- Fixed CHARSET_UNICODE_COMPAT (ISO-8859-1 is compatible in the relevant sense).

- Fixed usage of zend_multibyte_get_internal_encoding (its return cannot be
  cast to char*).
- Change tests to reflect that charset detection now relies on
  internal_encoding, not on current_internal_encoding.
  NOTE: This fixes the changes in rev 306077, but it remains that that change
  introduced a BC break. I assumed it was intentional
This commit is contained in:
Gustavo André dos Santos Lopes 2011-01-25 10:57:07 +00:00
parent 05b2d22a00
commit 4a946a91e5
10 changed files with 28 additions and 45 deletions

View File

@ -148,6 +148,9 @@ UPGRADE NOTES - PHP X.Y
behavior follows the recommendations of Unicode Technical Report #36.
- htmlspecialchars_decode/html_entity_decode now decode ' if the document
type is ENT_XML1, ENT_XHTML, or ENT_HTML5.
- Charset detection with $charset == '' no longer turns to mbstring's
internal encoding defined through mb_internal_encoding(). Only the encoding
defined through the ini setting mbstring.internal_encoding is considered.
- number_format() no longer truncates multibyte decimal points and thousand
separators to the first byte.
- The third parameter ($matches) to preg_match_all() is now optional. If

View File

@ -367,6 +367,7 @@ static enum entity_charset determine_charset(char *charset_hint TSRMLS_DC)
int i;
enum entity_charset charset = cs_utf_8;
int len = 0;
const zend_encoding *zenc;
/* Default is now UTF-8 */
if (charset_hint == NULL)
@ -376,9 +377,20 @@ static enum entity_charset determine_charset(char *charset_hint TSRMLS_DC)
goto det_charset;
}
charset_hint = (char*)zend_multibyte_get_internal_encoding(TSRMLS_C);
if (charset_hint != NULL && (len=strlen(charset_hint)) != 0) {
goto det_charset;
zenc = zend_multibyte_get_internal_encoding(TSRMLS_C);
if (zenc != NULL) {
charset_hint = zend_multibyte_get_encoding_name(zenc);
if (charset_hint != NULL && (len=strlen(charset_hint)) != 0) {
if ((len == 4) /* sizeof (none|auto|pass) */ &&
(!memcmp("pass", charset_hint, 4) ||
!memcmp("auto", charset_hint, 4) ||
!memcmp("auto", charset_hint, 4))) {
charset_hint = NULL;
len = 0;
} else {
goto det_charset;
}
}
}
charset_hint = SG(default_charset);

View File

@ -33,7 +33,7 @@ enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
cs_numelems /* used to count the number of charsets */
};
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8)
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_8859_1)
#define CHARSET_SINGLE_BYTE(cs) ((cs) > cs_utf_8 && (cs) < cs_big5)
#define CHARSET_PARTIAL_SUPPORT(cs) ((cs) >= cs_big5)

View File

@ -56,7 +56,7 @@ enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
cs_numelems /* used to count the number of charsets */
};
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8)
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_8859_1)
#define CHARSET_SINGLE_BYTE(cs) ((cs) > cs_utf_8 && (cs) < cs_big5)
#define CHARSET_PARTIAL_SUPPORT(cs) ((cs) >= cs_big5)

View File

@ -2,19 +2,12 @@
htmlentities() test 5 (mbstring / cp1252)
--INI--
output_handler=
mbstring.internal_encoding=cp1252
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
mb_internal_encoding('cp1252');
$php_errormsg = NULL;
@htmlentities("\x82\x86\x99\x9f", ENT_QUOTES, '');
if ($php_errormsg) {
die("skip cp1252 chracter set is not supported on this platform.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('cp1252');
print mb_internal_encoding()."\n";
var_dump(htmlentities("\x82\x86\x99\x9f", ENT_QUOTES, ''));
var_dump(htmlentities("\x80\xa2\xa3\xa4\xa5", ENT_QUOTES, ''));

View File

@ -2,15 +2,10 @@
htmlentities() test 6 (mbstring / ISO-8859-15)
--INI--
output_handler=
mbstring.internal_encoding=ISO-8859-15
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
@mb_internal_encoding('ISO-8859-15');
@htmlentities("\xbc\xbd\xbe", ENT_QUOTES, '');
if (@$php_errormsg) {
die("skip ISO-8859-15 chracter set is not supported on this platform.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('ISO-8859-15');

View File

@ -2,16 +2,10 @@
htmlentities() test 7 (mbstring / ISO-8859-1)
--INI--
output_handler=
mbstring.internal_encoding=ISO-8859-1
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
mb_internal_encoding('ISO-8859-1');
$php_errormsg = NULL;
@htmlentities("\xe4\xf6\xfc", ENT_QUOTES, '');
if ($php_errormsg) {
die("skip ISO-8859-1 chracter set is not supported on this platform.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('ISO-8859-1');

View File

@ -2,16 +2,11 @@
htmlentities() test 8 (mbstring / EUC-JP)
--INI--
output_handler=
error_reporting=~E_STRICT
mbstring.internal_encoding=EUC-JP
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
mb_internal_encoding('EUC-JP');
$php_errormsg = NULL;
@htmlentities("\xa1\xa2\xa1\xa3\xa1\xa4", ENT_QUOTES, '');
if ($php_errormsg) {
die("skip EUC-JP chracter set is not supported on this platform.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('EUC-JP');

View File

@ -2,16 +2,11 @@
htmlentities() test 9 (mbstring / Shift_JIS)
--INI--
output_handler=
error_reporting=~E_STRICT
mbstring.internal_encoding=Shift_JIS
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
mb_internal_encoding('Shift_JIS');
$php_errormsg = NULL;
@htmlentities("\x81\x41\x81\x42\x81\x43", ENT_QUOTES, '');
if ($php_errormsg) {
die("skip Shift_JIS chracter set is not supported on this platform.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('Shift_JIS');

View File

@ -2,17 +2,13 @@
htmlentities() test 16 (mbstring / cp1251)
--INI--
output_handler=
mbstring.internal_encoding=cp1251
--SKIPIF--
<?php
extension_loaded("mbstring") or die("skip mbstring not available\n");
if (!@mb_internal_encoding('cp1251') ||
@htmlentities("\x88\xa9\xd2\xcf\xd3\xcb\xcf\xdb\xce\xd9\xca", ENT_QUOTES, '') == '') {
die("skip cp1251 character set is not available in this build.\n");
}
?>
--FILE--
<?php
mb_internal_encoding('cp1251');
$str = "\x88\xa9\xf0\xee\xf1\xea\xee\xf8\xed\xfb\xe9";
var_dump(bin2hex($str), bin2hex(htmlentities($str, ENT_QUOTES, '')));
var_dump(htmlentities($str, ENT_QUOTES | ENT_HTML5, ''));