Rev 4226 | Rev 4265 | Go to most recent revision | Details | Compare with Previous | Last modification | View Log | RSS feed
Rev | Author | Line No. | Line |
---|---|---|---|
999 | palkovsky | 1 | /* |
2071 | jermar | 2 | * Copyright (c) 2005 Martin Decky |
3730 | svoboda | 3 | * Copyright (c) 2008 Jiri Svoboda |
999 | palkovsky | 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 |
||
8 | * are met: |
||
9 | * |
||
10 | * - Redistributions of source code must retain the above copyright |
||
11 | * notice, this list of conditions and the following disclaimer. |
||
12 | * - 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 | * - The name of the author may not be used to endorse or promote products |
||
16 | * derived from this software without specific prior written permission. |
||
17 | * |
||
18 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR |
||
19 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
||
20 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. |
||
21 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, |
||
22 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
||
23 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
||
24 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
||
25 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
||
26 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
||
27 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
||
28 | */ |
||
29 | |||
1719 | decky | 30 | /** @addtogroup libc |
1653 | cejka | 31 | * @{ |
32 | */ |
||
33 | /** @file |
||
34 | */ |
||
35 | |||
999 | palkovsky | 36 | #include <string.h> |
3731 | svoboda | 37 | #include <stdlib.h> |
38 | #include <limits.h> |
||
1314 | cejka | 39 | #include <ctype.h> |
3238 | jermar | 40 | #include <malloc.h> |
4226 | svoboda | 41 | #include <errno.h> |
4234 | svoboda | 42 | #include <align.h> |
4226 | svoboda | 43 | #include <string.h> |
999 | palkovsky | 44 | |
4226 | svoboda | 45 | /** Byte mask consisting of lowest @n bits (out of 8) */ |
46 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1)) |
||
47 | |||
48 | /** Byte mask consisting of lowest @n bits (out of 32) */ |
||
49 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1)) |
||
50 | |||
51 | /** Byte mask consisting of highest @n bits (out of 8) */ |
||
52 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n))) |
||
53 | |||
54 | /** Number of data bits in a UTF-8 continuation byte */ |
||
55 | #define CONT_BITS 6 |
||
56 | |||
57 | /** Decode a single character from a string. |
||
58 | * |
||
59 | * Decode a single character from a string of size @a size. Decoding starts |
||
60 | * at @a offset and this offset is moved to the beginning of the next |
||
61 | * character. In case of decoding error, offset generally advances at least |
||
62 | * by one. However, offset is never moved beyond size. |
||
63 | * |
||
64 | * @param str String (not necessarily NULL-terminated). |
||
65 | * @param offset Byte offset in string where to start decoding. |
||
66 | * @param size Size of the string (in bytes). |
||
67 | * |
||
68 | * @return Value of decoded character, U_SPECIAL on decoding error or |
||
69 | * NULL if attempt to decode beyond @a size. |
||
70 | * |
||
71 | */ |
||
72 | wchar_t str_decode(const char *str, size_t *offset, size_t size) |
||
73 | { |
||
74 | if (*offset + 1 > size) |
||
75 | return 0; |
||
76 | |||
77 | /* First byte read from string */ |
||
78 | uint8_t b0 = (uint8_t) str[(*offset)++]; |
||
79 | |||
80 | /* Determine code length */ |
||
81 | |||
82 | unsigned int b0_bits; /* Data bits in first byte */ |
||
83 | unsigned int cbytes; /* Number of continuation bytes */ |
||
84 | |||
85 | if ((b0 & 0x80) == 0) { |
||
86 | /* 0xxxxxxx (Plain ASCII) */ |
||
87 | b0_bits = 7; |
||
88 | cbytes = 0; |
||
89 | } else if ((b0 & 0xe0) == 0xc0) { |
||
90 | /* 110xxxxx 10xxxxxx */ |
||
91 | b0_bits = 5; |
||
92 | cbytes = 1; |
||
93 | } else if ((b0 & 0xf0) == 0xe0) { |
||
94 | /* 1110xxxx 10xxxxxx 10xxxxxx */ |
||
95 | b0_bits = 4; |
||
96 | cbytes = 2; |
||
97 | } else if ((b0 & 0xf8) == 0xf0) { |
||
98 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ |
||
99 | b0_bits = 3; |
||
100 | cbytes = 3; |
||
101 | } else { |
||
102 | /* 10xxxxxx -- unexpected continuation byte */ |
||
103 | return U_SPECIAL; |
||
104 | } |
||
105 | |||
106 | if (*offset + cbytes > size) |
||
107 | return U_SPECIAL; |
||
108 | |||
109 | wchar_t ch = b0 & LO_MASK_8(b0_bits); |
||
110 | |||
111 | /* Decode continuation bytes */ |
||
112 | while (cbytes > 0) { |
||
113 | uint8_t b = (uint8_t) str[(*offset)++]; |
||
114 | |||
115 | /* Must be 10xxxxxx */ |
||
116 | if ((b & 0xc0) != 0x80) |
||
117 | return U_SPECIAL; |
||
118 | |||
119 | /* Shift data bits to ch */ |
||
120 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS)); |
||
121 | cbytes--; |
||
122 | } |
||
123 | |||
124 | return ch; |
||
125 | } |
||
126 | |||
127 | /** Encode a single character to string representation. |
||
128 | * |
||
129 | * Encode a single character to string representation (i.e. UTF-8) and store |
||
130 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset |
||
131 | * is moved to the position where the next character can be written to. |
||
132 | * |
||
133 | * @param ch Input character. |
||
134 | * @param str Output buffer. |
||
135 | * @param offset Byte offset where to start writing. |
||
136 | * @param size Size of the output buffer (in bytes). |
||
137 | * |
||
138 | * @return EOK if the character was encoded successfully, EOVERFLOW if there |
||
139 | * was not enough space in the output buffer or EINVAL if the character |
||
140 | * code was invalid. |
||
141 | */ |
||
142 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size) |
||
143 | { |
||
144 | if (*offset >= size) |
||
145 | return EOVERFLOW; |
||
146 | |||
147 | if (!chr_check(ch)) |
||
148 | return EINVAL; |
||
149 | |||
150 | /* Unsigned version of ch (bit operations should only be done |
||
151 | on unsigned types). */ |
||
152 | uint32_t cc = (uint32_t) ch; |
||
153 | |||
154 | /* Determine how many continuation bytes are needed */ |
||
155 | |||
156 | unsigned int b0_bits; /* Data bits in first byte */ |
||
157 | unsigned int cbytes; /* Number of continuation bytes */ |
||
158 | |||
159 | if ((cc & ~LO_MASK_32(7)) == 0) { |
||
160 | b0_bits = 7; |
||
161 | cbytes = 0; |
||
162 | } else if ((cc & ~LO_MASK_32(11)) == 0) { |
||
163 | b0_bits = 5; |
||
164 | cbytes = 1; |
||
165 | } else if ((cc & ~LO_MASK_32(16)) == 0) { |
||
166 | b0_bits = 4; |
||
167 | cbytes = 2; |
||
168 | } else if ((cc & ~LO_MASK_32(21)) == 0) { |
||
169 | b0_bits = 3; |
||
170 | cbytes = 3; |
||
171 | } else { |
||
172 | /* Codes longer than 21 bits are not supported */ |
||
173 | return EINVAL; |
||
174 | } |
||
175 | |||
176 | /* Check for available space in buffer */ |
||
177 | if (*offset + cbytes >= size) |
||
178 | return EOVERFLOW; |
||
179 | |||
180 | /* Encode continuation bytes */ |
||
181 | unsigned int i; |
||
182 | for (i = cbytes; i > 0; i--) { |
||
183 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS)); |
||
184 | cc = cc >> CONT_BITS; |
||
185 | } |
||
186 | |||
187 | /* Encode first byte */ |
||
188 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1); |
||
189 | |||
190 | /* Advance offset */ |
||
191 | *offset += cbytes + 1; |
||
192 | |||
193 | return EOK; |
||
194 | } |
||
195 | |||
4234 | svoboda | 196 | /** Get size of string. |
197 | * |
||
198 | * Get the number of bytes which are used by the string @a str (excluding the |
||
199 | * NULL-terminator). |
||
200 | * |
||
201 | * @param str String to consider. |
||
202 | * |
||
203 | * @return Number of bytes used by the string |
||
204 | * |
||
205 | */ |
||
206 | size_t str_size(const char *str) |
||
207 | { |
||
208 | size_t size = 0; |
||
209 | |||
210 | while (*str++ != 0) |
||
211 | size++; |
||
212 | |||
213 | return size; |
||
214 | } |
||
215 | |||
216 | /** Get size of wide string. |
||
217 | * |
||
218 | * Get the number of bytes which are used by the wide string @a str (excluding the |
||
219 | * NULL-terminator). |
||
220 | * |
||
221 | * @param str Wide string to consider. |
||
222 | * |
||
223 | * @return Number of bytes used by the wide string |
||
224 | * |
||
225 | */ |
||
226 | size_t wstr_size(const wchar_t *str) |
||
227 | { |
||
228 | return (wstr_length(str) * sizeof(wchar_t)); |
||
229 | } |
||
230 | |||
231 | /** Get size of string with length limit. |
||
232 | * |
||
233 | * Get the number of bytes which are used by up to @a max_len first |
||
234 | * characters in the string @a str. If @a max_len is greater than |
||
235 | * the length of @a str, the entire string is measured (excluding the |
||
236 | * NULL-terminator). |
||
237 | * |
||
238 | * @param str String to consider. |
||
239 | * @param max_len Maximum number of characters to measure. |
||
240 | * |
||
241 | * @return Number of bytes used by the characters. |
||
242 | * |
||
243 | */ |
||
244 | size_t str_lsize(const char *str, count_t max_len) |
||
245 | { |
||
246 | count_t len = 0; |
||
247 | size_t offset = 0; |
||
248 | |||
249 | while (len < max_len) { |
||
250 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0) |
||
251 | break; |
||
252 | |||
253 | len++; |
||
254 | } |
||
255 | |||
256 | return offset; |
||
257 | } |
||
258 | |||
259 | /** Get size of wide string with length limit. |
||
260 | * |
||
261 | * Get the number of bytes which are used by up to @a max_len first |
||
262 | * wide characters in the wide string @a str. If @a max_len is greater than |
||
263 | * the length of @a str, the entire wide string is measured (excluding the |
||
264 | * NULL-terminator). |
||
265 | * |
||
266 | * @param str Wide string to consider. |
||
267 | * @param max_len Maximum number of wide characters to measure. |
||
268 | * |
||
269 | * @return Number of bytes used by the wide characters. |
||
270 | * |
||
271 | */ |
||
272 | size_t wstr_lsize(const wchar_t *str, count_t max_len) |
||
273 | { |
||
274 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t)); |
||
275 | } |
||
276 | |||
277 | /** Get number of characters in a string. |
||
278 | * |
||
279 | * @param str NULL-terminated string. |
||
280 | * |
||
281 | * @return Number of characters in string. |
||
282 | * |
||
283 | */ |
||
284 | count_t str_length(const char *str) |
||
285 | { |
||
286 | count_t len = 0; |
||
287 | size_t offset = 0; |
||
288 | |||
289 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0) |
||
290 | len++; |
||
291 | |||
292 | return len; |
||
293 | } |
||
294 | |||
295 | /** Get number of characters in a wide string. |
||
296 | * |
||
297 | * @param str NULL-terminated wide string. |
||
298 | * |
||
299 | * @return Number of characters in @a str. |
||
300 | * |
||
301 | */ |
||
302 | count_t wstr_length(const wchar_t *wstr) |
||
303 | { |
||
304 | count_t len = 0; |
||
305 | |||
306 | while (*wstr++ != 0) |
||
307 | len++; |
||
308 | |||
309 | return len; |
||
310 | } |
||
311 | |||
312 | /** Get number of characters in a string with size limit. |
||
313 | * |
||
314 | * @param str NULL-terminated string. |
||
315 | * @param size Maximum number of bytes to consider. |
||
316 | * |
||
317 | * @return Number of characters in string. |
||
318 | * |
||
319 | */ |
||
320 | count_t str_nlength(const char *str, size_t size) |
||
321 | { |
||
322 | count_t len = 0; |
||
323 | size_t offset = 0; |
||
324 | |||
325 | while (str_decode(str, &offset, size) != 0) |
||
326 | len++; |
||
327 | |||
328 | return len; |
||
329 | } |
||
330 | |||
331 | /** Get number of characters in a string with size limit. |
||
332 | * |
||
333 | * @param str NULL-terminated string. |
||
334 | * @param size Maximum number of bytes to consider. |
||
335 | * |
||
336 | * @return Number of characters in string. |
||
337 | * |
||
338 | */ |
||
339 | count_t wstr_nlength(const wchar_t *str, size_t size) |
||
340 | { |
||
341 | count_t len = 0; |
||
342 | count_t limit = ALIGN_DOWN(size, sizeof(wchar_t)); |
||
343 | count_t offset = 0; |
||
344 | |||
345 | while ((offset < limit) && (*str++ != 0)) { |
||
346 | len++; |
||
347 | offset += sizeof(wchar_t); |
||
348 | } |
||
349 | |||
350 | return len; |
||
351 | } |
||
352 | |||
353 | /** Check whether character is plain ASCII. |
||
354 | * |
||
355 | * @return True if character is plain ASCII. |
||
356 | * |
||
357 | */ |
||
358 | bool ascii_check(wchar_t ch) |
||
359 | { |
||
360 | if ((ch >= 0) && (ch <= 127)) |
||
361 | return true; |
||
362 | |||
363 | return false; |
||
364 | } |
||
365 | |||
4226 | svoboda | 366 | /** Check whether character is valid |
367 | * |
||
368 | * @return True if character is a valid Unicode code point. |
||
369 | * |
||
370 | */ |
||
4234 | svoboda | 371 | bool chr_check(wchar_t ch) |
4226 | svoboda | 372 | { |
373 | if ((ch >= 0) && (ch <= 1114111)) |
||
374 | return true; |
||
375 | |||
376 | return false; |
||
377 | } |
||
378 | |||
4234 | svoboda | 379 | /** Compare two NULL terminated strings. |
380 | * |
||
381 | * Do a char-by-char comparison of two NULL-terminated strings. |
||
382 | * The strings are considered equal iff they consist of the same |
||
383 | * characters on the minimum of their lengths. |
||
384 | * |
||
385 | * @param s1 First string to compare. |
||
386 | * @param s2 Second string to compare. |
||
387 | * |
||
388 | * @return 0 if the strings are equal, -1 if first is smaller, |
||
389 | * 1 if second smaller. |
||
390 | * |
||
391 | */ |
||
392 | int str_cmp(const char *s1, const char *s2) |
||
393 | { |
||
394 | wchar_t c1 = 0; |
||
395 | wchar_t c2 = 0; |
||
396 | |||
397 | size_t off1 = 0; |
||
398 | size_t off2 = 0; |
||
399 | |||
400 | while (true) { |
||
401 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
||
402 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
||
403 | |||
404 | if (c1 < c2) |
||
405 | return -1; |
||
406 | |||
407 | if (c1 > c2) |
||
408 | return 1; |
||
409 | |||
410 | if (c1 == 0 || c2 == 0) |
||
411 | break; |
||
412 | } |
||
413 | |||
414 | return 0; |
||
415 | } |
||
416 | |||
417 | /** Compare two NULL terminated strings with length limit. |
||
418 | * |
||
419 | * Do a char-by-char comparison of two NULL-terminated strings. |
||
420 | * The strings are considered equal iff they consist of the same |
||
421 | * characters on the minimum of their lengths and the length limit. |
||
422 | * |
||
423 | * @param s1 First string to compare. |
||
424 | * @param s2 Second string to compare. |
||
425 | * @param max_len Maximum number of characters to consider. |
||
426 | * |
||
427 | * @return 0 if the strings are equal, -1 if first is smaller, |
||
428 | * 1 if second smaller. |
||
429 | * |
||
430 | */ |
||
431 | int str_lcmp(const char *s1, const char *s2, count_t max_len) |
||
432 | { |
||
433 | wchar_t c1 = 0; |
||
434 | wchar_t c2 = 0; |
||
435 | |||
436 | size_t off1 = 0; |
||
437 | size_t off2 = 0; |
||
438 | |||
439 | count_t len = 0; |
||
440 | |||
441 | while (true) { |
||
442 | if (len >= max_len) |
||
443 | break; |
||
444 | |||
445 | c1 = str_decode(s1, &off1, STR_NO_LIMIT); |
||
446 | c2 = str_decode(s2, &off2, STR_NO_LIMIT); |
||
447 | |||
448 | if (c1 < c2) |
||
449 | return -1; |
||
450 | |||
451 | if (c1 > c2) |
||
452 | return 1; |
||
453 | |||
454 | if (c1 == 0 || c2 == 0) |
||
455 | break; |
||
456 | |||
457 | ++len; |
||
458 | } |
||
459 | |||
460 | return 0; |
||
461 | |||
462 | } |
||
463 | |||
464 | /** Copy NULL-terminated string. |
||
465 | * |
||
466 | * Copy source string @a src to destination buffer @a dst. |
||
467 | * No more than @a size bytes are written. NULL-terminator is always |
||
468 | * written after the last succesfully copied character (i.e. if the |
||
469 | * destination buffer is has at least 1 byte, it will be always |
||
470 | * NULL-terminated). |
||
471 | * |
||
472 | * @param src Source string. |
||
473 | * @param dst Destination buffer. |
||
474 | * @param count Size of the destination buffer. |
||
475 | * |
||
476 | */ |
||
477 | void str_ncpy(char *dst, const char *src, size_t size) |
||
478 | { |
||
479 | /* No space for the NULL-terminator in the buffer */ |
||
480 | if (size == 0) |
||
481 | return; |
||
482 | |||
483 | wchar_t ch; |
||
484 | size_t str_off = 0; |
||
485 | size_t dst_off = 0; |
||
486 | |||
487 | while ((ch = str_decode(src, &str_off, STR_NO_LIMIT)) != 0) { |
||
488 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
||
489 | break; |
||
490 | } |
||
491 | |||
492 | if (dst_off >= size) |
||
493 | dst[size - 1] = 0; |
||
494 | else |
||
495 | dst[dst_off] = 0; |
||
496 | } |
||
497 | |||
498 | /** Copy NULL-terminated wide string to string |
||
499 | * |
||
500 | * Copy source wide string @a src to destination buffer @a dst. |
||
501 | * No more than @a size bytes are written. NULL-terminator is always |
||
502 | * written after the last succesfully copied character (i.e. if the |
||
503 | * destination buffer is has at least 1 byte, it will be always |
||
504 | * NULL-terminated). |
||
505 | * |
||
506 | * @param src Source wide string. |
||
507 | * @param dst Destination buffer. |
||
508 | * @param count Size of the destination buffer. |
||
509 | * |
||
510 | */ |
||
511 | void wstr_nstr(char *dst, const wchar_t *src, size_t size) |
||
512 | { |
||
513 | /* No space for the NULL-terminator in the buffer */ |
||
514 | if (size == 0) |
||
515 | return; |
||
516 | |||
517 | wchar_t ch; |
||
518 | count_t src_idx = 0; |
||
519 | size_t dst_off = 0; |
||
520 | |||
521 | while ((ch = src[src_idx++]) != 0) { |
||
522 | if (chr_encode(ch, dst, &dst_off, size) != EOK) |
||
523 | break; |
||
524 | } |
||
525 | |||
526 | if (dst_off >= size) |
||
527 | dst[size - 1] = 0; |
||
528 | else |
||
529 | dst[dst_off] = 0; |
||
530 | } |
||
531 | |||
532 | /** Find first occurence of character in string. |
||
533 | * |
||
534 | * @param str String to search. |
||
535 | * @param ch Character to look for. |
||
536 | * |
||
537 | * @return Pointer to character in @a str or NULL if not found. |
||
538 | * |
||
539 | */ |
||
540 | const char *str_chr(const char *str, wchar_t ch) |
||
541 | { |
||
542 | wchar_t acc; |
||
543 | size_t off = 0; |
||
544 | |||
545 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) { |
||
546 | if (acc == ch) |
||
547 | return (str + off); |
||
548 | } |
||
549 | |||
550 | return NULL; |
||
551 | } |
||
552 | |||
553 | /** Insert a wide character into a wide string. |
||
554 | * |
||
555 | * Insert a wide character into a wide string at position |
||
556 | * @a pos. The characters after the position are shifted. |
||
557 | * |
||
558 | * @param str String to insert to. |
||
559 | * @param ch Character to insert to. |
||
560 | * @param pos Character index where to insert. |
||
561 | @ @param max_pos Characters in the buffer. |
||
562 | * |
||
563 | * @return True if the insertion was sucessful, false if the position |
||
564 | * is out of bounds. |
||
565 | * |
||
566 | */ |
||
567 | bool wstr_linsert(wchar_t *str, wchar_t ch, count_t pos, count_t max_pos) |
||
568 | { |
||
569 | count_t len = wstr_length(str); |
||
570 | |||
571 | if ((pos > len) || (pos + 1 > max_pos)) |
||
572 | return false; |
||
573 | |||
574 | count_t i; |
||
575 | for (i = len; i + 1 > pos; i--) |
||
576 | str[i + 1] = str[i]; |
||
577 | |||
578 | str[pos] = ch; |
||
579 | |||
580 | return true; |
||
581 | } |
||
582 | |||
583 | /** Remove a wide character from a wide string. |
||
584 | * |
||
585 | * Remove a wide character from a wide string at position |
||
586 | * @a pos. The characters after the position are shifted. |
||
587 | * |
||
588 | * @param str String to remove from. |
||
589 | * @param pos Character index to remove. |
||
590 | * |
||
591 | * @return True if the removal was sucessful, false if the position |
||
592 | * is out of bounds. |
||
593 | * |
||
594 | */ |
||
595 | bool wstr_remove(wchar_t *str, count_t pos) |
||
596 | { |
||
597 | count_t len = wstr_length(str); |
||
598 | |||
599 | if (pos >= len) |
||
600 | return false; |
||
601 | |||
602 | count_t i; |
||
603 | for (i = pos + 1; i <= len; i++) |
||
604 | str[i - 1] = str[i]; |
||
605 | |||
606 | return true; |
||
607 | } |
||
608 | |||
1314 | cejka | 609 | /** Count the number of characters in the string, not including terminating 0. |
3261 | jermar | 610 | * |
611 | * @param str String. |
||
612 | * @return Number of characters in string. |
||
1314 | cejka | 613 | */ |
1173 | cejka | 614 | size_t strlen(const char *str) |
615 | { |
||
1197 | cejka | 616 | size_t counter = 0; |
1173 | cejka | 617 | |
1719 | decky | 618 | while (str[counter] != 0) |
1173 | cejka | 619 | counter++; |
620 | |||
621 | return counter; |
||
622 | } |
||
1314 | cejka | 623 | |
1719 | decky | 624 | int strcmp(const char *a, const char *b) |
1319 | vana | 625 | { |
1719 | decky | 626 | int c = 0; |
1319 | vana | 627 | |
1719 | decky | 628 | while (a[c] && b[c] && (!(a[c] - b[c]))) |
629 | c++; |
||
1319 | vana | 630 | |
1719 | decky | 631 | return (a[c] - b[c]); |
1319 | vana | 632 | } |
633 | |||
2640 | cejka | 634 | int strncmp(const char *a, const char *b, size_t n) |
635 | { |
||
636 | size_t c = 0; |
||
1319 | vana | 637 | |
2640 | cejka | 638 | while (c < n && a[c] && b[c] && (!(a[c] - b[c]))) |
639 | c++; |
||
640 | |||
641 | return ( c < n ? a[c] - b[c] : 0); |
||
642 | |||
643 | } |
||
644 | |||
3271 | jermar | 645 | int stricmp(const char *a, const char *b) |
646 | { |
||
647 | int c = 0; |
||
648 | |||
649 | while (a[c] && b[c] && (!(tolower(a[c]) - tolower(b[c])))) |
||
650 | c++; |
||
651 | |||
652 | return (tolower(a[c]) - tolower(b[c])); |
||
653 | } |
||
654 | |||
3261 | jermar | 655 | /** Return pointer to the first occurence of character c in string. |
656 | * |
||
657 | * @param str Scanned string. |
||
658 | * @param c Searched character (taken as one byte). |
||
659 | * @return Pointer to the matched character or NULL if it is not |
||
660 | * found in given string. |
||
1314 | cejka | 661 | */ |
662 | char *strchr(const char *str, int c) |
||
663 | { |
||
664 | while (*str != '\0') { |
||
1719 | decky | 665 | if (*str == (char) c) |
666 | return (char *) str; |
||
1314 | cejka | 667 | str++; |
668 | } |
||
669 | |||
670 | return NULL; |
||
671 | } |
||
672 | |||
3261 | jermar | 673 | /** Return pointer to the last occurence of character c in string. |
674 | * |
||
675 | * @param str Scanned string. |
||
676 | * @param c Searched character (taken as one byte). |
||
677 | * @return Pointer to the matched character or NULL if it is not |
||
678 | * found in given string. |
||
1314 | cejka | 679 | */ |
680 | char *strrchr(const char *str, int c) |
||
681 | { |
||
682 | char *retval = NULL; |
||
683 | |||
684 | while (*str != '\0') { |
||
1719 | decky | 685 | if (*str == (char) c) |
686 | retval = (char *) str; |
||
1314 | cejka | 687 | str++; |
688 | } |
||
689 | |||
1719 | decky | 690 | return (char *) retval; |
1314 | cejka | 691 | } |
692 | |||
693 | /** Convert string to a number. |
||
694 | * Core of strtol and strtoul functions. |
||
3261 | jermar | 695 | * |
696 | * @param nptr Pointer to string. |
||
697 | * @param endptr If not NULL, function stores here pointer to the first |
||
698 | * invalid character. |
||
699 | * @param base Zero or number between 2 and 36 inclusive. |
||
700 | * @param sgn It's set to 1 if minus found. |
||
701 | * @return Result of conversion. |
||
1314 | cejka | 702 | */ |
3261 | jermar | 703 | static unsigned long |
704 | _strtoul(const char *nptr, char **endptr, int base, char *sgn) |
||
1314 | cejka | 705 | { |
706 | unsigned char c; |
||
707 | unsigned long result = 0; |
||
708 | unsigned long a, b; |
||
709 | const char *str = nptr; |
||
710 | const char *tmpptr; |
||
711 | |||
712 | while (isspace(*str)) |
||
713 | str++; |
||
714 | |||
715 | if (*str == '-') { |
||
716 | *sgn = 1; |
||
717 | ++str; |
||
718 | } else if (*str == '+') |
||
719 | ++str; |
||
720 | |||
721 | if (base) { |
||
722 | if ((base == 1) || (base > 36)) { |
||
723 | /* FIXME: set errno to EINVAL */ |
||
724 | return 0; |
||
725 | } |
||
3261 | jermar | 726 | if ((base == 16) && (*str == '0') && ((str[1] == 'x') || |
727 | (str[1] == 'X'))) { |
||
1314 | cejka | 728 | str += 2; |
729 | } |
||
730 | } else { |
||
731 | base = 10; |
||
732 | |||
733 | if (*str == '0') { |
||
734 | base = 8; |
||
735 | if ((str[1] == 'X') || (str[1] == 'x')) { |
||
736 | base = 16; |
||
737 | str += 2; |
||
738 | } |
||
739 | } |
||
740 | } |
||
741 | |||
742 | tmpptr = str; |
||
743 | |||
744 | while (*str) { |
||
745 | c = *str; |
||
3261 | jermar | 746 | c = (c >= 'a' ? c - 'a' + 10 : (c >= 'A' ? c - 'A' + 10 : |
747 | (c <= '9' ? c - '0' : 0xff))); |
||
1314 | cejka | 748 | if (c > base) { |
749 | break; |
||
750 | } |
||
751 | |||
752 | a = (result & 0xff) * base + c; |
||
753 | b = (result >> 8) * base + (a >> 8); |
||
754 | |||
755 | if (b > (ULONG_MAX >> 8)) { |
||
756 | /* overflow */ |
||
757 | /* FIXME: errno = ERANGE*/ |
||
758 | return ULONG_MAX; |
||
759 | } |
||
760 | |||
761 | result = (b << 8) + (a & 0xff); |
||
762 | ++str; |
||
763 | } |
||
764 | |||
765 | if (str == tmpptr) { |
||
3261 | jermar | 766 | /* |
767 | * No number was found => first invalid character is the first |
||
768 | * character of the string. |
||
769 | */ |
||
1314 | cejka | 770 | /* FIXME: set errno to EINVAL */ |
771 | str = nptr; |
||
772 | result = 0; |
||
773 | } |
||
774 | |||
775 | if (endptr) |
||
1719 | decky | 776 | *endptr = (char *) str; |
1314 | cejka | 777 | |
778 | if (nptr == str) { |
||
779 | /*FIXME: errno = EINVAL*/ |
||
780 | return 0; |
||
781 | } |
||
782 | |||
783 | return result; |
||
784 | } |
||
785 | |||
786 | /** Convert initial part of string to long int according to given base. |
||
3261 | jermar | 787 | * The number may begin with an arbitrary number of whitespaces followed by |
788 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
||
789 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
||
790 | * and the number begin with a zero, number will be taken as octal one (as with |
||
791 | * base 8). Otherwise the base 0 is taken as decimal. |
||
792 | * |
||
793 | * @param nptr Pointer to string. |
||
794 | * @param endptr If not NULL, function stores here pointer to the first |
||
795 | * invalid character. |
||
796 | * @param base Zero or number between 2 and 36 inclusive. |
||
797 | * @return Result of conversion. |
||
1314 | cejka | 798 | */ |
799 | long int strtol(const char *nptr, char **endptr, int base) |
||
800 | { |
||
801 | char sgn = 0; |
||
802 | unsigned long number = 0; |
||
803 | |||
804 | number = _strtoul(nptr, endptr, base, &sgn); |
||
805 | |||
806 | if (number > LONG_MAX) { |
||
1719 | decky | 807 | if ((sgn) && (number == (unsigned long) (LONG_MAX) + 1)) { |
1314 | cejka | 808 | /* FIXME: set 0 to errno */ |
809 | return number; |
||
810 | } |
||
811 | /* FIXME: set ERANGE to errno */ |
||
1719 | decky | 812 | return (sgn ? LONG_MIN : LONG_MAX); |
1314 | cejka | 813 | } |
814 | |||
1719 | decky | 815 | return (sgn ? -number : number); |
1314 | cejka | 816 | } |
817 | |||
818 | |||
819 | /** Convert initial part of string to unsigned long according to given base. |
||
3261 | jermar | 820 | * The number may begin with an arbitrary number of whitespaces followed by |
821 | * optional sign (`+' or `-'). If the base is 0 or 16, the prefix `0x' may be |
||
822 | * inserted and the number will be taken as hexadecimal one. If the base is 0 |
||
823 | * and the number begin with a zero, number will be taken as octal one (as with |
||
824 | * base 8). Otherwise the base 0 is taken as decimal. |
||
825 | * |
||
826 | * @param nptr Pointer to string. |
||
827 | * @param endptr If not NULL, function stores here pointer to the first |
||
828 | * invalid character |
||
829 | * @param base Zero or number between 2 and 36 inclusive. |
||
830 | * @return Result of conversion. |
||
1314 | cejka | 831 | */ |
832 | unsigned long strtoul(const char *nptr, char **endptr, int base) |
||
833 | { |
||
834 | char sgn = 0; |
||
835 | unsigned long number = 0; |
||
836 | |||
837 | number = _strtoul(nptr, endptr, base, &sgn); |
||
838 | |||
1719 | decky | 839 | return (sgn ? -number : number); |
1314 | cejka | 840 | } |
1472 | palkovsky | 841 | |
842 | char *strcpy(char *dest, const char *src) |
||
843 | { |
||
1719 | decky | 844 | char *orig = dest; |
845 | |||
2754 | jermar | 846 | while ((*(dest++) = *(src++))) |
847 | ; |
||
1719 | decky | 848 | return orig; |
1472 | palkovsky | 849 | } |
850 | |||
851 | char *strncpy(char *dest, const char *src, size_t n) |
||
852 | { |
||
1719 | decky | 853 | char *orig = dest; |
854 | |||
2754 | jermar | 855 | while ((*(dest++) = *(src++)) && --n) |
856 | ; |
||
1719 | decky | 857 | return orig; |
1472 | palkovsky | 858 | } |
1653 | cejka | 859 | |
2754 | jermar | 860 | char *strcat(char *dest, const char *src) |
861 | { |
||
862 | char *orig = dest; |
||
863 | while (*dest++) |
||
864 | ; |
||
865 | --dest; |
||
866 | while ((*dest++ = *src++)) |
||
867 | ; |
||
868 | return orig; |
||
869 | } |
||
870 | |||
3238 | jermar | 871 | char * strdup(const char *s1) |
872 | { |
||
873 | size_t len = strlen(s1) + 1; |
||
874 | void *ret = malloc(len); |
||
875 | |||
876 | if (ret == NULL) |
||
877 | return (char *) NULL; |
||
878 | |||
879 | return (char *) memcpy(ret, s1, len); |
||
880 | } |
||
881 | |||
3730 | svoboda | 882 | char *strtok(char *s, const char *delim) |
3427 | post | 883 | { |
3730 | svoboda | 884 | static char *next; |
3427 | post | 885 | |
3730 | svoboda | 886 | return strtok_r(s, delim, &next); |
887 | } |
||
3427 | post | 888 | |
3730 | svoboda | 889 | char *strtok_r(char *s, const char *delim, char **next) |
890 | { |
||
891 | char *start, *end; |
||
3427 | post | 892 | |
3730 | svoboda | 893 | if (s == NULL) |
894 | s = *next; |
||
3427 | post | 895 | |
3730 | svoboda | 896 | /* Skip over leading delimiters. */ |
897 | while (*s && (strchr(delim, *s) != NULL)) ++s; |
||
898 | start = s; |
||
3427 | post | 899 | |
3730 | svoboda | 900 | /* Skip over token characters. */ |
901 | while (*s && (strchr(delim, *s) == NULL)) ++s; |
||
902 | end = s; |
||
903 | *next = (*s ? s + 1 : s); |
||
904 | |||
905 | if (start == end) { |
||
906 | return NULL; /* No more tokens. */ |
||
3427 | post | 907 | } |
908 | |||
3730 | svoboda | 909 | /* Overwrite delimiter with NULL terminator. */ |
910 | *end = '\0'; |
||
911 | return start; |
||
3427 | post | 912 | } |
913 | |||
1719 | decky | 914 | /** @} |
1653 | cejka | 915 | */ |