FCKeditor/function parse
From Meta, a Wikimedia project coordination wiki
function parse( $text, &$title, $options, $linestart = true, $clearState = true, $revid = null ) {
/**
* First pass--just handle <nowiki> sections, pass the rest off
* to internalParse() which does all the real work.
*/
global $wgUseTidy, $wgAlwaysUseTidy, $wgContLang;
$fname = 'Parser::parse';
wfProfileIn( $fname );
if ( $clearState ) {
$this->clearState();
}
$this->mOptions = $options;
$this->mTitle =& $title;
$this->mRevisionId = $revid;
$this->mOutputType = OT_HTML;
$this->mStripState = NULL;
//$text = $this->strip( $text, $this->mStripState );
// VOODOO MAGIC FIX! Sometimes the above segfaults in PHP5.
$x =& $this->mStripState;
# patch fck editor
global $wgUseEditor, $wgEditorToken;
if (eregi($wgEditorToken, $text, $eregi_result)) {
$wgUseEditor = true;
}
wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$x ) );
$text = $this->strip( $text, $x );
wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$x ) );
if ($wgUseEditor == true) $text = preg_replace("|$wgEditorToken|i", "", $text);
# Hook to suspend the parser in this state
if ( !wfRunHooks( 'ParserBeforeInternalParse', array( &$this, &$text, &$x ) ) ) {
wfProfileOut( $fname );
return $text ;
}
$text = $this->internalParse( $text );
$text = $this->unstrip( $text, $this->mStripState );
# Clean up special characters, only run once, next-to-last before doBlockLevels
$fixtags = array(
# french spaces, last one Guillemet-left
# only if there is something before the space
'/(.) (?=\\?|:|;|!|\302円\273円)/' => '\1円 \2円',
# french spaces, Guillemet-right
'/(\302円\253円) /' => '\1円 ',
'/<center *>(.*)<\\/center *>/i' => '<div class="center">\1円</div>',
);
$text = preg_replace( array_keys($fixtags), array_values($fixtags), $text );
# only once and last
if (!$wgUseEditor) $text = $this->doBlockLevels( $text, $linestart ); # patch editor
$this->replaceLinkHolders( $text );
# the position of the parserConvert() call should not be changed. it
# assumes that the links are all replaced and the only thing left
# is the <nowiki> mark.
# Side-effects: this calls $this->mOutput->setTitleText()
$text = $wgContLang->parserConvert( $text, $this );
$text = $this->unstripNoWiki( $text, $this->mStripState );
wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
$text = Sanitizer::normalizeCharReferences( $text );
if (($wgUseTidy and $this->mOptions->mTidy) or $wgAlwaysUseTidy) {
$text = Parser::tidy($text);
} else {
# attempt to sanitize at least some nesting problems
# (bug #2702 and quite a few others)
$tidyregs = array(
# ''Something [http://www.cool.com cool''] -->
# <i>Something</i><a href="http://www.cool.com"..><i>cool></i></a>
'/(<([bi])>)(<([bi])>)?([^<]*)(<\/?a[^<]*>)([^<]*)(<\/\4円>)?(<\/\2円>)/' =>
'\1円\3円\5円\8円\9円\6円\1円\3円\7円\8円\9円',
# fix up an anchor inside another anchor, only
# at least for a single single nested link (bug 3695)
'/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
'\1円\2円</a>\3円</a>\1円\4円</a>',
# fix div inside inline elements- doBlockLevels won't wrap a line which
# contains a div, so fix it up here; replace
# div with escaped text
'/(<([aib]) [^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\/div>)([^<]*)(<\/\2円>)/' =>
'\1円\3円<div\5円>\6円</div>\8円\9円',
# remove empty italic or bold tag pairs, some
# introduced by rules above
'/<([bi])><\/\1円>/' => ''
);
$text = preg_replace(
array_keys( $tidyregs ),
array_values( $tidyregs ),
$text );
}
wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
$this->mOutput->setText( $text );
wfProfileOut( $fname );
return $this->mOutput;
}
</nowiki>