mirror of
https://github.com/php/php-src.git
synced 2024-09-27 21:07:25 +00:00
7aa43a8d83
- Dramatic improvements on the performance of html_entity_decode and htmlspecialchars_decode, as the string is now traversed only once. Speedups of 20 to 25 times with Windows release builds and a ~250 characters string (for 2nd and subsequent calls). - Consistent behavior on html_entity_decode. For instance, the entity in "&<" would be decoded, but not "&é". Not anymore. The code path for "basic" and non-basic entities is now mostly shared. - Code of html_entity_decode and htmlspecialchars_decode is now shared. - [DOC] More consistent behavior of htmlspecialchars_decode. Instead of translating only <, >, &, ", ' and ', now e.g. ", ', ', ', etc. are also decoded. - [DOC] Previous translation of unicode code points in numerical entities was seriously broken. When the code points for some character were not the same in unicode and the target encoding, the behavior could be an erroneous translation (e.g. 0x80-0xA0 in win-1252) or no translation at all. Added unicode translation tables for all single-byte encodings. Entities are not translated for multi-byte entities, except for ASCII characters whose code points are shared. We could add the huge translation tables (several thousand elements) for those encodings in the future. - Fixed numerical entities that after # had text accepted by strcol being accepted. - Much more commented and well-structured code... - Tests for get_html_translation_table()) are broken. I stared fixing the tests, but then I realized it was completely helpless because get_html_translation_table() is broken by not handling multi-byte characters correctly.
170 lines
4.4 KiB
PHP
170 lines
4.4 KiB
PHP
--TEST--
|
|
Translation of HTML entities for encoding WIN-1252
|
|
--FILE--
|
|
<?php
|
|
$arr = array(
|
|
0x20AC => array(0x80, "EURO SIGN"),
|
|
//0x81 #UNDEFINED
|
|
0x201A => array(0x82, "SINGLE LOW-9 QUOTATION MARK"),
|
|
0x0192 => array(0x83, "LATIN SMALL LETTER F WITH HOOK"),
|
|
0x201E => array(0x84, "DOUBLE LOW-9 QUOTATION MARK"),
|
|
0x2026 => array(0x85, "HORIZONTAL ELLIPSIS"),
|
|
0x2020 => array(0x86, "DAGGER"),
|
|
0x2021 => array(0x87, "DOUBLE DAGGER"),
|
|
0x02C6 => array(0x88, "MODIFIER LETTER CIRCUMFLEX ACCENT"),
|
|
0x2030 => array(0x89, "PER MILLE SIGN"),
|
|
0x0160 => array(0x8A, "LATIN CAPITAL LETTER S WITH CARON"),
|
|
0x2039 => array(0x8B, "SINGLE LEFT-POINTING ANGLE QUOTATION MARK"),
|
|
0x0152 => array(0x8C, "LATIN CAPITAL LIGATURE OE"),
|
|
//0x8D #UNDEFINED
|
|
0x017D => array(0x8E, "LATIN CAPITAL LETTER Z WITH CARON"),
|
|
//0x8F #UNDEFINED
|
|
//0x90 #UNDEFINED
|
|
0x2018 => array(0x91, "LEFT SINGLE QUOTATION MARK"),
|
|
0x2019 => array(0x92, "RIGHT SINGLE QUOTATION MARK"),
|
|
0x201C => array(0x93, "LEFT DOUBLE QUOTATION MARK"),
|
|
0x201D => array(0x94, "RIGHT DOUBLE QUOTATION MARK"),
|
|
0x2022 => array(0x95, "BULLET"),
|
|
0x2013 => array(0x96, "EN DASH"),
|
|
0x2014 => array(0x97, "EM DASH"),
|
|
0x02DC => array(0x98, "SMALL TILDE"),
|
|
0x2122 => array(0x99, "TRADE MARK SIGN"),
|
|
0x0161 => array(0x9A, "LATIN SMALL LETTER S WITH CARON"),
|
|
0x203A => array(0x9B, "SINGLE RIGHT-POINTING ANGLE QUOTATION MARK"),
|
|
0x0153 => array(0x9C, "LATIN SMALL LIGATURE OE"),
|
|
//0x9D #UNDEFINED
|
|
0x017E => array(0x9E, "LATIN SMALL LETTER Z WITH CARON"),
|
|
0x0178 => array(0x9F, "LATIN CAPITAL LETTER Y WITH DIAERESIS"),
|
|
);
|
|
|
|
$res = html_entity_decode("", ENT_QUOTES, 'WINDOWS-1252');
|
|
echo "Special test for  (shouldn't decode):\n";
|
|
echo $res,"\n\n";
|
|
|
|
$res = html_entity_decode("", ENT_QUOTES, 'WINDOWS-1252');
|
|
echo "Special test for  (shouldn't decode):\n";
|
|
echo $res,"\n\n";
|
|
|
|
$res = html_entity_decode("", ENT_QUOTES, 'WINDOWS-1252');
|
|
echo "Special test for  (shouldn't decode):\n";
|
|
echo $res,"\n\n";
|
|
|
|
$res = html_entity_decode("", ENT_QUOTES, 'WINDOWS-1252');
|
|
echo "Special test for  (shouldn't decode):\n";
|
|
echo $res,"\n\n";
|
|
|
|
$res = html_entity_decode("", ENT_QUOTES, 'WINDOWS-1252');
|
|
echo "Special test for  (shouldn't decode):\n";
|
|
echo $res,"\n\n";
|
|
|
|
foreach ($arr as $u => $v) {
|
|
$ent = sprintf("&#x%X;", $u);
|
|
$res = html_entity_decode($ent, ENT_QUOTES, 'WINDOWS-1252');
|
|
$d = unpack("H*", $res);
|
|
echo sprintf("%s: %s => %s\n", $v[1], $ent, $d[1]);
|
|
|
|
$ent = sprintf("&#x%X;", $v[0]);
|
|
$res = html_entity_decode($ent, ENT_QUOTES, 'WINDOWS-1252');
|
|
if ($res[0] != "&" || $res[1] != "#")
|
|
$res = unpack("H*", $res)[1];
|
|
echo sprintf("%s => %s\n\n", $ent, $res);
|
|
}
|
|
--EXPECT--
|
|
Special test for  (shouldn't decode):
|
|

|
|
|
|
Special test for  (shouldn't decode):
|
|

|
|
|
|
Special test for  (shouldn't decode):
|
|

|
|
|
|
Special test for  (shouldn't decode):
|
|

|
|
|
|
Special test for  (shouldn't decode):
|
|

|
|
|
|
EURO SIGN: € => 80
|
|
€ => €
|
|
|
|
SINGLE LOW-9 QUOTATION MARK: ‚ => 82
|
|
‚ => ‚
|
|
|
|
LATIN SMALL LETTER F WITH HOOK: ƒ => 83
|
|
ƒ => ƒ
|
|
|
|
DOUBLE LOW-9 QUOTATION MARK: „ => 84
|
|
„ => „
|
|
|
|
HORIZONTAL ELLIPSIS: … => 85
|
|
… => …
|
|
|
|
DAGGER: † => 86
|
|
† => †
|
|
|
|
DOUBLE DAGGER: ‡ => 87
|
|
‡ => ‡
|
|
|
|
MODIFIER LETTER CIRCUMFLEX ACCENT: ˆ => 88
|
|
ˆ => ˆ
|
|
|
|
PER MILLE SIGN: ‰ => 89
|
|
‰ => ‰
|
|
|
|
LATIN CAPITAL LETTER S WITH CARON: Š => 8a
|
|
Š => Š
|
|
|
|
SINGLE LEFT-POINTING ANGLE QUOTATION MARK: ‹ => 8b
|
|
‹ => ‹
|
|
|
|
LATIN CAPITAL LIGATURE OE: Π=> 8c
|
|
Œ => Œ
|
|
|
|
LATIN CAPITAL LETTER Z WITH CARON: Ž => 8e
|
|
Ž => Ž
|
|
|
|
LEFT SINGLE QUOTATION MARK: ‘ => 91
|
|
‘ => ‘
|
|
|
|
RIGHT SINGLE QUOTATION MARK: ’ => 92
|
|
’ => ’
|
|
|
|
LEFT DOUBLE QUOTATION MARK: “ => 93
|
|
“ => “
|
|
|
|
RIGHT DOUBLE QUOTATION MARK: ” => 94
|
|
” => ”
|
|
|
|
BULLET: • => 95
|
|
• => •
|
|
|
|
EN DASH: – => 96
|
|
– => –
|
|
|
|
EM DASH: — => 97
|
|
— => —
|
|
|
|
SMALL TILDE: ˜ => 98
|
|
˜ => ˜
|
|
|
|
TRADE MARK SIGN: ™ => 99
|
|
™ => ™
|
|
|
|
LATIN SMALL LETTER S WITH CARON: š => 9a
|
|
š => š
|
|
|
|
SINGLE RIGHT-POINTING ANGLE QUOTATION MARK: › => 9b
|
|
› => ›
|
|
|
|
LATIN SMALL LIGATURE OE: œ => 9c
|
|
œ => œ
|
|
|
|
LATIN SMALL LETTER Z WITH CARON: ž => 9e
|
|
ž => ž
|
|
|
|
LATIN CAPITAL LETTER Y WITH DIAERESIS: Ÿ => 9f
|
|
Ÿ => Ÿ
|
|
|
|
|