*sigh* bumpy
found the parse code in the mediawiki distros...
/**
* Replace magic variables, templates, and template arguments
* with the appropriate text. Templates are substituted recursively,
* taking care to avoid infinite loops.
*
* Note that the substitution depends on value of $mOutputType:
* OT_WIKI: only {{subst:}} templates
* OT_MSG: only magic variables
* OT_HTML: all templates and magic variables
*
* @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
* @private
*/
function replaceVariables( $text, $args = array(), $argsOnly = false ) {
# Prevent too big inclusions
if( strlen( $text ) > $this->mOptions->getMaxIncludeSize() ) {
return $text;
}
$fname = __METHOD__ /*. '-L' . count( $this->mArgStack )*/;
wfProfileIn( $fname );
# This function is called recursively. To keep track of arguments we need a stack:
array_push( $this->mArgStack, $args );
$braceCallbacks = array();
if ( !$argsOnly ) {
$braceCallbacks[2] = array( &$this, 'braceSubstitution' );
}
if ( $this->mOutputType != OT_MSG ) {
$braceCallbacks[3] = array( &$this, 'argSubstitution' );
}
if ( $braceCallbacks ) {
$callbacks = array(
'{' => array(
'end' => '}',
'cb' => $braceCallbacks,
'min' => $argsOnly ? 3 : 2,
'max' => isset( $braceCallbacks[3] ) ? 3 : 2,
),
'[' => array(
'end' => ']',
'cb' => array(2=>null),
'min' => 2,
'max' => 2,
)
);
$text = $this->replace_callback ($text, $callbacks);
array_pop( $this->mArgStack );
}
wfProfileOut( $fname );
return $text;
}
/**
* Replace magic variables
* @private
*/
function variableSubstitution( $matches ) {
global $wgContLang;
$fname = 'Parser::variableSubstitution';
$varname = $wgContLang->lc($matches[1]);
wfProfileIn( $fname );
$skip = false;
if ( $this->mOutputType == OT_WIKI ) {
# Do only magic variables prefixed by SUBST
$mwSubst =& MagicWord::get( 'subst' );
if (!$mwSubst->matchStartAndRemove( $varname ))
$skip = true;
# Note that if we don't substitute the variable below,
# we don't remove the {{subst:}} magic word, in case
# it is a template rather than a magic variable.
}
if ( !$skip && array_key_exists( $varname, $this->mVariables ) ) {
$id = $this->mVariables[$varname];
# Now check if we did really match, case sensitive or not
$mw =& MagicWord::get( $id );
if ($mw->match($matches[1])) {
$text = $this->getVariableValue( $id );
$this->mOutput->mContainsOldMagic = true;
} else {
$text = $matches[0];
}
} else {
$text = $matches[0];
}
wfProfileOut( $fname );
return $text;
}
/// Clean up argument array - refactored in 1.9 so parserfunctions can use it, too.
static function createAssocArgs( $args ) {
$assocArgs = array();
$index = 1;
foreach( $args as $arg ) {
$eqpos = strpos( $arg, '=' );
if ( $eqpos === false ) {
$assocArgs[$index++] = $arg;
} else {
$name = trim( substr( $arg, 0, $eqpos ) );
$value = trim( substr( $arg, $eqpos+1 ) );
if ( $value === false ) {
$value = '';
}
if ( $name !== false ) {
$assocArgs[$name] = $value;
}
}
}
return $assocArgs;
}
/**
* Return the text of a template, after recursively
* replacing any variables or templates within the template.
*
* @param array $piece The parts of the template
* $piece['text']: matched text
* $piece['title']: the title, i.e. the part before the |
* $piece['parts']: the parameter array
* @return string the text of the template
* @private
*/
function braceSubstitution( $piece ) {
global $wgContLang, $wgLang, $wgAllowDisplayTitle, $wgNonincludableNamespaces;
$fname = __METHOD__ /*. '-L' . count( $this->mArgStack )*/;
wfProfileIn( $fname );
wfProfileIn( __METHOD__.'-setup' );
# 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.
$noargs = false; # Don't replace triple-brace arguments in $text
$replaceHeadings = false; # Make the edit section links go to the template not the article
$headingOffset = 0; # Skip headings when number, to account for those that weren't transcluded.
$isHTML = false; # $text is HTML, armour it against wikitext transformation
$forceRawInterwiki = false; # Force interwiki transclusion to be done in raw mode not rendered
# Title object, where $text came from
$title = NULL;
$linestart = '';
# $part1 is the bit before the first |, and must contain only title characters
# $args is a list of arguments, starting from index 0, not including $part1
$titleText = $part1 = $piece['title'];
# If the third subpattern matched anything, it will start with |
if (null == $piece['parts']) {
$replaceWith = $this->variableSubstitution (array ($piece['text'], $piece['title']));
if ($replaceWith != $piece['text']) {
$text = $replaceWith;
$found = true;
$noparse = true;
$noargs = true;
}
}
$args = (null == $piece['parts']) ? array() : $piece['parts'];
wfProfileOut( __METHOD__.'-setup' );
# SUBST
wfProfileIn( __METHOD__.'-modifiers' );
if ( !$found ) {
$mwSubst =& MagicWord::get( 'subst' );
if ( $mwSubst->matchStartAndRemove( $part1 ) xor $this->ot['wiki'] ) {
# One of two possibilities is true:
# 1) Found SUBST but not in the PST phase
# 2) Didn't find SUBST and in the PST phase
# In either case, return without further processing
$text = $piece['text'];
$found = true;
$noparse = true;
$noargs = true;
}
}
# MSG, MSGNW and RAW
if ( !$found ) {
# Check for MSGNW:
$mwMsgnw =& MagicWord::get( 'msgnw' );
if ( $mwMsgnw->matchStartAndRemove( $part1 ) ) {
$nowiki = true;
} else {
# Remove obsolete MSG:
$mwMsg =& MagicWord::get( 'msg' );
$mwMsg->matchStartAndRemove( $part1 );
}
# Check for RAW:
$mwRaw =& MagicWord::get( 'raw' );
if ( $mwRaw->matchStartAndRemove( $part1 ) ) {
$forceRawInterwiki = true;
}
}
wfProfileOut( __METHOD__.'-modifiers' );
//save path level before recursing into functions & templates.
$lastPathLevel = $this->mTemplatePath;
# Parser functions
if ( !$found ) {
wfProfileIn( __METHOD__ . '-pfunc' );
$colonPos = strpos( $part1, ':' );
if ( $colonPos !== false ) {
# Case sensitive functions
$function = substr( $part1, 0, $colonPos );
if ( isset( $this->mFunctionSynonyms[1][$function] ) ) {
$function = $this->mFunctionSynonyms[1][$function];
} else {
# Case insensitive functions
$function = strtolower( $function );
if ( isset( $this->mFunctionSynonyms[0][$function] ) ) {
$function = $this->mFunctionSynonyms[0][$function];
} else {
$function = false;
}
}
if ( $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 ) ) {
if ( isset( $result[0] ) ) {
$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 . $result;
}
}
}
wfProfileOut( __METHOD__ . '-pfunc' );
}
# Template table test
# Did we encounter this template already? If yes, it is in the cache
# and we need to check for loops.
if ( !$found && isset( $this->mTemplates[$piece['title']] ) ) {
$found = true;
# Infinite loop test
if ( isset( $this->mTemplatePath[$part1] ) ) {
$noparse = true;
$noargs = true;
$found = true;
$text = $linestart .
"[[$part1]]<!-- WARNING: template loop detected -->";
wfDebug( __METHOD__.": template loop broken at '$part1'\n" );
} else {
# set $text to cached message.
$text = $linestart . $this->mTemplates[$piece['title']];
#treat title for cached page the same as others
$ns = NS_TEMPLATE;
$subpage = '';
$part1 = $this->maybeDoSubpageLink( $part1, $subpage );
if ($subpage !== '') {
$ns = $this->mTitle->getNamespace();
}
$title = Title::newFromText( $part1, $ns );
//used by include size checking
$titleText = $title->getPrefixedText();
//used by edit section links
$replaceHeadings = true;
}
}
# Load from database
if ( !$found ) {
wfProfileIn( __METHOD__ . '-loadtpl' );
$ns = NS_TEMPLATE;
# 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();
}
$title = Title::newFromText( $part1, $ns );
if ( !is_null( $title ) ) {
$titleText = $title->getPrefixedText();
# Check for language variants if the template is not found
if($wgContLang->hasVariants() && $title->getArticleID() == 0){
$wgContLang->findVariantLink($part1, $title);
}
if ( !$title->isExternal() ) {
if ( $title->getNamespace() == NS_SPECIAL && $this->mOptions->getAllowSpecialInclusion() && $this->ot['html'] ) {
$text = SpecialPage::capturePath( $title );
if ( is_string( $text ) ) {
$found = true;
$noparse = true;
$noargs = true;
$isHTML = true;
$this->disableCache();
}
} else if ( $wgNonincludableNamespaces && in_array( $title->getNamespace(), $wgNonincludableNamespaces ) ) {
$found = false; //access denied
wfDebug( "$fname: template inclusion denied for " . $title->getPrefixedDBkey() );
} else {
list($articleContent,$title) = $this->fetchTemplateAndtitle( $title );
if ( $articleContent !== false ) {
$found = true;
$text = $articleContent;
$replaceHeadings = true;
}
}
# If the title is valid but undisplayable, make a link to it
if ( !$found && ( $this->ot['html'] || $this->ot['pre'] ) ) {
$text = "[[:$titleText]]";
$found = true;
}
} elseif ( $title->isTrans() ) {
// Interwiki transclusion
if ( $this->ot['html'] && !$forceRawInterwiki ) {
$text = $this->interwikiTransclude( $title, 'render' );
$isHTML = true;
$noparse = true;
} else {
$text = $this->interwikiTransclude( $title, 'raw' );
$replaceHeadings = true;
}
$found = true;
}
# Template cache array insertion
# Use the original $piece['title'] not the mangled $part1, so that
# modifiers such as RAW: produce separate cache entries
if( $found ) {
if( $isHTML ) {
// A special page; don't store it in the template cache.
} else {
$this->mTemplates[$piece['title']] = $text;
}
$text = $linestart . $text;
}
}
wfProfileOut( __METHOD__ . '-loadtpl' );
}
if ( $found && !$this->incrementIncludeSize( 'pre-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
$text = $linestart .
"[[$titleText]]<!-- WARNING: template omitted, pre-expand include size too large -->";
$noparse = true;
$noargs = true;
}
# Recursive parsing, escaping and link table handling
# Only for HTML output
if ( $nowiki && $found && ( $this->ot['html'] || $this->ot['pre'] ) ) {
$text = wfEscapeWikiText( $text );
} elseif ( !$this->ot['msg'] && $found ) {
if ( $noargs ) {
$assocArgs = array();
} else {
# Clean up argument array
$assocArgs = self::createAssocArgs($args);
# Add a new element to the templace recursion path
$this->mTemplatePath[$part1] = 1;
}
if ( !$noparse ) {
# If there are any <onlyinclude> tags, only include them
if ( in_string( '<onlyinclude>', $text ) && in_string( '</onlyinclude>', $text ) ) {
$replacer = new OnlyIncludeReplacer;
StringUtils::delimiterReplaceCallback( '<onlyinclude>', '</onlyinclude>',
array( &$replacer, 'replace' ), $text );
$text = $replacer->output;
}
# Remove <noinclude> sections and <includeonly> tags
$text = StringUtils::delimiterReplace( '<noinclude>', '</noinclude>', '', $text );
$text = strtr( $text, array( '<includeonly>' => '' , '</includeonly>' => '' ) );
if( $this->ot['html'] || $this->ot['pre'] ) {
# Strip <nowiki>, <pre>, etc.
$text = $this->strip( $text, $this->mStripState );
if ( $this->ot['html'] ) {
$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ), $assocArgs );
} elseif ( $this->ot['pre'] && $this->mOptions->getRemoveComments() ) {
$text = Sanitizer::removeHTMLcomments( $text );
}
}
$text = $this->replaceVariables( $text, $assocArgs );
# If the template begins with a table or block-level
# element, it should be treated as beginning a new line.
if (!$piece['lineStart'] && preg_match('/^(?:{\\||:|;|#|\*)/', $text)) /*}*/{
$text = "\n" . $text;
}
} elseif ( !$noargs ) {
# $noparse and !$noargs
# Just replace the arguments, not any double-brace items
# This is used for rendered interwiki transclusion
$text = $this->replaceVariables( $text, $assocArgs, true );
}
}
# Prune lower levels off the recursion check path
$this->mTemplatePath = $lastPathLevel;
if ( $found && !$this->incrementIncludeSize( 'post-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
$text = $linestart .
"[[$titleText]]<!-- WARNING: template omitted, post-expand include size too large -->";
$noparse = true;
$noargs = true;
}
if ( !$found ) {
wfProfileOut( $fname );
return $piece['text'];
} else {
wfProfileIn( __METHOD__ . '-placeholders' );
if ( $isHTML ) {
# Replace raw HTML by a placeholder
# Add a blank line preceding, to prevent it from mucking up
# immediately preceding headings
$text = "\n\n" . $this->insertStripItem( $text, $this->mStripState );
} else {
# replace ==section headers==
# XXX this needs to go away once we have a better parser.
if ( !$this->ot['wiki'] && !$this->ot['pre'] && $replaceHeadings ) {
if( !is_null( $title ) )
$encodedname = base64_encode($title->getPrefixedDBkey());
else
$encodedname = base64_encode("");
$m = preg_split('/(^={1,6}.*?={1,6}\s*?$)/m', $text, -1,
PREG_SPLIT_DELIM_CAPTURE);
$text = '';
$nsec = $headingOffset;
for( $i = 0; $i < count($m); $i += 2 ) {
$text .= $m[$i];
if (!isset($m[$i + 1]) || $m[$i + 1] == "") continue;
$hl = $m[$i + 1];
if( strstr($hl, "<!--MWTEMPLATESECTION") ) {
$text .= $hl;
continue;
}
$m2 = array();
preg_match('/^(={1,6})(.*?)(={1,6})\s*?$/m', $hl, $m2);
$text .= $m2[1] . $m2[2] . "<!--MWTEMPLATESECTION="
. $encodedname . "&" . base64_encode("$nsec") . "-->" . $m2[3];
$nsec++;
}
}
}
wfProfileOut( __METHOD__ . '-placeholders' );
}
# Prune lower levels off the recursion check path
$this->mTemplatePath = $lastPathLevel;
if ( !$found ) {
wfProfileOut( $fname );
return $piece['text'];
} else {
wfProfileOut( $fname );
return $text;
}
}
/**
* Fetch the unparsed text of a template and register a reference to it.
*/
function fetchTemplateAndtitle( $title ) {
$text = $skip = false;
$finalTitle = $title;
// Loop to fetch the article, with up to 1 redirect
for ( $i = 0; $i < 2 && is_object( $title ); $i++ ) {
# Give extensions a chance to select the revision instead
$id = false; // Assume current
wfRunHooks( 'BeforeParserFetchTemplateAndtitle', array( &$this, &$title, &$skip, &$id ) );
if( $skip ) {
$text = false;
$this->mOutput->addTemplate( $title, $title->getArticleID(), null );
break;
}
$rev = $id ? Revision::newFromId( $id ) : Revision::newFromTitle( $title );
$rev_id = $rev ? $rev->getId() : 0;
$this->mOutput->addTemplate( $title, $title->getArticleID(), $rev_id );
if( $rev ) {
$text = $rev->getText();
} elseif( $title->getNamespace() == NS_MEDIAWIKI ) {
global $wgLang;
$message = $wgLang->lcfirst( $title->getText() );
$text = wfMsgForContentNoTrans( $message );
if( wfEmptyMsg( $message, $text ) ) {
$text = false;
break;
}
} else {
break;
}
if ( $text === false ) {
break;
}
// Redirect?
$finalTitle = $title;
$title = Title::newFromRedirect( $text );
}
return array($text,$finalTitle);
}
function fetchTemplate( $title ) {
$rv = $this->fetchTemplateAndtitle($title);
return $rv[0];
}
/**
* Transclude an interwiki link.
*/
function interwikiTransclude( $title, $action ) {
global $wgEnableScaryTranscluding;
if (!$wgEnableScaryTranscluding)
return wfMsg('scarytranscludedisabled');
$url = $title->getFullUrl( "action=$action" );
if (strlen($url) > 255)
return wfMsg('scarytranscludetoolong');
return $this->fetchScaryTemplateMaybeFromCache($url);
}
function fetchScaryTemplateMaybeFromCache($url) {
global $wgTranscludeCacheExpiry;
$dbr = wfGetDB(DB_SLAVE);
$obj = $dbr->selectRow('transcache', array('tc_time', 'tc_contents'),
array('tc_url' => $url));
if ($obj) {
$time = $obj->tc_time;
$text = $obj->tc_contents;
if ($time && time() < $time + $wgTranscludeCacheExpiry ) {
return $text;
}
}
$text = Http::get($url);
if (!$text)
return wfMsg('scarytranscludefailed', $url);
$dbw = wfGetDB(DB_MASTER);
$dbw->replace('transcache', array('tc_url'), array(
'tc_url' => $url,
'tc_time' => time(),
'tc_contents' => $text));
return $text;
}
/**
* Triple brace replacement -- used for template arguments
* @private
*/
function argSubstitution( $matches ) {
$arg = trim( $matches['title'] );
$text = $matches['text'];
$inputArgs = end( $this->mArgStack );
if ( array_key_exists( $arg, $inputArgs ) ) {
$text = $inputArgs[$arg];
} else if (($this->mOutputType == OT_HTML || $this->mOutputType == OT_PREPROCESS ) &&
null != $matches['parts'] && count($matches['parts']) > 0) {
$text = $matches['parts'][0];
}
if ( !$this->incrementIncludeSize( 'arg', strlen( $text ) ) ) {
$text = $matches['text'] .
'<!-- WARNING: argument omitted, expansion size too large -->';
}
return $text;
}
/**
* Increment an include size counter
*
* @param string $type The type of expansion
* @param integer $size The size of the text
* @return boolean False if this inclusion would take it over the maximum, true otherwise
*/
function incrementIncludeSize( $type, $size ) {
if ( $this->mIncludeSizes[$type] + $size > $this->mOptions->getMaxIncludeSize() ) {
return false;
} else {
$this->mIncludeSizes[$type] += $size;
return true;
}
}
I dunno how to use them to make it into ONE php file and also to convert this to vB stuff, etc...into a create_bbcode plugin or something...