avstring.h 14 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423
  1. /*
  2. * Copyright (c) 2007 Mans Rullgard
  3. *
  4. * This file is part of FFmpeg.
  5. *
  6. * FFmpeg 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. * FFmpeg 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 FFmpeg; if not, write to the Free Software
  18. * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  19. */
  20. #ifndef AVUTIL_AVSTRING_H
  21. #define AVUTIL_AVSTRING_H
  22. #include <stddef.h>
  23. #include <stdint.h>
  24. #include "attributes.h"
  25. #include "version.h"
  26. /**
  27. * @addtogroup lavu_string
  28. * @{
  29. */
  30. /**
  31. * Return non-zero if pfx is a prefix of str. If it is, *ptr is set to
  32. * the address of the first character in str after the prefix.
  33. *
  34. * @param str input string
  35. * @param pfx prefix to test
  36. * @param ptr updated if the prefix is matched inside str
  37. * @return non-zero if the prefix matches, zero otherwise
  38. */
  39. int av_strstart(const char *str, const char *pfx, const char **ptr);
  40. /**
  41. * Return non-zero if pfx is a prefix of str independent of case. If
  42. * it is, *ptr is set to the address of the first character in str
  43. * after the prefix.
  44. *
  45. * @param str input string
  46. * @param pfx prefix to test
  47. * @param ptr updated if the prefix is matched inside str
  48. * @return non-zero if the prefix matches, zero otherwise
  49. */
  50. int av_stristart(const char *str, const char *pfx, const char **ptr);
  51. /**
  52. * Locate the first case-independent occurrence in the string haystack
  53. * of the string needle. A zero-length string needle is considered to
  54. * match at the start of haystack.
  55. *
  56. * This function is a case-insensitive version of the standard strstr().
  57. *
  58. * @param haystack string to search in
  59. * @param needle string to search for
  60. * @return pointer to the located match within haystack
  61. * or a null pointer if no match
  62. */
  63. char *av_stristr(const char *haystack, const char *needle);
  64. /**
  65. * Locate the first occurrence of the string needle in the string haystack
  66. * where not more than hay_length characters are searched. A zero-length
  67. * string needle is considered to match at the start of haystack.
  68. *
  69. * This function is a length-limited version of the standard strstr().
  70. *
  71. * @param haystack string to search in
  72. * @param needle string to search for
  73. * @param hay_length length of string to search in
  74. * @return pointer to the located match within haystack
  75. * or a null pointer if no match
  76. */
  77. char *av_strnstr(const char *haystack, const char *needle, size_t hay_length);
  78. /**
  79. * Copy the string src to dst, but no more than size - 1 bytes, and
  80. * null-terminate dst.
  81. *
  82. * This function is the same as BSD strlcpy().
  83. *
  84. * @param dst destination buffer
  85. * @param src source string
  86. * @param size size of destination buffer
  87. * @return the length of src
  88. *
  89. * @warning since the return value is the length of src, src absolutely
  90. * _must_ be a properly 0-terminated string, otherwise this will read beyond
  91. * the end of the buffer and possibly crash.
  92. */
  93. size_t av_strlcpy(char *dst, const char *src, size_t size);
  94. /**
  95. * Append the string src to the string dst, but to a total length of
  96. * no more than size - 1 bytes, and null-terminate dst.
  97. *
  98. * This function is similar to BSD strlcat(), but differs when
  99. * size <= strlen(dst).
  100. *
  101. * @param dst destination buffer
  102. * @param src source string
  103. * @param size size of destination buffer
  104. * @return the total length of src and dst
  105. *
  106. * @warning since the return value use the length of src and dst, these
  107. * absolutely _must_ be a properly 0-terminated strings, otherwise this
  108. * will read beyond the end of the buffer and possibly crash.
  109. */
  110. size_t av_strlcat(char *dst, const char *src, size_t size);
  111. /**
  112. * Append output to a string, according to a format. Never write out of
  113. * the destination buffer, and always put a terminating 0 within
  114. * the buffer.
  115. * @param dst destination buffer (string to which the output is
  116. * appended)
  117. * @param size total size of the destination buffer
  118. * @param fmt printf-compatible format string, specifying how the
  119. * following parameters are used
  120. * @return the length of the string that would have been generated
  121. * if enough space had been available
  122. */
  123. size_t av_strlcatf(char *dst, size_t size, const char *fmt, ...) av_printf_format(3, 4);
  124. /**
  125. * Get the count of continuous non zero chars starting from the beginning.
  126. *
  127. * @param len maximum number of characters to check in the string, that
  128. * is the maximum value which is returned by the function
  129. */
  130. static inline size_t av_strnlen(const char *s, size_t len)
  131. {
  132. size_t i;
  133. for (i = 0; i < len && s[i]; i++)
  134. ;
  135. return i;
  136. }
  137. /**
  138. * Print arguments following specified format into a large enough auto
  139. * allocated buffer. It is similar to GNU asprintf().
  140. * @param fmt printf-compatible format string, specifying how the
  141. * following parameters are used.
  142. * @return the allocated string
  143. * @note You have to free the string yourself with av_free().
  144. */
  145. char *av_asprintf(const char *fmt, ...) av_printf_format(1, 2);
  146. #if FF_API_D2STR
  147. /**
  148. * Convert a number to an av_malloced string.
  149. * @deprecated use av_asprintf() with "%f" or a more specific format
  150. */
  151. attribute_deprecated
  152. char *av_d2str(double d);
  153. #endif
  154. /**
  155. * Unescape the given string until a non escaped terminating char,
  156. * and return the token corresponding to the unescaped string.
  157. *
  158. * The normal \ and ' escaping is supported. Leading and trailing
  159. * whitespaces are removed, unless they are escaped with '\' or are
  160. * enclosed between ''.
  161. *
  162. * @param buf the buffer to parse, buf will be updated to point to the
  163. * terminating char
  164. * @param term a 0-terminated list of terminating chars
  165. * @return the malloced unescaped string, which must be av_freed by
  166. * the user, NULL in case of allocation failure
  167. */
  168. char *av_get_token(const char **buf, const char *term);
  169. /**
  170. * Split the string into several tokens which can be accessed by
  171. * successive calls to av_strtok().
  172. *
  173. * A token is defined as a sequence of characters not belonging to the
  174. * set specified in delim.
  175. *
  176. * On the first call to av_strtok(), s should point to the string to
  177. * parse, and the value of saveptr is ignored. In subsequent calls, s
  178. * should be NULL, and saveptr should be unchanged since the previous
  179. * call.
  180. *
  181. * This function is similar to strtok_r() defined in POSIX.1.
  182. *
  183. * @param s the string to parse, may be NULL
  184. * @param delim 0-terminated list of token delimiters, must be non-NULL
  185. * @param saveptr user-provided pointer which points to stored
  186. * information necessary for av_strtok() to continue scanning the same
  187. * string. saveptr is updated to point to the next character after the
  188. * first delimiter found, or to NULL if the string was terminated
  189. * @return the found token, or NULL when no token is found
  190. */
  191. char *av_strtok(char *s, const char *delim, char **saveptr);
  192. /**
  193. * Locale-independent conversion of ASCII isdigit.
  194. */
  195. static inline av_const int av_isdigit(int c)
  196. {
  197. return c >= '0' && c <= '9';
  198. }
  199. /**
  200. * Locale-independent conversion of ASCII isgraph.
  201. */
  202. static inline av_const int av_isgraph(int c)
  203. {
  204. return c > 32 && c < 127;
  205. }
  206. /**
  207. * Locale-independent conversion of ASCII isspace.
  208. */
  209. static inline av_const int av_isspace(int c)
  210. {
  211. return c == ' ' || c == '\f' || c == '\n' || c == '\r' || c == '\t' ||
  212. c == '\v';
  213. }
  214. /**
  215. * Locale-independent conversion of ASCII characters to uppercase.
  216. */
  217. static inline av_const int av_toupper(int c)
  218. {
  219. if (c >= 'a' && c <= 'z')
  220. c ^= 0x20;
  221. return c;
  222. }
  223. /**
  224. * Locale-independent conversion of ASCII characters to lowercase.
  225. */
  226. static inline av_const int av_tolower(int c)
  227. {
  228. if (c >= 'A' && c <= 'Z')
  229. c ^= 0x20;
  230. return c;
  231. }
  232. /**
  233. * Locale-independent conversion of ASCII isxdigit.
  234. */
  235. static inline av_const int av_isxdigit(int c)
  236. {
  237. c = av_tolower(c);
  238. return av_isdigit(c) || (c >= 'a' && c <= 'f');
  239. }
  240. /**
  241. * Locale-independent case-insensitive compare.
  242. * @note This means only ASCII-range characters are case-insensitive
  243. */
  244. int av_strcasecmp(const char *a, const char *b);
  245. /**
  246. * Locale-independent case-insensitive compare.
  247. * @note This means only ASCII-range characters are case-insensitive
  248. */
  249. int av_strncasecmp(const char *a, const char *b, size_t n);
  250. /**
  251. * Locale-independent strings replace.
  252. * @note This means only ASCII-range characters are replace
  253. */
  254. char *av_strireplace(const char *str, const char *from, const char *to);
  255. /**
  256. * Thread safe basename.
  257. * @param path the string to parse, on DOS both \ and / are considered separators.
  258. * @return pointer to the basename substring.
  259. * If path does not contain a slash, the function returns a copy of path.
  260. * If path is a NULL pointer or points to an empty string, a pointer
  261. * to a string "." is returned.
  262. */
  263. const char *av_basename(const char *path);
  264. /**
  265. * Thread safe dirname.
  266. * @param path the string to parse, on DOS both \ and / are considered separators.
  267. * @return A pointer to a string that's the parent directory of path.
  268. * If path is a NULL pointer or points to an empty string, a pointer
  269. * to a string "." is returned.
  270. * @note the function may modify the contents of the path, so copies should be passed.
  271. */
  272. const char *av_dirname(char *path);
  273. /**
  274. * Match instances of a name in a comma-separated list of names.
  275. * List entries are checked from the start to the end of the names list,
  276. * the first match ends further processing. If an entry prefixed with '-'
  277. * matches, then 0 is returned. The "ALL" list entry is considered to
  278. * match all names.
  279. *
  280. * @param name Name to look for.
  281. * @param names List of names.
  282. * @return 1 on match, 0 otherwise.
  283. */
  284. int av_match_name(const char *name, const char *names);
  285. /**
  286. * Append path component to the existing path.
  287. * Path separator '/' is placed between when needed.
  288. * Resulting string have to be freed with av_free().
  289. * @param path base path
  290. * @param component component to be appended
  291. * @return new path or NULL on error.
  292. */
  293. char *av_append_path_component(const char *path, const char *component);
  294. enum AVEscapeMode {
  295. AV_ESCAPE_MODE_AUTO, ///< Use auto-selected escaping mode.
  296. AV_ESCAPE_MODE_BACKSLASH, ///< Use backslash escaping.
  297. AV_ESCAPE_MODE_QUOTE, ///< Use single-quote escaping.
  298. };
  299. /**
  300. * Consider spaces special and escape them even in the middle of the
  301. * string.
  302. *
  303. * This is equivalent to adding the whitespace characters to the special
  304. * characters lists, except it is guaranteed to use the exact same list
  305. * of whitespace characters as the rest of libavutil.
  306. */
  307. #define AV_ESCAPE_FLAG_WHITESPACE (1 << 0)
  308. /**
  309. * Escape only specified special characters.
  310. * Without this flag, escape also any characters that may be considered
  311. * special by av_get_token(), such as the single quote.
  312. */
  313. #define AV_ESCAPE_FLAG_STRICT (1 << 1)
  314. /**
  315. * Escape string in src, and put the escaped string in an allocated
  316. * string in *dst, which must be freed with av_free().
  317. *
  318. * @param dst pointer where an allocated string is put
  319. * @param src string to escape, must be non-NULL
  320. * @param special_chars string containing the special characters which
  321. * need to be escaped, can be NULL
  322. * @param mode escape mode to employ, see AV_ESCAPE_MODE_* macros.
  323. * Any unknown value for mode will be considered equivalent to
  324. * AV_ESCAPE_MODE_BACKSLASH, but this behaviour can change without
  325. * notice.
  326. * @param flags flags which control how to escape, see AV_ESCAPE_FLAG_ macros
  327. * @return the length of the allocated string, or a negative error code in case of error
  328. * @see av_bprint_escape()
  329. */
  330. av_warn_unused_result
  331. int av_escape(char **dst, const char *src, const char *special_chars,
  332. enum AVEscapeMode mode, int flags);
  333. #define AV_UTF8_FLAG_ACCEPT_INVALID_BIG_CODES 1 ///< accept codepoints over 0x10FFFF
  334. #define AV_UTF8_FLAG_ACCEPT_NON_CHARACTERS 2 ///< accept non-characters - 0xFFFE and 0xFFFF
  335. #define AV_UTF8_FLAG_ACCEPT_SURROGATES 4 ///< accept UTF-16 surrogates codes
  336. #define AV_UTF8_FLAG_EXCLUDE_XML_INVALID_CONTROL_CODES 8 ///< exclude control codes not accepted by XML
  337. #define AV_UTF8_FLAG_ACCEPT_ALL \
  338. AV_UTF8_FLAG_ACCEPT_INVALID_BIG_CODES|AV_UTF8_FLAG_ACCEPT_NON_CHARACTERS|AV_UTF8_FLAG_ACCEPT_SURROGATES
  339. /**
  340. * Read and decode a single UTF-8 code point (character) from the
  341. * buffer in *buf, and update *buf to point to the next byte to
  342. * decode.
  343. *
  344. * In case of an invalid byte sequence, the pointer will be updated to
  345. * the next byte after the invalid sequence and the function will
  346. * return an error code.
  347. *
  348. * Depending on the specified flags, the function will also fail in
  349. * case the decoded code point does not belong to a valid range.
  350. *
  351. * @note For speed-relevant code a carefully implemented use of
  352. * GET_UTF8() may be preferred.
  353. *
  354. * @param codep pointer used to return the parsed code in case of success.
  355. * The value in *codep is set even in case the range check fails.
  356. * @param bufp pointer to the address the first byte of the sequence
  357. * to decode, updated by the function to point to the
  358. * byte next after the decoded sequence
  359. * @param buf_end pointer to the end of the buffer, points to the next
  360. * byte past the last in the buffer. This is used to
  361. * avoid buffer overreads (in case of an unfinished
  362. * UTF-8 sequence towards the end of the buffer).
  363. * @param flags a collection of AV_UTF8_FLAG_* flags
  364. * @return >= 0 in case a sequence was successfully read, a negative
  365. * value in case of invalid sequence
  366. */
  367. av_warn_unused_result
  368. int av_utf8_decode(int32_t *codep, const uint8_t **bufp, const uint8_t *buf_end,
  369. unsigned int flags);
  370. /**
  371. * Check if a name is in a list.
  372. * @returns 0 if not found, or the 1 based index where it has been found in the
  373. * list.
  374. */
  375. int av_match_list(const char *name, const char *list, char separator);
  376. /**
  377. * See libc sscanf manual for more information.
  378. * Locale-independent sscanf implementation.
  379. */
  380. int av_sscanf(const char *string, const char *format, ...);
  381. /**
  382. * @}
  383. */
  384. #endif /* AVUTIL_AVSTRING_H */