mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-06 06:07:26 +02:00
Code Issues Releases Wiki Activity

Release 2.0.1, merged in 1181 to HEAD.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1255 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2007-06-27 14:30:45 +00:00
parent 42858ad594
commit 495164e938
326 changed files with 3025 additions and 826 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
library/HTMLPurifier/Lexer.php
View File

@@ -54,14 +54,15 @@ HTMLPurifier_ConfigSchema::define(
);
HTMLPurifier_ConfigSchema::define(
'Core', 'MaintainLineNumbers', false, 'bool', '
'Core', 'MaintainLineNumbers', null, 'bool/null', '
<p>
If true, HTML Purifier will add line number information to all tokens.
This is useful when error reporting is turned on, but can result in
significant performance degradation and should not be used when
unnecessary. This directive must be used with the DirectLex lexer,
as the DOMLex lexer does not (yet) support this functionality. This directive
has been available since 2.0.0.
as the DOMLex lexer does not (yet) support this functionality.
If the value is null, an appropriate value will be selected based
on other configuration. This directive has been available since 2.0.0.
</p>
');
@@ -154,7 +155,11 @@ class HTMLPurifier_Lexer
// once PHP DOM implements native line numbers, or we
// hack out something using XSLT, remove this stipulation
if ($config->get('Core', 'MaintainLineNumbers')) {
$line_numbers = $config->get('Core', 'MaintainLineNumbers');
if (
$line_numbers === true ||
($line_numbers === null && $config->get('Core', 'CollectErrors'))
) {
$lexer = 'DirectLex';
break;
}
@@ -259,7 +264,18 @@ class HTMLPurifier_Lexer
*/
static function escapeCDATA($string) {
return preg_replace_callback(
'/<!\[CDATA\[(.+?)\]\]>/',
'/<!\[CDATA\[(.+?)\]\]>/s',
array('HTMLPurifier_Lexer', 'CDATACallback'),
$string
);
}
/**
* Special CDATA case that is especiall convoluted for <script>
*/
function escapeCommentedCDATA($string) {
return preg_replace_callback(
'#<!--//--><!\[CDATA\[//><!--(.+?)//--><!\]\]>#s',
array('HTMLPurifier_Lexer', 'CDATACallback'),
$string
);
@@ -291,6 +307,15 @@ class HTMLPurifier_Lexer
$html = $this->extractBody($html);
}
// normalize newlines to \n
$html = str_replace("\r\n", "\n", $html);
$html = str_replace("\r", "\n", $html);
if ($config->get('HTML', 'Trusted')) {
// escape convoluted CDATA
$html = $this->escapeCommentedCDATA($html);
}
// escape CDATA
$html = $this->escapeCDATA($html);
@@ -320,4 +345,3 @@ class HTMLPurifier_Lexer
}
?>