utf8proc

view utf8proc.h @ 2:aaad485d5335

find changesets by author, revision, files, or words in the commit message
Version 0.3

- changed normalization from NFC to NFKC for postgresql unifold function
- added support to mark the beginning of a grapheme cluster with 0xFF (option: CHARBOUND)
- added the ruby method String#chars, which is returning an array of UTF-8 encoded grapheme clusters
- added NLF2LF transformation in postgresql unifold function
- added the DECOMPOSE option, if you neither use COMPOSE or DECOMPOSE, no normalization will be performed (different from previous versions)
- using integer constants rather than C-strings for character properties
- fixed (hopefully) a problem with the ruby library on Mac OS X, which occured when compiler optimization was switched on
author jbe
date Fri Aug 04 12:00:00 2006 +0200 (2006-08-04)
parents 61a89ecc2fb9
children 4ee0d5f54af1
line source
1 /*
2 * Copyright (c) 2006, FlexiGuided GmbH, Berlin, Germany
3 * Author: Jan Behrens <jan.behrens@flexiguided.de>
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions are
8 * met:
9 *
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the FlexiGuided GmbH nor the names of its
16 * contributors may be used to endorse or promote products derived from
17 * this software without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
22 * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
23 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
24 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
25 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
26 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
27 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
28 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
29 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30 *
31 *
32 * This library contains derived data from a modified version of the
33 * Unicode data files.
34 *
35 * The original data files are available at
36 * http://www.unicode.org/Public/UNIDATA/
37 *
38 * Please notice the copyright statement in the file "utf8proc_data.c".
39 *
40 */
41
42
43 /*
44 * File name: utf8proc.h
45 * Version: 0.3
46 * Last changed: 2006-08-04
47 *
48 * Description:
49 * Header files for libutf8proc, which is a mapping tool for UTF-8 strings
50 * with following features:
51 * - decomposing and composing of strings
52 * - replacing compatibility characters with their equivalents
53 * - stripping of "default ignorable characters"
54 * like SOFT-HYPHEN or ZERO-WIDTH-SPACE
55 * - optional rejection of strings containing non-assigned code points
56 * - stripping of control characters
57 * - transformation of LF, CRLF, CR and NEL to line-feed (LF)
58 * or to the unicode chararacters for paragraph separation (PS)
59 * or line separation (LS).
60 * - unicode case folding (for case insensitive string comparisons)
61 * - rejection of illegal UTF-8 data (i.e. UTF-8 encoded UTF-16 surrogates)
62 * - support for korean hangul characters
63 * Unicode Version 5.0.0 is supported.
64 */
65
66
67 #ifndef UTF8PROC_H
68 #define UTF8PROC_H
69
70
71 #include <stdlib.h>
72 #include <stdbool.h>
73 #include <sys/types.h>
74 #include <inttypes.h>
75 #include <limits.h>
76
77 #ifndef SSIZE_MAX
78 #define SSIZE_MAX (SIZE_MAX/2)
79 #endif
80
81 #define UTF8PROC_NULLTERM (1<<0)
82 #define UTF8PROC_STABLE (1<<1)
83 #define UTF8PROC_COMPAT (1<<2)
84 #define UTF8PROC_COMPOSE (1<<3)
85 #define UTF8PROC_DECOMPOSE (1<<4)
86 #define UTF8PROC_IGNORE (1<<5)
87 #define UTF8PROC_REJECTNA (1<<6)
88 #define UTF8PROC_NLF2LS (1<<7)
89 #define UTF8PROC_NLF2PS (1<<8)
90 #define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS)
91 #define UTF8PROC_STRIPCC (1<<9)
92 #define UTF8PROC_CASEFOLD (1<<10)
93 #define UTF8PROC_CHARBOUND (1<<11)
94 /*
95 * Flags being regarded by several functions in the library:
96 * NULLTERM: The given UTF-8 input is NULL terminated.
97 * STABLE: Unicode Versioning Stability has to be respected.
98 * COMPAT: Compatiblity decomposition
99 * (i.e. formatting information is lost)
100 * COMPOSE: Return a result with composed characters.
101 * DECOMPOSE: Return a result with decomposed characters.
102 * IGNORE: Strip "default ignorable characters"
103 * REJECTNA: Return an error, if the input contains unassigned code points.
104 * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are
105 * representing a line break, and should be converted to the
106 * unicode character for line separation (LS).
107 * NLF2PS: Indicating that NLF-sequences are representing a paragraph
108 * break, and should be converted to the unicode character for
109 * paragraph separation (PS).
110 * NLF2LF: Indicating that the meaning of NLF-sequences is unknown.
111 * STRIPCC: Strips and/or convers control characters.
112 * NLF-sequences are transformed into space, except if one of the
113 * NLF2LS/PS/LF options is given.
114 * HorizontalTab (HT) and FormFeed (FF) are treated as a
115 * NLF-sequence in this case.
116 * All other control characters are simply removed.
117 * CASEFOLD: Performs unicode case folding, to be able to do a
118 * case-insensitive string comparison.
119 * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which is
120 * representing a single grapheme cluster (a single character).
121 */
122
123 #define UTF8PROC_ERROR_NOMEM -1
124 #define UTF8PROC_ERROR_OVERFLOW -2
125 #define UTF8PROC_ERROR_INVALIDUTF8 -3
126 #define UTF8PROC_ERROR_NOTASSIGNED -4
127 /*
128 * Error codes being returned by almost all functions:
129 * ERROR_NOMEM: Memory could not be allocated.
130 * ERROR_OVERFLOW: The given string is too long to be processed.
131 * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string.
132 * ERROR_NOTASSIGNED: The REJECTNA flag was set,
133 * and an unassigned code point was found.
134 */
135
136 typedef struct utf8proc_property_struct {
137 int16_t category;
138 int16_t combining_class;
139 int16_t bidi_class;
140 int16_t decomp_type;
141 const int32_t *decomp_mapping;
142 const unsigned bidi_mirrored:1;
143 const int32_t uppercase_mapping;
144 const int32_t lowercase_mapping;
145 const int32_t titlecase_mapping;
146 const int32_t comb1st_index;
147 const int32_t comb2nd_index;
148 const unsigned comp_exclusion:1;
149 const unsigned ignorable:1;
150 const unsigned control_boundary:1;
151 const unsigned extend:1;
152 const int32_t *casefold_mapping;
153 } utf8proc_property_t;
154
155 #define UTF8PROC_CATEGORY_LU 1
156 #define UTF8PROC_CATEGORY_LL 2
157 #define UTF8PROC_CATEGORY_LT 3
158 #define UTF8PROC_CATEGORY_LM 4
159 #define UTF8PROC_CATEGORY_LO 5
160 #define UTF8PROC_CATEGORY_MN 6
161 #define UTF8PROC_CATEGORY_MC 7
162 #define UTF8PROC_CATEGORY_ME 8
163 #define UTF8PROC_CATEGORY_ND 9
164 #define UTF8PROC_CATEGORY_NL 10
165 #define UTF8PROC_CATEGORY_NO 11
166 #define UTF8PROC_CATEGORY_PC 12
167 #define UTF8PROC_CATEGORY_PD 13
168 #define UTF8PROC_CATEGORY_PS 14
169 #define UTF8PROC_CATEGORY_PE 15
170 #define UTF8PROC_CATEGORY_PI 16
171 #define UTF8PROC_CATEGORY_PF 17
172 #define UTF8PROC_CATEGORY_PO 18
173 #define UTF8PROC_CATEGORY_SM 19
174 #define UTF8PROC_CATEGORY_SC 20
175 #define UTF8PROC_CATEGORY_SK 21
176 #define UTF8PROC_CATEGORY_SO 22
177 #define UTF8PROC_CATEGORY_ZS 23
178 #define UTF8PROC_CATEGORY_ZL 24
179 #define UTF8PROC_CATEGORY_ZP 25
180 #define UTF8PROC_CATEGORY_CC 26
181 #define UTF8PROC_CATEGORY_CF 27
182 #define UTF8PROC_CATEGORY_CS 28
183 #define UTF8PROC_CATEGORY_CO 29
184 #define UTF8PROC_CATEGORY_CN 30
185 #define UTF8PROC_BIDI_CLASS_L 1
186 #define UTF8PROC_BIDI_CLASS_LRE 2
187 #define UTF8PROC_BIDI_CLASS_LRO 3
188 #define UTF8PROC_BIDI_CLASS_R 4
189 #define UTF8PROC_BIDI_CLASS_AL 5
190 #define UTF8PROC_BIDI_CLASS_RLE 6
191 #define UTF8PROC_BIDI_CLASS_RLO 7
192 #define UTF8PROC_BIDI_CLASS_PDF 8
193 #define UTF8PROC_BIDI_CLASS_EN 9
194 #define UTF8PROC_BIDI_CLASS_ES 10
195 #define UTF8PROC_BIDI_CLASS_ET 11
196 #define UTF8PROC_BIDI_CLASS_AN 12
197 #define UTF8PROC_BIDI_CLASS_CS 13
198 #define UTF8PROC_BIDI_CLASS_NSM 14
199 #define UTF8PROC_BIDI_CLASS_BN 15
200 #define UTF8PROC_BIDI_CLASS_B 16
201 #define UTF8PROC_BIDI_CLASS_S 17
202 #define UTF8PROC_BIDI_CLASS_WS 18
203 #define UTF8PROC_BIDI_CLASS_ON 19
204 #define UTF8PROC_DECOMP_TYPE_FONT 1
205 #define UTF8PROC_DECOMP_TYPE_NOBREAK 2
206 #define UTF8PROC_DECOMP_TYPE_INITIAL 3
207 #define UTF8PROC_DECOMP_TYPE_MEDIAL 4
208 #define UTF8PROC_DECOMP_TYPE_FINAL 5
209 #define UTF8PROC_DECOMP_TYPE_ISOLATED 6
210 #define UTF8PROC_DECOMP_TYPE_CIRCLE 7
211 #define UTF8PROC_DECOMP_TYPE_SUPER 8
212 #define UTF8PROC_DECOMP_TYPE_SUB 9
213 #define UTF8PROC_DECOMP_TYPE_VERTICAL 10
214 #define UTF8PROC_DECOMP_TYPE_WIDE 11
215 #define UTF8PROC_DECOMP_TYPE_NARROW 12
216 #define UTF8PROC_DECOMP_TYPE_SMALL 13
217 #define UTF8PROC_DECOMP_TYPE_SQUARE 14
218 #define UTF8PROC_DECOMP_TYPE_FRACTION 15
219 #define UTF8PROC_DECOMP_TYPE_COMPAT 16
220
221 extern const int8_t utf8proc_utf8class[256];
222
223 const char *utf8proc_errmsg(ssize_t errcode);
224 /*
225 * Returns a static error string for the given error code.
226 */
227
228 ssize_t utf8proc_iterate(uint8_t *str, ssize_t strlen, int32_t *dst);
229 /*
230 * Reads a single char from the UTF-8 sequence being pointed to by 'str'.
231 * The maximum number of bytes read is 'strlen', unless 'strlen' is
232 * negative.
233 * If a valid unicode char could be read, it is stored in the variable
234 * being pointed to by 'dst', otherwise that variable will be set to -1.
235 * In case of success the number of bytes read is returned, otherwise a
236 * negative error code is returned.
237 */
238
239 ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst);
240 /*
241 * Encodes the unicode char with the code point 'uc' as an UTF-8 string in
242 * the byte array being pointed to by 'dst'. This array has to be at least
243 * 4 bytes long.
244 * In case of success the number of bytes written is returned, otherwise 0.
245 * This function does not check if 'uc' is a valid unicode code point.
246 */
247
248 const utf8proc_property_t *utf8proc_get_property(int32_t uc);
249 /*
250 * Returns a pointer to a (constant) struct containing information about
251 * the unicode char with the given code point 'uc'.
252 * If the character is not existent a pointer to a special struct is
253 * returned, where 'category' is a NULL pointer.
254 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
255 * 0x10FFFF, otherwise the program might crash!
256 */
257
258 ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,
259 int options, int *last_boundclass);
260 /*
261 * Writes a decomposition of the unicode char 'uc' into the array being
262 * pointed to by 'dst'.
263 * Following flags in the 'options' field are regarded:
264 * REJECTNA: an unassigned unicode code point leads to an error
265 * IGNORE: "default ignorable" chars are stripped
266 * CASEFOLD: unicode casefolding is applied
267 * COMPAT: replace certain characters with their
268 * compatibility decomposition
269 * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster
270 * The pointer 'last_boundclass' has to point to an integer variable which is
271 * storing the last character boundary class, if the CHARBOUND option is
272 * used.
273 * In case of success the number of chars written is returned,
274 * in case of an error, a negative error code is returned.
275 * If the number of written chars would be bigger than 'bufsize',
276 * the buffer (up to 'bufsize') has inpredictable data, and the needed
277 * buffer size is returned.
278 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
279 * 0x10FFFF, otherwise the program might crash!
280 */
281
282 ssize_t utf8proc_decompose(uint8_t *str, ssize_t strlen,
283 int32_t *buffer, ssize_t bufsize, int options);
284 /*
285 * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8
286 * string, and orders the decomposed sequences correctly.
287 * If the NULLTERM flag in 'options' is set, processing will be stopped,
288 * when a NULL byte is encounted, otherwise 'strlen' bytes are processed.
289 * The result in form of unicode code points is written into the buffer
290 * being pointed to by 'buffer', having the length of 'bufsize' entries.
291 * In case of success the number of chars written is returned,
292 * in case of an error, a negative error code is returned.
293 * If the number of written chars would be bigger than 'bufsize',
294 * the buffer (up to 'bufsize') has inpredictable data, and the needed
295 * buffer size is returned.
296 */
297
298 ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);
299 /*
300 * Reencodes the sequence of unicode characters given by the pointer
301 * 'buffer' and 'length' as UTF-8.
302 * The result is stored in the same memory area where the data is read.
303 * Following flags in the 'options' field are regarded:
304 * NLF2LS: converts LF, CRLF, CR and NEL into LS
305 * NLF2PS: converts LF, CRLF, CR and NEL into PS
306 * NLF2LF: converts LF, CRLF, CR and NEL into LF
307 * STRIPCC: strips or converts all non-affected control characters
308 * COMPOSE: tries to combine decomposed characters into composite characters
309 * STABLE: prohibits combining characters which would violate
310 * the unicode versioning stability
311 * In case of success the length of the resulting UTF-8 string is returned,
312 * otherwise a negative error code is returned.
313 * WARNING: The amount of free space being pointed to by 'buffer', has to
314 * exceed the amount of the input data by one byte, and the
315 * entries of the array pointed to by 'str' have to be in the
316 * range of 0x0000 to 0x10FFFF, otherwise the program might crash!
317 */
318
319 ssize_t utf8proc_map(uint8_t *str, ssize_t strlen, uint8_t **dstptr,
320 int options);
321 /*
322 * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8
323 * string, which is allocated dynamically, and afterwards pointed to by the
324 * pointer being pointed to by 'dstptr'.
325 * If the NULLTERM flag in the 'options' field is set, the length is
326 * determined by a NULL terminator, otherwise the parameter 'strlen' is
327 * evaluated to determine the string length, but in any case the result
328 * will be NULL terminated (though it might contain NULL characters before).
329 * Other flags in the 'options' field are passed to the functions defined
330 * above, and regarded as described.
331 * In case of success the length of the new string is returned,
332 * otherwise a negative error code is returned.
333 * NOTICE: The memory of the new UTF-8 string will have been allocated with
334 * 'malloc', and has theirfore to be freed with 'free'.
335 */
336
337 uint8_t *utf8proc_NFD(uint8_t *str);
338 uint8_t *utf8proc_NFC(uint8_t *str);
339 uint8_t *utf8proc_NFKD(uint8_t *str);
340 uint8_t *utf8proc_NFKC(uint8_t *str);
341 /*
342 * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
343 * normalized version of the null-terminated string 'str'.
344 */
345
346
347 #endif
348
349

Impressum / About Us