mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-04 21:28:06 +02:00
Code Issues Releases Wiki Activity

[1.1.1] To make up for DOMLex's tendency to drop tags, we've added a configuration option to let Tidy cleanup the HTML afterwards. Good for hand-editors. Also, Tidy is a smart solution for pretty-printed HTML, so we're marking the related TODO wontfix.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@454 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-09-24 21:23:54 +00:00
parent 6adbaf0e5c
commit 24663d65ed
4 changed files with 65 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
library/HTMLPurifier/Generator.php
View File

@@ -23,6 +23,19 @@ HTMLPurifier_ConfigSchema::define(
'This directive was available since 1.1.'
);
// extension constraints could be factored into ConfigSchema
HTMLPurifier_ConfigSchema::define(
'Core', 'TidyFormat', false, 'bool',
'Determines whether or not to run Tidy on the final output for pretty '.
'formatting reasons, such as indentation and wrap. This can greatly '.
'improve readability for editors who are hand-editing the HTML, but is '.
'by no means necessary as HTML Purifier has already fixed all major '.
'errors the HTML may have had and could potentially result in data loss '.
'due to bugs in Tidy. Tidy is a non-default extension, and this directive '.
'will silently fail if Tidy is not available. This '.
'directive was available since 1.1.1.'
);
/**
* Generates HTML from tokens.
*/
@@ -56,6 +69,30 @@ class HTMLPurifier_Generator
foreach ($tokens as $token) {
$html .= $this->generateFromToken($token);
}
if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
$tidy_options = array(
'indent'=> true,
'output-xhtml' => $this->_xhtml,
'show-body-only' => true,
'indent-spaces' => 2,
'wrap' => 68,
);
if (version_compare(PHP_VERSION, '5', '<')) {
tidy_set_encoding('utf8');
foreach ($tidy_options as $key => $value) {
tidy_setopt($key, $value);
}
tidy_parse_string($html);
tidy_clean_repair();
$html = tidy_get_output();
} else {
$tidy = new Tidy;
$tidy->parseString($html, $tidy_options, 'utf8');
$tidy->cleanRepair();
$html = (string) $tidy;
}
}
return $html;
}