/* {{{ prototypes */
ZEND_DECLARE_MODULE_GLOBALS(mbstring)
+
static PHP_GINIT_FUNCTION(mbstring);
static PHP_GSHUTDOWN_FUNCTION(mbstring);
+
+static size_t php_mb_oddlen(const unsigned char *string, size_t length, const char *encoding TSRMLS_DC);
+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);
+static char* php_mb_encoding_detector(const unsigned char *arg_string, size_t arg_length, char *arg_list TSRMLS_DC);
+static int php_mb_set_zend_encoding(TSRMLS_D);
/* }}} */
/* {{{ php_mb_default_identify_list */
#if HAVE_ONIG
/* {{{ _php_mb_compile_regex */
-void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
+static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
{
php_mb_regex_t *retval;
OnigErrorInfo err_info;
/* }}} */
/* {{{ _php_mb_match_regex */
-int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
+static 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,
/* }}} */
/* {{{ _php_mb_free_regex */
-void _php_mb_free_regex(void *opaque)
+static 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)
+static void *_php_mb_compile_regex(const char *pattern TSRMLS_DC)
{
pcre *retval;
const char *err_str;
/* }}} */
/* {{{ _php_mb_match_regex */
-int _php_mb_match_regex(void *opaque, const char *str, size_t str_len)
+static 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)
+static void _php_mb_free_regex(void *opaque)
{
pcre_free(opaque);
}
/* }}} */
#ifdef ZEND_MULTIBYTE
-
/* {{{ php_mb_set_zend_encoding() */
static int php_mb_set_zend_encoding(TSRMLS_D)
{
/* }}} */
/* {{{ int php_mb_encoding_converter() */
-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)
+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)
{
mbfl_string string, result, *ret;
enum mbfl_no_encoding from_encoding, to_encoding;
--- /dev/null
+--TEST--
+zend multibyte (1)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=Shift_JIS
+mbstring.internal_encoding=Shift_JIS
+--FILE--
+<?php
+ function \97\\8e\\94\($\88ø\90\94)
+ {
+ echo $\88ø\90\94;
+ }
+
+ \97\\8e\\94\("\83h\83\8c\83~\83t\83@\83\");
+?>
+--EXPECT--
+\83h\83\8c\83~\83t\83@\83\
--- /dev/null
+--TEST--
+zend multibyte (2)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=UTF-8
+mbstring.internal_encoding=CP932
+--FILE--
+<?php
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(12) "836583588367"
--- /dev/null
+--TEST--
+zend multibyte (3)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=UTF-8
+mbstring.internal_encoding=EUC-JP
+--FILE--
+<?php
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(12) "a5c6a5b9a5c8"
--- /dev/null
+--TEST--
+zend multibyte (4)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=CP932
+mbstring.internal_encoding=UTF-8
+--FILE--
+<?php
+var_dump(bin2hex("\83e\83X\83g"));
+?>
+--EXPECT--
+string(18) "e38386e382b9e38388"
--- /dev/null
+--TEST--
+zend multibyte (5)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=EUC-JP
+mbstring.internal_encoding=UTF-8
+--FILE--
+<?php
+// forcefully interpret an UTF-8 encoded string as EUC-JP and then convert it
+// back to UTF-8. There should be only a pair of consecutive bytes that is
+// valid EUC-encoded character "鴻".
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(16) "3f3f3fe9b4bb3f3f"
--- /dev/null
+--TEST--
+zend multibyte (6)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=EUC-JP
+mbstring.internal_encoding=CP932
+--FILE--
+<?php
+declare(encoding="UTF-8");
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(12) "836583588367"
--- /dev/null
+--TEST--
+zend multibyte (7)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=ISO-8859-1
+mbstring.internal_encoding=EUC-JP
+--FILE--
+<?php
+declare(encoding="UTF-8");
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(12) "a5c6a5b9a5c8"
--- /dev/null
+--TEST--
+zend multibyte (8)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=ISO-8859-1
+mbstring.internal_encoding=UTF-8
+--FILE--
+<?php
+declare(encoding="CP932");
+var_dump(bin2hex("\83e\83X\83g"));
+?>
+--EXPECT--
+string(18) "e38386e382b9e38388"
--- /dev/null
+--TEST--
+zend multibyte (9)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=cp1251
+mbstring.internal_encoding=UTF-8
+--FILE--
+<?php
+declare(encoding="EUC-JP");
+// forcefully interpret an UTF-8 encoded string as EUC-JP and then convert it
+// back to UTF-8. There should be only a pair of consecutive bytes that is
+// valid EUC-encoded character "鴻".
+var_dump(bin2hex("テスト"));
+?>
+--EXPECT--
+string(16) "3f3f3fe9b4bb3f3f"
--- /dev/null
+--TEST--
+zend multibyte (10)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--FILE--
+<?php
+declare(encoding="ISO-8859-15");
+declare(encoding="ISO-8859-1");
+?>
+--EXPECTF--
+Fatal error: Encoding declaration pragma must be the very first statement in the script in %s on line 3
--- /dev/null
+--TEST--
+zend multibyte (11)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--FILE--
+<?php
+declare(encoding="ISO-8859-15") {
+ declare(encoding="ISO-8859-1");
+}
+?>
+--EXPECTF--
+Fatal error: Encoding declaration pragma must be the very first statement in the script in %s on line 3
--- /dev/null
+--TEST--
+zend multibyte (12)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--FILE--
+<?php
+declare(encoding="ISO-8859-15");
+echo 1;
+declare(encoding="ISO-8859-1");
+?>
+--EXPECTF--
+Fatal error: Encoding declaration pragma must be the very first statement in the script in %s on line 4
--- /dev/null
+--TEST--
+zend multibyte (13)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=UTF-8
+mbstring.internal_encoding=ISO-8859-1
+--FILE--
+<?php
+var_dump(substr(file_get_contents(__FILE__), __COMPILER_HALT_OFFSET__));
+var_dump(bin2hex("äëüáéú"));
+__halt_compiler();test
+test
+--EXPECT--
+string(10) "test
+test
+"
+string(12) "e4ebfce1e9fa"
--- /dev/null
+--TEST--
+zend multibyte (14)
+--SKIPIF--
+<?php
+ini_set("mbstring.script_encoding","SJIS");
+if (ini_set("mbstring.script_encoding","SJIS") != "SJIS") {
+ die("skip zend-multibyte is not available");
+}
+?>
+--INI--
+mbstring.script_encoding=UTF-8
+mbstring.internal_encoding=UTF-8
+--FILE--
+<?php
+var_dump(substr(file_get_contents(__FILE__), __COMPILER_HALT_OFFSET__));
+var_dump(bin2hex("äëüáéú"));
+__halt_compiler();test
+test
+--EXPECT--
+string(10) "test
+test
+"
+string(24) "c3a4c3abc3bcc3a1c3a9c3ba"