• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1 /*
2  * Copyright © 1991-2015 Unicode, Inc. All rights reserved.
3  * Distributed under the Terms of Use in
4  * http://www.unicode.org/copyright.html.
5  *
6  * Permission is hereby granted, free of charge, to any person obtaining
7  * a copy of the Unicode data files and any associated documentation
8  * (the "Data Files") or Unicode software and any associated documentation
9  * (the "Software") to deal in the Data Files or Software
10  * without restriction, including without limitation the rights to use,
11  * copy, modify, merge, publish, distribute, and/or sell copies of
12  * the Data Files or Software, and to permit persons to whom the Data Files
13  * or Software are furnished to do so, provided that
14  * (a) this copyright and permission notice appear with all copies
15  * of the Data Files or Software,
16  * (b) this copyright and permission notice appear in associated
17  * documentation, and
18  * (c) there is clear notice in each modified Data File or in the Software
19  * as well as in the documentation associated with the Data File(s) or
20  * Software that the data or software has been modified.
21  *
22  * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF
23  * ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
24  * WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
25  * NONINFRINGEMENT OF THIRD PARTY RIGHTS.
26  * IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS
27  * NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL
28  * DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
29  * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
30  * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
31  * PERFORMANCE OF THE DATA FILES OR SOFTWARE.
32  *
33  * Except as contained in this notice, the name of a copyright holder
34  * shall not be used in advertising or otherwise to promote the sale,
35  * use or other dealings in these Data Files or Software without prior
36  * written authorization of the copyright holder.
37  */
38 
39 #ifndef COMMON_CONVERT_UTF_H_
40 #define COMMON_CONVERT_UTF_H_
41 
42 /* ---------------------------------------------------------------------
43 
44 Conversions between UTF32, UTF-16, and UTF-8.  Header file.
45 
46 Several funtions are included here, forming a complete set of
47 conversions between the three formats.  UTF-7 is not included
48 here, but is handled in a separate source file.
49 
50 Each of these routines takes pointers to input buffers and output
51 buffers.  The input buffers are const.
52 
53 Each routine converts the text between *sourceStart and sourceEnd,
54 putting the result into the buffer between *targetStart and
55 targetEnd. Note: the end pointers are *after* the last item: e.g.
56 *(sourceEnd - 1) is the last item.
57 
58 The return result indicates whether the conversion was successful,
59 and if not, whether the problem was in the source or target buffers.
60 (Only the first encountered problem is indicated.)
61 
62 After the conversion, *sourceStart and *targetStart are both
63 updated to point to the end of last text successfully converted in
64 the respective buffers.
65 
66 Input parameters:
67 sourceStart - pointer to a pointer to the source buffer.
68 The contents of this are modified on return so that
69 it points at the next thing to be converted.
70 targetStart - similarly, pointer to pointer to the target buffer.
71 sourceEnd, targetEnd - respectively pointers to the ends of the
72 two buffers, for overflow checking only.
73 
74 These conversion functions take a ConversionFlags argument. When this
75 flag is set to strict, both irregular sequences and isolated surrogates
76 will cause an error.  When the flag is set to lenient, both irregular
77 sequences and isolated surrogates are converted.
78 
79 Whether the flag is strict or lenient, all illegal sequences will cause
80 an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
81 or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
82 must check for illegal sequences.
83 
84 When the flag is set to lenient, characters over 0x10FFFF are converted
85 to the replacement character; otherwise (when the flag is set to strict)
86 they constitute an error.
87 
88 Output parameters:
89 The value "sourceIllegal" is returned from some routines if the input
90 sequence is malformed.  When "sourceIllegal" is returned, the source
91 value will point to the illegal value that caused the problem. E.g.,
92 in UTF-8 when a sequence is malformed, it points to the start of the
93 malformed sequence.
94 
95 Author: Mark E. Davis, 1994.
96 Rev History: Rick McGowan, fixes & updates May 2001.
97 Fixes & updates, Sept 2001.
98 
99 ------------------------------------------------------------------------ */
100 
101 /* ---------------------------------------------------------------------
102 The following 4 definitions are compiler-specific.
103 The C standard does not guarantee that wchar_t has at least
104 16 bits, so wchar_t is no less portable than unsigned short!
105 All should be unsigned values to avoid sign extension during
106 bit mask & shift operations.
107 ------------------------------------------------------------------------ */
108 
109 typedef unsigned long	UTF32;	/* at least 32 bits */
110 typedef unsigned short	UTF16;	/* at least 16 bits */
111 typedef unsigned char	UTF8;	/* typically 8 bits */
112 typedef unsigned char	Boolean; /* 0 or 1 */
113 
114 /* Some fundamental constants */
115 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
116 #define UNI_MAX_BMP (UTF32)0x0000FFFF
117 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
118 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
119 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
120 
121 typedef enum {
122 	conversionOK, 		/* conversion successful */
123 	sourceExhausted,	/* partial character in source, but hit end */
124 	targetExhausted,	/* insuff. room in target for conversion */
125 	sourceIllegal		/* source sequence is illegal/malformed */
126 } ConversionResult;
127 
128 typedef enum {
129 	strictConversion = 0,
130 	lenientConversion
131 } ConversionFlags;
132 
133 /* This is for C++ and does no harm in C */
134 #ifdef __cplusplus
135 extern "C" {
136 #endif
137 
138 ConversionResult ConvertUTF8toUTF16 (const UTF8** sourceStart, const UTF8* sourceEnd,
139                                      UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
140 
141 ConversionResult ConvertUTF16toUTF8 (const UTF16** sourceStart, const UTF16* sourceEnd,
142                                      UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
143 
144 ConversionResult ConvertUTF8toUTF32 (const UTF8** sourceStart, const UTF8* sourceEnd,
145                                      UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
146 
147 ConversionResult ConvertUTF32toUTF8 (const UTF32** sourceStart, const UTF32* sourceEnd,
148                                      UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
149 
150 ConversionResult ConvertUTF16toUTF32 (const UTF16** sourceStart, const UTF16* sourceEnd,
151                                       UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
152 
153 ConversionResult ConvertUTF32toUTF16 (const UTF32** sourceStart, const UTF32* sourceEnd,
154                                       UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
155 
156 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
157 
158 #ifdef __cplusplus
159 }
160 #endif
161 
162 /* --------------------------------------------------------------------- */
163 
164 #endif  // COMMON_CONVERT_UTF_H_
165