the factory function when an ID matching + * the registration ID is being instantiated with this factory. + * @stable ICU 2.4 + */ + typedef Transliterator* (U_EXPORT2 *Factory)(const UnicodeString& ID, Token context); + +protected: + + /** + * Default constructor. + * @param ID the string identifier for this transliterator + * @param adoptedFilter the filter. Any character for which + * <tt>filter.contains()</tt> returns <tt>false</tt> will not be + * altered by this transliterator. If <tt>filter</tt> is + * <tt>null</tt> then no filtering is applied. + * @stable ICU 2.4 + */ + Transliterator(const UnicodeString& ID, UnicodeFilter* adoptedFilter); + + /** + * Copy constructor. + * @stable ICU 2.4 + */ + Transliterator(const Transliterator&); + + /** + * Assignment operator. + * @stable ICU 2.4 + */ + Transliterator& operator=(const Transliterator&); + + /** + * Create a transliterator from a basic ID. This is an ID + * containing only the forward direction source, target, and + * variant. + * @param id a basic ID of the form S-T or S-T/V. + * @param canon canonical ID to assign to the object, or + * NULL to leave the ID unchanged + * @return a newly created Transliterator or null if the ID is + * invalid. + * @stable ICU 2.4 + */ + static Transliterator* createBasicInstance(const UnicodeString& id, + const UnicodeString* canon); + + friend class TransliteratorParser; // for parseID() + friend class TransliteratorIDParser; // for createBasicInstance() + friend class TransliteratorAlias; // for setID() + +public: + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~Transliterator(); + + /** + * Implements Cloneable. + * All subclasses are encouraged to implement this method if it is + * possible and reasonable to do so. Subclasses that are to be + * registered with the system using <tt>registerInstance()</tt> + * are required to implement this method. If a subclass does not + * implement clone() properly and is registered with the system + * using registerInstance(), then the default clone() implementation + * will return null, and calls to createInstance() will fail. + * + * @return a copy of the object. + * @see #registerInstance + * @stable ICU 2.0 + */ + virtual Transliterator* clone() const; + + /** + * Transliterates a segment of a string, with optional filtering. + * + * @param text the string to be transliterated + * @param start the beginning index, inclusive; <code>0 <= start + * <= limit</code>. + * @param limit the ending index, exclusive; <code>start <= limit + * <= text.length()</code>. + * @return The new limit index. The text previously occupying <code>[start, + * limit)</code> has been transliterated, possibly to a string of a different + * length, at <code>[start, </code><em>new-limit</em><code>)</code>, where + * <em>new-limit</em> is the return value. If the input offsets are out of bounds, + * the returned value is -1 and the input string remains unchanged. + * @stable ICU 2.0 + */ + virtual int32_t transliterate(Replaceable& text, + int32_t start, int32_t limit) const; + + /** + * Transliterates an entire string in place. Convenience method. + * @param text the string to be transliterated + * @stable ICU 2.0 + */ + virtual void transliterate(Replaceable& text) const; + + /** + * Transliterates the portion of the text buffer that can be + * transliterated unambiguosly after new text has been inserted, + * typically as a result of a keyboard event. The new text in + * <code>insertion</code> will be inserted into <code>text</code> + * at <code>index.limit</code>, advancing + * <code>index.limit</code> by <code>insertion.length()</code>. + * Then the transliterator will try to transliterate characters of + * <code>text</code> between <code>index.cursor</code> and + * <code>index.limit</code>. Characters before + * <code>index.cursor</code> will not be changed. + * + * <p>Upon return, values in <code>index</code> will be updated. + * <code>index.start</code> will be advanced to the first + * character that future calls to this method will read. + * <code>index.cursor</code> and <code>index.limit</code> will + * be adjusted to delimit the range of text that future calls to + * this method may change. + * + * <p>Typical usage of this method begins with an initial call + * with <code>index.start</code> and <code>index.limit</code> + * set to indicate the portion of <code>text</code> to be + * transliterated, and <code>index.cursor == index.start</code>. + * Thereafter, <code>index</code> can be used without + * modification in future calls, provided that all changes to + * <code>text</code> are made via this method. + * + * <p>This method assumes that future calls may be made that will + * insert new text into the buffer. As a result, it only performs + * unambiguous transliterations. After the last call to this + * method, there may be untransliterated text that is waiting for + * more input to resolve an ambiguity. In order to perform these + * pending transliterations, clients should call {@link + * #finishTransliteration } after the last call to this + * method has been made. + * + * @param text the buffer holding transliterated and untransliterated text + * @param index an array of three integers. + * + * <ul><li><code>index.start</code>: the beginning index, + * inclusive; <code>0 <= index.start <= index.limit</code>. + * + * <li><code>index.limit</code>: the ending index, exclusive; + * <code>index.start <= index.limit <= text.length()</code>. + * <code>insertion</code> is inserted at + * <code>index.limit</code>. + * + * <li><code>index.cursor</code>: the next character to be + * considered for transliteration; <code>index.start <= + * index.cursor <= index.limit</code>. Characters before + * <code>index.cursor</code> will not be changed by future calls + * to this method.</ul> + * + * @param insertion text to be inserted and possibly + * transliterated into the translation buffer at + * <code>index.limit</code>. If <code>null</code> then no text + * is inserted. + * @param status Output param to filled in with a success or an error. + * @see #handleTransliterate + * @exception IllegalArgumentException if <code>index</code> + * is invalid + * @see UTransPosition + * @stable ICU 2.0 + */ + virtual void transliterate(Replaceable& text, UTransPosition& index, + const UnicodeString& insertion, + UErrorCode& status) const; + + /** + * Transliterates the portion of the text buffer that can be + * transliterated unambiguosly after a new character has been + * inserted, typically as a result of a keyboard event. This is a + * convenience method; see {@link + * #transliterate(Replaceable&, UTransPosition&, const UnicodeString&, UErrorCode&) const} + * for details. + * @param text the buffer holding transliterated and + * untransliterated text + * @param index an array of three integers. See {@link + * #transliterate(Replaceable&, UTransPosition&, const UnicodeString&, UErrorCode&) const }. + * @param insertion text to be inserted and possibly + * transliterated into the translation buffer at + * <code>index.limit</code>. + * @param status Output param to filled in with a success or an error. + * @see #transliterate(Replaceable&, UTransPosition&, const UnicodeString&, UErrorCode&) const + * @stable ICU 2.0 + */ + virtual void transliterate(Replaceable& text, UTransPosition& index, + UChar32 insertion, + UErrorCode& status) const; + + /** + * Transliterates the portion of the text buffer that can be + * transliterated unambiguosly. This is a convenience method; see + * {@link + * #transliterate(Replaceable&, UTransPosition&, const UnicodeString&, UErrorCode&) const } + * for details. + * @param text the buffer holding transliterated and + * untransliterated text + * @param index an array of three integers. See {@link + * #transliterate(Replaceable&, UTransPosition&, const UnicodeString&, UErrorCode&) const }. + * @param status Output param to filled in with a success or an error. + * @see #transliterate(Replaceable, int[], String) + * @stable ICU 2.0 + */ + virtual void transliterate(Replaceable& text, UTransPosition& index, + UErrorCode& status) const; + + /** + * Finishes any pending transliterations that were waiting for + * more characters. Clients should call this method as the last + * call after a sequence of one or more calls to + * <code>transliterate()</code>. + * @param text the buffer holding transliterated and + * untransliterated text. + * @param index the array of indices previously passed to {@link + * #transliterate } + * @stable ICU 2.0 + */ + virtual void finishTransliteration(Replaceable& text, + UTransPosition& index) const; + +private: + + /** + * This internal method does incremental transliteration. If the + * 'insertion' is non-null then we append it to 'text' before + * proceeding. This method calls through to the pure virtual + * framework method handleTransliterate() to do the actual + * work. + * @param text the buffer holding transliterated and + * untransliterated text + * @param index an array of three integers. See {@link + * #transliterate(Replaceable, int[], String)}. + * @param insertion text to be inserted and possibly + * transliterated into the translation buffer at + * <code>index.limit</code>. + * @param status Output param to filled in with a success or an error. + */ + void _transliterate(Replaceable& text, + UTransPosition& index, + const UnicodeString* insertion, + UErrorCode &status) const; + +protected: + + /** + * Abstract method that concrete subclasses define to implement + * their transliteration algorithm. This method handles both + * incremental and non-incremental transliteration. Let + * <code>originalStart</code> refer to the value of + * <code>pos.start</code> upon entry. + * + * <ul> + * <li>If <code>incremental</code> is false, then this method + * should transliterate all characters between + * <code>pos.start</code> and <code>pos.limit</code>. Upon return + * <code>pos.start</code> must == <code> pos.limit</code>.</li> + * + * <li>If <code>incremental</code> is true, then this method + * should transliterate all characters between + * <code>pos.start</code> and <code>pos.limit</code> that can be + * unambiguously transliterated, regardless of future insertions + * of text at <code>pos.limit</code>. Upon return, + * <code>pos.start</code> should be in the range + * [<code>originalStart</code>, <code>pos.limit</code>). + * <code>pos.start</code> should be positioned such that + * characters [<code>originalStart</code>, <code> + * pos.start</code>) will not be changed in the future by this + * transliterator and characters [<code>pos.start</code>, + * <code>pos.limit</code>) are unchanged.</li> + * </ul> + * + * <p>Implementations of this method should also obey the + * following invariants:</p> + * + * <ul> + * <li> <code>pos.limit</code> and <code>pos.contextLimit</code> + * should be updated to reflect changes in length of the text + * between <code>pos.start</code> and <code>pos.limit</code>. The + * difference <code> pos.contextLimit - pos.limit</code> should + * not change.</li> + * + * <li><code>pos.contextStart</code> should not change.</li> + * + * <li>Upon return, neither <code>pos.start</code> nor + * <code>pos.limit</code> should be less than + * <code>originalStart</code>.</li> + * + * <li>Text before <code>originalStart</code> and text after + * <code>pos.limit</code> should not change.</li> + * + * <li>Text before <code>pos.contextStart</code> and text after + * <code> pos.contextLimit</code> should be ignored.</li> + * </ul> + * + * <p>Subclasses may safely assume that all characters in + * [<code>pos.start</code>, <code>pos.limit</code>) are filtered. + * In other words, the filter has already been applied by the time + * this method is called. See + * <code>filteredTransliterate()</code>. + * + * <p>This method is <b>not</b> for public consumption. Calling + * this method directly will transliterate + * [<code>pos.start</code>, <code>pos.limit</code>) without + * applying the filter. End user code should call <code> + * transliterate()</code> instead of this method. Subclass code + * and wrapping transliterators should call + * <code>filteredTransliterate()</code> instead of this method.<p> + * + * @param text the buffer holding transliterated and + * untransliterated text + * + * @param pos the indices indicating the start, limit, context + * start, and context limit of the text. + * + * @param incremental if true, assume more text may be inserted at + * <code>pos.limit</code> and act accordingly. Otherwise, + * transliterate all text between <code>pos.start</code> and + * <code>pos.limit</code> and move <code>pos.start</code> up to + * <code>pos.limit</code>. + * + * @see #transliterate + * @stable ICU 2.4 + */ + virtual void handleTransliterate(Replaceable& text, + UTransPosition& pos, + UBool incremental) const = 0; + +public: + /** + * Transliterate a substring of text, as specified by index, taking filters + * into account. This method is for subclasses that need to delegate to + * another transliterator, such as CompoundTransliterator. + * @param text the text to be transliterated + * @param index the position indices + * @param incremental if TRUE, then assume more characters may be inserted + * at index.limit, and postpone processing to accomodate future incoming + * characters + * @stable ICU 2.4 + */ + virtual void filteredTransliterate(Replaceable& text, + UTransPosition& index, + UBool incremental) const; + +private: + + /** + * Top-level transliteration method, handling filtering, incremental and + * non-incremental transliteration, and rollback. All transliteration + * public API methods eventually call this method with a rollback argument + * of TRUE. Other entities may call this method but rollback should be + * FALSE. + * + * <p>If this transliterator has a filter, break up the input text into runs + * of unfiltered characters. Pass each run to + * <subclass>.handleTransliterate(). + * + * <p>In incremental mode, if rollback is TRUE, perform a special + * incremental procedure in which several passes are made over the input + * text, adding one character at a time, and committing successful + * transliterations as they occur. Unsuccessful transliterations are rolled + * back and retried with additional characters to give correct results. + * + * @param text the text to be transliterated + * @param index the position indices + * @param incremental if TRUE, then assume more characters may be inserted + * at index.limit, and postpone processing to accomodate future incoming + * characters + * @param rollback if TRUE and if incremental is TRUE, then perform special + * incremental processing, as described above, and undo partial + * transliterations where necessary. If incremental is FALSE then this + * parameter is ignored. + */ + virtual void filteredTransliterate(Replaceable& text, + UTransPosition& index, + UBool incremental, + UBool rollback) const; + +public: + + /** + * Returns the length of the longest context required by this transliterator. + * This is <em>preceding</em> context. The default implementation supplied + * by <code>Transliterator</code> returns zero; subclasses + * that use preceding context should override this method to return the + * correct value. For example, if a transliterator translates "ddd" (where + * d is any digit) to "555" when preceded by "(ddd)", then the preceding + * context length is 5, the length of "(ddd)". + * + * @return The maximum number of preceding context characters this + * transliterator needs to examine + * @stable ICU 2.0 + */ + int32_t getMaximumContextLength(void) const; + +protected: + + /** + * Method for subclasses to use to set the maximum context length. + * @param maxContextLength the new value to be set. + * @see #getMaximumContextLength + * @stable ICU 2.4 + */ + void setMaximumContextLength(int32_t maxContextLength); + +public: + + /** + * Returns a programmatic identifier for this transliterator. + * If this identifier is passed to <code>createInstance()</code>, it + * will return this object, if it has been registered. + * @return a programmatic identifier for this transliterator. + * @see #registerInstance + * @see #registerFactory + * @see #getAvailableIDs + * @stable ICU 2.0 + */ + virtual const UnicodeString& getID(void) const; + + /** + * Returns a name for this transliterator that is appropriate for + * display to the user in the default locale. See {@link + * #getDisplayName } for details. + * @param ID the string identifier for this transliterator + * @param result Output param to receive the display name + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const UnicodeString& ID, + UnicodeString& result); + + /** + * Returns a name for this transliterator that is appropriate for + * display to the user in the given locale. This name is taken + * from the locale resource data in the standard manner of the + * <code>java.text</code> package. + * + * <p>If no localized names exist in the system resource bundles, + * a name is synthesized using a localized + * <code>MessageFormat</code> pattern from the resource data. The + * arguments to this pattern are an integer followed by one or two + * strings. The integer is the number of strings, either 1 or 2. + * The strings are formed by splitting the ID for this + * transliterator at the first '-'. If there is no '-', then the + * entire ID forms the only string. + * @param ID the string identifier for this transliterator + * @param inLocale the Locale in which the display name should be + * localized. + * @param result Output param to receive the display name + * @return A reference to 'result'. + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const UnicodeString& ID, + const Locale& inLocale, + UnicodeString& result); + + /** + * Returns the filter used by this transliterator, or <tt>NULL</tt> + * if this transliterator uses no filter. + * @return the filter used by this transliterator, or <tt>NULL</tt> + * if this transliterator uses no filter. + * @stable ICU 2.0 + */ + const UnicodeFilter* getFilter(void) const; + + /** + * Returns the filter used by this transliterator, or <tt>NULL</tt> if this + * transliterator uses no filter. The caller must eventually delete the + * result. After this call, this transliterator's filter is set to + * <tt>NULL</tt>. + * @return the filter used by this transliterator, or <tt>NULL</tt> if this + * transliterator uses no filter. + * @stable ICU 2.4 + */ + UnicodeFilter* orphanFilter(void); + + /** + * Changes the filter used by this transliterator. If the filter + * is set to <tt>null</tt> then no filtering will occur. + * + * <p>Callers must take care if a transliterator is in use by + * multiple threads. The filter should not be changed by one + * thread while another thread may be transliterating. + * @param adoptedFilter the new filter to be adopted. + * @stable ICU 2.0 + */ + void adoptFilter(UnicodeFilter* adoptedFilter); + + /** + * Returns this transliterator's inverse. See the class + * documentation for details. This implementation simply inverts + * the two entities in the ID and attempts to retrieve the + * resulting transliterator. That is, if <code>getID()</code> + * returns "A-B", then this method will return the result of + * <code>createInstance("B-A")</code>, or <code>null</code> if that + * call fails. + * + * <p>Subclasses with knowledge of their inverse may wish to + * override this method. + * + * @param status Output param to filled in with a success or an error. + * @return a transliterator that is an inverse, not necessarily + * exact, of this transliterator, or <code>null</code> if no such + * transliterator is registered. + * @see #registerInstance + * @stable ICU 2.0 + */ + Transliterator* createInverse(UErrorCode& status) const; + + /** + * Returns a <code>Transliterator</code> object given its ID. + * The ID must be either a system transliterator ID or a ID registered + * using <code>registerInstance()</code>. + * + * @param ID a valid ID, as enumerated by <code>getAvailableIDs()</code> + * @param dir either FORWARD or REVERSE. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param to filled in with a success or an error. + * @return A <code>Transliterator</code> object with the given ID + * @see #registerInstance + * @see #getAvailableIDs + * @see #getID + * @stable ICU 2.0 + */ + static Transliterator* U_EXPORT2 createInstance(const UnicodeString& ID, + UTransDirection dir, + UParseError& parseError, + UErrorCode& status); + + /** + * Returns a <code>Transliterator</code> object given its ID. + * The ID must be either a system transliterator ID or a ID registered + * using <code>registerInstance()</code>. + * @param ID a valid ID, as enumerated by <code>getAvailableIDs()</code> + * @param dir either FORWARD or REVERSE. + * @param status Output param to filled in with a success or an error. + * @return A <code>Transliterator</code> object with the given ID + * @stable ICU 2.0 + */ + static Transliterator* U_EXPORT2 createInstance(const UnicodeString& ID, + UTransDirection dir, + UErrorCode& status); + + /** + * Returns a <code>Transliterator</code> object constructed from + * the given rule string. This will be a RuleBasedTransliterator, + * if the rule string contains only rules, or a + * CompoundTransliterator, if it contains ID blocks, or a + * NullTransliterator, if it contains ID blocks which parse as + * empty for the given direction. + * @param ID the id for the transliterator. + * @param rules rules, separated by ';' + * @param dir either FORWARD or REVERSE. + * @param parseError Struct to recieve information on position + * of error if an error is encountered + * @param status Output param set to success/failure code. + * @stable ICU 2.0 + */ + static Transliterator* U_EXPORT2 createFromRules(const UnicodeString& ID, + const UnicodeString& rules, + UTransDirection dir, + UParseError& parseError, + UErrorCode& status); + + /** + * Create a rule string that can be passed to createFromRules() + * to recreate this transliterator. + * @param result the string to receive the rules. Previous + * contents will be deleted. + * @param escapeUnprintable if TRUE then convert unprintable + * character to their hex escape representations, \\uxxxx or + * \\Uxxxxxxxx. Unprintable characters are those other than + * U+000A, U+0020..U+007E. + * @stable ICU 2.0 + */ + virtual UnicodeString& toRules(UnicodeString& result, + UBool escapeUnprintable) const; + + /** + * Return the number of elements that make up this transliterator. + * For example, if the transliterator "NFD;Jamo-Latin;Latin-Greek" + * were created, the return value of this method would be 3. + * + * <p>If this transliterator is not composed of other + * transliterators, then this method returns 1. + * @return the number of transliterators that compose this + * transliterator, or 1 if this transliterator is not composed of + * multiple transliterators + * @stable ICU 3.0 + */ + int32_t countElements() const; + + /** + * Return an element that makes up this transliterator. For + * example, if the transliterator "NFD;Jamo-Latin;Latin-Greek" + * were created, the return value of this method would be one + * of the three transliterator objects that make up that + * transliterator: [NFD, Jamo-Latin, Latin-Greek]. + * + * <p>If this transliterator is not composed of other + * transliterators, then this method will return a reference to + * this transliterator when given the index 0. + * @param index a value from 0..countElements()-1 indicating the + * transliterator to return + * @param ec input-output error code + * @return one of the transliterators that makes up this + * transliterator, if this transliterator is made up of multiple + * transliterators, otherwise a reference to this object if given + * an index of 0 + * @stable ICU 3.0 + */ + const Transliterator& getElement(int32_t index, UErrorCode& ec) const; + + /** + * Returns the set of all characters that may be modified in the + * input text by this Transliterator. This incorporates this + * object's current filter; if the filter is changed, the return + * value of this function will change. The default implementation + * returns an empty set. Some subclasses may override {@link + * #handleGetSourceSet } to return a more precise result. The + * return result is approximate in any case and is intended for + * use by tests, tools, or utilities. + * @param result receives result set; previous contents lost + * @return a reference to result + * @see #getTargetSet + * @see #handleGetSourceSet + * @stable ICU 2.4 + */ + UnicodeSet& getSourceSet(UnicodeSet& result) const; + + /** + * Framework method that returns the set of all characters that + * may be modified in the input text by this Transliterator, + * ignoring the effect of this object's filter. The base class + * implementation returns the empty set. Subclasses that wish to + * implement this should override this method. + * @return the set of characters that this transliterator may + * modify. The set may be modified, so subclasses should return a + * newly-created object. + * @param result receives result set; previous contents lost + * @see #getSourceSet + * @see #getTargetSet + * @stable ICU 2.4 + */ + virtual void handleGetSourceSet(UnicodeSet& result) const; + + /** + * Returns the set of all characters that may be generated as + * replacement text by this transliterator. The default + * implementation returns the empty set. Some subclasses may + * override this method to return a more precise result. The + * return result is approximate in any case and is intended for + * use by tests, tools, or utilities requiring such + * meta-information. + * @param result receives result set; previous contents lost + * @return a reference to result + * @see #getTargetSet + * @stable ICU 2.4 + */ + virtual UnicodeSet& getTargetSet(UnicodeSet& result) const; + +public: + + /** + * Registers a factory function that creates transliterators of + * a given ID. + * @param id the ID being registered + * @param factory a function pointer that will be copied and + * called later when the given ID is passed to createInstance() + * @param context a context pointer that will be stored and + * later passed to the factory function when an ID matching + * the registration ID is being instantiated with this factory. + * @stable ICU 2.0 + */ + static void U_EXPORT2 registerFactory(const UnicodeString& id, + Factory factory, + Token context); + + /** + * Registers an instance <tt>obj</tt> of a subclass of + * <code>Transliterator</code> with the system. When + * <tt>createInstance()</tt> is called with an ID string that is + * equal to <tt>obj->getID()</tt>, then <tt>obj->clone()</tt> is + * returned. + * + * After this call the Transliterator class owns the adoptedObj + * and will delete it. + * + * @param adoptedObj an instance of subclass of + * <code>Transliterator</code> that defines <tt>clone()</tt> + * @see #createInstance + * @see #registerFactory + * @see #unregister + * @stable ICU 2.0 + */ + static void U_EXPORT2 registerInstance(Transliterator* adoptedObj); + + /** + * Registers an ID string as an alias of another ID string. + * That is, after calling this function, <tt>createInstance(aliasID)</tt> + * will return the same thing as <tt>createInstance(realID)</tt>. + * This is generally used to create shorter, more mnemonic aliases + * for long compound IDs. + * + * @param aliasID The new ID being registered. + * @param realID The ID that the new ID is to be an alias for. + * This can be a compound ID and can include filters and should + * refer to transliterators that have already been registered with + * the framework, although this isn't checked. + * @stable ICU 3.6 + */ + static void U_EXPORT2 registerAlias(const UnicodeString& aliasID, + const UnicodeString& realID); + +protected: + + /** + * @internal + * @param id the ID being registered + * @param factory a function pointer that will be copied and + * called later when the given ID is passed to createInstance() + * @param context a context pointer that will be stored and + * later passed to the factory function when an ID matching + * the registration ID is being instantiated with this factory. + */ + static void _registerFactory(const UnicodeString& id, + Factory factory, + Token context); + + /** + * @internal + */ + static void _registerInstance(Transliterator* adoptedObj); + + /** + * @internal + */ + static void _registerAlias(const UnicodeString& aliasID, const UnicodeString& realID); + + /** + * Register two targets as being inverses of one another. For + * example, calling registerSpecialInverse("NFC", "NFD", true) causes + * Transliterator to form the following inverse relationships: + * + * <pre>NFC => NFD + * Any-NFC => Any-NFD + * NFD => NFC + * Any-NFD => Any-NFC</pre> + * + * (Without the special inverse registration, the inverse of NFC + * would be NFC-Any.) Note that NFD is shorthand for Any-NFD, but + * that the presence or absence of "Any-" is preserved. + * + * <p>The relationship is symmetrical; registering (a, b) is + * equivalent to registering (b, a). + * + * <p>The relevant IDs must still be registered separately as + * factories or classes. + * + * <p>Only the targets are specified. Special inverses always + * have the form Any-Target1 <=> Any-Target2. The target should + * have canonical casing (the casing desired to be produced when + * an inverse is formed) and should contain no whitespace or other + * extraneous characters. + * + * @param target the target against which to register the inverse + * @param inverseTarget the inverse of target, that is + * Any-target.getInverse() => Any-inverseTarget + * @param bidirectional if true, register the reverse relation + * as well, that is, Any-inverseTarget.getInverse() => Any-target + * @internal + */ + static void _registerSpecialInverse(const UnicodeString& target, + const UnicodeString& inverseTarget, + UBool bidirectional); + +public: + + /** + * Unregisters a transliterator or class. This may be either + * a system transliterator or a user transliterator or class. + * Any attempt to construct an unregistered transliterator based + * on its ID will fail. + * + * @param ID the ID of the transliterator or class + * @return the <code>Object</code> that was registered with + * <code>ID</code>, or <code>null</code> if none was + * @see #registerInstance + * @see #registerFactory + * @stable ICU 2.0 + */ + static void U_EXPORT2 unregister(const UnicodeString& ID); + +public: + + /** + * Return a StringEnumeration over the IDs available at the time of the + * call, including user-registered IDs. + * @param ec input-output error code + * @return a newly-created StringEnumeration over the transliterators + * available at the time of the call. The caller should delete this object + * when done using it. + * @stable ICU 3.0 + */ + static StringEnumeration* U_EXPORT2 getAvailableIDs(UErrorCode& ec); + + /** + * Return the number of registered source specifiers. + * @return the number of registered source specifiers. + * @stable ICU 2.0 + */ + static int32_t U_EXPORT2 countAvailableSources(void); + + /** + * Return a registered source specifier. + * @param index which specifier to return, from 0 to n-1, where + * n = countAvailableSources() + * @param result fill-in paramter to receive the source specifier. + * If index is out of range, result will be empty. + * @return reference to result + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getAvailableSource(int32_t index, + UnicodeString& result); + + /** + * Return the number of registered target specifiers for a given + * source specifier. + * @param source the given source specifier. + * @return the number of registered target specifiers for a given + * source specifier. + * @stable ICU 2.0 + */ + static int32_t U_EXPORT2 countAvailableTargets(const UnicodeString& source); + + /** + * Return a registered target specifier for a given source. + * @param index which specifier to return, from 0 to n-1, where + * n = countAvailableTargets(source) + * @param source the source specifier + * @param result fill-in paramter to receive the target specifier. + * If source is invalid or if index is out of range, result will + * be empty. + * @return reference to result + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getAvailableTarget(int32_t index, + const UnicodeString& source, + UnicodeString& result); + + /** + * Return the number of registered variant specifiers for a given + * source-target pair. + * @param source the source specifiers. + * @param target the target specifiers. + * @stable ICU 2.0 + */ + static int32_t U_EXPORT2 countAvailableVariants(const UnicodeString& source, + const UnicodeString& target); + + /** + * Return a registered variant specifier for a given source-target + * pair. + * @param index which specifier to return, from 0 to n-1, where + * n = countAvailableVariants(source, target) + * @param source the source specifier + * @param target the target specifier + * @param result fill-in paramter to receive the variant + * specifier. If source is invalid or if target is invalid or if + * index is out of range, result will be empty. + * @return reference to result + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getAvailableVariant(int32_t index, + const UnicodeString& source, + const UnicodeString& target, + UnicodeString& result); + +protected: + + /** + * Non-mutexed internal method + * @internal + */ + static int32_t _countAvailableSources(void); + + /** + * Non-mutexed internal method + * @internal + */ + static UnicodeString& _getAvailableSource(int32_t index, + UnicodeString& result); + + /** + * Non-mutexed internal method + * @internal + */ + static int32_t _countAvailableTargets(const UnicodeString& source); + + /** + * Non-mutexed internal method + * @internal + */ + static UnicodeString& _getAvailableTarget(int32_t index, + const UnicodeString& source, + UnicodeString& result); + + /** + * Non-mutexed internal method + * @internal + */ + static int32_t _countAvailableVariants(const UnicodeString& source, + const UnicodeString& target); + + /** + * Non-mutexed internal method + * @internal + */ + static UnicodeString& _getAvailableVariant(int32_t index, + const UnicodeString& source, + const UnicodeString& target, + UnicodeString& result); + +protected: + + /** + * Set the ID of this transliterators. Subclasses shouldn't do + * this, unless the underlying script behavior has changed. + * @param id the new id t to be set. + * @stable ICU 2.4 + */ + void setID(const UnicodeString& id); + +public: + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). + * Note that Transliterator is an abstract base class, and therefor + * no fully constructed object will have a dynamic + * UCLassID that equals the UClassID returned from + * TRansliterator::getStaticClassID(). + * @return The class ID for class Transliterator. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID <b>polymorphically</b>. This method + * is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * <p>Concrete subclasses of Transliterator must use the + * UOBJECT_DEFINE_RTTI_IMPLEMENTATION macro from + * uobject.h to provide the RTTI functions. + * + * @return The class ID for this object. All objects of a given + * class have the same class ID. Objects of other classes have + * different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + +private: + static UBool initializeRegistry(void); + +public: + /** + * Return the number of IDs currently registered with the system. + * To retrieve the actual IDs, call getAvailableID(i) with + * i from 0 to countAvailableIDs() - 1. + * @return the number of IDs currently registered with the system. + * @obsolete ICU 3.4 use getAvailableIDs() instead + */ + static int32_t U_EXPORT2 countAvailableIDs(void); + + /** + * Return the index-th available ID. index must be between 0 + * and countAvailableIDs() - 1, inclusive. If index is out of + * range, the result of getAvailableID(0) is returned. + * @param index the given ID index. + * @return the index-th available ID. index must be between 0 + * and countAvailableIDs() - 1, inclusive. If index is out of + * range, the result of getAvailableID(0) is returned. + * @obsolete ICU 3.4 use getAvailableIDs() instead; this function + * is not thread safe, since it returns a reference to storage that + * may become invalid if another thread calls unregister + */ + static const UnicodeString& U_EXPORT2 getAvailableID(int32_t index); +}; + +inline int32_t Transliterator::getMaximumContextLength(void) const { + return maximumContextLength; +} + +inline void Transliterator::setID(const UnicodeString& id) { + ID = id; + // NUL-terminate the ID string, which is a non-aliased copy. + ID.append((UChar)0); + ID.truncate(ID.length()-1); +} + +inline Transliterator::Token Transliterator::integerToken(int32_t i) { + Token t; + t.integer = i; + return t; +} + +inline Transliterator::Token Transliterator::pointerToken(void* p) { + Token t; + t.pointer = p; + return t; +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_TRANSLITERATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/tzrule.h b/Build/source/libs/icu-xetex/i18n/unicode/tzrule.h new file mode 100644 index 00000000000..a0576ca87a3 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/tzrule.h @@ -0,0 +1,828 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef TZRULE_H +#define TZRULE_H + +/** + * \file + * \brief C++ API: Time zone rule classes + */ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/dtrule.h" + +U_NAMESPACE_BEGIN + +/** + * <code>TimeZoneRule</code> is a class representing a rule for time zone. + * <code>TimeZoneRule</code> has a set of time zone attributes, such as zone name, + * raw offset (UTC offset for standard time) and daylight saving time offset. + * + * @draft ICU 3.8 + */ +class U_I18N_API TimeZoneRule : public UObject { +public: + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~TimeZoneRule(); + + /** + * Clone this TimeZoneRule object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + virtual TimeZoneRule* clone(void) const = 0; + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZoneRule& that) const; + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZoneRule& that) const; + + /** + * Fills in "name" with the name of this time zone. + * @param name Receives the name of this time zone. + * @return A reference to "name" + * @draft ICU 3.8 + */ + UnicodeString& getName(UnicodeString& name) const; + + /** + * Gets the standard time offset. + * @return The standard time offset from UTC in milliseconds. + * @draft ICU 3.8 + */ + int32_t getRawOffset(void) const; + + /** + * Gets the amount of daylight saving delta time from the standard time. + * @return The amount of daylight saving offset used by this rule + * in milliseconds. + * @draft ICU 3.8 + */ + int32_t getDSTSavings(void) const; + + /** + * Returns if this rule represents the same rule and offsets as another. + * When two <code>TimeZoneRule</code> objects differ only its names, this method + * returns true. + * @param other The <code>TimeZoneRule</code> object to be compared with. + * @return true if the other <code>TimeZoneRule</code> is the same as this one. + * @draft ICU 3.8 + */ + virtual UBool isEquivalentTo(const TimeZoneRule& other) const; + + /** + * Gets the very first time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the very first time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFirstStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const = 0; + + /** + * Gets the final time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the final time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFinalStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const = 0; + + /** + * Gets the first time when this rule takes effect after the specified time. + * @param base The first start time after this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The first time when this rule takes effect after + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getNextStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const = 0; + + /** + * Gets the most recent time when this rule takes effect before the specified time. + * @param base The most recent time before this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The most recent time when this rule takes effect before + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getPreviousStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const = 0; + +protected: + + /** + * Constructs a <code>TimeZoneRule</code> with the name, the GMT offset of its + * standard time and the amount of daylight saving offset adjustment. + * @param name The time zone name. + * @param rawOffset The UTC offset of its standard time in milliseconds. + * @param dstSavings The amount of daylight saving offset adjustment in milliseconds. + * If this ia a rule for standard time, the value of this argument is 0. + * @draft ICU 3.8 + */ + TimeZoneRule(const UnicodeString& name, int32_t rawOffset, int32_t dstSavings); + + /** + * Copy constructor. + * @param source The TimeZoneRule object to be copied. + * @draft ICU 3.8 + */ + TimeZoneRule(const TimeZoneRule& source); + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + TimeZoneRule& operator=(const TimeZoneRule& right); + +private: + UnicodeString fName; // time name + int32_t fRawOffset; // UTC offset of the standard time in milliseconds + int32_t fDSTSavings; // DST saving amount in milliseconds +}; + +/** + * <code>InitialTimeZoneRule</code> represents a time zone rule + * representing a time zone effective from the beginning and + * has no actual start times. + * @draft ICU 3.8 + */ +class U_I18N_API InitialTimeZoneRule : public TimeZoneRule { +public: + /** + * Constructs an <code>InitialTimeZoneRule</code> with the name, the GMT offset of its + * standard time and the amount of daylight saving offset adjustment. + * @param name The time zone name. + * @param rawOffset The UTC offset of its standard time in milliseconds. + * @param dstSavings The amount of daylight saving offset adjustment in milliseconds. + * If this ia a rule for standard time, the value of this argument is 0. + * @draft ICU 3.8 + */ + InitialTimeZoneRule(const UnicodeString& name, int32_t rawOffset, int32_t dstSavings); + + /** + * Copy constructor. + * @param source The InitialTimeZoneRule object to be copied. + * @draft ICU 3.8 + */ + InitialTimeZoneRule(const InitialTimeZoneRule& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~InitialTimeZoneRule(); + + /** + * Clone this InitialTimeZoneRule object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + virtual InitialTimeZoneRule* clone(void) const; + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + InitialTimeZoneRule& operator=(const InitialTimeZoneRule& right); + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZoneRule& that) const; + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZoneRule& that) const; + + /** + * Gets the time when this rule takes effect in the given year. + * @param year The Gregorian year, with 0 == 1 BCE, -1 == 2 BCE, etc. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the start time in the year. + * @return true if this rule takes effect in the year and the result is set to + * "result". + * @draft ICU 3.8 + */ + UBool getStartInYear(int32_t year, int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Returns if this rule represents the same rule and offsets as another. + * When two <code>TimeZoneRule</code> objects differ only its names, this method + * returns true. + * @param that The <code>TimeZoneRule</code> object to be compared with. + * @return true if the other <code>TimeZoneRule</code> is equivalent to this one. + * @draft ICU 3.8 + */ + virtual UBool isEquivalentTo(const TimeZoneRule& that) const; + + /** + * Gets the very first time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the very first time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFirstStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the final time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the final time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFinalStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the first time when this rule takes effect after the specified time. + * @param base The first start time after this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The first time when this rule takes effect after + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getNextStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + + /** + * Gets the most recent time when this rule takes effect before the specified time. + * @param base The most recent time before this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The most recent time when this rule takes effect before + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getPreviousStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +/** + * <code>AnnualTimeZoneRule</code> is a class used for representing a time zone + * rule which takes effect annually. The calenday system used for the rule is + * is based on Gregorian calendar + * + * @draft ICU 3.8 + */ +class U_I18N_API AnnualTimeZoneRule : public TimeZoneRule { +public: + /** + * The constant representing the maximum year used for designating + * a rule is permanent. + */ + static const int32_t MAX_YEAR; + + /** + * Constructs a <code>AnnualTimeZoneRule</code> with the name, the GMT offset of its + * standard time, the amount of daylight saving offset adjustment, the annual start + * time rule and the start/until years. The input DateTimeRule is copied by this + * constructor, so the caller remains responsible for deleting the object. + * @param name The time zone name. + * @param rawOffset The GMT offset of its standard time in milliseconds. + * @param dstSavings The amount of daylight saving offset adjustment in + * milliseconds. If this ia a rule for standard time, + * the value of this argument is 0. + * @param dateTimeRule The start date/time rule repeated annually. + * @param startYear The first year when this rule takes effect. + * @param endYear The last year when this rule takes effect. If this + * rule is effective forever in future, specify MAX_YEAR. + * @draft ICU 3.8 + */ + AnnualTimeZoneRule(const UnicodeString& name, int32_t rawOffset, int32_t dstSavings, + const DateTimeRule& dateTimeRule, int32_t startYear, int32_t endYear); + + /** + * Constructs a <code>AnnualTimeZoneRule</code> with the name, the GMT offset of its + * standard time, the amount of daylight saving offset adjustment, the annual start + * time rule and the start/until years. The input DateTimeRule object is adopted + * by this object, therefore, the caller must not delete the object. + * @param name The time zone name. + * @param rawOffset The GMT offset of its standard time in milliseconds. + * @param dstSavings The amount of daylight saving offset adjustment in + * milliseconds. If this ia a rule for standard time, + * the value of this argument is 0. + * @param dateTimeRule The start date/time rule repeated annually. + * @param startYear The first year when this rule takes effect. + * @param endYear The last year when this rule takes effect. If this + * rule is effective forever in future, specify MAX_YEAR. + * @draft ICU 3.8 + */ + AnnualTimeZoneRule(const UnicodeString& name, int32_t rawOffset, int32_t dstSavings, + DateTimeRule* dateTimeRule, int32_t startYear, int32_t endYear); + + /** + * Copy constructor. + * @param source The AnnualTimeZoneRule object to be copied. + * @draft ICU 3.8 + */ + AnnualTimeZoneRule(const AnnualTimeZoneRule& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~AnnualTimeZoneRule(); + + /** + * Clone this AnnualTimeZoneRule object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + virtual AnnualTimeZoneRule* clone(void) const; + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + AnnualTimeZoneRule& operator=(const AnnualTimeZoneRule& right); + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZoneRule& that) const; + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZoneRule& that) const; + + /** + * Gets the start date/time rule used by this rule. + * @return The <code>AnnualDateTimeRule</code> which represents the start date/time + * rule used by this time zone rule. + * @draft ICU 3.8 + */ + const DateTimeRule* getRule(void) const; + + /** + * Gets the first year when this rule takes effect. + * @return The start year of this rule. The year is in Gregorian calendar + * with 0 == 1 BCE, -1 == 2 BCE, etc. + * @draft ICU 3.8 + */ + int32_t getStartYear(void) const; + + /** + * Gets the end year when this rule takes effect. + * @return The end year of this rule (inclusive). The year is in Gregorian calendar + * with 0 == 1 BCE, -1 == 2 BCE, etc. + * @draft ICU 3.8 + */ + int32_t getEndYear(void) const; + + /** + * Gets the time when this rule takes effect in the given year. + * @param year The Gregorian year, with 0 == 1 BCE, -1 == 2 BCE, etc. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the start time in the year. + * @return true if this rule takes effect in the year and the result is set to + * "result". + * @draft ICU 3.8 + */ + UBool getStartInYear(int32_t year, int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Returns if this rule represents the same rule and offsets as another. + * When two <code>TimeZoneRule</code> objects differ only its names, this method + * returns true. + * @param that The <code>TimeZoneRule</code> object to be compared with. + * @return true if the other <code>TimeZoneRule</code> is equivalent to this one. + * @draft ICU 3.8 + */ + virtual UBool isEquivalentTo(const TimeZoneRule& that) const; + + /** + * Gets the very first time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the very first time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFirstStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the final time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the final time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFinalStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the first time when this rule takes effect after the specified time. + * @param base The first start time after this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The first time when this rule takes effect after + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getNextStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + + /** + * Gets the most recent time when this rule takes effect before the specified time. + * @param base The most recent time before this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The most recent time when this rule takes effect before + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getPreviousStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + + +private: + DateTimeRule* fDateTimeRule; + int32_t fStartYear; + int32_t fEndYear; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +/** + * <code>TimeArrayTimeZoneRule</code> represents a time zone rule whose start times are + * defined by an array of milliseconds since the standard base time. + * + * @draft ICU 3.8 + */ +class U_I18N_API TimeArrayTimeZoneRule : public TimeZoneRule { +public: + /** + * Constructs a <code>TimeArrayTimeZoneRule</code> with the name, the GMT offset of its + * standard time, the amount of daylight saving offset adjustment and + * the array of times when this rule takes effect. + * @param name The time zone name. + * @param rawOffset The UTC offset of its standard time in milliseconds. + * @param dstSavings The amount of daylight saving offset adjustment in + * milliseconds. If this ia a rule for standard time, + * the value of this argument is 0. + * @param startTimes The array start times in milliseconds since the base time + * (January 1, 1970, 00:00:00). + * @param numStartTimes The number of elements in the parameter "startTimes" + * @param timeRuleType The time type of the start times, which is one of + * <code>DataTimeRule::WALL_TIME</code>, <code>STANDARD_TIME</code> + * and <code>UNIVERSAL_TIME</code>. + * @draft ICU 3.8 + */ + TimeArrayTimeZoneRule(const UnicodeString& name, int32_t rawOffset, int32_t dstSavings, + const UDate* startTimes, int32_t numStartTimes, DateTimeRule::TimeRuleType timeRuleType); + + /** + * Copy constructor. + * @param source The TimeArrayTimeZoneRule object to be copied. + * @draft ICU 3.8 + */ + TimeArrayTimeZoneRule(const TimeArrayTimeZoneRule& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~TimeArrayTimeZoneRule(); + + /** + * Clone this TimeArrayTimeZoneRule object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + virtual TimeArrayTimeZoneRule* clone(void) const; + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + TimeArrayTimeZoneRule& operator=(const TimeArrayTimeZoneRule& right); + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZoneRule& that) const; + + /** + * Return true if the given <code>TimeZoneRule</code> objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZoneRule</code> objects are semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZoneRule& that) const; + + /** + * Gets the time type of the start times used by this rule. The return value + * is either <code>DateTimeRule::WALL_TIME</code> or <code>STANDARD_TIME</code> + * or <code>UNIVERSAL_TIME</code>. + * + * @return The time type used of the start times used by this rule. + * @draft ICU 3.8 + */ + DateTimeRule::TimeRuleType getTimeType(void) const; + + /** + * Gets a start time at the index stored in this rule. + * @param index The index of start times + * @param result Receives the start time at the index + * @return true if the index is within the valid range and + * and the result is set. When false, the output + * parameger "result" is unchanged. + * @draft ICU 3.8 + */ + UBool getStartTimeAt(int32_t index, UDate& result) const; + + /** + * Returns the number of start times stored in this rule + * @return The number of start times. + * @draft ICU 3.8 + */ + int32_t countStartTimes(void) const; + + /** + * Returns if this rule represents the same rule and offsets as another. + * When two <code>TimeZoneRule</code> objects differ only its names, this method + * returns true. + * @param that The <code>TimeZoneRule</code> object to be compared with. + * @return true if the other <code>TimeZoneRule</code> is equivalent to this one. + * @draft ICU 3.8 + */ + virtual UBool isEquivalentTo(const TimeZoneRule& that) const; + + /** + * Gets the very first time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the very first time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFirstStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the final time when this rule takes effect. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param result Receives the final time when this rule takes effect. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getFinalStart(int32_t prevRawOffset, int32_t prevDSTSavings, UDate& result) const; + + /** + * Gets the first time when this rule takes effect after the specified time. + * @param base The first start time after this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The first time when this rule takes effect after + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getNextStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + + /** + * Gets the most recent time when this rule takes effect before the specified time. + * @param base The most recent time before this base time will be returned. + * @param prevRawOffset The standard time offset from UTC before this rule + * takes effect in milliseconds. + * @param prevDSTSavings The amount of daylight saving offset from the + * standard time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives The most recent time when this rule takes effect before + * the specified base time. + * @return true if the start time is available. When false is returned, output parameter + * "result" is unchanged. + * @draft ICU 3.8 + */ + virtual UBool getPreviousStart(UDate base, int32_t prevRawOffset, int32_t prevDSTSavings, + UBool inclusive, UDate& result) const; + + +private: + enum { TIMEARRAY_STACK_BUFFER_SIZE = 32 }; + UBool initStartTimes(const UDate source[], int32_t size, UErrorCode& ec); + UDate getUTC(UDate time, int32_t raw, int32_t dst) const; + + DateTimeRule::TimeRuleType fTimeRuleType; + int32_t fNumStartTimes; + UDate* fStartTimes; + UDate fLocalStartTimes[TIMEARRAY_STACK_BUFFER_SIZE]; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // TZRULE_H + +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/tztrans.h b/Build/source/libs/icu-xetex/i18n/unicode/tztrans.h new file mode 100644 index 00000000000..6c7b0215f03 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/tztrans.h @@ -0,0 +1,195 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef TZTRANS_H +#define TZTRANS_H + +/** + * \file + * \brief C++ API: Time zone transition + */ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN + +// Forward declaration +class TimeZoneRule; + +/** + * <code>TimeZoneTransition</code> is a class representing a time zone transition. + * An instance has a time of transition and rules for both before and after the transition. + * @draft ICU 3.8 + */ +class U_I18N_API TimeZoneTransition : public UObject { +public: + /** + * Constructs a <code>TimeZoneTransition</code> with the time and the rules before/after + * the transition. + * + * @param time The time of transition in milliseconds since the base time. + * @param from The time zone rule used before the transition. + * @param to The time zone rule used after the transition. + * @draft ICU 3.8 + */ + TimeZoneTransition(UDate time, const TimeZoneRule& from, const TimeZoneRule& to); + + /** + * Constructs an empty <code>TimeZoneTransition</code> + * @draft ICU 3.8 + */ + TimeZoneTransition(); + + /** + * Copy constructor. + * @param source The TimeZoneTransition object to be copied. + * @draft ICU 3.8 + */ + TimeZoneTransition(const TimeZoneTransition& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + ~TimeZoneTransition(); + + /** + * Clone this TimeZoneTransition object polymorphically. The caller owns the result and + * should delete it when done. + * @return A copy of the object. + * @draft ICU 3.8 + */ + TimeZoneTransition* clone(void) const; + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + TimeZoneTransition& operator=(const TimeZoneTransition& right); + + /** + * Return true if the given TimeZoneTransition objects are semantically equal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given TimeZoneTransition objects are semantically equal. + * @draft ICU 3.8 + */ + UBool operator==(const TimeZoneTransition& that) const; + + /** + * Return true if the given TimeZoneTransition objects are semantically unequal. Objects + * of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given TimeZoneTransition objects are semantically unequal. + * @draft ICU 3.8 + */ + UBool operator!=(const TimeZoneTransition& that) const; + + /** + * Returns the time of transition in milliseconds. + * @return The time of the transition in milliseconds since the 1970 Jan 1 epoch time. + * @draft ICU 3.8 + */ + UDate getTime(void) const; + + /** + * Sets the time of transition in milliseconds. + * @param time The time of the transition in milliseconds since the 1970 Jan 1 epoch time. + * @draft ICU 3.8 + */ + void setTime(UDate time); + + /** + * Returns the rule used before the transition. + * @return The time zone rule used after the transition. + * @draft ICU 3.8 + */ + const TimeZoneRule* getFrom(void) const; + + /** + * Sets the rule used before the transition. The caller remains + * responsible for deleting the <code>TimeZoneRule</code> object. + * @param from The time zone rule used before the transition. + * @draft ICU 3.8 + */ + void setFrom(const TimeZoneRule& from); + + /** + * Adopts the rule used before the transition. The caller must + * not delete the <code>TimeZoneRule</code> object passed in. + * @param from The time zone rule used before the transition. + * @draft ICU 3.8 + */ + void adoptFrom(TimeZoneRule* from); + + /** + * Sets the rule used after the transition. The caller remains + * responsible for deleting the <code>TimeZoneRule</code> object. + * @param to The time zone rule used after the transition. + * @draft ICU 3.8 + */ + void setTo(const TimeZoneRule& to); + + /** + * Adopts the rule used after the transition. The caller must + * not delete the <code>TimeZoneRule</code> object passed in. + * @param to The time zone rule used after the transition. + * @draft ICU 3.8 + */ + void adoptTo(TimeZoneRule* to); + + /** + * Returns the rule used after the transition. + * @return The time zone rule used after the transition. + * @draft ICU 3.8 + */ + const TimeZoneRule* getTo(void) const; + +private: + UDate fTime; + TimeZoneRule* fFrom; + TimeZoneRule* fTo; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // TZTRANS_H + +//eof diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ucal.h b/Build/source/libs/icu-xetex/i18n/unicode/ucal.h new file mode 100644 index 00000000000..43648f4c502 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ucal.h @@ -0,0 +1,1089 @@ +/* + ******************************************************************************* + * Copyright (C) 1996-2007, International Business Machines Corporation and + * others. All Rights Reserved. + ******************************************************************************* + */ + +#ifndef UCAL_H +#define UCAL_H + +#include "unicode/utypes.h" +#include "unicode/uenum.h" +#include "unicode/uloc.h" + +#if !UCONFIG_NO_FORMATTING + +/** + * \file + * \brief C API: Calendar + * + * <h2>Calendar C API</h2> + * + * UCalendar C API is used for converting between a <code>UDate</code> object + * and a set of integer fields such as <code>UCAL_YEAR</code>, <code>UCAL_MONTH</code>, + * <code>UCAL_DAY</code>, <code>UCAL_HOUR</code>, and so on. + * (A <code>UDate</code> object represents a specific instant in + * time with millisecond precision. See UDate + * for information about the <code>UDate</code> .) + * + * <p> + * Types of <code>UCalendar</code> interpret a <code>UDate</code> + * according to the rules of a specific calendar system. The U_STABLE + * provides the enum UCalendarType with UCAL_TRADITIONAL and + * UCAL_GREGORIAN. + * <p> + * Like other locale-sensitive C API, calendar API provides a + * function, <code>ucal_open()</code>, which returns a pointer to + * <code>UCalendar</code> whose time fields have been initialized + * with the current date and time. We need to specify the type of + * calendar to be opened and the timezoneId. + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * UCalendar *caldef; + * UChar *tzId; + * UErrorCode status; + * tzId=(UChar*)malloc(sizeof(UChar) * (strlen("PST") +1) ); + * u_uastrcpy(tzId, "PST"); + * caldef=ucal_open(tzID, u_strlen(tzID), NULL, UCAL_TRADITIONAL, &status); + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <p> + * A <code>UCalendar</code> object can produce all the time field values + * needed to implement the date-time formatting for a particular language + * and calendar style (for example, Japanese-Gregorian, Japanese-Traditional). + * + * <p> + * When computing a <code>UDate</code> from time fields, two special circumstances + * may arise: there may be insufficient information to compute the + * <code>UDate</code> (such as only year and month but no day in the month), + * or there may be inconsistent information (such as "Tuesday, July 15, 1996" + * -- July 15, 1996 is actually a Monday). + * + * <p> + * <strong>Insufficient information.</strong> The calendar will use default + * information to specify the missing fields. This may vary by calendar; for + * the Gregorian calendar, the default for a field is the same as that of the + * start of the epoch: i.e., UCAL_YEAR = 1970, UCAL_MONTH = JANUARY, UCAL_DATE = 1, etc. + * + * <p> + * <strong>Inconsistent information.</strong> If fields conflict, the calendar + * will give preference to fields set more recently. For example, when + * determining the day, the calendar will look for one of the following + * combinations of fields. The most recent combination, as determined by the + * most recently set single field, will be used. + * + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * UCAL_MONTH + UCAL_DAY_OF_MONTH + * UCAL_MONTH + UCAL_WEEK_OF_MONTH + UCAL_DAY_OF_WEEK + * UCAL_MONTH + UCAL_DAY_OF_WEEK_IN_MONTH + UCAL_DAY_OF_WEEK + * UCAL_DAY_OF_YEAR + * UCAL_DAY_OF_WEEK + UCAL_WEEK_OF_YEAR + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * For the time of day: + * + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * UCAL_HOUR_OF_DAY + * UCAL_AM_PM + UCAL_HOUR + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <p> + * <strong>Note:</strong> for some non-Gregorian calendars, different + * fields may be necessary for complete disambiguation. For example, a full + * specification of the historial Arabic astronomical calendar requires year, + * month, day-of-month <em>and</em> day-of-week in some cases. + * + * <p> + * <strong>Note:</strong> There are certain possible ambiguities in + * interpretation of certain singular times, which are resolved in the + * following ways: + * <ol> + * <li> 24:00:00 "belongs" to the following day. That is, + * 23:59 on Dec 31, 1969 < 24:00 on Jan 1, 1970 < 24:01:00 on Jan 1, 1970 + * + * <li> Although historically not precise, midnight also belongs to "am", + * and noon belongs to "pm", so on the same day, + * 12:00 am (midnight) < 12:01 am, and 12:00 pm (noon) < 12:01 pm + * </ol> + * + * <p> + * The date or time format strings are not part of the definition of a + * calendar, as those must be modifiable or overridable by the user at + * runtime. Use {@link DateFormat} + * to format dates. + * + * <p> + * <code>Calendar</code> provides an API for field "rolling", where fields + * can be incremented or decremented, but wrap around. For example, rolling the + * month up in the date <code>December 12, <b>1996</b></code> results in + * <code>January 12, <b>1996</b></code>. + * + * <p> + * <code>Calendar</code> also provides a date arithmetic function for + * adding the specified (signed) amount of time to a particular time field. + * For example, subtracting 5 days from the date <code>September 12, 1996</code> + * results in <code>September 7, 1996</code>. + * + * @stable ICU 2.0 + */ + +/** A calendar. + * For usage in C programs. + * @stable ICU 2.0 + */ +typedef void* UCalendar; + +/** Possible types of UCalendars + * @stable ICU 2.0 + */ +enum UCalendarType { + /** A traditional calendar for the locale */ + UCAL_TRADITIONAL, + /** The Gregorian calendar */ + UCAL_GREGORIAN +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarType UCalendarType; + +/** Possible fields in a UCalendar + * @stable ICU 2.0 + */ +enum UCalendarDateFields { + /** + * Field number indicating the era, e.g., AD or BC in the Gregorian (Julian) calendar. + * This is a calendar-specific value. + * @stable ICU 2.6 + */ + UCAL_ERA, + + /** + * Field number indicating the year. This is a calendar-specific value. + * @stable ICU 2.6 + */ + UCAL_YEAR, + + /** + * Field number indicating the month. This is a calendar-specific value. + * The first month of the year is + * <code>JANUARY</code>; the last depends on the number of months in a year. + * @see #UCAL_JANUARY + * @see #UCAL_FEBRUARY + * @see #UCAL_MARCH + * @see #UCAL_APRIL + * @see #UCAL_MAY + * @see #UCAL_JUNE + * @see #UCAL_JULY + * @see #UCAL_AUGUST + * @see #UCAL_SEPTEMBER + * @see #UCAL_OCTOBER + * @see #UCAL_NOVEMBER + * @see #UCAL_DECEMBER + * @see #UCAL_UNDECIMBER + * @stable ICU 2.6 + */ + UCAL_MONTH, + + /** + * Field number indicating the + * week number within the current year. The first week of the year, as + * defined by <code>UCAL_FIRST_DAY_OF_WEEK</code> and <code>UCAL_MINIMAL_DAYS_IN_FIRST_WEEK</code> + * attributes, has value 1. Subclasses define + * the value of <code>UCAL_WEEK_OF_YEAR</code> for days before the first week of + * the year. + * @see ucal_getAttribute + * @see ucal_setAttribute + * @stable ICU 2.6 + */ + UCAL_WEEK_OF_YEAR, + + /** + * Field number indicating the + * week number within the current month. The first week of the month, as + * defined by <code>UCAL_FIRST_DAY_OF_WEEK</code> and <code>UCAL_MINIMAL_DAYS_IN_FIRST_WEEK</code> + * attributes, has value 1. Subclasses define + * the value of <code>WEEK_OF_MONTH</code> for days before the first week of + * the month. + * @see ucal_getAttribute + * @see ucal_setAttribute + * @see #UCAL_FIRST_DAY_OF_WEEK + * @see #UCAL_MINIMAL_DAYS_IN_FIRST_WEEK + * @stable ICU 2.6 + */ + UCAL_WEEK_OF_MONTH, + + /** + * Field number indicating the + * day of the month. This is a synonym for <code>DAY_OF_MONTH</code>. + * The first day of the month has value 1. + * @see #UCAL_DAY_OF_MONTH + * @stable ICU 2.6 + */ + UCAL_DATE, + + /** + * Field number indicating the day + * number within the current year. The first day of the year has value 1. + * @stable ICU 2.6 + */ + UCAL_DAY_OF_YEAR, + + /** + * Field number indicating the day + * of the week. This field takes values <code>SUNDAY</code>, + * <code>MONDAY</code>, <code>TUESDAY</code>, <code>WEDNESDAY</code>, + * <code>THURSDAY</code>, <code>FRIDAY</code>, and <code>SATURDAY</code>. + * @see #UCAL_SUNDAY + * @see #UCAL_MONDAY + * @see #UCAL_TUESDAY + * @see #UCAL_WEDNESDAY + * @see #UCAL_THURSDAY + * @see #UCAL_FRIDAY + * @see #UCAL_SATURDAY + * @stable ICU 2.6 + */ + UCAL_DAY_OF_WEEK, + + /** + * Field number indicating the + * ordinal number of the day of the week within the current month. Together + * with the <code>DAY_OF_WEEK</code> field, this uniquely specifies a day + * within a month. Unlike <code>WEEK_OF_MONTH</code> and + * <code>WEEK_OF_YEAR</code>, this field's value does <em>not</em> depend on + * <code>getFirstDayOfWeek()</code> or + * <code>getMinimalDaysInFirstWeek()</code>. <code>DAY_OF_MONTH 1</code> + * through <code>7</code> always correspond to <code>DAY_OF_WEEK_IN_MONTH + * 1</code>; <code>8</code> through <code>15</code> correspond to + * <code>DAY_OF_WEEK_IN_MONTH 2</code>, and so on. + * <code>DAY_OF_WEEK_IN_MONTH 0</code> indicates the week before + * <code>DAY_OF_WEEK_IN_MONTH 1</code>. Negative values count back from the + * end of the month, so the last Sunday of a month is specified as + * <code>DAY_OF_WEEK = SUNDAY, DAY_OF_WEEK_IN_MONTH = -1</code>. Because + * negative values count backward they will usually be aligned differently + * within the month than positive values. For example, if a month has 31 + * days, <code>DAY_OF_WEEK_IN_MONTH -1</code> will overlap + * <code>DAY_OF_WEEK_IN_MONTH 5</code> and the end of <code>4</code>. + * @see #UCAL_DAY_OF_WEEK + * @see #UCAL_WEEK_OF_MONTH + * @stable ICU 2.6 + */ + UCAL_DAY_OF_WEEK_IN_MONTH, + + /** + * Field number indicating + * whether the <code>HOUR</code> is before or after noon. + * E.g., at 10:04:15.250 PM the <code>AM_PM</code> is <code>PM</code>. + * @see #UCAL_AM + * @see #UCAL_PM + * @see #UCAL_HOUR + * @stable ICU 2.6 + */ + UCAL_AM_PM, + + /** + * Field number indicating the + * hour of the morning or afternoon. <code>HOUR</code> is used for the 12-hour + * clock. + * E.g., at 10:04:15.250 PM the <code>HOUR</code> is 10. + * @see #UCAL_AM_PM + * @see #UCAL_HOUR_OF_DAY + * @stable ICU 2.6 + */ + UCAL_HOUR, + + /** + * Field number indicating the + * hour of the day. <code>HOUR_OF_DAY</code> is used for the 24-hour clock. + * E.g., at 10:04:15.250 PM the <code>HOUR_OF_DAY</code> is 22. + * @see #UCAL_HOUR + * @stable ICU 2.6 + */ + UCAL_HOUR_OF_DAY, + + /** + * Field number indicating the + * minute within the hour. + * E.g., at 10:04:15.250 PM the <code>UCAL_MINUTE</code> is 4. + * @stable ICU 2.6 + */ + UCAL_MINUTE, + + /** + * Field number indicating the + * second within the minute. + * E.g., at 10:04:15.250 PM the <code>UCAL_SECOND</code> is 15. + * @stable ICU 2.6 + */ + UCAL_SECOND, + + /** + * Field number indicating the + * millisecond within the second. + * E.g., at 10:04:15.250 PM the <code>UCAL_MILLISECOND</code> is 250. + * @stable ICU 2.6 + */ + UCAL_MILLISECOND, + + /** + * Field number indicating the + * raw offset from GMT in milliseconds. + * @stable ICU 2.6 + */ + UCAL_ZONE_OFFSET, + + /** + * Field number indicating the + * daylight savings offset in milliseconds. + * @stable ICU 2.6 + */ + UCAL_DST_OFFSET, + + /** + * Field number + * indicating the extended year corresponding to the + * <code>UCAL_WEEK_OF_YEAR</code> field. This may be one greater or less + * than the value of <code>UCAL_EXTENDED_YEAR</code>. + * @stable ICU 2.6 + */ + UCAL_YEAR_WOY, + + /** + * Field number + * indicating the localized day of week. This will be a value from 1 + * to 7 inclusive, with 1 being the localized first day of the week. + * @stable ICU 2.6 + */ + UCAL_DOW_LOCAL, + + /** + * Year of this calendar system, encompassing all supra-year fields. For example, + * in Gregorian/Julian calendars, positive Extended Year values indicate years AD, + * 1 BC = 0 extended, 2 BC = -1 extended, and so on. + * @stable ICU 2.8 + */ + UCAL_EXTENDED_YEAR, + + /** + * Field number + * indicating the modified Julian day number. This is different from + * the conventional Julian day number in two regards. First, it + * demarcates days at local zone midnight, rather than noon GMT. + * Second, it is a local number; that is, it depends on the local time + * zone. It can be thought of as a single number that encompasses all + * the date-related fields. + * @stable ICU 2.8 + */ + UCAL_JULIAN_DAY, + + /** + * Ranges from 0 to 23:59:59.999 (regardless of DST). This field behaves <em>exactly</em> + * like a composite of all time-related fields, not including the zone fields. As such, + * it also reflects discontinuities of those fields on DST transition days. On a day + * of DST onset, it will jump forward. On a day of DST cessation, it will jump + * backward. This reflects the fact that it must be combined with the DST_OFFSET field + * to obtain a unique local time value. + * @stable ICU 2.8 + */ + UCAL_MILLISECONDS_IN_DAY, + + /** + * Field count + * @stable ICU 2.6 + */ + UCAL_FIELD_COUNT, + + /** + * Field number indicating the + * day of the month. This is a synonym for <code>UCAL_DATE</code>. + * The first day of the month has value 1. + * @see #UCAL_DATE + * Synonym for UCAL_DATE + * @stable ICU 2.8 + **/ + UCAL_DAY_OF_MONTH=UCAL_DATE +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarDateFields UCalendarDateFields; + /** + * Useful constant for days of week. Note: Calendar day-of-week is 1-based. Clients + * who create locale resources for the field of first-day-of-week should be aware of + * this. For instance, in US locale, first-day-of-week is set to 1, i.e., UCAL_SUNDAY. + */ +/** Possible days of the week in a UCalendar + * @stable ICU 2.0 + */ +enum UCalendarDaysOfWeek { + /** Sunday */ + UCAL_SUNDAY = 1, + /** Monday */ + UCAL_MONDAY, + /** Tuesday */ + UCAL_TUESDAY, + /** Wednesday */ + UCAL_WEDNESDAY, + /** Thursday */ + UCAL_THURSDAY, + /** Friday */ + UCAL_FRIDAY, + /** Saturday */ + UCAL_SATURDAY +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarDaysOfWeek UCalendarDaysOfWeek; + +/** Possible months in a UCalendar. Note: Calendar month is 0-based. + * @stable ICU 2.0 + */ +enum UCalendarMonths { + /** January */ + UCAL_JANUARY, + /** February */ + UCAL_FEBRUARY, + /** March */ + UCAL_MARCH, + /** April */ + UCAL_APRIL, + /** May */ + UCAL_MAY, + /** June */ + UCAL_JUNE, + /** July */ + UCAL_JULY, + /** August */ + UCAL_AUGUST, + /** September */ + UCAL_SEPTEMBER, + /** October */ + UCAL_OCTOBER, + /** November */ + UCAL_NOVEMBER, + /** December */ + UCAL_DECEMBER, + /** Value of the <code>UCAL_MONTH</code> field indicating the + * thirteenth month of the year. Although the Gregorian calendar + * does not use this value, lunar calendars do. + */ + UCAL_UNDECIMBER +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarMonths UCalendarMonths; + +/** Possible AM/PM values in a UCalendar + * @stable ICU 2.0 + */ +enum UCalendarAMPMs { + /** AM */ + UCAL_AM, + /** PM */ + UCAL_PM +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarAMPMs UCalendarAMPMs; + +/** + * Create an enumeration over all time zones. + * + * @param ec input/output error code + * + * @return an enumeration object that the caller must dispose of using + * uenum_close(), or NULL upon failure. In case of failure *ec will + * indicate the error. + * + * @stable ICU 2.6 + */ +U_STABLE UEnumeration* U_EXPORT2 +ucal_openTimeZones(UErrorCode* ec); + +/** + * Create an enumeration over all time zones associated with the given + * country. Some zones are affiliated with no country (e.g., "UTC"); + * these may also be retrieved, as a group. + * + * @param country the ISO 3166 two-letter country code, or NULL to + * retrieve zones not affiliated with any country + * + * @param ec input/output error code + * + * @return an enumeration object that the caller must dispose of using + * uenum_close(), or NULL upon failure. In case of failure *ec will + * indicate the error. + * + * @stable ICU 2.6 + */ +U_STABLE UEnumeration* U_EXPORT2 +ucal_openCountryTimeZones(const char* country, UErrorCode* ec); + +/** + * Return the default time zone. The default is determined initially + * by querying the host operating system. It may be changed with + * ucal_setDefaultTimeZone() or with the C++ TimeZone API. + * + * @param result A buffer to receive the result, or NULL + * + * @param resultCapacity The capacity of the result buffer + * + * @param ec input/output error code + * + * @return The result string length, not including the terminating + * null + * + * @stable ICU 2.6 + */ +U_STABLE int32_t U_EXPORT2 +ucal_getDefaultTimeZone(UChar* result, int32_t resultCapacity, UErrorCode* ec); + +/** + * Set the default time zone. + * + * @param zoneID null-terminated time zone ID + * + * @param ec input/output error code + * + * @stable ICU 2.6 + */ +U_STABLE void U_EXPORT2 +ucal_setDefaultTimeZone(const UChar* zoneID, UErrorCode* ec); + +/** + * Return the amount of time in milliseconds that the clock is + * advanced during daylight savings time for the given time zone, or + * zero if the time zone does not observe daylight savings time. + * + * @param zoneID null-terminated time zone ID + * + * @param ec input/output error code + * + * @return the number of milliseconds the time is advanced with + * respect to standard time when the daylight savings rules are in + * effect. This is always a non-negative number, most commonly either + * 3,600,000 (one hour) or zero. + * + * @stable ICU 2.6 + */ +U_STABLE int32_t U_EXPORT2 +ucal_getDSTSavings(const UChar* zoneID, UErrorCode* ec); + +/** + * Get the current date and time. + * The value returned is represented as milliseconds from the epoch. + * @return The current date and time. + * @stable ICU 2.0 + */ +U_STABLE UDate U_EXPORT2 +ucal_getNow(void); + +/** + * Open a UCalendar. + * A UCalendar may be used to convert a millisecond value to a year, + * month, and day. + * @param zoneID The desired TimeZone ID. If 0, use the default time zone. + * @param len The length of zoneID, or -1 if null-terminated. + * @param locale The desired locale + * @param type The type of UCalendar to open. + * @param status A pointer to an UErrorCode to receive any errors + * @return A pointer to a UCalendar, or 0 if an error occurred. + * @stable ICU 2.0 + */ +U_STABLE UCalendar* U_EXPORT2 +ucal_open(const UChar* zoneID, + int32_t len, + const char* locale, + UCalendarType type, + UErrorCode* status); + +/** + * Close a UCalendar. + * Once closed, a UCalendar may no longer be used. + * @param cal The UCalendar to close. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_close(UCalendar *cal); + +/** + * Set the TimeZone used by a UCalendar. + * A UCalendar uses a timezone for converting from Greenwich time to local time. + * @param cal The UCalendar to set. + * @param zoneID The desired TimeZone ID. If 0, use the default time zone. + * @param len The length of zoneID, or -1 if null-terminated. + * @param status A pointer to an UErrorCode to receive any errors. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_setTimeZone(UCalendar* cal, + const UChar* zoneID, + int32_t len, + UErrorCode* status); + +/** + * Possible formats for a UCalendar's display name + * @stable ICU 2.0 + */ +enum UCalendarDisplayNameType { + /** Standard display name */ + UCAL_STANDARD, + /** Short standard display name */ + UCAL_SHORT_STANDARD, + /** Daylight savings display name */ + UCAL_DST, + /** Short daylight savings display name */ + UCAL_SHORT_DST +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarDisplayNameType UCalendarDisplayNameType; + +/** + * Get the display name for a UCalendar's TimeZone. + * A display name is suitable for presentation to a user. + * @param cal The UCalendar to query. + * @param type The desired display name format; one of UCAL_STANDARD, UCAL_SHORT_STANDARD, + * UCAL_DST, UCAL_SHORT_DST + * @param locale The desired locale for the display name. + * @param result A pointer to a buffer to receive the formatted number. + * @param resultLength The maximum size of result. + * @param status A pointer to an UErrorCode to receive any errors + * @return The total buffer size needed; if greater than resultLength, the output was truncated. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucal_getTimeZoneDisplayName(const UCalendar* cal, + UCalendarDisplayNameType type, + const char* locale, + UChar* result, + int32_t resultLength, + UErrorCode* status); + +/** + * Determine if a UCalendar is currently in daylight savings time. + * Daylight savings time is not used in all parts of the world. + * @param cal The UCalendar to query. + * @param status A pointer to an UErrorCode to receive any errors + * @return TRUE if cal is currently in daylight savings time, FALSE otherwise + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucal_inDaylightTime(const UCalendar* cal, + UErrorCode* status ); + +/** + * Sets the GregorianCalendar change date. This is the point when the switch from + * Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October + * 15, 1582. Previous to this time and date will be Julian dates. + * + * This function works only for Gregorian calendars. If the UCalendar is not + * an instance of a Gregorian calendar, then a U_UNSUPPORTED_ERROR + * error code is set. + * + * @param cal The calendar object. + * @param date The given Gregorian cutover date. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * + * @see GregorianCalendar::setGregorianChange + * @see ucal_getGregorianChange + * @stable ICU 3.6 + */ +U_STABLE void U_EXPORT2 +ucal_setGregorianChange(UCalendar *cal, UDate date, UErrorCode *pErrorCode); + +/** + * Gets the Gregorian Calendar change date. This is the point when the switch from + * Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October + * 15, 1582. Previous to this time and date will be Julian dates. + * + * This function works only for Gregorian calendars. If the UCalendar is not + * an instance of a Gregorian calendar, then a U_UNSUPPORTED_ERROR + * error code is set. + * + * @param cal The calendar object. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The Gregorian cutover time for this calendar. + * + * @see GregorianCalendar::getGregorianChange + * @see ucal_setGregorianChange + * @stable ICU 3.6 + */ +U_STABLE UDate U_EXPORT2 +ucal_getGregorianChange(const UCalendar *cal, UErrorCode *pErrorCode); + +/** + * Types of UCalendar attributes + * @stable ICU 2.0 + */ +enum UCalendarAttribute { + /** Lenient parsing */ + UCAL_LENIENT, + /** First day of week */ + UCAL_FIRST_DAY_OF_WEEK, + /** Minimum number of days in first week */ + UCAL_MINIMAL_DAYS_IN_FIRST_WEEK +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarAttribute UCalendarAttribute; + +/** + * Get a numeric attribute associated with a UCalendar. + * Numeric attributes include the first day of the week, or the minimal numbers + * of days in the first week of the month. + * @param cal The UCalendar to query. + * @param attr The desired attribute; one of UCAL_LENIENT, UCAL_FIRST_DAY_OF_WEEK, + * or UCAL_MINIMAL_DAYS_IN_FIRST_WEEK + * @return The value of attr. + * @see ucal_setAttribute + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucal_getAttribute(const UCalendar* cal, + UCalendarAttribute attr); + +/** + * Set a numeric attribute associated with a UCalendar. + * Numeric attributes include the first day of the week, or the minimal numbers + * of days in the first week of the month. + * @param cal The UCalendar to set. + * @param attr The desired attribute; one of UCAL_LENIENT, UCAL_FIRST_DAY_OF_WEEK, + * or UCAL_MINIMAL_DAYS_IN_FIRST_WEEK + * @param newValue The new value of attr. + * @see ucal_getAttribute + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_setAttribute(UCalendar* cal, + UCalendarAttribute attr, + int32_t newValue); + +/** + * Get a locale for which calendars are available. + * A UCalendar in a locale returned by this function will contain the correct + * day and month names for the locale. + * @param index The index of the desired locale. + * @return A locale for which calendars are available, or 0 if none. + * @see ucal_countAvailable + * @stable ICU 2.0 + */ +U_STABLE const char* U_EXPORT2 +ucal_getAvailable(int32_t index); + +/** + * Determine how many locales have calendars available. + * This function is most useful as determining the loop ending condition for + * calls to \ref ucal_getAvailable. + * @return The number of locales for which calendars are available. + * @see ucal_getAvailable + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucal_countAvailable(void); + +/** + * Get a UCalendar's current time in millis. + * The time is represented as milliseconds from the epoch. + * @param cal The UCalendar to query. + * @param status A pointer to an UErrorCode to receive any errors + * @return The calendar's current time in millis. + * @see ucal_setMillis + * @see ucal_setDate + * @see ucal_setDateTime + * @stable ICU 2.0 + */ +U_STABLE UDate U_EXPORT2 +ucal_getMillis(const UCalendar* cal, + UErrorCode* status); + +/** + * Set a UCalendar's current time in millis. + * The time is represented as milliseconds from the epoch. + * @param cal The UCalendar to set. + * @param dateTime The desired date and time. + * @param status A pointer to an UErrorCode to receive any errors + * @see ucal_getMillis + * @see ucal_setDate + * @see ucal_setDateTime + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_setMillis(UCalendar* cal, + UDate dateTime, + UErrorCode* status ); + +/** + * Set a UCalendar's current date. + * The date is represented as a series of 32-bit integers. + * @param cal The UCalendar to set. + * @param year The desired year. + * @param month The desired month; one of UCAL_JANUARY, UCAL_FEBRUARY, UCAL_MARCH, UCAL_APRIL, UCAL_MAY, + * UCAL_JUNE, UCAL_JULY, UCAL_AUGUST, UCAL_SEPTEMBER, UCAL_OCTOBER, UCAL_NOVEMBER, UCAL_DECEMBER, UCAL_UNDECIMBER + * @param date The desired day of the month. + * @param status A pointer to an UErrorCode to receive any errors + * @see ucal_getMillis + * @see ucal_setMillis + * @see ucal_setDateTime + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_setDate(UCalendar* cal, + int32_t year, + int32_t month, + int32_t date, + UErrorCode* status); + +/** + * Set a UCalendar's current date. + * The date is represented as a series of 32-bit integers. + * @param cal The UCalendar to set. + * @param year The desired year. + * @param month The desired month; one of UCAL_JANUARY, UCAL_FEBRUARY, UCAL_MARCH, UCAL_APRIL, UCAL_MAY, + * UCAL_JUNE, UCAL_JULY, UCAL_AUGUST, UCAL_SEPTEMBER, UCAL_OCTOBER, UCAL_NOVEMBER, UCAL_DECEMBER, UCAL_UNDECIMBER + * @param date The desired day of the month. + * @param hour The desired hour of day. + * @param minute The desired minute. + * @param second The desirec second. + * @param status A pointer to an UErrorCode to receive any errors + * @see ucal_getMillis + * @see ucal_setMillis + * @see ucal_setDate + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_setDateTime(UCalendar* cal, + int32_t year, + int32_t month, + int32_t date, + int32_t hour, + int32_t minute, + int32_t second, + UErrorCode* status); + +/** + * Returns TRUE if two UCalendars are equivalent. Equivalent + * UCalendars will behave identically, but they may be set to + * different times. + * @param cal1 The first of the UCalendars to compare. + * @param cal2 The second of the UCalendars to compare. + * @return TRUE if cal1 and cal2 are equivalent, FALSE otherwise. + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucal_equivalentTo(const UCalendar* cal1, + const UCalendar* cal2); + +/** + * Add a specified signed amount to a particular field in a UCalendar. + * This can modify more significant fields in the calendar. + * @param cal The UCalendar to which to add. + * @param field The field to which to add the signed value; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @param amount The signed amount to add to field. If the amount causes the value + * to exceed to maximum or minimum values for that field, other fields are modified + * to preserve the magnitude of the change. + * @param status A pointer to an UErrorCode to receive any errors + * @see ucal_roll + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_add(UCalendar* cal, + UCalendarDateFields field, + int32_t amount, + UErrorCode* status); + +/** + * Add a specified signed amount to a particular field in a UCalendar. + * This will not modify more significant fields in the calendar. + * @param cal The UCalendar to which to add. + * @param field The field to which to add the signed value; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @param amount The signed amount to add to field. If the amount causes the value + * to exceed to maximum or minimum values for that field, the field is pinned to a permissible + * value. + * @param status A pointer to an UErrorCode to receive any errors + * @see ucal_add + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_roll(UCalendar* cal, + UCalendarDateFields field, + int32_t amount, + UErrorCode* status); + +/** + * Get the current value of a field from a UCalendar. + * All fields are represented as 32-bit integers. + * @param cal The UCalendar to query. + * @param field The desired field; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @param status A pointer to an UErrorCode to receive any errors + * @return The value of the desired field. + * @see ucal_set + * @see ucal_isSet + * @see ucal_clearField + * @see ucal_clear + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucal_get(const UCalendar* cal, + UCalendarDateFields field, + UErrorCode* status ); + +/** + * Set the value of a field in a UCalendar. + * All fields are represented as 32-bit integers. + * @param cal The UCalendar to set. + * @param field The field to set; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @param value The desired value of field. + * @see ucal_get + * @see ucal_isSet + * @see ucal_clearField + * @see ucal_clear + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_set(UCalendar* cal, + UCalendarDateFields field, + int32_t value); + +/** + * Determine if a field in a UCalendar is set. + * All fields are represented as 32-bit integers. + * @param cal The UCalendar to query. + * @param field The desired field; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @return TRUE if field is set, FALSE otherwise. + * @see ucal_get + * @see ucal_set + * @see ucal_clearField + * @see ucal_clear + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucal_isSet(const UCalendar* cal, + UCalendarDateFields field); + +/** + * Clear a field in a UCalendar. + * All fields are represented as 32-bit integers. + * @param cal The UCalendar containing the field to clear. + * @param field The field to clear; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @see ucal_get + * @see ucal_set + * @see ucal_isSet + * @see ucal_clear + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_clearField(UCalendar* cal, + UCalendarDateFields field); + +/** + * Clear all fields in a UCalendar. + * All fields are represented as 32-bit integers. + * @param calendar The UCalendar to clear. + * @see ucal_get + * @see ucal_set + * @see ucal_isSet + * @see ucal_clearField + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucal_clear(UCalendar* calendar); + +/** + * Possible limit values for a UCalendar + * @stable ICU 2.0 + */ +enum UCalendarLimitType { + /** Minimum value */ + UCAL_MINIMUM, + /** Maximum value */ + UCAL_MAXIMUM, + /** Greatest minimum value */ + UCAL_GREATEST_MINIMUM, + /** Leaest maximum value */ + UCAL_LEAST_MAXIMUM, + /** Actual minimum value */ + UCAL_ACTUAL_MINIMUM, + /** Actual maximum value */ + UCAL_ACTUAL_MAXIMUM +}; + +/** @stable ICU 2.0 */ +typedef enum UCalendarLimitType UCalendarLimitType; + +/** + * Determine a limit for a field in a UCalendar. + * A limit is a maximum or minimum value for a field. + * @param cal The UCalendar to query. + * @param field The desired field; one of UCAL_ERA, UCAL_YEAR, UCAL_MONTH, + * UCAL_WEEK_OF_YEAR, UCAL_WEEK_OF_MONTH, UCAL_DATE, UCAL_DAY_OF_YEAR, UCAL_DAY_OF_WEEK, + * UCAL_DAY_OF_WEEK_IN_MONTH, UCAL_AM_PM, UCAL_HOUR, UCAL_HOUR_OF_DAY, UCAL_MINUTE, UCAL_SECOND, + * UCAL_MILLISECOND, UCAL_ZONE_OFFSET, UCAL_DST_OFFSET. + * @param type The desired critical point; one of UCAL_MINIMUM, UCAL_MAXIMUM, UCAL_GREATEST_MINIMUM, + * UCAL_LEAST_MAXIMUM, UCAL_ACTUAL_MINIMUM, UCAL_ACTUAL_MAXIMUM + * @param status A pointer to an UErrorCode to receive any errors. + * @return The requested value. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucal_getLimit(const UCalendar* cal, + UCalendarDateFields field, + UCalendarLimitType type, + UErrorCode* status); + +/** Get the locale for this calendar object. You can choose between valid and actual locale. + * @param cal The calendar object + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale name + * @stable ICU 2.8 + */ +U_STABLE const char * U_EXPORT2 +ucal_getLocaleByType(const UCalendar *cal, ULocDataLocaleType type, UErrorCode* status); + +/** + * Returns the timezone data version currently used by ICU. + * @param status error code for the operation + * @return the version string, such as "2007f" + * @draft ICU 3.8 + */ +U_DRAFT const char * U_EXPORT2 +ucal_getTZDataVersion(UErrorCode* status); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ucol.h b/Build/source/libs/icu-xetex/i18n/unicode/ucol.h new file mode 100644 index 00000000000..37abe2cc22e --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ucol.h @@ -0,0 +1,1223 @@ +/* +******************************************************************************* +* Copyright (c) 1996-2007, International Business Machines Corporation and others. +* All Rights Reserved. +******************************************************************************* +*/ + +#ifndef UCOL_H +#define UCOL_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_COLLATION + +#include "unicode/unorm.h" +#include "unicode/parseerr.h" +#include "unicode/uloc.h" +#include "unicode/uset.h" + +/** + * \file + * \brief C API: Collator + * + * <h2> Collator C API </h2> + * + * The C API for Collator performs locale-sensitive + * string comparison. You use this service to build + * searching and sorting routines for natural language text. + * <em>Important: </em>The ICU collation service has been reimplemented + * in order to achieve better performance and UCA compliance. + * For details, see the + * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm"> + * collation design document</a>. + * <p> + * For more information about the collation service see + * <a href="http://icu-project.org/userguide/Collate_Intro.html">the users guide</a>. + * <p> + * Collation service provides correct sorting orders for most locales supported in ICU. + * If specific data for a locale is not available, the orders eventually falls back + * to the <a href="http://www.unicode.org/unicode/reports/tr10/">UCA sort order</a>. + * <p> + * Sort ordering may be customized by providing your own set of rules. For more on + * this subject see the + * <a href="http://icu-project.org/userguide/Collate_Customization.html"> + * Collation customization</a> section of the users guide. + * <p> + * @see UCollationResult + * @see UNormalizationMode + * @see UCollationStrength + * @see UCollationElements + */ + +/** A collator. +* For usage in C programs. +*/ +struct UCollator; +/** structure representing a collator object instance + * @stable ICU 2.0 + */ +typedef struct UCollator UCollator; + + +/** + * UCOL_LESS is returned if source string is compared to be less than target + * string in the u_strcoll() method. + * UCOL_EQUAL is returned if source string is compared to be equal to target + * string in the u_strcoll() method. + * UCOL_GREATER is returned if source string is compared to be greater than + * target string in the u_strcoll() method. + * @see u_strcoll() + * <p> + * Possible values for a comparison result + * @stable ICU 2.0 + */ +typedef enum { + /** string a == string b */ + UCOL_EQUAL = 0, + /** string a > string b */ + UCOL_GREATER = 1, + /** string a < string b */ + UCOL_LESS = -1 +} UCollationResult ; + + +/** Enum containing attribute values for controling collation behavior. + * Here are all the allowable values. Not every attribute can take every value. The only + * universal value is UCOL_DEFAULT, which resets the attribute value to the predefined + * value for that locale + * @stable ICU 2.0 + */ +typedef enum { + /** accepted by most attributes */ + UCOL_DEFAULT = -1, + + /** Primary collation strength */ + UCOL_PRIMARY = 0, + /** Secondary collation strength */ + UCOL_SECONDARY = 1, + /** Tertiary collation strength */ + UCOL_TERTIARY = 2, + /** Default collation strength */ + UCOL_DEFAULT_STRENGTH = UCOL_TERTIARY, + UCOL_CE_STRENGTH_LIMIT, + /** Quaternary collation strength */ + UCOL_QUATERNARY=3, + /** Identical collation strength */ + UCOL_IDENTICAL=15, + UCOL_STRENGTH_LIMIT, + + /** Turn the feature off - works for UCOL_FRENCH_COLLATION, + UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE + & UCOL_DECOMPOSITION_MODE*/ + UCOL_OFF = 16, + /** Turn the feature on - works for UCOL_FRENCH_COLLATION, + UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE + & UCOL_DECOMPOSITION_MODE*/ + UCOL_ON = 17, + + /** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be shifted */ + UCOL_SHIFTED = 20, + /** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be non ignorable */ + UCOL_NON_IGNORABLE = 21, + + /** Valid for UCOL_CASE_FIRST - + lower case sorts before upper case */ + UCOL_LOWER_FIRST = 24, + /** upper case sorts before lower case */ + UCOL_UPPER_FIRST = 25, + + UCOL_ATTRIBUTE_VALUE_COUNT + +} UColAttributeValue; + +/** + * Base letter represents a primary difference. Set comparison + * level to UCOL_PRIMARY to ignore secondary and tertiary differences. + * Use this to set the strength of a Collator object. + * Example of primary difference, "abc" < "abd" + * + * Diacritical differences on the same base letter represent a secondary + * difference. Set comparison level to UCOL_SECONDARY to ignore tertiary + * differences. Use this to set the strength of a Collator object. + * Example of secondary difference, "ä" >> "a". + * + * Uppercase and lowercase versions of the same character represents a + * tertiary difference. Set comparison level to UCOL_TERTIARY to include + * all comparison differences. Use this to set the strength of a Collator + * object. + * Example of tertiary difference, "abc" <<< "ABC". + * + * Two characters are considered "identical" when they have the same + * unicode spellings. UCOL_IDENTICAL. + * For example, "ä" == "ä". + * + * UCollationStrength is also used to determine the strength of sort keys + * generated from UCollator objects + * These values can be now found in the UColAttributeValue enum. + * @stable ICU 2.0 + **/ +typedef UColAttributeValue UCollationStrength; + +/** Attributes that collation service understands. All the attributes can take UCOL_DEFAULT + * value, as well as the values specific to each one. + * @stable ICU 2.0 + */ +typedef enum { + /** Attribute for direction of secondary weights - used in French. + * Acceptable values are UCOL_ON, which results in secondary weights + * being considered backwards and UCOL_OFF which treats secondary + * weights in the order they appear.*/ + UCOL_FRENCH_COLLATION, + /** Attribute for handling variable elements. + * Acceptable values are UCOL_NON_IGNORABLE (default) + * which treats all the codepoints with non-ignorable + * primary weights in the same way, + * and UCOL_SHIFTED which causes codepoints with primary + * weights that are equal or below the variable top value + * to be ignored on primary level and moved to the quaternary + * level.*/ + UCOL_ALTERNATE_HANDLING, + /** Controls the ordering of upper and lower case letters. + * Acceptable values are UCOL_OFF (default), which orders + * upper and lower case letters in accordance to their tertiary + * weights, UCOL_UPPER_FIRST which forces upper case letters to + * sort before lower case letters, and UCOL_LOWER_FIRST which does + * the opposite. */ + UCOL_CASE_FIRST, + /** Controls whether an extra case level (positioned before the third + * level) is generated or not. Acceptable values are UCOL_OFF (default), + * when case level is not generated, and UCOL_ON which causes the case + * level to be generated. Contents of the case level are affected by + * the value of UCOL_CASE_FIRST attribute. A simple way to ignore + * accent differences in a string is to set the strength to UCOL_PRIMARY + * and enable case level. */ + UCOL_CASE_LEVEL, + /** Controls whether the normalization check and necessary normalizations + * are performed. When set to UCOL_OFF (default) no normalization check + * is performed. The correctness of the result is guaranteed only if the + * input data is in so-called FCD form (see users manual for more info). + * When set to UCOL_ON, an incremental check is performed to see whether + * the input data is in the FCD form. If the data is not in the FCD form, + * incremental NFD normalization is performed. */ + UCOL_NORMALIZATION_MODE, + /** An alias for UCOL_NORMALIZATION_MODE attribute */ + UCOL_DECOMPOSITION_MODE = UCOL_NORMALIZATION_MODE, + /** The strength attribute. Can be either UCOL_PRIMARY, UCOL_SECONDARY, + * UCOL_TERTIARY, UCOL_QUATERNARY or UCOL_IDENTICAL. The usual strength + * for most locales (except Japanese) is tertiary. Quaternary strength + * is useful when combined with shifted setting for alternate handling + * attribute and for JIS x 4061 collation, when it is used to distinguish + * between Katakana and Hiragana (this is achieved by setting the + * UCOL_HIRAGANA_QUATERNARY mode to on. Otherwise, quaternary level + * is affected only by the number of non ignorable code points in + * the string. Identical strength is rarely useful, as it amounts + * to codepoints of the NFD form of the string. */ + UCOL_STRENGTH, + /** When turned on, this attribute positions Hiragana before all + * non-ignorables on quaternary level This is a sneaky way to produce JIS + * sort order */ + UCOL_HIRAGANA_QUATERNARY_MODE, + /** When turned on, this attribute generates a collation key + * for the numeric value of substrings of digits. + * This is a way to get '100' to sort AFTER '2'. */ + UCOL_NUMERIC_COLLATION, + UCOL_ATTRIBUTE_COUNT +} UColAttribute; + +/** Options for retrieving the rule string + * @stable ICU 2.0 + */ +typedef enum { + /** Retrieve tailoring only */ + UCOL_TAILORING_ONLY, + /** Retrieve UCA rules and tailoring */ + UCOL_FULL_RULES +} UColRuleOption ; + +/** + * Open a UCollator for comparing strings. + * The UCollator pointer is used in all the calls to the Collation + * service. After finished, collator must be disposed of by calling + * {@link #ucol_close }. + * @param loc The locale containing the required collation rules. + * Special values for locales can be passed in - + * if NULL is passed for the locale, the default locale + * collation rules will be used. If empty string ("") or + * "root" are passed, UCA rules will be used. + * @param status A pointer to an UErrorCode to receive any errors + * @return A pointer to a UCollator, or 0 if an error occurred. + * @see ucol_openRules + * @see ucol_safeClone + * @see ucol_close + * @stable ICU 2.0 + */ +U_STABLE UCollator* U_EXPORT2 +ucol_open(const char *loc, UErrorCode *status); + +/** + * Produce an UCollator instance according to the rules supplied. + * The rules are used to change the default ordering, defined in the + * UCA in a process called tailoring. The resulting UCollator pointer + * can be used in the same way as the one obtained by {@link #ucol_strcoll }. + * @param rules A string describing the collation rules. For the syntax + * of the rules please see users guide. + * @param rulesLength The length of rules, or -1 if null-terminated. + * @param normalizationMode The normalization mode: One of + * UCOL_OFF (expect the text to not need normalization), + * UCOL_ON (normalize), or + * UCOL_DEFAULT (set the mode according to the rules) + * @param strength The default collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY, + * UCOL_TERTIARY, UCOL_IDENTICAL,UCOL_DEFAULT_STRENGTH - can be also set in the rules. + * @param parseError A pointer to UParseError to recieve information about errors + * occurred during parsing. This argument can currently be set + * to NULL, but at users own risk. Please provide a real structure. + * @param status A pointer to an UErrorCode to receive any errors + * @return A pointer to a UCollator. It is not guaranteed that NULL be returned in case + * of error - please use status argument to check for errors. + * @see ucol_open + * @see ucol_safeClone + * @see ucol_close + * @stable ICU 2.0 + */ +U_STABLE UCollator* U_EXPORT2 +ucol_openRules( const UChar *rules, + int32_t rulesLength, + UColAttributeValue normalizationMode, + UCollationStrength strength, + UParseError *parseError, + UErrorCode *status); + +/** + * Open a collator defined by a short form string. + * The structure and the syntax of the string is defined in the "Naming collators" + * section of the users guide: + * http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators + * Attributes are overriden by the subsequent attributes. So, for "S2_S3", final + * strength will be 3. 3066bis locale overrides individual locale parts. + * The call to this function is equivalent to a call to ucol_open, followed by a + * series of calls to ucol_setAttribute and ucol_setVariableTop. + * @param definition A short string containing a locale and a set of attributes. + * Attributes not explicitly mentioned are left at the default + * state for a locale. + * @param parseError if not NULL, structure that will get filled with error's pre + * and post context in case of error. + * @param forceDefaults if FALSE, the settings that are the same as the collator + * default settings will not be applied (for example, setting + * French secondary on a French collator would not be executed). + * If TRUE, all the settings will be applied regardless of the + * collator default value. If the definition + * strings are to be cached, should be set to FALSE. + * @param status Error code. Apart from regular error conditions connected to + * instantiating collators (like out of memory or similar), this + * API will return an error if an invalid attribute or attribute/value + * combination is specified. + * @return A pointer to a UCollator or 0 if an error occured (including an + * invalid attribute). + * @see ucol_open + * @see ucol_setAttribute + * @see ucol_setVariableTop + * @see ucol_getShortDefinitionString + * @see ucol_normalizeShortDefinitionString + * @stable ICU 3.0 + * + */ +U_STABLE UCollator* U_EXPORT2 +ucol_openFromShortString( const char *definition, + UBool forceDefaults, + UParseError *parseError, + UErrorCode *status); + +/** + * Get a set containing the contractions defined by the collator. The set includes + * both the UCA contractions and the contractions defined by the collator. This set + * will contain only strings. If a tailoring explicitly suppresses contractions from + * the UCA (like Russian), removed contractions will not be in the resulting set. + * @param coll collator + * @param conts the set to hold the result. It gets emptied before + * contractions are added. + * @param status to hold the error code + * @return the size of the contraction set + * + * @deprecated ICU 3.4, use ucol_getContractionsAndExpansions instead + */ +U_DEPRECATED int32_t U_EXPORT2 +ucol_getContractions( const UCollator *coll, + USet *conts, + UErrorCode *status); + +/** + * Get a set containing the expansions defined by the collator. The set includes + * both the UCA expansions and the expansions defined by the tailoring + * @param coll collator + * @param contractions if not NULL, the set to hold the contractions + * @param expansions if not NULL, the set to hold the expansions + * @param addPrefixes add the prefix contextual elements to contractions + * @param status to hold the error code + * + * @stable ICU 3.4 + */ +U_STABLE void U_EXPORT2 +ucol_getContractionsAndExpansions( const UCollator *coll, + USet *contractions, USet *expansions, + UBool addPrefixes, UErrorCode *status); + +/** + * Close a UCollator. + * Once closed, a UCollator should not be used. Every open collator should + * be closed. Otherwise, a memory leak will result. + * @param coll The UCollator to close. + * @see ucol_open + * @see ucol_openRules + * @see ucol_safeClone + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_close(UCollator *coll); + +/** + * Compare two strings. + * The strings will be compared using the options already specified. + * @param coll The UCollator containing the comparison rules. + * @param source The source string. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param target The target string. + * @param targetLength The length of target, or -1 if null-terminated. + * @return The result of comparing the strings; one of UCOL_EQUAL, + * UCOL_GREATER, UCOL_LESS + * @see ucol_greater + * @see ucol_greaterOrEqual + * @see ucol_equal + * @stable ICU 2.0 + */ +U_STABLE UCollationResult U_EXPORT2 +ucol_strcoll( const UCollator *coll, + const UChar *source, + int32_t sourceLength, + const UChar *target, + int32_t targetLength); + +/** + * Determine if one string is greater than another. + * This function is equivalent to {@link #ucol_strcoll } == UCOL_GREATER + * @param coll The UCollator containing the comparison rules. + * @param source The source string. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param target The target string. + * @param targetLength The length of target, or -1 if null-terminated. + * @return TRUE if source is greater than target, FALSE otherwise. + * @see ucol_strcoll + * @see ucol_greaterOrEqual + * @see ucol_equal + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucol_greater(const UCollator *coll, + const UChar *source, int32_t sourceLength, + const UChar *target, int32_t targetLength); + +/** + * Determine if one string is greater than or equal to another. + * This function is equivalent to {@link #ucol_strcoll } != UCOL_LESS + * @param coll The UCollator containing the comparison rules. + * @param source The source string. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param target The target string. + * @param targetLength The length of target, or -1 if null-terminated. + * @return TRUE if source is greater than or equal to target, FALSE otherwise. + * @see ucol_strcoll + * @see ucol_greater + * @see ucol_equal + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucol_greaterOrEqual(const UCollator *coll, + const UChar *source, int32_t sourceLength, + const UChar *target, int32_t targetLength); + +/** + * Compare two strings for equality. + * This function is equivalent to {@link #ucol_strcoll } == UCOL_EQUAL + * @param coll The UCollator containing the comparison rules. + * @param source The source string. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param target The target string. + * @param targetLength The length of target, or -1 if null-terminated. + * @return TRUE if source is equal to target, FALSE otherwise + * @see ucol_strcoll + * @see ucol_greater + * @see ucol_greaterOrEqual + * @stable ICU 2.0 + */ +U_STABLE UBool U_EXPORT2 +ucol_equal(const UCollator *coll, + const UChar *source, int32_t sourceLength, + const UChar *target, int32_t targetLength); + +/** + * Compare two UTF-8 encoded trings. + * The strings will be compared using the options already specified. + * @param coll The UCollator containing the comparison rules. + * @param sIter The source string iterator. + * @param tIter The target string iterator. + * @return The result of comparing the strings; one of UCOL_EQUAL, + * UCOL_GREATER, UCOL_LESS + * @param status A pointer to an UErrorCode to receive any errors + * @see ucol_strcoll + * @stable ICU 2.6 + */ +U_STABLE UCollationResult U_EXPORT2 +ucol_strcollIter( const UCollator *coll, + UCharIterator *sIter, + UCharIterator *tIter, + UErrorCode *status); + +/** + * Get the collation strength used in a UCollator. + * The strength influences how strings are compared. + * @param coll The UCollator to query. + * @return The collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY, + * UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL + * @see ucol_setStrength + * @stable ICU 2.0 + */ +U_STABLE UCollationStrength U_EXPORT2 +ucol_getStrength(const UCollator *coll); + +/** + * Set the collation strength used in a UCollator. + * The strength influences how strings are compared. + * @param coll The UCollator to set. + * @param strength The desired collation strength; one of UCOL_PRIMARY, + * UCOL_SECONDARY, UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL, UCOL_DEFAULT + * @see ucol_getStrength + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_setStrength(UCollator *coll, + UCollationStrength strength); + +/** + * Get the display name for a UCollator. + * The display name is suitable for presentation to a user. + * @param objLoc The locale of the collator in question. + * @param dispLoc The locale for display. + * @param result A pointer to a buffer to receive the attribute. + * @param resultLength The maximum size of result. + * @param status A pointer to an UErrorCode to receive any errors + * @return The total buffer size needed; if greater than resultLength, + * the output was truncated. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getDisplayName( const char *objLoc, + const char *dispLoc, + UChar *result, + int32_t resultLength, + UErrorCode *status); + +/** + * Get a locale for which collation rules are available. + * A UCollator in a locale returned by this function will perform the correct + * collation for the locale. + * @param index The index of the desired locale. + * @return A locale for which collation rules are available, or 0 if none. + * @see ucol_countAvailable + * @stable ICU 2.0 + */ +U_STABLE const char* U_EXPORT2 +ucol_getAvailable(int32_t index); + +/** + * Determine how many locales have collation rules available. + * This function is most useful as determining the loop ending condition for + * calls to {@link #ucol_getAvailable }. + * @return The number of locales for which collation rules are available. + * @see ucol_getAvailable + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_countAvailable(void); + +#if !UCONFIG_NO_SERVICE +/** + * Create a string enumerator of all locales for which a valid + * collator may be opened. + * @param status input-output error code + * @return a string enumeration over locale strings. The caller is + * responsible for closing the result. + * @stable ICU 3.0 + */ +U_STABLE UEnumeration* U_EXPORT2 +ucol_openAvailableLocales(UErrorCode *status); +#endif + +/** + * Create a string enumerator of all possible keywords that are relevant to + * collation. At this point, the only recognized keyword for this + * service is "collation". + * @param status input-output error code + * @return a string enumeration over locale strings. The caller is + * responsible for closing the result. + * @stable ICU 3.0 + */ +U_STABLE UEnumeration* U_EXPORT2 +ucol_getKeywords(UErrorCode *status); + +/** + * Given a keyword, create a string enumeration of all values + * for that keyword that are currently in use. + * @param keyword a particular keyword as enumerated by + * ucol_getKeywords. If any other keyword is passed in, *status is set + * to U_ILLEGAL_ARGUMENT_ERROR. + * @param status input-output error code + * @return a string enumeration over collation keyword values, or NULL + * upon error. The caller is responsible for closing the result. + * @stable ICU 3.0 + */ +U_STABLE UEnumeration* U_EXPORT2 +ucol_getKeywordValues(const char *keyword, UErrorCode *status); + +/** + * Return the functionally equivalent locale for the given + * requested locale, with respect to given keyword, for the + * collation service. If two locales return the same result, then + * collators instantiated for these locales will behave + * equivalently. The converse is not always true; two collators + * may in fact be equivalent, but return different results, due to + * internal details. The return result has no other meaning than + * that stated above, and implies nothing as to the relationship + * between the two locales. This is intended for use by + * applications who wish to cache collators, or otherwise reuse + * collators when possible. The functional equivalent may change + * over time. For more information, please see the <a + * href="http://icu-project.org/userguide/locale.html#services"> + * Locales and Services</a> section of the ICU User Guide. + * @param result fillin for the functionally equivalent locale + * @param resultCapacity capacity of the fillin buffer + * @param keyword a particular keyword as enumerated by + * ucol_getKeywords. + * @param locale the requested locale + * @param isAvailable if non-NULL, pointer to a fillin parameter that + * indicates whether the requested locale was 'available' to the + * collation service. A locale is defined as 'available' if it + * physically exists within the collation locale data. + * @param status pointer to input-output error code + * @return the actual buffer size needed for the locale. If greater + * than resultCapacity, the returned full name will be truncated and + * an error code will be returned. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getFunctionalEquivalent(char* result, int32_t resultCapacity, + const char* keyword, const char* locale, + UBool* isAvailable, UErrorCode* status); + +/** + * Get the collation rules from a UCollator. + * The rules will follow the rule syntax. + * @param coll The UCollator to query. + * @param length + * @return The collation rules. + * @stable ICU 2.0 + */ +U_STABLE const UChar* U_EXPORT2 +ucol_getRules( const UCollator *coll, + int32_t *length); + +/** Get the short definition string for a collator. This API harvests the collator's + * locale and the attribute set and produces a string that can be used for opening + * a collator with the same properties using the ucol_openFromShortString API. + * This string will be normalized. + * The structure and the syntax of the string is defined in the "Naming collators" + * section of the users guide: + * http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators + * This API supports preflighting. + * @param coll a collator + * @param locale a locale that will appear as a collators locale in the resulting + * short string definition. If NULL, the locale will be harvested + * from the collator. + * @param buffer space to hold the resulting string + * @param capacity capacity of the buffer + * @param status for returning errors. All the preflighting errors are featured + * @return length of the resulting string + * @see ucol_openFromShortString + * @see ucol_normalizeShortDefinitionString + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getShortDefinitionString(const UCollator *coll, + const char *locale, + char *buffer, + int32_t capacity, + UErrorCode *status); + +/** Verifies and normalizes short definition string. + * Normalized short definition string has all the option sorted by the argument name, + * so that equivalent definition strings are the same. + * This API supports preflighting. + * @param source definition string + * @param destination space to hold the resulting string + * @param capacity capacity of the buffer + * @param parseError if not NULL, structure that will get filled with error's pre + * and post context in case of error. + * @param status Error code. This API will return an error if an invalid attribute + * or attribute/value combination is specified. All the preflighting + * errors are also featured + * @return length of the resulting normalized string. + * + * @see ucol_openFromShortString + * @see ucol_getShortDefinitionString + * + * @stable ICU 3.0 + */ + +U_STABLE int32_t U_EXPORT2 +ucol_normalizeShortDefinitionString(const char *source, + char *destination, + int32_t capacity, + UParseError *parseError, + UErrorCode *status); + + +/** + * Get a sort key for a string from a UCollator. + * Sort keys may be compared using <TT>strcmp</TT>. + * @param coll The UCollator containing the collation rules. + * @param source The string to transform. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param result A pointer to a buffer to receive the attribute. + * @param resultLength The maximum size of result. + * @return The size needed to fully store the sort key.. + * @see ucol_keyHashCode + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getSortKey(const UCollator *coll, + const UChar *source, + int32_t sourceLength, + uint8_t *result, + int32_t resultLength); + + +/** Gets the next count bytes of a sort key. Caller needs + * to preserve state array between calls and to provide + * the same type of UCharIterator set with the same string. + * The destination buffer provided must be big enough to store + * the number of requested bytes. Generated sortkey is not + * compatible with sortkeys generated using ucol_getSortKey + * API, since we don't do any compression. If uncompressed + * sortkeys are required, this API can be used. + * @param coll The UCollator containing the collation rules. + * @param iter UCharIterator containing the string we need + * the sort key to be calculated for. + * @param state Opaque state of sortkey iteration. + * @param dest Buffer to hold the resulting sortkey part + * @param count number of sort key bytes required. + * @param status error code indicator. + * @return the actual number of bytes of a sortkey. It can be + * smaller than count if we have reached the end of + * the sort key. + * @stable ICU 2.6 + */ +U_STABLE int32_t U_EXPORT2 +ucol_nextSortKeyPart(const UCollator *coll, + UCharIterator *iter, + uint32_t state[2], + uint8_t *dest, int32_t count, + UErrorCode *status); + +/** enum that is taken by ucol_getBound API + * See below for explanation + * do not change the values assigned to the + * members of this enum. Underlying code + * depends on them having these numbers + * @stable ICU 2.0 + */ +typedef enum { + /** lower bound */ + UCOL_BOUND_LOWER = 0, + /** upper bound that will match strings of exact size */ + UCOL_BOUND_UPPER = 1, + /** upper bound that will match all the strings that have the same initial substring as the given string */ + UCOL_BOUND_UPPER_LONG = 2, + UCOL_BOUND_VALUE_COUNT +} UColBoundMode; + +/** + * Produce a bound for a given sortkey and a number of levels. + * Return value is always the number of bytes needed, regardless of + * whether the result buffer was big enough or even valid.<br> + * Resulting bounds can be used to produce a range of strings that are + * between upper and lower bounds. For example, if bounds are produced + * for a sortkey of string "smith", strings between upper and lower + * bounds with one level would include "Smith", "SMITH", "sMiTh".<br> + * There are two upper bounds that can be produced. If UCOL_BOUND_UPPER + * is produced, strings matched would be as above. However, if bound + * produced using UCOL_BOUND_UPPER_LONG is used, the above example will + * also match "Smithsonian" and similar.<br> + * For more on usage, see example in cintltst/capitst.c in procedure + * TestBounds. + * Sort keys may be compared using <TT>strcmp</TT>. + * @param source The source sortkey. + * @param sourceLength The length of source, or -1 if null-terminated. + * (If an unmodified sortkey is passed, it is always null + * terminated). + * @param boundType Type of bound required. It can be UCOL_BOUND_LOWER, which + * produces a lower inclusive bound, UCOL_BOUND_UPPER, that + * produces upper bound that matches strings of the same length + * or UCOL_BOUND_UPPER_LONG that matches strings that have the + * same starting substring as the source string. + * @param noOfLevels Number of levels required in the resulting bound (for most + * uses, the recommended value is 1). See users guide for + * explanation on number of levels a sortkey can have. + * @param result A pointer to a buffer to receive the resulting sortkey. + * @param resultLength The maximum size of result. + * @param status Used for returning error code if something went wrong. If the + * number of levels requested is higher than the number of levels + * in the source key, a warning (U_SORT_KEY_TOO_SHORT_WARNING) is + * issued. + * @return The size needed to fully store the bound. + * @see ucol_keyHashCode + * @stable ICU 2.1 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getBound(const uint8_t *source, + int32_t sourceLength, + UColBoundMode boundType, + uint32_t noOfLevels, + uint8_t *result, + int32_t resultLength, + UErrorCode *status); + +/** + * Gets the version information for a Collator. Version is currently + * an opaque 32-bit number which depends, among other things, on major + * versions of the collator tailoring and UCA. + * @param coll The UCollator to query. + * @param info the version # information, the result will be filled in + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_getVersion(const UCollator* coll, UVersionInfo info); + +/** + * Gets the UCA version information for a Collator. Version is the + * UCA version number (3.1.1, 4.0). + * @param coll The UCollator to query. + * @param info the version # information, the result will be filled in + * @stable ICU 2.8 + */ +U_STABLE void U_EXPORT2 +ucol_getUCAVersion(const UCollator* coll, UVersionInfo info); + +/** + * Merge two sort keys. The levels are merged with their corresponding counterparts + * (primaries with primaries, secondaries with secondaries etc.). Between the values + * from the same level a separator is inserted. + * example (uncompressed): + * 191B1D 01 050505 01 910505 00 and 1F2123 01 050505 01 910505 00 + * will be merged as + * 191B1D 02 1F212301 050505 02 050505 01 910505 02 910505 00 + * This allows for concatenating of first and last names for sorting, among other things. + * If the destination buffer is not big enough, the results are undefined. + * If any of source lengths are zero or any of source pointers are NULL/undefined, + * result is of size zero. + * @param src1 pointer to the first sortkey + * @param src1Length length of the first sortkey + * @param src2 pointer to the second sortkey + * @param src2Length length of the second sortkey + * @param dest buffer to hold the result + * @param destCapacity size of the buffer for the result + * @return size of the result. If the buffer is big enough size is always + * src1Length+src2Length-1 + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_mergeSortkeys(const uint8_t *src1, int32_t src1Length, + const uint8_t *src2, int32_t src2Length, + uint8_t *dest, int32_t destCapacity); + +/** + * Universal attribute setter + * @param coll collator which attributes are to be changed + * @param attr attribute type + * @param value attribute value + * @param status to indicate whether the operation went on smoothly or there were errors + * @see UColAttribute + * @see UColAttributeValue + * @see ucol_getAttribute + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_setAttribute(UCollator *coll, UColAttribute attr, UColAttributeValue value, UErrorCode *status); + +/** + * Universal attribute getter + * @param coll collator which attributes are to be changed + * @param attr attribute type + * @return attribute value + * @param status to indicate whether the operation went on smoothly or there were errors + * @see UColAttribute + * @see UColAttributeValue + * @see ucol_setAttribute + * @stable ICU 2.0 + */ +U_STABLE UColAttributeValue U_EXPORT2 +ucol_getAttribute(const UCollator *coll, UColAttribute attr, UErrorCode *status); + +/** Variable top + * is a two byte primary value which causes all the codepoints with primary values that + * are less or equal than the variable top to be shifted when alternate handling is set + * to UCOL_SHIFTED. + * Sets the variable top to a collation element value of a string supplied. + * @param coll collator which variable top needs to be changed + * @param varTop one or more (if contraction) UChars to which the variable top should be set + * @param len length of variable top string. If -1 it is considered to be zero terminated. + * @param status error code. If error code is set, the return value is undefined. + * Errors set by this function are: <br> + * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such + * a contraction<br> + * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes + * @return a 32 bit value containing the value of the variable top in upper 16 bits. + * Lower 16 bits are undefined + * @see ucol_getVariableTop + * @see ucol_restoreVariableTop + * @stable ICU 2.0 + */ +U_STABLE uint32_t U_EXPORT2 +ucol_setVariableTop(UCollator *coll, + const UChar *varTop, int32_t len, + UErrorCode *status); + +/** + * Gets the variable top value of a Collator. + * Lower 16 bits are undefined and should be ignored. + * @param coll collator which variable top needs to be retrieved + * @param status error code (not changed by function). If error code is set, + * the return value is undefined. + * @return the variable top value of a Collator. + * @see ucol_setVariableTop + * @see ucol_restoreVariableTop + * @stable ICU 2.0 + */ +U_STABLE uint32_t U_EXPORT2 ucol_getVariableTop(const UCollator *coll, UErrorCode *status); + +/** + * Sets the variable top to a collation element value supplied. Variable top is + * set to the upper 16 bits. + * Lower 16 bits are ignored. + * @param coll collator which variable top needs to be changed + * @param varTop CE value, as returned by ucol_setVariableTop or ucol)getVariableTop + * @param status error code (not changed by function) + * @see ucol_getVariableTop + * @see ucol_setVariableTop + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_restoreVariableTop(UCollator *coll, const uint32_t varTop, UErrorCode *status); + +/** + * Thread safe cloning operation. The result is a clone of a given collator. + * @param coll collator to be cloned + * @param stackBuffer user allocated space for the new clone. + * If NULL new memory will be allocated. + * If buffer is not large enough, new memory will be allocated. + * Clients can use the U_COL_SAFECLONE_BUFFERSIZE. + * This will probably be enough to avoid memory allocations. + * @param pBufferSize pointer to size of allocated space. + * If *pBufferSize == 0, a sufficient size for use in cloning will + * be returned ('pre-flighting') + * If *pBufferSize is not enough for a stack-based safe clone, + * new memory will be allocated. + * @param status to indicate whether the operation went on smoothly or there were errors + * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any + * allocations were necessary. + * @return pointer to the new clone + * @see ucol_open + * @see ucol_openRules + * @see ucol_close + * @stable ICU 2.0 + */ +U_STABLE UCollator* U_EXPORT2 +ucol_safeClone(const UCollator *coll, + void *stackBuffer, + int32_t *pBufferSize, + UErrorCode *status); + +/** default memory size for the new clone. It needs to be this large for os/400 large pointers + * @stable ICU 2.0 + */ +#define U_COL_SAFECLONE_BUFFERSIZE 512 + +/** + * Returns current rules. Delta defines whether full rules are returned or just the tailoring. + * Returns number of UChars needed to store rules. If buffer is NULL or bufferLen is not enough + * to store rules, will store up to available space. + * @param coll collator to get the rules from + * @param delta one of UCOL_TAILORING_ONLY, UCOL_FULL_RULES. + * @param buffer buffer to store the result in. If NULL, you'll get no rules. + * @param bufferLen lenght of buffer to store rules in. If less then needed you'll get only the part that fits in. + * @return current rules + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getRulesEx(const UCollator *coll, UColRuleOption delta, UChar *buffer, int32_t bufferLen); + +/** + * gets the locale name of the collator. If the collator + * is instantiated from the rules, then this function returns + * NULL. + * @param coll The UCollator for which the locale is needed + * @param type You can choose between requested, valid and actual + * locale. For description see the definition of + * ULocDataLocaleType in uloc.h + * @param status error code of the operation + * @return real locale name from which the collation data comes. + * If the collator was instantiated from rules, returns + * NULL. + * @deprecated ICU 2.8 Use ucol_getLocaleByType instead + */ +U_DEPRECATED const char * U_EXPORT2 +ucol_getLocale(const UCollator *coll, ULocDataLocaleType type, UErrorCode *status); + + +/** + * gets the locale name of the collator. If the collator + * is instantiated from the rules, then this function returns + * NULL. + * @param coll The UCollator for which the locale is needed + * @param type You can choose between requested, valid and actual + * locale. For description see the definition of + * ULocDataLocaleType in uloc.h + * @param status error code of the operation + * @return real locale name from which the collation data comes. + * If the collator was instantiated from rules, returns + * NULL. + * @stable ICU 2.8 + */ +U_STABLE const char * U_EXPORT2 +ucol_getLocaleByType(const UCollator *coll, ULocDataLocaleType type, UErrorCode *status); + +/** + * Get an Unicode set that contains all the characters and sequences tailored in + * this collator. The result must be disposed of by using uset_close. + * @param coll The UCollator for which we want to get tailored chars + * @param status error code of the operation + * @return a pointer to newly created USet. Must be be disposed by using uset_close + * @see ucol_openRules + * @see uset_close + * @stable ICU 2.4 + */ +U_STABLE USet * U_EXPORT2 +ucol_getTailoredSet(const UCollator *coll, UErrorCode *status); + +#ifndef U_HIDE_INTERNAL_API +/** + * Returned by ucol_collatorToIdentifier to signify that collator is + * not encodable as an identifier. + * @internal ICU 3.0 + */ +#define UCOL_SIT_COLLATOR_NOT_ENCODABLE 0x80000000 +#endif /* U_HIDE_INTERNAL_API */ + +/** + * Get a 31-bit identifier given a collator. + * @param coll UCollator + * @param locale a locale that will appear as a collators locale in the resulting + * short string definition. If NULL, the locale will be harvested + * from the collator. + * @param status holds error messages + * @return 31-bit identifier. MSB is used if the collator cannot be encoded. In that + * case UCOL_SIT_COLLATOR_NOT_ENCODABLE is returned + * @see ucol_openFromIdentifier + * @see ucol_identifierToShortString + * @internal ICU 3.0 + */ +U_INTERNAL uint32_t U_EXPORT2 +ucol_collatorToIdentifier(const UCollator *coll, + const char *locale, + UErrorCode *status); + +/** + * Open a collator given a 31-bit identifier + * @param identifier 31-bit identifier, encoded by calling ucol_collatorToIdentifier + * @param forceDefaults if FALSE, the settings that are the same as the collator + * default settings will not be applied (for example, setting + * French secondary on a French collator would not be executed). + * If TRUE, all the settings will be applied regardless of the + * collator default value. If the definition + * strings that can be produced from a collator instantiated by + * calling this API are to be cached, should be set to FALSE. + * @param status for returning errors + * @return UCollator object + * @see ucol_collatorToIdentifier + * @see ucol_identifierToShortString + * @internal ICU 3.0 + */ +U_INTERNAL UCollator* U_EXPORT2 +ucol_openFromIdentifier(uint32_t identifier, + UBool forceDefaults, + UErrorCode *status); + + +/** + * Calculate the short definition string given an identifier. Supports preflighting. + * @param identifier 31-bit identifier, encoded by calling ucol_collatorToIdentifier + * @param buffer buffer to store the result + * @param capacity buffer capacity + * @param forceDefaults whether the settings that are the same as the default setting + * should be forced anyway. Setting this argument to FALSE reduces + * the number of different configurations, but decreases performace + * as a collator has to be instantiated. + * @param status for returning errors + * @return length of the short definition string + * @see ucol_collatorToIdentifier + * @see ucol_openFromIdentifier + * @see ucol_shortStringToIdentifier + * @internal ICU 3.0 + */ +U_INTERNAL int32_t U_EXPORT2 +ucol_identifierToShortString(uint32_t identifier, + char *buffer, + int32_t capacity, + UBool forceDefaults, + UErrorCode *status); + +/** + * Calculate the identifier given a short definition string. Supports preflighting. + * @param definition short string definition + * @param forceDefaults whether the settings that are the same as the default setting + * should be forced anyway. Setting this argument to FALSE reduces + * the number of different configurations, but decreases performace + * as a collator has to be instantiated. + * @param status for returning errors + * @return identifier + * @see ucol_collatorToIdentifier + * @see ucol_openFromIdentifier + * @see ucol_identifierToShortString + * @internal ICU 3.0 + */ +U_INTERNAL uint32_t U_EXPORT2 +ucol_shortStringToIdentifier(const char *definition, + UBool forceDefaults, + UErrorCode *status); + + + +/** + * Universal attribute getter that returns UCOL_DEFAULT if the value is default + * @param coll collator which attributes are to be changed + * @param attr attribute type + * @return attribute value or UCOL_DEFAULT if the value is default + * @param status to indicate whether the operation went on smoothly or there were errors + * @see UColAttribute + * @see UColAttributeValue + * @see ucol_setAttribute + * @internal ICU 3.0 + */ +U_INTERNAL UColAttributeValue U_EXPORT2 +ucol_getAttributeOrDefault(const UCollator *coll, UColAttribute attr, UErrorCode *status); + +/** Check whether two collators are equal. Collators are considered equal if they + * will sort strings the same. This means that both the current attributes and the + * rules must be equivalent. Currently used for RuleBasedCollator::operator==. + * @param source first collator + * @param target second collator + * @return TRUE or FALSE + * @internal ICU 3.0 + */ +U_INTERNAL UBool U_EXPORT2 +ucol_equals(const UCollator *source, const UCollator *target); + +/** Calculates the set of unsafe code points, given a collator. + * A character is unsafe if you could append any character and cause the ordering to alter significantly. + * Collation sorts in normalized order, so anything that rearranges in normalization can cause this. + * Thus if you have a character like a_umlaut, and you add a lower_dot to it, + * then it normalizes to a_lower_dot + umlaut, and sorts differently. + * @param coll Collator + * @param unsafe a fill-in set to receive the unsafe points + * @param status for catching errors + * @return number of elements in the set + * @internal ICU 3.0 + */ +U_INTERNAL int32_t U_EXPORT2 +ucol_getUnsafeSet( const UCollator *coll, + USet *unsafe, + UErrorCode *status); + +/** Reset UCA's static pointers. You don't want to use this, unless your static memory can go away. + * @internal ICU 3.2.1 + */ +U_INTERNAL void U_EXPORT2 +ucol_forgetUCA(void); + +/** Touches all resources needed for instantiating a collator from a short string definition, + * thus filling up the cache. + * @param definition A short string containing a locale and a set of attributes. + * Attributes not explicitly mentioned are left at the default + * state for a locale. + * @param parseError if not NULL, structure that will get filled with error's pre + * and post context in case of error. + * @param forceDefaults if FALSE, the settings that are the same as the collator + * default settings will not be applied (for example, setting + * French secondary on a French collator would not be executed). + * If TRUE, all the settings will be applied regardless of the + * collator default value. If the definition + * strings are to be cached, should be set to FALSE. + * @param status Error code. Apart from regular error conditions connected to + * instantiating collators (like out of memory or similar), this + * API will return an error if an invalid attribute or attribute/value + * combination is specified. + * @see ucol_openFromShortString + * @internal ICU 3.2.1 + */ +U_INTERNAL void U_EXPORT2 +ucol_prepareShortStringOpen( const char *definition, + UBool forceDefaults, + UParseError *parseError, + UErrorCode *status); + +/** Creates a binary image of a collator. This binary image can be stored and + * later used to instantiate a collator using ucol_openBinary. + * This API supports preflighting. + * @param coll Collator + * @param buffer a fill-in buffer to receive the binary image + * @param capacity capacity of the destination buffer + * @param status for catching errors + * @return size of the image + * @see ucol_openBinary + * @stable ICU 3.2 + */ +U_STABLE int32_t U_EXPORT2 +ucol_cloneBinary(const UCollator *coll, + uint8_t *buffer, int32_t capacity, + UErrorCode *status); + +/** Opens a collator from a collator binary image created using + * ucol_cloneBinary. Binary image used in instantiation of the + * collator remains owned by the user and should stay around for + * the lifetime of the collator. The API also takes a base collator + * which usualy should be UCA. + * @param bin binary image owned by the user and required through the + * lifetime of the collator + * @param length size of the image. If negative, the API will try to + * figure out the length of the image + * @param base fallback collator, usually UCA. Base is required to be + * present through the lifetime of the collator. Currently + * it cannot be NULL. + * @param status for catching errors + * @return newly created collator + * @see ucol_cloneBinary + * @stable ICU 3.2 + */ +U_STABLE UCollator* U_EXPORT2 +ucol_openBinary(const uint8_t *bin, int32_t length, + const UCollator *base, + UErrorCode *status); + + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ucoleitr.h b/Build/source/libs/icu-xetex/i18n/unicode/ucoleitr.h new file mode 100644 index 00000000000..7184e96a767 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ucoleitr.h @@ -0,0 +1,268 @@ +/* +******************************************************************************* +* Copyright (C) 2001-2004, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* +* File ucoleitr.cpp +* +* Modification History: +* +* Date Name Description +* 02/15/2001 synwee Modified all methods to process its own function +* instead of calling the equivalent c++ api (coleitr.h) +*******************************************************************************/ + +#ifndef UCOLEITR_H +#define UCOLEITR_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_COLLATION + +/** + * This indicates an error has occured during processing or if no more CEs is + * to be returned. + * @stable ICU 2.0 + */ +#define UCOL_NULLORDER ((int32_t)0xFFFFFFFF) + +#include "unicode/ucol.h" + +/** + * The UCollationElements struct. + * For usage in C programs. + * @stable ICU 2.0 + */ +typedef struct UCollationElements UCollationElements; + +/** + * \file + * \brief C API: UCollationElements + * + * The UCollationElements API is used as an iterator to walk through each + * character of an international string. Use the iterator to return the + * ordering priority of the positioned character. The ordering priority of a + * character, which we refer to as a key, defines how a character is collated + * in the given collation object. + * For example, consider the following in Spanish: + * <pre> + * . "ca" -> the first key is key('c') and second key is key('a'). + * . "cha" -> the first key is key('ch') and second key is key('a'). + * </pre> + * And in German, + * <pre> + * . "<ae ligature>b"-> the first key is key('a'), the second key is key('e'), and + * . the third key is key('b'). + * </pre> + * <p>Example of the iterator usage: (without error checking) + * <pre> + * . void CollationElementIterator_Example() + * . { + * . UChar *s; + * . t_int32 order, primaryOrder; + * . UCollationElements *c; + * . UCollatorOld *coll; + * . UErrorCode success = U_ZERO_ERROR; + * . s=(UChar*)malloc(sizeof(UChar) * (strlen("This is a test")+1) ); + * . u_uastrcpy(s, "This is a test"); + * . coll = ucol_open(NULL, &success); + * . c = ucol_openElements(coll, str, u_strlen(str), &status); + * . order = ucol_next(c, &success); + * . ucol_reset(c); + * . order = ucol_prev(c, &success); + * . free(s); + * . ucol_close(coll); + * . ucol_closeElements(c); + * . } + * </pre> + * <p> + * ucol_next() returns the collation order of the next. + * ucol_prev() returns the collation order of the previous character. + * The Collation Element Iterator moves only in one direction between calls to + * ucol_reset. That is, ucol_next() and ucol_prev can not be inter-used. + * Whenever ucol_prev is to be called after ucol_next() or vice versa, + * ucol_reset has to be called first to reset the status, shifting pointers to + * either the end or the start of the string. Hence at the next call of + * ucol_prev or ucol_next, the first or last collation order will be returned. + * If a change of direction is done without a ucol_reset, the result is + * undefined. + * The result of a forward iterate (ucol_next) and reversed result of the + * backward iterate (ucol_prev) on the same string are equivalent, if + * collation orders with the value UCOL_IGNORABLE are ignored. + * Character based on the comparison level of the collator. A collation order + * consists of primary order, secondary order and tertiary order. The data + * type of the collation order is <strong>t_int32</strong>. + * + * @see UCollator + */ + +/** + * Open the collation elements for a string. + * + * @param coll The collator containing the desired collation rules. + * @param text The text to iterate over. + * @param textLength The number of characters in text, or -1 if null-terminated + * @param status A pointer to an UErrorCode to receive any errors. + * @return a struct containing collation element information + * @stable ICU 2.0 + */ +U_STABLE UCollationElements* U_EXPORT2 +ucol_openElements(const UCollator *coll, + const UChar *text, + int32_t textLength, + UErrorCode *status); + +/** + * get a hash code for a key... Not very useful! + * @param key the given key. + * @param length the size of the key array. + * @return the hash code. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_keyHashCode(const uint8_t* key, int32_t length); + +/** + * Close a UCollationElements. + * Once closed, a UCollationElements may no longer be used. + * @param elems The UCollationElements to close. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_closeElements(UCollationElements *elems); + +/** + * Reset the collation elements to their initial state. + * This will move the 'cursor' to the beginning of the text. + * Property settings for collation will be reset to the current status. + * @param elems The UCollationElements to reset. + * @see ucol_next + * @see ucol_previous + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_reset(UCollationElements *elems); + +/** + * Get the ordering priority of the next collation element in the text. + * A single character may contain more than one collation element. + * @param elems The UCollationElements containing the text. + * @param status A pointer to an UErrorCode to receive any errors. + * @return The next collation elements ordering, otherwise returns NULLORDER + * if an error has occured or if the end of string has been reached + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_next(UCollationElements *elems, UErrorCode *status); + +/** + * Get the ordering priority of the previous collation element in the text. + * A single character may contain more than one collation element. + * Note that internally a stack is used to store buffered collation elements. + * It is very rare that the stack will overflow, however if such a case is + * encountered, the problem can be solved by increasing the size + * UCOL_EXPAND_CE_BUFFER_SIZE in ucol_imp.h. + * @param elems The UCollationElements containing the text. + * @param status A pointer to an UErrorCode to receive any errors. Noteably + * a U_BUFFER_OVERFLOW_ERROR is returned if the internal stack + * buffer has been exhausted. + * @return The previous collation elements ordering, otherwise returns + * NULLORDER if an error has occured or if the start of string has + * been reached. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_previous(UCollationElements *elems, UErrorCode *status); + +/** + * Get the maximum length of any expansion sequences that end with the + * specified comparison order. + * This is useful for .... ? + * @param elems The UCollationElements containing the text. + * @param order A collation order returned by previous or next. + * @return maximum size of the expansion sequences ending with the collation + * element or 1 if collation element does not occur at the end of any + * expansion sequence + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getMaxExpansion(const UCollationElements *elems, int32_t order); + +/** + * Set the text containing the collation elements. + * Property settings for collation will remain the same. + * In order to reset the iterator to the current collation property settings, + * the API reset() has to be called. + * @param elems The UCollationElements to set. + * @param text The source text containing the collation elements. + * @param textLength The length of text, or -1 if null-terminated. + * @param status A pointer to an UErrorCode to receive any errors. + * @see ucol_getText + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_setText( UCollationElements *elems, + const UChar *text, + int32_t textLength, + UErrorCode *status); + +/** + * Get the offset of the current source character. + * This is an offset into the text of the character containing the current + * collation elements. + * @param elems The UCollationElements to query. + * @return The offset of the current source character. + * @see ucol_setOffset + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +ucol_getOffset(const UCollationElements *elems); + +/** + * Set the offset of the current source character. + * This is an offset into the text of the character to be processed. + * Property settings for collation will remain the same. + * In order to reset the iterator to the current collation property settings, + * the API reset() has to be called. + * @param elems The UCollationElements to set. + * @param offset The desired character offset. + * @param status A pointer to an UErrorCode to receive any errors. + * @see ucol_getOffset + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +ucol_setOffset(UCollationElements *elems, + int32_t offset, + UErrorCode *status); + +/** +* Get the primary order of a collation order. +* @param order the collation order +* @return the primary order of a collation order. +* @stable ICU 2.6 +*/ +U_STABLE int32_t U_EXPORT2 +ucol_primaryOrder (int32_t order); + +/** +* Get the secondary order of a collation order. +* @param order the collation order +* @return the secondary order of a collation order. +* @stable ICU 2.6 +*/ +U_STABLE int32_t U_EXPORT2 +ucol_secondaryOrder (int32_t order); + +/** +* Get the tertiary order of a collation order. +* @param order the collation order +* @return the tertiary order of a collation order. +* @stable ICU 2.6 +*/ +U_STABLE int32_t U_EXPORT2 +ucol_tertiaryOrder (int32_t order); + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ucsdet.h b/Build/source/libs/icu-xetex/i18n/unicode/ucsdet.h new file mode 100644 index 00000000000..31f622c01a4 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ucsdet.h @@ -0,0 +1,349 @@ +/* + ********************************************************************** + * Copyright (C) 2005-2007, International Business Machines + * Corporation and others. All Rights Reserved. + ********************************************************************** + * file name: ucsdet.h + * encoding: US-ASCII + * indentation:4 + * + * created on: 2005Aug04 + * created by: Andy Heninger + * + * ICU Character Set Detection, API for C + * + * Draft version 18 Oct 2005 + * + */ + +#ifndef __UCSDET_H +#define __UCSDET_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_CONVERSION +#include "unicode/uenum.h" + +/** + * \file + * \brief C API: Charset Detection API + * + * This API provides a facility for detecting the + * charset or encoding of character data in an unknown text format. + * The input data can be from an array of bytes. + * <p> + * Character set detection is at best an imprecise operation. The detection + * process will attempt to identify the charset that best matches the characteristics + * of the byte data, but the process is partly statistical in nature, and + * the results can not be guaranteed to always be correct. + * <p> + * For best accuracy in charset detection, the input data should be primarily + * in a single language, and a minimum of a few hundred bytes worth of plain text + * in the language are needed. The detection process will attempt to + * ignore html or xml style markup that could otherwise obscure the content. + */ + + +struct UCharsetDetector; +/** + * Structure representing a charset detector + * @stable ICU 3.6 + */ +typedef struct UCharsetDetector UCharsetDetector; + +struct UCharsetMatch; +/** + * Opaque structure representing a match that was identified + * from a charset detection operation. + * @stable ICU 3.6 + */ +typedef struct UCharsetMatch UCharsetMatch; + +/** + * Open a charset detector. + * + * @param status Any error conditions occurring during the open + * operation are reported back in this variable. + * @return the newly opened charset detector. + * @stable ICU 3.6 + */ +U_STABLE UCharsetDetector * U_EXPORT2 +ucsdet_open(UErrorCode *status); + +/** + * Close a charset detector. All storage and any other resources + * owned by this charset detector will be released. Failure to + * close a charset detector when finished with it can result in + * memory leaks in the application. + * + * @param ucsd The charset detector to be closed. + * @stable ICU 3.6 + */ +U_STABLE void U_EXPORT2 +ucsdet_close(UCharsetDetector *ucsd); + +/** + * Set the input byte data whose charset is to detected. + * + * Ownership of the input text byte array remains with the caller. + * The input string must not be altered or deleted until the charset + * detector is either closed or reset to refer to different input text. + * + * @param ucsd the charset detector to be used. + * @param textIn the input text of unknown encoding. . + * @param len the length of the input text, or -1 if the text + * is NUL terminated. + * @param status any error conditions are reported back in this variable. + * + * @stable ICU 3.6 + */ +U_STABLE void U_EXPORT2 +ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status); + + +/** Set the declared encoding for charset detection. + * The declared encoding of an input text is an encoding obtained + * by the user from an http header or xml declaration or similar source that + * can be provided as an additional hint to the charset detector. + * + * How and whether the declared encoding will be used during the + * detection process is TBD. + * + * @param ucsd the charset detector to be used. + * @param encoding an encoding for the current data obtained from + * a header or declaration or other source outside + * of the byte data itself. + * @param length the length of the encoding name, or -1 if the name string + * is NUL terminated. + * @param status any error conditions are reported back in this variable. + * + * @stable ICU 3.6 + */ +U_STABLE void U_EXPORT2 +ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status); + + +/** + * Return the charset that best matches the supplied input data. + * + * Note though, that because the detection + * only looks at the start of the input data, + * there is a possibility that the returned charset will fail to handle + * the full set of input data. + * <p> + * The returned UCharsetMatch object is owned by the UCharsetDetector. + * It will remain valid until the detector input is reset, or until + * the detector is closed. + * <p> + * The function will fail if + * <ul> + * <li>no charset appears to match the data.</li> + * <li>no input text has been provided</li> + * </ul> + * + * @param ucsd the charset detector to be used. + * @param status any error conditions are reported back in this variable. + * @return a UCharsetMatch representing the best matching charset, + * or NULL if no charset matches the byte data. + * + * @stable ICU 3.6 + */ +U_STABLE const UCharsetMatch * U_EXPORT2 +ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status); + + +/** + * Find all charset matches that appear to be consistent with the input, + * returning an array of results. The results are ordered with the + * best quality match first. + * + * Because the detection only looks at a limited amount of the + * input byte data, some of the returned charsets may fail to handle + * the all of input data. + * <p> + * The returned UCharsetMatch objects are owned by the UCharsetDetector. + * They will remain valid until the detector is closed or modified + * + * <p> + * Return an error if + * <ul> + * <li>no charsets appear to match the input data.</li> + * <li>no input text has been provided</li> + * </ul> + * + * @param ucsd the charset detector to be used. + * @param matchesFound pointer to a variable that will be set to the + * number of charsets identified that are consistent with + * the input data. Output only. + * @param status any error conditions are reported back in this variable. + * @return A pointer to an array of pointers to UCharSetMatch objects. + * This array, and the UCharSetMatch instances to which it refers, + * are owned by the UCharsetDetector, and will remain valid until + * the detector is closed or modified. + * @stable ICU 3.6 + */ +U_STABLE const UCharsetMatch ** U_EXPORT2 +ucsdet_detectAll(UCharsetDetector *ucsd, int32_t *matchesFound, UErrorCode *status); + + + +/** + * Get the name of the charset represented by a UCharsetMatch. + * + * The storage for the returned name string is owned by the + * UCharsetMatch, and will remain valid while the UCharsetMatch + * is valid. + * + * The name returned is suitable for use with the ICU conversion APIs. + * + * @param ucsm The charset match object. + * @param status Any error conditions are reported back in this variable. + * @return The name of the matching charset. + * + * @stable ICU 3.6 + */ +U_STABLE const char * U_EXPORT2 +ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status); + +/** + * Get a confidence number for the quality of the match of the byte + * data with the charset. Confidence numbers range from zero to 100, + * with 100 representing complete confidence and zero representing + * no confidence. + * + * The confidence values are somewhat arbitrary. They define an + * an ordering within the results for any single detection operation + * but are not generally comparable between the results for different input. + * + * A confidence value of ten does have a general meaning - it is used + * for charsets that can represent the input data, but for which there + * is no other indication that suggests that the charset is the correct one. + * Pure 7 bit ASCII data, for example, is compatible with a + * great many charsets, most of which will appear as possible matches + * with a confidence of 10. + * + * @param ucsm The charset match object. + * @param status Any error conditions are reported back in this variable. + * @return A confidence number for the charset match. + * + * @stable ICU 3.6 + */ +U_STABLE int32_t U_EXPORT2 +ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status); + +/** + * Get the RFC 3066 code for the language of the input data. + * + * The Charset Detection service is intended primarily for detecting + * charsets, not language. For some, but not all, charsets, a language is + * identified as a byproduct of the detection process, and that is what + * is returned by this function. + * + * CAUTION: + * 1. Language information is not available for input data encoded in + * all charsets. In particular, no language is identified + * for UTF-8 input data. + * + * 2. Closely related languages may sometimes be confused. + * + * If more accurate language detection is required, a linguistic + * analysis package should be used. + * + * The storage for the returned name string is owned by the + * UCharsetMatch, and will remain valid while the UCharsetMatch + * is valid. + * + * @param ucsm The charset match object. + * @param status Any error conditions are reported back in this variable. + * @return The RFC 3066 code for the language of the input data, or + * an empty string if the language could not be determined. + * + * @stable ICU 3.6 + */ +U_STABLE const char * U_EXPORT2 +ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status); + + +/** + * Get the entire input text as a UChar string, placing it into + * a caller-supplied buffer. A terminating + * NUL character will be appended to the buffer if space is available. + * + * The number of UChars in the output string, not including the terminating + * NUL, is returned. + * + * If the supplied buffer is smaller than required to hold the output, + * the contents of the buffer are undefined. The full output string length + * (in UChars) is returned as always, and can be used to allocate a buffer + * of the correct size. + * + * + * @param ucsm The charset match object. + * @param buf A UChar buffer to be filled with the converted text data. + * @param cap The capacity of the buffer in UChars. + * @param status Any error conditions are reported back in this variable. + * @return The number of UChars in the output string. + * + * @stable ICU 3.6 + */ +U_STABLE int32_t U_EXPORT2 +ucsdet_getUChars(const UCharsetMatch *ucsm, + UChar *buf, int32_t cap, UErrorCode *status); + + + +/** + * Get an iterator over the set of all detectable charsets - + * over the charsets that are known to the charset detection + * service. + * + * The returned UEnumeration provides access to the names of + * the charsets. + * + * The state of the Charset detector that is passed in does not + * affect the result of this function, but requiring a valid, open + * charset detector as a parameter insures that the charset detection + * service has been safely initialized and that the required detection + * data is available. + * + * @param ucsd a Charset detector. + * @param status Any error conditions are reported back in this variable. + * @return an iterator providing access to the detectable charset names. + * @stable ICU 3.6 + */ +U_STABLE UEnumeration * U_EXPORT2 +ucsdet_getAllDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status); + + +/** + * Test whether input filtering is enabled for this charset detector. + * Input filtering removes text that appears to be HTML or xml + * markup from the input before applying the code page detection + * heuristics. + * + * @param ucsd The charset detector to check. + * @return TRUE if filtering is enabled. + * @stable ICU 3.6 + */ +U_STABLE UBool U_EXPORT2 +ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd); + + +/** + * Enable filtering of input text. If filtering is enabled, + * text within angle brackets ("<" and ">") will be removed + * before detection, which will remove most HTML or xml markup. + * + * @param ucsd the charset detector to be modified. + * @param filter <code>true</code> to enable input text filtering. + * @return The previous setting. + * + * @stable ICU 3.6 + */ +U_STABLE UBool U_EXPORT2 +ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter); + +#endif +#endif /* __UCSDET_H */ + + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ucurr.h b/Build/source/libs/icu-xetex/i18n/unicode/ucurr.h new file mode 100644 index 00000000000..842b8864472 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ucurr.h @@ -0,0 +1,225 @@ +/* +********************************************************************** +* Copyright (c) 2002-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +*/ +#ifndef _UCURR_H_ +#define _UCURR_H_ + +#include "unicode/utypes.h" +#include "unicode/uenum.h" + +/** + * \file + * \brief C API: Encapsulates information about a currency. + */ + +#if !UCONFIG_NO_FORMATTING + +/** + * The ucurr API encapsulates information about a currency, as defined by + * ISO 4217. A currency is represented by a 3-character string + * containing its ISO 4217 code. This API can return various data + * necessary the proper display of a currency: + * + * <ul><li>A display symbol, for a specific locale + * <li>The number of fraction digits to display + * <li>A rounding increment + * </ul> + * + * The <tt>DecimalFormat</tt> class uses these data to display + * currencies. + * @author Alan Liu + * @since ICU 2.2 + */ + +/** + * Finds a currency code for the given locale. + * @param locale the locale for which to retrieve a currency code. + * Currency can be specified by the "currency" keyword + * in which case it overrides the default currency code + * @param buff fill in buffer. Can be NULL for preflighting. + * @param buffCapacity capacity of the fill in buffer. Can be 0 for + * preflighting. If it is non-zero, the buff parameter + * must not be NULL. + * @param ec error code + * @return length of the currency string. It should always be 3. If 0, + * currency couldn't be found or the input values are + * invalid. + * @stable ICU 2.8 + */ +U_STABLE int32_t U_EXPORT2 +ucurr_forLocale(const char* locale, + UChar* buff, + int32_t buffCapacity, + UErrorCode* ec); + +/** + * Selector constants for ucurr_getName(). + * + * @see ucurr_getName + * @stable ICU 2.6 + */ +typedef enum UCurrNameStyle { + /** + * Selector for ucurr_getName indicating a symbolic name for a + * currency, such as "$" for USD. + * @stable ICU 2.6 + */ + UCURR_SYMBOL_NAME, + + /** + * Selector for ucurr_getName indicating the long name for a + * currency, such as "US Dollar" for USD. + * @stable ICU 2.6 + */ + UCURR_LONG_NAME +} UCurrNameStyle; + +#if !UCONFIG_NO_SERVICE +/** + * @stable ICU 2.6 + */ +typedef const void* UCurrRegistryKey; + +/** + * Register an (existing) ISO 4217 currency code for the given locale. + * Only the country code and the two variants EURO and PRE_EURO are + * recognized. + * @param isoCode the three-letter ISO 4217 currency code + * @param locale the locale for which to register this currency code + * @param status the in/out status code + * @return a registry key that can be used to unregister this currency code, or NULL + * if there was an error. + * @stable ICU 2.6 + */ +U_STABLE UCurrRegistryKey U_EXPORT2 +ucurr_register(const UChar* isoCode, + const char* locale, + UErrorCode* status); +/** + * Unregister the previously-registered currency definitions using the + * URegistryKey returned from ucurr_register. Key becomes invalid after + * a successful call and should not be used again. Any currency + * that might have been hidden by the original ucurr_register call is + * restored. + * @param key the registry key returned by a previous call to ucurr_register + * @param status the in/out status code, no special meanings are assigned + * @return TRUE if the currency for this key was successfully unregistered + * @stable ICU 2.6 + */ +U_STABLE UBool U_EXPORT2 +ucurr_unregister(UCurrRegistryKey key, UErrorCode* status); +#endif /* UCONFIG_NO_SERVICE */ + +/** + * Returns the display name for the given currency in the + * given locale. For example, the display name for the USD + * currency object in the en_US locale is "$". + * @param currency null-terminated 3-letter ISO 4217 code + * @param locale locale in which to display currency + * @param nameStyle selector for which kind of name to return + * @param isChoiceFormat fill-in set to TRUE if the returned value + * is a ChoiceFormat pattern; otherwise it is a static string + * @param len fill-in parameter to receive length of result + * @param ec error code + * @return pointer to display string of 'len' UChars. If the resource + * data contains no entry for 'currency', then 'currency' itself is + * returned. If *isChoiceFormat is TRUE, then the result is a + * ChoiceFormat pattern. Otherwise it is a static string. + * @stable ICU 2.6 + */ +U_STABLE const UChar* U_EXPORT2 +ucurr_getName(const UChar* currency, + const char* locale, + UCurrNameStyle nameStyle, + UBool* isChoiceFormat, + int32_t* len, + UErrorCode* ec); + +/** + * Returns the number of the number of fraction digits that should + * be displayed for the given currency. + * @param currency null-terminated 3-letter ISO 4217 code + * @param ec input-output error code + * @return a non-negative number of fraction digits to be + * displayed, or 0 if there is an error + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +ucurr_getDefaultFractionDigits(const UChar* currency, + UErrorCode* ec); + +/** + * Returns the rounding increment for the given currency, or 0.0 if no + * rounding is done by the currency. + * @param currency null-terminated 3-letter ISO 4217 code + * @param ec input-output error code + * @return the non-negative rounding increment, or 0.0 if none, + * or 0.0 if there is an error + * @stable ICU 3.0 + */ +U_STABLE double U_EXPORT2 +ucurr_getRoundingIncrement(const UChar* currency, + UErrorCode* ec); + +/** + * Selector constants for ucurr_openCurrencies(). + * + * @see ucurr_openCurrencies + * @stable ICU 3.2 + */ +typedef enum UCurrCurrencyType { + /** + * Select all ISO-4217 currency codes. + * @stable ICU 3.2 + */ + UCURR_ALL = INT32_MAX, + /** + * Select only ISO-4217 commonly used currency codes. + * These currencies can be found in common use, and they usually have + * bank notes or coins associated with the currency code. + * This does not include fund codes, precious metals and other + * various ISO-4217 codes limited to special financial products. + * @stable ICU 3.2 + */ + UCURR_COMMON = 1, + /** + * Select ISO-4217 uncommon currency codes. + * These codes respresent fund codes, precious metals and other + * various ISO-4217 codes limited to special financial products. + * A fund code is a monetary resource associated with a currency. + * @stable ICU 3.2 + */ + UCURR_UNCOMMON = 2, + /** + * Select only deprecated ISO-4217 codes. + * These codes are no longer in general public use. + * @stable ICU 3.2 + */ + UCURR_DEPRECATED = 4, + /** + * Select only non-deprecated ISO-4217 codes. + * These codes are in general public use. + * @stable ICU 3.2 + */ + UCURR_NON_DEPRECATED = 8 +} UCurrCurrencyType; + +/** + * Provides a UEnumeration object for listing ISO-4217 codes. + * @param currType You can use one of several UCurrCurrencyType values for this + * variable. You can also | (or) them together to get a specific list of + * currencies. Most people will want to use the (UCURR_CURRENCY|UCURR_NON_DEPRECATED) value to + * get a list of current currencies. + * @param pErrorCode Error code + * @stable ICU 3.2 + */ +U_STABLE UEnumeration * U_EXPORT2 +ucurr_openISOCurrencies(uint32_t currType, UErrorCode *pErrorCode); + + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/udat.h b/Build/source/libs/icu-xetex/i18n/unicode/udat.h new file mode 100644 index 00000000000..34573d2a1cf --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/udat.h @@ -0,0 +1,826 @@ +/* + ******************************************************************************* + * Copyright (C) 1996-2007, International Business Machines + * Corporation and others. All Rights Reserved. + ******************************************************************************* +*/ + +#ifndef UDAT_H +#define UDAT_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/ucal.h" +#include "unicode/unum.h" +/** + * \file + * \brief C API: DateFormat + * + * <h2> Date Format C API</h2> + * + * Date Format C API consists of functions that convert dates and + * times from their internal representations to textual form and back again in a + * language-independent manner. Converting from the internal representation (milliseconds + * since midnight, January 1, 1970) to text is known as "formatting," and converting + * from text to millis is known as "parsing." We currently define only one concrete + * structure UDateFormat, which can handle pretty much all normal + * date formatting and parsing actions. + * <P> + * Date Format helps you to format and parse dates for any locale. Your code can + * be completely independent of the locale conventions for months, days of the + * week, or even the calendar format: lunar vs. solar. + * <P> + * To format a date for the current Locale with default time and date style, + * use one of the static factory methods: + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * UChar *myString; + * int32_t myStrlen = 0; + * UDateFormat* dfmt = udat_open(UDAT_DEFAULT, UDAT_DEFAULT, NULL, NULL, -1, NULL, -1, &status); + * myStrlen = udat_format(dfmt, myDate, NULL, myStrlen, NULL, &status); + * if (status==U_BUFFER_OVERFLOW_ERROR){ + * status=U_ZERO_ERROR; + * myString=(UChar*)malloc(sizeof(UChar) * (myStrlen+1) ); + * udat_format(dfmt, myDate, myString, myStrlen+1, NULL, &status); + * } + * \endcode + * </pre> + * If you are formatting multiple numbers, it is more efficient to get the + * format and use it multiple times so that the system doesn't have to fetch the + * information about the local language and country conventions multiple times. + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * int32_t i, myStrlen = 0; + * UChar* myString; + * char buffer[1024]; + * UDate myDateArr[] = { 0.0, 100000000.0, 2000000000.0 }; // test values + * UDateFormat* df = udat_open(UDAT_DEFAULT, UDAT_DEFAULT, NULL, NULL, -1, NULL, 0, &status); + * for (i = 0; i < 3; i++) { + * myStrlen = udat_format(df, myDateArr[i], NULL, myStrlen, NULL, &status); + * if(status == U_BUFFER_OVERFLOW_ERROR){ + * status = U_ZERO_ERROR; + * myString = (UChar*)malloc(sizeof(UChar) * (myStrlen+1) ); + * udat_format(df, myDateArr[i], myString, myStrlen+1, NULL, &status); + * printf("%s\n", u_austrcpy(buffer, myString) ); + * free(myString); + * } + * } + * \endcode + * </pre> + * To get specific fields of a date, you can use UFieldPosition to + * get specific fields. + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * UFieldPosition pos; + * UChar *myString; + * int32_t myStrlen = 0; + * char buffer[1024]; + * + * pos.field = 1; // Same as the DateFormat::EField enum + * UDateFormat* dfmt = udat_open(UDAT_DEFAULT, UDAT_DEFAULT, NULL, -1, NULL, 0, &status); + * myStrlen = udat_format(dfmt, myDate, NULL, myStrlen, &pos, &status); + * if (status==U_BUFFER_OVERFLOW_ERROR){ + * status=U_ZERO_ERROR; + * myString=(UChar*)malloc(sizeof(UChar) * (myStrlen+1) ); + * udat_format(dfmt, myDate, myString, myStrlen+1, &pos, &status); + * } + * printf("date format: %s\n", u_austrcpy(buffer, myString)); + * buffer[pos.endIndex] = 0; // NULL terminate the string. + * printf("UFieldPosition position equals %s\n", &buffer[pos.beginIndex]); + * \endcode + * </pre> + * To format a date for a different Locale, specify it in the call to + * udat_open() + * <pre> + * \code + * UDateFormat* df = udat_open(UDAT_SHORT, UDAT_SHORT, "fr_FR", NULL, -1, NULL, 0, &status); + * \endcode + * </pre> + * You can use a DateFormat API udat_parse() to parse. + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * int32_t parsepos=0; + * UDate myDate = udat_parse(df, myString, u_strlen(myString), &parsepos, &status); + * \endcode + * </pre> + * You can pass in different options for the arguments for date and time style + * to control the length of the result; from SHORT to MEDIUM to LONG to FULL. + * The exact result depends on the locale, but generally: + * see UDateFormatStyle for more details + * <ul type=round> + * <li> UDAT_SHORT is completely numeric, such as 12/13/52 or 3:30pm + * <li> UDAT_MEDIUM is longer, such as Jan 12, 1952 + * <li> UDAT_LONG is longer, such as January 12, 1952 or 3:30:32pm + * <li> UDAT_FULL is pretty completely specified, such as + * Tuesday, April 12, 1952 AD or 3:30:42pm PST. + * </ul> + * You can also set the time zone on the format if you wish. + * <P> + * You can also use forms of the parse and format methods with Parse Position and + * UFieldPosition to allow you to + * <ul type=round> + * <li> Progressively parse through pieces of a string. + * <li> Align any particular field, or find out where it is for selection + * on the screen. + * </ul> + */ + +/** A date formatter. + * For usage in C programs. + * @stable ICU 2.6 + */ +typedef void* UDateFormat; + +/** The possible date/time format styles + * @stable ICU 2.6 + */ +typedef enum UDateFormatStyle { + /** Full style */ + UDAT_FULL, + /** Long style */ + UDAT_LONG, + /** Medium style */ + UDAT_MEDIUM, + /** Short style */ + UDAT_SHORT, + /** Default style */ + UDAT_DEFAULT = UDAT_MEDIUM, + + /** Bitfield for relative date */ + UDAT_RELATIVE = (1 << 7), + + UDAT_FULL_RELATIVE = UDAT_FULL | UDAT_RELATIVE, + + UDAT_LONG_RELATIVE = UDAT_LONG | UDAT_RELATIVE, + + UDAT_MEDIUM_RELATIVE = UDAT_MEDIUM | UDAT_RELATIVE, + + UDAT_SHORT_RELATIVE = UDAT_SHORT | UDAT_RELATIVE, + + + /** No style */ + UDAT_NONE = -1, + /** for internal API use only */ + UDAT_IGNORE = -2 + +} UDateFormatStyle; + +/** + * FieldPosition and UFieldPosition selectors for format fields + * defined by DateFormat and UDateFormat. + * @stable ICU 3.0 + */ +typedef enum UDateFormatField { + /** + * FieldPosition and UFieldPosition selector for 'G' field alignment, + * corresponding to the UCAL_ERA field. + * @stable ICU 3.0 + */ + UDAT_ERA_FIELD = 0, + + /** + * FieldPosition and UFieldPosition selector for 'y' field alignment, + * corresponding to the UCAL_YEAR field. + * @stable ICU 3.0 + */ + UDAT_YEAR_FIELD = 1, + + /** + * FieldPosition and UFieldPosition selector for 'M' field alignment, + * corresponding to the UCAL_MONTH field. + * @stable ICU 3.0 + */ + UDAT_MONTH_FIELD = 2, + + /** + * FieldPosition and UFieldPosition selector for 'd' field alignment, + * corresponding to the UCAL_DATE field. + * @stable ICU 3.0 + */ + UDAT_DATE_FIELD = 3, + + /** + * FieldPosition and UFieldPosition selector for 'k' field alignment, + * corresponding to the UCAL_HOUR_OF_DAY field. + * UDAT_HOUR_OF_DAY1_FIELD is used for the one-based 24-hour clock. + * For example, 23:59 + 01:00 results in 24:59. + * @stable ICU 3.0 + */ + UDAT_HOUR_OF_DAY1_FIELD = 4, + + /** + * FieldPosition and UFieldPosition selector for 'H' field alignment, + * corresponding to the UCAL_HOUR_OF_DAY field. + * UDAT_HOUR_OF_DAY0_FIELD is used for the zero-based 24-hour clock. + * For example, 23:59 + 01:00 results in 00:59. + * @stable ICU 3.0 + */ + UDAT_HOUR_OF_DAY0_FIELD = 5, + + /** + * FieldPosition and UFieldPosition selector for 'm' field alignment, + * corresponding to the UCAL_MINUTE field. + * @stable ICU 3.0 + */ + UDAT_MINUTE_FIELD = 6, + + /** + * FieldPosition and UFieldPosition selector for 's' field alignment, + * corresponding to the UCAL_SECOND field. + * @stable ICU 3.0 + */ + UDAT_SECOND_FIELD = 7, + + /** + * FieldPosition and UFieldPosition selector for 'S' field alignment, + * corresponding to the UCAL_MILLISECOND field. + * @stable ICU 3.0 + */ + UDAT_FRACTIONAL_SECOND_FIELD = 8, + + /** + * FieldPosition and UFieldPosition selector for 'E' field alignment, + * corresponding to the UCAL_DAY_OF_WEEK field. + * @stable ICU 3.0 + */ + UDAT_DAY_OF_WEEK_FIELD = 9, + + /** + * FieldPosition and UFieldPosition selector for 'D' field alignment, + * corresponding to the UCAL_DAY_OF_YEAR field. + * @stable ICU 3.0 + */ + UDAT_DAY_OF_YEAR_FIELD = 10, + + /** + * FieldPosition and UFieldPosition selector for 'F' field alignment, + * corresponding to the UCAL_DAY_OF_WEEK_IN_MONTH field. + * @stable ICU 3.0 + */ + UDAT_DAY_OF_WEEK_IN_MONTH_FIELD = 11, + + /** + * FieldPosition and UFieldPosition selector for 'w' field alignment, + * corresponding to the UCAL_WEEK_OF_YEAR field. + * @stable ICU 3.0 + */ + UDAT_WEEK_OF_YEAR_FIELD = 12, + + /** + * FieldPosition and UFieldPosition selector for 'W' field alignment, + * corresponding to the UCAL_WEEK_OF_MONTH field. + * @stable ICU 3.0 + */ + UDAT_WEEK_OF_MONTH_FIELD = 13, + + /** + * FieldPosition and UFieldPosition selector for 'a' field alignment, + * corresponding to the UCAL_AM_PM field. + * @stable ICU 3.0 + */ + UDAT_AM_PM_FIELD = 14, + + /** + * FieldPosition and UFieldPosition selector for 'h' field alignment, + * corresponding to the UCAL_HOUR field. + * UDAT_HOUR1_FIELD is used for the one-based 12-hour clock. + * For example, 11:30 PM + 1 hour results in 12:30 AM. + * @stable ICU 3.0 + */ + UDAT_HOUR1_FIELD = 15, + + /** + * FieldPosition and UFieldPosition selector for 'K' field alignment, + * corresponding to the UCAL_HOUR field. + * UDAT_HOUR0_FIELD is used for the zero-based 12-hour clock. + * For example, 11:30 PM + 1 hour results in 00:30 AM. + * @stable ICU 3.0 + */ + UDAT_HOUR0_FIELD = 16, + + /** + * FieldPosition and UFieldPosition selector for 'z' field alignment, + * corresponding to the UCAL_ZONE_OFFSET and + * UCAL_DST_OFFSET fields. + * @stable ICU 3.0 + */ + UDAT_TIMEZONE_FIELD = 17, + + /** + * FieldPosition and UFieldPosition selector for 'Y' field alignment, + * corresponding to the UCAL_YEAR_WOY field. + * @stable ICU 3.0 + */ + UDAT_YEAR_WOY_FIELD = 18, + + /** + * FieldPosition and UFieldPosition selector for 'e' field alignment, + * corresponding to the UCAL_DOW_LOCAL field. + * @stable ICU 3.0 + */ + UDAT_DOW_LOCAL_FIELD = 19, + + /** + * FieldPosition and UFieldPosition selector for 'u' field alignment, + * corresponding to the UCAL_EXTENDED_YEAR field. + * @stable ICU 3.0 + */ + UDAT_EXTENDED_YEAR_FIELD = 20, + + /** + * FieldPosition and UFieldPosition selector for 'g' field alignment, + * corresponding to the UCAL_JULIAN_DAY field. + * @stable ICU 3.0 + */ + UDAT_JULIAN_DAY_FIELD = 21, + + /** + * FieldPosition and UFieldPosition selector for 'A' field alignment, + * corresponding to the UCAL_MILLISECONDS_IN_DAY field. + * @stable ICU 3.0 + */ + UDAT_MILLISECONDS_IN_DAY_FIELD = 22, + + /** + * FieldPosition and UFieldPosition selector for 'Z' field alignment, + * corresponding to the UCAL_ZONE_OFFSET and + * UCAL_DST_OFFSET fields. + * @stable ICU 3.0 + */ + UDAT_TIMEZONE_RFC_FIELD = 23, + + /** + * FieldPosition and UFieldPosition selector for 'v' field alignment, + * corresponding to the UCAL_ZONE_OFFSET field. + * @stable ICU 3.4 + */ + UDAT_TIMEZONE_GENERIC_FIELD = 24, + /** + * FieldPosition selector for 'c' field alignment, + * corresponding to the {@link #UCAL_DAY} field. + * This displays the stand alone day name, if available. + * @stable ICU 3.4 + */ + UDAT_STANDALONE_DAY_FIELD = 25, + + /** + * FieldPosition selector for 'L' field alignment, + * corresponding to the {@link #UCAL_MONTH} field. + * This displays the stand alone month name, if available. + * @stable ICU 3.4 + */ + UDAT_STANDALONE_MONTH_FIELD = 26, + + /** + * FieldPosition selector for "Q" field alignment, + * corresponding to quarters. This is implemented + * using the {@link #UCAL_MONTH} field. This + * displays the quarter. + * @stable ICU 3.6 + */ + UDAT_QUARTER_FIELD = 27, + + /** + * FieldPosition selector for the "q" field alignment, + * corresponding to stand-alone quarters. This is + * implemented using the {@link #UCAL_MONTH} field. + * This displays the stand-alone quarter. + * @stable ICU 3.6 + */ + UDAT_STANDALONE_QUARTER_FIELD = 28, + + /** + * FieldPosition and UFieldPosition selector for 'V' field alignment, + * corresponding to the UCAL_ZONE_OFFSET field. + * @stable ICU 3.8 + */ + UDAT_TIMEZONE_SPECIAL_FIELD = 29, + + /** + * Number of FieldPosition and UFieldPosition selectors for + * DateFormat and UDateFormat. + * Valid selectors range from 0 to UDAT_FIELD_COUNT-1. + * This value is subject to change if new fields are defined + * in the future. + * @stable ICU 3.0 + */ + UDAT_FIELD_COUNT = 30 + +} UDateFormatField; + +/** + * Open a new UDateFormat for formatting and parsing dates and times. + * A UDateFormat may be used to format dates in calls to {@link #udat_format }, + * and to parse dates in calls to {@link #udat_parse }. + * @param timeStyle The style used to format times; one of UDAT_FULL, UDAT_LONG, + * UDAT_MEDIUM, UDAT_SHORT, or UDAT_DEFAULT + * @param dateStyle The style used to format dates; one of UDAT_FULL, UDAT_LONG, + * UDAT_MEDIUM, UDAT_SHORT, or UDAT_DEFAULT + * @param locale The locale specifying the formatting conventions + * @param tzID A timezone ID specifying the timezone to use. If 0, use + * the default timezone. + * @param tzIDLength The length of tzID, or -1 if null-terminated. + * @param pattern A pattern specifying the format to use. + * @param patternLength The number of characters in the pattern, or -1 if null-terminated. + * @param status A pointer to an UErrorCode to receive any errors + * @return A pointer to a UDateFormat to use for formatting dates and times, or 0 if + * an error occurred. + * @stable ICU 2.0 + */ +U_STABLE UDateFormat* U_EXPORT2 +udat_open(UDateFormatStyle timeStyle, + UDateFormatStyle dateStyle, + const char *locale, + const UChar *tzID, + int32_t tzIDLength, + const UChar *pattern, + int32_t patternLength, + UErrorCode *status); + + +/** +* Close a UDateFormat. +* Once closed, a UDateFormat may no longer be used. +* @param format The formatter to close. +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_close(UDateFormat* format); + +/** + * Open a copy of a UDateFormat. + * This function performs a deep copy. + * @param fmt The format to copy + * @param status A pointer to an UErrorCode to receive any errors. + * @return A pointer to a UDateFormat identical to fmt. + * @stable ICU 2.0 + */ +U_STABLE UDateFormat* U_EXPORT2 +udat_clone(const UDateFormat *fmt, + UErrorCode *status); + +/** +* Format a date using an UDateFormat. +* The date will be formatted using the conventions specified in {@link #udat_open } +* @param format The formatter to use +* @param dateToFormat The date to format +* @param result A pointer to a buffer to receive the formatted number. +* @param resultLength The maximum size of result. +* @param position A pointer to a UFieldPosition. On input, position->field +* is read. On output, position->beginIndex and position->endIndex indicate +* the beginning and ending indices of field number position->field, if such +* a field exists. This parameter may be NULL, in which case no field +* position data is returned. +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see udat_parse +* @see UFieldPosition +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +udat_format( const UDateFormat* format, + UDate dateToFormat, + UChar* result, + int32_t resultLength, + UFieldPosition* position, + UErrorCode* status); + +/** +* Parse a string into an date/time using a UDateFormat. +* The date will be parsed using the conventions specified in {@link #udat_open } +* @param format The formatter to use. +* @param text The text to parse. +* @param textLength The length of text, or -1 if null-terminated. +* @param parsePos If not 0, on input a pointer to an integer specifying the offset at which +* to begin parsing. If not 0, on output the offset at which parsing ended. +* @param status A pointer to an UErrorCode to receive any errors +* @return The value of the parsed date/time +* @see udat_format +* @stable ICU 2.0 +*/ +U_STABLE UDate U_EXPORT2 +udat_parse( const UDateFormat* format, + const UChar* text, + int32_t textLength, + int32_t *parsePos, + UErrorCode *status); + +/** +* Parse a string into an date/time using a UDateFormat. +* The date will be parsed using the conventions specified in {@link #udat_open } +* @param format The formatter to use. +* @param calendar The calendar in which to store the parsed data. +* @param text The text to parse. +* @param textLength The length of text, or -1 if null-terminated. +* @param parsePos If not 0, on input a pointer to an integer specifying the offset at which +* to begin parsing. If not 0, on output the offset at which parsing ended. +* @param status A pointer to an UErrorCode to receive any errors +* @see udat_format +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_parseCalendar(const UDateFormat* format, + UCalendar* calendar, + const UChar* text, + int32_t textLength, + int32_t *parsePos, + UErrorCode *status); + +/** +* Determine if an UDateFormat will perform lenient parsing. +* With lenient parsing, the parser may use heuristics to interpret inputs that do not +* precisely match the pattern. With strict parsing, inputs must match the pattern. +* @param fmt The formatter to query +* @return TRUE if fmt is set to perform lenient parsing, FALSE otherwise. +* @see udat_setLenient +* @stable ICU 2.0 +*/ +U_STABLE UBool U_EXPORT2 +udat_isLenient(const UDateFormat* fmt); + +/** +* Specify whether an UDateFormat will perform lenient parsing. +* With lenient parsing, the parser may use heuristics to interpret inputs that do not +* precisely match the pattern. With strict parsing, inputs must match the pattern. +* @param fmt The formatter to set +* @param isLenient TRUE if fmt should perform lenient parsing, FALSE otherwise. +* @see dat_isLenient +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_setLenient( UDateFormat* fmt, + UBool isLenient); + +/** +* Get the UCalendar associated with an UDateFormat. +* A UDateFormat uses a UCalendar to convert a raw value to, for example, +* the day of the week. +* @param fmt The formatter to query. +* @return A pointer to the UCalendar used by fmt. +* @see udat_setCalendar +* @stable ICU 2.0 +*/ +U_STABLE const UCalendar* U_EXPORT2 +udat_getCalendar(const UDateFormat* fmt); + +/** +* Set the UCalendar associated with an UDateFormat. +* A UDateFormat uses a UCalendar to convert a raw value to, for example, +* the day of the week. +* @param fmt The formatter to set. +* @param calendarToSet A pointer to an UCalendar to be used by fmt. +* @see udat_setCalendar +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_setCalendar( UDateFormat* fmt, + const UCalendar* calendarToSet); + +/** +* Get the UNumberFormat associated with an UDateFormat. +* A UDateFormat uses a UNumberFormat to format numbers within a date, +* for example the day number. +* @param fmt The formatter to query. +* @return A pointer to the UNumberFormat used by fmt to format numbers. +* @see udat_setNumberFormat +* @stable ICU 2.0 +*/ +U_STABLE const UNumberFormat* U_EXPORT2 +udat_getNumberFormat(const UDateFormat* fmt); + +/** +* Set the UNumberFormat associated with an UDateFormat. +* A UDateFormat uses a UNumberFormat to format numbers within a date, +* for example the day number. +* @param fmt The formatter to set. +* @param numberFormatToSet A pointer to the UNumberFormat to be used by fmt to format numbers. +* @see udat_getNumberFormat +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_setNumberFormat( UDateFormat* fmt, + const UNumberFormat* numberFormatToSet); + +/** +* Get a locale for which date/time formatting patterns are available. +* A UDateFormat in a locale returned by this function will perform the correct +* formatting and parsing for the locale. +* @param index The index of the desired locale. +* @return A locale for which date/time formatting patterns are available, or 0 if none. +* @see udat_countAvailable +* @stable ICU 2.0 +*/ +U_STABLE const char* U_EXPORT2 +udat_getAvailable(int32_t index); + +/** +* Determine how many locales have date/time formatting patterns available. +* This function is most useful as determining the loop ending condition for +* calls to {@link #udat_getAvailable }. +* @return The number of locales for which date/time formatting patterns are available. +* @see udat_getAvailable +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +udat_countAvailable(void); + +/** +* Get the year relative to which all 2-digit years are interpreted. +* For example, if the 2-digit start year is 2100, the year 99 will be +* interpreted as 2199. +* @param fmt The formatter to query. +* @param status A pointer to an UErrorCode to receive any errors +* @return The year relative to which all 2-digit years are interpreted. +* @see udat_Set2DigitYearStart +* @stable ICU 2.0 +*/ +U_STABLE UDate U_EXPORT2 +udat_get2DigitYearStart( const UDateFormat *fmt, + UErrorCode *status); + +/** +* Set the year relative to which all 2-digit years will be interpreted. +* For example, if the 2-digit start year is 2100, the year 99 will be +* interpreted as 2199. +* @param fmt The formatter to set. +* @param d The year relative to which all 2-digit years will be interpreted. +* @param status A pointer to an UErrorCode to receive any errors +* @see udat_Set2DigitYearStart +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_set2DigitYearStart( UDateFormat *fmt, + UDate d, + UErrorCode *status); + +/** +* Extract the pattern from a UDateFormat. +* The pattern will follow the pattern syntax rules. +* @param fmt The formatter to query. +* @param localized TRUE if the pattern should be localized, FALSE otherwise. +* @param result A pointer to a buffer to receive the pattern. +* @param resultLength The maximum size of result. +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see udat_applyPattern +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +udat_toPattern( const UDateFormat *fmt, + UBool localized, + UChar *result, + int32_t resultLength, + UErrorCode *status); + +/** +* Set the pattern used by an UDateFormat. +* The pattern should follow the pattern syntax rules. +* @param format The formatter to set. +* @param localized TRUE if the pattern is localized, FALSE otherwise. +* @param pattern The new pattern +* @param patternLength The length of pattern, or -1 if null-terminated. +* @see udat_toPattern +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_applyPattern( UDateFormat *format, + UBool localized, + const UChar *pattern, + int32_t patternLength); + +/** + * The possible types of date format symbols + * @stable ICU 2.6 + */ +typedef enum UDateFormatSymbolType { + /** The era names, for example AD */ + UDAT_ERAS, + /** The month names, for example February */ + UDAT_MONTHS, + /** The short month names, for example Feb. */ + UDAT_SHORT_MONTHS, + /** The weekday names, for example Monday */ + UDAT_WEEKDAYS, + /** The short weekday names, for example Mon. */ + UDAT_SHORT_WEEKDAYS, + /** The AM/PM names, for example AM */ + UDAT_AM_PMS, + /** The localized characters */ + UDAT_LOCALIZED_CHARS, + /** The long era names, for example Anno Domini */ + UDAT_ERA_NAMES, + /** The narrow month names, for example F */ + UDAT_NARROW_MONTHS, + /** The narrow weekday names, for example N */ + UDAT_NARROW_WEEKDAYS, + /** Standalone context versions of months */ + UDAT_STANDALONE_MONTHS, + UDAT_STANDALONE_SHORT_MONTHS, + UDAT_STANDALONE_NARROW_MONTHS, + /** Standalone context versions of weekdays */ + UDAT_STANDALONE_WEEKDAYS, + UDAT_STANDALONE_SHORT_WEEKDAYS, + UDAT_STANDALONE_NARROW_WEEKDAYS, + /** The quarters, for example 1st Quarter */ + UDAT_QUARTERS, + /** The short quarter names, for example Q1 */ + UDAT_SHORT_QUARTERS, + /** Standalone context versions of quarters */ + UDAT_STANDALONE_QUARTERS, + UDAT_STANDALONE_SHORT_QUARTERS + +} UDateFormatSymbolType; + +struct UDateFormatSymbols; +/** Date format symbols. + * For usage in C programs. + * @stable ICU 2.6 + */ +typedef struct UDateFormatSymbols UDateFormatSymbols; + +/** +* Get the symbols associated with an UDateFormat. +* The symbols are what a UDateFormat uses to represent locale-specific data, +* for example month or day names. +* @param fmt The formatter to query. +* @param type The type of symbols to get. One of UDAT_ERAS, UDAT_MONTHS, UDAT_SHORT_MONTHS, +* UDAT_WEEKDAYS, UDAT_SHORT_WEEKDAYS, UDAT_AM_PMS, or UDAT_LOCALIZED_CHARS +* @param index The desired symbol of type type. +* @param result A pointer to a buffer to receive the pattern. +* @param resultLength The maximum size of result. +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see udat_countSymbols +* @see udat_setSymbols +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +udat_getSymbols(const UDateFormat *fmt, + UDateFormatSymbolType type, + int32_t index, + UChar *result, + int32_t resultLength, + UErrorCode *status); + +/** +* Count the number of particular symbols for an UDateFormat. +* This function is most useful as for detemining the loop termination condition +* for calls to {@link #udat_getSymbols }. +* @param fmt The formatter to query. +* @param type The type of symbols to count. One of UDAT_ERAS, UDAT_MONTHS, UDAT_SHORT_MONTHS, +* UDAT_WEEKDAYS, UDAT_SHORT_WEEKDAYS, UDAT_AM_PMS, or UDAT_LOCALIZED_CHARS +* @return The number of symbols of type type. +* @see udat_getSymbols +* @see udat_setSymbols +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +udat_countSymbols( const UDateFormat *fmt, + UDateFormatSymbolType type); + +/** +* Set the symbols associated with an UDateFormat. +* The symbols are what a UDateFormat uses to represent locale-specific data, +* for example month or day names. +* @param format The formatter to set +* @param type The type of symbols to set. One of UDAT_ERAS, UDAT_MONTHS, UDAT_SHORT_MONTHS, +* UDAT_WEEKDAYS, UDAT_SHORT_WEEKDAYS, UDAT_AM_PMS, or UDAT_LOCALIZED_CHARS +* @param index The index of the symbol to set of type type. +* @param value The new value +* @param valueLength The length of value, or -1 if null-terminated +* @param status A pointer to an UErrorCode to receive any errors +* @see udat_getSymbols +* @see udat_countSymbols +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +udat_setSymbols( UDateFormat *format, + UDateFormatSymbolType type, + int32_t index, + UChar *value, + int32_t valueLength, + UErrorCode *status); + +/** + * Get the locale for this date format object. + * You can choose between valid and actual locale. + * @param fmt The formatter to get the locale from + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale name + * @stable ICU 2.8 + */ +U_STABLE const char* U_EXPORT2 +udat_getLocaleByType(const UDateFormat *fmt, + ULocDataLocaleType type, + UErrorCode* status); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/udatpg.h b/Build/source/libs/icu-xetex/i18n/unicode/udatpg.h new file mode 100644 index 00000000000..4a7f29594dd --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/udatpg.h @@ -0,0 +1,475 @@ +/* +******************************************************************************* +* +* Copyright (C) 2007, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: udatpg.h +* encoding: US-ASCII +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2007jul30 +* created by: Markus W. Scherer +*/ + +#ifndef __UDATPG_H__ +#define __UDATPG_H__ + +#include "unicode/utypes.h" +#include "unicode/uenum.h" + +/** + * \file + * \brief C API: Wrapper for DateTimePatternGenerator (unicode/dtptngen.h). + * + * UDateTimePatternGenerator provides flexible generation of date format patterns, + * like "yy-MM-dd". The user can build up the generator by adding successive + * patterns. Once that is done, a query can be made using a "skeleton", which is + * a pattern which just includes the desired fields and lengths. The generator + * will return the "best fit" pattern corresponding to that skeleton. + * <p>The main method people will use is udatpg_getBestPattern, since normally + * UDateTimePatternGenerator is pre-built with data from a particular locale. + * However, generators can be built directly from other data as well. + * <p><i>Issue: may be useful to also have a function that returns the list of + * fields in a pattern, in order, since we have that internally. + * That would be useful for getting the UI order of field elements.</i> + */ + +/** + * Opaque type for a date/time pattern generator object. + * @draft ICU 3.8 + */ +typedef void *UDateTimePatternGenerator; + +#ifndef U_HIDE_DRAFT_API + +/** + * Field number constants for udatpg_getAppendItemFormats() and similar functions. + * These constants are separate from UDateFormatField despite semantic overlap + * because some fields are merged for the date/time pattern generator. + * @draft ICU 3.8 + */ +typedef enum UDateTimePatternField { + /** @draft ICU 3.8 */ + UDATPG_ERA_FIELD, + /** @draft ICU 3.8 */ + UDATPG_YEAR_FIELD, + /** @draft ICU 3.8 */ + UDATPG_QUARTER_FIELD, + /** @draft ICU 3.8 */ + UDATPG_MONTH_FIELD, + /** @draft ICU 3.8 */ + UDATPG_WEEK_OF_YEAR_FIELD, + /** @draft ICU 3.8 */ + UDATPG_WEEK_OF_MONTH_FIELD, + /** @draft ICU 3.8 */ + UDATPG_WEEKDAY_FIELD, + /** @draft ICU 3.8 */ + UDATPG_DAY_OF_YEAR_FIELD, + /** @draft ICU 3.8 */ + UDATPG_DAY_OF_WEEK_IN_MONTH_FIELD, + /** @draft ICU 3.8 */ + UDATPG_DAY_FIELD, + /** @draft ICU 3.8 */ + UDATPG_DAYPERIOD_FIELD, + /** @draft ICU 3.8 */ + UDATPG_HOUR_FIELD, + /** @draft ICU 3.8 */ + UDATPG_MINUTE_FIELD, + /** @draft ICU 3.8 */ + UDATPG_SECOND_FIELD, + /** @draft ICU 3.8 */ + UDATPG_FRACTIONAL_SECOND_FIELD, + /** @draft ICU 3.8 */ + UDATPG_ZONE_FIELD, + /** @draft ICU 3.8 */ + UDATPG_FIELD_COUNT +} UDateTimePatternField; + +/** + * Status return values from udatpg_addPattern(). + * @draft ICU 3.8 + */ +typedef enum UDateTimePatternConflict { + /** @draft ICU 3.8 */ + UDATPG_NO_CONFLICT, + /** @draft ICU 3.8 */ + UDATPG_BASE_CONFLICT, + /** @draft ICU 3.8 */ + UDATPG_CONFLICT, + /** @draft ICU 3.8 */ + UDATPG_CONFLICT_COUNT +} UDateTimePatternConflict; + +#endif + +/** + * Open a generator according to a given locale. + * @param locale + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return a pointer to UDateTimePatternGenerator. + * @draft ICU 3.8 + */ +U_DRAFT UDateTimePatternGenerator * U_EXPORT2 +udatpg_open(const char *locale, UErrorCode *pErrorCode); + +/** + * Open an empty generator, to be constructed with udatpg_addPattern(...) etc. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return a pointer to UDateTimePatternGenerator. + * @draft ICU 3.8 + */ +U_DRAFT UDateTimePatternGenerator * U_EXPORT2 +udatpg_openEmpty(UErrorCode *pErrorCode); + +/** + * Close a generator. + * @param dtpg a pointer to UDateTimePatternGenerator. + * @draft ICU 3.8 + */ +U_DRAFT void U_EXPORT2 +udatpg_close(UDateTimePatternGenerator *dtpg); + +/** + * Create a copy pf a generator. + * @param dtpg a pointer to UDateTimePatternGenerator to be copied. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return a pointer to a new UDateTimePatternGenerator. + * @draft ICU 3.8 + */ +U_DRAFT UDateTimePatternGenerator * U_EXPORT2 +udatpg_clone(const UDateTimePatternGenerator *dtpg, UErrorCode *pErrorCode); + +/** + * Get the best pattern matching the input skeleton. It is guaranteed to + * have all of the fields in the skeleton. + * + * Note that this function uses a non-const UDateTimePatternGenerator: + * It uses a stateful pattern parser which is set up for each generator object, + * rather than creating one for each function call. + * Consecutive calls to this function do not affect each other, + * but this function cannot be used concurrently on a single generator object. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param skeleton + * The skeleton is a pattern containing only the variable fields. + * For example, "MMMdd" and "mmhh" are skeletons. + * @param length the length of skeleton + * @param bestPattern + * The best pattern found from the given skeleton. + * @param capacity the capacity of bestPattern. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return the length of bestPattern. + * @draft ICU 3.8 + */ +U_DRAFT int32_t U_EXPORT2 +udatpg_getBestPattern(UDateTimePatternGenerator *dtpg, + const UChar *skeleton, int32_t length, + UChar *bestPattern, int32_t capacity, + UErrorCode *pErrorCode); + +/** + * Get a unique skeleton from a given pattern. For example, + * both "MMM-dd" and "dd/MMM" produce the skeleton "MMMdd". + * + * Note that this function uses a non-const UDateTimePatternGenerator: + * It uses a stateful pattern parser which is set up for each generator object, + * rather than creating one for each function call. + * Consecutive calls to this function do not affect each other, + * but this function cannot be used concurrently on a single generator object. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pattern input pattern, such as "dd/MMM". + * @param length the length of pattern. + * @param skeleton such as "MMMdd" + * @param capacity the capacity of skeleton. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return the length of skeleton. + * @draft ICU 3.8 + */ +U_DRAFT int32_t U_EXPORT2 +udatpg_getSkeleton(UDateTimePatternGenerator *dtpg, + const UChar *pattern, int32_t length, + UChar *skeleton, int32_t capacity, + UErrorCode *pErrorCode); + +/** + * Get a unique base skeleton from a given pattern. This is the same + * as the skeleton, except that differences in length are minimized so + * as to only preserve the difference between string and numeric form. So + * for example, both "MMM-dd" and "d/MMM" produce the skeleton "MMMd" + * (notice the single d). + * + * Note that this function uses a non-const UDateTimePatternGenerator: + * It uses a stateful pattern parser which is set up for each generator object, + * rather than creating one for each function call. + * Consecutive calls to this function do not affect each other, + * but this function cannot be used concurrently on a single generator object. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pattern input pattern, such as "dd/MMM". + * @param length the length of pattern. + * @param baseSkeleton such as "Md" + * @param capacity the capacity of base skeleton. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return the length of baseSkeleton. + * @draft ICU 3.8 + */ +U_DRAFT int32_t U_EXPORT2 +udatpg_getBaseSkeleton(UDateTimePatternGenerator *dtpg, + const UChar *pattern, int32_t length, + UChar *baseSkeleton, int32_t capacity, + UErrorCode *pErrorCode); + +/** + * Adds a pattern to the generator. If the pattern has the same skeleton as + * an existing pattern, and the override parameter is set, then the previous + * value is overriden. Otherwise, the previous value is retained. In either + * case, the conflicting status is set and previous vale is stored in + * conflicting pattern. + * <p> + * Note that single-field patterns (like "MMM") are automatically added, and + * don't need to be added explicitly! + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pattern input pattern, such as "dd/MMM" + * @param patternLength the length of pattern. + * @param override When existing values are to be overridden use true, + * otherwise use false. + * @param conflictingPattern Previous pattern with the same skeleton. + * @param capacity the capacity of conflictingPattern. + * @param pLength a pointer to the length of conflictingPattern. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return conflicting status. The value could be UDATPG_NO_CONFLICT, + * UDATPG_BASE_CONFLICT or UDATPG_CONFLICT. + * @draft ICU 3.8 + */ +U_DRAFT UDateTimePatternConflict U_EXPORT2 +udatpg_addPattern(UDateTimePatternGenerator *dtpg, + const UChar *pattern, int32_t patternLength, + UBool override, + UChar *conflictingPattern, int32_t capacity, int32_t *pLength, + UErrorCode *pErrorCode); + +/** + * An AppendItem format is a pattern used to append a field if there is no + * good match. For example, suppose that the input skeleton is "GyyyyMMMd", + * and there is no matching pattern internally, but there is a pattern + * matching "yyyyMMMd", say "d-MM-yyyy". Then that pattern is used, plus the + * G. The way these two are conjoined is by using the AppendItemFormat for G + * (era). So if that value is, say "{0}, {1}" then the final resulting + * pattern is "d-MM-yyyy, G". + * <p> + * There are actually three available variables: {0} is the pattern so far, + * {1} is the element we are adding, and {2} is the name of the element. + * <p> + * This reflects the way that the CLDR data is organized. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param field UDateTimePatternField, such as UDATPG_ERA_FIELD + * @param value pattern, such as "{0}, {1}" + * @param length the length of value. + * @draft ICU 3.8 + */ +U_DRAFT void U_EXPORT2 +udatpg_setAppendItemFormat(UDateTimePatternGenerator *dtpg, + UDateTimePatternField field, + const UChar *value, int32_t length); + +/** + * Getter corresponding to setAppendItemFormat. Values below 0 or at or + * above UDATPG_FIELD_COUNT are illegal arguments. + * + * @param dtpg A pointer to UDateTimePatternGenerator. + * @param field UDateTimePatternField, such as UDATPG_ERA_FIELD + * @param pLength A pointer that will receive the length of appendItemFormat. + * @return appendItemFormat for field. + * @draft ICU 3.8 + */ +U_DRAFT const UChar * U_EXPORT2 +udatpg_getAppendItemFormat(const UDateTimePatternGenerator *dtpg, + UDateTimePatternField field, + int32_t *pLength); + +/** + * Set the name of field, eg "era" in English for ERA. These are only + * used if the corresponding AppendItemFormat is used, and if it contains a + * {2} variable. + * <p> + * This reflects the way that the CLDR data is organized. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param field UDateTimePatternField + * @param value name for the field. + * @param length the length of value. + * @draft ICU 3.8 + */ +U_DRAFT void U_EXPORT2 +udatpg_setAppendItemName(UDateTimePatternGenerator *dtpg, + UDateTimePatternField field, + const UChar *value, int32_t length); + +/** + * Getter corresponding to setAppendItemNames. Values below 0 or at or above + * UDATPG_FIELD_COUNT are illegal arguments. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param field UDateTimePatternField, such as UDATPG_ERA_FIELD + * @param pLength A pointer that will receive the length of the name for field. + * @return name for field + * @draft ICU 3.8 + */ +U_DRAFT const UChar * U_EXPORT2 +udatpg_getAppendItemName(const UDateTimePatternGenerator *dtpg, + UDateTimePatternField field, + int32_t *pLength); + +/** + * The date time format is a message format pattern used to compose date and + * time patterns. The default value is "{0} {1}", where {0} will be replaced + * by the date pattern and {1} will be replaced by the time pattern. + * <p> + * This is used when the input skeleton contains both date and time fields, + * but there is not a close match among the added patterns. For example, + * suppose that this object was created by adding "dd-MMM" and "hh:mm", and + * its datetimeFormat is the default "{0} {1}". Then if the input skeleton + * is "MMMdhmm", there is not an exact match, so the input skeleton is + * broken up into two components "MMMd" and "hmm". There are close matches + * for those two skeletons, so the result is put together with this pattern, + * resulting in "d-MMM h:mm". + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param dtFormat + * message format pattern, here {0} will be replaced by the date + * pattern and {1} will be replaced by the time pattern. + * @param length the length of dtFormat. + * @draft ICU 3.8 + */ +U_DRAFT void U_EXPORT2 +udatpg_setDateTimeFormat(const UDateTimePatternGenerator *dtpg, + const UChar *dtFormat, int32_t length); + +/** + * Getter corresponding to setDateTimeFormat. + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pLength A pointer that will receive the length of the format + * @return dateTimeFormat. + * @draft ICU 3.8 + */ +U_DRAFT const UChar * U_EXPORT2 +udatpg_getDateTimeFormat(const UDateTimePatternGenerator *dtpg, + int32_t *pLength); + +/** + * The decimal value is used in formatting fractions of seconds. If the + * skeleton contains fractional seconds, then this is used with the + * fractional seconds. For example, suppose that the input pattern is + * "hhmmssSSSS", and the best matching pattern internally is "H:mm:ss", and + * the decimal string is ",". Then the resulting pattern is modified to be + * "H:mm:ss,SSSS" + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param decimal + * @param length the length of decimal. + * @draft ICU 3.8 + */ +U_DRAFT void U_EXPORT2 +udatpg_setDecimal(UDateTimePatternGenerator *dtpg, + const UChar *decimal, int32_t length); + +/** + * Getter corresponding to setDecimal. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pLength A pointer that will receive the length of the decimal string. + * @return corresponding to the decimal point. + * @draft ICU 3.8 + */ +U_DRAFT const UChar * U_EXPORT2 +udatpg_getDecimal(const UDateTimePatternGenerator *dtpg, + int32_t *pLength); + +/** + * Adjusts the field types (width and subtype) of a pattern to match what is + * in a skeleton. That is, if you supply a pattern like "d-M H:m", and a + * skeleton of "MMMMddhhmm", then the input pattern is adjusted to be + * "dd-MMMM hh:mm". This is used internally to get the best match for the + * input skeleton, but can also be used externally. + * + * Note that this function uses a non-const UDateTimePatternGenerator: + * It uses a stateful pattern parser which is set up for each generator object, + * rather than creating one for each function call. + * Consecutive calls to this function do not affect each other, + * but this function cannot be used concurrently on a single generator object. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pattern Input pattern + * @param patternLength the length of input pattern. + * @param skeleton + * @param skeletonLength the length of input skeleton. + * @param dest pattern adjusted to match the skeleton fields widths and subtypes. + * @param destCapacity the capacity of dest. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return the length of dest. + * @draft ICU 3.8 + */ +U_DRAFT int32_t U_EXPORT2 +udatpg_replaceFieldTypes(UDateTimePatternGenerator *dtpg, + const UChar *pattern, int32_t patternLength, + const UChar *skeleton, int32_t skeletonLength, + UChar *dest, int32_t destCapacity, + UErrorCode *pErrorCode); + +/** + * Return a UEnumeration list of all the skeletons in canonical form. + * Call udatpg_getPatternForSkeleton() to get the corresponding pattern. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call + * @return a UEnumeration list of all the skeletons + * The caller must close the object. + * @draft ICU 3.8 + */ +U_DRAFT UEnumeration * U_EXPORT2 +udatpg_openSkeletons(const UDateTimePatternGenerator *dtpg, UErrorCode *pErrorCode); + +/** + * Return a UEnumeration list of all the base skeletons in canonical form. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param pErrorCode a pointer to the UErrorCode which must not indicate a + * failure before the function call. + * @return a UEnumeration list of all the base skeletons + * The caller must close the object. + * @draft ICU 3.8 + */ +U_DRAFT UEnumeration * U_EXPORT2 +udatpg_openBaseSkeletons(const UDateTimePatternGenerator *dtpg, UErrorCode *pErrorCode); + +/** + * Get the pattern corresponding to a given skeleton. + * + * @param dtpg a pointer to UDateTimePatternGenerator. + * @param skeleton + * @param skeletonLength pointer to the length of skeleton. + * @param pLength pointer to the length of return pattern. + * @return pattern corresponding to a given skeleton. + * @draft ICU 3.8 + */ +U_DRAFT const UChar * U_EXPORT2 +udatpg_getPatternForSkeleton(const UDateTimePatternGenerator *dtpg, + const UChar *skeleton, int32_t skeletonLength, + int32_t *pLength); + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/ulocdata.h b/Build/source/libs/icu-xetex/i18n/unicode/ulocdata.h new file mode 100644 index 00000000000..6bcc47220a7 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/ulocdata.h @@ -0,0 +1,194 @@ +/* +****************************************************************************** +* * +* Copyright (C) 2003-2007, International Business Machines * +* Corporation and others. All Rights Reserved. * +* * +****************************************************************************** +* file name: ulocdata.h +* encoding: US-ASCII +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2003Oct21 +* created by: Ram Viswanadha +*/ + +#ifndef __ULOCDATA_H__ +#define __ULOCDATA_H__ + +#include "unicode/ures.h" +#include "unicode/uloc.h" +#include "unicode/uset.h" + +/** + * \file + * \brief C API: Provides access to locale data. + */ + +/** Forward declaration of the ULocaleData structure. @stable ICU 3.6 */ +struct ULocaleData; + +/** A locale data object. @stable ICU 3.6 */ +typedef struct ULocaleData ULocaleData; + + + +/** The possible types of exemplar character sets. + * @stable ICU 3.4 + */ +typedef enum ULocaleDataExemplarSetType { + ULOCDATA_ES_STANDARD=0, /* Basic set */ + ULOCDATA_ES_AUXILIARY=1, /* Auxiliary set */ + ULOCDATA_ES_COUNT=2 +} ULocaleDataExemplarSetType; + +/** The possible types of delimiters. + * @stable ICU 3.4 + */ +typedef enum ULocaleDataDelimiterType { +#ifndef U_HIDE_DRAFT_API + ULOCDATA_QUOTATION_START = 0, /* Quotation start */ + ULOCDATA_QUOTATION_END = 1, /* Quotation end */ + ULOCDATA_ALT_QUOTATION_START = 2, /* Alternate quotation start */ + ULOCDATA_ALT_QUOTATION_END = 3, /* Alternate quotation end */ +#endif + ULOCDATA_DELIMITER_COUNT = 4 +} ULocaleDataDelimiterType; + +/** + * Opens a locale data object for the given locale + * + * @param localeID Specifies the locale associated with this locale + * data object. + * @param status Pointer to error status code. + * @stable ICU 3.4 + */ +U_STABLE ULocaleData* U_EXPORT2 +ulocdata_open(const char *localeID, UErrorCode *status); + +/** + * Closes a locale data object. + * + * @param uld The locale data object to close + * @stable ICU 3.4 + */ +U_STABLE void U_EXPORT2 +ulocdata_close(ULocaleData *uld); + +/** + * Sets the "no Substitute" attribute of the locale data + * object. If true, then any methods associated with the + * locale data object will return null when there is no + * data available for that method, given the locale ID + * supplied to ulocdata_open(). + * + * @param uld The locale data object to set. + * @param setting Value of the "no substitute" attribute. + * @stable ICU 3.4 + */ +U_STABLE void U_EXPORT2 +ulocdata_setNoSubstitute(ULocaleData *uld, UBool setting); + +/** + * Retrieves the current "no Substitute" value of the locale data + * object. If true, then any methods associated with the + * locale data object will return null when there is no + * data available for that method, given the locale ID + * supplied to ulocdata_open(). + * + * @param uld Pointer to the The locale data object to set. + * @return UBool Value of the "no substitute" attribute. + * @stable ICU 3.4 + */ +U_STABLE UBool U_EXPORT2 +ulocdata_getNoSubstitute(ULocaleData *uld); + +/** + * Returns the set of exemplar characters for a locale. + * + * @param uld Pointer to the locale data object from which the + * exemplar character set is to be retrieved. + * @param fillIn Pointer to a USet object to receive the + * exemplar character set for the given locale. Previous + * contents of fillIn are lost. <em>If fillIn is NULL, + * then a new USet is created and returned. The caller + * owns the result and must dispose of it by calling + * uset_close.</em> + * @param options Bitmask for options to apply to the exemplar pattern. + * Specify zero to retrieve the exemplar set as it is + * defined in the locale data. Specify + * USET_CASE_INSENSITIVE to retrieve a case-folded + * exemplar set. See uset_applyPattern for a complete + * list of valid options. The USET_IGNORE_SPACE bit is + * always set, regardless of the value of 'options'. + * @param extype Specifies the type of exemplar set to be retrieved. + * @param status Pointer to an input-output error code value; + * must not be NULL. + * @return USet* Either fillIn, or if fillIn is NULL, a pointer to + * a newly-allocated USet that the user must close. + * @stable ICU 3.4 + */ +U_STABLE USet* U_EXPORT2 +ulocdata_getExemplarSet(ULocaleData *uld, USet *fillIn, + uint32_t options, ULocaleDataExemplarSetType extype, UErrorCode *status); + +/** + * Returns one of the delimiter strings associated with a locale. + * + * @param uld Pointer to the locale data object from which the + * delimiter string is to be retrieved. + * @param type the type of delimiter to be retrieved. + * @param result A pointer to a buffer to receive the result. + * @param resultLength The maximum size of result. + * @param status Pointer to an error code value + * @return int32_t The total buffer size needed; if greater than resultLength, + * the output was truncated. + * @stable ICU 3.4 + */ +U_STABLE int32_t U_EXPORT2 +ulocdata_getDelimiter(ULocaleData *uld, ULocaleDataDelimiterType type, UChar *result, int32_t resultLength, UErrorCode *status); + +/** + * Enumeration for representing the measurement systems. + * @stable ICU 2.8 + */ +typedef enum UMeasurementSystem { + UMS_SI, /** Measurement system specified by SI otherwise known as Metric system. */ + UMS_US, /** Measurement system followed in the United States of America. */ + UMS_LIMIT +} UMeasurementSystem; + +/** + * Returns the measurement system used in the locale specified by the localeID. + * Please note that this API will change in ICU 3.6 and will use an ulocdata object. + * + * @param localeID The id of the locale for which the measurement system to be retrieved. + * @param status Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return UMeasurementSystem the measurement system used in the locale. + * @stable ICU 2.8 + */ +U_STABLE UMeasurementSystem U_EXPORT2 +ulocdata_getMeasurementSystem(const char *localeID, UErrorCode *status); + +/** + * Returns the element gives the normal business letter size, and customary units. + * The units for the numbers are always in <em>milli-meters</em>. + * For US since 8.5 and 11 do not yeild an integral value when converted to milli-meters, + * the values are rounded off. + * So for A4 size paper the height and width are 297 mm and 210 mm repectively, + * and for US letter size the height and width are 279 mm and 216 mm respectively. + * Please note that this API will change in ICU 3.6 and will use an ulocdata object. + * + * @param localeID The id of the locale for which the paper size information to be retrieved. + * @param height A pointer to int to recieve the height information. + * @param width A pointer to int to recieve the width information. + * @param status Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @stable ICU 2.8 + */ +U_STABLE void U_EXPORT2 +ulocdata_getPaperSize(const char *localeID, int32_t *height, int32_t *width, UErrorCode *status); + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/umsg.h b/Build/source/libs/icu-xetex/i18n/unicode/umsg.h new file mode 100644 index 00000000000..32ed063c274 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/umsg.h @@ -0,0 +1,647 @@ +/* +******************************************************************************* +* Copyright (C) 1996-2006, International Business Machines Corporation +* and others. All Rights Reserved. +******************************************************************************* +* +* file name: umsg.h +* encoding: US-ASCII +* tab size: 8 (not used) +* indentation:4 +* +* Change history: +* +* 08/5/2001 Ram Added C wrappers for C++ API. +* +* +*/ + +#ifndef UMSG_H +#define UMSG_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uloc.h" +#include "unicode/parseerr.h" +#include <stdarg.h> +/** + * \file + * \brief C API: MessageFormat + * + * <h2>Message Format C API </h2> + * + * Provides means to produce concatenated messages in language-neutral way. + * Use this for all concatenations that show up to end users. + * <P> + * Takes a set of objects, formats them, then inserts the formatted + * strings into the pattern at the appropriate places. + * <P> + * Here are some examples of usage: + * Example 1: + * <pre> + * \code + * UChar *result, *tzID, *str; + * UChar pattern[100]; + * int32_t resultLengthOut, resultlength; + * UCalendar *cal; + * UDate d1; + * UDateFormat *def1; + * UErrorCode status = U_ZERO_ERROR; + * + * str=(UChar*)malloc(sizeof(UChar) * (strlen("disturbance in force") +1)); + * u_uastrcpy(str, "disturbance in force"); + * tzID=(UChar*)malloc(sizeof(UChar) * 4); + * u_uastrcpy(tzID, "PST"); + * cal=ucal_open(tzID, u_strlen(tzID), "en_US", UCAL_TRADITIONAL, &status); + * ucal_setDateTime(cal, 1999, UCAL_MARCH, 18, 0, 0, 0, &status); + * d1=ucal_getMillis(cal, &status); + * u_uastrcpy(pattern, "On {0, date, long}, there was a {1} on planet {2,number,integer}"); + * resultlength=0; + * resultLengthOut=u_formatMessage( "en_US", pattern, u_strlen(pattern), NULL, resultlength, &status, d1, str, 7); + * if(status==U_BUFFER_OVERFLOW_ERROR){ + * status=U_ZERO_ERROR; + * resultlength=resultLengthOut+1; + * result=(UChar*)realloc(result, sizeof(UChar) * resultlength); + * u_formatMessage( "en_US", pattern, u_strlen(pattern), result, resultlength, &status, d1, str, 7); + * } + * printf("%s\n", austrdup(result) );//austrdup( a function used to convert UChar* to char*) + * //output>: "On March 18, 1999, there was a disturbance in force on planet 7 + * \endcode + * </pre> + * Typically, the message format will come from resources, and the + * arguments will be dynamically set at runtime. + * <P> + * Example 2: + * <pre> + * \code + * UChar* str; + * UErrorCode status = U_ZERO_ERROR; + * UChar *result; + * UChar pattern[100]; + * int32_t resultlength, resultLengthOut, i; + * double testArgs= { 100.0, 1.0, 0.0}; + * + * str=(UChar*)malloc(sizeof(UChar) * 10); + * u_uastrcpy(str, "MyDisk"); + * u_uastrcpy(pattern, "The disk {1} contains {0,choice,0#no files|1#one file|1<{0,number,integer} files}"); + * for(i=0; i<3; i++){ + * resultlength=0; + * resultLengthOut=u_formatMessage( "en_US", pattern, u_strlen(pattern), NULL, resultlength, &status, testArgs[i], str); + * if(status==U_BUFFER_OVERFLOW_ERROR){ + * status=U_ZERO_ERROR; + * resultlength=resultLengthOut+1; + * result=(UChar*)malloc(sizeof(UChar) * resultlength); + * u_formatMessage( "en_US", pattern, u_strlen(pattern), result, resultlength, &status, testArgs[i], str); + * } + * printf("%s\n", austrdup(result) ); //austrdup( a function used to convert UChar* to char*) + * free(result); + * } + * // output, with different testArgs: + * // output: The disk "MyDisk" contains 100 files. + * // output: The disk "MyDisk" contains one file. + * // output: The disk "MyDisk" contains no files. + * \endcode + * </pre> + * + * The pattern is of the following form. Legend: + * <pre> + * \code + * {optional item} + * (group that may be repeated)* + * \endcode + * </pre> + * Do not confuse optional items with items inside quotes braces, such + * as this: "{". Quoted braces are literals. + * <pre> + * \code + * messageFormatPattern := string ( "{" messageFormatElement "}" string )* + * + * messageFormatElement := argument { "," elementFormat } + * + * elementFormat := "time" { "," datetimeStyle } + * | "date" { "," datetimeStyle } + * | "number" { "," numberStyle } + * | "choice" "," choiceStyle + * + * datetimeStyle := "short" + * | "medium" + * | "long" + * | "full" + * | dateFormatPattern + * + * numberStyle := "currency" + * | "percent" + * | "integer" + * | numberFormatPattern + * + * choiceStyle := choiceFormatPattern + * \endcode + * </pre> + * If there is no elementFormat, then the argument must be a string, + * which is substituted. If there is no dateTimeStyle or numberStyle, + * then the default format is used (e.g. NumberFormat.getInstance(), + * DateFormat.getDefaultTime() or DateFormat.getDefaultDate(). For + * a ChoiceFormat, the pattern must always be specified, since there + * is no default. + * <P> + * In strings, single quotes can be used to quote the "{" sign if + * necessary. A real single quote is represented by ''. Inside a + * messageFormatElement, quotes are [not] removed. For example, + * {1,number,$'#',##} will produce a number format with the pound-sign + * quoted, with a result such as: "$#31,45". + * <P> + * If a pattern is used, then unquoted braces in the pattern, if any, + * must match: that is, "ab {0} de" and "ab '}' de" are ok, but "ab + * {0'}' de" and "ab } de" are not. + * <p> + * <dl><dt><b>Warning:</b><dd>The rules for using quotes within message + * format patterns unfortunately have shown to be somewhat confusing. + * In particular, it isn't always obvious to localizers whether single + * quotes need to be doubled or not. Make sure to inform localizers about + * the rules, and tell them (for example, by using comments in resource + * bundle source files) which strings will be processed by MessageFormat. + * Note that localizers may need to use single quotes in translated + * strings where the original version doesn't have them. + * <br>Note also that the simplest way to avoid the problem is to + * use the real apostrophe (single quote) character U+2019 (') for + * human-readable text, and to use the ASCII apostrophe (U+0027 ' ) + * only in program syntax, like quoting in MessageFormat. + * See the annotations for U+0027 Apostrophe in The Unicode Standard.</p> + * </dl> + * <P> + * The argument is a number from 0 to 9, which corresponds to the + * arguments presented in an array to be formatted. + * <P> + * It is ok to have unused arguments in the array. With missing + * arguments or arguments that are not of the right class for the + * specified format, a failing UErrorCode result is set. + * <P> + + * <P> + * [Note:] As we see above, the string produced by a choice Format in + * MessageFormat is treated specially; occurances of '{' are used to + * indicated subformats. + * <P> + * [Note:] Formats are numbered by order of variable in the string. + * This is [not] the same as the argument numbering! + * <pre> + * \code + * For example: with "abc{2}def{3}ghi{0}...", + * + * format0 affects the first variable {2} + * format1 affects the second variable {3} + * format2 affects the second variable {0} + * \endcode + * </pre> + * and so on. + */ + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param locale The locale for which the message will be formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments specified + * in pattern. + * @return The total buffer size needed; if greater than resultLength, the + * output was truncated. + * @see u_parseMessage + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_formatMessage(const char *locale, + const UChar *pattern, + int32_t patternLength, + UChar *result, + int32_t resultLength, + UErrorCode *status, + ...); + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param locale The locale for which the message will be formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param ap A variable-length argument list containing the arguments specified + * @param status A pointer to an UErrorCode to receive any errors + * in pattern. + * @return The total buffer size needed; if greater than resultLength, the + * output was truncated. + * @see u_parseMessage + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_vformatMessage( const char *locale, + const UChar *pattern, + int32_t patternLength, + UChar *result, + int32_t resultLength, + va_list ap, + UErrorCode *status); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #u_formatMessage }. + * @param locale The locale for which the message is formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments + * specified in pattern. + * @see u_formatMessage + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +u_parseMessage( const char *locale, + const UChar *pattern, + int32_t patternLength, + const UChar *source, + int32_t sourceLength, + UErrorCode *status, + ...); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #u_formatMessage }. + * @param locale The locale for which the message is formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param ap A variable-length argument list containing the arguments + * @param status A pointer to an UErrorCode to receive any errors + * specified in pattern. + * @see u_formatMessage + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +u_vparseMessage(const char *locale, + const UChar *pattern, + int32_t patternLength, + const UChar *source, + int32_t sourceLength, + va_list ap, + UErrorCode *status); + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param locale The locale for which the message will be formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments specified + * in pattern. + * @param parseError A pointer to UParseError to receive information about errors + * occurred during parsing. + * @return The total buffer size needed; if greater than resultLength, the + * output was truncated. + * @see u_parseMessage + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_formatMessageWithError( const char *locale, + const UChar *pattern, + int32_t patternLength, + UChar *result, + int32_t resultLength, + UParseError *parseError, + UErrorCode *status, + ...); + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param locale The locale for which the message will be formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param parseError A pointer to UParseError to receive information about errors + * occurred during parsing. + * @param ap A variable-length argument list containing the arguments specified + * @param status A pointer to an UErrorCode to receive any errors + * in pattern. + * @return The total buffer size needed; if greater than resultLength, the + * output was truncated. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_vformatMessageWithError( const char *locale, + const UChar *pattern, + int32_t patternLength, + UChar *result, + int32_t resultLength, + UParseError* parseError, + va_list ap, + UErrorCode *status); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #u_formatMessage }. + * @param locale The locale for which the message is formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param parseError A pointer to UParseError to receive information about errors + * occurred during parsing. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments + * specified in pattern. + * @see u_formatMessage + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +u_parseMessageWithError(const char *locale, + const UChar *pattern, + int32_t patternLength, + const UChar *source, + int32_t sourceLength, + UParseError *parseError, + UErrorCode *status, + ...); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #u_formatMessage }. + * @param locale The locale for which the message is formatted + * @param pattern The pattern specifying the message's format + * @param patternLength The length of pattern + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param ap A variable-length argument list containing the arguments + * @param parseError A pointer to UParseError to receive information about errors + * occurred during parsing. + * @param status A pointer to an UErrorCode to receive any errors + * specified in pattern. + * @see u_formatMessage + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +u_vparseMessageWithError(const char *locale, + const UChar *pattern, + int32_t patternLength, + const UChar *source, + int32_t sourceLength, + va_list ap, + UParseError *parseError, + UErrorCode* status); + +/*----------------------- New experimental API --------------------------- */ +/** + * The message format object + * @stable ICU 2.0 + */ +typedef void* UMessageFormat; + + +/** + * Open a message formatter with given pattern and for the given locale. + * @param pattern A pattern specifying the format to use. + * @param patternLength Length of the pattern to use + * @param locale The locale for which the messages are formatted. + * @param parseError A pointer to UParseError struct to receive any errors + * occured during parsing. Can be NULL. + * @param status A pointer to an UErrorCode to receive any errors. + * @return A pointer to a UMessageFormat to use for formatting + * messages, or 0 if an error occurred. + * @stable ICU 2.0 + */ +U_STABLE UMessageFormat* U_EXPORT2 +umsg_open( const UChar *pattern, + int32_t patternLength, + const char *locale, + UParseError *parseError, + UErrorCode *status); + +/** + * Close a UMessageFormat. + * Once closed, a UMessageFormat may no longer be used. + * @param format The formatter to close. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +umsg_close(UMessageFormat* format); + +/** + * Open a copy of a UMessageFormat. + * This function performs a deep copy. + * @param fmt The formatter to copy + * @param status A pointer to an UErrorCode to receive any errors. + * @return A pointer to a UDateFormat identical to fmt. + * @stable ICU 2.0 + */ +U_STABLE UMessageFormat U_EXPORT2 +umsg_clone(const UMessageFormat *fmt, + UErrorCode *status); + +/** + * Sets the locale. This locale is used for fetching default number or date + * format information. + * @param fmt The formatter to set + * @param locale The locale the formatter should use. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +umsg_setLocale(UMessageFormat *fmt, + const char* locale); + +/** + * Gets the locale. This locale is used for fetching default number or date + * format information. + * @param fmt The formatter to querry + * @return the locale. + * @stable ICU 2.0 + */ +U_STABLE const char* U_EXPORT2 +umsg_getLocale(const UMessageFormat *fmt); + +/** + * Sets the pattern. + * @param fmt The formatter to use + * @param pattern The pattern to be applied. + * @param patternLength Length of the pattern to use + * @param parseError Struct to receive information on position + * of error if an error is encountered.Can be NULL. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +umsg_applyPattern( UMessageFormat *fmt, + const UChar* pattern, + int32_t patternLength, + UParseError* parseError, + UErrorCode* status); + +/** + * Gets the pattern. + * @param fmt The formatter to use + * @param result A pointer to a buffer to receive the pattern. + * @param resultLength The maximum size of result. + * @param status Output param set to success/failure code on + * exit. If the pattern is invalid, this will be + * set to a failure result. + * @return the pattern of the format + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +umsg_toPattern(const UMessageFormat *fmt, + UChar* result, + int32_t resultLength, + UErrorCode* status); + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param fmt The formatter to use + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments + * specified in pattern. + * @return The total buffer size needed; if greater than resultLength, + * the output was truncated. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +umsg_format( const UMessageFormat *fmt, + UChar *result, + int32_t resultLength, + UErrorCode *status, + ...); + +/** + * Format a message for a locale. + * This function may perform re-ordering of the arguments depending on the + * locale. For all numeric arguments, double is assumed unless the type is + * explicitly integer. All choice format arguments must be of type double. + * @param fmt The formatter to use + * @param result A pointer to a buffer to receive the formatted message. + * @param resultLength The maximum size of result. + * @param ap A variable-length argument list containing the arguments + * @param status A pointer to an UErrorCode to receive any errors + * specified in pattern. + * @return The total buffer size needed; if greater than resultLength, + * the output was truncated. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +umsg_vformat( const UMessageFormat *fmt, + UChar *result, + int32_t resultLength, + va_list ap, + UErrorCode *status); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #umsg_format }. + * @param fmt The formatter to use + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param count Output param to receive number of elements returned. + * @param status A pointer to an UErrorCode to receive any errors + * @param ... A variable-length argument list containing the arguments + * specified in pattern. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +umsg_parse( const UMessageFormat *fmt, + const UChar *source, + int32_t sourceLength, + int32_t *count, + UErrorCode *status, + ...); + +/** + * Parse a message. + * For numeric arguments, this function will always use doubles. Integer types + * should not be passed. + * This function is not able to parse all output from {@link #umsg_format }. + * @param fmt The formatter to use + * @param source The text to parse. + * @param sourceLength The length of source, or -1 if null-terminated. + * @param count Output param to receive number of elements returned. + * @param ap A variable-length argument list containing the arguments + * @param status A pointer to an UErrorCode to receive any errors + * specified in pattern. + * @see u_formatMessage + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +umsg_vparse(const UMessageFormat *fmt, + const UChar *source, + int32_t sourceLength, + int32_t *count, + va_list ap, + UErrorCode *status); + + +/** + * Convert an 'apostrophe-friendly' pattern into a standard + * pattern. Standard patterns treat all apostrophes as + * quotes, which is problematic in some languages, e.g. + * French, where apostrophe is commonly used. This utility + * assumes that only an unpaired apostrophe immediately before + * a brace is a true quote. Other unpaired apostrophes are paired, + * and the resulting standard pattern string is returned. + * + * <p><b>Note</b> it is not guaranteed that the returned pattern + * is indeed a valid pattern. The only effect is to convert + * between patterns having different quoting semantics. + * + * @param pattern the 'apostrophe-friendly' patttern to convert + * @param patternLength the length of pattern, or -1 if unknown and pattern is null-terminated + * @param dest the buffer for the result, or NULL if preflight only + * @param destCapacity the length of the buffer, or 0 if preflighting + * @param ec the error code + * @return the length of the resulting text, not including trailing null + * if buffer has room for the trailing null, it is provided, otherwise + * not + * @stable ICU 3.4 + */ +U_STABLE int32_t U_EXPORT2 +umsg_autoQuoteApostrophe(const UChar* pattern, + int32_t patternLength, + UChar* dest, + int32_t destCapacity, + UErrorCode* ec); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/unirepl.h b/Build/source/libs/icu-xetex/i18n/unicode/unirepl.h new file mode 100644 index 00000000000..6b7746b2213 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/unirepl.h @@ -0,0 +1,97 @@ +/* +********************************************************************** +* Copyright (c) 2002-2005, International Business Machines Corporation +* and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 01/14/2002 aliu Creation. +********************************************************************** +*/ +#ifndef UNIREPL_H +#define UNIREPL_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: UnicodeReplacer + */ + +U_NAMESPACE_BEGIN + +class Replaceable; +class UnicodeString; +class UnicodeSet; + +/** + * <code>UnicodeReplacer</code> defines a protocol for objects that + * replace a range of characters in a Replaceable string with output + * text. The replacement is done via the Replaceable API so as to + * preserve out-of-band data. + * + * <p>This is a mixin class. + * @author Alan Liu + * @stable ICU 2.4 + */ +class U_I18N_API UnicodeReplacer /* not : public UObject because this is an interface/mixin class */ { + + public: + + /** + * Destructor. + * @stable ICU 2.4 + */ + virtual ~UnicodeReplacer(); + + /** + * Replace characters in 'text' from 'start' to 'limit' with the + * output text of this object. Update the 'cursor' parameter to + * give the cursor position and return the length of the + * replacement text. + * + * @param text the text to be matched + * @param start inclusive start index of text to be replaced + * @param limit exclusive end index of text to be replaced; + * must be greater than or equal to start + * @param cursor output parameter for the cursor position. + * Not all replacer objects will update this, but in a complete + * tree of replacer objects, representing the entire output side + * of a transliteration rule, at least one must update it. + * @return the number of 16-bit code units in the text replacing + * the characters at offsets start..(limit-1) in text + * @stable ICU 2.4 + */ + virtual int32_t replace(Replaceable& text, + int32_t start, + int32_t limit, + int32_t& cursor) = 0; + + /** + * Returns a string representation of this replacer. If the + * result of calling this function is passed to the appropriate + * parser, typically TransliteratorParser, it will produce another + * replacer that is equal to this one. + * @param result the string to receive the pattern. Previous + * contents will be deleted. + * @param escapeUnprintable if TRUE then convert unprintable + * character to their hex escape representations, \\uxxxx or + * \\Uxxxxxxxx. Unprintable characters are defined by + * Utility.isUnprintable(). + * @return a reference to 'result'. + * @stable ICU 2.4 + */ + virtual UnicodeString& toReplacerPattern(UnicodeString& result, + UBool escapeUnprintable) const = 0; + + /** + * Union the set of all characters that may output by this object + * into the given set. + * @param toUnionTo the set into which to union the output characters + * @stable ICU 2.4 + */ + virtual void addReplacementSetTo(UnicodeSet& toUnionTo) const = 0; +}; + +U_NAMESPACE_END + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/unum.h b/Build/source/libs/icu-xetex/i18n/unicode/unum.h new file mode 100644 index 00000000000..c69d2f4b8b5 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/unum.h @@ -0,0 +1,869 @@ +/* +******************************************************************************* +* Copyright (C) 1997-2007, International Business Machines Corporation and others. +* All Rights Reserved. +* Modification History: +* +* Date Name Description +* 06/24/99 helena Integrated Alan's NF enhancements and Java2 bug fixes +******************************************************************************* +*/ + +#ifndef _UNUM +#define _UNUM + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/uloc.h" +#include "unicode/umisc.h" +#include "unicode/parseerr.h" +/** + * \file + * \brief C API: NumberFormat + * + * <h2> Number Format C API </h2> + * + * Number Format C API Provides functions for + * formatting and parsing a number. Also provides methods for + * determining which locales have number formats, and what their names + * are. + * <P> + * UNumberFormat helps you to format and parse numbers for any locale. + * Your code can be completely independent of the locale conventions + * for decimal points, thousands-separators, or even the particular + * decimal digits used, or whether the number format is even decimal. + * There are different number format styles like decimal, currency, + * percent and spellout. + * <P> + * To format a number for the current Locale, use one of the static + * factory methods: + * <pre> + * \code + * UChar myString[20]; + * double myNumber = 7.0; + * UErrorCode status = U_ZERO_ERROR; + * UNumberFormat* nf = unum_open(UNUM_DEFAULT, NULL, -1, NULL, NULL, &status); + * unum_formatDouble(nf, myNumber, myString, 20, NULL, &status); + * printf(" Example 1: %s\n", austrdup(myString) ); //austrdup( a function used to convert UChar* to char*) + * \endcode + * </pre> + * If you are formatting multiple numbers, it is more efficient to get + * the format and use it multiple times so that the system doesn't + * have to fetch the information about the local language and country + * conventions multiple times. + * <pre> + * \code + * uint32_t i, resultlength, reslenneeded; + * UErrorCode status = U_ZERO_ERROR; + * UFieldPosition pos; + * uint32_t a[] = { 123, 3333, -1234567 }; + * const uint32_t a_len = sizeof(a) / sizeof(a[0]); + * UNumberFormat* nf; + * UChar* result = NULL; + * + * nf = unum_open(UNUM_DEFAULT, NULL, -1, NULL, NULL, &status); + * for (i = 0; i < a_len; i++) { + * resultlength=0; + * reslenneeded=unum_format(nf, a[i], NULL, resultlength, &pos, &status); + * result = NULL; + * if(status==U_BUFFER_OVERFLOW_ERROR){ + * status=U_ZERO_ERROR; + * resultlength=reslenneeded+1; + * result=(UChar*)malloc(sizeof(UChar) * resultlength); + * unum_format(nf, a[i], result, resultlength, &pos, &status); + * } + * printf( " Example 2: %s\n", austrdup(result)); + * free(result); + * } + * \endcode + * </pre> + * To format a number for a different Locale, specify it in the + * call to unum_open(). + * <pre> + * \code + * UNumberFormat* nf = unum_open(UNUM_DEFAULT, NULL, -1, "fr_FR", NULL, &success) + * \endcode + * </pre> + * You can use a NumberFormat API unum_parse() to parse. + * <pre> + * \code + * UErrorCode status = U_ZERO_ERROR; + * int32_t pos=0; + * int32_t num; + * num = unum_parse(nf, str, u_strlen(str), &pos, &status); + * \endcode + * </pre> + * Use UCAL_DECIMAL to get the normal number format for that country. + * There are other static options available. Use UCAL_CURRENCY + * to get the currency number format for that country. Use UCAL_PERCENT + * to get a format for displaying percentages. With this format, a + * fraction from 0.53 is displayed as 53%. + * <P> + * Use a pattern to create either a DecimalFormat or a RuleBasedNumberFormat + * formatter. The pattern must conform to the syntax defined for those + * formatters. + * <P> + * You can also control the display of numbers with such function as + * unum_getAttribues() and unum_setAtributes(), which let you set the + * miminum fraction digits, grouping, etc. + * @see UNumberFormatAttributes for more details + * <P> + * You can also use forms of the parse and format methods with + * ParsePosition and UFieldPosition to allow you to: + * <ul type=round> + * <li>(a) progressively parse through pieces of a string. + * <li>(b) align the decimal point and other areas. + * </ul> + * <p> + * It is also possible to change or set the symbols used for a particular + * locale like the currency symbol, the grouping seperator , monetary seperator + * etc by making use of functions unum_setSymbols() and unum_getSymbols(). + */ + +/** A number formatter. + * For usage in C programs. + * @stable ICU 2.0 + */ +typedef void* UNumberFormat; + +/** The possible number format styles. + * @stable ICU 2.0 + */ +typedef enum UNumberFormatStyle { + /** + * Decimal format defined by pattern + * @stable ICU 3.0 + */ + UNUM_PATTERN_DECIMAL=0, + /** Decimal format */ + UNUM_DECIMAL=1, + /** Currency format */ + UNUM_CURRENCY, + /** Percent format */ + UNUM_PERCENT, + /** Scientific format */ + UNUM_SCIENTIFIC, + /** Spellout rule-based format */ + UNUM_SPELLOUT, + /** + * Ordinal rule-based format + * @stable ICU 3.0 + */ + UNUM_ORDINAL, + /** + * Duration rule-based format + * @stable ICU 3.0 + */ + UNUM_DURATION, + /** + * Rule-based format defined by pattern + * @stable ICU 3.0 + */ + UNUM_PATTERN_RULEBASED, + /** Default format */ + UNUM_DEFAULT = UNUM_DECIMAL, + /** (Alias for UNUM_PATTERN_DECIMAL) */ + UNUM_IGNORE = UNUM_PATTERN_DECIMAL +} UNumberFormatStyle; + +/** The possible number format rounding modes. + * @stable ICU 2.0 + */ +typedef enum UNumberFormatRoundingMode { + UNUM_ROUND_CEILING, + UNUM_ROUND_FLOOR, + UNUM_ROUND_DOWN, + UNUM_ROUND_UP, + /** + * Half-even rounding, misspelled name + * @deprecated, ICU 3.8 + */ + UNUM_FOUND_HALFEVEN, + UNUM_ROUND_HALFDOWN, + UNUM_ROUND_HALFUP, + /** + * Half-even rounding + * @stable, ICU 3.8 + */ + UNUM_ROUND_HALFEVEN = UNUM_FOUND_HALFEVEN +} UNumberFormatRoundingMode; + +/** The possible number format pad positions. + * @stable ICU 2.0 + */ +typedef enum UNumberFormatPadPosition { + UNUM_PAD_BEFORE_PREFIX, + UNUM_PAD_AFTER_PREFIX, + UNUM_PAD_BEFORE_SUFFIX, + UNUM_PAD_AFTER_SUFFIX +} UNumberFormatPadPosition; + +/** + * Create and return a new UNumberFormat for formatting and parsing + * numbers. A UNumberFormat may be used to format numbers by calling + * {@link #unum_format }, and to parse numbers by calling {@link #unum_parse }. + * The caller must call {@link #unum_close } when done to release resources + * used by this object. + * @param style The type of number format to open: one of + * UNUM_DECIMAL, UNUM_CURRENCY, UNUM_PERCENT, UNUM_SCIENTIFIC, UNUM_SPELLOUT, + * UNUM_PATTERN_DECIMAL, UNUM_PATTERN_RULEBASED, or UNUM_DEFAULT. + * If UNUM_PATTERN_DECIMAL or UNUM_PATTERN_RULEBASED is passed then the + * number format is opened using the given pattern, which must conform + * to the syntax described in DecimalFormat or RuleBasedNumberFormat, + * respectively. + * @param pattern A pattern specifying the format to use. + * This parameter is ignored unless the style is + * UNUM_PATTERN_DECIMAL or UNUM_PATTERN_RULEBASED. + * @param patternLength The number of characters in the pattern, or -1 + * if null-terminated. This parameter is ignored unless the style is + * UNUM_PATTERN. + * @param locale A locale identifier to use to determine formatting + * and parsing conventions, or NULL to use the default locale. + * @param parseErr A pointer to a UParseError struct to receive the + * details of any parsing errors, or NULL if no parsing error details + * are desired. + * @param status A pointer to an input-output UErrorCode. + * @return A pointer to a newly created UNumberFormat, or NULL if an + * error occurred. + * @see unum_close + * @see DecimalFormat + * @stable ICU 2.0 + */ +U_STABLE UNumberFormat* U_EXPORT2 +unum_open( UNumberFormatStyle style, + const UChar* pattern, + int32_t patternLength, + const char* locale, + UParseError* parseErr, + UErrorCode* status); + + +/** +* Close a UNumberFormat. +* Once closed, a UNumberFormat may no longer be used. +* @param fmt The formatter to close. +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +unum_close(UNumberFormat* fmt); + +/** + * Open a copy of a UNumberFormat. + * This function performs a deep copy. + * @param fmt The format to copy + * @param status A pointer to an UErrorCode to receive any errors. + * @return A pointer to a UNumberFormat identical to fmt. + * @stable ICU 2.0 + */ +U_STABLE UNumberFormat* U_EXPORT2 +unum_clone(const UNumberFormat *fmt, + UErrorCode *status); + +/** +* Format an integer using a UNumberFormat. +* The integer will be formatted according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param number The number to format. +* @param result A pointer to a buffer to receive the formatted number. +* @param resultLength The maximum size of result. +* @param pos A pointer to a UFieldPosition. On input, position->field +* is read. On output, position->beginIndex and position->endIndex indicate +* the beginning and ending indices of field number position->field, if such +* a field exists. This parameter may be NULL, in which case no field +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see unum_formatInt64 +* @see unum_formatDouble +* @see unum_parse +* @see unum_parseInt64 +* @see unum_parseDouble +* @see UFieldPosition +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_format( const UNumberFormat* fmt, + int32_t number, + UChar* result, + int32_t resultLength, + UFieldPosition *pos, + UErrorCode* status); + +/** +* Format an int64 using a UNumberFormat. +* The int64 will be formatted according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param number The number to format. +* @param result A pointer to a buffer to receive the formatted number. +* @param resultLength The maximum size of result. +* @param pos A pointer to a UFieldPosition. On input, position->field +* is read. On output, position->beginIndex and position->endIndex indicate +* the beginning and ending indices of field number position->field, if such +* a field exists. This parameter may be NULL, in which case no field +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see unum_format +* @see unum_formatDouble +* @see unum_parse +* @see unum_parseInt64 +* @see unum_parseDouble +* @see UFieldPosition +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_formatInt64(const UNumberFormat *fmt, + int64_t number, + UChar* result, + int32_t resultLength, + UFieldPosition *pos, + UErrorCode* status); + +/** +* Format a double using a UNumberFormat. +* The double will be formatted according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param number The number to format. +* @param result A pointer to a buffer to receive the formatted number. +* @param resultLength The maximum size of result. +* @param pos A pointer to a UFieldPosition. On input, position->field +* is read. On output, position->beginIndex and position->endIndex indicate +* the beginning and ending indices of field number position->field, if such +* a field exists. This parameter may be NULL, in which case no field +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see unum_format +* @see unum_formatInt64 +* @see unum_parse +* @see unum_parseInt64 +* @see unum_parseDouble +* @see UFieldPosition +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_formatDouble( const UNumberFormat* fmt, + double number, + UChar* result, + int32_t resultLength, + UFieldPosition *pos, /* 0 if ignore */ + UErrorCode* status); + +/** + * Format a double currency amount using a UNumberFormat. + * The double will be formatted according to the UNumberFormat's locale. + * @param fmt the formatter to use + * @param number the number to format + * @param currency the 3-letter null-terminated ISO 4217 currency code + * @param result a pointer to the buffer to receive the formatted number + * @param resultLength the maximum number of UChars to write to result + * @param pos a pointer to a UFieldPosition. On input, + * position->field is read. On output, position->beginIndex and + * position->endIndex indicate the beginning and ending indices of + * field number position->field, if such a field exists. This + * parameter may be NULL, in which case it is ignored. + * @param status a pointer to an input-output UErrorCode + * @return the total buffer size needed; if greater than resultLength, + * the output was truncated. + * @see unum_formatDouble + * @see unum_parseDoubleCurrency + * @see UFieldPosition + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +unum_formatDoubleCurrency(const UNumberFormat* fmt, + double number, + UChar* currency, + UChar* result, + int32_t resultLength, + UFieldPosition* pos, /* ignored if 0 */ + UErrorCode* status); + +/** +* Parse a string into an integer using a UNumberFormat. +* The string will be parsed according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param text The text to parse. +* @param textLength The length of text, or -1 if null-terminated. +* @param parsePos If not 0, on input a pointer to an integer specifying the offset at which +* to begin parsing. If not 0, on output the offset at which parsing ended. +* @param status A pointer to an UErrorCode to receive any errors +* @return The value of the parsed integer +* @see unum_parseInt64 +* @see unum_parseDouble +* @see unum_format +* @see unum_formatInt64 +* @see unum_formatDouble +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_parse( const UNumberFormat* fmt, + const UChar* text, + int32_t textLength, + int32_t *parsePos /* 0 = start */, + UErrorCode *status); + +/** +* Parse a string into an int64 using a UNumberFormat. +* The string will be parsed according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param text The text to parse. +* @param textLength The length of text, or -1 if null-terminated. +* @param parsePos If not 0, on input a pointer to an integer specifying the offset at which +* to begin parsing. If not 0, on output the offset at which parsing ended. +* @param status A pointer to an UErrorCode to receive any errors +* @return The value of the parsed integer +* @see unum_parse +* @see unum_parseDouble +* @see unum_format +* @see unum_formatInt64 +* @see unum_formatDouble +* @stable ICU 2.8 +*/ +U_STABLE int64_t U_EXPORT2 +unum_parseInt64(const UNumberFormat* fmt, + const UChar* text, + int32_t textLength, + int32_t *parsePos /* 0 = start */, + UErrorCode *status); + +/** +* Parse a string into a double using a UNumberFormat. +* The string will be parsed according to the UNumberFormat's locale. +* @param fmt The formatter to use. +* @param text The text to parse. +* @param textLength The length of text, or -1 if null-terminated. +* @param parsePos If not 0, on input a pointer to an integer specifying the offset at which +* to begin parsing. If not 0, on output the offset at which parsing ended. +* @param status A pointer to an UErrorCode to receive any errors +* @return The value of the parsed double +* @see unum_parse +* @see unum_parseInt64 +* @see unum_format +* @see unum_formatInt64 +* @see unum_formatDouble +* @stable ICU 2.0 +*/ +U_STABLE double U_EXPORT2 +unum_parseDouble( const UNumberFormat* fmt, + const UChar* text, + int32_t textLength, + int32_t *parsePos /* 0 = start */, + UErrorCode *status); + +/** + * Parse a string into a double and a currency using a UNumberFormat. + * The string will be parsed according to the UNumberFormat's locale. + * @param fmt the formatter to use + * @param text the text to parse + * @param textLength the length of text, or -1 if null-terminated + * @param parsePos a pointer to an offset index into text at which to + * begin parsing. On output, *parsePos will point after the last + * parsed character. This parameter may be 0, in which case parsing + * begins at offset 0. + * @param currency a pointer to the buffer to receive the parsed null- + * terminated currency. This buffer must have a capacity of at least + * 4 UChars. + * @param status a pointer to an input-output UErrorCode + * @return the parsed double + * @see unum_parseDouble + * @see unum_formatDoubleCurrency + * @stable ICU 3.0 + */ +U_STABLE double U_EXPORT2 +unum_parseDoubleCurrency(const UNumberFormat* fmt, + const UChar* text, + int32_t textLength, + int32_t* parsePos, /* 0 = start */ + UChar* currency, + UErrorCode* status); + +/** + * Set the pattern used by a UNumberFormat. This can only be used + * on a DecimalFormat, other formats return U_ILLEGAL_ARGUMENT_ERROR + * in the status. + * @param format The formatter to set. + * @param localized TRUE if the pattern is localized, FALSE otherwise. + * @param pattern The new pattern + * @param patternLength The length of pattern, or -1 if null-terminated. + * @param parseError A pointer to UParseError to recieve information + * about errors occurred during parsing, or NULL if no parse error + * information is desired. + * @param status A pointer to an input-output UErrorCode. + * @see unum_toPattern + * @see DecimalFormat + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +unum_applyPattern( UNumberFormat *format, + UBool localized, + const UChar *pattern, + int32_t patternLength, + UParseError *parseError, + UErrorCode *status + ); + +/** +* Get a locale for which decimal formatting patterns are available. +* A UNumberFormat in a locale returned by this function will perform the correct +* formatting and parsing for the locale. The results of this call are not +* valid for rule-based number formats. +* @param index The index of the desired locale. +* @return A locale for which number formatting patterns are available, or 0 if none. +* @see unum_countAvailable +* @stable ICU 2.0 +*/ +U_STABLE const char* U_EXPORT2 +unum_getAvailable(int32_t index); + +/** +* Determine how many locales have decimal formatting patterns available. The +* results of this call are not valid for rule-based number formats. +* This function is useful for determining the loop ending condition for +* calls to {@link #unum_getAvailable }. +* @return The number of locales for which decimal formatting patterns are available. +* @see unum_getAvailable +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_countAvailable(void); + +/** The possible UNumberFormat numeric attributes @stable ICU 2.0 */ +typedef enum UNumberFormatAttribute { + /** Parse integers only */ + UNUM_PARSE_INT_ONLY, + /** Use grouping separator */ + UNUM_GROUPING_USED, + /** Always show decimal point */ + UNUM_DECIMAL_ALWAYS_SHOWN, + /** Maximum integer digits */ + UNUM_MAX_INTEGER_DIGITS, + /** Minimum integer digits */ + UNUM_MIN_INTEGER_DIGITS, + /** Integer digits */ + UNUM_INTEGER_DIGITS, + /** Maximum fraction digits */ + UNUM_MAX_FRACTION_DIGITS, + /** Minimum fraction digits */ + UNUM_MIN_FRACTION_DIGITS, + /** Fraction digits */ + UNUM_FRACTION_DIGITS, + /** Multiplier */ + UNUM_MULTIPLIER, + /** Grouping size */ + UNUM_GROUPING_SIZE, + /** Rounding Mode */ + UNUM_ROUNDING_MODE, + /** Rounding increment */ + UNUM_ROUNDING_INCREMENT, + /** The width to which the output of <code>format()</code> is padded. */ + UNUM_FORMAT_WIDTH, + /** The position at which padding will take place. */ + UNUM_PADDING_POSITION, + /** Secondary grouping size */ + UNUM_SECONDARY_GROUPING_SIZE, + /** Use significant digits + * @stable ICU 3.0 */ + UNUM_SIGNIFICANT_DIGITS_USED, + /** Minimum significant digits + * @stable ICU 3.0 */ + UNUM_MIN_SIGNIFICANT_DIGITS, + /** Maximum significant digits + * @stable ICU 3.0 */ + UNUM_MAX_SIGNIFICANT_DIGITS, + /** Lenient parse mode used by rule-based formats. + * @stable ICU 3.0 + */ + UNUM_LENIENT_PARSE +} UNumberFormatAttribute; + +/** +* Get a numeric attribute associated with a UNumberFormat. +* An example of a numeric attribute is the number of integer digits a formatter will produce. +* @param fmt The formatter to query. +* @param attr The attribute to query; one of UNUM_PARSE_INT_ONLY, UNUM_GROUPING_USED, +* UNUM_DECIMAL_ALWAYS_SHOWN, UNUM_MAX_INTEGER_DIGITS, UNUM_MIN_INTEGER_DIGITS, UNUM_INTEGER_DIGITS, +* UNUM_MAX_FRACTION_DIGITS, UNUM_MIN_FRACTION_DIGITS, UNUM_FRACTION_DIGITS, UNUM_MULTIPLIER, +* UNUM_GROUPING_SIZE, UNUM_ROUNDING_MODE, UNUM_FORMAT_WIDTH, UNUM_PADDING_POSITION, UNUM_SECONDARY_GROUPING_SIZE. +* @return The value of attr. +* @see unum_setAttribute +* @see unum_getDoubleAttribute +* @see unum_setDoubleAttribute +* @see unum_getTextAttribute +* @see unum_setTextAttribute +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_getAttribute(const UNumberFormat* fmt, + UNumberFormatAttribute attr); + +/** +* Set a numeric attribute associated with a UNumberFormat. +* An example of a numeric attribute is the number of integer digits a formatter will produce. If the +* formatter does not understand the attribute, the call is ignored. Rule-based formatters only understand +* the lenient-parse attribute. +* @param fmt The formatter to set. +* @param attr The attribute to set; one of UNUM_PARSE_INT_ONLY, UNUM_GROUPING_USED, +* UNUM_DECIMAL_ALWAYS_SHOWN, UNUM_MAX_INTEGER_DIGITS, UNUM_MIN_INTEGER_DIGITS, UNUM_INTEGER_DIGITS, +* UNUM_MAX_FRACTION_DIGITS, UNUM_MIN_FRACTION_DIGITS, UNUM_FRACTION_DIGITS, UNUM_MULTIPLIER, +* UNUM_GROUPING_SIZE, UNUM_ROUNDING_MODE, UNUM_FORMAT_WIDTH, UNUM_PADDING_POSITION, UNUM_SECONDARY_GROUPING_SIZE, +* or UNUM_LENIENT_PARSE. +* @param newValue The new value of attr. +* @see unum_getAttribute +* @see unum_getDoubleAttribute +* @see unum_setDoubleAttribute +* @see unum_getTextAttribute +* @see unum_setTextAttribute +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +unum_setAttribute( UNumberFormat* fmt, + UNumberFormatAttribute attr, + int32_t newValue); + + +/** +* Get a numeric attribute associated with a UNumberFormat. +* An example of a numeric attribute is the number of integer digits a formatter will produce. +* If the formatter does not understand the attribute, -1 is returned. +* @param fmt The formatter to query. +* @param attr The attribute to query; e.g. UNUM_ROUNDING_INCREMENT. +* @return The value of attr. +* @see unum_getAttribute +* @see unum_setAttribute +* @see unum_setDoubleAttribute +* @see unum_getTextAttribute +* @see unum_setTextAttribute +* @stable ICU 2.0 +*/ +U_STABLE double U_EXPORT2 +unum_getDoubleAttribute(const UNumberFormat* fmt, + UNumberFormatAttribute attr); + +/** +* Set a numeric attribute associated with a UNumberFormat. +* An example of a numeric attribute is the number of integer digits a formatter will produce. +* If the formatter does not understand the attribute, this call is ignored. +* @param fmt The formatter to set. +* @param attr The attribute to set; e.g. UNUM_ROUNDING_INCREMENT. +* @param newValue The new value of attr. +* @see unum_getAttribute +* @see unum_setAttribute +* @see unum_getDoubleAttribute +* @see unum_getTextAttribute +* @see unum_setTextAttribute +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +unum_setDoubleAttribute( UNumberFormat* fmt, + UNumberFormatAttribute attr, + double newValue); + +/** The possible UNumberFormat text attributes @stable ICU 2.0*/ +typedef enum UNumberFormatTextAttribute { + /** Positive prefix */ + UNUM_POSITIVE_PREFIX, + /** Positive suffix */ + UNUM_POSITIVE_SUFFIX, + /** Negative prefix */ + UNUM_NEGATIVE_PREFIX, + /** Negative suffix */ + UNUM_NEGATIVE_SUFFIX, + /** The character used to pad to the format width. */ + UNUM_PADDING_CHARACTER, + /** The ISO currency code */ + UNUM_CURRENCY_CODE, + /** + * The default rule set. This is only available with rule-based formatters. + * @stable ICU 3.0 + */ + UNUM_DEFAULT_RULESET, + /** + * The public rule sets. This is only available with rule-based formatters. + * This is a read-only attribute. The public rulesets are returned as a + * single string, with each ruleset name delimited by ';' (semicolon). + * @stable ICU 3.0 + */ + UNUM_PUBLIC_RULESETS +} UNumberFormatTextAttribute; + +/** +* Get a text attribute associated with a UNumberFormat. +* An example of a text attribute is the suffix for positive numbers. If the formatter +* does not understand the attributre, U_UNSUPPORTED_ERROR is returned as the status. +* Rule-based formatters only understand UNUM_DEFAULT_RULESET and UNUM_PUBLIC_RULESETS. +* @param fmt The formatter to query. +* @param tag The attribute to query; one of UNUM_POSITIVE_PREFIX, UNUM_POSITIVE_SUFFIX, +* UNUM_NEGATIVE_PREFIX, UNUM_NEGATIVE_SUFFIX, UNUM_PADDING_CHARACTER, UNUM_CURRENCY_CODE, +* UNUM_DEFAULT_RULESET, or UNUM_PUBLIC_RULESETS. +* @param result A pointer to a buffer to receive the attribute. +* @param resultLength The maximum size of result. +* @param status A pointer to an UErrorCode to receive any errors +* @return The total buffer size needed; if greater than resultLength, the output was truncated. +* @see unum_setTextAttribute +* @see unum_getAttribute +* @see unum_setAttribute +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_getTextAttribute( const UNumberFormat* fmt, + UNumberFormatTextAttribute tag, + UChar* result, + int32_t resultLength, + UErrorCode* status); + +/** +* Set a text attribute associated with a UNumberFormat. +* An example of a text attribute is the suffix for positive numbers. Rule-based formatters +* only understand UNUM_DEFAULT_RULESET. +* @param fmt The formatter to set. +* @param tag The attribute to set; one of UNUM_POSITIVE_PREFIX, UNUM_POSITIVE_SUFFIX, +* UNUM_NEGATIVE_PREFIX, UNUM_NEGATIVE_SUFFIX, UNUM_PADDING_CHARACTER, UNUM_CURRENCY_CODE, +* or UNUM_DEFAULT_RULESET. +* @param newValue The new value of attr. +* @param newValueLength The length of newValue, or -1 if null-terminated. +* @param status A pointer to an UErrorCode to receive any errors +* @see unum_getTextAttribute +* @see unum_getAttribute +* @see unum_setAttribute +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +unum_setTextAttribute( UNumberFormat* fmt, + UNumberFormatTextAttribute tag, + const UChar* newValue, + int32_t newValueLength, + UErrorCode *status); + +/** + * Extract the pattern from a UNumberFormat. The pattern will follow + * the DecimalFormat pattern syntax. + * @param fmt The formatter to query. + * @param isPatternLocalized TRUE if the pattern should be localized, + * FALSE otherwise. This is ignored if the formatter is a rule-based + * formatter. + * @param result A pointer to a buffer to receive the pattern. + * @param resultLength The maximum size of result. + * @param status A pointer to an input-output UErrorCode. + * @return The total buffer size needed; if greater than resultLength, + * the output was truncated. + * @see unum_applyPattern + * @see DecimalFormat + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +unum_toPattern( const UNumberFormat* fmt, + UBool isPatternLocalized, + UChar* result, + int32_t resultLength, + UErrorCode* status); + + +/** + * Constants for specifying a number format symbol. + * @stable ICU 2.0 + */ +typedef enum UNumberFormatSymbol { + /** The decimal separator */ + UNUM_DECIMAL_SEPARATOR_SYMBOL = 0, + /** The grouping separator */ + UNUM_GROUPING_SEPARATOR_SYMBOL = 1, + /** The pattern separator */ + UNUM_PATTERN_SEPARATOR_SYMBOL = 2, + /** The percent sign */ + UNUM_PERCENT_SYMBOL = 3, + /** Zero*/ + UNUM_ZERO_DIGIT_SYMBOL = 4, + /** Character representing a digit in the pattern */ + UNUM_DIGIT_SYMBOL = 5, + /** The minus sign */ + UNUM_MINUS_SIGN_SYMBOL = 6, + /** The plus sign */ + UNUM_PLUS_SIGN_SYMBOL = 7, + /** The currency symbol */ + UNUM_CURRENCY_SYMBOL = 8, + /** The international currency symbol */ + UNUM_INTL_CURRENCY_SYMBOL = 9, + /** The monetary separator */ + UNUM_MONETARY_SEPARATOR_SYMBOL = 10, + /** The exponential symbol */ + UNUM_EXPONENTIAL_SYMBOL = 11, + /** Per mill symbol */ + UNUM_PERMILL_SYMBOL = 12, + /** Escape padding character */ + UNUM_PAD_ESCAPE_SYMBOL = 13, + /** Infinity symbol */ + UNUM_INFINITY_SYMBOL = 14, + /** Nan symbol */ + UNUM_NAN_SYMBOL = 15, + /** Significant digit symbol + * @stable ICU 3.0 */ + UNUM_SIGNIFICANT_DIGIT_SYMBOL = 16, + /** The monetary grouping separator + * @stable ICU 3.6 + */ + UNUM_MONETARY_GROUPING_SEPARATOR_SYMBOL = 17, + /** count symbol constants */ + UNUM_FORMAT_SYMBOL_COUNT = 18 +} UNumberFormatSymbol; + +/** +* Get a symbol associated with a UNumberFormat. +* A UNumberFormat uses symbols to represent the special locale-dependent +* characters in a number, for example the percent sign. This API is not +* supported for rule-based formatters. +* @param fmt The formatter to query. +* @param symbol The UNumberFormatSymbol constant for the symbol to get +* @param buffer The string buffer that will receive the symbol string; +* if it is NULL, then only the length of the symbol is returned +* @param size The size of the string buffer +* @param status A pointer to an UErrorCode to receive any errors +* @return The length of the symbol; the buffer is not modified if +* <code>length>=size</code> +* @see unum_setSymbol +* @stable ICU 2.0 +*/ +U_STABLE int32_t U_EXPORT2 +unum_getSymbol(const UNumberFormat *fmt, + UNumberFormatSymbol symbol, + UChar *buffer, + int32_t size, + UErrorCode *status); + +/** +* Set a symbol associated with a UNumberFormat. +* A UNumberFormat uses symbols to represent the special locale-dependent +* characters in a number, for example the percent sign. This API is not +* supported for rule-based formatters. +* @param fmt The formatter to set. +* @param symbol The UNumberFormatSymbol constant for the symbol to set +* @param value The string to set the symbol to +* @param length The length of the string, or -1 for a zero-terminated string +* @param status A pointer to an UErrorCode to receive any errors. +* @see unum_getSymbol +* @stable ICU 2.0 +*/ +U_STABLE void U_EXPORT2 +unum_setSymbol(UNumberFormat *fmt, + UNumberFormatSymbol symbol, + const UChar *value, + int32_t length, + UErrorCode *status); + + +/** + * Get the locale for this number format object. + * You can choose between valid and actual locale. + * @param fmt The formatter to get the locale from + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale name + * @stable ICU 2.8 + */ +U_STABLE const char* U_EXPORT2 +unum_getLocaleByType(const UNumberFormat *fmt, + ULocDataLocaleType type, + UErrorCode* status); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/uregex.h b/Build/source/libs/icu-xetex/i18n/unicode/uregex.h new file mode 100644 index 00000000000..862cf344641 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/uregex.h @@ -0,0 +1,631 @@ +/* +********************************************************************** +* Copyright (C) 2004-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* file name: regex.h +* encoding: US-ASCII +* indentation:4 +* +* created on: 2004mar09 +* created by: Andy Heninger +* +* ICU Regular Expressions, API for C +*/ + +/** + * \file + * \brief C API: Regular Expressions + * + * <p>This is a C wrapper around the C++ RegexPattern and RegexMatcher classes.</p> + */ + +#ifndef UREGEX_H +#define UREGEX_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_REGULAR_EXPRESSIONS + +#include "unicode/parseerr.h" + +struct URegularExpression; +/** + * Structure represeting a compiled regular rexpression, plus the results + * of a match operation. + * @stable ICU 3.0 + */ +typedef struct URegularExpression URegularExpression; + + +/** + * Constants for Regular Expression Match Modes. + * @stable ICU 2.4 + */ +typedef enum URegexpFlag{ + +#ifndef U_HIDE_DRAFT_API + /** Forces normalization of pattern and strings. + Not implemented yet, just a placeholder, hence draft. + @draft ICU 2.4 */ + UREGEX_CANON_EQ = 128, +#endif + /** Enable case insensitive matching. @stable ICU 2.4 */ + UREGEX_CASE_INSENSITIVE = 2, + + /** Allow white space and comments within patterns @stable ICU 2.4 */ + UREGEX_COMMENTS = 4, + + /** If set, '.' matches line terminators, otherwise '.' matching stops at line end. + * @stable ICU 2.4 */ + UREGEX_DOTALL = 32, + + /** Control behavior of "$" and "^" + * If set, recognize line terminators within string, + * otherwise, match only at start and end of input string. + * @stable ICU 2.4 */ + UREGEX_MULTILINE = 8, + + /** Unicode word boundaries. + * If set, \b uses the Unicode TR 29 definition of word boundaries. + * Warning: Unicode word boundaries are quite different from + * traditional regular expression word boundaries. See + * http://unicode.org/reports/tr29/#Word_Boundaries + * @stable ICU 2.8 + */ + UREGEX_UWORD = 256 +} URegexpFlag; + +/** + * Open (compile) an ICU regular expression. Compiles the regular expression in + * string form into an internal representation using the specified match mode flags. + * The resulting regular expression handle can then be used to perform various + * matching operations. + * + * @param pattern The Regular Expression pattern to be compiled. + * @param patternLength The length of the pattern, or -1 if the pattern is + * NUL termintated. + * @param flags Flags that alter the default matching behavior for + * the regular expression, UREGEX_CASE_INSENSITIVE, for + * example. For default behavior, set this parameter to zero. + * See <code>enum URegexpFlag</code>. All desired flags + * are bitwise-ORed together. + * @param pe Receives the position (line and column nubers) of any syntax + * error within the source regular expression string. If this + * information is not wanted, pass NULL for this parameter. + * @param status Receives error detected by this function. + * @stable ICU 3.0 + * + */ +U_STABLE URegularExpression * U_EXPORT2 +uregex_open( const UChar *pattern, + int32_t patternLength, + uint32_t flags, + UParseError *pe, + UErrorCode *status); + +/** + * Open (compile) an ICU regular expression. The resulting regular expression + * handle can then be used to perform various matching operations. + * <p> + * This function is the same as uregex_open, except that the pattern + * is supplied as an 8 bit char * string in the default code page. + * + * @param pattern The Regular Expression pattern to be compiled, + * NUL termintated. + * @param flags Flags that alter the default matching behavior for + * the regular expression, UREGEX_CASE_INSENSITIVE, for + * example. For default behavior, set this parameter to zero. + * See <code>enum URegexpFlag</code>. All desired flags + * are bitwise-ORed together. + * @param pe Receives the position (line and column nubers) of any syntax + * error within the source regular expression string. If this + * information is not wanted, pass NULL for this parameter. + * @param status Receives errors detected by this function. + * @return The URegularExpression object representing the compiled + * pattern. + * + * @stable ICU 3.0 + */ +#if !UCONFIG_NO_CONVERSION +U_STABLE URegularExpression * U_EXPORT2 +uregex_openC( const char *pattern, + uint32_t flags, + UParseError *pe, + UErrorCode *status); +#endif + + + +/** + * Close the regular expression, recovering all resources (memory) it + * was holding. + * + * @param regexp The regular expression to be closed. + * @stable ICU 3.0 + */ +U_STABLE void U_EXPORT2 +uregex_close(URegularExpression *regexp); + +/** + * Make a copy of a compiled regular expression. Cloning a regular + * expression is faster than opening a second instance from the source + * form of the expression, and requires less memory. + * <p> + * Note that the current input string and the position of any matched text + * within it are not cloned; only the pattern itself and and the + * match mode flags are copied. + * <p> + * Cloning can be particularly useful to threaded applications that perform + * multiple match operations in parallel. Each concurrent RE + * operation requires its own instance of a URegularExpression. + * + * @param regexp The compiled regular expression to be cloned. + * @param status Receives indication of any errors encountered + * @return the cloned copy of the compiled regular expression. + * @stable ICU 3.0 + */ +U_STABLE URegularExpression * U_EXPORT2 +uregex_clone(const URegularExpression *regexp, UErrorCode *status); + +/** + * Return a pointer to the source form of the pattern for this regular expression. + * + * @param regexp The compiled regular expression. + * @param patLength This output parameter will be set to the length of the + * pattern string. A NULL pointer may be used here if the + * pattern length is not needed, as would be the case if + * the pattern is known in advance to be a NUL terminated + * string. + * @param status Receives errors detected by this function. + * @return a pointer to the pattern string. The storage for the string is + * owned by the regular expression object, and must not be + * altered or deleted by the application. The returned string + * will remain valid until the regular expression is closed. + * @stable ICU 3.0 + */ +U_STABLE const UChar * U_EXPORT2 +uregex_pattern(const URegularExpression *regexp, + int32_t *patLength, + UErrorCode *status); + + +/** + * Get the match mode flags that were specified when compiling this regular expression. + * @param status Receives errors detected by this function. + * @param regexp The compiled regular expression. + * @return The match mode flags + * @see URegexpFlag + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_flags(const URegularExpression *regexp, + UErrorCode *status); + + +/** + * Set the subject text string upon which the regular expression will look for matches. + * This function may be called any number of times, allowing the regular + * expression pattern to be applied to different strings. + * <p> + * Regular expression matching operations work directly on the application's + * string data. No copy is made. The subject string data must not be + * altered after calling this function until after all regular expression + * operations involving this string data are completed. + * <p> + * Zero length strings are permitted. In this case, no subsequent match + * operation will dereference the text string pointer. + * + * @param regexp The compiled regular expression. + * @param text The subject text string. + * @param textLength The length of the subject text, or -1 if the string + * is NUL terminated. + * @param status Receives errors detected by this function. + * @stable ICU 3.0 + */ +U_STABLE void U_EXPORT2 +uregex_setText(URegularExpression *regexp, + const UChar *text, + int32_t textLength, + UErrorCode *status); + +/** + * Get the subject text that is currently associated with this + * regular expression object. This simply returns whatever string + * pointer was previously supplied via uregex_setText(). + * + * @param regexp The compiled regular expression. + * @param textLength The length of the string is returned in this output parameter. + * A NULL pointer may be used here if the + * text length is not needed, as would be the case if + * the text is known in advance to be a NUL terminated + * string. + * @param status Receives errors detected by this function. + * @return Poiner to the subject text string currently associated with + * this regular expression. + * @stable ICU 3.0 + */ +U_STABLE const UChar * U_EXPORT2 +uregex_getText(URegularExpression *regexp, + int32_t *textLength, + UErrorCode *status); + +/** + * Attempts to match the input string, beginning at startIndex, against the pattern. + * To succeed, the match must extend to the end of the input string. + * + * @param regexp The compiled regular expression. + * @param startIndex The input string index at which to begin matching. + * @param status Receives errors detected by this function. + * @return TRUE if there is a match + * @stable ICU 3.0 + */ +U_STABLE UBool U_EXPORT2 +uregex_matches(URegularExpression *regexp, + int32_t startIndex, + UErrorCode *status); + +/** + * Attempts to match the input string, starting from the specified index, against the pattern. + * The match may be of any length, and is not required to extend to the end + * of the input string. Contrast with uregex_matches(). + * + * <p>If the match succeeds then more information can be obtained via the + * <code>uregexp_start()</code>, <code>uregexp_end()</code>, + * and <code>uregexp_group()</code> functions.</p> + * + * @param regexp The compiled regular expression. + * @param startIndex The input string index at which to begin matching. + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if there is a match. + * @stable ICU 3.0 + */ +U_STABLE UBool U_EXPORT2 +uregex_lookingAt(URegularExpression *regexp, + int32_t startIndex, + UErrorCode *status); + +/** + * Find the first matching substring of the input string that matches the pattern. + * The search for a match begins at the specified index. + * If a match is found, <code>uregex_start(), uregex_end()</code>, and + * <code>uregex_group()</code> will provide more information regarding the match. + * + * @param regexp The compiled regular expression. + * @param startIndex The position in the input string to begin the search + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if a match is found. + * @stable ICU 3.0 + */ +U_STABLE UBool U_EXPORT2 +uregex_find(URegularExpression *regexp, + int32_t startIndex, + UErrorCode *status); + +/** + * Find the next pattern match in the input string. + * Begin searching the input at the location following the end of + * the previous match, or at the start of the string if there is no previous match. + * If a match is found, <code>uregex_start(), uregex_end()</code>, and + * <code>uregex_group()</code> will provide more information regarding the match. + * + * @param regexp The compiled regular expression. + * @param status A reference to a UErrorCode to receive any errors. + * @return TRUE if a match is found. + * @see uregex_reset + * @stable ICU 3.0 + */ +U_STABLE UBool U_EXPORT2 +uregex_findNext(URegularExpression *regexp, + UErrorCode *status); + +/** + * Get the number of capturing groups in this regular expression's pattern. + * @param regexp The compiled regular expression. + * @param status A reference to a UErrorCode to receive any errors. + * @return the number of capture groups + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_groupCount(URegularExpression *regexp, + UErrorCode *status); + +/** Extract the string for the specified matching expression or subexpression. + * Group #0 is the complete string of matched text. + * Group #1 is the text matched by the first set of capturing parentheses. + * + * @param regexp The compiled regular expression. + * @param groupNum The capture group to extract. Group 0 is the complete + * match. The value of this parameter must be + * less than or equal to the number of capture groups in + * the pattern. + * @param dest Buffer to receive the matching string data + * @param destCapacity Capacity of the dest buffer. + * @param status A reference to a UErrorCode to receive any errors. + * @return Length of matching data, + * or -1 if no applicable match. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_group(URegularExpression *regexp, + int32_t groupNum, + UChar *dest, + int32_t destCapacity, + UErrorCode *status); + + +/** + * Returns the index in the input string of the start of the text matched by the + * specified capture group during the previous match operation. Return -1 if + * the capture group was not part of the last match. + * Group #0 refers to the complete range of matched text. + * Group #1 refers to the text matched by the first set of capturing parentheses. + * + * @param regexp The compiled regular expression. + * @param groupNum The capture group number + * @param status A reference to a UErrorCode to receive any errors. + * @return the starting position in the input of the text matched + * by the specified group. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_start(URegularExpression *regexp, + int32_t groupNum, + UErrorCode *status); + +/** + * Returns the index in the input string of the position following the end + * of the text matched by the specified capture group. + * Return -1 if the capture group was not part of the last match. + * Group #0 refers to the complete range of matched text. + * Group #1 refers to the text matched by the first set of capturing parentheses. + * + * @param regexp The compiled regular expression. + * @param groupNum The capture group number + * @param status A reference to a UErrorCode to receive any errors. + * @return the index of the position following the last matched character. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_end(URegularExpression *regexp, + int32_t groupNum, + UErrorCode *status); + +/** + * Reset any saved state from the previous match. Has the effect of + * causing uregex_findNext to begin at the specified index, and causing + * uregex_start(), uregex_end() and uregex_group() to return an error + * indicating that there is no match information available. + * + * @param regexp The compiled regular expression. + * @param index The position in the text at which a + * uregex_findNext() should begin searching. + * @param status A reference to a UErrorCode to receive any errors. + * @stable ICU 3.0 + */ +U_STABLE void U_EXPORT2 +uregex_reset(URegularExpression *regexp, + int32_t index, + UErrorCode *status); + +/** + * Replaces every substring of the input that matches the pattern + * with the given replacement string. This is a convenience function that + * provides a complete find-and-replace-all operation. + * + * This method scans the input string looking for matches of the pattern. + * Input that is not part of any match is copied unchanged to the + * destination buffer. Matched regions are replaced in the output + * buffer by the replacement string. The replacement string may contain + * references to capture groups; these take the form of $1, $2, etc. + * + * @param regexp The compiled regular expression. + * @param replacementText A string containing the replacement text. + * @param replacementLength The length of the replacement string, or + * -1 if it is NUL terminated. + * @param destBuf A (UChar *) buffer that will receive the result. + * @param destCapacity The capacity of the desitnation buffer. + * @param status A reference to a UErrorCode to receive any errors. + * @return The length of the string resulting from the find + * and replace operation. In the event that the + * destination capacity is inadequate, the return value + * is still the full length of the untruncated string. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_replaceAll(URegularExpression *regexp, + const UChar *replacementText, + int32_t replacementLength, + UChar *destBuf, + int32_t destCapacity, + UErrorCode *status); + + +/** + * Replaces the first substring of the input that matches the pattern + * with the given replacement string. This is a convenience function that + * provides a complete find-and-replace operation. + * + * This method scans the input string looking for a match of the pattern. + * All input that is not part of the match is copied unchanged to the + * destination buffer. The matched region is replaced in the output + * buffer by the replacement string. The replacement string may contain + * references to capture groups; these take the form of $1, $2, etc. + * + * @param regexp The compiled regular expression. + * @param replacementText A string containing the replacement text. + * @param replacementLength The length of the replacement string, or + * -1 if it is NUL terminated. + * @param destBuf A (UChar *) buffer that will receive the result. + * @param destCapacity The capacity of the desitnation buffer. + * @param status a reference to a UErrorCode to receive any errors. + * @return The length of the string resulting from the find + * and replace operation. In the event that the + * destination capacity is inadequate, the return value + * is still the full length of the untruncated string. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_replaceFirst(URegularExpression *regexp, + const UChar *replacementText, + int32_t replacementLength, + UChar *destBuf, + int32_t destCapacity, + UErrorCode *status); + + +/** + * Implements a replace operation intended to be used as part of an + * incremental find-and-replace. + * + * <p>The input string, starting from the end of the previous match and ending at + * the start of the current match, is appended to the destination string. Then the + * replacement string is appended to the output string, + * including handling any substitutions of captured text.</p> + * + * <p>A note on preflight computation of buffersize and error handling: + * Calls to uregex_appendReplacement() and uregex_appendTail() are + * designed to be chained, one after another, with the destination + * buffer pointer and buffer capacity updated after each in preparation + * to for the next. If the destination buffer is exhausted partway through such a + * sequence, a U_BUFFER_OVERFLOW_ERROR status will be returned. Normal + * ICU conventions are for a function to perform no action if it is + * called with an error status, but for this one case, uregex_appendRepacement() + * will operate normally so that buffer size computations will complete + * correctly. + * + * <p>For simple, prepackaged, non-incremental find-and-replace + * operations, see replaceFirst() or replaceAll().</p> + * + * @param regexp The regular expression object. + * @param replacementText The string that will replace the matched portion of the + * input string as it is copied to the destination buffer. + * The replacement text may contain references ($1, for + * example) to capture groups from the match. + * @param replacementLength The length of the replacement text string, + * or -1 if the string is NUL terminated. + * @param destBuf The buffer into which the results of the + * find-and-replace are placed. On return, this pointer + * will be updated to refer to the beginning of the + * unused portion of buffer, leaving it in position for + * a subsequent call to this function. + * @param destCapacity The size of the output buffer, On return, this + * parameter will be updated to reflect the space remaining + * unused in the output buffer. + * @param status A reference to a UErrorCode to receive any errors. + * @return The length of the result string. In the event that + * destCapacity is inadequate, the full length of the + * untruncated output string is returned. + * + * @stable ICU 3.0 + * + */ +U_STABLE int32_t U_EXPORT2 +uregex_appendReplacement(URegularExpression *regexp, + const UChar *replacementText, + int32_t replacementLength, + UChar **destBuf, + int32_t *destCapacity, + UErrorCode *status); + + +/** + * As the final step in a find-and-replace operation, append the remainder + * of the input string, starting at the position following the last match, + * to the destination string. <code>uregex_appendTail()</code> is intended + * to be invoked after one or more invocations of the + * <code>uregex_appendReplacement()</code> function. + * + * @param regexp The regular expression object. This is needed to + * obtain the input string and with the position + * of the last match within it. + * @param destBuf The buffer in which the results of the + * find-and-replace are placed. On return, the pointer + * will be updated to refer to the beginning of the + * unused portion of buffer. + * @param destCapacity The size of the output buffer, On return, this + * value will be updated to reflect the space remaining + * unused in the output buffer. + * @param status A reference to a UErrorCode to receive any errors. + * @return The length of the result string. In the event that + * destCapacity is inadequate, the full length of the + * untruncated output string is returned. + * + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_appendTail(URegularExpression *regexp, + UChar **destBuf, + int32_t *destCapacity, + UErrorCode *status); + + + + + /** + * Split a string into fields. Somewhat like split() from Perl. + * The pattern matches identify delimiters that separate the input + * into fields. The input data between the matches becomes the + * fields themselves. + * <p> + * Each of the fields is copied from the input string to the destination + * buffer, and the NUL terminated. The position of each field within + * the destination buffer is returned in the destFields array. + * + * Note: another choice for the design of this function would be to not + * copy the resulting fields at all, but to return indexes and + * lengths within the source text. + * Advantages would be + * o Faster. No Copying. + * o Nothing extra needed when field data may contain embedded NUL chars. + * o Less memory needed if working on large data. + * Disadvantages + * o Less consistent with C++ split, which copies into an + * array of UnicodeStrings. + * o No NUL termination, extracted fields would be less convenient + * to use in most cases. + * o Possible problems in the future, when support Unicode Normalization + * could cause the fields to not correspond exactly to + * a range of the source text. + * + * @param regexp The compiled regular expression. + * @param destBuf A (UChar *) buffer to receive the fields that + * are extracted from the input string. These + * field pointers will refer to positions within the + * destination buffer supplied by the caller. Any + * extra positions within the destFields array will be + * set to NULL. + * @param destCapacity The capacity of the destBuf. + * @param requiredCapacity The actual capacity required of the destBuf. + * If destCapacity is too small, requiredCapacity will return + * the total capacity required to hold all of the output, and + * a U_BUFFER_OVERFLOW_ERROR will be returned. + * @param destFields An array to be filled with the position of each + * of the extracted fields within destBuf. + * @param destFieldsCapacity The number of elements in the destFields array. + * If the number of fields found is less than destFieldsCapacity, + * the extra destFields elements are set to zero. + * If destFieldsCapacity is too small, the trailing part of the + * input, including any field delimiters, is treated as if it + * were the last field - it is copied to the destBuf, and + * its position is in the destBuf is stored in the last element + * of destFields. This behavior mimics that of Perl. It is not + * an error condition, and no error status is returned when all destField + * positions are used. + * @param status A reference to a UErrorCode to receive any errors. + * @return The number of fields into which the input string was split. + * @stable ICU 3.0 + */ +U_STABLE int32_t U_EXPORT2 +uregex_split( URegularExpression *regexp, + UChar *destBuf, + int32_t destCapacity, + int32_t *requiredCapacity, + UChar *destFields[], + int32_t destFieldsCapacity, + UErrorCode *status); + + + +#endif /* !UCONFIG_NO_REGULAR_EXPRESSIONS */ +#endif /* UREGEX_H */ diff --git a/Build/source/libs/icu-xetex/i18n/unicode/usearch.h b/Build/source/libs/icu-xetex/i18n/unicode/usearch.h new file mode 100644 index 00000000000..0de1abb9e1a --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/usearch.h @@ -0,0 +1,646 @@ +/* +********************************************************************** +* Copyright (C) 2001-2007 IBM and others. All rights reserved. +********************************************************************** +* Date Name Description +* 06/28/2001 synwee Creation. +********************************************************************** +*/ +#ifndef USEARCH_H +#define USEARCH_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_COLLATION + +#include "unicode/ucol.h" +#include "unicode/ucoleitr.h" +#include "unicode/ubrk.h" + +/** + * \file + * \brief C API: StringSearch + * + * C Apis for an engine that provides language-sensitive text searching based + * on the comparison rules defined in a <tt>UCollator</tt> data struct, + * see <tt>ucol.h</tt>. This ensures that language eccentricity can be + * handled, e.g. for the German collator, characters ß and SS will be matched + * if case is chosen to be ignored. + * See the <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm"> + * "ICU Collation Design Document"</a> for more information. + * <p> + * The algorithm implemented is a modified form of the Boyer Moore's search. + * For more information see + * <a href="http://icu-project.org/docs/papers/efficient_text_searching_in_java.html"> + * "Efficient Text Searching in Java"</a>, published in <i>Java Report</i> + * in February, 1999, for further information on the algorithm. + * <p> + * There are 2 match options for selection:<br> + * Let S' be the sub-string of a text string S between the offsets start and + * end <start, end>. + * <br> + * A pattern string P matches a text string S at the offsets <start, end> + * if + * <pre> + * option 1. Some canonical equivalent of P matches some canonical equivalent + * of S' + * option 2. P matches S' and if P starts or ends with a combining mark, + * there exists no non-ignorable combining mark before or after S' + * in S respectively. + * </pre> + * Option 2. will be the default. + * <p> + * This search has APIs similar to that of other text iteration mechanisms + * such as the break iterators in <tt>ubrk.h</tt>. Using these + * APIs, it is easy to scan through text looking for all occurances of + * a given pattern. This search iterator allows changing of direction by + * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>. + * Though a direction change can occur without calling <tt>reset</tt> first, + * this operation comes with some speed penalty. + * Generally, match results in the forward direction will match the result + * matches in the backwards direction in the reverse order + * <p> + * <tt>usearch.h</tt> provides APIs to specify the starting position + * within the text string to be searched, e.g. <tt>usearch_setOffset</tt>, + * <tt>usearch_preceding</tt> and <tt>usearch_following</tt>. Since the + * starting position will be set as it is specified, please take note that + * there are some dangerous positions which the search may render incorrect + * results: + * <ul> + * <li> The midst of a substring that requires normalization. + * <li> If the following match is to be found, the position should not be the + * second character which requires to be swapped with the preceding + * character. Vice versa, if the preceding match is to be found, + * position to search from should not be the first character which + * requires to be swapped with the next character. E.g certain Thai and + * Lao characters require swapping. + * <li> If a following pattern match is to be found, any position within a + * contracting sequence except the first will fail. Vice versa if a + * preceding pattern match is to be found, a invalid starting point + * would be any character within a contracting sequence except the last. + * </ul> + * <p> + * A breakiterator can be used if only matches at logical breaks are desired. + * Using a breakiterator will only give you results that exactly matches the + * boundaries given by the breakiterator. For instance the pattern "e" will + * not be found in the string "\u00e9" if a character break iterator is used. + * <p> + * Options are provided to handle overlapping matches. + * E.g. In English, overlapping matches produces the result 0 and 2 + * for the pattern "abab" in the text "ababab", where else mutually + * exclusive matches only produce the result of 0. + * <p> + * Though collator attributes will be taken into consideration while + * performing matches, there are no APIs here for setting and getting the + * attributes. These attributes can be set by getting the collator + * from <tt>usearch_getCollator</tt> and using the APIs in <tt>ucol.h</tt>. + * Lastly to update String Search to the new collator attributes, + * usearch_reset() has to be called. + * <p> + * Restriction: <br> + * Currently there are no composite characters that consists of a + * character with combining class > 0 before a character with combining + * class == 0. However, if such a character exists in the future, the + * search mechanism does not guarantee the results for option 1. + * + * <p> + * Example of use:<br> + * <pre><code> + * char *tgtstr = "The quick brown fox jumped over the lazy fox"; + * char *patstr = "fox"; + * UChar target[64]; + * UChar pattern[16]; + * UErrorCode status = U_ZERO_ERROR; + * u_uastrcpy(target, tgtstr); + * u_uastrcpy(pattern, patstr); + * + * UStringSearch *search = usearch_open(pattern, -1, target, -1, "en_US", + * NULL, &status); + * if (U_SUCCESS(status)) { + * for (int pos = usearch_first(search, &status); + * pos != USEARCH_DONE; + * pos = usearch_next(search, &status)) + * { + * printf("Found match at %d pos, length is %d\n", pos, + * usearch_getMatchLength(search)); + * } + * } + * + * usearch_close(search); + * </code></pre> + * @stable ICU 2.4 + */ + +/** +* DONE is returned by previous() and next() after all valid matches have +* been returned, and by first() and last() if there are no matches at all. +* @stable ICU 2.4 +*/ +#define USEARCH_DONE -1 + +/** +* Data structure for searching +* @stable ICU 2.4 +*/ +struct UStringSearch; +/** +* Data structure for searching +* @stable ICU 2.4 +*/ +typedef struct UStringSearch UStringSearch; + +/** +* @stable ICU 2.4 +*/ +typedef enum { + /** Option for overlapping matches */ + USEARCH_OVERLAP, + /** + Option for canonical matches. option 1 in header documentation. + The default value will be USEARCH_OFF + */ + USEARCH_CANONICAL_MATCH, + USEARCH_ATTRIBUTE_COUNT +} USearchAttribute; + +/** +* @stable ICU 2.4 +*/ +typedef enum { + /** default value for any USearchAttribute */ + USEARCH_DEFAULT = -1, + /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */ + USEARCH_OFF, + /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */ + USEARCH_ON, + USEARCH_ATTRIBUTE_VALUE_COUNT +} USearchAttributeValue; + +/* open and close ------------------------------------------------------ */ + +/** +* Creating a search iterator data struct using the argument locale language +* rule set. A collator will be created in the process, which will be owned by +* this search and will be deleted in <tt>usearch_close</tt>. +* @param pattern for matching +* @param patternlength length of the pattern, -1 for null-termination +* @param text text string +* @param textlength length of the text string, -1 for null-termination +* @param locale name of locale for the rules to be used +* @param breakiter A BreakIterator that will be used to restrict the points +* at which matches are detected. If a match is found, but +* the match's start or end index is not a boundary as +* determined by the <tt>BreakIterator</tt>, the match will +* be rejected and another will be searched for. +* If this parameter is <tt>NULL</tt>, no break detection is +* attempted. +* @param status for errors if it occurs. If pattern or text is NULL, or if +* patternlength or textlength is 0 then an +* U_ILLEGAL_ARGUMENT_ERROR is returned. +* @return search iterator data structure, or NULL if there is an error. +* @stable ICU 2.4 +*/ +U_STABLE UStringSearch * U_EXPORT2 usearch_open(const UChar *pattern, + int32_t patternlength, + const UChar *text, + int32_t textlength, + const char *locale, + UBreakIterator *breakiter, + UErrorCode *status); + +/** +* Creating a search iterator data struct using the argument collator language +* rule set. Note, user retains the ownership of this collator, thus the +* responsibility of deletion lies with the user. +* NOTE: string search cannot be instantiated from a collator that has +* collate digits as numbers (CODAN) turned on. +* @param pattern for matching +* @param patternlength length of the pattern, -1 for null-termination +* @param text text string +* @param textlength length of the text string, -1 for null-termination +* @param collator used for the language rules +* @param breakiter A BreakIterator that will be used to restrict the points +* at which matches are detected. If a match is found, but +* the match's start or end index is not a boundary as +* determined by the <tt>BreakIterator</tt>, the match will +* be rejected and another will be searched for. +* If this parameter is <tt>NULL</tt>, no break detection is +* attempted. +* @param status for errors if it occurs. If collator, pattern or text is NULL, +* or if patternlength or textlength is 0 then an +* U_ILLEGAL_ARGUMENT_ERROR is returned. +* @return search iterator data structure, or NULL if there is an error. +* @stable ICU 2.4 +*/ +U_STABLE UStringSearch * U_EXPORT2 usearch_openFromCollator( + const UChar *pattern, + int32_t patternlength, + const UChar *text, + int32_t textlength, + const UCollator *collator, + UBreakIterator *breakiter, + UErrorCode *status); + +/** +* Destroying and cleaning up the search iterator data struct. +* If a collator is created in <tt>usearch_open</tt>, it will be destroyed here. +* @param searchiter data struct to clean up +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_close(UStringSearch *searchiter); + +/* get and set methods -------------------------------------------------- */ + +/** +* Sets the current position in the text string which the next search will +* start from. Clears previous states. +* This method takes the argument index and sets the position in the text +* string accordingly without checking if the index is pointing to a +* valid starting point to begin searching. +* Search positions that may render incorrect results are highlighted in the +* header comments +* @param strsrch search iterator data struct +* @param position position to start next search from. If position is less +* than or greater than the text range for searching, +* an U_INDEX_OUTOFBOUNDS_ERROR will be returned +* @param status error status if any. +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setOffset(UStringSearch *strsrch, + int32_t position, + UErrorCode *status); + +/** +* Return the current index in the string text being searched. +* If the iteration has gone past the end of the text (or past the beginning +* for a backwards search), <tt>USEARCH_DONE</tt> is returned. +* @param strsrch search iterator data struct +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_getOffset(const UStringSearch *strsrch); + +/** +* Sets the text searching attributes located in the enum USearchAttribute +* with values from the enum USearchAttributeValue. +* <tt>USEARCH_DEFAULT</tt> can be used for all attributes for resetting. +* @param strsrch search iterator data struct +* @param attribute text attribute to be set +* @param value text attribute value +* @param status for errors if it occurs +* @see #usearch_getAttribute +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setAttribute(UStringSearch *strsrch, + USearchAttribute attribute, + USearchAttributeValue value, + UErrorCode *status); + +/** +* Gets the text searching attributes. +* @param strsrch search iterator data struct +* @param attribute text attribute to be retrieve +* @return text attribute value +* @see #usearch_setAttribute +* @stable ICU 2.4 +*/ +U_STABLE USearchAttributeValue U_EXPORT2 usearch_getAttribute( + const UStringSearch *strsrch, + USearchAttribute attribute); + +/** +* Returns the index to the match in the text string that was searched. +* This call returns a valid result only after a successful call to +* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>, +* or <tt>usearch_last</tt>. +* Just after construction, or after a searching method returns +* <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>. +* <p> +* Use <tt>usearch_getMatchedLength</tt> to get the matched string length. +* @param strsrch search iterator data struct +* @return index to a substring within the text string that is being +* searched. +* @see #usearch_first +* @see #usearch_next +* @see #usearch_previous +* @see #usearch_last +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_getMatchedStart( + const UStringSearch *strsrch); + +/** +* Returns the length of text in the string which matches the search pattern. +* This call returns a valid result only after a successful call to +* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>, +* or <tt>usearch_last</tt>. +* Just after construction, or after a searching method returns +* <tt>USEARCH_DONE</tt>, this method will return 0. +* @param strsrch search iterator data struct +* @return The length of the match in the string text, or 0 if there is no +* match currently. +* @see #usearch_first +* @see #usearch_next +* @see #usearch_previous +* @see #usearch_last +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_getMatchedLength( + const UStringSearch *strsrch); + +/** +* Returns the text that was matched by the most recent call to +* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>, +* or <tt>usearch_last</tt>. +* If the iterator is not pointing at a valid match (e.g. just after +* construction or after <tt>USEARCH_DONE</tt> has been returned, returns +* an empty string. If result is not large enough to store the matched text, +* result will be filled with the partial text and an U_BUFFER_OVERFLOW_ERROR +* will be returned in status. result will be null-terminated whenever +* possible. If the buffer fits the matched text exactly, a null-termination +* is not possible, then a U_STRING_NOT_TERMINATED_ERROR set in status. +* Pre-flighting can be either done with length = 0 or the API +* <tt>usearch_getMatchLength</tt>. +* @param strsrch search iterator data struct +* @param result UChar buffer to store the matched string +* @param resultCapacity length of the result buffer +* @param status error returned if result is not large enough +* @return exact length of the matched text, not counting the null-termination +* @see #usearch_first +* @see #usearch_next +* @see #usearch_previous +* @see #usearch_last +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_getMatchedText(const UStringSearch *strsrch, + UChar *result, + int32_t resultCapacity, + UErrorCode *status); + +#if !UCONFIG_NO_BREAK_ITERATION + +/** +* Set the BreakIterator that will be used to restrict the points at which +* matches are detected. +* @param strsrch search iterator data struct +* @param breakiter A BreakIterator that will be used to restrict the points +* at which matches are detected. If a match is found, but +* the match's start or end index is not a boundary as +* determined by the <tt>BreakIterator</tt>, the match will +* be rejected and another will be searched for. +* If this parameter is <tt>NULL</tt>, no break detection is +* attempted. +* @param status for errors if it occurs +* @see #usearch_getBreakIterator +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setBreakIterator(UStringSearch *strsrch, + UBreakIterator *breakiter, + UErrorCode *status); + +/** +* Returns the BreakIterator that is used to restrict the points at which +* matches are detected. This will be the same object that was passed to the +* constructor or to <tt>usearch_setBreakIterator</tt>. Note that +* <tt>NULL</tt> +* is a legal value; it means that break detection should not be attempted. +* @param strsrch search iterator data struct +* @return break iterator used +* @see #usearch_setBreakIterator +* @stable ICU 2.4 +*/ +U_STABLE const UBreakIterator * U_EXPORT2 usearch_getBreakIterator( + const UStringSearch *strsrch); + +#endif + +/** +* Set the string text to be searched. Text iteration will hence begin at the +* start of the text string. This method is useful if you want to re-use an +* iterator to search for the same pattern within a different body of text. +* @param strsrch search iterator data struct +* @param text new string to look for match +* @param textlength length of the new string, -1 for null-termination +* @param status for errors if it occurs. If text is NULL, or textlength is 0 +* then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change +* done to strsrch. +* @see #usearch_getText +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setText( UStringSearch *strsrch, + const UChar *text, + int32_t textlength, + UErrorCode *status); + +/** +* Return the string text to be searched. +* @param strsrch search iterator data struct +* @param length returned string text length +* @return string text +* @see #usearch_setText +* @stable ICU 2.4 +*/ +U_STABLE const UChar * U_EXPORT2 usearch_getText(const UStringSearch *strsrch, + int32_t *length); + +/** +* Gets the collator used for the language rules. +* <p> +* Deleting the returned <tt>UCollator</tt> before calling +* <tt>usearch_close</tt> would cause the string search to fail. +* <tt>usearch_close</tt> will delete the collator if this search owns it. +* @param strsrch search iterator data struct +* @return collator +* @stable ICU 2.4 +*/ +U_STABLE UCollator * U_EXPORT2 usearch_getCollator( + const UStringSearch *strsrch); + +/** +* Sets the collator used for the language rules. User retains the ownership +* of this collator, thus the responsibility of deletion lies with the user. +* This method causes internal data such as Boyer-Moore shift tables to +* be recalculated, but the iterator's position is unchanged. +* @param strsrch search iterator data struct +* @param collator to be used +* @param status for errors if it occurs +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setCollator( UStringSearch *strsrch, + const UCollator *collator, + UErrorCode *status); + +/** +* Sets the pattern used for matching. +* Internal data like the Boyer Moore table will be recalculated, but the +* iterator's position is unchanged. +* @param strsrch search iterator data struct +* @param pattern string +* @param patternlength pattern length, -1 for null-terminated string +* @param status for errors if it occurs. If text is NULL, or textlength is 0 +* then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change +* done to strsrch. +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_setPattern( UStringSearch *strsrch, + const UChar *pattern, + int32_t patternlength, + UErrorCode *status); + +/** +* Gets the search pattern +* @param strsrch search iterator data struct +* @param length return length of the pattern, -1 indicates that the pattern +* is null-terminated +* @return pattern string +* @stable ICU 2.4 +*/ +U_STABLE const UChar * U_EXPORT2 usearch_getPattern( + const UStringSearch *strsrch, + int32_t *length); + +/* methods ------------------------------------------------------------- */ + +/** +* Returns the first index at which the string text matches the search +* pattern. +* The iterator is adjusted so that its current index (as returned by +* <tt>usearch_getOffset</tt>) is the match position if one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>. +* @param strsrch search iterator data struct +* @param status for errors if it occurs +* @return The character index of the first match, or +* <tt>USEARCH_DONE</tt> if there are no matches. +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_first(UStringSearch *strsrch, + UErrorCode *status); + +/** +* Returns the first index greater than <tt>position</tt> at which the string +* text +* matches the search pattern. The iterator is adjusted so that its current +* index (as returned by <tt>usearch_getOffset</tt>) is the match position if +* one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt> +* <p> +* Search positions that may render incorrect results are highlighted in the +* header comments. If position is less than or greater than the text range +* for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned +* @param strsrch search iterator data struct +* @param position to start the search at +* @param status for errors if it occurs +* @return The character index of the first match following <tt>pos</tt>, +* or <tt>USEARCH_DONE</tt> if there are no matches. +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_following(UStringSearch *strsrch, + int32_t position, + UErrorCode *status); + +/** +* Returns the last index in the target text at which it matches the search +* pattern. The iterator is adjusted so that its current +* index (as returned by <tt>usearch_getOffset</tt>) is the match position if +* one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>. +* @param strsrch search iterator data struct +* @param status for errors if it occurs +* @return The index of the first match, or <tt>USEARCH_DONE</tt> if there +* are no matches. +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_last(UStringSearch *strsrch, + UErrorCode *status); + +/** +* Returns the first index less than <tt>position</tt> at which the string text +* matches the search pattern. The iterator is adjusted so that its current +* index (as returned by <tt>usearch_getOffset</tt>) is the match position if +* one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt> +* <p> +* Search positions that may render incorrect results are highlighted in the +* header comments. If position is less than or greater than the text range +* for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned +* @param strsrch search iterator data struct +* @param position index position the search is to begin at +* @param status for errors if it occurs +* @return The character index of the first match preceding <tt>pos</tt>, +* or <tt>USEARCH_DONE</tt> if there are no matches. +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_preceding(UStringSearch *strsrch, + int32_t position, + UErrorCode *status); + +/** +* Returns the index of the next point at which the string text matches the +* search pattern, starting from the current position. +* The iterator is adjusted so that its current +* index (as returned by <tt>usearch_getOffset</tt>) is the match position if +* one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt> +* @param strsrch search iterator data struct +* @param status for errors if it occurs +* @return The index of the next match after the current position, or +* <tt>USEARCH_DONE</tt> if there are no more matches. +* @see #usearch_first +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_next(UStringSearch *strsrch, + UErrorCode *status); + +/** +* Returns the index of the previous point at which the string text matches +* the search pattern, starting at the current position. +* The iterator is adjusted so that its current +* index (as returned by <tt>usearch_getOffset</tt>) is the match position if +* one was found. +* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and +* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt> +* @param strsrch search iterator data struct +* @param status for errors if it occurs +* @return The index of the previous match before the current position, +* or <tt>USEARCH_DONE</tt> if there are no more matches. +* @see #usearch_last +* @see #usearch_getOffset +* @see #USEARCH_DONE +* @stable ICU 2.4 +*/ +U_STABLE int32_t U_EXPORT2 usearch_previous(UStringSearch *strsrch, + UErrorCode *status); + +/** +* Reset the iteration. +* Search will begin at the start of the text string if a forward iteration +* is initiated before a backwards iteration. Otherwise if a backwards +* iteration is initiated before a forwards iteration, the search will begin +* at the end of the text string. +* @param strsrch search iterator data struct +* @see #usearch_first +* @stable ICU 2.4 +*/ +U_STABLE void U_EXPORT2 usearch_reset(UStringSearch *strsrch); + +#endif /* #if !UCONFIG_NO_COLLATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/utmscale.h b/Build/source/libs/icu-xetex/i18n/unicode/utmscale.h new file mode 100644 index 00000000000..e903c88b7f8 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/utmscale.h @@ -0,0 +1,481 @@ +/* +******************************************************************************* +* Copyright (C) 2004 - 2006, International Business Machines Corporation and +* others. All Rights Reserved. +******************************************************************************* +*/ + +#ifndef UTMSCALE_H +#define UTMSCALE_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +/** + * \file + * \brief C API: Universal Time Scale + * + * There are quite a few different conventions for binary datetime, depending on different + * platforms and protocols. Some of these have severe drawbacks. For example, people using + * Unix time (seconds since Jan 1, 1970) think that they are safe until near the year 2038. + * But cases can and do arise where arithmetic manipulations causes serious problems. Consider + * the computation of the average of two datetimes, for example: if one calculates them with + * <code>averageTime = (time1 + time2)/2</code>, there will be overflow even with dates + * around the present. Moreover, even if these problems don't occur, there is the issue of + * conversion back and forth between different systems. + * + * <p> + * Binary datetimes differ in a number of ways: the datatype, the unit, + * and the epoch (origin). We'll refer to these as time scales. For example: + * + * <table border="1" cellspacing="0" cellpadding="4"> + * <caption>Table 1: Binary Time Scales</caption> + * <tr> + * <th align="left">Source</th> + * <th align="left">Datatype</th> + * <th align="left">Unit</th> + * <th align="left">Epoch</th> + * </tr> + * + * <tr> + * <td>UDTS_JAVA_TIME</td> + * <td>int64_t</td> + * <td>milliseconds</td> + * <td>Jan 1, 1970</td> + * </tr> + * <tr> + * + * <td>UDTS_UNIX_TIME</td> + * <td>int32_t or int64_t</td> + * <td>seconds</td> + * <td>Jan 1, 1970</td> + * </tr> + * <tr> + * <td>UDTS_ICU4C_TIME</td> + * + * <td>double</td> + * <td>milliseconds</td> + * <td>Jan 1, 1970</td> + * </tr> + * <tr> + * <td>UDTS_WINDOWS_FILE_TIME</td> + * <td>int64_t</td> + * + * <td>ticks (100 nanoseconds)</td> + * <td>Jan 1, 1601</td> + * </tr> + * <tr> + * <td>UDTS_DOTNET_DATE_TIME</td> + * <td>int64_t</td> + * <td>ticks (100 nanoseconds)</td> + * + * <td>Jan 1, 0001</td> + * </tr> + * <tr> + * <td>UDTS_MAC_OLD_TIME</td> + * <td>int32_t or int64_t</td> + * <td>seconds</td> + * <td>Jan 1, 1904</td> + * + * </tr> + * <tr> + * <td>UDTS_MAC_TIME</td> + * <td>double</td> + * <td>seconds</td> + * <td>Jan 1, 2001</td> + * </tr> + * + * <tr> + * <td>UDTS_EXCEL_TIME</td> + * <td>?</td> + * <td>days</td> + * <td>Dec 31, 1899</td> + * </tr> + * <tr> + * + * <td>UDTS_DB2_TIME</td> + * <td>?</td> + * <td>days</td> + * <td>Dec 31, 1899</td> + * </tr> + * + * <tr> + * <td>UDTS_UNIX_MICROSECONDS_TIME</td> + * <td>int64_t</td> + * <td>microseconds</td> + * <td>Jan 1, 1970</td> + * </tr> + * </table> + * + * <p> + * All of the epochs start at 00:00 am (the earliest possible time on the day in question), + * and are assumed to be UTC. + * + * <p> + * The ranges for different datatypes are given in the following table (all values in years). + * The range of years includes the entire range expressible with positive and negative + * values of the datatype. The range of years for double is the range that would be allowed + * without losing precision to the corresponding unit. + * + * <table border="1" cellspacing="0" cellpadding="4"> + * <tr> + * <th align="left">Units</th> + * <th align="left">int64_t</th> + * <th align="left">double</th> + * <th align="left">int32_t</th> + * </tr> + * + * <tr> + * <td>1 sec</td> + * <td align="right">5.84542x10<sup>11</sup></td> + * <td align="right">285,420,920.94</td> + * <td align="right">136.10</td> + * </tr> + * <tr> + * + * <td>1 millisecond</td> + * <td align="right">584,542,046.09</td> + * <td align="right">285,420.92</td> + * <td align="right">0.14</td> + * </tr> + * <tr> + * <td>1 microsecond</td> + * + * <td align="right">584,542.05</td> + * <td align="right">285.42</td> + * <td align="right">0.00</td> + * </tr> + * <tr> + * <td>100 nanoseconds (tick)</td> + * <td align="right">58,454.20</td> + * <td align="right">28.54</td> + * <td align="right">0.00</td> + * </tr> + * <tr> + * <td>1 nanosecond</td> + * <td align="right">584.5420461</td> + * <td align="right">0.2854</td> + * <td align="right">0.00</td> + * </tr> + * </table> + * + * <p> + * These functions implement a universal time scale which can be used as a 'pivot', + * and provide conversion functions to and from all other major time scales. + * This datetimes to be converted to the pivot time, safely manipulated, + * and converted back to any other datetime time scale. + * + *<p> + * So what to use for this pivot? Java time has plenty of range, but cannot represent + * .NET <code>System.DateTime</code> values without severe loss of precision. ICU4C time addresses this by using a + * <code>double</code> that is otherwise equivalent to the Java time. However, there are disadvantages + * with <code>doubles</code>. They provide for much more graceful degradation in arithmetic operations. + * But they only have 53 bits of accuracy, which means that they will lose precision when + * converting back and forth to ticks. What would really be nice would be a + * <code>long double</code> (80 bits -- 64 bit mantissa), but that is not supported on most systems. + * + *<p> + * The Unix extended time uses a structure with two components: time in seconds and a + * fractional field (microseconds). However, this is clumsy, slow, and + * prone to error (you always have to keep track of overflow and underflow in the + * fractional field). <code>BigDecimal</code> would allow for arbitrary precision and arbitrary range, + * but we do not want to use this as the normal type, because it is slow and does not + * have a fixed size. + * + *<p> + * Because of these issues, we ended up concluding that the .NET framework's + * <code>System.DateTime</code> would be the best pivot. However, we use the full range + * allowed by the datatype, allowing for datetimes back to 29,000 BC and up to 29,000 AD. + * This time scale is very fine grained, does not lose precision, and covers a range that + * will meet almost all requirements. It will not handle the range that Java times do, + * but frankly, being able to handle dates before 29,000 BC or after 29,000 AD is of very limited interest. + * + */ + +/** + * <code>UDateTimeScale</code> values are used to specify the time scale used for + * conversion into or out if the universal time scale. + * + * @stable ICU 3.2 + */ +typedef enum UDateTimeScale { + /** + * Used in the JDK. Data is a Java <code>long</code> (<code>int64_t</code>). Value + * is milliseconds since January 1, 1970. + * + * @stable ICU 3.2 + */ + UDTS_JAVA_TIME = 0, + + /** + * Used on Unix systems. Data is <code>int32_t</code> or <code>int64_t</code>. Value + * is seconds since January 1, 1970. + * + * @stable ICU 3.2 + */ + UDTS_UNIX_TIME, + + /** + * Used in IUC4C. Data is a <code>double</code>. Value + * is milliseconds since January 1, 1970. + * + * @stable ICU 3.2 + */ + UDTS_ICU4C_TIME, + + /** + * Used in Windows for file times. Data is an <code>int64_t</code>. Value + * is ticks (1 tick == 100 nanoseconds) since January 1, 1601. + * + * @stable ICU 3.2 + */ + UDTS_WINDOWS_FILE_TIME, + + /** + * Used in the .NET framework's <code>System.DateTime</code> structure. Data is an <code>int64_t</code>. Value + * is ticks (1 tick == 100 nanoseconds) since January 1, 0001. + * + * @stable ICU 3.2 + */ + UDTS_DOTNET_DATE_TIME, + + /** + * Used in older Macintosh systems. Data is <code>int32_t</code> or <code>int64_t</code>. Value + * is seconds since January 1, 1904. + * + * @stable ICU 3.2 + */ + UDTS_MAC_OLD_TIME, + + /** + * Used in newer Macintosh systems. Data is a <code>double</code>. Value + * is seconds since January 1, 2001. + * + * @stable ICU 3.2 + */ + UDTS_MAC_TIME, + + /** + * Used in Excel. Data is an <code>?unknown?</code>. Value + * is days since December 31, 1899. + * + * @stable ICU 3.2 + */ + UDTS_EXCEL_TIME, + + /** + * Used in DB2. Data is an <code>?unknown?</code>. Value + * is days since December 31, 1899. + * + * @stable ICU 3.2 + */ + UDTS_DB2_TIME, + + /** + * Data is a <code>long</code>. Value is microseconds since January 1, 1970. + * Similar to Unix time (linear value from 1970) and struct timeval + * (microseconds resolution). + * + * @draft ICU 3.8 + */ + UDTS_UNIX_MICROSECONDS_TIME, + + /** + * The first unused time scale value. The limit of this enum + */ + UDTS_MAX_SCALE +} UDateTimeScale; + +/** + * <code>UTimeScaleValue</code> values are used to specify the time scale values + * to <code>utmscale_getTimeScaleValue</code>. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ +typedef enum UTimeScaleValue { + /** + * The constant used to select the units vale + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_UNITS_VALUE = 0, + + /** + * The constant used to select the epoch offset value + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_EPOCH_OFFSET_VALUE=1, + + /** + * The constant used to select the minimum from value + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_FROM_MIN_VALUE=2, + + /** + * The constant used to select the maximum from value + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_FROM_MAX_VALUE=3, + + /** + * The constant used to select the minimum to value + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_TO_MIN_VALUE=4, + + /** + * The constant used to select the maximum to value + * for a time scale. + * + * @see utmscale_getTimeScaleValue + * + * @stable ICU 3.2 + */ + UTSV_TO_MAX_VALUE=5, + +#ifndef U_HIDE_INTERNAL_API + /** + * The constant used to select the epoch plus one value + * for a time scale. + * + * NOTE: This is an internal value. DO NOT USE IT. May not + * actually be equal to the epoch offset value plus one. + * + * @see utmscale_getTimeScaleValue + * + * @internal ICU 3.2 + */ + UTSV_EPOCH_OFFSET_PLUS_1_VALUE=6, + + /** + * The constant used to select the epoch plus one value + * for a time scale. + * + * NOTE: This is an internal value. DO NOT USE IT. May not + * actually be equal to the epoch offset value plus one. + * + * @see utmscale_getTimeScaleValue + * + * @internal ICU 3.2 + */ + UTSV_EPOCH_OFFSET_MINUS_1_VALUE=7, + + /** + * The constant used to select the units round value + * for a time scale. + * + * NOTE: This is an internal value. DO NOT USE IT. + * + * @see utmscale_getTimeScaleValue + * + * @internal ICU 3.2 + */ + UTSV_UNITS_ROUND_VALUE=8, + + /** + * The constant used to select the minimum safe rounding value + * for a time scale. + * + * NOTE: This is an internal value. DO NOT USE IT. + * + * @see utmscale_getTimeScaleValue + * + * @internal ICU 3.2 + */ + UTSV_MIN_ROUND_VALUE=9, + + /** + * The constant used to select the maximum safe rounding value + * for a time scale. + * + * NOTE: This is an internal value. DO NOT USE IT. + * + * @see utmscale_getTimeScaleValue + * + * @internal ICU 3.2 + */ + UTSV_MAX_ROUND_VALUE=10, + +#endif /* U_HIDE_INTERNAL_API */ + + /** + * The number of time scale values, in other words limit of this enum. + * + * @see utmscale_getTimeScaleValue + */ + UTSV_MAX_SCALE_VALUE=11 + +} UTimeScaleValue; + +/** + * Get a value associated with a particular time scale. + * + * @param timeScale The time scale + * @param value A constant representing the value to get + * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if arguments are invalid. + * @return - the value. + * + * @stable ICU 3.2 + */ +U_STABLE int64_t U_EXPORT2 + utmscale_getTimeScaleValue(UDateTimeScale timeScale, UTimeScaleValue value, UErrorCode *status); + +/* Conversion to 'universal time scale' */ + +/** + * Convert a <code>int64_t</code> datetime from the given time scale to the universal time scale. + * + * @param otherTime The <code>int64_t</code> datetime + * @param timeScale The time scale to convert from + * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the conversion is out of range. + * + * @return The datetime converted to the universal time scale + * + * @stable ICU 3.2 + */ +U_STABLE int64_t U_EXPORT2 + utmscale_fromInt64(int64_t otherTime, UDateTimeScale timeScale, UErrorCode *status); + +/* Conversion from 'universal time scale' */ + +/** + * Convert a datetime from the universal time scale to a <code>int64_t</code> in the given time scale. + * + * @param universalTime The datetime in the universal time scale + * @param timeScale The time scale to convert to + * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the conversion is out of range. + * + * @return The datetime converted to the given time scale + * + * @stable ICU 3.2 + */ +U_STABLE int64_t U_EXPORT2 + utmscale_toInt64(int64_t universalTime, UDateTimeScale timeScale, UErrorCode *status); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif + diff --git a/Build/source/libs/icu-xetex/i18n/unicode/utrans.h b/Build/source/libs/icu-xetex/i18n/unicode/utrans.h new file mode 100644 index 00000000000..a460a34c5b7 --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/utrans.h @@ -0,0 +1,583 @@ +/* +******************************************************************************* +* Copyright (C) 1997-2005, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* Date Name Description +* 06/21/00 aliu Creation. +******************************************************************************* +*/ + +#ifndef UTRANS_H +#define UTRANS_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_TRANSLITERATION + +#include "unicode/urep.h" +#include "unicode/parseerr.h" +#include "unicode/uenum.h" + +/******************************************************************** + * General Notes + ******************************************************************** + */ +/** + * \file + * \brief C API: Transliterator + * + * <h2> Transliteration </h2> + * The data structures and functions described in this header provide + * transliteration services. Transliteration services are implemented + * as C++ classes. The comments and documentation in this header + * assume the reader is familiar with the C++ headers translit.h and + * associated documentation. + * + * A significant but incomplete subset of the C++ transliteration + * services are available to C code through this header. In order to + * access more complex transliteration services, refer to the C++ + * headers and documentation. + * + * There are two sets of functions for working with transliterator IDs: + * + * An old, deprecated set uses char * IDs, which works for true and pure + * identifiers that these APIs were designed for, + * for example "Cyrillic-Latin". + * It does not work when the ID contains filters ("[:Script=Cyrl:]") + * or even a complete set of rules because then the ID string contains more + * than just "invariant" characters (see utypes.h). + * + * A new set of functions replaces the old ones and uses UChar * IDs, + * paralleling the UnicodeString IDs in the C++ API. (New in ICU 2.8.) + */ + +/******************************************************************** + * Data Structures + ********************************************************************/ + +/** + * An opaque transliterator for use in C. Open with utrans_openxxx() + * and close with utrans_close() when done. Equivalent to the C++ class + * Transliterator and its subclasses. + * @see Transliterator + * @stable ICU 2.0 + */ +typedef void* UTransliterator; + +/** + * Direction constant indicating the direction in a transliterator, + * e.g., the forward or reverse rules of a RuleBasedTransliterator. + * Specified when a transliterator is opened. An "A-B" transliterator + * transliterates A to B when operating in the forward direction, and + * B to A when operating in the reverse direction. + * @stable ICU 2.0 + */ +typedef enum UTransDirection { + + /** + * UTRANS_FORWARD means from <source> to <target> for a + * transliterator with ID <source>-<target>. For a transliterator + * opened using a rule, it means forward direction rules, e.g., + * "A > B". + */ + UTRANS_FORWARD, + + /** + * UTRANS_REVERSE means from <target> to <source> for a + * transliterator with ID <source>-<target>. For a transliterator + * opened using a rule, it means reverse direction rules, e.g., + * "A < B". + */ + UTRANS_REVERSE + +} UTransDirection; + +/** + * Position structure for utrans_transIncremental() incremental + * transliteration. This structure defines two substrings of the text + * being transliterated. The first region, [contextStart, + * contextLimit), defines what characters the transliterator will read + * as context. The second region, [start, limit), defines what + * characters will actually be transliterated. The second region + * should be a subset of the first. + * + * <p>After a transliteration operation, some of the indices in this + * structure will be modified. See the field descriptions for + * details. + * + * <p>contextStart <= start <= limit <= contextLimit + * + * <p>Note: All index values in this structure must be at code point + * boundaries. That is, none of them may occur between two code units + * of a surrogate pair. If any index does split a surrogate pair, + * results are unspecified. + * + * @stable ICU 2.0 + */ +typedef struct UTransPosition { + + /** + * Beginning index, inclusive, of the context to be considered for + * a transliteration operation. The transliterator will ignore + * anything before this index. INPUT/OUTPUT parameter: This parameter + * is updated by a transliteration operation to reflect the maximum + * amount of antecontext needed by a transliterator. + * @stable ICU 2.4 + */ + int32_t contextStart; + + /** + * Ending index, exclusive, of the context to be considered for a + * transliteration operation. The transliterator will ignore + * anything at or after this index. INPUT/OUTPUT parameter: This + * parameter is updated to reflect changes in the length of the + * text, but points to the same logical position in the text. + * @stable ICU 2.4 + */ + int32_t contextLimit; + + /** + * Beginning index, inclusive, of the text to be transliteratd. + * INPUT/OUTPUT parameter: This parameter is advanced past + * characters that have already been transliterated by a + * transliteration operation. + * @stable ICU 2.4 + */ + int32_t start; + + /** + * Ending index, exclusive, of the text to be transliteratd. + * INPUT/OUTPUT parameter: This parameter is updated to reflect + * changes in the length of the text, but points to the same + * logical position in the text. + * @stable ICU 2.4 + */ + int32_t limit; + +} UTransPosition; + +/******************************************************************** + * General API + ********************************************************************/ + +/** + * Open a custom transliterator, given a custom rules string + * OR + * a system transliterator, given its ID. + * Any non-NULL result from this function should later be closed with + * utrans_close(). + * + * @param id a valid transliterator ID + * @param idLength the length of the ID string, or -1 if NUL-terminated + * @param dir the desired direction + * @param rules the transliterator rules. See the C++ header rbt.h for + * rules syntax. If NULL then a system transliterator matching + * the ID is returned. + * @param rulesLength the length of the rules, or -1 if the rules + * are NUL-terminated. + * @param parseError a pointer to a UParseError struct to receive the details + * of any parsing errors. This parameter may be NULL if no + * parsing error details are desired. + * @param pErrorCode a pointer to the UErrorCode + * @return a transliterator pointer that may be passed to other + * utrans_xxx() functions, or NULL if the open call fails. + * @stable ICU 2.8 + */ +U_STABLE UTransliterator* U_EXPORT2 +utrans_openU(const UChar *id, + int32_t idLength, + UTransDirection dir, + const UChar *rules, + int32_t rulesLength, + UParseError *parseError, + UErrorCode *pErrorCode); + +/** + * Open an inverse of an existing transliterator. For this to work, + * the inverse must be registered with the system. For example, if + * the Transliterator "A-B" is opened, and then its inverse is opened, + * the result is the Transliterator "B-A", if such a transliterator is + * registered with the system. Otherwise the result is NULL and a + * failing UErrorCode is set. Any non-NULL result from this function + * should later be closed with utrans_close(). + * + * @param trans the transliterator to open the inverse of. + * @param status a pointer to the UErrorCode + * @return a pointer to a newly-opened transliterator that is the + * inverse of trans, or NULL if the open call fails. + * @stable ICU 2.0 + */ +U_STABLE UTransliterator* U_EXPORT2 +utrans_openInverse(const UTransliterator* trans, + UErrorCode* status); + +/** + * Create a copy of a transliterator. Any non-NULL result from this + * function should later be closed with utrans_close(). + * + * @param trans the transliterator to be copied. + * @param status a pointer to the UErrorCode + * @return a transliterator pointer that may be passed to other + * utrans_xxx() functions, or NULL if the clone call fails. + * @stable ICU 2.0 + */ +U_STABLE UTransliterator* U_EXPORT2 +utrans_clone(const UTransliterator* trans, + UErrorCode* status); + +/** + * Close a transliterator. Any non-NULL pointer returned by + * utrans_openXxx() or utrans_clone() should eventually be closed. + * @param trans the transliterator to be closed. + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_close(UTransliterator* trans); + +/** + * Return the programmatic identifier for this transliterator. + * If this identifier is passed to utrans_openU(), it will open + * a transliterator equivalent to this one, if the ID has been + * registered. + * + * @param trans the transliterator to return the ID of. + * @param resultLength pointer to an output variable receiving the length + * of the ID string; can be NULL + * @return the NUL-terminated ID string. This pointer remains + * valid until utrans_close() is called on this transliterator. + * + * @stable ICU 2.8 + */ +U_STABLE const UChar * U_EXPORT2 +utrans_getUnicodeID(const UTransliterator *trans, + int32_t *resultLength); + +/** + * Register an open transliterator with the system. When + * utrans_open() is called with an ID string that is equal to that + * returned by utrans_getID(adoptedTrans,...), then + * utrans_clone(adoptedTrans,...) is returned. + * + * <p>NOTE: After this call the system owns the adoptedTrans and will + * close it. The user must not call utrans_close() on adoptedTrans. + * + * @param adoptedTrans a transliterator, typically the result of + * utrans_openRules(), to be registered with the system. + * @param status a pointer to the UErrorCode + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_register(UTransliterator* adoptedTrans, + UErrorCode* status); + +/** + * Unregister a transliterator from the system. After this call the + * system will no longer recognize the given ID when passed to + * utrans_open(). If the ID is invalid then nothing is done. + * + * @param id an ID to unregister + * @param idLength the length of id, or -1 if id is zero-terminated + * @stable ICU 2.8 + */ +U_STABLE void U_EXPORT2 +utrans_unregisterID(const UChar* id, int32_t idLength); + +/** + * Set the filter used by a transliterator. A filter can be used to + * make the transliterator pass certain characters through untouched. + * The filter is expressed using a UnicodeSet pattern. If the + * filterPattern is NULL or the empty string, then the transliterator + * will be reset to use no filter. + * + * @param trans the transliterator + * @param filterPattern a pattern string, in the form accepted by + * UnicodeSet, specifying which characters to apply the + * transliteration to. May be NULL or the empty string to indicate no + * filter. + * @param filterPatternLen the length of filterPattern, or -1 if + * filterPattern is zero-terminated + * @param status a pointer to the UErrorCode + * @see UnicodeSet + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_setFilter(UTransliterator* trans, + const UChar* filterPattern, + int32_t filterPatternLen, + UErrorCode* status); + +/** + * Return the number of system transliterators. + * It is recommended to use utrans_openIDs() instead. + * + * @return the number of system transliterators. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +utrans_countAvailableIDs(void); + +/** + * Return a UEnumeration for the available transliterators. + * + * @param pErrorCode Pointer to the UErrorCode in/out parameter. + * @return UEnumeration for the available transliterators. + * Close with uenum_close(). + * + * @stable ICU 2.8 + */ +U_STABLE UEnumeration * U_EXPORT2 +utrans_openIDs(UErrorCode *pErrorCode); + +/******************************************************************** + * Transliteration API + ********************************************************************/ + +/** + * Transliterate a segment of a UReplaceable string. The string is + * passed in as a UReplaceable pointer rep and a UReplaceableCallbacks + * function pointer struct repFunc. Functions in the repFunc struct + * will be called in order to modify the rep string. + * + * @param trans the transliterator + * @param rep a pointer to the string. This will be passed to the + * repFunc functions. + * @param repFunc a set of function pointers that will be used to + * modify the string pointed to by rep. + * @param start the beginning index, inclusive; <code>0 <= start <= + * limit</code>. + * @param limit pointer to the ending index, exclusive; <code>start <= + * limit <= repFunc->length(rep)</code>. Upon return, *limit will + * contain the new limit index. The text previously occupying + * <code>[start, limit)</code> has been transliterated, possibly to a + * string of a different length, at <code>[start, + * </code><em>new-limit</em><code>)</code>, where <em>new-limit</em> + * is the return value. + * @param status a pointer to the UErrorCode + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_trans(const UTransliterator* trans, + UReplaceable* rep, + UReplaceableCallbacks* repFunc, + int32_t start, + int32_t* limit, + UErrorCode* status); + +/** + * Transliterate the portion of the UReplaceable text buffer that can + * be transliterated unambiguosly. This method is typically called + * after new text has been inserted, e.g. as a result of a keyboard + * event. The transliterator will try to transliterate characters of + * <code>rep</code> between <code>index.cursor</code> and + * <code>index.limit</code>. Characters before + * <code>index.cursor</code> will not be changed. + * + * <p>Upon return, values in <code>index</code> will be updated. + * <code>index.start</code> will be advanced to the first + * character that future calls to this method will read. + * <code>index.cursor</code> and <code>index.limit</code> will + * be adjusted to delimit the range of text that future calls to + * this method may change. + * + * <p>Typical usage of this method begins with an initial call + * with <code>index.start</code> and <code>index.limit</code> + * set to indicate the portion of <code>text</code> to be + * transliterated, and <code>index.cursor == index.start</code>. + * Thereafter, <code>index</code> can be used without + * modification in future calls, provided that all changes to + * <code>text</code> are made via this method. + * + * <p>This method assumes that future calls may be made that will + * insert new text into the buffer. As a result, it only performs + * unambiguous transliterations. After the last call to this method, + * there may be untransliterated text that is waiting for more input + * to resolve an ambiguity. In order to perform these pending + * transliterations, clients should call utrans_trans() with a start + * of index.start and a limit of index.end after the last call to this + * method has been made. + * + * @param trans the transliterator + * @param rep a pointer to the string. This will be passed to the + * repFunc functions. + * @param repFunc a set of function pointers that will be used to + * modify the string pointed to by rep. + * @param pos a struct containing the start and limit indices of the + * text to be read and the text to be transliterated + * @param status a pointer to the UErrorCode + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_transIncremental(const UTransliterator* trans, + UReplaceable* rep, + UReplaceableCallbacks* repFunc, + UTransPosition* pos, + UErrorCode* status); + +/** + * Transliterate a segment of a UChar* string. The string is passed + * in in a UChar* buffer. The string is modified in place. If the + * result is longer than textCapacity, it is truncated. The actual + * length of the result is returned in *textLength, if textLength is + * non-NULL. *textLength may be greater than textCapacity, but only + * textCapacity UChars will be written to *text, including the zero + * terminator. + * + * @param trans the transliterator + * @param text a pointer to a buffer containing the text to be + * transliterated on input and the result text on output. + * @param textLength a pointer to the length of the string in text. + * If the length is -1 then the string is assumed to be + * zero-terminated. Upon return, the new length is stored in + * *textLength. If textLength is NULL then the string is assumed to + * be zero-terminated. + * @param textCapacity a pointer to the length of the text buffer. + * Upon return, + * @param start the beginning index, inclusive; <code>0 <= start <= + * limit</code>. + * @param limit pointer to the ending index, exclusive; <code>start <= + * limit <= repFunc->length(rep)</code>. Upon return, *limit will + * contain the new limit index. The text previously occupying + * <code>[start, limit)</code> has been transliterated, possibly to a + * string of a different length, at <code>[start, + * </code><em>new-limit</em><code>)</code>, where <em>new-limit</em> + * is the return value. + * @param status a pointer to the UErrorCode + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_transUChars(const UTransliterator* trans, + UChar* text, + int32_t* textLength, + int32_t textCapacity, + int32_t start, + int32_t* limit, + UErrorCode* status); + +/** + * Transliterate the portion of the UChar* text buffer that can be + * transliterated unambiguosly. See utrans_transIncremental(). The + * string is passed in in a UChar* buffer. The string is modified in + * place. If the result is longer than textCapacity, it is truncated. + * The actual length of the result is returned in *textLength, if + * textLength is non-NULL. *textLength may be greater than + * textCapacity, but only textCapacity UChars will be written to + * *text, including the zero terminator. See utrans_transIncremental() + * for usage details. + * + * @param trans the transliterator + * @param text a pointer to a buffer containing the text to be + * transliterated on input and the result text on output. + * @param textLength a pointer to the length of the string in text. + * If the length is -1 then the string is assumed to be + * zero-terminated. Upon return, the new length is stored in + * *textLength. If textLength is NULL then the string is assumed to + * be zero-terminated. + * @param textCapacity the length of the text buffer + * @param pos a struct containing the start and limit indices of the + * text to be read and the text to be transliterated + * @param status a pointer to the UErrorCode + * @see utrans_transIncremental + * @stable ICU 2.0 + */ +U_STABLE void U_EXPORT2 +utrans_transIncrementalUChars(const UTransliterator* trans, + UChar* text, + int32_t* textLength, + int32_t textCapacity, + UTransPosition* pos, + UErrorCode* status); + +/* deprecated API ----------------------------------------------------------- */ + +/* see utrans.h documentation for why these functions are deprecated */ + +/** + * Deprecated, use utrans_openU() instead. + * Open a custom transliterator, given a custom rules string + * OR + * a system transliterator, given its ID. + * Any non-NULL result from this function should later be closed with + * utrans_close(). + * + * @param id a valid ID, as returned by utrans_getAvailableID() + * @param dir the desired direction + * @param rules the transliterator rules. See the C++ header rbt.h + * for rules syntax. If NULL then a system transliterator matching + * the ID is returned. + * @param rulesLength the length of the rules, or -1 if the rules + * are zero-terminated. + * @param parseError a pointer to a UParseError struct to receive the + * details of any parsing errors. This parameter may be NULL if no + * parsing error details are desired. + * @param status a pointer to the UErrorCode + * @return a transliterator pointer that may be passed to other + * utrans_xxx() functions, or NULL if the open call fails. + * @deprecated ICU 2.8 Use utrans_openU() instead, see utrans.h + */ +U_DEPRECATED UTransliterator* U_EXPORT2 +utrans_open(const char* id, + UTransDirection dir, + const UChar* rules, /* may be Null */ + int32_t rulesLength, /* -1 if null-terminated */ + UParseError* parseError, /* may be Null */ + UErrorCode* status); + +/** + * Deprecated, use utrans_getUnicodeID() instead. + * Return the programmatic identifier for this transliterator. + * If this identifier is passed to utrans_open(), it will open + * a transliterator equivalent to this one, if the ID has been + * registered. + * @param trans the transliterator to return the ID of. + * @param buf the buffer in which to receive the ID. This may be + * NULL, in which case no characters are copied. + * @param bufCapacity the capacity of the buffer. Ignored if buf is + * NULL. + * @return the actual length of the ID, not including + * zero-termination. This may be greater than bufCapacity. + * @deprecated ICU 2.8 Use utrans_getUnicodeID() instead, see utrans.h + */ +U_DEPRECATED int32_t U_EXPORT2 +utrans_getID(const UTransliterator* trans, + char* buf, + int32_t bufCapacity); + +/** + * Deprecated, use utrans_unregisterID() instead. + * Unregister a transliterator from the system. After this call the + * system will no longer recognize the given ID when passed to + * utrans_open(). If the id is invalid then nothing is done. + * + * @param id a zero-terminated ID + * @deprecated ICU 2.8 Use utrans_unregisterID() instead, see utrans.h + */ +U_DEPRECATED void U_EXPORT2 +utrans_unregister(const char* id); + +/** + * Deprecated, use utrans_openIDs() instead. + * Return the ID of the index-th system transliterator. The result + * is placed in the given buffer. If the given buffer is too small, + * the initial substring is copied to buf. The result in buf is + * always zero-terminated. + * + * @param index the number of the transliterator to return. Must + * satisfy 0 <= index < utrans_countAvailableIDs(). If index is out + * of range then it is treated as if it were 0. + * @param buf the buffer in which to receive the ID. This may be + * NULL, in which case no characters are copied. + * @param bufCapacity the capacity of the buffer. Ignored if buf is + * NULL. + * @return the actual length of the index-th ID, not including + * zero-termination. This may be greater than bufCapacity. + * @deprecated ICU 2.8 Use utrans_openIDs() instead, see utrans.h + */ +U_DEPRECATED int32_t U_EXPORT2 +utrans_getAvailableID(int32_t index, + char* buf, + int32_t bufCapacity); + +#endif /* #if !UCONFIG_NO_TRANSLITERATION */ + +#endif diff --git a/Build/source/libs/icu-xetex/i18n/unicode/vtzone.h b/Build/source/libs/icu-xetex/i18n/unicode/vtzone.h new file mode 100644 index 00000000000..420f61a2baa --- /dev/null +++ b/Build/source/libs/icu-xetex/i18n/unicode/vtzone.h @@ -0,0 +1,443 @@ +/* +******************************************************************************* +* Copyright (C) 2007, International Business Machines Corporation and * +* others. All Rights Reserved. * +******************************************************************************* +*/ +#ifndef VTZONE_H +#define VTZONE_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: RFC2445 VTIMEZONE support + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/basictz.h" + +U_NAMESPACE_BEGIN + +class VTZWriter; +class VTZReader; +class UVector; + +/** + * <code>VTimeZone</code> is a class implementing RFC2445 VTIMEZONE. You can create a + * <code>VTimeZone</code> instance from a time zone ID supported by <code>TimeZone</code>. + * With the <code>VTimeZone</code> instance created from the ID, you can write out the rule + * in RFC2445 VTIMEZONE format. Also, you can create a <code>VTimeZone</code> instance + * from RFC2445 VTIMEZONE data stream, which allows you to calculate time + * zone offset by the rules defined by the data.<br><br> + * Note: The consumer of this class reading or writing VTIMEZONE data is responsible to + * decode or encode Non-ASCII text. Methods reading/writing VTIMEZONE data in this class + * do nothing with MIME encoding. + * @draft ICU 3.8 + */ +class U_I18N_API VTimeZone : public BasicTimeZone { +public: + /** + * Copy constructor. + * @param source The <code>VTimeZone</code> object to be copied. + * @draft ICU 3.8 + */ + VTimeZone(const VTimeZone& source); + + /** + * Destructor. + * @draft ICU 3.8 + */ + virtual ~VTimeZone(); + + /** + * Assignment operator. + * @param right The object to be copied. + * @draft ICU 3.8 + */ + VTimeZone& operator=(const VTimeZone& right); + + /** + * Return true if the given <code>TimeZone</code> objects are + * semantically equal. Objects of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZone</code> objects are + *semantically equal. + * @draft ICU 3.8 + */ + virtual UBool operator==(const TimeZone& that) const; + + /** + * Return true if the given <code>TimeZone</code> objects are + * semantically unequal. Objects of different subclasses are considered unequal. + * @param that The object to be compared with. + * @return true if the given <code>TimeZone</code> objects are + * semantically unequal. + * @draft ICU 3.8 + */ + virtual UBool operator!=(const TimeZone& that) const; + + /** + * Create a <code>VTimeZone</code> instance by the time zone ID. + * @param ID The time zone ID, such as America/New_York + * @return A <code>VTimeZone</code> object initialized by the time zone ID, + * or NULL when the ID is unknown. + * @draft ICU 3.8 + */ + static VTimeZone* createVTimeZoneByID(const UnicodeString& ID); + + /** + * Create a <code>VTimeZone</code> instance by RFC2445 VTIMEZONE data + * + * @param vtzdata The string including VTIMEZONE data block + * @param status Output param to filled in with a success or an error. + * @return A <code>VTimeZone</code> initialized by the VTIMEZONE data or + * NULL if failed to load the rule from the VTIMEZONE data. + * @draft ICU 3.8 + */ + static VTimeZone* createVTimeZone(const UnicodeString& vtzdata, UErrorCode& status); + + /** + * Gets the RFC2445 TZURL property value. When a <code>VTimeZone</code> instance was + * created from VTIMEZONE data, the initial value is set by the TZURL property value + * in the data. Otherwise, the initial value is not set. + * @param url Receives the RFC2445 TZURL property value. + * @return TRUE if TZURL attribute is available and value is set. + * @draft ICU 3.8 + */ + UBool getTZURL(UnicodeString& url) const; + + /** + * Sets the RFC2445 TZURL property value. + * @param url The TZURL property value. + * @draft ICU 3.8 + */ + void setTZURL(const UnicodeString& url); + + /** + * Gets the RFC2445 LAST-MODIFIED property value. When a <code>VTimeZone</code> instance + * was created from VTIMEZONE data, the initial value is set by the LAST-MODIFIED property + * value in the data. Otherwise, the initial value is not set. + * @param lastModified Receives the last modified date. + * @return TRUE if lastModified attribute is available and value is set. + * @draft ICU 3.8 + */ + UBool getLastModified(UDate& lastModified) const; + + /** + * Sets the RFC2445 LAST-MODIFIED property value. + * @param lastModified The LAST-MODIFIED date. + * @draft ICU 3.8 + */ + void setLastModified(UDate lastModified); + + /** + * Writes RFC2445 VTIMEZONE data for this time zone + * @param result Output param to filled in with the VTIMEZONE data. + * @param status Output param to filled in with a success or an error. + * @draft ICU 3.8 + */ + void write(UnicodeString& result, UErrorCode& status) const; + + /** + * Writes RFC2445 VTIMEZONE data for this time zone applicalbe + * for dates after the specified start time. + * @param start The start date. + * @param result Output param to filled in with the VTIMEZONE data. + * @param status Output param to filled in with a success or an error. + * @draft ICU 3.8 + */ + void write(UDate start, UnicodeString& result, UErrorCode& status) /*const*/; + + /** + * Writes RFC2445 VTIMEZONE data applicalbe for the specified date. + * Some common iCalendar implementations can only handle a single time + * zone property or a pair of standard and daylight time properties using + * BYDAY rule with day of week (such as BYDAY=1SUN). This method produce + * the VTIMEZONE data which can be handled these implementations. The rules + * produced by this method can be used only for calculating time zone offset + * around the specified date. + * @param time The date used for rule extraction. + * @param result Output param to filled in with the VTIMEZONE data. + * @param status Output param to filled in with a success or an error. + * @draft ICU 3.8 + */ + void writeSimple(UDate time, UnicodeString& result, UErrorCode& status) /*const*/; + + /** + * Clones TimeZone objects polymorphically. Clients are responsible for deleting + * the TimeZone object cloned. + * @return A new copy of this TimeZone object. + * @draft ICU 3.8 + */ + virtual TimeZone* clone(void) const; + + /** + * Returns the TimeZone's adjusted GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time in this time zone, taking daylight savings time into + * account) as of a particular reference date. The reference date is used to determine + * whether daylight savings time is in effect and needs to be figured into the offset + * that is returned (in other words, what is the adjusted GMT offset in this time zone + * at this particular date and time?). For the time zones produced by createTimeZone(), + * the reference data is specified according to the Gregorian calendar, and the date + * and time fields are local standard time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, local standard time + * @param status Output param to filled in with a success or an error. + * @return The offset in milliseconds to add to GMT to get local time. + * @draft ICU 3.8 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, UErrorCode& status) const; + + /** + * Gets the time zone offset, for current date, modified in case of + * daylight savings. This is the offset to add *to* UTC to get local time. + * + * <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload, + * which returns both the raw and the DST offset for a given time. This method + * is retained only for backward compatibility. + * + * @param era The reference date's era + * @param year The reference date's year + * @param month The reference date's month (0-based; 0 is January) + * @param day The reference date's day-in-month (1-based) + * @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday) + * @param millis The reference date's milliseconds in day, local standard time + * @param monthLength The length of the given month in days. + * @param status Output param to filled in with a success or an error. + * @return The offset in milliseconds to add to GMT to get local time. + * @draft ICU 3.8 + */ + virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day, + uint8_t dayOfWeek, int32_t millis, + int32_t monthLength, UErrorCode& status) const; + + /** + * Returns the time zone raw and GMT offset for the given moment + * in time. Upon return, local-millis = GMT-millis + rawOffset + + * dstOffset. All computations are performed in the proleptic + * Gregorian calendar. The default implementation in the TimeZone + * class delegates to the 8-argument getOffset(). + * + * @param date moment in time for which to return offsets, in + * units of milliseconds from January 1, 1970 0:00 GMT, either GMT + * time or local wall time, depending on `local'. + * @param local if true, `date' is local wall time; otherwise it + * is in GMT time. + * @param rawOffset output parameter to receive the raw offset, that + * is, the offset not including DST adjustments + * @param dstOffset output parameter to receive the DST offset, + * that is, the offset to be added to `rawOffset' to obtain the + * total offset between local and GMT time. If DST is not in + * effect, this value is zero; otherwise it is a positive value, + * typically one hour. + * @param ec input-output error code + * @draft ICU 3.8 + */ + virtual void getOffset(UDate date, UBool local, int32_t& rawOffset, + int32_t& dstOffset, UErrorCode& ec) const; + + /** + * Sets the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @param offsetMillis The new raw GMT offset for this time zone. + * @draft ICU 3.8 + */ + virtual void setRawOffset(int32_t offsetMillis); + + /** + * Returns the TimeZone's raw GMT offset (i.e., the number of milliseconds to add + * to GMT to get local time, before taking daylight savings time into account). + * + * @return The TimeZone's raw GMT offset. + * @draft ICU 3.8 + */ + virtual int32_t getRawOffset(void) const; + + /** + * Queries if this time zone uses daylight savings time. + * @return true if this time zone uses daylight savings time, + * false, otherwise. + * @draft ICU 3.8 + */ + virtual UBool useDaylightTime(void) const; + + /** + * Queries if the given date is in daylight savings time in + * this time zone. + * This method is wasteful since it creates a new GregorianCalendar and + * deletes it each time it is called. This is a deprecated method + * and provided only for Java compatibility. + * + * @param date the given UDate. + * @param status Output param filled in with success/error code. + * @return true if the given date is in daylight savings time, + * false, otherwise. + * @deprecated ICU 2.4. Use Calendar::inDaylightTime() instead. + */ + virtual UBool inDaylightTime(UDate date, UErrorCode& status) const; + + /** + * Returns true if this zone has the same rule and offset as another zone. + * That is, if this zone differs only in ID, if at all. + * @param other the <code>TimeZone</code> object to be compared with + * @return true if the given zone is the same as this one, + * with the possible exception of the ID + * @draft ICU 3.8 + */ + virtual UBool hasSameRules(const TimeZone& other) const; + + /** + * Gets the first time zone transition after the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the first transition after the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Gets the most recent time zone transition before the base time. + * @param base The base time. + * @param inclusive Whether the base time is inclusive or not. + * @param result Receives the most recent transition before the base time. + * @return TRUE if the transition is found. + * @draft ICU 3.8 + */ + virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) /*const*/; + + /** + * Returns the number of <code>TimeZoneRule</code>s which represents time transitions, + * for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except + * <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value. + * @param status Receives error status code. + * @return The number of <code>TimeZoneRule</code>s representing time transitions. + * @draft ICU 3.8 + */ + virtual int32_t countTransitionRules(UErrorCode& status) /*const*/; + + /** + * Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code> + * which represent time transitions for this time zone. On successful return, + * the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and + * the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code> + * instances up to the size specified by trscount. The results are referencing the + * rule instance held by this time zone instance. Therefore, after this time zone + * is destructed, they are no longer available. + * @param initial Receives the initial timezone rule + * @param trsrules Receives the timezone transition rules + * @param trscount On input, specify the size of the array 'transitions' receiving + * the timezone transition rules. On output, actual number of + * rules filled in the array will be set. + * @param status Receives error status code. + * @draft ICU 3.8 + */ + virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial, + const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) /*const*/; + +private: + enum { DEFAULT_VTIMEZONE_LINES = 100 }; + + /** + * Default constructor. + */ + VTimeZone(); + static VTimeZone* createVTimeZone(VTZReader* reader); + void write(VTZWriter& writer, UErrorCode& status) const; + void write(UDate start, VTZWriter& writer, UErrorCode& status) /*const*/; + void writeSimple(UDate time, VTZWriter& writer, UErrorCode& status) /*const*/; + void load(VTZReader& reader, UErrorCode& status); + void parse(UErrorCode& status); + + void writeZone(VTZWriter& w, BasicTimeZone& basictz, UVector* customProps, + UErrorCode& status) const; + + void writeHeaders(VTZWriter& w, UErrorCode& status) const; + void writeFooter(VTZWriter& writer, UErrorCode& status) const; + + void writeZonePropsByTime(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, UDate time, UBool withRDATE, + UErrorCode& status) const; + void writeZonePropsByDOM(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, + int32_t month, int32_t dayOfMonth, UDate startTime, UDate untilTime, + UErrorCode& status) const; + void writeZonePropsByDOW(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, + int32_t month, int32_t weekInMonth, int32_t dayOfWeek, + UDate startTime, UDate untilTime, UErrorCode& status) const; + void writeZonePropsByDOW_GEQ_DOM(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, + int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + UDate startTime, UDate untilTime, UErrorCode& status) const; + void writeZonePropsByDOW_GEQ_DOM_sub(VTZWriter& writer, int32_t month, int32_t dayOfMonth, + int32_t dayOfWeek, int32_t numDays, + UDate untilTime, int32_t fromOffset, UErrorCode& status) const; + void writeZonePropsByDOW_LEQ_DOM(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, + int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, + UDate startTime, UDate untilTime, UErrorCode& status) const; + void writeFinalRule(VTZWriter& writer, UBool isDst, const AnnualTimeZoneRule* rule, + int32_t fromRawOffset, int32_t fromDSTSavings, + UDate startTime, UErrorCode& status) const; + + void beginZoneProps(VTZWriter& writer, UBool isDst, const UnicodeString& tzname, + int32_t fromOffset, int32_t toOffset, UDate startTime, UErrorCode& status) const; + void endZoneProps(VTZWriter& writer, UBool isDst, UErrorCode& status) const; + void beginRRULE(VTZWriter& writer, int32_t month, UErrorCode& status) const; + void appendUNTIL(VTZWriter& writer, const UnicodeString& until, UErrorCode& status) const; + + BasicTimeZone *tz; + UVector *vtzlines; + UnicodeString tzurl; + UDate lastmod; + UnicodeString olsonzid; + UnicodeString icutzver; + +public: + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . erived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @draft ICU 3.8 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @draft ICU 3.8 + */ + virtual UClassID getDynamicClassID(void) const; +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif // VTZONE_H +//eof |