1 | /*
|
---|
2 | * Copyright (c) 2001-2004 Jakub Jermar
|
---|
3 | * All rights reserved.
|
---|
4 | *
|
---|
5 | * Redistribution and use in source and binary forms, with or without
|
---|
6 | * modification, are permitted provided that the following conditions
|
---|
7 | * are met:
|
---|
8 | *
|
---|
9 | * - Redistributions of source code must retain the above copyright
|
---|
10 | * notice, this list of conditions and the following disclaimer.
|
---|
11 | * - Redistributions in binary form must reproduce the above copyright
|
---|
12 | * notice, this list of conditions and the following disclaimer in the
|
---|
13 | * documentation and/or other materials provided with the distribution.
|
---|
14 | * - The name of the author may not be used to endorse or promote products
|
---|
15 | * derived from this software without specific prior written permission.
|
---|
16 | *
|
---|
17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
---|
18 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
---|
19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
---|
20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
---|
21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
---|
22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
---|
23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
---|
24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
---|
25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
---|
26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
---|
27 | */
|
---|
28 |
|
---|
29 | /** @addtogroup generic
|
---|
30 | * @{
|
---|
31 | */
|
---|
32 |
|
---|
33 | /**
|
---|
34 | * @file
|
---|
35 | * @brief String functions.
|
---|
36 | *
|
---|
37 | * Strings and characters use the Universal Character Set (UCS). The standard
|
---|
38 | * strings, called just strings are encoded in UTF-8. Wide strings (encoded
|
---|
39 | * in UTF-32) are supported to a limited degree. A single character is
|
---|
40 | * represented as wchar_t.@n
|
---|
41 | *
|
---|
42 | * Overview of the terminology:@n
|
---|
43 | *
|
---|
44 | * Term Meaning
|
---|
45 | * -------------------- ----------------------------------------------------
|
---|
46 | * byte 8 bits stored in uint8_t (unsigned 8 bit integer)
|
---|
47 | *
|
---|
48 | * character UTF-32 encoded Unicode character, stored in wchar_t
|
---|
49 | * (signed 32 bit integer), code points 0 .. 1114111
|
---|
50 | * are valid
|
---|
51 | *
|
---|
52 | * ASCII character 7 bit encoded ASCII character, stored in char
|
---|
53 | * (usually signed 8 bit integer), code points 0 .. 127
|
---|
54 | * are valid
|
---|
55 | *
|
---|
56 | * string UTF-8 encoded NULL-terminated Unicode string, char *
|
---|
57 | *
|
---|
58 | * wide string UTF-32 encoded NULL-terminated Unicode string,
|
---|
59 | * wchar_t *
|
---|
60 | *
|
---|
61 | * [wide] string size number of BYTES in a [wide] string (excluding
|
---|
62 | * the NULL-terminator), size_t
|
---|
63 | *
|
---|
64 | * [wide] string length number of CHARACTERS in a [wide] string (excluding
|
---|
65 | * the NULL-terminator), size_t
|
---|
66 | *
|
---|
67 | * [wide] string width number of display cells on a monospace display taken
|
---|
68 | * by a [wide] string, size_t
|
---|
69 | *
|
---|
70 | *
|
---|
71 | * Overview of string metrics:@n
|
---|
72 | *
|
---|
73 | * Metric Abbrev. Type Meaning
|
---|
74 | * ------ ------ ------ -------------------------------------------------
|
---|
75 | * size n size_t number of BYTES in a string (excluding the
|
---|
76 | * NULL-terminator)
|
---|
77 | *
|
---|
78 | * length l size_t number of CHARACTERS in a string (excluding the
|
---|
79 | * null terminator)
|
---|
80 | *
|
---|
81 | * width w size_t number of display cells on a monospace display
|
---|
82 | * taken by a string
|
---|
83 | *
|
---|
84 | *
|
---|
85 | * Function naming prefixes:@n
|
---|
86 | *
|
---|
87 | * chr_ operate on characters
|
---|
88 | * ascii_ operate on ASCII characters
|
---|
89 | * str_ operate on strings
|
---|
90 | * wstr_ operate on wide strings
|
---|
91 | *
|
---|
92 | * [w]str_[n|l|w] operate on a prefix limited by size, length
|
---|
93 | * or width
|
---|
94 | *
|
---|
95 | *
|
---|
96 | * A specific character inside a [wide] string can be referred to by:@n
|
---|
97 | *
|
---|
98 | * pointer (char *, wchar_t *)
|
---|
99 | * byte offset (size_t)
|
---|
100 | * character index (size_t)
|
---|
101 | *
|
---|
102 | */
|
---|
103 |
|
---|
104 | #include <str.h>
|
---|
105 | #include <print.h>
|
---|
106 | #include <cpu.h>
|
---|
107 | #include <arch/asm.h>
|
---|
108 | #include <arch.h>
|
---|
109 | #include <errno.h>
|
---|
110 | #include <align.h>
|
---|
111 | #include <debug.h>
|
---|
112 | #include <macros.h>
|
---|
113 |
|
---|
114 | /** Check the condition if wchar_t is signed */
|
---|
115 | #ifdef WCHAR_IS_UNSIGNED
|
---|
116 | #define WCHAR_SIGNED_CHECK(cond) (true)
|
---|
117 | #else
|
---|
118 | #define WCHAR_SIGNED_CHECK(cond) (cond)
|
---|
119 | #endif
|
---|
120 |
|
---|
121 | /** Byte mask consisting of lowest @n bits (out of 8) */
|
---|
122 | #define LO_MASK_8(n) ((uint8_t) ((1 << (n)) - 1))
|
---|
123 |
|
---|
124 | /** Byte mask consisting of lowest @n bits (out of 32) */
|
---|
125 | #define LO_MASK_32(n) ((uint32_t) ((1 << (n)) - 1))
|
---|
126 |
|
---|
127 | /** Byte mask consisting of highest @n bits (out of 8) */
|
---|
128 | #define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
|
---|
129 |
|
---|
130 | /** Number of data bits in a UTF-8 continuation byte */
|
---|
131 | #define CONT_BITS 6
|
---|
132 |
|
---|
133 | /** Decode a single character from a string.
|
---|
134 | *
|
---|
135 | * Decode a single character from a string of size @a size. Decoding starts
|
---|
136 | * at @a offset and this offset is moved to the beginning of the next
|
---|
137 | * character. In case of decoding error, offset generally advances at least
|
---|
138 | * by one. However, offset is never moved beyond size.
|
---|
139 | *
|
---|
140 | * @param str String (not necessarily NULL-terminated).
|
---|
141 | * @param offset Byte offset in string where to start decoding.
|
---|
142 | * @param size Size of the string (in bytes).
|
---|
143 | *
|
---|
144 | * @return Value of decoded character, U_SPECIAL on decoding error or
|
---|
145 | * NULL if attempt to decode beyond @a size.
|
---|
146 | *
|
---|
147 | */
|
---|
148 | wchar_t str_decode(const char *str, size_t *offset, size_t size)
|
---|
149 | {
|
---|
150 | if (*offset + 1 > size)
|
---|
151 | return 0;
|
---|
152 |
|
---|
153 | /* First byte read from string */
|
---|
154 | uint8_t b0 = (uint8_t) str[(*offset)++];
|
---|
155 |
|
---|
156 | /* Determine code length */
|
---|
157 |
|
---|
158 | unsigned int b0_bits; /* Data bits in first byte */
|
---|
159 | unsigned int cbytes; /* Number of continuation bytes */
|
---|
160 |
|
---|
161 | if ((b0 & 0x80) == 0) {
|
---|
162 | /* 0xxxxxxx (Plain ASCII) */
|
---|
163 | b0_bits = 7;
|
---|
164 | cbytes = 0;
|
---|
165 | } else if ((b0 & 0xe0) == 0xc0) {
|
---|
166 | /* 110xxxxx 10xxxxxx */
|
---|
167 | b0_bits = 5;
|
---|
168 | cbytes = 1;
|
---|
169 | } else if ((b0 & 0xf0) == 0xe0) {
|
---|
170 | /* 1110xxxx 10xxxxxx 10xxxxxx */
|
---|
171 | b0_bits = 4;
|
---|
172 | cbytes = 2;
|
---|
173 | } else if ((b0 & 0xf8) == 0xf0) {
|
---|
174 | /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
|
---|
175 | b0_bits = 3;
|
---|
176 | cbytes = 3;
|
---|
177 | } else {
|
---|
178 | /* 10xxxxxx -- unexpected continuation byte */
|
---|
179 | return U_SPECIAL;
|
---|
180 | }
|
---|
181 |
|
---|
182 | if (*offset + cbytes > size)
|
---|
183 | return U_SPECIAL;
|
---|
184 |
|
---|
185 | wchar_t ch = b0 & LO_MASK_8(b0_bits);
|
---|
186 |
|
---|
187 | /* Decode continuation bytes */
|
---|
188 | while (cbytes > 0) {
|
---|
189 | uint8_t b = (uint8_t) str[(*offset)++];
|
---|
190 |
|
---|
191 | /* Must be 10xxxxxx */
|
---|
192 | if ((b & 0xc0) != 0x80)
|
---|
193 | return U_SPECIAL;
|
---|
194 |
|
---|
195 | /* Shift data bits to ch */
|
---|
196 | ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS));
|
---|
197 | cbytes--;
|
---|
198 | }
|
---|
199 |
|
---|
200 | return ch;
|
---|
201 | }
|
---|
202 |
|
---|
203 | /** Encode a single character to string representation.
|
---|
204 | *
|
---|
205 | * Encode a single character to string representation (i.e. UTF-8) and store
|
---|
206 | * it into a buffer at @a offset. Encoding starts at @a offset and this offset
|
---|
207 | * is moved to the position where the next character can be written to.
|
---|
208 | *
|
---|
209 | * @param ch Input character.
|
---|
210 | * @param str Output buffer.
|
---|
211 | * @param offset Byte offset where to start writing.
|
---|
212 | * @param size Size of the output buffer (in bytes).
|
---|
213 | *
|
---|
214 | * @return EOK if the character was encoded successfully, EOVERFLOW if there
|
---|
215 | * was not enough space in the output buffer or EINVAL if the character
|
---|
216 | * code was invalid.
|
---|
217 | */
|
---|
218 | int chr_encode(const wchar_t ch, char *str, size_t *offset, size_t size)
|
---|
219 | {
|
---|
220 | if (*offset >= size)
|
---|
221 | return EOVERFLOW;
|
---|
222 |
|
---|
223 | if (!chr_check(ch))
|
---|
224 | return EINVAL;
|
---|
225 |
|
---|
226 | /* Unsigned version of ch (bit operations should only be done
|
---|
227 | on unsigned types). */
|
---|
228 | uint32_t cc = (uint32_t) ch;
|
---|
229 |
|
---|
230 | /* Determine how many continuation bytes are needed */
|
---|
231 |
|
---|
232 | unsigned int b0_bits; /* Data bits in first byte */
|
---|
233 | unsigned int cbytes; /* Number of continuation bytes */
|
---|
234 |
|
---|
235 | if ((cc & ~LO_MASK_32(7)) == 0) {
|
---|
236 | b0_bits = 7;
|
---|
237 | cbytes = 0;
|
---|
238 | } else if ((cc & ~LO_MASK_32(11)) == 0) {
|
---|
239 | b0_bits = 5;
|
---|
240 | cbytes = 1;
|
---|
241 | } else if ((cc & ~LO_MASK_32(16)) == 0) {
|
---|
242 | b0_bits = 4;
|
---|
243 | cbytes = 2;
|
---|
244 | } else if ((cc & ~LO_MASK_32(21)) == 0) {
|
---|
245 | b0_bits = 3;
|
---|
246 | cbytes = 3;
|
---|
247 | } else {
|
---|
248 | /* Codes longer than 21 bits are not supported */
|
---|
249 | return EINVAL;
|
---|
250 | }
|
---|
251 |
|
---|
252 | /* Check for available space in buffer */
|
---|
253 | if (*offset + cbytes >= size)
|
---|
254 | return EOVERFLOW;
|
---|
255 |
|
---|
256 | /* Encode continuation bytes */
|
---|
257 | unsigned int i;
|
---|
258 | for (i = cbytes; i > 0; i--) {
|
---|
259 | str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS));
|
---|
260 | cc = cc >> CONT_BITS;
|
---|
261 | }
|
---|
262 |
|
---|
263 | /* Encode first byte */
|
---|
264 | str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1);
|
---|
265 |
|
---|
266 | /* Advance offset */
|
---|
267 | *offset += cbytes + 1;
|
---|
268 |
|
---|
269 | return EOK;
|
---|
270 | }
|
---|
271 |
|
---|
272 | /** Get size of string.
|
---|
273 | *
|
---|
274 | * Get the number of bytes which are used by the string @a str (excluding the
|
---|
275 | * NULL-terminator).
|
---|
276 | *
|
---|
277 | * @param str String to consider.
|
---|
278 | *
|
---|
279 | * @return Number of bytes used by the string
|
---|
280 | *
|
---|
281 | */
|
---|
282 | size_t str_size(const char *str)
|
---|
283 | {
|
---|
284 | size_t size = 0;
|
---|
285 |
|
---|
286 | while (*str++ != 0)
|
---|
287 | size++;
|
---|
288 |
|
---|
289 | return size;
|
---|
290 | }
|
---|
291 |
|
---|
292 | /** Get size of wide string.
|
---|
293 | *
|
---|
294 | * Get the number of bytes which are used by the wide string @a str (excluding the
|
---|
295 | * NULL-terminator).
|
---|
296 | *
|
---|
297 | * @param str Wide string to consider.
|
---|
298 | *
|
---|
299 | * @return Number of bytes used by the wide string
|
---|
300 | *
|
---|
301 | */
|
---|
302 | size_t wstr_size(const wchar_t *str)
|
---|
303 | {
|
---|
304 | return (wstr_length(str) * sizeof(wchar_t));
|
---|
305 | }
|
---|
306 |
|
---|
307 | /** Get size of string with length limit.
|
---|
308 | *
|
---|
309 | * Get the number of bytes which are used by up to @a max_len first
|
---|
310 | * characters in the string @a str. If @a max_len is greater than
|
---|
311 | * the length of @a str, the entire string is measured (excluding the
|
---|
312 | * NULL-terminator).
|
---|
313 | *
|
---|
314 | * @param str String to consider.
|
---|
315 | * @param max_len Maximum number of characters to measure.
|
---|
316 | *
|
---|
317 | * @return Number of bytes used by the characters.
|
---|
318 | *
|
---|
319 | */
|
---|
320 | size_t str_lsize(const char *str, size_t max_len)
|
---|
321 | {
|
---|
322 | size_t len = 0;
|
---|
323 | size_t offset = 0;
|
---|
324 |
|
---|
325 | while (len < max_len) {
|
---|
326 | if (str_decode(str, &offset, STR_NO_LIMIT) == 0)
|
---|
327 | break;
|
---|
328 |
|
---|
329 | len++;
|
---|
330 | }
|
---|
331 |
|
---|
332 | return offset;
|
---|
333 | }
|
---|
334 |
|
---|
335 | /** Get size of wide string with length limit.
|
---|
336 | *
|
---|
337 | * Get the number of bytes which are used by up to @a max_len first
|
---|
338 | * wide characters in the wide string @a str. If @a max_len is greater than
|
---|
339 | * the length of @a str, the entire wide string is measured (excluding the
|
---|
340 | * NULL-terminator).
|
---|
341 | *
|
---|
342 | * @param str Wide string to consider.
|
---|
343 | * @param max_len Maximum number of wide characters to measure.
|
---|
344 | *
|
---|
345 | * @return Number of bytes used by the wide characters.
|
---|
346 | *
|
---|
347 | */
|
---|
348 | size_t wstr_lsize(const wchar_t *str, size_t max_len)
|
---|
349 | {
|
---|
350 | return (wstr_nlength(str, max_len * sizeof(wchar_t)) * sizeof(wchar_t));
|
---|
351 | }
|
---|
352 |
|
---|
353 | /** Get number of characters in a string.
|
---|
354 | *
|
---|
355 | * @param str NULL-terminated string.
|
---|
356 | *
|
---|
357 | * @return Number of characters in string.
|
---|
358 | *
|
---|
359 | */
|
---|
360 | size_t str_length(const char *str)
|
---|
361 | {
|
---|
362 | size_t len = 0;
|
---|
363 | size_t offset = 0;
|
---|
364 |
|
---|
365 | while (str_decode(str, &offset, STR_NO_LIMIT) != 0)
|
---|
366 | len++;
|
---|
367 |
|
---|
368 | return len;
|
---|
369 | }
|
---|
370 |
|
---|
371 | /** Get number of characters in a wide string.
|
---|
372 | *
|
---|
373 | * @param str NULL-terminated wide string.
|
---|
374 | *
|
---|
375 | * @return Number of characters in @a str.
|
---|
376 | *
|
---|
377 | */
|
---|
378 | size_t wstr_length(const wchar_t *wstr)
|
---|
379 | {
|
---|
380 | size_t len = 0;
|
---|
381 |
|
---|
382 | while (*wstr++ != 0)
|
---|
383 | len++;
|
---|
384 |
|
---|
385 | return len;
|
---|
386 | }
|
---|
387 |
|
---|
388 | /** Get number of characters in a string with size limit.
|
---|
389 | *
|
---|
390 | * @param str NULL-terminated string.
|
---|
391 | * @param size Maximum number of bytes to consider.
|
---|
392 | *
|
---|
393 | * @return Number of characters in string.
|
---|
394 | *
|
---|
395 | */
|
---|
396 | size_t str_nlength(const char *str, size_t size)
|
---|
397 | {
|
---|
398 | size_t len = 0;
|
---|
399 | size_t offset = 0;
|
---|
400 |
|
---|
401 | while (str_decode(str, &offset, size) != 0)
|
---|
402 | len++;
|
---|
403 |
|
---|
404 | return len;
|
---|
405 | }
|
---|
406 |
|
---|
407 | /** Get number of characters in a string with size limit.
|
---|
408 | *
|
---|
409 | * @param str NULL-terminated string.
|
---|
410 | * @param size Maximum number of bytes to consider.
|
---|
411 | *
|
---|
412 | * @return Number of characters in string.
|
---|
413 | *
|
---|
414 | */
|
---|
415 | size_t wstr_nlength(const wchar_t *str, size_t size)
|
---|
416 | {
|
---|
417 | size_t len = 0;
|
---|
418 | size_t limit = ALIGN_DOWN(size, sizeof(wchar_t));
|
---|
419 | size_t offset = 0;
|
---|
420 |
|
---|
421 | while ((offset < limit) && (*str++ != 0)) {
|
---|
422 | len++;
|
---|
423 | offset += sizeof(wchar_t);
|
---|
424 | }
|
---|
425 |
|
---|
426 | return len;
|
---|
427 | }
|
---|
428 |
|
---|
429 | /** Check whether character is plain ASCII.
|
---|
430 | *
|
---|
431 | * @return True if character is plain ASCII.
|
---|
432 | *
|
---|
433 | */
|
---|
434 | bool ascii_check(wchar_t ch)
|
---|
435 | {
|
---|
436 | if (WCHAR_SIGNED_CHECK(ch >= 0) && (ch <= 127))
|
---|
437 | return true;
|
---|
438 |
|
---|
439 | return false;
|
---|
440 | }
|
---|
441 |
|
---|
442 | /** Check whether character is valid
|
---|
443 | *
|
---|
444 | * @return True if character is a valid Unicode code point.
|
---|
445 | *
|
---|
446 | */
|
---|
447 | bool chr_check(wchar_t ch)
|
---|
448 | {
|
---|
449 | if (WCHAR_SIGNED_CHECK(ch >= 0) && (ch <= 1114111))
|
---|
450 | return true;
|
---|
451 |
|
---|
452 | return false;
|
---|
453 | }
|
---|
454 |
|
---|
455 | /** Compare two NULL terminated strings.
|
---|
456 | *
|
---|
457 | * Do a char-by-char comparison of two NULL-terminated strings.
|
---|
458 | * The strings are considered equal iff they consist of the same
|
---|
459 | * characters on the minimum of their lengths.
|
---|
460 | *
|
---|
461 | * @param s1 First string to compare.
|
---|
462 | * @param s2 Second string to compare.
|
---|
463 | *
|
---|
464 | * @return 0 if the strings are equal, -1 if first is smaller,
|
---|
465 | * 1 if second smaller.
|
---|
466 | *
|
---|
467 | */
|
---|
468 | int str_cmp(const char *s1, const char *s2)
|
---|
469 | {
|
---|
470 | wchar_t c1 = 0;
|
---|
471 | wchar_t c2 = 0;
|
---|
472 |
|
---|
473 | size_t off1 = 0;
|
---|
474 | size_t off2 = 0;
|
---|
475 |
|
---|
476 | while (true) {
|
---|
477 | c1 = str_decode(s1, &off1, STR_NO_LIMIT);
|
---|
478 | c2 = str_decode(s2, &off2, STR_NO_LIMIT);
|
---|
479 |
|
---|
480 | if (c1 < c2)
|
---|
481 | return -1;
|
---|
482 |
|
---|
483 | if (c1 > c2)
|
---|
484 | return 1;
|
---|
485 |
|
---|
486 | if (c1 == 0 || c2 == 0)
|
---|
487 | break;
|
---|
488 | }
|
---|
489 |
|
---|
490 | return 0;
|
---|
491 | }
|
---|
492 |
|
---|
493 | /** Compare two NULL terminated strings with length limit.
|
---|
494 | *
|
---|
495 | * Do a char-by-char comparison of two NULL-terminated strings.
|
---|
496 | * The strings are considered equal iff they consist of the same
|
---|
497 | * characters on the minimum of their lengths and the length limit.
|
---|
498 | *
|
---|
499 | * @param s1 First string to compare.
|
---|
500 | * @param s2 Second string to compare.
|
---|
501 | * @param max_len Maximum number of characters to consider.
|
---|
502 | *
|
---|
503 | * @return 0 if the strings are equal, -1 if first is smaller,
|
---|
504 | * 1 if second smaller.
|
---|
505 | *
|
---|
506 | */
|
---|
507 | int str_lcmp(const char *s1, const char *s2, size_t max_len)
|
---|
508 | {
|
---|
509 | wchar_t c1 = 0;
|
---|
510 | wchar_t c2 = 0;
|
---|
511 |
|
---|
512 | size_t off1 = 0;
|
---|
513 | size_t off2 = 0;
|
---|
514 |
|
---|
515 | size_t len = 0;
|
---|
516 |
|
---|
517 | while (true) {
|
---|
518 | if (len >= max_len)
|
---|
519 | break;
|
---|
520 |
|
---|
521 | c1 = str_decode(s1, &off1, STR_NO_LIMIT);
|
---|
522 | c2 = str_decode(s2, &off2, STR_NO_LIMIT);
|
---|
523 |
|
---|
524 | if (c1 < c2)
|
---|
525 | return -1;
|
---|
526 |
|
---|
527 | if (c1 > c2)
|
---|
528 | return 1;
|
---|
529 |
|
---|
530 | if (c1 == 0 || c2 == 0)
|
---|
531 | break;
|
---|
532 |
|
---|
533 | ++len;
|
---|
534 | }
|
---|
535 |
|
---|
536 | return 0;
|
---|
537 |
|
---|
538 | }
|
---|
539 |
|
---|
540 | /** Copy string.
|
---|
541 | *
|
---|
542 | * Copy source string @a src to destination buffer @a dest.
|
---|
543 | * No more than @a size bytes are written. If the size of the output buffer
|
---|
544 | * is at least one byte, the output string will always be well-formed, i.e.
|
---|
545 | * null-terminated and containing only complete characters.
|
---|
546 | *
|
---|
547 | * @param dest Destination buffer.
|
---|
548 | * @param count Size of the destination buffer (must be > 0).
|
---|
549 | * @param src Source string.
|
---|
550 | *
|
---|
551 | */
|
---|
552 | void str_cpy(char *dest, size_t size, const char *src)
|
---|
553 | {
|
---|
554 | /* There must be space for a null terminator in the buffer. */
|
---|
555 | ASSERT(size > 0);
|
---|
556 | ASSERT(src != NULL);
|
---|
557 |
|
---|
558 | size_t src_off = 0;
|
---|
559 | size_t dest_off = 0;
|
---|
560 |
|
---|
561 | wchar_t ch;
|
---|
562 | while ((ch = str_decode(src, &src_off, STR_NO_LIMIT)) != 0) {
|
---|
563 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
564 | break;
|
---|
565 | }
|
---|
566 |
|
---|
567 | dest[dest_off] = '\0';
|
---|
568 | }
|
---|
569 |
|
---|
570 | /** Copy size-limited substring.
|
---|
571 | *
|
---|
572 | * Copy prefix of string @a src of max. size @a size to destination buffer
|
---|
573 | * @a dest. No more than @a size bytes are written. The output string will
|
---|
574 | * always be well-formed, i.e. null-terminated and containing only complete
|
---|
575 | * characters.
|
---|
576 | *
|
---|
577 | * No more than @a n bytes are read from the input string, so it does not
|
---|
578 | * have to be null-terminated.
|
---|
579 | *
|
---|
580 | * @param dest Destination buffer.
|
---|
581 | * @param count Size of the destination buffer (must be > 0).
|
---|
582 | * @param src Source string.
|
---|
583 | * @param n Maximum number of bytes to read from @a src.
|
---|
584 | *
|
---|
585 | */
|
---|
586 | void str_ncpy(char *dest, size_t size, const char *src, size_t n)
|
---|
587 | {
|
---|
588 | /* There must be space for a null terminator in the buffer. */
|
---|
589 | ASSERT(size > 0);
|
---|
590 |
|
---|
591 | size_t src_off = 0;
|
---|
592 | size_t dest_off = 0;
|
---|
593 |
|
---|
594 | wchar_t ch;
|
---|
595 | while ((ch = str_decode(src, &src_off, n)) != 0) {
|
---|
596 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
597 | break;
|
---|
598 | }
|
---|
599 |
|
---|
600 | dest[dest_off] = '\0';
|
---|
601 | }
|
---|
602 |
|
---|
603 | /** Duplicate string.
|
---|
604 | *
|
---|
605 | * Allocate a new string and copy characters from the source
|
---|
606 | * string into it. The duplicate string is allocated via sleeping
|
---|
607 | * malloc(), thus this function can sleep in no memory conditions.
|
---|
608 | *
|
---|
609 | * The allocation cannot fail and the return value is always
|
---|
610 | * a valid pointer. The duplicate string is always a well-formed
|
---|
611 | * null-terminated UTF-8 string, but it can differ from the source
|
---|
612 | * string on the byte level.
|
---|
613 | *
|
---|
614 | * @param src Source string.
|
---|
615 | *
|
---|
616 | * @return Duplicate string.
|
---|
617 | *
|
---|
618 | */
|
---|
619 | char *str_dup(const char *src)
|
---|
620 | {
|
---|
621 | size_t size = str_size(src) + 1;
|
---|
622 | char *dest = malloc(size, 0);
|
---|
623 | ASSERT(dest);
|
---|
624 |
|
---|
625 | str_cpy(dest, size, src);
|
---|
626 | return dest;
|
---|
627 | }
|
---|
628 |
|
---|
629 | /** Duplicate string with size limit.
|
---|
630 | *
|
---|
631 | * Allocate a new string and copy up to @max_size bytes from the source
|
---|
632 | * string into it. The duplicate string is allocated via sleeping
|
---|
633 | * malloc(), thus this function can sleep in no memory conditions.
|
---|
634 | * No more than @max_size + 1 bytes is allocated, but if the size
|
---|
635 | * occupied by the source string is smaller than @max_size + 1,
|
---|
636 | * less is allocated.
|
---|
637 | *
|
---|
638 | * The allocation cannot fail and the return value is always
|
---|
639 | * a valid pointer. The duplicate string is always a well-formed
|
---|
640 | * null-terminated UTF-8 string, but it can differ from the source
|
---|
641 | * string on the byte level.
|
---|
642 | *
|
---|
643 | * @param src Source string.
|
---|
644 | * @param n Maximum number of bytes to duplicate.
|
---|
645 | *
|
---|
646 | * @return Duplicate string.
|
---|
647 | *
|
---|
648 | */
|
---|
649 | char *str_ndup(const char *src, size_t n)
|
---|
650 | {
|
---|
651 | size_t size = str_size(src);
|
---|
652 | if (size > n)
|
---|
653 | size = n;
|
---|
654 |
|
---|
655 | char *dest = malloc(size + 1, 0);
|
---|
656 | ASSERT(dest);
|
---|
657 |
|
---|
658 | str_ncpy(dest, size + 1, src, size);
|
---|
659 | return dest;
|
---|
660 | }
|
---|
661 |
|
---|
662 | /** Convert wide string to string.
|
---|
663 | *
|
---|
664 | * Convert wide string @a src to string. The output is written to the buffer
|
---|
665 | * specified by @a dest and @a size. @a size must be non-zero and the string
|
---|
666 | * written will always be well-formed.
|
---|
667 | *
|
---|
668 | * @param dest Destination buffer.
|
---|
669 | * @param size Size of the destination buffer.
|
---|
670 | * @param src Source wide string.
|
---|
671 | */
|
---|
672 | void wstr_to_str(char *dest, size_t size, const wchar_t *src)
|
---|
673 | {
|
---|
674 | wchar_t ch;
|
---|
675 | size_t src_idx;
|
---|
676 | size_t dest_off;
|
---|
677 |
|
---|
678 | /* There must be space for a null terminator in the buffer. */
|
---|
679 | ASSERT(size > 0);
|
---|
680 |
|
---|
681 | src_idx = 0;
|
---|
682 | dest_off = 0;
|
---|
683 |
|
---|
684 | while ((ch = src[src_idx++]) != 0) {
|
---|
685 | if (chr_encode(ch, dest, &dest_off, size - 1) != EOK)
|
---|
686 | break;
|
---|
687 | }
|
---|
688 |
|
---|
689 | dest[dest_off] = '\0';
|
---|
690 | }
|
---|
691 |
|
---|
692 | /** Find first occurence of character in string.
|
---|
693 | *
|
---|
694 | * @param str String to search.
|
---|
695 | * @param ch Character to look for.
|
---|
696 | *
|
---|
697 | * @return Pointer to character in @a str or NULL if not found.
|
---|
698 | *
|
---|
699 | */
|
---|
700 | char *str_chr(const char *str, wchar_t ch)
|
---|
701 | {
|
---|
702 | wchar_t acc;
|
---|
703 | size_t off = 0;
|
---|
704 | size_t last = 0;
|
---|
705 |
|
---|
706 | while ((acc = str_decode(str, &off, STR_NO_LIMIT)) != 0) {
|
---|
707 | if (acc == ch)
|
---|
708 | return (char *) (str + last);
|
---|
709 | last = off;
|
---|
710 | }
|
---|
711 |
|
---|
712 | return NULL;
|
---|
713 | }
|
---|
714 |
|
---|
715 | /** Insert a wide character into a wide string.
|
---|
716 | *
|
---|
717 | * Insert a wide character into a wide string at position
|
---|
718 | * @a pos. The characters after the position are shifted.
|
---|
719 | *
|
---|
720 | * @param str String to insert to.
|
---|
721 | * @param ch Character to insert to.
|
---|
722 | * @param pos Character index where to insert.
|
---|
723 | @ @param max_pos Characters in the buffer.
|
---|
724 | *
|
---|
725 | * @return True if the insertion was sucessful, false if the position
|
---|
726 | * is out of bounds.
|
---|
727 | *
|
---|
728 | */
|
---|
729 | bool wstr_linsert(wchar_t *str, wchar_t ch, size_t pos, size_t max_pos)
|
---|
730 | {
|
---|
731 | size_t len = wstr_length(str);
|
---|
732 |
|
---|
733 | if ((pos > len) || (pos + 1 > max_pos))
|
---|
734 | return false;
|
---|
735 |
|
---|
736 | size_t i;
|
---|
737 | for (i = len; i + 1 > pos; i--)
|
---|
738 | str[i + 1] = str[i];
|
---|
739 |
|
---|
740 | str[pos] = ch;
|
---|
741 |
|
---|
742 | return true;
|
---|
743 | }
|
---|
744 |
|
---|
745 | /** Remove a wide character from a wide string.
|
---|
746 | *
|
---|
747 | * Remove a wide character from a wide string at position
|
---|
748 | * @a pos. The characters after the position are shifted.
|
---|
749 | *
|
---|
750 | * @param str String to remove from.
|
---|
751 | * @param pos Character index to remove.
|
---|
752 | *
|
---|
753 | * @return True if the removal was sucessful, false if the position
|
---|
754 | * is out of bounds.
|
---|
755 | *
|
---|
756 | */
|
---|
757 | bool wstr_remove(wchar_t *str, size_t pos)
|
---|
758 | {
|
---|
759 | size_t len = wstr_length(str);
|
---|
760 |
|
---|
761 | if (pos >= len)
|
---|
762 | return false;
|
---|
763 |
|
---|
764 | size_t i;
|
---|
765 | for (i = pos + 1; i <= len; i++)
|
---|
766 | str[i - 1] = str[i];
|
---|
767 |
|
---|
768 | return true;
|
---|
769 | }
|
---|
770 |
|
---|
771 | /** Convert string to uint64_t (internal variant).
|
---|
772 | *
|
---|
773 | * @param nptr Pointer to string.
|
---|
774 | * @param endptr Pointer to the first invalid character is stored here.
|
---|
775 | * @param base Zero or number between 2 and 36 inclusive.
|
---|
776 | * @param neg Indication of unary minus is stored here.
|
---|
777 | * @apram result Result of the conversion.
|
---|
778 | *
|
---|
779 | * @return EOK if conversion was successful.
|
---|
780 | *
|
---|
781 | */
|
---|
782 | static int str_uint(const char *nptr, char **endptr, unsigned int base,
|
---|
783 | bool *neg, uint64_t *result)
|
---|
784 | {
|
---|
785 | ASSERT(endptr != NULL);
|
---|
786 | ASSERT(neg != NULL);
|
---|
787 | ASSERT(result != NULL);
|
---|
788 |
|
---|
789 | *neg = false;
|
---|
790 | const char *str = nptr;
|
---|
791 |
|
---|
792 | /* Ignore leading whitespace */
|
---|
793 | while (isspace(*str))
|
---|
794 | str++;
|
---|
795 |
|
---|
796 | if (*str == '-') {
|
---|
797 | *neg = true;
|
---|
798 | str++;
|
---|
799 | } else if (*str == '+')
|
---|
800 | str++;
|
---|
801 |
|
---|
802 | if (base == 0) {
|
---|
803 | /* Decode base if not specified */
|
---|
804 | base = 10;
|
---|
805 |
|
---|
806 | if (*str == '0') {
|
---|
807 | base = 8;
|
---|
808 | str++;
|
---|
809 |
|
---|
810 | switch (*str) {
|
---|
811 | case 'b':
|
---|
812 | case 'B':
|
---|
813 | base = 2;
|
---|
814 | str++;
|
---|
815 | break;
|
---|
816 | case 'o':
|
---|
817 | case 'O':
|
---|
818 | base = 8;
|
---|
819 | str++;
|
---|
820 | break;
|
---|
821 | case 'd':
|
---|
822 | case 'D':
|
---|
823 | case 't':
|
---|
824 | case 'T':
|
---|
825 | base = 10;
|
---|
826 | str++;
|
---|
827 | break;
|
---|
828 | case 'x':
|
---|
829 | case 'X':
|
---|
830 | base = 16;
|
---|
831 | str++;
|
---|
832 | break;
|
---|
833 | default:
|
---|
834 | str--;
|
---|
835 | }
|
---|
836 | }
|
---|
837 | } else {
|
---|
838 | /* Check base range */
|
---|
839 | if ((base < 2) || (base > 36)) {
|
---|
840 | *endptr = (char *) str;
|
---|
841 | return EINVAL;
|
---|
842 | }
|
---|
843 | }
|
---|
844 |
|
---|
845 | *result = 0;
|
---|
846 | const char *startstr = str;
|
---|
847 |
|
---|
848 | while (*str != 0) {
|
---|
849 | unsigned int digit;
|
---|
850 |
|
---|
851 | if ((*str >= 'a') && (*str <= 'z'))
|
---|
852 | digit = *str - 'a' + 10;
|
---|
853 | else if ((*str >= 'A') && (*str <= 'Z'))
|
---|
854 | digit = *str - 'A' + 10;
|
---|
855 | else if ((*str >= '0') && (*str <= '9'))
|
---|
856 | digit = *str - '0';
|
---|
857 | else
|
---|
858 | break;
|
---|
859 |
|
---|
860 | if (digit >= base)
|
---|
861 | break;
|
---|
862 |
|
---|
863 | uint64_t prev = *result;
|
---|
864 | *result = (*result) * base + digit;
|
---|
865 |
|
---|
866 | if (*result < prev) {
|
---|
867 | /* Overflow */
|
---|
868 | *endptr = (char *) str;
|
---|
869 | return EOVERFLOW;
|
---|
870 | }
|
---|
871 |
|
---|
872 | str++;
|
---|
873 | }
|
---|
874 |
|
---|
875 | if (str == startstr) {
|
---|
876 | /*
|
---|
877 | * No digits were decoded => first invalid character is
|
---|
878 | * the first character of the string.
|
---|
879 | */
|
---|
880 | str = nptr;
|
---|
881 | }
|
---|
882 |
|
---|
883 | *endptr = (char *) str;
|
---|
884 |
|
---|
885 | if (str == nptr)
|
---|
886 | return EINVAL;
|
---|
887 |
|
---|
888 | return EOK;
|
---|
889 | }
|
---|
890 |
|
---|
891 | /** Convert string to uint64_t.
|
---|
892 | *
|
---|
893 | * @param nptr Pointer to string.
|
---|
894 | * @param endptr If not NULL, pointer to the first invalid character
|
---|
895 | * is stored here.
|
---|
896 | * @param base Zero or number between 2 and 36 inclusive.
|
---|
897 | * @param strict Do not allow any trailing characters.
|
---|
898 | * @param result Result of the conversion.
|
---|
899 | *
|
---|
900 | * @return EOK if conversion was successful.
|
---|
901 | *
|
---|
902 | */
|
---|
903 | int str_uint64_t(const char *nptr, char **endptr, unsigned int base,
|
---|
904 | bool strict, uint64_t *result)
|
---|
905 | {
|
---|
906 | ASSERT(result != NULL);
|
---|
907 |
|
---|
908 | bool neg;
|
---|
909 | char *lendptr;
|
---|
910 | int ret = str_uint(nptr, &lendptr, base, &neg, result);
|
---|
911 |
|
---|
912 | if (endptr != NULL)
|
---|
913 | *endptr = (char *) lendptr;
|
---|
914 |
|
---|
915 | if (ret != EOK)
|
---|
916 | return ret;
|
---|
917 |
|
---|
918 | /* Do not allow negative values */
|
---|
919 | if (neg)
|
---|
920 | return EINVAL;
|
---|
921 |
|
---|
922 | /* Check whether we are at the end of
|
---|
923 | the string in strict mode */
|
---|
924 | if ((strict) && (*lendptr != 0))
|
---|
925 | return EINVAL;
|
---|
926 |
|
---|
927 | return EOK;
|
---|
928 | }
|
---|
929 |
|
---|
930 | void order_suffix(const uint64_t val, uint64_t *rv, char *suffix)
|
---|
931 | {
|
---|
932 | if (val > UINT64_C(10000000000000000000)) {
|
---|
933 | *rv = val / UINT64_C(1000000000000000000);
|
---|
934 | *suffix = 'Z';
|
---|
935 | } else if (val > UINT64_C(1000000000000000000)) {
|
---|
936 | *rv = val / UINT64_C(1000000000000000);
|
---|
937 | *suffix = 'E';
|
---|
938 | } else if (val > UINT64_C(1000000000000000)) {
|
---|
939 | *rv = val / UINT64_C(1000000000000);
|
---|
940 | *suffix = 'T';
|
---|
941 | } else if (val > UINT64_C(1000000000000)) {
|
---|
942 | *rv = val / UINT64_C(1000000000);
|
---|
943 | *suffix = 'G';
|
---|
944 | } else if (val > UINT64_C(1000000000)) {
|
---|
945 | *rv = val / UINT64_C(1000000);
|
---|
946 | *suffix = 'M';
|
---|
947 | } else if (val > UINT64_C(1000000)) {
|
---|
948 | *rv = val / UINT64_C(1000);
|
---|
949 | *suffix = 'k';
|
---|
950 | } else {
|
---|
951 | *rv = val;
|
---|
952 | *suffix = ' ';
|
---|
953 | }
|
---|
954 | }
|
---|
955 |
|
---|
956 | void bin_order_suffix(const uint64_t val, uint64_t *rv, const char **suffix,
|
---|
957 | bool fixed)
|
---|
958 | {
|
---|
959 | if (val > UINT64_C(1152921504606846976)) {
|
---|
960 | *rv = val / UINT64_C(1125899906842624);
|
---|
961 | *suffix = "EiB";
|
---|
962 | } else if (val > UINT64_C(1125899906842624)) {
|
---|
963 | *rv = val / UINT64_C(1099511627776);
|
---|
964 | *suffix = "TiB";
|
---|
965 | } else if (val > UINT64_C(1099511627776)) {
|
---|
966 | *rv = val / UINT64_C(1073741824);
|
---|
967 | *suffix = "GiB";
|
---|
968 | } else if (val > UINT64_C(1073741824)) {
|
---|
969 | *rv = val / UINT64_C(1048576);
|
---|
970 | *suffix = "MiB";
|
---|
971 | } else if (val > UINT64_C(1048576)) {
|
---|
972 | *rv = val / UINT64_C(1024);
|
---|
973 | *suffix = "KiB";
|
---|
974 | } else {
|
---|
975 | *rv = val;
|
---|
976 | if (fixed)
|
---|
977 | *suffix = "B ";
|
---|
978 | else
|
---|
979 | *suffix = "B";
|
---|
980 | }
|
---|
981 | }
|
---|
982 |
|
---|
983 | /** @}
|
---|
984 | */
|
---|