* changes in an incompatible way, so the parser cache
* can automatically discard old data.
*/
-define( 'MW_PARSER_VERSION', '1.6.0' );
+define( 'MW_PARSER_VERSION', '1.6.1' );
/**
* Variable substitution O(N^2) attack
class Parser
{
/**#@+
- * @access private
+ * @private
*/
# Persistent:
- var $mTagHooks;
+ var $mTagHooks, $mFunctionHooks;
# Cleared with clearState():
var $mOutput, $mAutonumber, $mDTopen, $mStripState = array();
/**
* Constructor
*
- * @access public
+ * @public
*/
function Parser() {
$this->mTagHooks = array();
+ $this->mFunctionHooks = array();
$this->clearState();
}
/**
* Clear Parser state
*
- * @access private
+ * @private
*/
function clearState() {
$this->mOutput = new ParserOutput;
/**
* Accessor for mUniqPrefix.
*
- * @access public
+ * @public
*/
function UniqPrefix() {
return $this->mUniqPrefix;
* Convert wikitext to HTML
* Do not call this function recursively.
*
- * @access private
+ * @private
* @param string $text Text we want to parse
* @param Title &$title A title object
* @param array $options
$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 =& $this->mStripState;
if (($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>)?(<\/\\2>)/' =>
+ '\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9',
+ # fix up an anchor inside another anchor, only
+ # at least for a single single nested link (bug 3695)
+ '/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
+ '\\1\\2</a>\\3</a>\\1\\4</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>)/' =>
+ '\\1\\3<div\\5>\\6</div>\\8\\9',
+ # remove empty italic or bold tag pairs, some
+ # introduced by rules above
+ '/<([bi])><\/\\1>/' => ''
+ );
+
+ $text = preg_replace(
+ array_keys( $tidyregs ),
+ array_values( $tidyregs ),
+ $text );
}
wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
/**
* Get a random string
*
- * @access private
+ * @private
* @static
*/
function getRandomString() {
* If $tag is set to STRIP_COMMENTS, the function will extract
* <!-- HTML comments -->
*
- * @access private
+ * @private
* @static
*/
function extractTagsAndParams($tag, $text, &$content, &$tags, &$params, $uniq_prefix = ''){
}
if( $tag == STRIP_COMMENTS ) {
- $start = '/<!--()()/';
+ $start = '/<!--()/';
$end = '/-->/';
} else {
- $start = "/<$tag(\\s+[^\\/>]*|\\s*)(\\/?)>/i";
+ $start = "/<$tag(\\s+[^>]*|\\s*\/?)>/i";
$end = "/<\\/$tag\\s*>/i";
}
while ( '' != $text ) {
$p = preg_split( $start, $text, 2, PREG_SPLIT_DELIM_CAPTURE );
$stripped .= $p[0];
- if( count( $p ) < 4 ) {
+ if( count( $p ) < 3 ) {
break;
}
$attributes = $p[1];
- $empty = $p[2];
- $inside = $p[3];
+ $inside = $p[2];
+
+ // If $attributes ends with '/', we have an empty element tag, <tag />
+ if( $tag != STRIP_COMMENTS && substr( $attributes, -1 ) == '/' ) {
+ $attributes = substr( $attributes, 0, -1);
+ $empty = '/';
+ } else {
+ $empty = '';
+ }
$marker = $rnd . sprintf('%08X', $n++);
$stripped .= $marker;
* for cases where $tags and $params isn't needed
* i.e. where tags will never have params, like <nowiki>
*
- * @access private
+ * @private
* @static
*/
function extractTags( $tag, $text, &$content, $uniq_prefix = '' ) {
* for section editing, where these comments cause confusion when
* counting the sections in the wikisource
*
- * @access private
+ * @private
*/
function strip( $text, &$state, $stripcomments = false ) {
$render = ($this->mOutputType == OT_HTML);
}
# Comments
- if($stripcomments) {
- $text = Parser::extractTags(STRIP_COMMENTS, $text, $comment_content, $uniq_prefix);
- foreach( $comment_content as $marker => $content ){
- $comment_content[$marker] = '<!--'.$content.'-->';
- }
+ $text = Parser::extractTags(STRIP_COMMENTS, $text, $comment_content, $uniq_prefix);
+ foreach( $comment_content as $marker => $content ){
+ $comment_content[$marker] = '<!--'.$content.'-->';
}
# Extensions
}
}
+ # Unstrip comments unless explicitly told otherwise.
+ # (The comments are always stripped prior to this point, so as to
+ # not invoke any extension tags / parser hooks contained within
+ # a comment.)
+ if ( !$stripcomments ) {
+ $tempstate = array( 'comment' => $comment_content );
+ $text = $this->unstrip( $text, $tempstate );
+ $comment_content = array();
+ }
+
# Merge state with the pre-existing state, if there is one
if ( $state ) {
$state['html'] = $state['html'] + $html_content;
* restores pre, math, and hiero removed by strip()
*
* always call unstripNoWiki() after this one
- * @access private
+ * @private
*/
function unstrip( $text, &$state ) {
if ( !is_array( $state ) ) {
/**
* always call this after unstrip() to preserve the order
*
- * @access private
+ * @private
*/
function unstripNoWiki( $text, &$state ) {
if ( !is_array( $state ) ) {
* Returns the unique tag which must be inserted into the stripped text
* The tag will be replaced with the original text in unstrip()
*
- * @access private
+ * @private
*/
function insertStripItem( $text, &$state ) {
$rnd = $this->mUniqPrefix . '-item' . Parser::getRandomString();
*
* @param string $text Hideous HTML input
* @return string Corrected HTML output
- * @access public
+ * @public
* @static
*/
function tidy( $text ) {
/**
* Spawn an external HTML tidy process and get corrected markup back from it.
*
- * @access private
+ * @private
* @static
*/
function externalTidy( $text ) {
$process = proc_open("$wgTidyBin -config $wgTidyConf $wgTidyOpts$opts", $descriptorspec, $pipes);
if (is_resource($process)) {
// Theoretically, this style of communication could cause a deadlock
- // here. If the stdout buffer fills up, then writes to stdin could
+ // here. If the stdout buffer fills up, then writes to stdin could
// block. This doesn't appear to happen with tidy, because tidy only
- // writes to stdout after it's finished reading from stdin. Search
+ // writes to stdout after it's finished reading from stdin. Search
// for tidyParseStdin and tidySaveStdout in console/tidy.c
fwrite($pipes[0], $text);
fclose($pipes[0]);
*
* 'pear install tidy' should be able to compile the extension module.
*
- * @access private
+ * @private
* @static
*/
function internalTidy( $text ) {
/**
* parse the wiki syntax used to render tables
*
- * @access private
+ * @private
*/
function doTableStuff ( $t ) {
$fname = 'Parser::doTableStuff';
}
$after = substr ( $x , 1 ) ;
if ( $fc == '!' ) $after = str_replace ( '!!' , '||' , $after ) ;
- $after = explode ( '||' , $after ) ;
+
+ // Split up multiple cells on the same line.
+ // FIXME: This can result in improper nesting of tags processed
+ // by earlier parser steps, but should avoid splitting up eg
+ // attribute values containing literal "||".
+ $after = wfExplodeMarkup( '||', $after );
+
$t[$k] = '' ;
# Loop through each table cell
}
$t = implode ( "\n" , $t ) ;
+ # special case: don't return empty table
+ if($t == "<table>\n<tr><td></td></tr>\n</table>")
+ $t = '';
wfProfileOut( $fname );
return $t ;
}
* Helper function for parse() that transforms wiki markup into
* HTML. Only called for $mOutputType == OT_HTML.
*
- * @access private
+ * @private
*/
function internalParse( $text ) {
- global $wgContLang;
$args = array();
$isMain = true;
$fname = 'Parser::internalParse';
* Replace special strings like "ISBN xxx" and "RFC xxx" with
* magic external links.
*
- * @access private
+ * @private
*/
function &doMagicLinks( &$text ) {
$text = $this->magicISBN( $text );
/**
* Parse headers and return html
*
- * @access private
+ * @private
*/
function doHeadings( $text ) {
$fname = 'Parser::doHeadings';
/**
* Replace single quotes with HTML markup
- * @access private
+ * @private
* @return string the altered text
*/
function doAllQuotes( $text ) {
/**
* Helper function for doAllQuotes()
- * @access private
+ * @private
*/
function doQuotes( $text ) {
$arr = preg_split( "/(''+)/", $text, -1, PREG_SPLIT_DELIM_CAPTURE );
* Note: this is all very hackish and the order of execution matters a lot.
* Make sure to run maintenance/parserTests.php if you change this code.
*
- * @access private
+ * @private
*/
function replaceExternalLinks( $text ) {
global $wgContLang;
# Replace & from obsolete syntax with &.
# All HTML entities will be escaped by makeExternalLink()
$url = str_replace( '&', '&', $url );
- # Replace unnecessary URL escape codes with the referenced character
- # This prevents spammers from hiding links from the filters
- $url = Parser::replaceUnusualEscapes( $url );
# Process the trail (i.e. everything after this link up until start of the next link),
# replacing any non-bracketed links
# This was changed in August 2004
$s .= $sk->makeExternalLink( $url, $text, false, $linktype ) . $dtrail . $trail;
- # Register link in the output object
- $this->mOutput->addExternalLink( $url );
+ # Register link in the output object.
+ # Replace unnecessary URL escape codes with the referenced character
+ # This prevents spammers from hiding links from the filters
+ $pasteurized = Parser::replaceUnusualEscapes( $url );
+ $this->mOutput->addExternalLink( $pasteurized );
}
wfProfileOut( $fname );
/**
* Replace anything that looks like a URL with a link
- * @access private
+ * @private
*/
function replaceFreeExternalLinks( $text ) {
global $wgContLang;
$url = $protocol . $m[1];
$trail = $m[2];
+ # special case: handle urls as url args:
+ # http://www.example.com/foo?=http://www.example.com/bar
+ if(strlen($trail) == 0 &&
+ isset($bits[$i]) &&
+ preg_match('/^'. wfUrlProtocols() . '$/S', $bits[$i]) &&
+ preg_match( '/^('.EXT_LINK_URL_CLASS.'+)(.*)$/s', $bits[$i + 1], $m ))
+ {
+ # add protocol, arg
+ $url .= $bits[$i] . $m[1]; # protocol, url as arg to previous link
+ $i += 2;
+ $trail = $m[2];
+ }
+
# The characters '<' and '>' (which were escaped by
# removeHTMLtags()) should not be included in
# URLs, per RFC 2396.
# All HTML entities will be escaped by makeExternalLink()
# or maybeMakeExternalImage()
$url = str_replace( '&', '&', $url );
- # Replace unnecessary URL escape codes with their equivalent characters
- $url = Parser::replaceUnusualEscapes( $url );
# Is this an external image?
$text = $this->maybeMakeExternalImage( $url );
if ( $text === false ) {
# Not an image, make a link
$text = $sk->makeExternalLink( $url, $wgContLang->markNoConversion($url), true, 'free' );
- # Register it in the output object
- $this->mOutput->addExternalLink( $url );
+ # Register it in the output object...
+ # Replace unnecessary URL escape codes with their equivalent characters
+ $pasteurized = Parser::replaceUnusualEscapes( $url );
+ $this->mOutput->addExternalLink( $pasteurized );
}
$s .= $text . $trail;
} else {
/**
* Replace unusual URL escape codes with their equivalent characters
- * @param string
+ * @param string
* @return string
* @static
+ * @fixme This can merge genuinely required bits in the path or query string,
+ * breaking legit URLs. A proper fix would treat the various parts of
+ * the URL differently; as a workaround, just use the output for
+ * statistical records, not for actual linking/output.
*/
function replaceUnusualEscapes( $url ) {
- return preg_replace_callback( '/%[0-9A-Fa-f]{2}/',
+ return preg_replace_callback( '/%[0-9A-Fa-f]{2}/',
array( 'Parser', 'replaceUnusualEscapesCallback' ), $url );
}
* Callback function used in replaceUnusualEscapes().
* Replaces unusual URL escape codes with their equivalent character
* @static
- * @access private
+ * @private
*/
function replaceUnusualEscapesCallback( $matches ) {
$char = urldecode( $matches[0] );
/**
* make an image if it's allowed, either through the global
* option or through the exception
- * @access private
+ * @private
*/
function maybeMakeExternalImage( $url ) {
$sk =& $this->mOptions->getSkin();
/**
* Process [[ ]] wikilinks
*
- * @access private
+ * @private
*/
function replaceInternalLinks( $s ) {
global $wgContLang;
# Still some problems for cases where the ] is meant to be outside punctuation,
# and no image is in sight. See bug 2095.
#
- if( $text !== '' && preg_match( "/^\](.*)/s", $m[3], $n ) ) {
+ if( $text !== '' &&
+ preg_match( "/^\](.*)/s", $m[3], $n ) &&
+ strpos($text, '[') !== false
+ )
+ {
$text .= ']'; # so that replaceExternalLinks($text) works later
$m[3] = $n[1];
}
# fix up urlencoded title texts
- if(preg_match('/%/', $m[1] )) $m[1] = urldecode($m[1]);
+ if(preg_match('/%/', $m[1] ))
+ # Should anchors '#' also be rejected?
+ $m[1] = str_replace( array('<', '>'), array('<', '>'), urldecode($m[1]) );
$trail = $m[3];
} elseif( preg_match($e1_img, $line, $m) ) { # Invalid, but might be an image with a link in its caption
$might_be_img = true;
* @param string $target the source of the link
* @param string &$text the link text, modified as necessary
* @return string the full name of the link
- * @access private
+ * @private
*/
function maybeDoSubpageLink($target, &$text) {
# Valid link forms:
/**#@+
* Used by doBlockLevels()
- * @access private
+ * @private
*/
/* private */ function closeParagraph() {
$result = '';
/**
* Make lists from lines starting with ':', '*', '#', etc.
*
- * @access private
+ * @private
* @return string the lists rendered as HTML
*/
function doBlockLevels( $text, $linestart ) {
'<td|<th|<div|<\\/div|<hr|<\\/pre|<\\/p|'.$this->mUniqPrefix.'-pre|<\\/li|<\\/ul)/iS', $t );
if ( $openmatch or $closematch ) {
$paragraphStack = false;
+ #Â TODO bug 5718: paragraph closed
$output .= $this->closeParagraph();
if ( $preOpenMatch and !$preCloseMatch ) {
$this->mInPre = true;
/**
* Return value of a magic variable (like PAGENAME)
*
- * @access private
+ * @private
*/
function getVariableValue( $index ) {
global $wgContLang, $wgSitename, $wgServer, $wgServerName, $wgScriptPath;
return $this->mTitle->getPrefixedText();
case MAG_FULLPAGENAMEE:
return $this->mTitle->getPrefixedURL();
+ case MAG_SUBPAGENAME:
+ return $this->mTitle->getSubpageText();
+ case MAG_SUBPAGENAMEE:
+ return $this->mTitle->getSubpageUrlForm();
+ case MAG_TALKPAGENAME:
+ if( $this->mTitle->canTalk() ) {
+ $talkPage = $this->mTitle->getTalkPage();
+ return $talkPage->getPrefixedText();
+ } else {
+ return '';
+ }
+ case MAG_TALKPAGENAMEE:
+ if( $this->mTitle->canTalk() ) {
+ $talkPage = $this->mTitle->getTalkPage();
+ return $talkPage->getPrefixedUrl();
+ } else {
+ return '';
+ }
+ case MAG_SUBJECTPAGENAME:
+ $subjPage = $this->mTitle->getSubjectPage();
+ return $subjPage->getPrefixedText();
+ case MAG_SUBJECTPAGENAMEE:
+ $subjPage = $this->mTitle->getSubjectPage();
+ return $subjPage->getPrefixedUrl();
case MAG_REVISIONID:
return $this->mRevisionId;
case MAG_NAMESPACE:
return $wgContLang->getNsText( $this->mTitle->getNamespace() );
case MAG_NAMESPACEE:
return wfUrlencode( $wgContLang->getNsText( $this->mTitle->getNamespace() ) );
+ case MAG_TALKSPACE:
+ return $this->mTitle->canTalk() ? $this->mTitle->getTalkNsText() : '';
+ case MAG_TALKSPACEE:
+ return $this->mTitle->canTalk() ? wfUrlencode( $this->mTitle->getTalkNsText() ) : '';
+ case MAG_SUBJECTSPACE:
+ return $this->mTitle->getSubjectNsText();
+ case MAG_SUBJECTSPACEE:
+ return( wfUrlencode( $this->mTitle->getSubjectNsText() ) );
case MAG_CURRENTDAYNAME:
return $varCache[$index] = $wgContLang->getWeekdayName( date( 'w', $ts ) + 1 );
case MAG_CURRENTYEAR:
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfArticles() );
case MAG_NUMBEROFFILES:
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfFiles() );
+ case MAG_NUMBEROFUSERS:
+ return $varCache[$index] = $wgContLang->formatNum( wfNumberOfUsers() );
case MAG_SITENAME:
return $wgSitename;
case MAG_SERVER:
/**
* initialise the magic variables (like CURRENTMONTHNAME)
*
- * @access private
+ * @private
*/
function initialiseVariables() {
$fname = 'Parser::initialiseVariables';
* 4 => callback # replacement callback to call if {{{{..}}}} is found
* )
* )
- * @access private
+ * @private
*/
function replace_callback ($text, $callbacks) {
$openingBraceStack = array(); # this array will hold a stack of parentheses which are not closed yet
* @param string $tex The text to transform
* @param array $args Key-value pairs representing template parameters to substitute
* @param bool $argsOnly Only do argument (triple-brace) expansion, not double-brace expansion
- * @access private
+ * @private
*/
function replaceVariables( $text, $args = array(), $argsOnly = false ) {
# Prevent too big inclusions
/**
* Replace magic variables
- * @access private
+ * @private
*/
function variableSubstitution( $matches ) {
$fname = 'Parser::variableSubstitution';
* $piece['title']: the title, i.e. the part before the |
* $piece['parts']: the parameter array
* @return string the text of the template
- * @access private
+ * @private
*/
function braceSubstitution( $piece ) {
- global $wgContLang;
+ global $wgContLang, $wgLang, $wgAllowDisplayTitle, $action;
$fname = 'Parser::braceSubstitution';
wfProfileIn( $fname );
- # Flags
+ # Flags
$found = false; # $text has been filled
$nowiki = false; # wiki markup in $text should be escaped
$noparse = false; # Unsafe HTML tags should not be stripped, etc.
}
}
+ $lang = $this->mOptions->getInterfaceMessage() ? $wgLang : $wgContLang;
# GRAMMAR
if ( !$found && $argc == 1 ) {
$mwGrammar =& MagicWord::get( MAG_GRAMMAR );
if ( $mwGrammar->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $wgContLang->convertGrammar( $args[0], $part1 );
+ $text = $linestart . $lang->convertGrammar( $args[0], $part1 );
$found = true;
}
}
$mwPluralForm =& MagicWord::get( MAG_PLURAL );
if ( $mwPluralForm->matchStartAndRemove( $part1 ) ) {
if ($argc==2) {$args[2]=$args[1];}
- $text = $linestart . $wgContLang->convertPlural( $part1, $args[0], $args[1], $args[2]);
+ $text = $linestart . $lang->convertPlural( $part1, $args[0], $args[1], $args[2]);
$found = true;
}
}
+
+ # DISPLAYTITLE
+ if ( !$found && $argc == 1 && $wgAllowDisplayTitle ) {
+ $mwDT =& MagicWord::get( MAG_DISPLAYTITLE );
+ if ( $mwDT->matchStartAndRemove( $part1 ) ) {
+
+ # Set title in parser output object
+ $param = $args[0];
+ $parserOptions = new ParserOptions;
+ $local_parser = new Parser ();
+ $t2 = $local_parser->parse ( $param, $this->mTitle, $parserOptions, false );
+ $this->mOutput->mHTMLtitle = $t2->GetText();
+
+ # Add subtitle
+ $t = $this->mTitle->getPrefixedText();
+ $this->mOutput->mSubtitle .= wfMsg('displaytitle', $t);
+ $text = "" ;
+ $found = true ;
+ }
+ }
+
+ # NUMBEROFUSERS, NUMBEROFARTICLES, and NUMBEROFFILES
+ if( !$found ) {
+ $mwWordsToCheck = array( MAG_NUMBEROFUSERS => 'wfNumberOfUsers', MAG_NUMBEROFARTICLES => 'wfNumberOfArticles', MAG_NUMBEROFFILES => 'wfNumberOfFiles' );
+ foreach( $mwWordsToCheck as $word => $func ) {
+ $mwCurrentWord =& MagicWord::get( $word );
+ if( $mwCurrentWord->matchStartAndRemove( $part1 ) ) {
+ $mwRawSuffix =& MagicWord::get( MAG_RAWSUFFIX );
+ if( $mwRawSuffix->match( $args[0] ) ) {
+ # Raw and unformatted
+ $text = $linestart . call_user_func( $func );
+ } else {
+ # Formatted according to the content default
+ $text = $linestart . $wgContLang->formatNum( call_user_func( $func ) );
+ }
+ $found = true;
+ }
+ }
+ }
+
+ /*$mwNumUsers =& MagicWord::get( MAG_NUMBEROFUSERS );
+ if( $mwNumUsers->matchStartAndRemove( $part1 ) ) {
+ $mwRawSuffix =& MagicWord::get( MAG_RAWSUFFIX );
+ if( $mwRawSuffix->match( $args[0] ) ) {
+ # Raw and unformatted
+ $text = $linestart . wfNumberOfUsers();
+ } else {
+ # Default; formatted form
+ $text = $linestart . $wgContLang->formatNum( wfNumberOfUsers() );
+ }
+ $found = true;
+ }
+ }*/
+
+ # Extensions
+ if ( !$found && substr( $part1, 0, 1 ) == '#' ) {
+ $colonPos = strpos( $part1, ':' );
+ if ( $colonPos !== false ) {
+ $function = strtolower( substr( $part1, 1, $colonPos - 1 ) );
+ if ( isset( $this->mFunctionHooks[$function] ) ) {
+ $funcArgs = array_map( 'trim', $args );
+ $funcArgs = array_merge( array( &$this, trim( substr( $part1, $colonPos + 1 ) ) ), $funcArgs );
+ $result = call_user_func_array( $this->mFunctionHooks[$function], $funcArgs );
+ $found = true;
+
+ // The text is usually already parsed, doesn't need triple-brace tags expanded, etc.
+ //$noargs = true;
+ //$noparse = true;
+
+ if ( is_array( $result ) ) {
+ $text = $linestart . $result[0];
+ unset( $result[0] );
+
+ // Extract flags into the local scope
+ // This allows callers to set flags such as nowiki, noparse, found, etc.
+ extract( $result );
+ } else {
+ $text = $linestart . $result;
+ }
+ }
+ }
+ }
# Template table test
$lastPathLevel = $this->mTemplatePath;
if ( !$found ) {
$ns = NS_TEMPLATE;
- $part1 = $this->maybeDoSubpageLink( $part1, $subpage='' );
+ # declaring $subpage directly in the function call
+ # does not work correctly with references and breaks
+ # {{/subpage}}-style inclusions
+ $subpage = '';
+ $part1 = $this->maybeDoSubpageLink( $part1, $subpage );
if ($subpage !== '') {
$ns = $this->mTitle->getNamespace();
}
if ( $nowiki && $found && $this->mOutputType == OT_HTML ) {
$text = wfEscapeWikiText( $text );
} elseif ( ($this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI) && $found ) {
- if ( !$noargs ) {
+ if ( $noargs ) {
+ $assocArgs = array();
+ } else {
# Clean up argument array
$assocArgs = array();
$index = 1;
}
/**
- * Fetch the unparsed text of a template and register a reference to it.
+ * Fetch the unparsed text of a template and register a reference to it.
*/
function fetchTemplate( $title ) {
$text = false;
/**
* Triple brace replacement -- used for template arguments
- * @access private
+ * @private
*/
function argSubstitution( $matches ) {
$arg = trim( $matches['title'] );
/**
* Returns true if the function is allowed to include this entity
- * @access private
+ * @private
*/
function incrementIncludeCount( $dbk ) {
if ( !array_key_exists( $dbk, $this->mIncludeCount ) ) {
*
* @param string $text
* @param boolean $isMain
- * @access private
+ * @private
*/
function formatHeadings( $text, $isMain=true ) {
global $wgMaxTocLevel, $wgContLang;
$doShowToc = false;
}
+ # Allow user to stipulate that a page should have a "new section"
+ # link added via __NEWSECTIONLINK__
+ $mw =& MagicWord::get( MAG_NEWSECTIONLINK );
+ if( $mw->matchAndRemove( $text ) )
+ $this->mOutput->setNewSection( true );
+
# if the string __TOC__ (not case-sensitive) occurs in the HTML,
# override above conditions and always show TOC at that place
# Increase TOC level
$toclevel++;
$sublevelCount[$toclevel] = 0;
- $toc .= $sk->tocIndent();
+ if( $toclevel<$wgMaxTocLevel ) {
+ $toc .= $sk->tocIndent();
+ }
}
elseif ( $level < $prevlevel && $toclevel > 1 ) {
# Decrease TOC level, find level to jump to
}
}
}
-
- $toc .= $sk->tocUnindent( $prevtoclevel - $toclevel );
+ if( $toclevel<$wgMaxTocLevel ) {
+ $toc .= $sk->tocUnindent( $prevtoclevel - $toclevel );
+ }
}
else {
# No change in level, end TOC line
- $toc .= $sk->tocLineEnd();
+ if( $toclevel<$wgMaxTocLevel ) {
+ $toc .= $sk->tocLineEnd();
+ }
}
$levelCount[$toclevel] = $level;
$canonized_headline = preg_replace( '/<.*?' . '>/','',$canonized_headline );
$tocline = trim( $canonized_headline );
# Save headline for section edit hint before it's escaped
- $headline_hint = trim( $canonized_headline );
+ $headline_hint = trim( $canonized_headline );
$canonized_headline = Sanitizer::escapeId( $tocline );
$refers[$headlineCount] = $canonized_headline;
}
if( $doShowToc ) {
- $toc .= $sk->tocUnindent( $toclevel - 1 );
+ if( $toclevel<$wgMaxTocLevel ) {
+ $toc .= $sk->tocUnindent( $toclevel - 1 );
+ }
$toc = $sk->tocList( $toc );
}
/**
* Return an HTML link for the "ISBN 123456" text
- * @access private
+ * @private
*/
function magicISBN( $text ) {
$fname = 'Parser::magicISBN';
$valid = '0123456789-Xx';
foreach ( $a as $x ) {
+ # hack: don't replace inside thumbnail title/alt
+ # attributes
+ if(preg_match('/<[^>]+(alt|title)="[^">]*$/', $text)) {
+ $text .= "ISBN $x";
+ continue;
+ }
+
$isbn = $blank = '' ;
while ( ' ' == $x{0} ) {
$blank .= ' ';
} else {
$titleObj = Title::makeTitle( NS_SPECIAL, 'Booksources' );
$text .= '<a href="' .
- $titleObj->escapeLocalUrl( 'isbn='.$num ) .
+ $titleObj->escapeLocalUrl( 'isbn='.$num ) .
"\" class=\"internal\">ISBN $isbn</a>";
$text .= $x;
}
/**
* Return an HTML link for the "RFC 1234" text
*
- * @access private
+ * @private
* @param string $text Text to be processed
* @param string $keyword Magic keyword to use (default RFC)
* @param string $urlmsg Interface message to use (default rfcurl)
continue;
}
+ # hack: don't replace inside thumbnail title/alt
+ # attributes
+ if(preg_match('/<[^>]+(alt|title)="[^">]*$/', $text)) {
+ $text .= $keyword . $x;
+ continue;
+ }
+
$id = $blank = '' ;
/** remove and save whitespaces in $blank */
* @param ParserOptions $options parsing options
* @param bool $clearState whether to clear the parser state first
* @return string the altered wiki markup
- * @access public
+ * @public
*/
function preSaveTransform( $text, &$title, &$user, $options, $clearState = true ) {
$this->mOptions = $options;
);
$text = str_replace( array_keys( $pairs ), array_values( $pairs ), $text );
$text = $this->strip( $text, $stripState, true );
- $text = $this->pstPass2( $text, $user );
+ $text = $this->pstPass2( $text, $stripState, $user );
$text = $this->unstrip( $text, $stripState );
$text = $this->unstripNoWiki( $text, $stripState );
return $text;
/**
* Pre-save transform helper function
- * @access private
+ * @private
*/
- function pstPass2( $text, &$user ) {
+ function pstPass2( $text, &$stripState, &$user ) {
global $wgContLang, $wgLocaltimezone;
/* Note: This is the timestamp saved as hardcoded wikitext to
* the database, we use $wgContLang here in order to give
- * everyone the same signiture and use the default one rather
- * than the one selected in each users preferences.
+ * everyone the same signature and use the default one rather
+ * than the one selected in each user's preferences.
*/
if ( isset( $wgLocaltimezone ) ) {
$oldtz = getenv( 'TZ' );
# Because mOutputType is OT_WIKI, this will only process {{subst:xxx}} type tags
$text = $this->replaceVariables( $text );
+ # Strip out <nowiki> etc. added via replaceVariables
+ $text = $this->strip( $text, $stripState );
+
# Signatures
$sigText = $this->getUserSig( $user );
- $text = strtr( $text, array(
+ $text = strtr( $text, array(
'~~~~~' => $d,
'~~~~' => "$sigText $d",
'~~~' => $sigText
*
* @param User $user
* @return string
- * @access private
+ * @private
*/
function getUserSig( &$user ) {
- global $wgContLang;
-
$username = $user->getName();
$nickname = $user->getOption( 'nickname' );
$nickname = $nickname === '' ? $username : $nickname;
# Sig. might contain markup; validate this
if( $this->validateSig( $nickname ) !== false ) {
# Validated; clean up (if needed) and return it
- return( $this->cleanSig( $nickname ) );
+ return $this->cleanSig( $nickname, true );
} else {
# Failed to validate; fall back to the default
$nickname = $username;
* 2) Substitute all transclusions
*
* @param string $text
+ * @param $parsing Whether we're cleaning (preferences save) or parsing
* @return string Signature text
*/
- function cleanSig( $text ) {
+ function cleanSig( $text, $parsing = false ) {
+ global $wgTitle;
+ $this->startExternalParse( $wgTitle, new ParserOptions(), $parsing ? OT_WIKI : OT_MSG );
+
$substWord = MagicWord::get( MAG_SUBST );
$substRegex = '/\{\{(?!(?:' . $substWord->getBaseRegex() . '))/x' . $substWord->getRegexCase();
$substText = '{{' . $substWord->getSynonym( 0 );
$text = preg_replace( $substRegex, $substText, $text );
$text = preg_replace( '/~{3,5}/', '', $text );
$text = $this->replaceVariables( $text );
-
+
+ $this->clearState();
return $text;
}
/**
* Set up some variables which are usually set up in parse()
* so that an external function can call some class members with confidence
- * @access public
+ * @public
*/
function startExternalParse( &$title, $options, $outputType, $clearState = true ) {
$this->mTitle =& $title;
* @param string $text the text to transform
* @param ParserOptions $options options
* @return string the text with variables substituted
- * @access public
+ * @public
*/
function transformMsg( $text, $options ) {
global $wgTitle;
* Transform and return $text. Use $parser for any required context, e.g. use
* $parser->getTitle() and $parser->getOptions() not $wgTitle or $wgOut->mParserOptions
*
- * @access public
+ * @public
*
* @param mixed $tag The tag to use, e.g. 'hook' for <hook>
* @param mixed $callback The callback function (and object) to use for the tag
return $oldVal;
}
+ /**
+ * Create a function, e.g. {{sum:1|2|3}}
+ * The callback function should have the form:
+ * function myParserFunction( &$parser, $arg1, $arg2, $arg3 ) { ... }
+ *
+ * The callback may either return the text result of the function, or an array with the text
+ * in element 0, and a number of flags in the other elements. The names of the flags are
+ * specified in the keys. Valid flags are:
+ * found The text returned is valid, stop processing the template. This
+ * is on by default.
+ * nowiki Wiki markup in the return value should be escaped
+ * noparse Unsafe HTML tags should not be stripped, etc.
+ * noargs Don't replace triple-brace arguments in the return value
+ * isHTML The returned text is HTML, armour it against wikitext transformation
+ *
+ * @public
+ *
+ * @param string $name The function name. Function names are case-insensitive.
+ * @param mixed $callback The callback function (and object) to use
+ *
+ * @return The old callback function for this name, if any
+ */
+ function setFunctionHook( $name, $callback ) {
+ $name = strtolower( $name );
+ $oldVal = @$this->mFunctionHooks[$name];
+ $this->mFunctionHooks[$name] = $callback;
+ return $oldVal;
+ }
+
/**
* Replace <!--LINK--> link placeholders with actual links, in the buffer
* Placeholders created in Skin::makeLinkObj()
* @return string
*/
function replaceLinkHoldersText( $text ) {
- global $wgUser;
- global $wgOutputReplace;
-
$fname = 'Parser::replaceLinkHoldersText';
wfProfileIn( $fname );
/**
* @param array $matches
* @return string
- * @access private
+ * @private
*/
function replaceLinkHoldersTextCallback( $matches ) {
$type = $matches[1];
* Parse image options text and use it to make an image
*/
function makeImage( &$nt, $options ) {
- global $wgContLang, $wgUseImageResize, $wgUser;
+ global $wgUseImageResize;
$align = '';
}
# Strip bad stuff out of the alt text
$alt = $this->replaceLinkHoldersText( $caption );
+
+ # make sure there are no placeholders in thumbnail attributes
+ # that are later expanded to html- so expand them now and
+ # remove the tags
+ $alt = $this->unstrip($alt, $this->mStripState);
$alt = Sanitizer::stripAllTags( $alt );
# Linker does the rest
$this->mOutput->mCacheTime = -1;
}
- /**#@+
+ /**#@+
* Callback from the Sanitizer for expanding items found in HTML attribute
* values, so they can be safely tested and escaped.
* @param string $text
* @param array $args
* @return string
- * @access private
+ * @private
*/
function attributeStripCallback( &$text, $args ) {
$text = $this->replaceVariables( $text, $args );
$mLanguageLinks, # List of the full text of language links, in the order they appear
$mCategories, # Map of category names to sort keys
$mContainsOldMagic, # Boolean variable indicating if the input contained variables like {{CURRENTDAY}}
- $mCacheTime, # Timestamp on this article, or -1 for uncacheable. Used in ParserCache.
+ $mCacheTime, # Time when this object was generated, or -1 for uncacheable. Used in ParserCache.
$mVersion, # Compatibility check
$mTitleText, # title text of the chosen language variant
$mLinks, # 2-D map of NS/DBK to ID for the links in the document. ID=zero for broken.
$mTemplates, # 2-D map of NS/DBK to ID for the template references. ID=zero for broken.
$mImages, # DB keys of the images used, in the array key only
- $mExternalLinks; # External link URLs, in the key only
+ $mExternalLinks, # External link URLs, in the key only
+ $mHTMLtitle, # Display HTML title
+ $mSubtitle, # Additional subtitle
+ $mNewSection; # Show a new section link?
function ParserOutput( $text = '', $languageLinks = array(), $categoryLinks = array(),
$containsOldMagic = false, $titletext = '' )
$this->mTemplates = array();
$this->mImages = array();
$this->mExternalLinks = array();
+ $this->mHTMLtitle = "" ;
+ $this->mSubtitle = "" ;
+ $this->mNewSection = false;
}
function getText() { return $this->mText; }
- function getLanguageLinks() { return $this->mLanguageLinks; }
+ function &getLanguageLinks() { return $this->mLanguageLinks; }
function getCategoryLinks() { return array_keys( $this->mCategories ); }
function &getCategories() { return $this->mCategories; }
function getCacheTime() { return $this->mCacheTime; }
function addImage( $name ) { $this->mImages[$name] = 1; }
function addLanguageLink( $t ) { $this->mLanguageLinks[] = $t; }
function addExternalLink( $url ) { $this->mExternalLinks[$url] = 1; }
+
+ function setNewSection( $value ) {
+ $this->mNewSection = (bool)$value;
+ }
+ function getNewSection() {
+ return (bool)$this->mNewSection;
+ }
function addLink( $title, $id ) {
$ns = $title->getNamespace();
$this->mTemplates[$ns][$dbk] = $id;
}
- /**
- * @deprecated
- */
- /*
- function merge( $other ) {
- $this->mLanguageLinks = array_merge( $this->mLanguageLinks, $other->mLanguageLinks );
- $this->mCategories = array_merge( $this->mCategories, $this->mLanguageLinks );
- $this->mContainsOldMagic = $this->mContainsOldMagic || $other->mContainsOldMagic;
- }*/
-
/**
* Return true if this cached output object predates the global or
* per-article cache invalidation timestamps, or if it comes from
*
* @param string $touched the affected article's last touched timestamp
* @return bool
- * @access public
+ * @public
*/
function expired( $touched ) {
global $wgCacheEpoch;
var $mEditSection; # Create "edit section" links
var $mNumberHeadings; # Automatically number headings
var $mAllowSpecialInclusion; # Allow inclusion of special pages
- var $mTidy; # Ask for tidy cleanup
+ var $mTidy; # Ask for tidy cleanup
+ var $mInterfaceMessage; # Which lang to call for PLURAL and GRAMMAR
function getUseTeX() { return $this->mUseTeX; }
function getUseDynamicDates() { return $this->mUseDynamicDates; }
function getEditSection() { return $this->mEditSection; }
function getNumberHeadings() { return $this->mNumberHeadings; }
function getAllowSpecialInclusion() { return $this->mAllowSpecialInclusion; }
- function getTidy() { return $this->mTidy; }
+ function getTidy() { return $this->mTidy; }
+ function getInterfaceMessage() { return $this->mInterfaceMessage; }
function setUseTeX( $x ) { return wfSetVar( $this->mUseTeX, $x ); }
function setUseDynamicDates( $x ) { return wfSetVar( $this->mUseDynamicDates, $x ); }
function setEditSection( $x ) { return wfSetVar( $this->mEditSection, $x ); }
function setNumberHeadings( $x ) { return wfSetVar( $this->mNumberHeadings, $x ); }
function setAllowSpecialInclusion( $x ) { return wfSetVar( $this->mAllowSpecialInclusion, $x ); }
- function setTidy( $x ) { return wfSetVar( $this->mTidy, $x); }
+ function setTidy( $x ) { return wfSetVar( $this->mTidy, $x); }
function setSkin( &$x ) { $this->mSkin =& $x; }
+ function setInterfaceMessage( $x ) { return wfSetVar( $this->mInterfaceMessage, $x); }
function ParserOptions() {
global $wgUser;
/** Get user options */
function initialiseFromUser( &$userInput ) {
- global $wgUseTeX, $wgUseDynamicDates, $wgInterwikiMagic, $wgAllowExternalImages,
- $wgAllowExternalImagesFrom, $wgAllowSpecialInclusion;
+ global $wgUseTeX, $wgUseDynamicDates, $wgInterwikiMagic, $wgAllowExternalImages;
+ global $wgAllowExternalImagesFrom, $wgAllowSpecialInclusion;
$fname = 'ParserOptions::initialiseFromUser';
wfProfileIn( $fname );
if ( !$userInput ) {
$this->mNumberHeadings = $user->getOption( 'numberheadings' );
$this->mAllowSpecialInclusion = $wgAllowSpecialInclusion;
$this->mTidy = false;
+ $this->mInterfaceMessage = false;
wfProfileOut( $fname );
}
}
* Return the number of files
*/
function wfNumberOfFiles() {
- $fname = 'Parser::wfNumberOfFiles';
+ $fname = 'wfNumberOfFiles';
wfProfileIn( $fname );
$dbr =& wfGetDB( DB_SLAVE );
- $res = $dbr->selectField('image', 'COUNT(*)', array(), $fname );
+ $numImages = $dbr->selectField('site_stats', 'ss_images', array(), $fname );
wfProfileOut( $fname );
- return $res;
+ return $numImages;
+}
+
+/**
+ * Return the number of user accounts
+ * @return integer
+ */
+function wfNumberOfUsers() {
+ wfProfileIn( 'wfNumberOfUsers' );
+ $dbr =& wfGetDB( DB_SLAVE );
+ $count = $dbr->selectField( 'site_stats', 'ss_users', array(), 'wfNumberOfUsers' );
+ wfProfileOut( 'wfNumberOfUsers' );
+ return (int)$count;
}
/**
* Get various statistics from the database
- * @access private
+ * @private
*/
function wfLoadSiteStats() {
global $wgNumberOfArticles, $wgTotalViews, $wgTotalEdits;
* Escape html tags
* Basically replacing " > and < with HTML entities ( ", >, <)
*
- * @param string $in Text that might contain HTML tags
+ * @param $in String: text that might contain HTML tags.
* @return string Escaped string
*/
function wfEscapeHTMLTagsOnly( $in ) {
dépôts / lhc / web / wiklou.git / blobdiff