/php5/ext/mbstring/mbstring.c
C | 4894 lines | 3937 code | 551 blank | 406 comment | 1119 complexity | 5d03371e366ee3b8905913514bf2535b 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
- /*
- +----------------------------------------------------------------------+
- | PHP Version 5 |
- +----------------------------------------------------------------------+
- | Copyright (c) 1997-2009 The PHP Group |
- +----------------------------------------------------------------------+
- | This source file is subject to version 3.01 of the PHP license, |
- | that is bundled with this package in the file LICENSE, and is |
- | available through the world-wide-web at the following url: |
- | http://www.php.net/license/3_01.txt |
- | If you did not receive a copy of the PHP license and are unable to |
- | obtain it through the world-wide-web, please send a note to |
- | license@php.net so we can mail you a copy immediately. |
- +----------------------------------------------------------------------+
- | Author: Tsukada Takuya <tsukada@fminn.nagano.nagano.jp> |
- | Rui Hirokawa <hirokawa@php.net> |
- +----------------------------------------------------------------------+
- */
- /* $Id: mbstring.c,v 1.224.2.22.2.25.2.53 2009/04/20 16:07:59 jani Exp $ */
- /*
- * PHP 4 Multibyte String module "mbstring"
- *
- * History:
- * 2000.5.19 Release php-4.0RC2_jstring-1.0
- * 2001.4.1 Release php4_jstring-1.0.91
- * 2001.4.30 Release php4_jstring-1.1 (contribute to The PHP Group)
- * 2001.5.1 Renamed from jstring to mbstring (hirokawa@php.net)
- */
- /*
- * PHP3 Internationalization support program.
- *
- * Copyright (c) 1999,2000 by the PHP3 internationalization team.
- * All rights reserved.
- *
- * See README_PHP3-i18n-ja for more detail.
- *
- * Authors:
- * Hironori Sato <satoh@jpnnet.com>
- * Shigeru Kanemoto <sgk@happysize.co.jp>
- * Tsukada Takuya <tsukada@fminn.nagano.nagano.jp>
- * Rui Hirokawa <rui_hirokawa@ybb.ne.jp>
- */
- /* {{{ includes */
- #ifdef HAVE_CONFIG_H
- #include "config.h"
- #endif
- #include "php.h"
- #include "php_ini.h"
- #include "php_variables.h"
- #include "mbstring.h"
- #include "ext/standard/php_string.h"
- #include "ext/standard/php_mail.h"
- #include "ext/standard/exec.h"
- #include "ext/standard/php_smart_str.h"
- #include "ext/standard/url.h"
- #include "main/php_output.h"
- #include "ext/standard/info.h"
- #include "libmbfl/mbfl/mbfl_allocators.h"
- #include "php_variables.h"
- #include "php_globals.h"
- #include "rfc1867.h"
- #include "php_content_types.h"
- #include "SAPI.h"
- #include "php_unicode.h"
- #include "TSRM.h"
- #include "mb_gpc.h"
- #if HAVE_MBREGEX
- #include "php_mbregex.h"
- #endif
- #ifdef ZEND_MULTIBYTE
- #include "zend_multibyte.h"
- #endif /* ZEND_MULTIBYTE */
- #if HAVE_ONIG
- #include "php_onig_compat.h"
- #include <oniguruma.h>
- #undef UChar
- #elif HAVE_PCRE || HAVE_BUNDLED_PCRE
- #include "ext/pcre/php_pcre.h"
- #endif
- /* }}} */
- #if HAVE_MBSTRING
- /* {{{ prototypes */
- ZEND_DECLARE_MODULE_GLOBALS(mbstring)
- static PHP_GINIT_FUNCTION(mbstring);
- static PHP_GSHUTDOWN_FUNCTION(mbstring);
- /* }}} */
- /* {{{ php_mb_default_identify_list */
- typedef struct _php_mb_nls_ident_list {
- enum mbfl_no_language lang;
- const enum mbfl_no_encoding* list;
- int list_size;
- } php_mb_nls_ident_list;
- static const enum mbfl_no_encoding php_mb_default_identify_list_ja[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_jis,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_euc_jp,
- mbfl_no_encoding_sjis
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_cn[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_euc_cn,
- mbfl_no_encoding_cp936
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_tw_hk[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_euc_tw,
- mbfl_no_encoding_big5
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_kr[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_euc_kr,
- mbfl_no_encoding_uhc
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_ru[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_koi8r,
- mbfl_no_encoding_cp1251,
- mbfl_no_encoding_cp866
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_hy[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_armscii8
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_tr[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_cp1254,
- mbfl_no_encoding_8859_9
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_ua[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8,
- mbfl_no_encoding_koi8u
- };
- static const enum mbfl_no_encoding php_mb_default_identify_list_neut[] = {
- mbfl_no_encoding_ascii,
- mbfl_no_encoding_utf8
- };
- static const php_mb_nls_ident_list php_mb_default_identify_list[] = {
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) },
- { 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]) }
- };
- /* }}} */
- /* {{{ mb_overload_def mb_ovld[] */
- static const struct mb_overload_def mb_ovld[] = {
- {MB_OVERLOAD_MAIL, "mail", "mb_send_mail", "mb_orig_mail"},
- {MB_OVERLOAD_STRING, "strlen", "mb_strlen", "mb_orig_strlen"},
- {MB_OVERLOAD_STRING, "strpos", "mb_strpos", "mb_orig_strpos"},
- {MB_OVERLOAD_STRING, "strrpos", "mb_strrpos", "mb_orig_strrpos"},
- {MB_OVERLOAD_STRING, "stripos", "mb_stripos", "mb_orig_stripos"},
- {MB_OVERLOAD_STRING, "strripos", "mb_strripos", "mb_orig_stripos"},
- {MB_OVERLOAD_STRING, "strstr", "mb_strstr", "mb_orig_strstr"},
- {MB_OVERLOAD_STRING, "strrchr", "mb_strrchr", "mb_orig_strrchr"},
- {MB_OVERLOAD_STRING, "stristr", "mb_stristr", "mb_orig_stristr"},
- {MB_OVERLOAD_STRING, "substr", "mb_substr", "mb_orig_substr"},
- {MB_OVERLOAD_STRING, "strtolower", "mb_strtolower", "mb_orig_strtolower"},
- {MB_OVERLOAD_STRING, "strtoupper", "mb_strtoupper", "mb_orig_strtoupper"},
- {MB_OVERLOAD_STRING, "substr_count", "mb_substr_count", "mb_orig_substr_count"},
- #if HAVE_MBREGEX
- {MB_OVERLOAD_REGEX, "ereg", "mb_ereg", "mb_orig_ereg"},
- {MB_OVERLOAD_REGEX, "eregi", "mb_eregi", "mb_orig_eregi"},
- {MB_OVERLOAD_REGEX, "ereg_replace", "mb_ereg_replace", "mb_orig_ereg_replace"},
- {MB_OVERLOAD_REGEX, "eregi_replace", "mb_eregi_replace", "mb_orig_eregi_replace"},
- {MB_OVERLOAD_REGEX, "split", "mb_split", "mb_orig_split"},
- #endif
- {0, NULL, NULL, NULL}
- };
- /* }}} */
- /* {{{ arginfo */
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_language, 0, 0, 0)
- ZEND_ARG_INFO(0, language)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_internal_encoding, 0, 0, 0)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_http_input, 0, 0, 0)
- ZEND_ARG_INFO(0, type)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_http_output, 0, 0, 0)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_detect_order, 0, 0, 0)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substitute_character, 0, 0, 0)
- ZEND_ARG_INFO(0, substchar)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_preferred_mime_name, 0, 0, 1)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_parse_str, 0, 0, 1)
- ZEND_ARG_INFO(0, encoded_string)
- ZEND_ARG_INFO(1, result)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_output_handler, 0, 0, 2)
- ZEND_ARG_INFO(0, contents)
- ZEND_ARG_INFO(0, status)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strlen, 0, 0, 1)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strpos, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, offset)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrpos, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, offset)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_stripos, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, offset)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strripos, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, offset)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strstr, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, part)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrchr, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, part)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_stristr, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, part)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strrichr, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, part)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substr_count, 0, 0, 2)
- ZEND_ARG_INFO(0, haystack)
- ZEND_ARG_INFO(0, needle)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_substr, 0, 0, 2)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, start)
- ZEND_ARG_INFO(0, length)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strcut, 0, 0, 2)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, start)
- ZEND_ARG_INFO(0, length)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strwidth, 0, 0, 1)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strimwidth, 0, 0, 3)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, start)
- ZEND_ARG_INFO(0, width)
- ZEND_ARG_INFO(0, trimmarker)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_encoding, 0, 0, 2)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, to)
- ZEND_ARG_INFO(0, from)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_case, 0, 0, 2)
- ZEND_ARG_INFO(0, sourcestring)
- ZEND_ARG_INFO(0, mode)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strtoupper, 0, 0, 1)
- ZEND_ARG_INFO(0, sourcestring)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_strtolower, 0, 0, 1)
- ZEND_ARG_INFO(0, sourcestring)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_detect_encoding, 0, 0, 1)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, encoding_list)
- ZEND_ARG_INFO(0, strict)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO(arginfo_mb_list_encodings, 0)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encoding_aliases, 0, 0, 1)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encode_mimeheader, 0, 0, 1)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, charset)
- ZEND_ARG_INFO(0, transfer)
- ZEND_ARG_INFO(0, linefeed)
- ZEND_ARG_INFO(0, indent)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_decode_mimeheader, 0, 0, 1)
- ZEND_ARG_INFO(0, string)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_kana, 0, 0, 1)
- ZEND_ARG_INFO(0, str)
- ZEND_ARG_INFO(0, option)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_convert_variables, 1, 0, 3)
- ZEND_ARG_INFO(0, to)
- ZEND_ARG_INFO(0, from)
- ZEND_ARG_INFO(1, ...)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_encode_numericentity, 0, 0, 2)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, convmap)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_decode_numericentity, 0, 0, 2)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, convmap)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_send_mail, 0, 0, 3)
- ZEND_ARG_INFO(0, to)
- ZEND_ARG_INFO(0, subject)
- ZEND_ARG_INFO(0, message)
- ZEND_ARG_INFO(0, additional_headers)
- ZEND_ARG_INFO(0, additional_parameters)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_get_info, 0, 0, 0)
- ZEND_ARG_INFO(0, type)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_check_encoding, 0, 0, 0)
- ZEND_ARG_INFO(0, var)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_regex_encoding, 0, 0, 0)
- ZEND_ARG_INFO(0, encoding)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg, 0, 0, 2)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(1, registers)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_eregi, 0, 0, 2)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(1, registers)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_replace, 0, 0, 3)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, replacement)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_eregi_replace, 0, 0, 3)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, replacement)
- ZEND_ARG_INFO(0, string)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_split, 0, 0, 2)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, limit)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_match, 0, 0, 2)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search, 0, 0, 0)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_pos, 0, 0, 0)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_regs, 0, 0, 0)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_init, 0, 0, 1)
- ZEND_ARG_INFO(0, string)
- ZEND_ARG_INFO(0, pattern)
- ZEND_ARG_INFO(0, option)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO(arginfo_mb_ereg_search_getregs, 0)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO(arginfo_mb_ereg_search_getpos, 0)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_ereg_search_setpos, 0, 0, 1)
- ZEND_ARG_INFO(0, position)
- ZEND_END_ARG_INFO()
- ZEND_BEGIN_ARG_INFO_EX(arginfo_mb_regex_set_options, 0, 0, 0)
- ZEND_ARG_INFO(0, options)
- ZEND_END_ARG_INFO()
- /* }}} */
- /* {{{ zend_function_entry mbstring_functions[] */
- const zend_function_entry mbstring_functions[] = {
- PHP_FE(mb_convert_case, arginfo_mb_convert_case)
- PHP_FE(mb_strtoupper, arginfo_mb_strtoupper)
- PHP_FE(mb_strtolower, arginfo_mb_strtolower)
- PHP_FE(mb_language, arginfo_mb_language)
- PHP_FE(mb_internal_encoding, arginfo_mb_internal_encoding)
- PHP_FE(mb_http_input, arginfo_mb_http_input)
- PHP_FE(mb_http_output, arginfo_mb_http_output)
- PHP_FE(mb_detect_order, arginfo_mb_detect_order)
- PHP_FE(mb_substitute_character, arginfo_mb_substitute_character)
- PHP_FE(mb_parse_str, arginfo_mb_parse_str)
- PHP_FE(mb_output_handler, arginfo_mb_output_handler)
- PHP_FE(mb_preferred_mime_name, arginfo_mb_preferred_mime_name)
- PHP_FE(mb_strlen, arginfo_mb_strlen)
- PHP_FE(mb_strpos, arginfo_mb_strpos)
- PHP_FE(mb_strrpos, arginfo_mb_strrpos)
- PHP_FE(mb_stripos, arginfo_mb_stripos)
- PHP_FE(mb_strripos, arginfo_mb_strripos)
- PHP_FE(mb_strstr, arginfo_mb_strstr)
- PHP_FE(mb_strrchr, arginfo_mb_strrchr)
- PHP_FE(mb_stristr, arginfo_mb_stristr)
- PHP_FE(mb_strrichr, arginfo_mb_strrichr)
- PHP_FE(mb_substr_count, arginfo_mb_substr_count)
- PHP_FE(mb_substr, arginfo_mb_substr)
- PHP_FE(mb_strcut, arginfo_mb_strcut)
- PHP_FE(mb_strwidth, arginfo_mb_strwidth)
- PHP_FE(mb_strimwidth, arginfo_mb_strimwidth)
- PHP_FE(mb_convert_encoding, arginfo_mb_convert_encoding)
- PHP_FE(mb_detect_encoding, arginfo_mb_detect_encoding)
- PHP_FE(mb_list_encodings, arginfo_mb_list_encodings)
- PHP_FE(mb_encoding_aliases, arginfo_mb_encoding_aliases)
- PHP_FE(mb_convert_kana, arginfo_mb_convert_kana)
- PHP_FE(mb_encode_mimeheader, arginfo_mb_encode_mimeheader)
- PHP_FE(mb_decode_mimeheader, arginfo_mb_decode_mimeheader)
- PHP_FE(mb_convert_variables, arginfo_mb_convert_variables)
- PHP_FE(mb_encode_numericentity, arginfo_mb_encode_numericentity)
- PHP_FE(mb_decode_numericentity, arginfo_mb_decode_numericentity)
- PHP_FE(mb_send_mail, arginfo_mb_send_mail)
- PHP_FE(mb_get_info, arginfo_mb_get_info)
- PHP_FE(mb_check_encoding, arginfo_mb_check_encoding)
- #if HAVE_MBREGEX
- PHP_MBREGEX_FUNCTION_ENTRIES
- #endif
- { NULL, NULL, NULL }
- };
- /* }}} */
- /* {{{ zend_module_entry mbstring_module_entry */
- zend_module_entry mbstring_module_entry = {
- STANDARD_MODULE_HEADER,
- "mbstring",
- mbstring_functions,
- PHP_MINIT(mbstring),
- PHP_MSHUTDOWN(mbstring),
- PHP_RINIT(mbstring),
- PHP_RSHUTDOWN(mbstring),
- PHP_MINFO(mbstring),
- NO_VERSION_YET,
- PHP_MODULE_GLOBALS(mbstring),
- PHP_GINIT(mbstring),
- PHP_GSHUTDOWN(mbstring),
- NULL,
- STANDARD_MODULE_PROPERTIES_EX
- };
- /* }}} */
- /* {{{ static sapi_post_entry php_post_entries[] */
- static sapi_post_entry php_post_entries[] = {
- { DEFAULT_POST_CONTENT_TYPE, sizeof(DEFAULT_POST_CONTENT_TYPE)-1, sapi_read_standard_form_data, php_std_post_handler },
- { MULTIPART_CONTENT_TYPE, sizeof(MULTIPART_CONTENT_TYPE)-1, NULL, rfc1867_post_handler },
- { NULL, 0, NULL, NULL }
- };
- /* }}} */
- #ifdef COMPILE_DL_MBSTRING
- ZEND_GET_MODULE(mbstring)
- #endif
- /* {{{ allocators */
- static void *_php_mb_allocators_malloc(unsigned int sz)
- {
- return emalloc(sz);
- }
- static void *_php_mb_allocators_realloc(void *ptr, unsigned int sz)
- {
- return erealloc(ptr, sz);
- }
- static void *_php_mb_allocators_calloc(unsigned int nelems, unsigned int szelem)
- {
- return ecalloc(nelems, szelem);
- }
- static void _php_mb_allocators_free(void *ptr)
- {
- efree(ptr);
- }
- static void *_php_mb_allocators_pmalloc(unsigned int sz)
- {
- return pemalloc(sz, 1);
- }
- static void *_php_mb_allocators_prealloc(void *ptr, unsigned int sz)
- {
- return perealloc(ptr, sz, 1);
- }
- static void _php_mb_allocators_pfree(void *ptr)
- {
- pefree(ptr, 1);
- }
- static mbfl_allocators _php_mb_allocators = {
- _php_mb_allocators_malloc,
- _php_mb_allocators_realloc,
- _php_mb_allocators_calloc,
- _php_mb_allocators_free,
- _php_mb_allocators_pmalloc,
- _php_mb_allocators_prealloc,
- _php_mb_allocators_pfree
- };
- /* }}} */
- /* {{{ static sapi_post_entry mbstr_post_entries[] */
- static sapi_post_entry mbstr_post_entries[] = {
- { DEFAULT_POST_CONTENT_TYPE, sizeof(DEFAULT_POST_CONTENT_TYPE)-1, sapi_read_standard_form_data, php_mb_post_handler },
- { MULTIPART_CONTENT_TYPE, sizeof(MULTIPART_CONTENT_TYPE)-1, NULL, rfc1867_post_handler },
- { NULL, 0, NULL, NULL }
- };
- /* }}} */
- /* {{{ static int php_mb_parse_encoding_list()
- * Return 0 if input contains any illegal encoding, otherwise 1.
- * Even if any illegal encoding is detected the result may contain a list
- * of parsed encodings.
- */
- static int
- php_mb_parse_encoding_list(const char *value, int value_length, enum mbfl_no_encoding **return_list, int *return_size, int persistent TSRMLS_DC)
- {
- int n, l, size, bauto, ret = 1;
- char *p, *p1, *p2, *endp, *tmpstr;
- enum mbfl_no_encoding no_encoding;
- enum mbfl_no_encoding *src, *entry, *list;
- list = NULL;
- if (value == NULL || value_length <= 0) {
- if (return_list) {
- *return_list = NULL;
- }
- if (return_size) {
- *return_size = 0;
- }
- return 0;
- } else {
- enum mbfl_no_encoding *identify_list;
- int identify_list_size;
- identify_list = MBSTRG(default_detect_order_list);
- identify_list_size = MBSTRG(default_detect_order_list_size);
- /* copy the value string for work */
- if (value[0]=='"' && value[value_length-1]=='"' && value_length>2) {
- tmpstr = (char *)estrndup(value+1, value_length-2);
- value_length -= 2;
- }
- else
- tmpstr = (char *)estrndup(value, value_length);
- if (tmpstr == NULL) {
- return 0;
- }
- /* count the number of listed encoding names */
- endp = tmpstr + value_length;
- n = 1;
- p1 = tmpstr;
- while ((p2 = php_memnstr(p1, ",", 1, endp)) != NULL) {
- p1 = p2 + 1;
- n++;
- }
- size = n + identify_list_size;
- /* make list */
- list = (enum mbfl_no_encoding *)pecalloc(size, sizeof(int), persistent);
- if (list != NULL) {
- entry = list;
- n = 0;
- bauto = 0;
- p1 = tmpstr;
- do {
- p2 = p = php_memnstr(p1, ",", 1, endp);
- if (p == NULL) {
- p = endp;
- }
- *p = '\0';
- /* trim spaces */
- while (p1 < p && (*p1 == ' ' || *p1 == '\t')) {
- p1++;
- }
- p--;
- while (p > p1 && (*p == ' ' || *p == '\t')) {
- *p = '\0';
- p--;
- }
- /* convert to the encoding number and check encoding */
- if (strcasecmp(p1, "auto") == 0) {
- if (!bauto) {
- bauto = 1;
- l = identify_list_size;
- src = identify_list;
- while (l > 0) {
- *entry++ = *src++;
- l--;
- n++;
- }
- }
- } else {
- no_encoding = mbfl_name2no_encoding(p1);
- if (no_encoding != mbfl_no_encoding_invalid) {
- *entry++ = no_encoding;
- n++;
- } else {
- ret = 0;
- }
- }
- p1 = p2 + 1;
- } while (n < size && p2 != NULL);
- if (n > 0) {
- if (return_list) {
- *return_list = list;
- } else {
- pefree(list, persistent);
- }
- } else {
- pefree(list, persistent);
- if (return_list) {
- *return_list = NULL;
- }
- ret = 0;
- }
- if (return_size) {
- *return_size = n;
- }
- } else {
- if (return_list) {
- *return_list = NULL;
- }
- if (return_size) {
- *return_size = 0;
- }
- ret = 0;
- }
- efree(tmpstr);
- }
- return ret;
- }
- /* }}} */
- /* {{{ MBSTRING_API php_mb_check_encoding_list */
- MBSTRING_API int php_mb_check_encoding_list(const char *encoding_list TSRMLS_DC) {
- return php_mb_parse_encoding_list(encoding_list, strlen(encoding_list), NULL, NULL, 0 TSRMLS_CC);
- }
- /* }}} */
- /* {{{ static int php_mb_parse_encoding_array()
- * Return 0 if input contains any illegal encoding, otherwise 1.
- * Even if any illegal encoding is detected the result may contain a list
- * of parsed encodings.
- */
- static int
- php_mb_parse_encoding_array(zval *array, enum mbfl_no_encoding **return_list, int *return_size, int persistent TSRMLS_DC)
- {
- zval **hash_entry;
- HashTable *target_hash;
- int i, n, l, size, bauto,ret = 1;
- enum mbfl_no_encoding no_encoding;
- enum mbfl_no_encoding *src, *list, *entry;
- list = NULL;
- if (Z_TYPE_P(array) == IS_ARRAY) {
- enum mbfl_no_encoding *identify_list;
- int identify_list_size;
- identify_list = MBSTRG(default_detect_order_list);
- identify_list_size = MBSTRG(default_detect_order_list_size);
- target_hash = Z_ARRVAL_P(array);
- zend_hash_internal_pointer_reset(target_hash);
- i = zend_hash_num_elements(target_hash);
- size = i + identify_list_size;
- list = (enum mbfl_no_encoding *)pecalloc(size, sizeof(int), persistent);
- if (list != NULL) {
- entry = list;
- bauto = 0;
- n = 0;
- while (i > 0) {
- if (zend_hash_get_current_data(target_hash, (void **) &hash_entry) == FAILURE) {
- break;
- }
- convert_to_string_ex(hash_entry);
- if (strcasecmp(Z_STRVAL_PP(hash_entry), "auto") == 0) {
- if (!bauto) {
- bauto = 1;
- l = identify_list_size;
- src = identify_list;
- while (l > 0) {
- *entry++ = *src++;
- l--;
- n++;
- }
- }
- } else {
- no_encoding = mbfl_name2no_encoding(Z_STRVAL_PP(hash_entry));
- if (no_encoding != mbfl_no_encoding_invalid) {
- *entry++ = no_encoding;
- n++;
- } else {
- ret = 0;
- }
- }
- zend_hash_move_forward(target_hash);
- i--;
- }
- if (n > 0) {
- if (return_list) {
- *return_list = list;
- } else {
- pefree(list, persistent);
- }
- } else {
- pefree(list, persistent);
- if (return_list) {
- *return_list = NULL;
- }
- ret = 0;
- }
- if (return_size) {
- *return_size = n;
- }
- } else {
- if (return_list) {
- *return_list = NULL;
- }
- if (return_size) {
- *return_size = 0;
- }
- ret = 0;
- }
- }
- return ret;
- }
- /* }}} */
- static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC);
- static int _php_mb_match_regex(void *opaque, const char *str, size_t str_len);
- static void _php_mb_free_regex(void *opaque);
- #if HAVE_ONIG
- /* {{{ _php_mb_compile_regex */
- void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
- {
- php_mb_regex_t *retval;
- OnigErrorInfo err_info;
- int err_code;
- if ((err_code = onig_new(&retval,
- (const OnigUChar *)pattern,
- (const OnigUChar *)pattern + strlen(pattern),
- ONIG_OPTION_IGNORECASE | ONIG_OPTION_DONT_CAPTURE_GROUP,
- ONIG_ENCODING_ASCII, &OnigSyntaxPerl, &err_info))) {
- OnigUChar err_str[ONIG_MAX_ERROR_MESSAGE_LEN];
- onig_error_code_to_str(err_str, err_code, err_info);
- php_error_docref(NULL TSRMLS_CC, E_WARNING, "%s: %s", pattern, err_str);
- retval = NULL;
- }
- return retval;
- }
- /* }}} */
- /* {{{ _php_mb_match_regex */
- int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
- {
- return onig_search((php_mb_regex_t *)opaque, (const OnigUChar *)str,
- (const OnigUChar*)str + str_len, (const OnigUChar *)str,
- (const OnigUChar*)str + str_len, NULL, ONIG_OPTION_NONE) >= 0;
- }
- /* }}} */
- /* {{{ _php_mb_free_regex */
- void _php_mb_free_regex(void *opaque)
- {
- onig_free((php_mb_regex_t *)opaque);
- }
- /* }}} */
- #elif HAVE_PCRE || HAVE_BUNDLED_PCRE
- /* {{{ _php_mb_compile_regex */
- void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
- {
- pcre *retval;
- const char *err_str;
- int err_offset;
- if (!(retval = pcre_compile(pattern,
- PCRE_CASELESS, &err_str, &err_offset, NULL))) {
- php_error_docref(NULL TSRMLS_CC, E_WARNING, "%s (offset=%d): %s", pattern, err_offset, err_str);
- }
- return retval;
- }
- /* }}} */
- /* {{{ _php_mb_match_regex */
- int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
- {
- return pcre_exec((pcre *)opaque, NULL, str, (int)str_len, 0,
- 0, NULL, 0) >= 0;
- }
- /* }}} */
- /* {{{ _php_mb_free_regex */
- void _php_mb_free_regex(void *opaque)
- {
- pcre_free(opaque);
- }
- /* }}} */
- #endif
- /* {{{ php_mb_nls_get_default_detect_order_list */
- static int php_mb_nls_get_default_detect_order_list(enum mbfl_no_language lang, enum mbfl_no_encoding **plist, int* plist_size)
- {
- size_t i;
- *plist = (enum mbfl_no_encoding *) php_mb_default_identify_list_neut;
- *plist_size = sizeof(php_mb_default_identify_list_neut) / sizeof(php_mb_default_identify_list_neut[0]);
- for (i = 0; i < sizeof(php_mb_default_identify_list) / sizeof(php_mb_default_identify_list[0]); i++) {
- if (php_mb_default_identify_list[i].lang == lang) {
- *plist = (enum mbfl_no_encoding *)php_mb_default_identify_list[i].list;
- *plist_size = php_mb_default_identify_list[i].list_size;
- return 1;
- }
- }
- return 0;
- }
- /* }}} */
- /* {{{ php.ini directive handler */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_language) */
- static PHP_INI_MH(OnUpdate_mbstring_language)
- {
- enum mbfl_no_language no_language;
- no_language = mbfl_name2no_language(new_value);
- if (no_language == mbfl_no_language_invalid) {
- MBSTRG(language) = mbfl_no_language_neutral;
- return FAILURE;
- }
- MBSTRG(language) = no_language;
- php_mb_nls_get_default_detect_order_list(no_language, &MBSTRG(default_detect_order_list), &MBSTRG(default_detect_order_list_size));
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_detect_order) */
- static PHP_INI_MH(OnUpdate_mbstring_detect_order)
- {
- enum mbfl_no_encoding *list;
- int size;
- if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
- if (MBSTRG(detect_order_list)) {
- free(MBSTRG(detect_order_list));
- }
- MBSTRG(detect_order_list) = list;
- MBSTRG(detect_order_list_size) = size;
- } else {
- if (MBSTRG(detect_order_list)) {
- free(MBSTRG(detect_order_list));
- MBSTRG(detect_order_list) = NULL;
- }
- return FAILURE;
- }
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_input) */
- static PHP_INI_MH(OnUpdate_mbstring_http_input)
- {
- enum mbfl_no_encoding *list;
- int size;
- if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
- if (MBSTRG(http_input_list)) {
- free(MBSTRG(http_input_list));
- }
- MBSTRG(http_input_list) = list;
- MBSTRG(http_input_list_size) = size;
- } else {
- if (MBSTRG(http_input_list)) {
- free(MBSTRG(http_input_list));
- MBSTRG(http_input_list) = NULL;
- }
- MBSTRG(http_input_list_size) = 0;
- return FAILURE;
- }
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_output) */
- static PHP_INI_MH(OnUpdate_mbstring_http_output)
- {
- enum mbfl_no_encoding no_encoding;
- no_encoding = mbfl_name2no_encoding(new_value);
- if (no_encoding != mbfl_no_encoding_invalid) {
- MBSTRG(http_output_encoding) = no_encoding;
- MBSTRG(current_http_output_encoding) = no_encoding;
- } else {
- MBSTRG(http_output_encoding) = mbfl_no_encoding_pass;
- MBSTRG(current_http_output_encoding) = mbfl_no_encoding_pass;
- if (new_value != NULL && new_value_length > 0) {
- return FAILURE;
- }
- }
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static _php_mb_ini_mbstring_internal_encoding_set */
- int _php_mb_ini_mbstring_internal_encoding_set(const char *new_value, uint new_value_length TSRMLS_DC)
- {
- enum mbfl_no_encoding no_encoding;
- const char *enc_name = NULL;
- uint enc_name_len = 0;
-
- no_encoding = new_value ? mbfl_name2no_encoding(new_value):
- mbfl_no_encoding_invalid;
- if (no_encoding != mbfl_no_encoding_invalid) {
- enc_name = new_value;
- enc_name_len = new_value_length;
- } else {
- switch (MBSTRG(language)) {
- case mbfl_no_language_uni:
- enc_name = "UTF-8";
- enc_name_len = sizeof("UTF-8") - 1;
- break;
- case mbfl_no_language_japanese:
- enc_name = "EUC-JP";
- enc_name_len = sizeof("EUC-JP") - 1;
- break;
- case mbfl_no_language_korean:
- enc_name = "EUC-KR";
- enc_name_len = sizeof("EUC-KR") - 1;
- break;
- case mbfl_no_language_simplified_chinese:
- enc_name = "EUC-CN";
- enc_name_len = sizeof("EUC-CN") - 1;
- break;
- case mbfl_no_language_traditional_chinese:
- enc_name = "EUC-TW";
- enc_name_len = sizeof("EUC-TW") - 1;
- break;
- case mbfl_no_language_russian:
- enc_name = "KOI8-R";
- enc_name_len = sizeof("KOI8-R") - 1;
- break;
- case mbfl_no_language_german:
- enc_name = "ISO-8859-15";
- enc_name_len = sizeof("ISO-8859-15") - 1;
- break;
- case mbfl_no_language_armenian:
- enc_name = "ArmSCII-8";
- enc_name_len = sizeof("ArmSCII-8") - 1;
- break;
- case mbfl_no_language_turkish:
- enc_name = "ISO-8859-9";
- enc_name_len = sizeof("ISO-8859-9") - 1;
- break;
- default:
- enc_name = "ISO-8859-1";
- enc_name_len = sizeof("ISO-8859-1") - 1;
- break;
- }
- no_encoding = mbfl_name2no_encoding(enc_name);
- }
- MBSTRG(internal_encoding) = no_encoding;
- MBSTRG(current_internal_encoding) = no_encoding;
- #if HAVE_MBREGEX
- {
- const char *enc_name = new_value;
- if (FAILURE == php_mb_regex_set_default_mbctype(enc_name TSRMLS_CC)) {
- /* falls back to EUC-JP if an unknown encoding name is given */
- enc_name = "EUC-JP";
- php_mb_regex_set_default_mbctype(enc_name TSRMLS_CC);
- }
- php_mb_regex_set_mbctype(new_value TSRMLS_CC);
- }
- #endif
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_internal_encoding) */
- static PHP_INI_MH(OnUpdate_mbstring_internal_encoding)
- {
- if (stage == PHP_INI_STAGE_STARTUP || stage == PHP_INI_STAGE_SHUTDOWN
- || stage == PHP_INI_STAGE_RUNTIME) {
- return _php_mb_ini_mbstring_internal_encoding_set(new_value, new_value_length TSRMLS_CC);
- } else {
- /* the corresponding mbstring globals needs to be set according to the
- * ini value in the later stage because it never falls back to the
- * default value if 1. no value for mbstring.internal_encoding is given,
- * 2. mbstring.language directive is processed in per-dir or runtime
- * context and 3. call to the handler for mbstring.language is done
- * after mbstring.internal_encoding is handled. */
- return SUCCESS;
- }
- }
- /* }}} */
- #ifdef ZEND_MULTIBYTE
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_script_encoding) */
- static PHP_INI_MH(OnUpdate_mbstring_script_encoding)
- {
- int *list, size;
- if (php_mb_parse_encoding_list(new_value, new_value_length, &list, &size, 1 TSRMLS_CC)) {
- if (MBSTRG(script_encoding_list) != NULL) {
- free(MBSTRG(script_encoding_list));
- }
- MBSTRG(script_encoding_list) = list;
- MBSTRG(script_encoding_list_size) = size;
- } else {
- if (MBSTRG(script_encoding_list) != NULL) {
- free(MBSTRG(script_encoding_list));
- }
- MBSTRG(script_encoding_list) = NULL;
- MBSTRG(script_encoding_list_size) = 0;
- return FAILURE;
- }
- return SUCCESS;
- }
- /* }}} */
- #endif /* ZEND_MULTIBYTE */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_substitute_character) */
- static PHP_INI_MH(OnUpdate_mbstring_substitute_character)
- {
- int c;
- char *endptr = NULL;
- if (new_value != NULL) {
- if (strcasecmp("none", new_value) == 0) {
- MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE;
- MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE;
- } else if (strcasecmp("long", new_value) == 0) {
- MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_LONG;
- MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_LONG;
- } else if (strcasecmp("entity", new_value) == 0) {
- MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_ENTITY;
- MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_ENTITY;
- } else {
- MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- if (new_value_length >0) {
- c = strtol(new_value, &endptr, 0);
- if (*endptr == '\0') {
- MBSTRG(filter_illegal_substchar) = c;
- MBSTRG(current_filter_illegal_substchar) = c;
- }
- }
- }
- } else {
- MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- MBSTRG(filter_illegal_substchar) = 0x3f; /* '?' */
- MBSTRG(current_filter_illegal_substchar) = 0x3f; /* '?' */
- }
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_encoding_translation) */
- static PHP_INI_MH(OnUpdate_mbstring_encoding_translation)
- {
- if (new_value == NULL) {
- return FAILURE;
- }
- OnUpdateBool(entry, new_value, new_value_length, mh_arg1, mh_arg2, mh_arg3, stage TSRMLS_CC);
- if (MBSTRG(encoding_translation)) {
- sapi_unregister_post_entry(php_post_entries TSRMLS_CC);
- sapi_register_post_entries(mbstr_post_entries TSRMLS_CC);
- } else {
- sapi_unregister_post_entry(mbstr_post_entries TSRMLS_CC);
- sapi_register_post_entries(php_post_entries TSRMLS_CC);
- }
- return SUCCESS;
- }
- /* }}} */
- /* {{{ static PHP_INI_MH(OnUpdate_mbstring_http_output_conv_mimetypes */
- static PHP_INI_MH(OnUpdate_mbstring_http_output_conv_mimetypes)
- {
- zval tmp;
- void *re = NULL;
- if (!new_value) {
- new_value = entry->orig_value;
- new_value_length = entry->orig_value_length;
- }
- php_trim(new_value, new_value_length, NULL, 0, &tmp, 3 TSRMLS_CC);
- if (Z_STRLEN(tmp) > 0) {
- if (!(re = _php_mb_compile_regex(Z_STRVAL(tmp) TSRMLS_CC))) {
- zval_dtor(&tmp);
- return FAILURE;
- }
- }
- if (MBSTRG(http_output_conv_mimetypes)) {
- _php_mb_free_regex(MBSTRG(http_output_conv_mimetypes));
- }
- MBSTRG(http_output_conv_mimetypes) = re;
- zval_dtor(&tmp);
- return SUCCESS;
- }
- /* }}} */
- /* }}} */
- /* {{{ php.ini directive registration */
- PHP_INI_BEGIN()
- PHP_INI_ENTRY("mbstring.language", "neutral", PHP_INI_ALL, OnUpdate_mbstring_language)
- PHP_INI_ENTRY("mbstring.detect_order", NULL, PHP_INI_ALL, OnUpdate_mbstring_detect_order)
- PHP_INI_ENTRY("mbstring.http_input", "pass", PHP_INI_ALL, OnUpdate_mbstring_http_input)
- PHP_INI_ENTRY("mbstring.http_output", "pass", PHP_INI_ALL, OnUpdate_mbstring_http_output)
- PHP_INI_ENTRY("mbstring.internal_encoding", NULL, PHP_INI_ALL, OnUpdate_mbstring_internal_encoding)
- #ifdef ZEND_MULTIBYTE
- PHP_INI_ENTRY("mbstring.script_encoding", NULL, PHP_INI_ALL, OnUpdate_mbstring_script_encoding)
- #endif /* ZEND_MULTIBYTE */
- PHP_INI_ENTRY("mbstring.substitute_character", NULL, PHP_INI_ALL, OnUpdate_mbstring_substitute_character)
- STD_PHP_INI_ENTRY("mbstring.func_overload", "0",
- PHP_INI_SYSTEM, OnUpdateLong, func_overload, zend_mbstring_globals, mbstring_globals)
- STD_PHP_INI_BOOLEAN("mbstring.encoding_translation", "0",
- PHP_INI_SYSTEM | PHP_INI_PERDIR,
- OnUpdate_mbstring_encoding_translation,
- encoding_translation, zend_mbstring_globals, mbstring_globals)
- PHP_INI_ENTRY("mbstring.http_output_conv_mimetypes",
- "^(text/|application/xhtml\\+xml)",
- PHP_INI_ALL,
- OnUpdate_mbstring_http_output_conv_mimetypes)
- STD_PHP_INI_BOOLEAN("mbstring.strict_detection", "0",
- PHP_INI_ALL,
- OnUpdateLong,
- strict_detection, zend_mbstring_globals, mbstring_globals)
- PHP_INI_END()
- /* }}} */
- /* {{{ module global initialize handler */
- static PHP_GINIT_FUNCTION(mbstring)
- {
- mbstring_globals->language = mbfl_no_language_uni;
- mbstring_globals->internal_encoding = mbfl_no_encoding_invalid;
- mbstring_globals->current_internal_encoding = mbstring_globals->internal_encoding;
- #ifdef ZEND_MULTIBYTE
- mbstring_globals->script_encoding_list = NULL;
- mbstring_globals->script_encoding_list_size = 0;
- #endif /* ZEND_MULTIBYTE */
- mbstring_globals->http_output_encoding = mbfl_no_encoding_pass;
- mbstring_globals->current_http_output_encoding = mbfl_no_encoding_pass;
- mbstring_globals->http_input_identify = mbfl_no_encoding_invalid;
- mbstring_globals->http_input_identify_get = mbfl_no_encoding_invalid;
- mbstring_globals->http_input_identify_post = mbfl_no_encoding_invalid;
- mbstring_globals->http_input_identify_cookie = mbfl_no_encoding_invalid;
- mbstring_globals->http_input_identify_string = mbfl_no_encoding_invalid;
- mbstring_globals->http_input_list = NULL;
- mbstring_globals->http_input_list_size = 0;
- mbstring_globals->detect_order_list = NULL;
- mbstring_globals->detect_order_list_size = 0;
- mbstring_globals->current_detect_order_list = NULL;
- mbstring_globals->current_detect_order_list_size = 0;
- mbstring_globals->default_detect_order_list = (enum mbfl_no_encoding *) php_mb_default_identify_list_neut;
- mbstring_globals->default_detect_order_list_size = sizeof(php_mb_default_identify_list_neut) / sizeof(php_mb_default_identify_list_neut[0]);
- mbstring_globals->filter_illegal_mode = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- mbstring_globals->filter_illegal_substchar = 0x3f; /* '?' */
- mbstring_globals->current_filter_illegal_mode = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
- mbstring_globals->current_filter_illegal_substchar = 0x3f; /* '?' */
- mbstring_globals->illegalchars = 0;
- mbstring_globals->func_overload = 0;
- mbstring_globals->encoding_translation = 0;
- mbstring_globals->strict_detection = 0;
- mbstring_globals->outconv = NULL;
- mbstring_globals->http_output_conv_mimetypes = NULL;
- #if HAVE_MBREGEX
- mbstring_globals->mb_regex_globals = php_mb_regex_globals_alloc(TSRMLS_C);
- #endif
- }
- /* }}} */
- /* {{{ PHP_GSHUTDOWN_FUNCTION */
- static PHP_GSHUTDOWN_FUNCTION(mbstring)
- {
- if (mbstring_globals->http_input_list) {
- free(mbstring_globals->http_input_list);
- }
- #ifdef ZEND_MULTIBYTE
- if (mbstring_globals->script_encoding_list) {
- free(mbstring_globals->script_encoding_list);
- }
- #endif /* ZEND_MULTIBYTE */
- if (mbstring_globals->detect_order_list) {
- free(mbstring_globals->detect_order_list);
- }
- if (mbstring_globals->http_output_conv_mimetypes) {
- _php_mb_free_regex(mbstring_globals->http_output_conv_mimetypes);
- }
- #if HAVE_MBREGEX
- php_mb_regex_globals_free(mbstring_globals->mb_regex_globals TSRMLS_CC);
- #endif
- }
- /* }}} */
- /* {{{ PHP_MINIT_FUNCTION(mbstring) */
- PHP_MINIT_FUNCTION(mbstring)
- {
- __mbfl_allocators = &_php_mb_allocators;
- REGISTER_INI_ENTRIES();
- /* This is a global handler. Should not be set in a per-request handler. */
- sapi_register_treat_data(mbstr_treat_data);
- /* Post handlers are stored in the thread-local context. */
- if (MBSTRG(encoding_translation)) {
- sapi_register_post_entries(mbstr_post_entries TSRMLS_CC);
- }
- REGISTER_LONG_CONSTANT("MB_OVERLOAD_MAIL", MB_OVERLOAD_MAIL, CONST_CS | CONST_PERSISTENT);
- REGISTER_LONG_CONSTANT("MB_OVERLOAD_STRING", MB_OVERLOAD_STRING, CONST_CS | CONST_PERSISTENT);
- REGISTER_LONG_CONSTANT("MB_OVERLOAD_REGEX", MB_OVERLOAD_REGEX, CONST_CS | CONST_PERSISTENT);
- REGISTER_LONG_CONSTANT("MB_CASE_UPPER", PHP_UNICODE_CASE_UPPER, CONST_CS | CONST_PERSISTENT);
- REGISTER_LONG_CONSTANT("MB_CASE_LOWER", PHP_UNICODE_CASE_LOWER, CONST_CS | CONST_PERSISTENT);
- REGISTER_LONG_CONSTANT("MB_CASE_TITLE", PHP_UNICODE_CASE_TITLE, CONST_CS | CONST_PERSISTENT);
- #if HAVE_MBREGEX
- PHP_MINIT(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
- #endif
- return SUCCESS;
- }
- /* }}} */
- /* {{{ PHP_MSHUTDOWN_FUNCTION(mbstring) */
- PHP_MSHUTDOWN_FUNCTION(mbstring)
- {
- UNREGISTER_INI_ENTRIES();
-
- #if HAVE_MBREGEX
- PHP_MSHUTDOWN(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
- #endif
- return SUCCESS;
- }
- /* }}} */
- /* {{{ PHP_RINIT_FUNCTION(mbstring) */
- PHP_RINIT_FUNCTION(mbstring)
- {
- int n;
- enum mbfl_no_encoding *list=NULL, *entry;
- zend_function *func, *orig;
- const struct mb_overload_def *p;
- MBSTRG(current_internal_encoding) = MBSTRG(internal_encoding);
- MBSTRG(current_http_output_encoding) = MBSTRG(http_output_encoding);
- MBSTRG(current_filter_illegal_mode) = MBSTRG(filter_illegal_mode);
- MBSTRG(current_filter_illegal_substchar) = MBSTRG(filter_illegal_substchar);
- MBSTRG(illegalchars) = 0;
- n = 0;
- if (MBSTRG(detect_order_list)) {
- list = MBSTRG(detect_order_list);
- n = MBSTRG(detect_order_list_size);
- }
- if (n <= 0) {
- list = MBSTRG(default_detect_order_list);
- n = MBSTRG(default_detect_order_list_size);
- }
- entry = (enum mbfl_no_encoding *)safe_emalloc(n, sizeof(int), 0);
- MBSTRG(current_detect_order_list) = entry;
- MBSTRG(current_detect_order_list_size) = n;
- while (n > 0) {
- *entry++ = *list++;
- n--;
- }
- /* override original function. */
- if (MBSTRG(func_overload)){
- p = &(mb_ovld[0]);
-
- while (p->type > 0) {
- if ((MBSTRG(func_overload) & p->type) == p->type &&
- zend_hash_find(EG(function_table), p->save_func,
- strlen(p->save_func)+1, (void **)&orig) != SUCCESS) {
- zend_hash_find(EG(function_table), p->ovld_func, strlen(p->ovld_func)+1 , (void **)&func);
-
- if (zend_hash_find(EG(function_table), p->orig_func, strlen(p->orig_func)+1, (void **)&orig) != SUCCESS) {
- php_error_docref("ref.mbstring" TSRMLS_CC, E_WARNING, "mbstring couldn't find function %s.", p->orig_func);
- return FAILURE;
- } else {
- zend_hash_add(EG(function_table), p->save_func, strlen(p->save_func)+1, orig, sizeof(zend_function), NULL);
- if (zend_hash_update(EG(function_table), p->orig_func, strlen(p->orig_func)+1, func, sizeof(zend_function),
- NULL) == FAILURE) {
- php_error_docref("ref.mbstring" TSRMLS_CC, E_WARNING, "mbstring couldn't replace function %s.", p->orig_func);
- return FAILURE;
- }
- }
- }
- p++;
- }
- }
- #if HAVE_MBREGEX
- PHP_RINIT(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
- #endif
- #ifdef ZEND_MULTIBYTE
- zend_multibyte_set_internal_encoding(mbfl_no_encoding2name(MBSTRG(internal_encoding)) TSRMLS_CC);
- php_mb_set_zend_encoding(TSRMLS_C);
- #endif /* ZEND_MULTIBYTE */
- return SUCCESS;
- }
- /* }}} */
- /* {{{ PHP_RSHUTDOWN_FUNCTION(mbstring) */
- PHP_RSHUTDOWN_FUNCTION(mbstring)
- {
- const struct mb_overload_def *p;
- zend_function *orig;
- if (MBSTRG(current_detect_order_list) != NULL) {
- efree(MBSTRG(current_detect_order_list));
- MBSTRG(current_detect_order_list) = NULL;
- MBSTRG(current_detect_order_list_size) = 0;
- }
- if (MBSTRG(outconv) != NULL) {
- MBSTRG(illegalchars) += mbfl_buffer_illegalchars(MBSTRG(outconv));
- mbfl_buffer_converter_delete(MBSTRG(outconv));
- MBSTRG(outconv) = NULL;
- }
- /* clear http input identification. */
- MBSTRG(http_input_identify) = mbfl_no_encoding_invalid;
- MBSTRG(http_input_identify_post) = mbfl_no_encoding_invalid;
- MBSTRG(http_input_identify_get) = mbfl_no_encoding_invalid;
- MBSTRG(http_input_identify_cookie) = mbfl_no_encoding_invalid;
- MBSTRG(http_input_identify_string) = mbfl_no_encoding_invalid;
- /* clear overloaded function. */
- if (MBSTRG(func_overload)){
- p = &(mb_ovld[0]);
- while (p->type > 0) {
- if ((MBSTRG(func_overload) & p->type) == p->type &&
- zend_hash_find(EG(function_table), p->save_func,
- strlen(p->save_func)+1, (void **)&orig) == SUCCESS) {
-
- zend_hash_update(EG(function_table), p->orig_func, strlen(p->orig_func)+1, orig, sizeof(zend_function), NULL);
- zend_hash_del(EG(function_table), p->save_func, strlen(p->save_func)+1);
- }
- p++;
- }
- }
- #if HAVE_MBREGEX
- PHP_RSHUTDOWN(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
- #endif
- return SUCCESS;
- }
- /* }}} */
- /* {{{ PHP_MINFO_FUNCTION(mbstring) */
- PHP_MINFO_FUNCTION(mbstring)
- {
- php_info_print_table_start();
- php_info_print_table_row(2, "Multibyte Support", "enabled");
- php_info_print_table_row(2, "Multibyte string engine", "libmbfl");
- php_info_print_table_row(2, "HTTP input encoding translation", MBSTRG(encoding_translation) ? "enabled": "disabled");
- php_info_print_table_end();
- php_info_print_table_start();
- 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.");
- php_info_print_table_end();
- #if HAVE_MBREGEX
- PHP_MINFO(mb_regex)(ZEND_MODULE_INFO_FUNC_ARGS_PASSTHRU);
- #endif
- DISPLAY_INI_ENTRIES();
- }
- /* }}} */
- /* {{{ proto string mb_language([string language])
- Sets the current language or Returns the current language as a string */
- PHP_FUNCTION(mb_language)
- {
- char *name = NULL;
- int name_len = 0;
- if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &name, &name_len) == FAILURE) {
- return;
- }
- if (name == NULL) {
- RETVAL_STRING((char *)mbfl_no_language2name(MBSTRG(language)), 1);
- } else {
- if (FAILURE == zend_alter_ini_entry(
- "mbstring.language", sizeof("mbstring.language"),
- name, name_len, PHP_INI_USER, PHP_INI_STAGE_RUNTIME)) {
- php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown language \"%s\"", name);
- RETVAL_FALSE;
- } else {
- RETVAL_TRUE;
- }
- }
- }
- /* }}} */
- /* {{{ proto string mb_internal_encoding([string encoding])
- Sets the current internal encoding or Returns the current internal encoding as a string */
- PHP_FUNCTION(mb_internal_encoding)
- {
- char *name = NULL;
- int name_len;
- enum mbfl_no_encoding no_encoding;
- if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &name, &name_len) == FAILURE) {
- RETURN_FALSE;
- }
- if (name == NULL) {
- name = (char *)mbfl_no_encoding2name(MBSTRG(current_internal_encoding));
- if (name != NULL) {
- RETURN_STRING(name, 1);
- } else {
- RETURN_FALSE;
- }
- } else {
- no_encoding = mbfl_name2no_encoding(name);
- if (no_encoding == mbfl_no_encoding_invalid) {
- php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown encoding \"%s\"", name);
- RETURN_FALSE;
- } else {
- MBSTRG(current_internal_encoding) = no_encoding;
- #ifdef ZEND_MULTIBYTE
- /* TODO: make independent from mbstring.encoding_translation? */
- if (MBSTRG(encoding_translation)) {
- zend_multibyte_set_internal_encoding(name TSRMLS_CC);
- }
- #endif /* ZEND_MULTIBYTE */
- RETURN_TRUE;
- }
- }
- }
- /* }}} */
- /* {{{ proto mixed mb_http_input([string type])
- Returns the input encoding */
- PHP_FUNCTION(mb_http_input)
- {
- char *typ = NULL;
- int typ_len;
- int retname, n;
- char *name, *list, *temp;
- enum mbfl_no_encoding *entry;
- enum mbfl_no_encoding result = mbfl_no_encoding_invalid;
- retname = 1;
- if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &typ, &typ_len) == FAILURE) {
- RETURN_FALSE;
- }
- if (typ == NULL) {
- result = MBSTRG(http_input_identify);
- } else {
- switch (*typ) {
- case 'G':
- case 'g':
- result = MBSTRG(http_input_identify_get);
- break;
- case 'P':
- case 'p':
- result = MBSTRG(http_input_identify_post);
- break;
- case 'C':
- case 'c':
- result = MBSTRG(http_input_identify_cookie);
- break;
- case 'S':
- case 's':
- result = MBSTRG(http_input_identify_string);
- break;
- case 'I':
- case 'i':
- array_init(return_value);
- entry = MBSTRG(http_input_list);
- n = MBSTRG(http_input_list_size);
- while (n > 0) {
- name = (char *)mbfl_no_encoding2name(*entry);
- if (name) {
- add_next_index_string(return_value, name, 1);
- }
- entry++;
- n--;
- }
- retname = 0;
- break;
- case 'L':
- case 'l':
- entry = MBSTRG(http_input_list);
- n = MBSTRG(http_input_list_size);
- list = NULL;
- while (n > 0) {
- name = (char *)mbfl_no_encoding2name(*entry);
- if (name) {
- if (list) {
- temp = list;
- spprintf(&list, 0, "%s,%s", temp, name);
- efree(temp);
- if (!list) {
- break;
- }
- } else {
- list = estrdup(name);
- }
- }
- entry++;
- n--;
- }
- if (!list) {
- RETURN_FALSE;
- }
- RETVAL_STRING(list, 0);
- retname = 0;
- break;
- default:
- result = MBSTRG(http_input_identify);
- break;
- }
- }
- if (retname) {
- if (result != mbfl_no_encoding_invalid &&
- …
Large files files are truncated, but you can click here to view the full file