1 | /*
|
---|
2 | * Unicode string manipulation functions
|
---|
3 | *
|
---|
4 | * Copyright 2000 Alexandre Julliard
|
---|
5 | *
|
---|
6 | * This library is free software; you can redistribute it and/or
|
---|
7 | * modify it under the terms of the GNU Lesser General Public
|
---|
8 | * License as published by the Free Software Foundation; either
|
---|
9 | * version 2.1 of the License, or (at your option) any later version.
|
---|
10 | *
|
---|
11 | * This library is distributed in the hope that it will be useful,
|
---|
12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
---|
14 | * Lesser General Public License for more details.
|
---|
15 | *
|
---|
16 | * You should have received a copy of the GNU Lesser General Public
|
---|
17 | * License along with this library; if not, write to the Free Software
|
---|
18 | * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
|
---|
19 | */
|
---|
20 |
|
---|
21 | /*
|
---|
22 | * Sun LGPL Disclaimer: For the avoidance of doubt, except that if any license choice
|
---|
23 | * other than GPL or LGPL is available it will apply instead, Sun elects to use only
|
---|
24 | * the Lesser General Public License version 2.1 (LGPLv2) at this time for any software where
|
---|
25 | * a choice of LGPL license versions is made available with the language indicating
|
---|
26 | * that LGPLv2 or any later version may be used, or where a choice of which version
|
---|
27 | * of the LGPL is applied is otherwise unspecified.
|
---|
28 | */
|
---|
29 |
|
---|
30 | #include <assert.h>
|
---|
31 | #include <limits.h>
|
---|
32 | #include <stdio.h>
|
---|
33 |
|
---|
34 | #define WINE_UNICODE_INLINE /* nothing */
|
---|
35 | #include "wine/unicode.h"
|
---|
36 |
|
---|
37 | int strcmpiW( const WCHAR *str1, const WCHAR *str2 )
|
---|
38 | {
|
---|
39 | for (;;)
|
---|
40 | {
|
---|
41 | int ret = tolowerW(*str1) - tolowerW(*str2);
|
---|
42 | if (ret || !*str1) return ret;
|
---|
43 | str1++;
|
---|
44 | str2++;
|
---|
45 | }
|
---|
46 | }
|
---|
47 |
|
---|
48 | int strncmpiW( const WCHAR *str1, const WCHAR *str2, int n )
|
---|
49 | {
|
---|
50 | int ret = 0;
|
---|
51 | for ( ; n > 0; n--, str1++, str2++)
|
---|
52 | if ((ret = tolowerW(*str1) - tolowerW(*str2)) || !*str1) break;
|
---|
53 | return ret;
|
---|
54 | }
|
---|
55 |
|
---|
56 | int memicmpW( const WCHAR *str1, const WCHAR *str2, int n )
|
---|
57 | {
|
---|
58 | int ret = 0;
|
---|
59 | for ( ; n > 0; n--, str1++, str2++)
|
---|
60 | if ((ret = tolowerW(*str1) - tolowerW(*str2))) break;
|
---|
61 | return ret;
|
---|
62 | }
|
---|
63 |
|
---|
64 | WCHAR *strstrW( const WCHAR *str, const WCHAR *sub )
|
---|
65 | {
|
---|
66 | while (*str)
|
---|
67 | {
|
---|
68 | const WCHAR *p1 = str, *p2 = sub;
|
---|
69 | while (*p1 && *p2 && *p1 == *p2) { p1++; p2++; }
|
---|
70 | if (!*p2) return (WCHAR *)str;
|
---|
71 | str++;
|
---|
72 | }
|
---|
73 | return NULL;
|
---|
74 | }
|
---|
75 |
|
---|
76 | /* strtolW and strtoulW implementation based on the GNU C library code */
|
---|
77 | /* Copyright (C) 1991,92,94,95,96,97,98,99,2000,2001 Free Software Foundation, Inc. */
|
---|
78 |
|
---|
79 | long int strtolW( const WCHAR *nptr, WCHAR **endptr, int base )
|
---|
80 | {
|
---|
81 | int negative;
|
---|
82 | register unsigned long int cutoff;
|
---|
83 | register unsigned int cutlim;
|
---|
84 | register unsigned long int i;
|
---|
85 | register const WCHAR *s;
|
---|
86 | register WCHAR c;
|
---|
87 | const WCHAR *save, *end;
|
---|
88 | int overflow;
|
---|
89 |
|
---|
90 | if (base < 0 || base == 1 || base > 36) return 0;
|
---|
91 |
|
---|
92 | save = s = nptr;
|
---|
93 |
|
---|
94 | /* Skip white space. */
|
---|
95 | while (isspaceW (*s))
|
---|
96 | ++s;
|
---|
97 | if (!*s) goto noconv;
|
---|
98 |
|
---|
99 | /* Check for a sign. */
|
---|
100 | negative = 0;
|
---|
101 | if (*s == '-')
|
---|
102 | {
|
---|
103 | negative = 1;
|
---|
104 | ++s;
|
---|
105 | }
|
---|
106 | else if (*s == '+')
|
---|
107 | ++s;
|
---|
108 |
|
---|
109 | /* Recognize number prefix and if BASE is zero, figure it out ourselves. */
|
---|
110 | if (*s == '0')
|
---|
111 | {
|
---|
112 | if ((base == 0 || base == 16) && toupperW(s[1]) == 'X')
|
---|
113 | {
|
---|
114 | s += 2;
|
---|
115 | base = 16;
|
---|
116 | }
|
---|
117 | else if (base == 0)
|
---|
118 | base = 8;
|
---|
119 | }
|
---|
120 | else if (base == 0)
|
---|
121 | base = 10;
|
---|
122 |
|
---|
123 | /* Save the pointer so we can check later if anything happened. */
|
---|
124 | save = s;
|
---|
125 | end = NULL;
|
---|
126 |
|
---|
127 | cutoff = ULONG_MAX / (unsigned long int) base;
|
---|
128 | cutlim = ULONG_MAX % (unsigned long int) base;
|
---|
129 |
|
---|
130 | overflow = 0;
|
---|
131 | i = 0;
|
---|
132 | c = *s;
|
---|
133 | for (;c != '\0'; c = *++s)
|
---|
134 | {
|
---|
135 | if (s == end)
|
---|
136 | break;
|
---|
137 | if (c >= '0' && c <= '9')
|
---|
138 | c -= '0';
|
---|
139 | else if (isalphaW (c))
|
---|
140 | c = toupperW (c) - 'A' + 10;
|
---|
141 | else
|
---|
142 | break;
|
---|
143 | if ((int) c >= base)
|
---|
144 | break;
|
---|
145 | /* Check for overflow. */
|
---|
146 | if (i > cutoff || (i == cutoff && c > cutlim))
|
---|
147 | overflow = 1;
|
---|
148 | else
|
---|
149 | {
|
---|
150 | i *= (unsigned long int) base;
|
---|
151 | i += c;
|
---|
152 | }
|
---|
153 | }
|
---|
154 |
|
---|
155 | /* Check if anything actually happened. */
|
---|
156 | if (s == save)
|
---|
157 | goto noconv;
|
---|
158 |
|
---|
159 | /* Store in ENDPTR the address of one character
|
---|
160 | past the last character we converted. */
|
---|
161 | if (endptr != NULL)
|
---|
162 | *endptr = (WCHAR *)s;
|
---|
163 |
|
---|
164 | /* Check for a value that is within the range of
|
---|
165 | `unsigned LONG int', but outside the range of `LONG int'. */
|
---|
166 | if (overflow == 0
|
---|
167 | && i > (negative
|
---|
168 | ? -((unsigned long int) (LONG_MIN + 1)) + 1
|
---|
169 | : (unsigned long int) LONG_MAX))
|
---|
170 | overflow = 1;
|
---|
171 |
|
---|
172 | if (overflow)
|
---|
173 | {
|
---|
174 | return negative ? LONG_MIN : LONG_MAX;
|
---|
175 | }
|
---|
176 |
|
---|
177 | /* Return the result of the appropriate sign. */
|
---|
178 | return negative ? -i : i;
|
---|
179 |
|
---|
180 | noconv:
|
---|
181 | /* We must handle a special case here: the base is 0 or 16 and the
|
---|
182 | first two characters are '0' and 'x', but the rest are not
|
---|
183 | hexadecimal digits. This is no error case. We return 0 and
|
---|
184 | ENDPTR points to the `x`. */
|
---|
185 | if (endptr != NULL)
|
---|
186 | {
|
---|
187 | if (save - nptr >= 2 && toupperW (save[-1]) == 'X'
|
---|
188 | && save[-2] == '0')
|
---|
189 | *endptr = (WCHAR *)&save[-1];
|
---|
190 | else
|
---|
191 | /* There was no number to convert. */
|
---|
192 | *endptr = (WCHAR *)nptr;
|
---|
193 | }
|
---|
194 |
|
---|
195 | return 0L;
|
---|
196 | }
|
---|
197 |
|
---|
198 |
|
---|
199 | unsigned long int strtoulW( const WCHAR *nptr, WCHAR **endptr, int base )
|
---|
200 | {
|
---|
201 | int negative;
|
---|
202 | register unsigned long int cutoff;
|
---|
203 | register unsigned int cutlim;
|
---|
204 | register unsigned long int i;
|
---|
205 | register const WCHAR *s;
|
---|
206 | register WCHAR c;
|
---|
207 | const WCHAR *save, *end;
|
---|
208 | int overflow;
|
---|
209 |
|
---|
210 | if (base < 0 || base == 1 || base > 36) return 0;
|
---|
211 |
|
---|
212 | save = s = nptr;
|
---|
213 |
|
---|
214 | /* Skip white space. */
|
---|
215 | while (isspaceW (*s))
|
---|
216 | ++s;
|
---|
217 | if (!*s) goto noconv;
|
---|
218 |
|
---|
219 | /* Check for a sign. */
|
---|
220 | negative = 0;
|
---|
221 | if (*s == '-')
|
---|
222 | {
|
---|
223 | negative = 1;
|
---|
224 | ++s;
|
---|
225 | }
|
---|
226 | else if (*s == '+')
|
---|
227 | ++s;
|
---|
228 |
|
---|
229 | /* Recognize number prefix and if BASE is zero, figure it out ourselves. */
|
---|
230 | if (*s == '0')
|
---|
231 | {
|
---|
232 | if ((base == 0 || base == 16) && toupperW(s[1]) == 'X')
|
---|
233 | {
|
---|
234 | s += 2;
|
---|
235 | base = 16;
|
---|
236 | }
|
---|
237 | else if (base == 0)
|
---|
238 | base = 8;
|
---|
239 | }
|
---|
240 | else if (base == 0)
|
---|
241 | base = 10;
|
---|
242 |
|
---|
243 | /* Save the pointer so we can check later if anything happened. */
|
---|
244 | save = s;
|
---|
245 | end = NULL;
|
---|
246 |
|
---|
247 | cutoff = ULONG_MAX / (unsigned long int) base;
|
---|
248 | cutlim = ULONG_MAX % (unsigned long int) base;
|
---|
249 |
|
---|
250 | overflow = 0;
|
---|
251 | i = 0;
|
---|
252 | c = *s;
|
---|
253 | for (;c != '\0'; c = *++s)
|
---|
254 | {
|
---|
255 | if (s == end)
|
---|
256 | break;
|
---|
257 | if (c >= '0' && c <= '9')
|
---|
258 | c -= '0';
|
---|
259 | else if (isalphaW (c))
|
---|
260 | c = toupperW (c) - 'A' + 10;
|
---|
261 | else
|
---|
262 | break;
|
---|
263 | if ((int) c >= base)
|
---|
264 | break;
|
---|
265 | /* Check for overflow. */
|
---|
266 | if (i > cutoff || (i == cutoff && c > cutlim))
|
---|
267 | overflow = 1;
|
---|
268 | else
|
---|
269 | {
|
---|
270 | i *= (unsigned long int) base;
|
---|
271 | i += c;
|
---|
272 | }
|
---|
273 | }
|
---|
274 |
|
---|
275 | /* Check if anything actually happened. */
|
---|
276 | if (s == save)
|
---|
277 | goto noconv;
|
---|
278 |
|
---|
279 | /* Store in ENDPTR the address of one character
|
---|
280 | past the last character we converted. */
|
---|
281 | if (endptr != NULL)
|
---|
282 | *endptr = (WCHAR *)s;
|
---|
283 |
|
---|
284 | if (overflow)
|
---|
285 | {
|
---|
286 | return ULONG_MAX;
|
---|
287 | }
|
---|
288 |
|
---|
289 | /* Return the result of the appropriate sign. */
|
---|
290 | return negative ? -i : i;
|
---|
291 |
|
---|
292 | noconv:
|
---|
293 | /* We must handle a special case here: the base is 0 or 16 and the
|
---|
294 | first two characters are '0' and 'x', but the rest are not
|
---|
295 | hexadecimal digits. This is no error case. We return 0 and
|
---|
296 | ENDPTR points to the `x`. */
|
---|
297 | if (endptr != NULL)
|
---|
298 | {
|
---|
299 | if (save - nptr >= 2 && toupperW (save[-1]) == 'X'
|
---|
300 | && save[-2] == '0')
|
---|
301 | *endptr = (WCHAR *)&save[-1];
|
---|
302 | else
|
---|
303 | /* There was no number to convert. */
|
---|
304 | *endptr = (WCHAR *)nptr;
|
---|
305 | }
|
---|
306 |
|
---|
307 | return 0L;
|
---|
308 | }
|
---|
309 |
|
---|
310 |
|
---|
311 | /* format a WCHAR string according to a printf format; helper for vsnprintfW */
|
---|
312 | static int format_string( WCHAR *buffer, size_t len, const char *format, const WCHAR *str )
|
---|
313 | {
|
---|
314 | size_t count = 0;
|
---|
315 | int i, left_align = 0, width = 0, max = 0;
|
---|
316 |
|
---|
317 | assert( *format == '%' );
|
---|
318 | format++; /* skip '%' */
|
---|
319 |
|
---|
320 | while (*format == '0' || *format == '+' || *format == '-' || *format == ' ' || *format == '#')
|
---|
321 | {
|
---|
322 | if (*format == '-') left_align = 1;
|
---|
323 | format++;
|
---|
324 | }
|
---|
325 |
|
---|
326 | while (isdigit(*format)) width = width * 10 + *format++ - '0';
|
---|
327 |
|
---|
328 | if (*format == '.')
|
---|
329 | {
|
---|
330 | format++;
|
---|
331 | while (isdigit(*format)) max = max * 10 + *format++ - '0';
|
---|
332 | for (i = 0; i < max; i++) if (!str[i]) max = i;
|
---|
333 | }
|
---|
334 | else max = strlenW(str);
|
---|
335 |
|
---|
336 | if (*format == 'h' || *format == 'l') format++;
|
---|
337 |
|
---|
338 | assert( *format == 's' );
|
---|
339 |
|
---|
340 | if (!left_align && width > max)
|
---|
341 | {
|
---|
342 | if ((count += width - max) >= len) return -1;
|
---|
343 | for (i = 0; i < width - max; i++) *buffer++ = ' ';
|
---|
344 | }
|
---|
345 |
|
---|
346 | if ((count += max) >= len) return -1;
|
---|
347 | memcpy( buffer, str, max * sizeof(WCHAR) );
|
---|
348 | buffer += max;
|
---|
349 |
|
---|
350 | if (left_align && width > max)
|
---|
351 | {
|
---|
352 | if ((count += width - max) >= len) return -1;
|
---|
353 | for (i = 0; i < width - max; i++) *buffer++ = ' ';
|
---|
354 | }
|
---|
355 | return count;
|
---|
356 | }
|
---|
357 |
|
---|
358 | int vsnprintfW(WCHAR *str, size_t len, const WCHAR *format, va_list valist)
|
---|
359 | {
|
---|
360 | unsigned int written = 0;
|
---|
361 | const WCHAR *iter = format;
|
---|
362 | char bufa[256], fmtbufa[64], *fmta;
|
---|
363 |
|
---|
364 | while (*iter)
|
---|
365 | {
|
---|
366 | while (*iter && *iter != '%')
|
---|
367 | {
|
---|
368 | if (written++ >= len)
|
---|
369 | return -1;
|
---|
370 | *str++ = *iter++;
|
---|
371 | }
|
---|
372 | if (*iter == '%')
|
---|
373 | {
|
---|
374 | if (iter[1] == '%')
|
---|
375 | {
|
---|
376 | if (written++ >= len)
|
---|
377 | return -1;
|
---|
378 | *str++ = '%'; /* "%%"->'%' */
|
---|
379 | iter += 2;
|
---|
380 | continue;
|
---|
381 | }
|
---|
382 |
|
---|
383 | fmta = fmtbufa;
|
---|
384 | *fmta++ = *iter++;
|
---|
385 | while (*iter == '0' ||
|
---|
386 | *iter == '+' ||
|
---|
387 | *iter == '-' ||
|
---|
388 | *iter == ' ' ||
|
---|
389 | *iter == '*' ||
|
---|
390 | *iter == '#')
|
---|
391 | {
|
---|
392 | if (*iter == '*')
|
---|
393 | {
|
---|
394 | char *buffiter = bufa;
|
---|
395 | int fieldlen = va_arg(valist, int);
|
---|
396 | sprintf(buffiter, "%d", fieldlen);
|
---|
397 | while (*buffiter)
|
---|
398 | *fmta++ = *buffiter++;
|
---|
399 | }
|
---|
400 | else
|
---|
401 | *fmta++ = *iter;
|
---|
402 | iter++;
|
---|
403 | }
|
---|
404 |
|
---|
405 | while (isdigit(*iter))
|
---|
406 | *fmta++ = *iter++;
|
---|
407 |
|
---|
408 | if (*iter == '.')
|
---|
409 | {
|
---|
410 | *fmta++ = *iter++;
|
---|
411 | if (*iter == '*')
|
---|
412 | {
|
---|
413 | char *buffiter = bufa;
|
---|
414 | int fieldlen = va_arg(valist, int);
|
---|
415 | sprintf(buffiter, "%d", fieldlen);
|
---|
416 | while (*buffiter)
|
---|
417 | *fmta++ = *buffiter++;
|
---|
418 | }
|
---|
419 | else
|
---|
420 | while (isdigit(*iter))
|
---|
421 | *fmta++ = *iter++;
|
---|
422 | }
|
---|
423 | if (*iter == 'h' || *iter == 'l')
|
---|
424 | *fmta++ = *iter++;
|
---|
425 |
|
---|
426 | switch (*iter)
|
---|
427 | {
|
---|
428 | case 's':
|
---|
429 | {
|
---|
430 | static const WCHAR none[] = { '(','n','u','l','l',')',0 };
|
---|
431 | const WCHAR *wstr = va_arg(valist, const WCHAR *);
|
---|
432 | int count;
|
---|
433 |
|
---|
434 | *fmta++ = 's';
|
---|
435 | *fmta = 0;
|
---|
436 | count = format_string( str, len - written, fmtbufa, wstr ? wstr : none );
|
---|
437 | if (count == -1) return -1;
|
---|
438 | str += count;
|
---|
439 | written += count;
|
---|
440 | iter++;
|
---|
441 | break;
|
---|
442 | }
|
---|
443 |
|
---|
444 | case 'c':
|
---|
445 | {
|
---|
446 | WCHAR wstr[2];
|
---|
447 | int count;
|
---|
448 |
|
---|
449 | wstr[0] = va_arg(valist, int);
|
---|
450 | wstr[1] = 0;
|
---|
451 | *fmta++ = 's';
|
---|
452 | *fmta = 0;
|
---|
453 | count = format_string( str, len - written, fmtbufa, wstr );
|
---|
454 | if (count == -1) return -1;
|
---|
455 | str += count;
|
---|
456 | written += count;
|
---|
457 | iter++;
|
---|
458 | break;
|
---|
459 | }
|
---|
460 |
|
---|
461 | default:
|
---|
462 | {
|
---|
463 | /* For non wc types, use system sprintf and append to wide char output */
|
---|
464 | /* FIXME: for unrecognised types, should ignore % when printing */
|
---|
465 | char *bufaiter = bufa;
|
---|
466 | if (*iter == 'p')
|
---|
467 | sprintf(bufaiter, "%0*lX", 2 * (int)sizeof(void*),
|
---|
468 | (unsigned long)va_arg(valist, void *));
|
---|
469 | else
|
---|
470 | {
|
---|
471 | *fmta++ = *iter;
|
---|
472 | *fmta = '\0';
|
---|
473 | if (*iter == 'a' || *iter == 'A' ||
|
---|
474 | *iter == 'e' || *iter == 'E' ||
|
---|
475 | *iter == 'f' || *iter == 'F' ||
|
---|
476 | *iter == 'g' || *iter == 'G')
|
---|
477 | sprintf(bufaiter, fmtbufa, va_arg(valist, double));
|
---|
478 | else
|
---|
479 | {
|
---|
480 | /* FIXME: On 32 bit systems this doesn't handle int 64's. */
|
---|
481 | sprintf(bufaiter, fmtbufa, va_arg(valist, void *));
|
---|
482 | }
|
---|
483 | }
|
---|
484 | while (*bufaiter)
|
---|
485 | {
|
---|
486 | if (written++ >= len)
|
---|
487 | return -1;
|
---|
488 | *str++ = *bufaiter++;
|
---|
489 | }
|
---|
490 | iter++;
|
---|
491 | break;
|
---|
492 | }
|
---|
493 | }
|
---|
494 | }
|
---|
495 | }
|
---|
496 | if (written >= len)
|
---|
497 | return -1;
|
---|
498 | *str++ = 0;
|
---|
499 | return (int)written;
|
---|
500 | }
|
---|
501 |
|
---|
502 | int vsprintfW( WCHAR *str, const WCHAR *format, va_list valist )
|
---|
503 | {
|
---|
504 | return vsnprintfW( str, INT_MAX, format, valist );
|
---|
505 | }
|
---|
506 |
|
---|
507 | int snprintfW( WCHAR *str, size_t len, const WCHAR *format, ...)
|
---|
508 | {
|
---|
509 | int retval;
|
---|
510 | va_list valist;
|
---|
511 | va_start(valist, format);
|
---|
512 | retval = vsnprintfW(str, len, format, valist);
|
---|
513 | va_end(valist);
|
---|
514 | return retval;
|
---|
515 | }
|
---|
516 |
|
---|
517 | int sprintfW( WCHAR *str, const WCHAR *format, ...)
|
---|
518 | {
|
---|
519 | int retval;
|
---|
520 | va_list valist;
|
---|
521 | va_start(valist, format);
|
---|
522 | retval = vsnprintfW(str, INT_MAX, format, valist);
|
---|
523 | va_end(valist);
|
---|
524 | return retval;
|
---|
525 | }
|
---|