|
1 /* |
|
2 * Copyright 2001-2004 Unicode, Inc. |
|
3 * |
|
4 * Disclaimer |
|
5 * |
|
6 * This source code is provided as is by Unicode, Inc. No claims are |
|
7 * made as to fitness for any particular purpose. No warranties of any |
|
8 * kind are expressed or implied. The recipient agrees to determine |
|
9 * applicability of information provided. If this file has been |
|
10 * purchased on magnetic or optical media from Unicode, Inc., the |
|
11 * sole remedy for any claim will be exchange of defective media |
|
12 * within 90 days of receipt. |
|
13 * |
|
14 * Limitations on Rights to Redistribute This Code |
|
15 * |
|
16 * Unicode, Inc. hereby grants the right to freely use the information |
|
17 * supplied in this file in the creation of products supporting the |
|
18 * Unicode Standard, and to make copies of this file in any form |
|
19 * for internal or external distribution as long as this notice |
|
20 * remains attached. |
|
21 */ |
|
22 |
|
23 // Note that this component has been checked, see Nokia TALKO |
|
24 // component: unicode, version unicode-IDS-1 |
|
25 |
|
26 /* --------------------------------------------------------------------- |
|
27 |
|
28 Conversions between UTF32, UTF-16, and UTF-8. Header file. |
|
29 |
|
30 Several funtions are included here, forming a complete set of |
|
31 conversions between the three formats. UTF-7 is not included |
|
32 here, but is handled in a separate source file. |
|
33 |
|
34 Each of these routines takes pointers to input buffers and output |
|
35 buffers. The input buffers are const. |
|
36 |
|
37 Each routine converts the text between *sourceStart and sourceEnd, |
|
38 putting the result into the buffer between *targetStart and |
|
39 targetEnd. Note: the end pointers are *after* the last item: e.g. |
|
40 *(sourceEnd - 1) is the last item. |
|
41 |
|
42 The return result indicates whether the conversion was successful, |
|
43 and if not, whether the problem was in the source or target buffers. |
|
44 (Only the first encountered problem is indicated.) |
|
45 |
|
46 After the conversion, *sourceStart and *targetStart are both |
|
47 updated to point to the end of last text successfully converted in |
|
48 the respective buffers. |
|
49 |
|
50 Input parameters: |
|
51 sourceStart - pointer to a pointer to the source buffer. |
|
52 The contents of this are modified on return so that |
|
53 it points at the next thing to be converted. |
|
54 targetStart - similarly, pointer to pointer to the target buffer. |
|
55 sourceEnd, targetEnd - respectively pointers to the ends of the |
|
56 two buffers, for overflow checking only. |
|
57 |
|
58 These conversion functions take a ConversionFlags argument. When this |
|
59 flag is set to strict, both irregular sequences and isolated surrogates |
|
60 will cause an error. When the flag is set to lenient, both irregular |
|
61 sequences and isolated surrogates are converted. |
|
62 |
|
63 Whether the flag is strict or lenient, all illegal sequences will cause |
|
64 an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>, |
|
65 or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code |
|
66 must check for illegal sequences. |
|
67 |
|
68 When the flag is set to lenient, characters over 0x10FFFF are converted |
|
69 to the replacement character; otherwise (when the flag is set to strict) |
|
70 they constitute an error. |
|
71 |
|
72 Output parameters: |
|
73 The value "sourceIllegal" is returned from some routines if the input |
|
74 sequence is malformed. When "sourceIllegal" is returned, the source |
|
75 value will point to the illegal value that caused the problem. E.g., |
|
76 in UTF-8 when a sequence is malformed, it points to the start of the |
|
77 malformed sequence. |
|
78 |
|
79 Author: Mark E. Davis, 1994. |
|
80 Rev History: Rick McGowan, fixes & updates May 2001. |
|
81 Fixes & updates, Sept 2001. |
|
82 |
|
83 ------------------------------------------------------------------------ */ |
|
84 |
|
85 /* --------------------------------------------------------------------- |
|
86 The following 4 definitions are compiler-specific. |
|
87 The C standard does not guarantee that wchar_t has at least |
|
88 16 bits, so wchar_t is no less portable than unsigned short! |
|
89 All should be unsigned values to avoid sign extension during |
|
90 bit mask & shift operations. |
|
91 ------------------------------------------------------------------------ */ |
|
92 |
|
93 typedef unsigned long UTF32; /* at least 32 bits */ |
|
94 typedef unsigned short UTF16; /* at least 16 bits */ |
|
95 typedef unsigned char UTF8; /* typically 8 bits */ |
|
96 typedef unsigned char Boolean; /* 0 or 1 */ |
|
97 |
|
98 /* Some fundamental constants */ |
|
99 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD |
|
100 #define UNI_MAX_BMP (UTF32)0x0000FFFF |
|
101 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF |
|
102 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF |
|
103 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF |
|
104 |
|
105 typedef enum |
|
106 { |
|
107 conversionOK, /* conversion successful */ |
|
108 sourceExhausted, /* partial character in source, but hit end */ |
|
109 targetExhausted, /* insuff. room in target for conversion */ |
|
110 sourceIllegal /* source sequence is illegal/malformed */ |
|
111 } ConversionResult; |
|
112 |
|
113 typedef enum |
|
114 { |
|
115 strictConversion = 0, |
|
116 lenientConversion |
|
117 } ConversionFlags; |
|
118 |
|
119 /* This is for C++ and does no harm in C */ |
|
120 #ifdef __cplusplus |
|
121 extern "C" |
|
122 { |
|
123 #endif |
|
124 |
|
125 ConversionResult ConvertUTF8toUTF16( |
|
126 const UTF8** sourceStart, const UTF8* sourceEnd, |
|
127 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); |
|
128 |
|
129 ConversionResult ConvertUTF16toUTF8( |
|
130 const UTF16** sourceStart, const UTF16* sourceEnd, |
|
131 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); |
|
132 |
|
133 ConversionResult ConvertUTF8toUTF32( |
|
134 const UTF8** sourceStart, const UTF8* sourceEnd, |
|
135 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); |
|
136 |
|
137 ConversionResult ConvertUTF32toUTF8( |
|
138 const UTF32** sourceStart, const UTF32* sourceEnd, |
|
139 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); |
|
140 |
|
141 ConversionResult ConvertUTF16toUTF32( |
|
142 const UTF16** sourceStart, const UTF16* sourceEnd, |
|
143 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); |
|
144 |
|
145 ConversionResult ConvertUTF32toUTF16( |
|
146 const UTF32** sourceStart, const UTF32* sourceEnd, |
|
147 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); |
|
148 |
|
149 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd); |
|
150 |
|
151 #ifdef __cplusplus |
|
152 } |
|
153 #endif |
|
154 |
|
155 /* --------------------------------------------------------------------- */ |