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
150
151
152
153
154
155
156
|
/*
*******************************************************************************
*
* Copyright (C) 2003-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: usprep.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2003jul2
* created by: Ram Viswanadha
*/
#ifndef __USPREP_H__
#define __USPREP_H__
/**
* \file
* \brief C API: Implements the StringPrep algorithm.
*/
#include "unicode/utypes.h"
/**
*
* StringPrep API implements the StingPrep framework as described by RFC 3454.
* StringPrep prepares Unicode strings for use in network protocols.
* Profiles of StingPrep are set of rules and data according to with the
* Unicode Strings are prepared. Each profiles contains tables which describe
* how a code point should be treated. The tables are broadly classied into
* <ul>
* <li> Unassinged Table: Contains code points that are unassigned
* in the Unicode Version supported by StringPrep. Currently
* RFC 3454 supports Unicode 3.2. </li>
* <li> Prohibited Table: Contains code points that are prohibted from
* the output of the StringPrep processing function. </li>
* <li> Mapping Table: Contains code ponts that are deleted from the output or case mapped. </li>
* </ul>
*
* The procedure for preparing Unicode strings:
* <ol>
* <li> Map: For each character in the input, check if it has a mapping
* and, if so, replace it with its mapping. </li>
* <li> Normalize: Possibly normalize the result of step 1 using Unicode
* normalization. </li>
* <li> Prohibit: Check for any characters that are not allowed in the
* output. If any are found, return an error.</li>
* <li> Check bidi: Possibly check for right-to-left characters, and if
* any are found, make sure that the whole string satisfies the
* requirements for bidirectional strings. If the string does not
* satisfy the requirements for bidirectional strings, return an
* error. </li>
* </ol>
* @author Ram Viswanadha
*/
#if !UCONFIG_NO_IDNA
#include "unicode/parseerr.h"
/**
* The StringPrep profile
* @stable ICU 2.8
*/
typedef struct UStringPrepProfile UStringPrepProfile;
/**
* Option to prohibit processing of unassigned code points in the input
*
* @see usprep_prepare
* @stable ICU 2.8
*/
#define USPREP_DEFAULT 0x0000
/**
* Option to allow processing of unassigned code points in the input
*
* @see usprep_prepare
* @stable ICU 2.8
*/
#define USPREP_ALLOW_UNASSIGNED 0x0001
/**
* Creates a StringPrep profile from the data file.
*
* @param path string containing the full path pointing to the directory
* where the profile reside followed by the package name
* e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system.
* if NULL, ICU default data files will be used.
* @param fileName name of the profile file to be opened
* @param status ICU error code in/out parameter. Must not be NULL.
* Must fulfill U_SUCCESS before the function call.
* @return Pointer to UStringPrepProfile that is opened. Should be closed by
* calling usprep_close()
* @see usprep_close()
* @stable ICU 2.8
*/
U_STABLE UStringPrepProfile* U_EXPORT2
usprep_open(const char* path,
const char* fileName,
UErrorCode* status);
/**
* Closes the profile
* @param profile The profile to close
* @stable ICU 2.8
*/
U_STABLE void U_EXPORT2
usprep_close(UStringPrepProfile* profile);
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param prep The profile to use
* @param src Pointer to UChar buffer containing the string to prepare
* @param srcLength Number of characters in the source string
* @param dest Pointer to the destination buffer to receive the output
* @param destCapacity The capacity of destination array
* @param options A bit set of options:
*
* - USPREP_NONE Prohibit processing of unassigned code points in the input
*
* - USPREP_ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @param parseError Pointer to UParseError struct to receive information on position
* of error if an error is encountered. Can be NULL.
* @param status ICU in/out error code parameter.
* U_INVALID_CHAR_FOUND if src contains
* unmatched single surrogates.
* U_INDEX_OUTOFBOUNDS_ERROR if src contains
* too many code points.
* U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
* @return The number of UChars in the destination buffer
* @stable ICU 2.8
*/
U_STABLE int32_t U_EXPORT2
usprep_prepare( const UStringPrepProfile* prep,
const UChar* src, int32_t srcLength,
UChar* dest, int32_t destCapacity,
int32_t options,
UParseError* parseError,
UErrorCode* status );
#endif /* #if !UCONFIG_NO_IDNA */
#endif
|
