PageRenderTime 53ms CodeModel.GetById 24ms RepoModel.GetById 1ms app.codeStats 0ms

/ext/mbstring/mbstring.c

http://github.com/infusion/PHP
C | 4891 lines | 3935 code | 550 blank | 406 comment | 1115 complexity | 29f0a79516e817df9626e2903bdb7a4c MD5 | raw file
Possible License(s): MPL-2.0-no-copyleft-exception, LGPL-2.1, BSD-3-Clause

Large files files are truncated, but you can click here to view the full file

  1. /*
  2. +----------------------------------------------------------------------+
  3. | PHP Version 5 |
  4. +----------------------------------------------------------------------+
  5. | Copyright (c) 1997-2011 The PHP Group |
  6. +----------------------------------------------------------------------+
  7. | This source file is subject to version 3.01 of the PHP license, |
  8. | that is bundled with this package in the file LICENSE, and is |
  9. | available through the world-wide-web at the following url: |
  10. | http://www.php.net/license/3_01.txt |
  11. | If you did not receive a copy of the PHP license and are unable to |
  12. | obtain it through the world-wide-web, please send a note to |
  13. | license@php.net so we can mail you a copy immediately. |
  14. +----------------------------------------------------------------------+
  15. | Author: Tsukada Takuya <tsukada@fminn.nagano.nagano.jp> |
  16. | Rui Hirokawa <hirokawa@php.net> |
  17. +----------------------------------------------------------------------+
  18. */
  19. /* $Id: mbstring.c 306939 2011-01-01 02:19:59Z felipe $ */
  20. /*
  21. * PHP 4 Multibyte String module "mbstring"
  22. *
  23. * History:
  24. * 2000.5.19 Release php-4.0RC2_jstring-1.0
  25. * 2001.4.1 Release php4_jstring-1.0.91
  26. * 2001.4.30 Release php4_jstring-1.1 (contribute to The PHP Group)
  27. * 2001.5.1 Renamed from jstring to mbstring (hirokawa@php.net)
  28. */
  29. /*
  30. * PHP3 Internationalization support program.
  31. *
  32. * Copyright (c) 1999,2000 by the PHP3 internationalization team.
  33. * All rights reserved.
  34. *
  35. * See README_PHP3-i18n-ja for more detail.
  36. *
  37. * Authors:
  38. * Hironori Sato <satoh@jpnnet.com>
  39. * Shigeru Kanemoto <sgk@happysize.co.jp>
  40. * Tsukada Takuya <tsukada@fminn.nagano.nagano.jp>
  41. * Rui Hirokawa <rui_hirokawa@ybb.ne.jp>
  42. */
  43. /* {{{ includes */
  44. #ifdef HAVE_CONFIG_H
  45. #include "config.h"
  46. #endif
  47. #include "php.h"
  48. #include "php_ini.h"
  49. #include "php_variables.h"
  50. #include "mbstring.h"
  51. #include "ext/standard/php_string.h"
  52. #include "ext/standard/php_mail.h"
  53. #include "ext/standard/exec.h"
  54. #include "ext/standard/php_smart_str.h"
  55. #include "ext/standard/url.h"
  56. #include "main/php_output.h"
  57. #include "ext/standard/info.h"
  58. #include "libmbfl/mbfl/mbfl_allocators.h"
  59. #include "php_variables.h"
  60. #include "php_globals.h"
  61. #include "rfc1867.h"
  62. #include "php_content_types.h"
  63. #include "SAPI.h"
  64. #include "php_unicode.h"
  65. #include "TSRM.h"
  66. #include "mb_gpc.h"
  67. #if HAVE_MBREGEX
  68. #include "php_mbregex.h"
  69. #endif
  70. #ifdef ZEND_MULTIBYTE
  71. #include "zend_multibyte.h"
  72. #endif /* ZEND_MULTIBYTE */
  73. #if HAVE_ONIG
  74. #include "php_onig_compat.h"
  75. #include <oniguruma.h>
  76. #undef UChar
  77. #elif HAVE_PCRE || HAVE_BUNDLED_PCRE
  78. #include "ext/pcre/php_pcre.h"
  79. #endif
  80. /* }}} */
  81. #if HAVE_MBSTRING
  82. /* {{{ prototypes */
  83. ZEND_DECLARE_MODULE_GLOBALS(mbstring)
  84. static PHP_GINIT_FUNCTION(mbstring);
  85. static PHP_GSHUTDOWN_FUNCTION(mbstring);
  86. #ifdef ZEND_MULTIBYTE
  87. static size_t php_mb_oddlen(const unsigned char *string, size_t length, const char *encoding TSRMLS_DC);
  88. static int php_mb_encoding_converter(unsigned char **to, size_t *to_length, const unsigned char *from, size_t from_length, const char *encoding_to, const char *encoding_from TSRMLS_DC);
  89. static char* php_mb_encoding_detector(const unsigned char *arg_string, size_t arg_length, char *arg_list TSRMLS_DC);
  90. static int php_mb_set_zend_encoding(TSRMLS_D);
  91. #endif
  92. /* }}} */
  93. /* {{{ php_mb_default_identify_list */
  94. typedef struct _php_mb_nls_ident_list {
  95. enum mbfl_no_language lang;
  96. const enum mbfl_no_encoding* list;
  97. int list_size;
  98. } php_mb_nls_ident_list;
  99. static const enum mbfl_no_encoding php_mb_default_identify_list_ja[] = {
  100. mbfl_no_encoding_ascii,
  101. mbfl_no_encoding_jis,
  102. mbfl_no_encoding_utf8,
  103. mbfl_no_encoding_euc_jp,
  104. mbfl_no_encoding_sjis
  105. };
  106. static const enum mbfl_no_encoding php_mb_default_identify_list_cn[] = {
  107. mbfl_no_encoding_ascii,
  108. mbfl_no_encoding_utf8,
  109. mbfl_no_encoding_euc_cn,
  110. mbfl_no_encoding_cp936
  111. };
  112. static const enum mbfl_no_encoding php_mb_default_identify_list_tw_hk[] = {
  113. mbfl_no_encoding_ascii,
  114. mbfl_no_encoding_utf8,
  115. mbfl_no_encoding_euc_tw,
  116. mbfl_no_encoding_big5
  117. };
  118. static const enum mbfl_no_encoding php_mb_default_identify_list_kr[] = {
  119. mbfl_no_encoding_ascii,
  120. mbfl_no_encoding_utf8,
  121. mbfl_no_encoding_euc_kr,
  122. mbfl_no_encoding_uhc
  123. };
  124. static const enum mbfl_no_encoding php_mb_default_identify_list_ru[] = {
  125. mbfl_no_encoding_ascii,
  126. mbfl_no_encoding_utf8,
  127. mbfl_no_encoding_koi8r,
  128. mbfl_no_encoding_cp1251,
  129. mbfl_no_encoding_cp866
  130. };
  131. static const enum mbfl_no_encoding php_mb_default_identify_list_hy[] = {
  132. mbfl_no_encoding_ascii,
  133. mbfl_no_encoding_utf8,
  134. mbfl_no_encoding_armscii8
  135. };
  136. static const enum mbfl_no_encoding php_mb_default_identify_list_tr[] = {
  137. mbfl_no_encoding_ascii,
  138. mbfl_no_encoding_utf8,
  139. mbfl_no_encoding_cp1254,
  140. mbfl_no_encoding_8859_9
  141. };
  142. static const enum mbfl_no_encoding php_mb_default_identify_list_ua[] = {
  143. mbfl_no_encoding_ascii,
  144. mbfl_no_encoding_utf8,
  145. mbfl_no_encoding_koi8u
  146. };
  147. static const enum mbfl_no_encoding php_mb_default_identify_list_neut[] = {
  148. mbfl_no_encoding_ascii,
  149. mbfl_no_encoding_utf8
  150. };
  151. static const php_mb_nls_ident_list php_mb_default_identify_list[] = {
  152. { mbfl_no_language_japanese, php_mb_default_identify_list_ja, sizeof(php_mb_default_identify_list_ja) / sizeof(php_mb_default_identify_list_ja[0]) },
  153. { mbfl_no_language_korean, php_mb_default_identify_list_kr, sizeof(php_mb_default_identify_list_kr) / sizeof(php_mb_default_identify_list_kr[0]) },
  154. { mbfl_no_language_traditional_chinese, php_mb_default_identify_list_tw_hk, sizeof(php_mb_default_identify_list_tw_hk) / sizeof(php_mb_default_identify_list_tw_hk[0]) },
  155. { mbfl_no_language_simplified_chinese, php_mb_default_identify_list_cn, sizeof(php_mb_default_identify_list_cn) / sizeof(php_mb_default_identify_list_cn[0]) },
  156. { mbfl_no_language_russian, php_mb_default_identify_list_ru, sizeof(php_mb_default_identify_list_ru) / sizeof(php_mb_default_identify_list_ru[0]) },
  157. { mbfl_no_language_armenian, php_mb_default_identify_list_hy, sizeof(php_mb_default_identify_list_hy) / sizeof(php_mb_default_identify_list_hy[0]) },
  158. { mbfl_no_language_turkish, php_mb_default_identify_list_tr, sizeof(php_mb_default_identify_list_tr) / sizeof(php_mb_default_identify_list_tr[0]) },
  159. { mbfl_no_language_ukrainian, php_mb_default_identify_list_ua, sizeof(php_mb_default_identify_list_ua) / sizeof(php_mb_default_identify_list_ua[0]) },
  160. { mbfl_no_language_neutral, php_mb_default_identify_list_neut, sizeof(php_mb_default_identify_list_neut) / sizeof(php_mb_default_identify_list_neut[0]) }
  161. };
  162. /* }}} */
  163. /* {{{ mb_overload_def mb_ovld[] */
  164. static const struct mb_overload_def mb_ovld[] = {
  165. {MB_OVERLOAD_MAIL, "mail", "mb_send_mail", "mb_orig_mail"},
  166. {MB_OVERLOAD_STRING, "strlen", "mb_strlen", "mb_orig_strlen"},
  167. {MB_OVERLOAD_STRING, "strpos", "mb_strpos", "mb_orig_strpos"},
  168. {MB_OVERLOAD_STRING, "strrpos", "mb_strrpos", "mb_orig_strrpos"},
  169. {MB_OVERLOAD_STRING, "stripos", "mb_stripos", "mb_orig_stripos"},
  170. {MB_OVERLOAD_STRING, "strripos", "mb_strripos", "mb_orig_strripos"},
  171. {MB_OVERLOAD_STRING, "strstr", "mb_strstr", "mb_orig_strstr"},
  172. {MB_OVERLOAD_STRING, "strrchr", "mb_strrchr", "mb_orig_strrchr"},
  173. {MB_OVERLOAD_STRING, "stristr", "mb_stristr", "mb_orig_stristr"},
  174. {MB_OVERLOAD_STRING, "substr", "mb_substr", "mb_orig_substr"},
  175. {MB_OVERLOAD_STRING, "strtolower", "mb_strtolower", "mb_orig_strtolower"},
  176. {MB_OVERLOAD_STRING, "strtoupper", "mb_strtoupper", "mb_orig_strtoupper"},
  177. {MB_OVERLOAD_STRING, "substr_count", "mb_substr_count", "mb_orig_substr_count"},
  178. #if HAVE_MBREGEX
  179. {MB_OVERLOAD_REGEX, "ereg", "mb_ereg", "mb_orig_ereg"},
  180. {MB_OVERLOAD_REGEX, "eregi", "mb_eregi", "mb_orig_eregi"},
  181. {MB_OVERLOAD_REGEX, "ereg_replace", "mb_ereg_replace", "mb_orig_ereg_replace"},
  182. {MB_OVERLOAD_REGEX, "eregi_replace", "mb_eregi_replace", "mb_orig_eregi_replace"},
  183. {MB_OVERLOAD_REGEX, "split", "mb_split", "mb_orig_split"},
  184. #endif
  185. {0, NULL, NULL, NULL}
  186. };
  187. /* }}} */
  188. /* {{{ arginfo */
  189. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_language, 0, 0, 0)
  190. ZEND_ARG_INFO(0, language)
  191. ZEND_END_ARG_INFO()
  192. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_internal_encoding, 0, 0, 0)
  193. ZEND_ARG_INFO(0, encoding)
  194. ZEND_END_ARG_INFO()
  195. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_http_input, 0, 0, 0)
  196. ZEND_ARG_INFO(0, type)
  197. ZEND_END_ARG_INFO()
  198. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_http_output, 0, 0, 0)
  199. ZEND_ARG_INFO(0, encoding)
  200. ZEND_END_ARG_INFO()
  201. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_detect_order, 0, 0, 0)
  202. ZEND_ARG_INFO(0, encoding)
  203. ZEND_END_ARG_INFO()
  204. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substitute_character, 0, 0, 0)
  205. ZEND_ARG_INFO(0, substchar)
  206. ZEND_END_ARG_INFO()
  207. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_preferred_mime_name, 0, 0, 1)
  208. ZEND_ARG_INFO(0, encoding)
  209. ZEND_END_ARG_INFO()
  210. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_parse_str, 0, 0, 1)
  211. ZEND_ARG_INFO(0, encoded_string)
  212. ZEND_ARG_INFO(1, result)
  213. ZEND_END_ARG_INFO()
  214. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_output_handler, 0, 0, 2)
  215. ZEND_ARG_INFO(0, contents)
  216. ZEND_ARG_INFO(0, status)
  217. ZEND_END_ARG_INFO()
  218. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strlen, 0, 0, 1)
  219. ZEND_ARG_INFO(0, str)
  220. ZEND_ARG_INFO(0, encoding)
  221. ZEND_END_ARG_INFO()
  222. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strpos, 0, 0, 2)
  223. ZEND_ARG_INFO(0, haystack)
  224. ZEND_ARG_INFO(0, needle)
  225. ZEND_ARG_INFO(0, offset)
  226. ZEND_ARG_INFO(0, encoding)
  227. ZEND_END_ARG_INFO()
  228. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrpos, 0, 0, 2)
  229. ZEND_ARG_INFO(0, haystack)
  230. ZEND_ARG_INFO(0, needle)
  231. ZEND_ARG_INFO(0, offset)
  232. ZEND_ARG_INFO(0, encoding)
  233. ZEND_END_ARG_INFO()
  234. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_stripos, 0, 0, 2)
  235. ZEND_ARG_INFO(0, haystack)
  236. ZEND_ARG_INFO(0, needle)
  237. ZEND_ARG_INFO(0, offset)
  238. ZEND_ARG_INFO(0, encoding)
  239. ZEND_END_ARG_INFO()
  240. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strripos, 0, 0, 2)
  241. ZEND_ARG_INFO(0, haystack)
  242. ZEND_ARG_INFO(0, needle)
  243. ZEND_ARG_INFO(0, offset)
  244. ZEND_ARG_INFO(0, encoding)
  245. ZEND_END_ARG_INFO()
  246. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strstr, 0, 0, 2)
  247. ZEND_ARG_INFO(0, haystack)
  248. ZEND_ARG_INFO(0, needle)
  249. ZEND_ARG_INFO(0, part)
  250. ZEND_ARG_INFO(0, encoding)
  251. ZEND_END_ARG_INFO()
  252. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrchr, 0, 0, 2)
  253. ZEND_ARG_INFO(0, haystack)
  254. ZEND_ARG_INFO(0, needle)
  255. ZEND_ARG_INFO(0, part)
  256. ZEND_ARG_INFO(0, encoding)
  257. ZEND_END_ARG_INFO()
  258. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_stristr, 0, 0, 2)
  259. ZEND_ARG_INFO(0, haystack)
  260. ZEND_ARG_INFO(0, needle)
  261. ZEND_ARG_INFO(0, part)
  262. ZEND_ARG_INFO(0, encoding)
  263. ZEND_END_ARG_INFO()
  264. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrichr, 0, 0, 2)
  265. ZEND_ARG_INFO(0, haystack)
  266. ZEND_ARG_INFO(0, needle)
  267. ZEND_ARG_INFO(0, part)
  268. ZEND_ARG_INFO(0, encoding)
  269. ZEND_END_ARG_INFO()
  270. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substr_count, 0, 0, 2)
  271. ZEND_ARG_INFO(0, haystack)
  272. ZEND_ARG_INFO(0, needle)
  273. ZEND_ARG_INFO(0, encoding)
  274. ZEND_END_ARG_INFO()
  275. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substr, 0, 0, 2)
  276. ZEND_ARG_INFO(0, str)
  277. ZEND_ARG_INFO(0, start)
  278. ZEND_ARG_INFO(0, length)
  279. ZEND_ARG_INFO(0, encoding)
  280. ZEND_END_ARG_INFO()
  281. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strcut, 0, 0, 2)
  282. ZEND_ARG_INFO(0, str)
  283. ZEND_ARG_INFO(0, start)
  284. ZEND_ARG_INFO(0, length)
  285. ZEND_ARG_INFO(0, encoding)
  286. ZEND_END_ARG_INFO()
  287. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strwidth, 0, 0, 1)
  288. ZEND_ARG_INFO(0, str)
  289. ZEND_ARG_INFO(0, encoding)
  290. ZEND_END_ARG_INFO()
  291. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strimwidth, 0, 0, 3)
  292. ZEND_ARG_INFO(0, str)
  293. ZEND_ARG_INFO(0, start)
  294. ZEND_ARG_INFO(0, width)
  295. ZEND_ARG_INFO(0, trimmarker)
  296. ZEND_ARG_INFO(0, encoding)
  297. ZEND_END_ARG_INFO()
  298. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_encoding, 0, 0, 2)
  299. ZEND_ARG_INFO(0, str)
  300. ZEND_ARG_INFO(0, to)
  301. ZEND_ARG_INFO(0, from)
  302. ZEND_END_ARG_INFO()
  303. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_case, 0, 0, 2)
  304. ZEND_ARG_INFO(0, sourcestring)
  305. ZEND_ARG_INFO(0, mode)
  306. ZEND_ARG_INFO(0, encoding)
  307. ZEND_END_ARG_INFO()
  308. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strtoupper, 0, 0, 1)
  309. ZEND_ARG_INFO(0, sourcestring)
  310. ZEND_ARG_INFO(0, encoding)
  311. ZEND_END_ARG_INFO()
  312. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strtolower, 0, 0, 1)
  313. ZEND_ARG_INFO(0, sourcestring)
  314. ZEND_ARG_INFO(0, encoding)
  315. ZEND_END_ARG_INFO()
  316. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_detect_encoding, 0, 0, 1)
  317. ZEND_ARG_INFO(0, str)
  318. ZEND_ARG_INFO(0, encoding_list)
  319. ZEND_ARG_INFO(0, strict)
  320. ZEND_END_ARG_INFO()
  321. ZEND_BEGIN_ARG_INFO(arginfo_mb_list_encodings, 0)
  322. ZEND_END_ARG_INFO()
  323. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encoding_aliases, 0, 0, 1)
  324. ZEND_ARG_INFO(0, encoding)
  325. ZEND_END_ARG_INFO()
  326. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encode_mimeheader, 0, 0, 1)
  327. ZEND_ARG_INFO(0, str)
  328. ZEND_ARG_INFO(0, charset)
  329. ZEND_ARG_INFO(0, transfer)
  330. ZEND_ARG_INFO(0, linefeed)
  331. ZEND_ARG_INFO(0, indent)
  332. ZEND_END_ARG_INFO()
  333. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_decode_mimeheader, 0, 0, 1)
  334. ZEND_ARG_INFO(0, string)
  335. ZEND_END_ARG_INFO()
  336. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_kana, 0, 0, 1)
  337. ZEND_ARG_INFO(0, str)
  338. ZEND_ARG_INFO(0, option)
  339. ZEND_ARG_INFO(0, encoding)
  340. ZEND_END_ARG_INFO()
  341. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_variables, 1, 0, 3)
  342. ZEND_ARG_INFO(0, to)
  343. ZEND_ARG_INFO(0, from)
  344. ZEND_ARG_INFO(1, ...)
  345. ZEND_END_ARG_INFO()
  346. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encode_numericentity, 0, 0, 2)
  347. ZEND_ARG_INFO(0, string)
  348. ZEND_ARG_INFO(0, convmap)
  349. ZEND_ARG_INFO(0, encoding)
  350. ZEND_END_ARG_INFO()
  351. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_decode_numericentity, 0, 0, 2)
  352. ZEND_ARG_INFO(0, string)
  353. ZEND_ARG_INFO(0, convmap)
  354. ZEND_ARG_INFO(0, encoding)
  355. ZEND_END_ARG_INFO()
  356. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_send_mail, 0, 0, 3)
  357. ZEND_ARG_INFO(0, to)
  358. ZEND_ARG_INFO(0, subject)
  359. ZEND_ARG_INFO(0, message)
  360. ZEND_ARG_INFO(0, additional_headers)
  361. ZEND_ARG_INFO(0, additional_parameters)
  362. ZEND_END_ARG_INFO()
  363. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_get_info, 0, 0, 0)
  364. ZEND_ARG_INFO(0, type)
  365. ZEND_END_ARG_INFO()
  366. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_check_encoding, 0, 0, 0)
  367. ZEND_ARG_INFO(0, var)
  368. ZEND_ARG_INFO(0, encoding)
  369. ZEND_END_ARG_INFO()
  370. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_regex_encoding, 0, 0, 0)
  371. ZEND_ARG_INFO(0, encoding)
  372. ZEND_END_ARG_INFO()
  373. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg, 0, 0, 2)
  374. ZEND_ARG_INFO(0, pattern)
  375. ZEND_ARG_INFO(0, string)
  376. ZEND_ARG_INFO(1, registers)
  377. ZEND_END_ARG_INFO()
  378. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_eregi, 0, 0, 2)
  379. ZEND_ARG_INFO(0, pattern)
  380. ZEND_ARG_INFO(0, string)
  381. ZEND_ARG_INFO(1, registers)
  382. ZEND_END_ARG_INFO()
  383. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_replace, 0, 0, 3)
  384. ZEND_ARG_INFO(0, pattern)
  385. ZEND_ARG_INFO(0, replacement)
  386. ZEND_ARG_INFO(0, string)
  387. ZEND_ARG_INFO(0, option)
  388. ZEND_END_ARG_INFO()
  389. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_eregi_replace, 0, 0, 3)
  390. ZEND_ARG_INFO(0, pattern)
  391. ZEND_ARG_INFO(0, replacement)
  392. ZEND_ARG_INFO(0, string)
  393. ZEND_END_ARG_INFO()
  394. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_split, 0, 0, 2)
  395. ZEND_ARG_INFO(0, pattern)
  396. ZEND_ARG_INFO(0, string)
  397. ZEND_ARG_INFO(0, limit)
  398. ZEND_END_ARG_INFO()
  399. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_match, 0, 0, 2)
  400. ZEND_ARG_INFO(0, pattern)
  401. ZEND_ARG_INFO(0, string)
  402. ZEND_ARG_INFO(0, option)
  403. ZEND_END_ARG_INFO()
  404. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search, 0, 0, 0)
  405. ZEND_ARG_INFO(0, pattern)
  406. ZEND_ARG_INFO(0, option)
  407. ZEND_END_ARG_INFO()
  408. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_pos, 0, 0, 0)
  409. ZEND_ARG_INFO(0, pattern)
  410. ZEND_ARG_INFO(0, option)
  411. ZEND_END_ARG_INFO()
  412. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_regs, 0, 0, 0)
  413. ZEND_ARG_INFO(0, pattern)
  414. ZEND_ARG_INFO(0, option)
  415. ZEND_END_ARG_INFO()
  416. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_init, 0, 0, 1)
  417. ZEND_ARG_INFO(0, string)
  418. ZEND_ARG_INFO(0, pattern)
  419. ZEND_ARG_INFO(0, option)
  420. ZEND_END_ARG_INFO()
  421. ZEND_BEGIN_ARG_INFO(arginfo_mb_ereg_search_getregs, 0)
  422. ZEND_END_ARG_INFO()
  423. ZEND_BEGIN_ARG_INFO(arginfo_mb_ereg_search_getpos, 0)
  424. ZEND_END_ARG_INFO()
  425. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_setpos, 0, 0, 1)
  426. ZEND_ARG_INFO(0, position)
  427. ZEND_END_ARG_INFO()
  428. ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_regex_set_options, 0, 0, 0)
  429. ZEND_ARG_INFO(0, options)
  430. ZEND_END_ARG_INFO()
  431. /* }}} */
  432. /* {{{ zend_function_entry mbstring_functions[] */
  433. const zend_function_entry mbstring_functions[] = {
  434. PHP_FE(mb_convert_case, arginfo_mb_convert_case)
  435. PHP_FE(mb_strtoupper, arginfo_mb_strtoupper)
  436. PHP_FE(mb_strtolower, arginfo_mb_strtolower)
  437. PHP_FE(mb_language, arginfo_mb_language)
  438. PHP_FE(mb_internal_encoding, arginfo_mb_internal_encoding)
  439. PHP_FE(mb_http_input, arginfo_mb_http_input)
  440. PHP_FE(mb_http_output, arginfo_mb_http_output)
  441. PHP_FE(mb_detect_order, arginfo_mb_detect_order)
  442. PHP_FE(mb_substitute_character, arginfo_mb_substitute_character)
  443. PHP_FE(mb_parse_str, arginfo_mb_parse_str)
  444. PHP_FE(mb_output_handler, arginfo_mb_output_handler)
  445. PHP_FE(mb_preferred_mime_name, arginfo_mb_preferred_mime_name)
  446. PHP_FE(mb_strlen, arginfo_mb_strlen)
  447. PHP_FE(mb_strpos, arginfo_mb_strpos)
  448. PHP_FE(mb_strrpos, arginfo_mb_strrpos)
  449. PHP_FE(mb_stripos, arginfo_mb_stripos)
  450. PHP_FE(mb_strripos, arginfo_mb_strripos)
  451. PHP_FE(mb_strstr, arginfo_mb_strstr)
  452. PHP_FE(mb_strrchr, arginfo_mb_strrchr)
  453. PHP_FE(mb_stristr, arginfo_mb_stristr)
  454. PHP_FE(mb_strrichr, arginfo_mb_strrichr)
  455. PHP_FE(mb_substr_count, arginfo_mb_substr_count)
  456. PHP_FE(mb_substr, arginfo_mb_substr)
  457. PHP_FE(mb_strcut, arginfo_mb_strcut)
  458. PHP_FE(mb_strwidth, arginfo_mb_strwidth)
  459. PHP_FE(mb_strimwidth, arginfo_mb_strimwidth)
  460. PHP_FE(mb_convert_encoding, arginfo_mb_convert_encoding)
  461. PHP_FE(mb_detect_encoding, arginfo_mb_detect_encoding)
  462. PHP_FE(mb_list_encodings, arginfo_mb_list_encodings)
  463. PHP_FE(mb_encoding_aliases, arginfo_mb_encoding_aliases)
  464. PHP_FE(mb_convert_kana, arginfo_mb_convert_kana)
  465. PHP_FE(mb_encode_mimeheader, arginfo_mb_encode_mimeheader)
  466. PHP_FE(mb_decode_mimeheader, arginfo_mb_decode_mimeheader)
  467. PHP_FE(mb_convert_variables, arginfo_mb_convert_variables)
  468. PHP_FE(mb_encode_numericentity, arginfo_mb_encode_numericentity)
  469. PHP_FE(mb_decode_numericentity, arginfo_mb_decode_numericentity)
  470. PHP_FE(mb_send_mail, arginfo_mb_send_mail)
  471. PHP_FE(mb_get_info, arginfo_mb_get_info)
  472. PHP_FE(mb_check_encoding, arginfo_mb_check_encoding)
  473. #if HAVE_MBREGEX
  474. PHP_MBREGEX_FUNCTION_ENTRIES
  475. #endif
  476. { NULL, NULL, NULL }
  477. };
  478. /* }}} */
  479. /* {{{ zend_module_entry mbstring_module_entry */
  480. zend_module_entry mbstring_module_entry = {
  481. STANDARD_MODULE_HEADER,
  482. "mbstring",
  483. mbstring_functions,
  484. PHP_MINIT(mbstring),
  485. PHP_MSHUTDOWN(mbstring),
  486. PHP_RINIT(mbstring),
  487. PHP_RSHUTDOWN(mbstring),
  488. PHP_MINFO(mbstring),
  489. NO_VERSION_YET,
  490. PHP_MODULE_GLOBALS(mbstring),
  491. PHP_GINIT(mbstring),
  492. PHP_GSHUTDOWN(mbstring),
  493. NULL,
  494. STANDARD_MODULE_PROPERTIES_EX
  495. };
  496. /* }}} */
  497. /* {{{ static sapi_post_entry php_post_entries[] */
  498. static sapi_post_entry php_post_entries[] = {
  499. { DEFAULT_POST_CONTENT_TYPE, sizeof(DEFAULT_POST_CONTENT_TYPE)-1, sapi_read_standard_form_data, php_std_post_handler },
  500. { MULTIPART_CONTENT_TYPE, sizeof(MULTIPART_CONTENT_TYPE)-1, NULL, rfc1867_post_handler },
  501. { NULL, 0, NULL, NULL }
  502. };
  503. /* }}} */
  504. #ifdef COMPILE_DL_MBSTRING
  505. ZEND_GET_MODULE(mbstring)
  506. #endif
  507. /* {{{ allocators */
  508. static void *_php_mb_allocators_malloc(unsigned int sz)
  509. {
  510. return emalloc(sz);
  511. }
  512. static void *_php_mb_allocators_realloc(void *ptr, unsigned int sz)
  513. {
  514. return erealloc(ptr, sz);
  515. }
  516. static void *_php_mb_allocators_calloc(unsigned int nelems, unsigned int szelem)
  517. {
  518. return ecalloc(nelems, szelem);
  519. }
  520. static void _php_mb_allocators_free(void *ptr)
  521. {
  522. efree(ptr);
  523. }
  524. static void *_php_mb_allocators_pmalloc(unsigned int sz)
  525. {
  526. return pemalloc(sz, 1);
  527. }
  528. static void *_php_mb_allocators_prealloc(void *ptr, unsigned int sz)
  529. {
  530. return perealloc(ptr, sz, 1);
  531. }
  532. static void _php_mb_allocators_pfree(void *ptr)
  533. {
  534. pefree(ptr, 1);
  535. }
  536. static mbfl_allocators _php_mb_allocators = {
  537. _php_mb_allocators_malloc,
  538. _php_mb_allocators_realloc,
  539. _php_mb_allocators_calloc,
  540. _php_mb_allocators_free,
  541. _php_mb_allocators_pmalloc,
  542. _php_mb_allocators_prealloc,
  543. _php_mb_allocators_pfree
  544. };
  545. /* }}} */
  546. /* {{{ static sapi_post_entry mbstr_post_entries[] */
  547. static sapi_post_entry mbstr_post_entries[] = {
  548. { DEFAULT_POST_CONTENT_TYPE, sizeof(DEFAULT_POST_CONTENT_TYPE)-1, sapi_read_standard_form_data, php_mb_post_handler },
  549. { MULTIPART_CONTENT_TYPE, sizeof(MULTIPART_CONTENT_TYPE)-1, NULL, rfc1867_post_handler },
  550. { NULL, 0, NULL, NULL }
  551. };
  552. /* }}} */
  553. /* {{{ static int php_mb_parse_encoding_list()
  554. * Return 0 if input contains any illegal encoding, otherwise 1.
  555. * Even if any illegal encoding is detected the result may contain a list
  556. * of parsed encodings.
  557. */
  558. static int
  559. php_mb_parse_encoding_list(const char *value, int value_length, enum mbfl_no_encoding **return_list, int *return_size, int persistent TSRMLS_DC)
  560. {
  561. int n, l, size, bauto, ret = 1;
  562. char *p, *p1, *p2, *endp, *tmpstr;
  563. enum mbfl_no_encoding no_encoding;
  564. enum mbfl_no_encoding *src, *entry, *list;
  565. list = NULL;
  566. if (value == NULL || value_length <= 0) {
  567. if (return_list) {
  568. *return_list = NULL;
  569. }
  570. if (return_size) {
  571. *return_size = 0;
  572. }
  573. return 0;
  574. } else {
  575. enum mbfl_no_encoding *identify_list;
  576. int identify_list_size;
  577. identify_list = MBSTRG(default_detect_order_list);
  578. identify_list_size = MBSTRG(default_detect_order_list_size);
  579. /* copy the value string for work */
  580. if (value[0]=='"' && value[value_length-1]=='"' && value_length>2) {
  581. tmpstr = (char *)estrndup(value+1, value_length-2);
  582. value_length -= 2;
  583. }
  584. else
  585. tmpstr = (char *)estrndup(value, value_length);
  586. if (tmpstr == NULL) {
  587. return 0;
  588. }
  589. /* count the number of listed encoding names */
  590. endp = tmpstr + value_length;
  591. n = 1;
  592. p1 = tmpstr;
  593. while ((p2 = php_memnstr(p1, ",", 1, endp)) != NULL) {
  594. p1 = p2 + 1;
  595. n++;
  596. }
  597. size = n + identify_list_size;
  598. /* make list */
  599. list = (enum mbfl_no_encoding *)pecalloc(size, sizeof(int), persistent);
  600. if (list != NULL) {
  601. entry = list;
  602. n = 0;
  603. bauto = 0;
  604. p1 = tmpstr;
  605. do {
  606. p2 = p = php_memnstr(p1, ",", 1, endp);
  607. if (p == NULL) {
  608. p = endp;
  609. }
  610. *p = '\0';
  611. /* trim spaces */
  612. while (p1 < p && (*p1 == ' ' || *p1 == '\t')) {
  613. p1++;
  614. }
  615. p--;
  616. while (p > p1 && (*p == ' ' || *p == '\t')) {
  617. *p = '\0';
  618. p--;
  619. }
  620. /* convert to the encoding number and check encoding */
  621. if (strcasecmp(p1, "auto") == 0) {
  622. if (!bauto) {
  623. bauto = 1;
  624. l = identify_list_size;
  625. src = identify_list;
  626. while (l > 0) {
  627. *entry++ = *src++;
  628. l--;
  629. n++;
  630. }
  631. }
  632. } else {
  633. no_encoding = mbfl_name2no_encoding(p1);
  634. if (no_encoding != mbfl_no_encoding_invalid) {
  635. *entry++ = no_encoding;
  636. n++;
  637. } else {
  638. ret = 0;
  639. }
  640. }
  641. p1 = p2 + 1;
  642. } while (n < size && p2 != NULL);
  643. if (n > 0) {
  644. if (return_list) {
  645. *return_list = list;
  646. } else {
  647. pefree(list, persistent);
  648. }
  649. } else {
  650. pefree(list, persistent);
  651. if (return_list) {
  652. *return_list = NULL;
  653. }
  654. ret = 0;
  655. }
  656. if (return_size) {
  657. *return_size = n;
  658. }
  659. } else {
  660. if (return_list) {
  661. *return_list = NULL;
  662. }
  663. if (return_size) {
  664. *return_size = 0;
  665. }
  666. ret = 0;
  667. }
  668. efree(tmpstr);
  669. }
  670. return ret;
  671. }
  672. /* }}} */
  673. /* {{{ MBSTRING_API php_mb_check_encoding_list */
  674. MBSTRING_API int php_mb_check_encoding_list(const char *encoding_list TSRMLS_DC) {
  675. return php_mb_parse_encoding_list(encoding_list, strlen(encoding_list), NULL, NULL, 0 TSRMLS_CC);
  676. }
  677. /* }}} */
  678. /* {{{ static int php_mb_parse_encoding_array()
  679. * Return 0 if input contains any illegal encoding, otherwise 1.
  680. * Even if any illegal encoding is detected the result may contain a list
  681. * of parsed encodings.
  682. */
  683. static int
  684. php_mb_parse_encoding_array(zval *array, enum mbfl_no_encoding **return_list, int *return_size, int persistent TSRMLS_DC)
  685. {
  686. zval **hash_entry;
  687. HashTable *target_hash;
  688. int i, n, l, size, bauto,ret = 1;
  689. enum mbfl_no_encoding no_encoding;
  690. enum mbfl_no_encoding *src, *list, *entry;
  691. list = NULL;
  692. if (Z_TYPE_P(array) == IS_ARRAY) {
  693. enum mbfl_no_encoding *identify_list;
  694. int identify_list_size;
  695. identify_list = MBSTRG(default_detect_order_list);
  696. identify_list_size = MBSTRG(default_detect_order_list_size);
  697. target_hash = Z_ARRVAL_P(array);
  698. zend_hash_internal_pointer_reset(target_hash);
  699. i = zend_hash_num_elements(target_hash);
  700. size = i + identify_list_size;
  701. list = (enum mbfl_no_encoding *)pecalloc(size, sizeof(int), persistent);
  702. if (list != NULL) {
  703. entry = list;
  704. bauto = 0;
  705. n = 0;
  706. while (i > 0) {
  707. if (zend_hash_get_current_data(target_hash, (void **) &hash_entry) == FAILURE) {
  708. break;
  709. }
  710. convert_to_string_ex(hash_entry);
  711. if (strcasecmp(Z_STRVAL_PP(hash_entry), "auto") == 0) {
  712. if (!bauto) {
  713. bauto = 1;
  714. l = identify_list_size;
  715. src = identify_list;
  716. while (l > 0) {
  717. *entry++ = *src++;
  718. l--;
  719. n++;
  720. }
  721. }
  722. } else {
  723. no_encoding = mbfl_name2no_encoding(Z_STRVAL_PP(hash_entry));
  724. if (no_encoding != mbfl_no_encoding_invalid) {
  725. *entry++ = no_encoding;
  726. n++;
  727. } else {
  728. ret = 0;
  729. }
  730. }
  731. zend_hash_move_forward(target_hash);
  732. i--;
  733. }
  734. if (n > 0) {
  735. if (return_list) {
  736. *return_list = list;
  737. } else {
  738. pefree(list, persistent);
  739. }
  740. } else {
  741. pefree(list, persistent);
  742. if (return_list) {
  743. *return_list = NULL;
  744. }
  745. ret = 0;
  746. }
  747. if (return_size) {
  748. *return_size = n;
  749. }
  750. } else {
  751. if (return_list) {
  752. *return_list = NULL;
  753. }
  754. if (return_size) {
  755. *return_size = 0;
  756. }
  757. ret = 0;
  758. }
  759. }
  760. return ret;
  761. }
  762. /* }}} */
  763. static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC);
  764. static int _php_mb_match_regex(void *opaque, const char *str, size_t str_len);
  765. static void _php_mb_free_regex(void *opaque);
  766. #if HAVE_ONIG
  767. /* {{{ _php_mb_compile_regex */
  768. static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
  769. {
  770. php_mb_regex_t *retval;
  771. OnigErrorInfo err_info;
  772. int err_code;
  773. if ((err_code = onig_new(&retval,
  774. (const OnigUChar *)pattern,
  775. (const OnigUChar *)pattern + strlen(pattern),
  776. ONIG_OPTION_IGNORECASE | ONIG_OPTION_DONT_CAPTURE_GROUP,
  777. ONIG_ENCODING_ASCII, &OnigSyntaxPerl, &err_info))) {
  778. OnigUChar err_str[ONIG_MAX_ERROR_MESSAGE_LEN];
  779. onig_error_code_to_str(err_str, err_code, err_info);
  780. php_error_docref(NULL TSRMLS_CC, E_WARNING, "%s: %s", pattern, err_str);
  781. retval = NULL;
  782. }
  783. return retval;
  784. }
  785. /* }}} */
  786. /* {{{ _php_mb_match_regex */
  787. static int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
  788. {
  789. return onig_search((php_mb_regex_t *)opaque, (const OnigUChar *)str,
  790. (const OnigUChar*)str + str_len, (const OnigUChar *)str,
  791. (const OnigUChar*)str + str_len, NULL, ONIG_OPTION_NONE) >= 0;
  792. }
  793. /* }}} */
  794. /* {{{ _php_mb_free_regex */
  795. static void _php_mb_free_regex(void *opaque)
  796. {
  797. onig_free((php_mb_regex_t *)opaque);
  798. }
  799. /* }}} */
  800. #elif HAVE_PCRE || HAVE_BUNDLED_PCRE
  801. /* {{{ _php_mb_compile_regex */
  802. static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
  803. {
  804. pcre *retval;
  805. const char *err_str;
  806. int err_offset;
  807. if (!(retval = pcre_compile(pattern,
  808. PCRE_CASELESS, &err_str, &err_offset, NULL))) {
  809. php_error_docref(NULL TSRMLS_CC, E_WARNING, "%s (offset=%d): %s", pattern, err_offset, err_str);
  810. }
  811. return retval;
  812. }
  813. /* }}} */
  814. /* {{{ _php_mb_match_regex */
  815. static int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
  816. {
  817. return pcre_exec((pcre *)opaque, NULL, str, (int)str_len, 0,
  818. 0, NULL, 0) >= 0;
  819. }
  820. /* }}} */
  821. /* {{{ _php_mb_free_regex */
  822. static void _php_mb_free_regex(void *opaque)
  823. {
  824. pcre_free(opaque);
  825. }
  826. /* }}} */
  827. #endif
  828. /* {{{ php_mb_nls_get_default_detect_order_list */
  829. static int php_mb_nls_get_default_detect_order_list(enum mbfl_no_language lang, enum mbfl_no_encoding **plist, int* plist_size)
  830. {
  831. size_t i;
  832. *plist = (enum mbfl_no_encoding *) php_mb_default_identify_list_neut;
  833. *plist_size = sizeof(php_mb_default_identify_list_neut) / sizeof(php_mb_default_identify_list_neut[0]);
  834. for (i = 0; i < sizeof(php_mb_default_identify_list) / sizeof(php_mb_default_identify_list[0]); i++) {
  835. if (php_mb_default_identify_list[i].lang == lang) {
  836. *plist = (enum mbfl_no_encoding *)php_mb_default_identify_list[i].list;
  837. *plist_size = php_mb_default_identify_list[i].list_size;
  838. return 1;
  839. }
  840. }
  841. return 0;
  842. }
  843. /* }}} */
  844. /* {{{ php.ini directive handler */
  845. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_language) */
  846. static PHP_INI_MH(OnUpdate_mbstring_language)
  847. {
  848. enum mbfl_no_language no_language;
  849. no_language = mbfl_name2no_language(new_value);
  850. if (no_language == mbfl_no_language_invalid) {
  851. MBSTRG(language) = mbfl_no_language_neutral;
  852. return FAILURE;
  853. }
  854. MBSTRG(language) = no_language;
  855. php_mb_nls_get_default_detect_order_list(no_language, &MBSTRG(default_detect_order_list), &MBSTRG(default_detect_order_list_size));
  856. return SUCCESS;
  857. }
  858. /* }}} */
  859. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_detect_order) */
  860. static PHP_INI_MH(OnUpdate_mbstring_detect_order)
  861. {
  862. enum mbfl_no_encoding *list;
  863. int size;
  864. if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
  865. if (MBSTRG(detect_order_list)) {
  866. free(MBSTRG(detect_order_list));
  867. }
  868. MBSTRG(detect_order_list) = list;
  869. MBSTRG(detect_order_list_size) = size;
  870. } else {
  871. if (MBSTRG(detect_order_list)) {
  872. free(MBSTRG(detect_order_list));
  873. MBSTRG(detect_order_list) = NULL;
  874. }
  875. return FAILURE;
  876. }
  877. return SUCCESS;
  878. }
  879. /* }}} */
  880. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_input) */
  881. static PHP_INI_MH(OnUpdate_mbstring_http_input)
  882. {
  883. enum mbfl_no_encoding *list;
  884. int size;
  885. if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
  886. if (MBSTRG(http_input_list)) {
  887. free(MBSTRG(http_input_list));
  888. }
  889. MBSTRG(http_input_list) = list;
  890. MBSTRG(http_input_list_size) = size;
  891. } else {
  892. if (MBSTRG(http_input_list)) {
  893. free(MBSTRG(http_input_list));
  894. MBSTRG(http_input_list) = NULL;
  895. }
  896. MBSTRG(http_input_list_size) = 0;
  897. return FAILURE;
  898. }
  899. return SUCCESS;
  900. }
  901. /* }}} */
  902. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_output) */
  903. static PHP_INI_MH(OnUpdate_mbstring_http_output)
  904. {
  905. enum mbfl_no_encoding no_encoding;
  906. no_encoding = mbfl_name2no_encoding(new_value);
  907. if (no_encoding != mbfl_no_encoding_invalid) {
  908. MBSTRG(http_output_encoding) = no_encoding;
  909. MBSTRG(current_http_output_encoding) = no_encoding;
  910. } else {
  911. MBSTRG(http_output_encoding) = mbfl_no_encoding_pass;
  912. MBSTRG(current_http_output_encoding) = mbfl_no_encoding_pass;
  913. if (new_value != NULL && new_value_length > 0) {
  914. return FAILURE;
  915. }
  916. }
  917. return SUCCESS;
  918. }
  919. /* }}} */
  920. /* {{{ static _php_mb_ini_mbstring_internal_encoding_set */
  921. int _php_mb_ini_mbstring_internal_encoding_set(const char *new_value, uint new_value_length TSRMLS_DC)
  922. {
  923. enum mbfl_no_encoding no_encoding;
  924. const char *enc_name = NULL;
  925. uint enc_name_len = 0;
  926. no_encoding = new_value ? mbfl_name2no_encoding(new_value):
  927. mbfl_no_encoding_invalid;
  928. if (no_encoding != mbfl_no_encoding_invalid) {
  929. enc_name = new_value;
  930. enc_name_len = new_value_length;
  931. } else {
  932. switch (MBSTRG(language)) {
  933. case mbfl_no_language_uni:
  934. enc_name = "UTF-8";
  935. enc_name_len = sizeof("UTF-8") - 1;
  936. break;
  937. case mbfl_no_language_japanese:
  938. enc_name = "EUC-JP";
  939. enc_name_len = sizeof("EUC-JP") - 1;
  940. break;
  941. case mbfl_no_language_korean:
  942. enc_name = "EUC-KR";
  943. enc_name_len = sizeof("EUC-KR") - 1;
  944. break;
  945. case mbfl_no_language_simplified_chinese:
  946. enc_name = "EUC-CN";
  947. enc_name_len = sizeof("EUC-CN") - 1;
  948. break;
  949. case mbfl_no_language_traditional_chinese:
  950. enc_name = "EUC-TW";
  951. enc_name_len = sizeof("EUC-TW") - 1;
  952. break;
  953. case mbfl_no_language_russian:
  954. enc_name = "KOI8-R";
  955. enc_name_len = sizeof("KOI8-R") - 1;
  956. break;
  957. case mbfl_no_language_german:
  958. enc_name = "ISO-8859-15";
  959. enc_name_len = sizeof("ISO-8859-15") - 1;
  960. break;
  961. case mbfl_no_language_armenian:
  962. enc_name = "ArmSCII-8";
  963. enc_name_len = sizeof("ArmSCII-8") - 1;
  964. break;
  965. case mbfl_no_language_turkish:
  966. enc_name = "ISO-8859-9";
  967. enc_name_len = sizeof("ISO-8859-9") - 1;
  968. break;
  969. default:
  970. enc_name = "ISO-8859-1";
  971. enc_name_len = sizeof("ISO-8859-1") - 1;
  972. break;
  973. }
  974. no_encoding = mbfl_name2no_encoding(enc_name);
  975. }
  976. MBSTRG(internal_encoding) = no_encoding;
  977. MBSTRG(current_internal_encoding) = no_encoding;
  978. #if HAVE_MBREGEX
  979. {
  980. const char *enc_name = new_value;
  981. if (FAILURE == php_mb_regex_set_default_mbctype(enc_name TSRMLS_CC)) {
  982. /* falls back to EUC-JP if an unknown encoding name is given */
  983. enc_name = "EUC-JP";
  984. php_mb_regex_set_default_mbctype(enc_name TSRMLS_CC);
  985. }
  986. php_mb_regex_set_mbctype(new_value TSRMLS_CC);
  987. }
  988. #endif
  989. return SUCCESS;
  990. }
  991. /* }}} */
  992. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_internal_encoding) */
  993. static PHP_INI_MH(OnUpdate_mbstring_internal_encoding)
  994. {
  995. if (stage == PHP_INI_STAGE_STARTUP || stage == PHP_INI_STAGE_SHUTDOWN
  996. || stage == PHP_INI_STAGE_RUNTIME) {
  997. return _php_mb_ini_mbstring_internal_encoding_set(new_value, new_value_length TSRMLS_CC);
  998. } else {
  999. /* the corresponding mbstring globals needs to be set according to the
  1000. * ini value in the later stage because it never falls back to the
  1001. * default value if 1. no value for mbstring.internal_encoding is given,
  1002. * 2. mbstring.language directive is processed in per-dir or runtime
  1003. * context and 3. call to the handler for mbstring.language is done
  1004. * after mbstring.internal_encoding is handled. */
  1005. return SUCCESS;
  1006. }
  1007. }
  1008. /* }}} */
  1009. #ifdef ZEND_MULTIBYTE
  1010. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_script_encoding) */
  1011. static PHP_INI_MH(OnUpdate_mbstring_script_encoding)
  1012. {
  1013. int *list, size;
  1014. if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
  1015. if (MBSTRG(script_encoding_list) != NULL) {
  1016. free(MBSTRG(script_encoding_list));
  1017. }
  1018. MBSTRG(script_encoding_list) = list;
  1019. MBSTRG(script_encoding_list_size) = size;
  1020. } else {
  1021. if (MBSTRG(script_encoding_list) != NULL) {
  1022. free(MBSTRG(script_encoding_list));
  1023. }
  1024. MBSTRG(script_encoding_list) = NULL;
  1025. MBSTRG(script_encoding_list_size) = 0;
  1026. return FAILURE;
  1027. }
  1028. return SUCCESS;
  1029. }
  1030. /* }}} */
  1031. #endif /* ZEND_MULTIBYTE */
  1032. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_substitute_character) */
  1033. static PHP_INI_MH(OnUpdate_mbstring_substitute_character)
  1034. {
  1035. int c;
  1036. char *endptr = NULL;
  1037. if (new_value != NULL) {
  1038. if (strcasecmp("none", new_value) == 0) {
  1039. MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE;
  1040. MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE;
  1041. } else if (strcasecmp("long", new_value) == 0) {
  1042. MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_LONG;
  1043. MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_LONG;
  1044. } else if (strcasecmp("entity", new_value) == 0) {
  1045. MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_ENTITY;
  1046. MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_ENTITY;
  1047. } else {
  1048. MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1049. MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1050. if (new_value_length >0) {
  1051. c = strtol(new_value, &endptr, 0);
  1052. if (*endptr == '\0') {
  1053. MBSTRG(filter_illegal_substchar) = c;
  1054. MBSTRG(current_filter_illegal_substchar) = c;
  1055. }
  1056. }
  1057. }
  1058. } else {
  1059. MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1060. MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1061. MBSTRG(filter_illegal_substchar) = 0x3f; /* '?' */
  1062. MBSTRG(current_filter_illegal_substchar) = 0x3f; /* '?' */
  1063. }
  1064. return SUCCESS;
  1065. }
  1066. /* }}} */
  1067. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_encoding_translation) */
  1068. static PHP_INI_MH(OnUpdate_mbstring_encoding_translation)
  1069. {
  1070. if (new_value == NULL) {
  1071. return FAILURE;
  1072. }
  1073. OnUpdateBool(entry, new_value, new_value_length, mh_arg1, mh_arg2, mh_arg3, stage TSRMLS_CC);
  1074. if (MBSTRG(encoding_translation)) {
  1075. sapi_unregister_post_entry(php_post_entries TSRMLS_CC);
  1076. sapi_register_post_entries(mbstr_post_entries TSRMLS_CC);
  1077. } else {
  1078. sapi_unregister_post_entry(mbstr_post_entries TSRMLS_CC);
  1079. sapi_register_post_entries(php_post_entries TSRMLS_CC);
  1080. }
  1081. return SUCCESS;
  1082. }
  1083. /* }}} */
  1084. /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_output_conv_mimetypes */
  1085. static PHP_INI_MH(OnUpdate_mbstring_http_output_conv_mimetypes)
  1086. {
  1087. zval tmp;
  1088. void *re = NULL;
  1089. if (!new_value) {
  1090. new_value = entry->orig_value;
  1091. new_value_length = entry->orig_value_length;
  1092. }
  1093. php_trim(new_value, new_value_length, NULL, 0, &tmp, 3 TSRMLS_CC);
  1094. if (Z_STRLEN(tmp) > 0) {
  1095. if (!(re = _php_mb_compile_regex(Z_STRVAL(tmp) TSRMLS_CC))) {
  1096. zval_dtor(&tmp);
  1097. return FAILURE;
  1098. }
  1099. }
  1100. if (MBSTRG(http_output_conv_mimetypes)) {
  1101. _php_mb_free_regex(MBSTRG(http_output_conv_mimetypes));
  1102. }
  1103. MBSTRG(http_output_conv_mimetypes) = re;
  1104. zval_dtor(&tmp);
  1105. return SUCCESS;
  1106. }
  1107. /* }}} */
  1108. /* }}} */
  1109. /* {{{ php.ini directive registration */
  1110. PHP_INI_BEGIN()
  1111. PHP_INI_ENTRY("mbstring.language", "neutral", PHP_INI_ALL, OnUpdate_mbstring_language)
  1112. PHP_INI_ENTRY("mbstring.detect_order", NULL, PHP_INI_ALL, OnUpdate_mbstring_detect_order)
  1113. PHP_INI_ENTRY("mbstring.http_input", "pass", PHP_INI_ALL, OnUpdate_mbstring_http_input)
  1114. PHP_INI_ENTRY("mbstring.http_output", "pass", PHP_INI_ALL, OnUpdate_mbstring_http_output)
  1115. PHP_INI_ENTRY("mbstring.internal_encoding", NULL, PHP_INI_ALL, OnUpdate_mbstring_internal_encoding)
  1116. #ifdef ZEND_MULTIBYTE
  1117. PHP_INI_ENTRY("mbstring.script_encoding", NULL, PHP_INI_ALL, OnUpdate_mbstring_script_encoding)
  1118. #endif /* ZEND_MULTIBYTE */
  1119. PHP_INI_ENTRY("mbstring.substitute_character", NULL, PHP_INI_ALL, OnUpdate_mbstring_substitute_character)
  1120. STD_PHP_INI_ENTRY("mbstring.func_overload", "0",
  1121. PHP_INI_SYSTEM, OnUpdateLong, func_overload, zend_mbstring_globals, mbstring_globals)
  1122. STD_PHP_INI_BOOLEAN("mbstring.encoding_translation", "0",
  1123. PHP_INI_SYSTEM | PHP_INI_PERDIR,
  1124. OnUpdate_mbstring_encoding_translation,
  1125. encoding_translation, zend_mbstring_globals, mbstring_globals)
  1126. PHP_INI_ENTRY("mbstring.http_output_conv_mimetypes",
  1127. "^(text/|application/xhtml\\+xml)",
  1128. PHP_INI_ALL,
  1129. OnUpdate_mbstring_http_output_conv_mimetypes)
  1130. STD_PHP_INI_BOOLEAN("mbstring.strict_detection", "0",
  1131. PHP_INI_ALL,
  1132. OnUpdateLong,
  1133. strict_detection, zend_mbstring_globals, mbstring_globals)
  1134. PHP_INI_END()
  1135. /* }}} */
  1136. /* {{{ module global initialize handler */
  1137. static PHP_GINIT_FUNCTION(mbstring)
  1138. {
  1139. mbstring_globals->language = mbfl_no_language_uni;
  1140. mbstring_globals->internal_encoding = mbfl_no_encoding_invalid;
  1141. mbstring_globals->current_internal_encoding = mbstring_globals->internal_encoding;
  1142. #ifdef ZEND_MULTIBYTE
  1143. mbstring_globals->script_encoding_list = NULL;
  1144. mbstring_globals->script_encoding_list_size = 0;
  1145. #endif /* ZEND_MULTIBYTE */
  1146. mbstring_globals->http_output_encoding = mbfl_no_encoding_pass;
  1147. mbstring_globals->current_http_output_encoding = mbfl_no_encoding_pass;
  1148. mbstring_globals->http_input_identify = mbfl_no_encoding_invalid;
  1149. mbstring_globals->http_input_identify_get = mbfl_no_encoding_invalid;
  1150. mbstring_globals->http_input_identify_post = mbfl_no_encoding_invalid;
  1151. mbstring_globals->http_input_identify_cookie = mbfl_no_encoding_invalid;
  1152. mbstring_globals->http_input_identify_string = mbfl_no_encoding_invalid;
  1153. mbstring_globals->http_input_list = NULL;
  1154. mbstring_globals->http_input_list_size = 0;
  1155. mbstring_globals->detect_order_list = NULL;
  1156. mbstring_globals->detect_order_list_size = 0;
  1157. mbstring_globals->current_detect_order_list = NULL;
  1158. mbstring_globals->current_detect_order_list_size = 0;
  1159. mbstring_globals->default_detect_order_list = (enum mbfl_no_encoding *) php_mb_default_identify_list_neut;
  1160. mbstring_globals->default_detect_order_list_size = sizeof(php_mb_default_identify_list_neut) / sizeof(php_mb_default_identify_list_neut[0]);
  1161. mbstring_globals->filter_illegal_mode = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1162. mbstring_globals->filter_illegal_substchar = 0x3f; /* '?' */
  1163. mbstring_globals->current_filter_illegal_mode = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
  1164. mbstring_globals->current_filter_illegal_substchar = 0x3f; /* '?' */
  1165. mbstring_globals->illegalchars = 0;
  1166. mbstring_globals->func_overload = 0;
  1167. mbstring_globals->encoding_translation = 0;
  1168. mbstring_globals->strict_detection = 0;
  1169. mbstring_globals->outconv = NULL;
  1170. mbstring_globals->http_output_conv_mimetypes = NULL;
  1171. #if HAVE_MBREGEX
  1172. mbstring_globals->mb_regex_globals = php_mb_regex_globals_alloc(TSRMLS_C);
  1173. #endif
  1174. }
  1175. /* }}} */
  1176. /* {{{ PHP_GSHUTDOWN_FUNCTION */
  1177. static PHP_GSHUTDOWN_FUNCTION(mbstring)
  1178. {
  1179. if (mbstring_globals->http_input_list) {
  1180. free(mbstring_globals->http_input_list);
  1181. }
  1182. #ifdef ZEND_MULTIBYTE
  1183. if (mbstring_globals->script_encoding_list) {
  1184. free(mbstring_globals->script_encoding_list);
  1185. }
  1186. #endif /* ZEND_MULTIBYTE */
  1187. if (mbstring_globals->detect_order_list) {
  1188. free(mbstring_globals->detect_order_list);
  1189. }
  1190. if (mbstring_globals->http_output_conv_mimetypes) {
  1191. _php_mb_free_regex(mbstring_globals->http_output_conv_mimetypes);
  1192. }
  1193. #if HAVE_MBREGEX
  1194. php_mb_regex_globals_free(mbstring_globals->mb_regex_globals TSRMLS_CC);
  1195. #endif
  1196. }
  1197. /* }}} */
  1198. /* {{{ PHP_MINIT_FUNCTION(mbstring) */
  1199. PHP_MINIT_FUNCTION(mbstring)
  1200. {
  1201. __mbfl_allocators = &_php_mb_allocators;
  1202. REGISTER_INI_ENTRIES();
  1203. /* This is a global handler. Should not be set in a per-request handler. */
  1204. sapi_register_treat_data(mbstr_treat_data);
  1205. /* Post handlers are stored in the thread-local context. */
  1206. if (MBSTRG(encoding_translation)) {
  1207. sapi_register_post_entries(mbstr_post_entries TSRMLS_CC);
  1208. }
  1209. REGISTER_LONG_CONSTANT("MB_OVERLOAD_MAIL", MB_OVERLOAD_MAIL, CONST_CS | CONST_PERSISTENT);
  1210. REGISTER_LONG_CONSTANT("MB_OVERLOAD_STRING", MB_OVERLOAD_STRING, CONST_CS | CONST_PERSISTENT);
  1211. REGISTER_LONG_CONSTANT("MB_OVERLOAD_REGEX", MB_OVERLOAD_REGEX, CONST_CS | CONST_PERSISTENT);
  1212. REGISTER_LONG_CONSTANT("MB_CASE_UPPER", PHP_UNICODE_CASE_UPPER, CONST_CS | CONST_PERSISTENT);
  1213. REGISTER_LONG_CONSTANT("MB_CASE_LOWER", PHP_UNICODE_CASE_LOWER, CONST_CS | CONST_PERSISTENT);
  1214. REGISTER_LONG_CONSTANT("MB_CASE_TITLE", PHP_UNICODE_CASE_TITLE, CONST_CS | CONST_PERSISTENT);
  1215. #if HAVE_MBREGEX
  1216. PHP_MINIT(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
  1217. #endif
  1218. return SUCCESS;
  1219. }
  1220. /* }}} */
  1221. /* {{{ PHP_MSHUTDOWN_FUNCTION(mbstring) */
  1222. PHP_MSHUTDOWN_FUNCTION(mbstring)
  1223. {
  1224. UNREGISTER_INI_ENTRIES();
  1225. #if HAVE_MBREGEX
  1226. PHP_MSHUTDOWN(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
  1227. #endif
  1228. return SUCCESS;
  1229. }
  1230. /* }}} */
  1231. /* {{{ PHP_RINIT_FUNCTION(mbstring) */
  1232. PHP_RINIT_FUNCTION(mbstring)
  1233. {
  1234. int n;
  1235. enum mbfl_no_encoding *list=NULL, *entry;
  1236. zend_function *func, *orig;
  1237. const struct mb_overload_def *p;
  1238. MBSTRG(current_internal_encoding) = MBSTRG(internal_encoding);
  1239. MBSTRG(current_http_output_encoding) = MBSTRG(http_output_encoding);
  1240. MBSTRG(current_filter_illegal_mode) = MBSTRG(filter_illegal_mode);
  1241. MBSTRG(current_filter_illegal_substchar) = MBSTRG(filter_illegal_substchar);
  1242. MBSTRG(illegalchars) = 0;
  1243. n = 0;
  1244. if (MBSTRG(detect_order_list)) {
  1245. list = MBSTRG(detect_order_list);
  1246. n = MBSTRG(detect_order_list_size);
  1247. }
  1248. if (n <= 0) {
  1249. list = MBSTRG(default_detect_order_list);
  1250. n = MBSTRG(default_detect_order_list_size);
  1251. }
  1252. entry = (enum mbfl_no_encoding *)safe_emalloc(n, sizeof(int), 0);
  1253. MBSTRG(current_detect_order_list) = entry;
  1254. MBSTRG(current_detect_order_list_size) = n;
  1255. while (n > 0) {
  1256. *entry++ = *list++;
  1257. n--;
  1258. }
  1259. /* override original function. */
  1260. if (MBSTRG(func_overload)){
  1261. p = &(mb_ovld[0]);
  1262. while (p->type > 0) {
  1263. if ((MBSTRG(func_overload) & p->type) == p->type &&
  1264. zend_hash_find(EG(function_table), p->save_func,
  1265. strlen(p->save_func)+1, (void **)&orig) != SUCCESS) {
  1266. zend_hash_find(EG(function_table), p->ovld_func, strlen(p->ovld_func)+1 , (void **)&func);
  1267. if (zend_hash_find(EG(function_table), p->orig_func, strlen(p->orig_func)+1, (void **)&orig) != SUCCESS) {
  1268. php_error_docref("ref.mbstring" TSRMLS_CC, E_WARNING, "mbstring couldn't find function %s.", p->orig_func);
  1269. return FAILURE;
  1270. } else {
  1271. zend_hash_add(EG(function_table), p->save_func, strlen(p->save_func)+1, orig, sizeof(zend_function), NULL);
  1272. if (zend_hash_update(EG(function_table), p->orig_func, strlen(p->orig_func)+1, func, sizeof(zend_function),
  1273. NULL) == FAILURE) {
  1274. php_error_docref("ref.mbstring" TSRMLS_CC, E_WARNING, "mbstring couldn't replace function %s.", p->orig_func);
  1275. return FAILURE;
  1276. }
  1277. }
  1278. }
  1279. p++;
  1280. }
  1281. }
  1282. #if HAVE_MBREGEX
  1283. PHP_RINIT(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
  1284. #endif
  1285. #ifdef ZEND_MULTIBYTE
  1286. zend_multibyte_set_internal_encoding(mbfl_no_encoding2name(MBSTRG(internal_encoding)) TSRMLS_CC);
  1287. php_mb_set_zend_encoding(TSRMLS_C);
  1288. #endif /* ZEND_MULTIBYTE */
  1289. return SUCCESS;
  1290. }
  1291. /* }}} */
  1292. /* {{{ PHP_RSHUTDOWN_FUNCTION(mbstring) */
  1293. PHP_RSHUTDOWN_FUNCTION(mbstring)
  1294. {
  1295. const struct mb_overload_def *p;
  1296. zend_function *orig;
  1297. if (MBSTRG(current_detect_order_list) != NULL) {
  1298. efree(MBSTRG(current_detect_order_list));
  1299. MBSTRG(current_detect_order_list) = NULL;
  1300. MBSTRG(current_detect_order_list_size) = 0;
  1301. }
  1302. if (MBSTRG(outconv) != NULL) {
  1303. MBSTRG(illegalchars) += mbfl_buffer_illegalchars(MBSTRG(outconv));
  1304. mbfl_buffer_converter_delete(MBSTRG(outconv));
  1305. MBSTRG(outconv) = NULL;
  1306. }
  1307. /* clear http input identification. */
  1308. MBSTRG(http_input_identify) = mbfl_no_encoding_invalid;
  1309. MBSTRG(http_input_identify_post) = mbfl_no_encoding_invalid;
  1310. MBSTRG(http_input_identify_get) = mbfl_no_encoding_invalid;
  1311. MBSTRG(http_input_identify_cookie) = mbfl_no_encoding_invalid;
  1312. MBSTRG(http_input_identify_string) = mbfl_no_encoding_invalid;
  1313. /* clear overloaded function. */
  1314. if (MBSTRG(func_overload)){
  1315. p = &(mb_ovld[0]);
  1316. while (p->type > 0) {
  1317. if ((MBSTRG(func_overload) & p->type) == p->type &&
  1318. zend_hash_find(EG(function_table), p->save_func,
  1319. strlen(p->save_func)+1, (void **)&orig) == SUCCESS) {
  1320. zend_hash_update(EG(function_table), p->orig_func, strlen(p->orig_func)+1, orig, sizeof(zend_function), NULL);
  1321. zend_hash_del(EG(function_table), p->save_func, strlen(p->save_func)+1);
  1322. }
  1323. p++;
  1324. }
  1325. }
  1326. #if HAVE_MBREGEX
  1327. PHP_RSHUTDOWN(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
  1328. #endif
  1329. return SUCCESS;
  1330. }
  1331. /* }}} */
  1332. /* {{{ PHP_MINFO_FUNCTION(mbstring) */
  1333. PHP_MINFO_FUNCTION(mbstring)
  1334. {
  1335. php_info_print_table_start();
  1336. php_info_print_table_row(2, "Multibyte Support", "enabled");
  1337. php_info_print_table_row(2, "Multibyte string engine", "libmbfl");
  1338. php_info_print_table_row(2, "HTTP input encoding translation", MBSTRG(encoding_translation) ? "enabled": "disabled");
  1339. php_info_print_table_end();
  1340. php_info_print_table_start();
  1341. php_info_print_table_header(1, "mbstring extension makes use of \"streamable kanji code filter and converter\", which is distributed under the GNU Lesser General Public License version 2.1.");
  1342. php_info_print_table_end();
  1343. #if HAVE_MBREGEX
  1344. PHP_MINFO(mb_regex)(ZEND_MODULE_INFO_FUNC_ARGS_PASSTHRU);
  1345. #endif
  1346. DISPLAY_INI_ENTRIES();
  1347. }
  1348. /* }}} */
  1349. /* {{{ proto string mb_language([string language])
  1350. Sets the current language or Returns the current language as a string */
  1351. PHP_FUNCTION(mb_language)
  1352. {
  1353. char *name = NULL;
  1354. int name_len = 0;
  1355. if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &name, &name_len) == FAILURE) {
  1356. return;
  1357. }
  1358. if (name == NULL) {
  1359. RETVAL_STRING((char *)mbfl_no_language2name(MBSTRG(language)), 1);
  1360. } else {
  1361. if (FAILURE == zend_alter_ini_entry(
  1362. "mbstring.language", sizeof("mbstring.language"),
  1363. name, name_len, PHP_INI_USER, PHP_INI_STAGE_RUNTIME)) {
  1364. php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown language \"%s\"", name);
  1365. RETVAL_FALSE;
  1366. } else {
  1367. RETVAL_TRUE;
  1368. }
  1369. }
  1370. }
  1371. /* }}} */
  1372. /* {{{ proto string mb_internal_encoding([string encoding])
  1373. Sets the current internal encoding or Returns the current internal encoding as a string */
  1374. PHP_FUNCTION(mb_internal_encoding)
  1375. {
  1376. char *name = NULL;
  1377. int name_len;
  1378. enum mbfl_no_encoding no_encoding;
  1379. if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &name, &name_len) == FAILURE) {
  1380. RETURN_FALSE;
  1381. }
  1382. if (name == NULL) {
  1383. name = (char *)mbfl_no_encoding2name(MBSTRG(current_internal_encoding));
  1384. if (name != NULL) {
  1385. RETURN_STRING(name, 1);
  1386. } else {
  1387. RETURN_FALSE;
  1388. }
  1389. } else {
  1390. no_encoding = mbfl_name2no_encoding(name);
  1391. if (no_encoding == mbfl_no_encoding_invalid) {
  1392. php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown encoding \"%s\"", name);
  1393. RETURN_FALSE;
  1394. } else {
  1395. MBSTRG(current_internal_encoding) = no_encoding;
  1396. #ifdef ZEND_MULTIBYTE
  1397. /* TODO: make independent from mbstring.encoding_translation? */
  1398. if (MBSTRG(encoding_translation)) {
  1399. zend_multibyte_set_internal_encoding(name TSRMLS_CC);
  1400. }
  1401. #endif /* ZEND_MULTIBYTE */
  1402. RETURN_TRUE;
  1403. }
  1404. }
  1405. }
  1406. /* }}} */
  1407. /* {{{ proto mixed mb_http_input([string type])
  1408. Returns the input encoding */
  1409. PHP_FUNCTION(mb_http_input)
  1410. {
  1411. char *typ = NULL;
  1412. int typ_len;
  1413. int retname, n;
  1414. char *name, *list, *temp;
  1415. enum mbfl_no_encoding *entry;
  1416. enum mbfl_no_encoding result = mbfl_no_encoding_invalid;
  1417. retname = 1;
  1418. if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &typ, &typ_len) == FAILURE) {
  1419. RETURN_FALSE;
  1420. }
  1421. if (typ == NULL) {
  1422. result = MBSTRG(http_input_identify);
  1423. } else {
  1424. switch (*typ) {
  1425. case 'G':
  1426. case 'g':
  1427. result = MBSTRG(http_input_identify_get);
  1428. break;
  1429. case 'P':
  1430. case 'p':
  1431. result = MBSTRG(http_input_identify_post);
  1432. break;
  1433. case 'C':
  1434. case 'c':
  1435. result = MBSTRG(http_input_identify_cookie);
  1436. break;
  1437. case 'S':
  1438. case 's':
  1439. result = MBSTRG(http_input_identify_string);
  1440. break;
  1441. case 'I':
  1442. case 'i':
  1443. array_init(return_value);
  1444. entry = MBSTRG(http_input_list);
  1445. n = MBSTRG(http_input_list_size);
  1446. while (n > 0) {
  1447. name = (char *)mbfl_no_encoding2name(*entry);
  1448. if (name) {
  1449. add_next_index_string(return_value, name, 1);
  1450. }
  1451. entry++;
  1452. n--;
  1453. }
  1454. retname = 0;
  1455. break;
  1456. case 'L':
  1457. case 'l':
  1458. entry = MBSTRG(http_input_list);
  1459. n = MBSTRG(http_input_list_size);
  1460. list = NULL;
  1461. while (n > 0) {

Large files files are truncated, but you can click here to view the full file