archive/php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2025-08-19 08:49:28 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge pull request #1098

Browse source 
Fix bug #69086 enhancement for mb_convert_encoding
This commit is contained in:
Yasuo Ohgaki 2016-08-10 14:39:23 +09:00
parent 8ad4ef98b6
commit 850a0b5fb6
2 changed files with 64 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

70
ext/mbstring/mbstring.c
View file

@ -3148,6 +3148,31 @@ PHP_FUNCTION(mb_strimwidth)
} }
/* }}} */ /* }}} */
/* See mbfl_no_encoding definition for list of unsupported encodings */
static inline zend_bool php_mb_is_unsupported_no_encoding(enum mbfl_no_encoding no_enc)
{
return ((no_enc >= mbfl_no_encoding_invalid && no_enc <= mbfl_no_encoding_qprint)
|| (no_enc >= mbfl_no_encoding_utf7 && no_enc <= mbfl_no_encoding_utf7imap)
|| (no_enc >= mbfl_no_encoding_jis && no_enc <= mbfl_no_encoding_2022jpms)
|| (no_enc >= mbfl_no_encoding_cp50220 && no_enc <= mbfl_no_encoding_cp50222));
}
/* See mbfl_no_encoding definition for list of unicode encodings */
static inline zend_bool php_mb_is_no_encoding_unicode(enum mbfl_no_encoding no_enc)
{
return (no_enc >= mbfl_no_encoding_ucs4 && no_enc <= mbfl_no_encoding_utf8_sb);
}
/* See mbfl_no_encoding definition for list of UTF-8 encodings */
static inline zend_bool php_mb_is_no_encoding_utf8(enum mbfl_no_encoding no_enc)
{
return (no_enc >= mbfl_no_encoding_utf8 && no_enc <= mbfl_no_encoding_utf8_sb);
}
/* {{{ MBSTRING_API char *php_mb_convert_encoding() */ /* {{{ MBSTRING_API char *php_mb_convert_encoding() */
MBSTRING_API char * php_mb_convert_encoding(const char *input, size_t length, const char *_to_encoding, const char *_from_encodings, size_t *output_len) MBSTRING_API char * php_mb_convert_encoding(const char *input, size_t length, const char *_to_encoding, const char *_from_encodings, size_t *output_len)
{ {
@ -3218,7 +3243,28 @@ MBSTRING_API char * php_mb_convert_encoding(const char *input, size_t length, co
return NULL; return NULL;
} }
mbfl_buffer_converter_illegal_mode(convd, MBSTRG(current_filter_illegal_mode)); mbfl_buffer_converter_illegal_mode(convd, MBSTRG(current_filter_illegal_mode));
if (string.no_encoding == MBSTRG(current_internal_encoding)->no_encoding) {
mbfl_buffer_converter_illegal_substchar(convd, MBSTRG(current_filter_illegal_substchar)); mbfl_buffer_converter_illegal_substchar(convd, MBSTRG(current_filter_illegal_substchar));
} else if (php_mb_is_no_encoding_unicode(string.no_encoding) && php_mb_is_no_encoding_unicode(MBSTRG(current_internal_encoding)->no_encoding)) {
if (php_mb_is_no_encoding_utf8(string.no_encoding)) {
if (MBSTRG(current_filter_illegal_substchar) > 0xd7ff &&
0xe000 > MBSTRG(current_filter_illegal_substchar)
) {
mbfl_buffer_converter_illegal_substchar(convd, 0x3f);
} else {
mbfl_buffer_converter_illegal_substchar(convd, MBSTRG(current_filter_illegal_substchar));
}
} else {
mbfl_buffer_converter_illegal_substchar(convd, MBSTRG(current_filter_illegal_substchar));
}
} else {
mbfl_buffer_converter_illegal_substchar(convd, 0x3f);
}
/* do it */ /* do it */
ret = mbfl_buffer_converter_feed_result(convd, &string, &result); ret = mbfl_buffer_converter_feed_result(convd, &string, &result);
@ -4764,30 +4810,6 @@ PHP_FUNCTION(mb_check_encoding)
/* }}} */ /* }}} */
/* See mbfl_no_encoding definition for list of unsupported encodings */
static inline zend_bool php_mb_is_unsupported_no_encoding(enum mbfl_no_encoding no_enc)
{
return ((no_enc >= mbfl_no_encoding_invalid && no_enc <= mbfl_no_encoding_qprint)
|| (no_enc >= mbfl_no_encoding_utf7 && no_enc <= mbfl_no_encoding_utf7imap)
|| (no_enc >= mbfl_no_encoding_jis && no_enc <= mbfl_no_encoding_2022jpms)
|| (no_enc >= mbfl_no_encoding_cp50220 && no_enc <= mbfl_no_encoding_cp50222));
}
/* See mbfl_no_encoding definition for list of unicode encodings */
static inline zend_bool php_mb_is_no_encoding_unicode(enum mbfl_no_encoding no_enc)
{
return (no_enc >= mbfl_no_encoding_ucs4 && no_enc <= mbfl_no_encoding_utf8_sb);
}
/* See mbfl_no_encoding definition for list of UTF-8 encodings */
static inline zend_bool php_mb_is_no_encoding_utf8(enum mbfl_no_encoding no_enc)
{
return (no_enc >= mbfl_no_encoding_utf8 && no_enc <= mbfl_no_encoding_utf8_sb);
}
static inline zend_long php_mb_ord(const char* str, size_t str_len, const char* enc) static inline zend_long php_mb_ord(const char* str, size_t str_len, const char* enc)
{ {
enum mbfl_no_encoding no_enc; enum mbfl_no_encoding no_enc;

17
ext/mbstring/tests/bug69086.phpt Normal file
View file

@ -0,0 +1,17 @@
--TEST--
Request #69086 (enhancement for mb_convert_encoding)
--SKIPIF--
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
--FILE--
<?php
mb_substitute_character(0xfffd);
var_dump("?" === mb_convert_encoding("\x80", "Shift_JIS", "EUC-JP"));
mb_internal_encoding("UCS-4BE");
var_dump("\x00\x00\xff\xfd" === mb_convert_encoding("\x80", "UCS-4BE", "UTF-8"));
mb_substitute_character(0xd800);
var_dump("\x00\x00\x00\x3f" === mb_convert_encoding("\x80", "UCS-4BE", "UTF-8"));
?>
--EXPECT--
bool(true)
bool(true)
bool(true)