utf8proc

view utf8proc.c @ 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.c
45 * Version: 0.3
46 * Last changed: 2006-08-04
47 *
48 * Description:
49 * Implementation of libutf8proc.
50 */
51
52
53 #include "utf8proc.h"
54 #include "utf8proc_data.c"
55
56
57 const int8_t utf8proc_utf8class[256] = {
58 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
59 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
60 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
61 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
62 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
63 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
64 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
65 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
66 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
67 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
68 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
69 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
70 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
71 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
72 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
73 4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 };
74
75 #define UTF8PROC_HANGUL_SBASE 0xAC00
76 #define UTF8PROC_HANGUL_LBASE 0x1100
77 #define UTF8PROC_HANGUL_VBASE 0x1161
78 #define UTF8PROC_HANGUL_TBASE 0x11A7
79 #define UTF8PROC_HANGUL_LCOUNT 19
80 #define UTF8PROC_HANGUL_VCOUNT 21
81 #define UTF8PROC_HANGUL_TCOUNT 28
82 #define UTF8PROC_HANGUL_NCOUNT 588
83 #define UTF8PROC_HANGUL_SCOUNT 11172
84 // END is exclusive
85 #define UTF8PROC_HANGUL_L_START 0x1100
86 #define UTF8PROC_HANGUL_L_END 0x115A
87 #define UTF8PROC_HANGUL_L_FILLER 0x115F
88 #define UTF8PROC_HANGUL_V_START 0x1160
89 #define UTF8PROC_HANGUL_V_END 0x11A3
90 #define UTF8PROC_HANGUL_T_START 0x11A8
91 #define UTF8PROC_HANGUL_T_END 0x11FA
92 #define UTF8PROC_HANGUL_S_START 0xAC00
93 #define UTF8PROC_HANGUL_S_END 0xD7A4
94
95
96 #define UTF8PROC_BOUNDCLASS_START 0
97 #define UTF8PROC_BOUNDCLASS_OTHER 1
98 #define UTF8PROC_BOUNDCLASS_CR 2
99 #define UTF8PROC_BOUNDCLASS_LF 3
100 #define UTF8PROC_BOUNDCLASS_CONTROL 4
101 #define UTF8PROC_BOUNDCLASS_EXTEND 5
102 #define UTF8PROC_BOUNDCLASS_L 6
103 #define UTF8PROC_BOUNDCLASS_V 7
104 #define UTF8PROC_BOUNDCLASS_T 8
105 #define UTF8PROC_BOUNDCLASS_LV 9
106 #define UTF8PROC_BOUNDCLASS_LVT 10
107
108
109 const char *utf8proc_errmsg(ssize_t errcode) {
110 switch (errcode) {
111 case UTF8PROC_ERROR_NOMEM:
112 return "Memory for processing UTF-8 data could not be allocated.";
113 case UTF8PROC_ERROR_OVERFLOW:
114 return "UTF-8 string is too long to be processed.";
115 case UTF8PROC_ERROR_INVALIDUTF8:
116 return "Invalid UTF-8 string";
117 case UTF8PROC_ERROR_NOTASSIGNED:
118 return "Unassigned Unicode code point found in UTF-8 string.";
119 default:
120 return "An unknown error occured while processing UTF-8 data.";
121 }
122 }
123
124 ssize_t utf8proc_iterate(uint8_t *str, ssize_t strlen, int32_t *dst) {
125 int length;
126 int i;
127 int32_t uc = -1;
128 *dst = -1;
129 if (!strlen) return 0;
130 length = utf8proc_utf8class[str[0]];
131 if (!length) return UTF8PROC_ERROR_INVALIDUTF8;
132 if (strlen >= 0 && length > strlen) return UTF8PROC_ERROR_INVALIDUTF8;
133 for (i=1; i<length; i++) {
134 if ((str[i] & 0xC0) != 0x80) return UTF8PROC_ERROR_INVALIDUTF8;
135 }
136 switch (length) {
137 case 1:
138 uc = str[0];
139 break;
140 case 2:
141 uc = ((str[0] & 0x1F) << 6) + (str[1] & 0x3F);
142 if (uc < 0x80) uc = -1;
143 break;
144 case 3:
145 uc = ((str[0] & 0x0F) << 12) + ((str[1] & 0x3F) << 6)
146 + (str[2] & 0x3F);
147 if (uc < 0x800 || (uc >= 0xD800 && uc < 0xE000) ||
148 (uc >= 0xFDD0 && uc < 0xFDF0)) uc = -1;
149 break;
150 case 4:
151 uc = ((str[0] & 0x07) << 18) + ((str[1] & 0x3F) << 12)
152 + ((str[2] & 0x3F) << 6) + (str[3] & 0x3F);
153 if (uc < 0x10000 || uc >= 0x110000) uc = -1;
154 break;
155 }
156 if (uc < 0 || ((uc & 0xFFFF) >= 0xFFFE)) return UTF8PROC_ERROR_INVALIDUTF8;
157 *dst = uc;
158 return length;
159 }
160
161 ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) {
162 if (uc < 0x00) {
163 return 0;
164 } else if (uc < 0x80) {
165 dst[0] = uc;
166 return 1;
167 } else if (uc < 0x800) {
168 dst[0] = 0xC0 + (uc >> 6);
169 dst[1] = 0x80 + (uc & 0x3F);
170 return 2;
171 } else if (uc == 0xFFFF) {
172 dst[0] = 0xFF;
173 return 1;
174 } else if (uc == 0xFFFE) {
175 dst[0] = 0xFE;
176 return 1;
177 } else if (uc < 0x10000) {
178 dst[0] = 0xE0 + (uc >> 12);
179 dst[1] = 0x80 + ((uc >> 6) & 0x3F);
180 dst[2] = 0x80 + (uc & 0x3F);
181 return 3;
182 } else if (uc < 0x110000) {
183 dst[0] = 0xF0 + (uc >> 18);
184 dst[1] = 0x80 + ((uc >> 12) & 0x3F);
185 dst[2] = 0x80 + ((uc >> 6) & 0x3F);
186 dst[3] = 0x80 + (uc & 0x3F);
187 return 4;
188 } else return 0;
189 }
190
191 const utf8proc_property_t *utf8proc_get_property(int32_t uc) {
192 // ASSERT: uc >= 0 && uc < 0x110000
193 return utf8proc_properties + (
194 utf8proc_stage2table[
195 utf8proc_stage1table[uc >> 8] + (uc & 0xFF)
196 ]
197 );
198 }
199
200 ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,
201 int options, int *last_boundclass) {
202 // ASSERT: uc >= 0 && uc < 0x110000
203 const utf8proc_property_t *property;
204 int32_t hangul_sindex;
205 property = utf8proc_get_property(uc);
206 hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
207 if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) &&
208 hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
209 int32_t hangul_tindex;
210 if (bufsize >= 1) {
211 dst[0] = UTF8PROC_HANGUL_LBASE +
212 hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
213 if (bufsize >= 2) dst[1] = UTF8PROC_HANGUL_VBASE +
214 (hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
215 }
216 hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
217 if (!hangul_tindex) return 2;
218 if (bufsize >= 3) dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
219 return 3;
220 } else if ((options & UTF8PROC_REJECTNA) && !property->category) {
221 return UTF8PROC_ERROR_NOTASSIGNED;
222 } else if ((options & UTF8PROC_IGNORE) && property->ignorable) {
223 return 0;
224 } else if ((options & UTF8PROC_CASEFOLD) && property->casefold_mapping) {
225 const int32_t *casefold_entry;
226 ssize_t written = 0;
227 for (casefold_entry = property->casefold_mapping;
228 *casefold_entry >= 0; casefold_entry++) {
229 written += utf8proc_decompose_char(*casefold_entry, dst+written,
230 (bufsize > written) ? (bufsize - written) : 0, options,
231 last_boundclass);
232 if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
233 }
234 return written;
235 } else if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) &&
236 property->decomp_mapping &&
237 (!property->decomp_type || (options & UTF8PROC_COMPAT))) {
238 const int32_t *decomp_entry;
239 ssize_t written = 0;
240 for (decomp_entry = property->decomp_mapping;
241 *decomp_entry >= 0; decomp_entry++) {
242 written += utf8proc_decompose_char(*decomp_entry, dst+written,
243 (bufsize > written) ? (bufsize - written) : 0, options,
244 last_boundclass);
245 if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
246 }
247 return written;
248 } else if (options & UTF8PROC_CHARBOUND) {
249 bool boundary;
250 int tbc, lbc;
251 int category;
252 category = property->category;
253 tbc =
254 (uc == 0x000D) ? UTF8PROC_BOUNDCLASS_CR :
255 (uc == 0x000A) ? UTF8PROC_BOUNDCLASS_LF :
256 ((category == UTF8PROC_CATEGORY_ZL ||
257 category == UTF8PROC_CATEGORY_ZP ||
258 category == UTF8PROC_CATEGORY_CC ||
259 category == UTF8PROC_CATEGORY_CF) &&
260 !(uc == 0x200C || uc == 0x200D)) ? UTF8PROC_BOUNDCLASS_CONTROL :
261 property->extend ? UTF8PROC_BOUNDCLASS_EXTEND :
262 ((uc >= UTF8PROC_HANGUL_L_START && uc < UTF8PROC_HANGUL_L_END) ||
263 uc == UTF8PROC_HANGUL_L_FILLER) ? UTF8PROC_BOUNDCLASS_L :
264 (uc >= UTF8PROC_HANGUL_V_START && uc < UTF8PROC_HANGUL_V_END) ?
265 UTF8PROC_BOUNDCLASS_V :
266 (uc >= UTF8PROC_HANGUL_T_START && uc < UTF8PROC_HANGUL_T_END) ?
267 UTF8PROC_BOUNDCLASS_T :
268 (uc >= UTF8PROC_HANGUL_S_START && uc < UTF8PROC_HANGUL_S_END) ? (
269 ((uc-UTF8PROC_HANGUL_SBASE) % UTF8PROC_HANGUL_TCOUNT == 0) ?
270 UTF8PROC_BOUNDCLASS_LV : UTF8PROC_BOUNDCLASS_LVT
271 ) :
272 UTF8PROC_BOUNDCLASS_OTHER;
273 lbc = *last_boundclass;
274 boundary =
275 (tbc == UTF8PROC_BOUNDCLASS_EXTEND) ? false :
276 (lbc == UTF8PROC_BOUNDCLASS_START) ? true :
277 (lbc == UTF8PROC_BOUNDCLASS_CR &&
278 tbc == UTF8PROC_BOUNDCLASS_LF) ? false :
279 (lbc == UTF8PROC_BOUNDCLASS_CONTROL) ? true :
280 (tbc == UTF8PROC_BOUNDCLASS_CONTROL) ? true :
281 (lbc == UTF8PROC_BOUNDCLASS_L &&
282 (tbc == UTF8PROC_BOUNDCLASS_L ||
283 tbc == UTF8PROC_BOUNDCLASS_V ||
284 tbc == UTF8PROC_BOUNDCLASS_LV ||
285 tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false :
286 ((lbc == UTF8PROC_BOUNDCLASS_LV ||
287 lbc == UTF8PROC_BOUNDCLASS_V) &&
288 (tbc == UTF8PROC_BOUNDCLASS_V ||
289 tbc == UTF8PROC_BOUNDCLASS_T)) ? false :
290 ((lbc == UTF8PROC_BOUNDCLASS_LVT ||
291 lbc == UTF8PROC_BOUNDCLASS_T) &&
292 tbc == UTF8PROC_BOUNDCLASS_T) ? false :
293 true;
294 *last_boundclass = tbc;
295 if (boundary) {
296 if (bufsize >= 1) dst[0] = 0xFFFF;
297 if (bufsize >= 2) dst[1] = uc;
298 return 2;
299 }
300 }
301 if (bufsize >= 1) *dst = uc;
302 return 1;
303 }
304
305 ssize_t utf8proc_decompose(uint8_t *str, ssize_t strlen,
306 int32_t *buffer, ssize_t bufsize, int options) {
307 // strlen will be ignored, if UTF8PROC_NULLTERM is set in options
308 ssize_t wpos = 0;
309 {
310 int32_t uc;
311 ssize_t rpos = 0;
312 ssize_t decomp_result;
313 int boundclass = UTF8PROC_BOUNDCLASS_START;
314 while (1) {
315 if (options & UTF8PROC_NULLTERM) {
316 rpos += utf8proc_iterate(str + rpos, -1, &uc);
317 // checking of return value is not neccessary,
318 // as 'uc' is < 0 in case of error
319 if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
320 if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
321 if (uc == 0) break;
322 } else {
323 if (rpos >= strlen) break;
324 rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
325 if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
326 }
327 decomp_result = utf8proc_decompose_char(
328 uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options,
329 &boundclass
330 );
331 if (decomp_result < 0) return decomp_result;
332 wpos += decomp_result;
333 // prohibiting integer overflows due to too long strings:
334 if (wpos < 0 || wpos > SSIZE_MAX/sizeof(int32_t)/2)
335 return UTF8PROC_ERROR_OVERFLOW;
336 }
337 }
338 if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) && bufsize >= wpos) {
339 ssize_t pos = 0;
340 while (pos < wpos-1) {
341 int32_t uc1, uc2;
342 const utf8proc_property_t *property1, *property2;
343 uc1 = buffer[pos];
344 uc2 = buffer[pos+1];
345 property1 = utf8proc_get_property(uc1);
346 property2 = utf8proc_get_property(uc2);
347 if (property1->combining_class > property2->combining_class &&
348 property2->combining_class > 0) {
349 buffer[pos] = uc2;
350 buffer[pos+1] = uc1;
351 if (pos > 0) pos--; else pos++;
352 } else {
353 pos++;
354 }
355 }
356 }
357 return wpos;
358 }
359
360 ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
361 // UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
362 // ASSERT: 'buffer' has one spare byte of free space at the end!
363 if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
364 ssize_t rpos;
365 ssize_t wpos = 0;
366 int32_t uc;
367 for (rpos = 0; rpos < length; rpos++) {
368 uc = buffer[rpos];
369 if (uc == 0x000D && rpos < length-1 && buffer[rpos+1] == 0x000A) rpos++;
370 if (uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
371 ((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C))) {
372 if (options & UTF8PROC_NLF2LS) {
373 if (options & UTF8PROC_NLF2PS) {
374 buffer[wpos++] = 0x000A;
375 } else {
376 buffer[wpos++] = 0x2028;
377 }
378 } else {
379 if (options & UTF8PROC_NLF2PS) {
380 buffer[wpos++] = 0x2029;
381 } else {
382 buffer[wpos++] = 0x0020;
383 }
384 }
385 } else if ((options & UTF8PROC_STRIPCC) &&
386 (uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0))) {
387 if (uc == 0x0009) buffer[wpos++] = 0x0020;
388 } else {
389 buffer[wpos++] = uc;
390 }
391 }
392 length = wpos;
393 }
394 if (options & UTF8PROC_COMPOSE) {
395 int32_t *starter = NULL;
396 int32_t current_char;
397 const utf8proc_property_t *starter_property = NULL, *current_property;
398 int16_t max_combining_class = -1;
399 ssize_t rpos;
400 ssize_t wpos = 0;
401 int32_t composition;
402 for (rpos = 0; rpos < length; rpos++) {
403 current_char = buffer[rpos];
404 current_property = utf8proc_get_property(current_char);
405 if (starter && current_property->combining_class > max_combining_class) {
406 // combination perhaps possible
407 int32_t hangul_lindex;
408 int32_t hangul_sindex;
409 hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
410 if (hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT) {
411 int32_t hangul_vindex;
412 hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
413 if (hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT) {
414 *starter = UTF8PROC_HANGUL_SBASE +
415 (hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
416 UTF8PROC_HANGUL_TCOUNT;
417 starter_property = NULL;
418 continue;
419 }
420 }
421 hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
422 if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
423 (hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0) {
424 int32_t hangul_tindex;
425 hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
426 if (hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT) {
427 *starter += hangul_tindex;
428 starter_property = NULL;
429 continue;
430 }
431 }
432 if (!starter_property) {
433 starter_property = utf8proc_get_property(*starter);
434 }
435 if (starter_property->comb1st_index >= 0 &&
436 current_property->comb2nd_index >= 0) {
437 composition = utf8proc_combinations[
438 starter_property->comb1st_index +
439 current_property->comb2nd_index
440 ];
441 if (composition >= 0 && (!(options & UTF8PROC_STABLE) ||
442 !(utf8proc_get_property(composition)->comp_exclusion))) {
443 *starter = composition;
444 starter_property = NULL;
445 continue;
446 }
447 }
448 }
449 buffer[wpos] = current_char;
450 if (current_property->combining_class) {
451 if (current_property->combining_class > max_combining_class) {
452 max_combining_class = current_property->combining_class;
453 }
454 } else {
455 starter = buffer + wpos;
456 starter_property = NULL;
457 max_combining_class = -1;
458 }
459 wpos++;
460 }
461 length = wpos;
462 }
463 {
464 ssize_t rpos, wpos = 0;
465 int32_t uc;
466 for (rpos = 0; rpos < length; rpos++) {
467 uc = buffer[rpos];
468 wpos += utf8proc_encode_char(uc, ((uint8_t *)buffer) + wpos);
469 }
470 ((uint8_t *)buffer)[wpos] = 0;
471 return wpos;
472 }
473 }
474
475 ssize_t utf8proc_map(uint8_t *str, ssize_t strlen, uint8_t **dstptr,
476 int options) {
477 int32_t *buffer;
478 ssize_t result;
479 *dstptr = NULL;
480 result = utf8proc_decompose(str, strlen, NULL, 0, options);
481 if (result < 0) return result;
482 buffer = malloc(result * sizeof(int32_t) + 1);
483 if (!buffer) return UTF8PROC_ERROR_NOMEM;
484 result = utf8proc_decompose(str, strlen, buffer, result, options);
485 if (result < 0) {
486 free(buffer);
487 return result;
488 }
489 result = utf8proc_reencode(buffer, result, options);
490 if (result < 0) {
491 free(buffer);
492 return result;
493 }
494 {
495 int32_t *newptr;
496 newptr = realloc(buffer, result+1);
497 if (newptr) buffer = newptr;
498 }
499 *dstptr = (uint8_t *)buffer;
500 return result;
501 }
502
503 uint8_t *utf8proc_NFD(uint8_t *str) {
504 uint8_t *retval;
505 utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
506 UTF8PROC_DECOMPOSE);
507 return retval;
508 }
509
510 uint8_t *utf8proc_NFC(uint8_t *str) {
511 uint8_t *retval;
512 utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
513 UTF8PROC_COMPOSE);
514 return retval;
515 }
516
517 uint8_t *utf8proc_NFKD(uint8_t *str) {
518 uint8_t *retval;
519 utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
520 UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
521 return retval;
522 }
523
524 uint8_t *utf8proc_NFKC(uint8_t *str) {
525 uint8_t *retval;
526 utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
527 UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
528 return retval;
529 }
530
531

Impressum / About Us