utf8proc

view utf8proc.h @ 7:fcfd8c836c64

find changesets by author, revision, files, or words in the commit message
Version 1.1.1

- Added a new PostgreSQL function 'unistrip', which behaves like 'unifold', but also removes all character marks (e.g. accents).
- Changed license from BSD to MIT style.
- Added a new function 'utf8proc_codepoint_valid' to the C library.
- Changed compiler flags in Makefile from -g -O0 to -O2
- The ruby script, which was used to build the utf8proc_data.c file, is now included in the distribution.
author jbe
date Sun Jul 22 12:00:00 2007 +0200 (2007-07-22)
parents 4ee0d5f54af1
children 951e73a98021
line source
1 /*
2 * Copyright (c) 2006-2007 Jan Behrens, FlexiGuided GmbH, Berlin
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
17 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
19 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
20 * DEALINGS IN THE SOFTWARE.
21 */
22
23
24 /*
25 * File name: utf8proc.h
26 * Version: 1.1.1
27 * Last changed: 2007-07-22
28 *
29 * Description:
30 * Header files for libutf8proc, which is a mapping tool for UTF-8 strings
31 * with following features:
32 * - decomposing and composing of strings
33 * - replacing compatibility characters with their equivalents
34 * - stripping of "default ignorable characters"
35 * like SOFT-HYPHEN or ZERO-WIDTH-SPACE
36 * - folding of certain characters for string comparison
37 * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-")
38 * (see "LUMP" option)
39 * - optional rejection of strings containing non-assigned code points
40 * - stripping of control characters
41 * - stripping of character marks (accents, etc.)
42 * - transformation of LF, CRLF, CR and NEL to line-feed (LF)
43 * or to the unicode chararacters for paragraph separation (PS)
44 * or line separation (LS).
45 * - unicode case folding (for case insensitive string comparisons)
46 * - rejection of illegal UTF-8 data
47 * (i.e. UTF-8 encoded UTF-16 surrogates)
48 * - support for korean hangul characters
49 * Unicode Version 5.0.0 is supported.
50 */
51
52
53 #ifndef UTF8PROC_H
54 #define UTF8PROC_H
55
56
57 #include <stdlib.h>
58 #include <stdbool.h>
59 #include <sys/types.h>
60 #include <inttypes.h>
61 #include <limits.h>
62
63 #ifndef SSIZE_MAX
64 #define SSIZE_MAX (SIZE_MAX/2)
65 #endif
66
67 #define UTF8PROC_NULLTERM (1<<0)
68 #define UTF8PROC_STABLE (1<<1)
69 #define UTF8PROC_COMPAT (1<<2)
70 #define UTF8PROC_COMPOSE (1<<3)
71 #define UTF8PROC_DECOMPOSE (1<<4)
72 #define UTF8PROC_IGNORE (1<<5)
73 #define UTF8PROC_REJECTNA (1<<6)
74 #define UTF8PROC_NLF2LS (1<<7)
75 #define UTF8PROC_NLF2PS (1<<8)
76 #define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS)
77 #define UTF8PROC_STRIPCC (1<<9)
78 #define UTF8PROC_CASEFOLD (1<<10)
79 #define UTF8PROC_CHARBOUND (1<<11)
80 #define UTF8PROC_LUMP (1<<12)
81 #define UTF8PROC_STRIPMARK (1<<13)
82 /*
83 * Flags being regarded by several functions in the library:
84 * NULLTERM: The given UTF-8 input is NULL terminated.
85 * STABLE: Unicode Versioning Stability has to be respected.
86 * COMPAT: Compatiblity decomposition
87 * (i.e. formatting information is lost)
88 * COMPOSE: Return a result with composed characters.
89 * DECOMPOSE: Return a result with decomposed characters.
90 * IGNORE: Strip "default ignorable characters"
91 * REJECTNA: Return an error, if the input contains unassigned
92 * code points.
93 * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are
94 * representing a line break, and should be converted to the
95 * unicode character for line separation (LS).
96 * NLF2PS: Indicating that NLF-sequences are representing a paragraph
97 * break, and should be converted to the unicode character for
98 * paragraph separation (PS).
99 * NLF2LF: Indicating that the meaning of NLF-sequences is unknown.
100 * STRIPCC: Strips and/or convers control characters.
101 * NLF-sequences are transformed into space, except if one of
102 * the NLF2LS/PS/LF options is given.
103 * HorizontalTab (HT) and FormFeed (FF) are treated as a
104 * NLF-sequence in this case.
105 * All other control characters are simply removed.
106 * CASEFOLD: Performs unicode case folding, to be able to do a
107 * case-insensitive string comparison.
108 * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which
109 * is representing a single grapheme cluster (see UAX#29).
110 * LUMP: Lumps certain characters together
111 * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-").
112 * (See lump.txt for details.)
113 * If NLF2LF is set, this includes a transformation of
114 * paragraph and line separators to ASCII line-feed (LF).
115 * STRIPMARK: Strips all character markings
116 * (non-spacing, spacing and enclosing) (i.e. accents)
117 * NOTE: this option works only with COMPOSE or DECOMPOSE
118 */
119
120 #define UTF8PROC_ERROR_NOMEM -1
121 #define UTF8PROC_ERROR_OVERFLOW -2
122 #define UTF8PROC_ERROR_INVALIDUTF8 -3
123 #define UTF8PROC_ERROR_NOTASSIGNED -4
124 #define UTF8PROC_ERROR_INVALIDOPTS -5
125 /*
126 * Error codes being returned by almost all functions:
127 * ERROR_NOMEM: Memory could not be allocated.
128 * ERROR_OVERFLOW: The given string is too long to be processed.
129 * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string.
130 * ERROR_NOTASSIGNED: The REJECTNA flag was set,
131 * and an unassigned code point was found.
132 * ERROR_INVALIDOPTS: Invalid options have been used.
133 */
134
135 typedef int16_t utf8proc_propval_t;
136 typedef struct utf8proc_property_struct {
137 utf8proc_propval_t category;
138 utf8proc_propval_t combining_class;
139 utf8proc_propval_t bidi_class;
140 utf8proc_propval_t decomp_type;
141 const int32_t *decomp_mapping;
142 unsigned bidi_mirrored:1;
143 int32_t uppercase_mapping;
144 int32_t lowercase_mapping;
145 int32_t titlecase_mapping;
146 int32_t comb1st_index;
147 int32_t comb2nd_index;
148 unsigned comp_exclusion:1;
149 unsigned ignorable:1;
150 unsigned control_boundary:1;
151 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(const 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 bool utf8proc_codepoint_valid(int32_t uc);
240 /*
241 * Returns 1, if the given unicode code-point is valid, otherwise 0.
242 */
243
244 ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst);
245 /*
246 * Encodes the unicode char with the code point 'uc' as an UTF-8 string in
247 * the byte array being pointed to by 'dst'. This array has to be at least
248 * 4 bytes long.
249 * In case of success the number of bytes written is returned,
250 * otherwise 0.
251 * This function does not check if 'uc' is a valid unicode code point.
252 */
253
254 const utf8proc_property_t *utf8proc_get_property(int32_t uc);
255 /*
256 * Returns a pointer to a (constant) struct containing information about
257 * the unicode char with the given code point 'uc'.
258 * If the character is not existent a pointer to a special struct is
259 * returned, where 'category' is a NULL pointer.
260 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
261 * 0x10FFFF, otherwise the program might crash!
262 */
263
264 ssize_t utf8proc_decompose_char(
265 int32_t uc, int32_t *dst, ssize_t bufsize,
266 int options, int *last_boundclass
267 );
268 /*
269 * Writes a decomposition of the unicode char 'uc' into the array being
270 * pointed to by 'dst'.
271 * Following flags in the 'options' field are regarded:
272 * REJECTNA: an unassigned unicode code point leads to an error
273 * IGNORE: "default ignorable" chars are stripped
274 * CASEFOLD: unicode casefolding is applied
275 * COMPAT: replace certain characters with their
276 * compatibility decomposition
277 * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster
278 * LUMP: lumps certain different characters together
279 * STRIPMARK: removes all character marks
280 * The pointer 'last_boundclass' has to point to an integer variable which
281 * is storing the last character boundary class, if the CHARBOUND option
282 * is used.
283 * In case of success the number of chars written is returned,
284 * in case of an error, a negative error code is returned.
285 * If the number of written chars would be bigger than 'bufsize',
286 * the buffer (up to 'bufsize') has inpredictable data, and the needed
287 * buffer size is returned.
288 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
289 * 0x10FFFF, otherwise the program might crash!
290 */
291
292 ssize_t utf8proc_decompose(
293 const uint8_t *str, ssize_t strlen,
294 int32_t *buffer, ssize_t bufsize, int options
295 );
296 /*
297 * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8
298 * string, and orders the decomposed sequences correctly.
299 * If the NULLTERM flag in 'options' is set, processing will be stopped,
300 * when a NULL byte is encounted, otherwise 'strlen' bytes are processed.
301 * The result in form of unicode code points is written into the buffer
302 * being pointed to by 'buffer', having the length of 'bufsize' entries.
303 * In case of success the number of chars written is returned,
304 * in case of an error, a negative error code is returned.
305 * If the number of written chars would be bigger than 'bufsize',
306 * the buffer (up to 'bufsize') has inpredictable data, and the needed
307 * buffer size is returned.
308 */
309
310 ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);
311 /*
312 * Reencodes the sequence of unicode characters given by the pointer
313 * 'buffer' and 'length' as UTF-8.
314 * The result is stored in the same memory area where the data is read.
315 * Following flags in the 'options' field are regarded:
316 * NLF2LS: converts LF, CRLF, CR and NEL into LS
317 * NLF2PS: converts LF, CRLF, CR and NEL into PS
318 * NLF2LF: converts LF, CRLF, CR and NEL into LF
319 * STRIPCC: strips or converts all non-affected control characters
320 * COMPOSE: tries to combine decomposed characters into composite
321 * characters
322 * STABLE: prohibits combining characters which would violate
323 * the unicode versioning stability
324 * In case of success the length of the resulting UTF-8 string is
325 * returned, otherwise a negative error code is returned.
326 * WARNING: The amount of free space being pointed to by 'buffer', has to
327 * exceed the amount of the input data by one byte, and the
328 * entries of the array pointed to by 'str' have to be in the
329 * range of 0x0000 to 0x10FFFF, otherwise the program might
330 * crash!
331 */
332
333 ssize_t utf8proc_map(
334 const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options
335 );
336 /*
337 * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8
338 * string, which is allocated dynamically, and afterwards pointed to by
339 * the pointer being pointed to by 'dstptr'.
340 * If the NULLTERM flag in the 'options' field is set, the length is
341 * determined by a NULL terminator, otherwise the parameter 'strlen' is
342 * evaluated to determine the string length, but in any case the result
343 * will be NULL terminated (though it might contain NULL characters
344 * before). Other flags in the 'options' field are passed to the functions
345 * defined above, and regarded as described.
346 * In case of success the length of the new string is returned,
347 * otherwise a negative error code is returned.
348 * NOTICE: The memory of the new UTF-8 string will have been allocated with
349 * 'malloc', and has theirfore to be freed with 'free'.
350 */
351
352 uint8_t *utf8proc_NFD(const uint8_t *str);
353 uint8_t *utf8proc_NFC(const uint8_t *str);
354 uint8_t *utf8proc_NFKD(const uint8_t *str);
355 uint8_t *utf8proc_NFKC(const uint8_t *str);
356 /*
357 * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
358 * normalized version of the null-terminated string 'str'.
359 */
360
361
362 #endif
363

Impressum / About Us