1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
/*
**********************************************************************
* Copyright (C) 1999-2002, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File USC_IMPL.H
*
* Modification History:
*
* Date Name Description
* 07/08/2002 Eric Mader Creation.
******************************************************************************
*/
#ifndef USC_IMPL_H
#define USC_IMPL_H
#include "unicode/utypes.h"
#include "unicode/uscript.h"
/**
* <code>UScriptRun</code> is used to find runs of characters in
* the same script. It implements a simple iterator over an array
* of characters. The iterator will resolve script-neutral characters
* like punctuation into the script of the surrounding characters.
*
* The iterator will try to match paired punctuation. If it sees an
* opening punctuation character, it will remember the script that
* was assigned to that character, and assign the same script to the
* matching closing punctuation.
*
* Scripts are chosen based on the <code>UScriptCode</code> enumeration.
* No attempt is made to combine related scripts into a single run. In
* particular, Hiragana, Katakana, and Han characters will appear in seperate
* runs.
* Here is an example of how to iterate over script runs:
* <pre>
* \code
* void printScriptRuns(const UChar *text, int32_t length)
* {
* UErrorCode error = U_ZERO_ERROR;
* UScriptRun *scriptRun = uscript_openRun(text, testLength, &error);
* int32_t start = 0, limit = 0;
* UScriptCode code = USCRIPT_INVALID_CODE;
*
* while (uscript_nextRun(&start, &limit, &code)) {
* printf("Script '%s' from %d to %d.\n", uscript_getName(code), start, limit);
* }
*
* uscript_closeRun(scriptRun);
* }
* </pre>
*
* @draft ICU 2.2
*/
struct UScriptRun;
typedef struct UScriptRun UScriptRun;
/**
* Create a <code>UScriptRun</code> object for iterating over the given text. This object must
* be freed using <code>uscript_closeRun()</code>. Note that this object does not copy the source text,
* only the pointer to it. You must make sure that the pointer remains valid until you call
* <code>uscript_closeRun()</code> or <code>uscript_setRunText()</code>.
*
* @param src is the address of the array of characters over which to iterate.
* if <code>src == NULL</code> and <code>length == 0</code>,
* an empty <code>UScriptRun</code> object will be returned.
*
* @param length is the number of characters over which to iterate.
*
* @param pErrorCode is a pointer to a valid <code>UErrorCode</code> value. If this value
* indicates a failure on entry, the function will immediately return.
* On exit the value will indicate the success of the operation.
*
* @return the address of <code>UScriptRun</code> object which will iterate over the text,
* or <code>NULL</code> if the operation failed.
*
* @draft ICU 2.2
*/
U_CAPI UScriptRun * U_EXPORT2
uscript_openRun(const UChar *src, int32_t length, UErrorCode *pErrorCode);
/**
* Frees the given <code>UScriptRun</code> object and any storage associated with it.
* On return, scriptRun no longer points to a valid <code>UScriptRun</code> object.
*
* @param scriptRun is the <code>UScriptRun</code> object which will be freed.
*
* @draft ICU 2.2
*/
U_CAPI void U_EXPORT2
uscript_closeRun(UScriptRun *scriptRun);
/**
* Reset the <code>UScriptRun</code> object so that it will start iterating from
* the beginning.
*
* @param scriptRun is the address of the <code>UScriptRun</code> object to be reset.
*
* @draft ICU 2.2
*/
U_CAPI void U_EXPORT2
uscript_resetRun(UScriptRun *scriptRun);
/**
* Change the text over which the given <code>UScriptRun</code> object iterates.
*
* @param scriptRun is the <code>UScriptRun</code> object which will be changed.
*
* @param src is the address of the new array of characters over which to iterate.
* If <code>src == NULL</code> and <code>length == 0</code>,
* the <code>UScriptRun</code> object will become empty.
*
* @param length is the new number of characters over which to iterate
*
* @param pErrorCode is a pointer to a valid <code>UErrorCode</code> value. If this value
* indicates a failure on entry, the function will immediately return.
* On exit the value will indicate the success of the operation.
*
* @draft ICU 2.2
*/
U_CAPI void U_EXPORT2
uscript_setRunText(UScriptRun *scriptRun, const UChar *src, int32_t length, UErrorCode *pErrorCode);
/**
* Advance the <code>UScriptRun</code> object to the next script run, return the start and limit
* offsets, and the script of the run.
*
* @param scriptRun is the address of the <code>UScriptRun</code> object.
*
* @param pRunStart is a pointer to the variable to receive the starting offset of the next run.
* This pointer can be <code>NULL</code> if the value is not needed.
*
* @param pRunLimit is a pointer to the variable to receive the limit offset of the next run.
* This pointer can be <code>NULL</code> if the value is not needed.
*
* @param pRunScript is a pointer to the variable to receive the UScriptCode for the
* script of the current run. This pointer can be <code>NULL</code> if the value is not needed.
*
* @return true if there was another script run.
*
* @draft ICU 2.2
*/
U_CAPI UBool U_EXPORT2
uscript_nextRun(UScriptRun *scriptRun, int32_t *pRunStart, int32_t *pRunLimit, UScriptCode *pRunScript);
#endif
|
