* @subpackage Parser
*/
-/** */
-require_once( 'Sanitizer.php' );
-require_once( 'HttpFunctions.php' );
-
/**
* Update this version number when the ParserOutput format
* changes in an incompatible way, so the parser cache
define( 'OT_WIKI', 2 );
define( 'OT_MSG' , 3 );
+# Flags for setFunctionHook
+define( 'SFH_NO_HASH', 1 );
+
# string parameter for extractTags which will cause it
# to strip HTML comments in addition to regular
# <XML>-style tags. This should not be anything we
define( 'HTTP_PROTOCOLS', 'http:\/\/|https:\/\/' );
# Everything except bracket, space, or control characters
define( 'EXT_LINK_URL_CLASS', '[^][<>"\\x00-\\x20\\x7F]' );
-# Including space
-define( 'EXT_LINK_TEXT_CLASS', '[^\]\\x00-\\x1F\\x7F]' );
+# Including space, but excluding newlines
+define( 'EXT_LINK_TEXT_CLASS', '[^\]\\x0a\\x0d]' );
define( 'EXT_IMAGE_FNAME_CLASS', '[A-Za-z0-9_.,~%\\-+&;#*?!=()@\\x80-\\xFF]' );
define( 'EXT_IMAGE_EXTENSIONS', 'gif|png|jpg|jpeg' );
-define( 'EXT_LINK_BRACKETED', '/\[(\b(' . wfUrlProtocols() . ')'.EXT_LINK_URL_CLASS.'+) *('.EXT_LINK_TEXT_CLASS.'*?)\]/S' );
+define( 'EXT_LINK_BRACKETED', '/\[(\b(' . wfUrlProtocols() . ')'.
+ EXT_LINK_URL_CLASS.'+) *('.EXT_LINK_TEXT_CLASS.'*?)\]/S' );
define( 'EXT_IMAGE_REGEX',
'/^('.HTTP_PROTOCOLS.')'. # Protocol
'('.EXT_LINK_URL_CLASS.'+)\\/'. # Hostname and path
'('.EXT_IMAGE_FNAME_CLASS.'+)\\.((?i)'.EXT_IMAGE_EXTENSIONS.')$/S' # Filename
);
+// State constants for the definition list colon extraction
+define( 'MW_COLON_STATE_TEXT', 0 );
+define( 'MW_COLON_STATE_TAG', 1 );
+define( 'MW_COLON_STATE_TAGSTART', 2 );
+define( 'MW_COLON_STATE_CLOSETAG', 3 );
+define( 'MW_COLON_STATE_TAGSLASH', 4 );
+define( 'MW_COLON_STATE_COMMENT', 5 );
+define( 'MW_COLON_STATE_COMMENTDASH', 6 );
+define( 'MW_COLON_STATE_COMMENTDASHDASH', 7 );
+
/**
* PHP Parser
*
* @private
*/
# Persistent:
- var $mTagHooks, $mFunctionHooks;
+ var $mTagHooks, $mFunctionHooks, $mFunctionSynonyms, $mVariables;
# Cleared with clearState():
var $mOutput, $mAutonumber, $mDTopen, $mStripState = array();
- var $mVariables, $mIncludeCount, $mArgStack, $mLastSection, $mInPre;
+ var $mIncludeCount, $mArgStack, $mLastSection, $mInPre;
var $mInterwikiLinkHolders, $mLinkHolders, $mUniqPrefix;
var $mTemplates, // cache of already loaded templates, avoids
// multiple SQL queries for the same string
function Parser() {
$this->mTagHooks = array();
$this->mFunctionHooks = array();
- $this->clearState();
+ $this->mFunctionSynonyms = array( 0 => array(), 1 => array() );
+ $this->mFirstCall = true;
}
+ /**
+ * Do various kinds of initialisation on the first call of the parser
+ */
+ function firstCallInit() {
+ if ( !$this->mFirstCall ) {
+ return;
+ }
+
+ wfProfileIn( __METHOD__ );
+ global $wgAllowDisplayTitle, $wgAllowSlowParserFunctions;
+
+ $this->setHook( 'pre', array( $this, 'renderPreTag' ) );
+
+ $this->setFunctionHook( 'ns', array( 'CoreParserFunctions', 'ns' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'urlencode', array( 'CoreParserFunctions', 'urlencode' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'lcfirst', array( 'CoreParserFunctions', 'lcfirst' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'ucfirst', array( 'CoreParserFunctions', 'ucfirst' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'lc', array( 'CoreParserFunctions', 'lc' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'uc', array( 'CoreParserFunctions', 'uc' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'localurl', array( 'CoreParserFunctions', 'localurl' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'localurle', array( 'CoreParserFunctions', 'localurle' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'fullurl', array( 'CoreParserFunctions', 'fullurl' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'fullurle', array( 'CoreParserFunctions', 'fullurle' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'formatnum', array( 'CoreParserFunctions', 'formatnum' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'grammar', array( 'CoreParserFunctions', 'grammar' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'plural', array( 'CoreParserFunctions', 'plural' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'numberofpages', array( 'CoreParserFunctions', 'numberofpages' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'numberofusers', array( 'CoreParserFunctions', 'numberofusers' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'numberofarticles', array( 'CoreParserFunctions', 'numberofarticles' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'numberoffiles', array( 'CoreParserFunctions', 'numberoffiles' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'numberofadmins', array( 'CoreParserFunctions', 'numberofadmins' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'language', array( 'CoreParserFunctions', 'language' ), SFH_NO_HASH );
+
+ if ( $wgAllowDisplayTitle ) {
+ $this->setFunctionHook( 'displaytitle', array( 'CoreParserFunctions', 'displaytitle' ), SFH_NO_HASH );
+ }
+ if ( $wgAllowSlowParserFunctions ) {
+ $this->setFunctionHook( 'pagesinnamespace', array( 'CoreParserFunctions', 'pagesinnamespace' ), SFH_NO_HASH );
+ }
+
+ $this->initialiseVariables();
+
+ $this->mFirstCall = false;
+ wfProfileOut( __METHOD__ );
+ }
+
/**
* Clear Parser state
*
* @private
*/
function clearState() {
+ if ( $this->mFirstCall ) {
+ $this->firstCallInit();
+ }
$this->mOutput = new ParserOutput;
$this->mAutonumber = 0;
$this->mLastSection = '';
$this->mDTopen = false;
- $this->mVariables = false;
$this->mIncludeCount = array();
$this->mStripState = array();
$this->mArgStack = array();
$this->mShowToc = true;
$this->mForceTocPosition = false;
-
+
wfRunHooks( 'ParserClearState', array( &$this ) );
}
$this->mOptions = $options;
$this->mTitle =& $title;
- $this->mRevisionId = $revid;
+ $oldRevisionId = $this->mRevisionId;
+ if( $revid !== null ) {
+ $this->mRevisionId = $revid;
+ }
$this->mOutputType = OT_HTML;
//$text = $this->strip( $text, $this->mStripState );
'/(.) (?=\\?|:|;|!|\\302\\273)/' => '\\1 \\2',
# french spaces, Guillemet-right
'/(\\302\\253) /' => '\\1 ',
- '/<center *>(.*)<\\/center *>/i' => '<div class="center">\\1</div>',
);
$text = preg_replace( array_keys($fixtags), array_values($fixtags), $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''] -->
+ $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',
'\\1\\3<div\\5>\\6</div>\\8\\9',
# remove empty italic or bold tag pairs, some
# introduced by rules above
- '/<([bi])><\/\\1>/' => ''
+ '/<([bi])><\/\\1>/' => '',
);
- $text = preg_replace(
+ $text = preg_replace(
array_keys( $tidyregs ),
array_values( $tidyregs ),
$text );
wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
$this->mOutput->setText( $text );
+ $this->mRevisionId = $oldRevisionId;
wfProfileOut( $fname );
return $this->mOutput;
function &getTitle() { return $this->mTitle; }
function getOptions() { return $this->mOptions; }
+ function getFunctionLang() {
+ global $wgLang, $wgContLang;
+ return $this->mOptions->getInterfaceMessage() ? $wgLang : $wgContLang;
+ }
+
/**
- * Replaces all occurrences of <$tag>content</$tag> in the text
- * with a random marker and returns the new text. the output parameter
- * $content will be an associative array filled with data on the form
- * $unique_marker => content.
+ * Replaces all occurrences of HTML-style comments and the given tags
+ * in the text with a random marker and returns teh next text. The output
+ * parameter $matches will be an associative array filled with data in
+ * the form:
+ * 'UNIQ-xxxxx' => array(
+ * 'element',
+ * 'tag content',
+ * array( 'param' => 'x' ),
+ * '<element param="x">tag content</element>' ) )
*
- * If $content is already set, the additional entries will be appended
- * If $tag is set to STRIP_COMMENTS, the function will extract
- * <!-- HTML comments -->
+ * @param $elements list of element names. Comments are always extracted.
+ * @param $text Source text string.
+ * @param $uniq_prefix
*
* @private
* @static
*/
- function extractTagsAndParams($tag, $text, &$content, &$tags, &$params, $uniq_prefix = ''){
- $rnd = $uniq_prefix . '-' . $tag . Parser::getRandomString();
- if ( !$content ) {
- $content = array( );
- }
+ function extractTagsAndParams($elements, $text, &$matches, $uniq_prefix = ''){
+ $rand = Parser::getRandomString();
$n = 1;
$stripped = '';
+ $matches = array();
- if ( !$tags ) {
- $tags = array( );
- }
-
- if ( !$params ) {
- $params = array( );
- }
-
- if( $tag == STRIP_COMMENTS ) {
- $start = '/<!--()/';
- $end = '/-->/';
- } else {
- $start = "/<$tag(\\s+[^>]*|\\s*\/?)>/i";
- $end = "/<\\/$tag\\s*>/i";
- }
+ $taglist = implode( '|', $elements );
+ $start = "/<($taglist)(\\s+[^>]*?|\\s*?)(\/?>)|<(!--)/i";
while ( '' != $text ) {
$p = preg_split( $start, $text, 2, PREG_SPLIT_DELIM_CAPTURE );
$stripped .= $p[0];
- if( count( $p ) < 3 ) {
+ if( count( $p ) < 5 ) {
break;
}
- $attributes = $p[1];
- $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 = '/';
+ if( count( $p ) > 5 ) {
+ // comment
+ $element = $p[4];
+ $attributes = '';
+ $close = '';
+ $inside = $p[5];
} else {
- $empty = '';
+ // tag
+ $element = $p[1];
+ $attributes = $p[2];
+ $close = $p[3];
+ $inside = $p[4];
}
- $marker = $rnd . sprintf('%08X', $n++);
+ $marker = "$uniq_prefix-$element-$rand" . sprintf('%08X', $n++) . '-QINU';
$stripped .= $marker;
- $tags[$marker] = "<$tag$attributes$empty>";
- $params[$marker] = Sanitizer::decodeTagAttributes( $attributes );
-
- if ( $empty === '/' ) {
+ if ( $close === '/>' ) {
// Empty element tag, <tag />
- $content[$marker] = null;
+ $content = null;
$text = $inside;
+ $tail = null;
} else {
- $q = preg_split( $end, $inside, 2 );
- $content[$marker] = $q[0];
- if( count( $q ) < 2 ) {
+ if( $element == '!--' ) {
+ $end = '/(-->)/';
+ } else {
+ $end = "/(<\\/$element\\s*>)/i";
+ }
+ $q = preg_split( $end, $inside, 2, PREG_SPLIT_DELIM_CAPTURE );
+ $content = $q[0];
+ if( count( $q ) < 3 ) {
# No end tag -- let it run out to the end of the text.
- break;
+ $tail = '';
+ $text = '';
} else {
- $text = $q[1];
+ $tail = $q[1];
+ $text = $q[2];
}
}
+
+ $matches[$marker] = array( $element,
+ $content,
+ Sanitizer::decodeTagAttributes( $attributes ),
+ "<$element$attributes$close$content$tail" );
}
return $stripped;
}
- /**
- * Wrapper function for extractTagsAndParams
- * for cases where $tags and $params isn't needed
- * i.e. where tags will never have params, like <nowiki>
- *
- * @private
- * @static
- */
- function extractTags( $tag, $text, &$content, $uniq_prefix = '' ) {
- $dummy_tags = array();
- $dummy_params = array();
-
- return Parser::extractTagsAndParams( $tag, $text, $content,
- $dummy_tags, $dummy_params, $uniq_prefix );
- }
-
/**
* Strips and renders nowiki, pre, math, hiero
* If $render is set, performs necessary rendering operations on plugins
* will be stripped in addition to other tags. This is important
* for section editing, where these comments cause confusion when
* counting the sections in the wikisource
+ *
+ * @param array dontstrip contains tags which should not be stripped;
+ * used to prevent stipping of <gallery> when saving (fixes bug 2700)
*
* @private
*/
- function strip( $text, &$state, $stripcomments = false ) {
+ function strip( $text, &$state, $stripcomments = false , $dontstrip = array () ) {
$render = ($this->mOutputType == OT_HTML);
- $html_content = array();
- $nowiki_content = array();
- $math_content = array();
- $pre_content = array();
- $comment_content = array();
- $ext_content = array();
- $ext_tags = array();
- $ext_params = array();
- $gallery_content = array();
# Replace any instances of the placeholders
$uniq_prefix = $this->mUniqPrefix;
#$text = str_replace( $uniq_prefix, wfHtmlEscapeFirst( $uniq_prefix ), $text );
-
- # html
+ $commentState = array();
+
+ $elements = array_merge(
+ array( 'nowiki', 'gallery' ),
+ array_keys( $this->mTagHooks ) );
global $wgRawHtml;
if( $wgRawHtml ) {
- $text = Parser::extractTags('html', $text, $html_content, $uniq_prefix);
- foreach( $html_content as $marker => $content ) {
- if ($render ) {
- # Raw and unchecked for validity.
- $html_content[$marker] = $content;
- } else {
- $html_content[$marker] = '<html>'.$content.'</html>';
- }
- }
- }
-
- # nowiki
- $text = Parser::extractTags('nowiki', $text, $nowiki_content, $uniq_prefix);
- foreach( $nowiki_content as $marker => $content ) {
- if( $render ){
- $nowiki_content[$marker] = wfEscapeHTMLTagsOnly( $content );
- } else {
- $nowiki_content[$marker] = '<nowiki>'.$content.'</nowiki>';
- }
+ $elements[] = 'html';
}
-
- # math
if( $this->mOptions->getUseTeX() ) {
- $text = Parser::extractTags('math', $text, $math_content, $uniq_prefix);
- foreach( $math_content as $marker => $content ){
- if( $render ) {
- $math_content[$marker] = renderMath( $content );
- } else {
- $math_content[$marker] = '<math>'.$content.'</math>';
- }
- }
+ $elements[] = 'math';
}
-
- # pre
- $text = Parser::extractTags('pre', $text, $pre_content, $uniq_prefix);
- foreach( $pre_content as $marker => $content ){
- if( $render ){
- $pre_content[$marker] = '<pre>' . wfEscapeHTMLTagsOnly( $content ) . '</pre>';
- } else {
- $pre_content[$marker] = '<pre>'.$content.'</pre>';
- }
- }
-
- # gallery
- $text = Parser::extractTags('gallery', $text, $gallery_content, $uniq_prefix);
- foreach( $gallery_content as $marker => $content ) {
- require_once( 'ImageGallery.php' );
- if ( $render ) {
- $gallery_content[$marker] = $this->renderImageGallery( $content );
- } else {
- $gallery_content[$marker] = '<gallery>'.$content.'</gallery>';
- }
- }
-
- # Comments
- $text = Parser::extractTags(STRIP_COMMENTS, $text, $comment_content, $uniq_prefix);
- foreach( $comment_content as $marker => $content ){
- $comment_content[$marker] = '<!--'.$content.'-->';
+
+ # Removing $dontstrip tags from $elements list (currently only 'gallery', fixing bug 2700)
+ foreach ( $elements AS $k => $v ) {
+ if ( !in_array ( $v , $dontstrip ) ) continue;
+ unset ( $elements[$k] );
}
-
- # Extensions
- foreach ( $this->mTagHooks as $tag => $callback ) {
- $ext_content[$tag] = array();
- $text = Parser::extractTagsAndParams( $tag, $text, $ext_content[$tag],
- $ext_tags[$tag], $ext_params[$tag], $uniq_prefix );
- foreach( $ext_content[$tag] as $marker => $content ) {
- $full_tag = $ext_tags[$tag][$marker];
- $params = $ext_params[$tag][$marker];
- if ( $render )
- $ext_content[$tag][$marker] = call_user_func_array( $callback, array( $content, $params, &$this ) );
- else {
- if ( is_null( $content ) ) {
- // Empty element tag
- $ext_content[$tag][$marker] = $full_tag;
+
+ $matches = array();
+ $text = Parser::extractTagsAndParams( $elements, $text, $matches, $uniq_prefix );
+
+ foreach( $matches as $marker => $data ) {
+ list( $element, $content, $params, $tag ) = $data;
+ if( $render ) {
+ $tagName = strtolower( $element );
+ switch( $tagName ) {
+ case '!--':
+ // Comment
+ if( substr( $tag, -3 ) == '-->' ) {
+ $output = $tag;
} else {
- $ext_content[$tag][$marker] = "$full_tag$content</$tag>";
+ // Unclosed comment in input.
+ // Close it so later stripping can remove it
+ $output = "$tag-->";
+ }
+ break;
+ case 'html':
+ if( $wgRawHtml ) {
+ $output = $content;
+ break;
+ }
+ // Shouldn't happen otherwise. :)
+ case 'nowiki':
+ $output = wfEscapeHTMLTagsOnly( $content );
+ break;
+ case 'math':
+ $output = MathRenderer::renderMath( $content );
+ break;
+ case 'gallery':
+ $output = $this->renderImageGallery( $content, $params );
+ break;
+ default:
+ if( isset( $this->mTagHooks[$tagName] ) ) {
+ $output = call_user_func_array( $this->mTagHooks[$tagName],
+ array( $content, $params, $this ) );
+ } else {
+ throw new MWException( "Invalid call hook $element" );
}
}
+ } else {
+ // Just stripping tags; keep the source
+ $output = $tag;
+ }
+ if( !$stripcomments && $element == '!--' ) {
+ $commentState[$marker] = $output;
+ } else {
+ $state[$element][$marker] = $output;
}
}
# not invoke any extension tags / parser hooks contained within
# a comment.)
if ( !$stripcomments ) {
- $tempstate = array( 'comment' => $comment_content );
- $text = $this->unstrip( $text, $tempstate );
- $comment_content = array();
+ // Put them all back and forget them
+ $text = strtr( $text, $commentState );
}
- # Merge state with the pre-existing state, if there is one
- if ( $state ) {
- $state['html'] = $state['html'] + $html_content;
- $state['nowiki'] = $state['nowiki'] + $nowiki_content;
- $state['math'] = $state['math'] + $math_content;
- $state['pre'] = $state['pre'] + $pre_content;
- $state['gallery'] = $state['gallery'] + $gallery_content;
- $state['comment'] = $state['comment'] + $comment_content;
-
- foreach( $ext_content as $tag => $array ) {
- if ( array_key_exists( $tag, $state ) ) {
- $state[$tag] = $state[$tag] + $array;
- }
- }
- } else {
- $state = array(
- 'html' => $html_content,
- 'nowiki' => $nowiki_content,
- 'math' => $math_content,
- 'pre' => $pre_content,
- 'gallery' => $gallery_content,
- 'comment' => $comment_content,
- ) + $ext_content;
- }
return $text;
}
/**
- * restores pre, math, and hiero removed by strip()
+ * Restores pre, math, and other extensions removed by strip()
*
* always call unstripNoWiki() after this one
* @private
return $text;
}
- # Must expand in reverse order, otherwise nested tags will be corrupted
- foreach( array_reverse( $state, true ) as $tag => $contentDict ) {
+ $replacements = array();
+ foreach( $state as $tag => $contentDict ) {
if( $tag != 'nowiki' && $tag != 'html' ) {
- foreach( array_reverse( $contentDict, true ) as $uniq => $content ) {
- $text = str_replace( $uniq, $content, $text );
+ foreach( $contentDict as $uniq => $content ) {
+ $replacements[$uniq] = $content;
}
}
}
+ $text = strtr( $text, $replacements );
return $text;
}
/**
- * always call this after unstrip() to preserve the order
+ * Always call this after unstrip() to preserve the order
*
* @private
*/
return $text;
}
- # Must expand in reverse order, otherwise nested tags will be corrupted
- foreach( array_reverse( $state['nowiki'], true ) as $uniq => $content ) {
- $text = str_replace( $uniq, $content, $text );
- }
-
- global $wgRawHtml;
- if ($wgRawHtml) {
- foreach( array_reverse( $state['html'], true ) as $uniq => $content ) {
- $text = str_replace( $uniq, $content, $text );
+ $replacements = array();
+ foreach( $state as $tag => $contentDict ) {
+ if( $tag == 'nowiki' || $tag == 'html' ) {
+ foreach( $contentDict as $uniq => $content ) {
+ $replacements[$uniq] = $content;
+ }
}
}
+ $text = strtr( $text, $replacements );
return $text;
}
function insertStripItem( $text, &$state ) {
$rnd = $this->mUniqPrefix . '-item' . Parser::getRandomString();
if ( !$state ) {
- $state = array(
- 'html' => array(),
- 'nowiki' => array(),
- 'math' => array(),
- 'pre' => array(),
- 'comment' => array(),
- 'gallery' => array(),
- );
+ $state = array();
}
$state['item'][$rnd] = $text;
return $rnd;
}
$after = substr ( $x , 1 ) ;
if ( $fc == '!' ) $after = str_replace ( '!!' , '||' , $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
$text = strtr( $text, array( '<onlyinclude>' => '' , '</onlyinclude>' => '' ) );
$text = strtr( $text, array( '<noinclude>' => '', '</noinclude>' => '') );
$text = preg_replace( '/<includeonly>.*?<\/includeonly>/s', '', $text );
-
+
$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'attributeStripCallback' ) );
$text = $this->replaceVariables( $text, $args );
$text = preg_replace( '/(^|\n)-----*/', '\\1<hr />', $text );
$text = $this->stripToc( $text );
+ $this->stripNoGallery( $text );
$text = $this->doHeadings( $text );
if($this->mOptions->getUseDynamicDates()) {
$df =& DateFormatter::getInstance();
wfProfileIn( $fname );
for ( $i = 6; $i >= 1; --$i ) {
$h = str_repeat( '=', $i );
- $text = preg_replace( "/^{$h}(.+){$h}(\\s|$)/m",
+ $text = preg_replace( "/^{$h}(.+){$h}\\s*$/m",
"<h{$i}>\\1</h{$i}>\\2", $text );
}
wfProfileOut( $fname );
}
$text = $wgContLang->markNoConversion($text);
-
- # Normalize any HTML entities in input. They will be
- # re-escaped by makeExternalLink().
- $url = Sanitizer::decodeCharReferences( $url );
+
+ $url = Sanitizer::cleanUrl( $url );
# Process the trail (i.e. everything after this link up until start of the next link),
# replacing any non-bracketed links
$url = substr( $url, 0, -$numSepChars );
}
- # Normalize any HTML entities in input. They will be
- # re-escaped by makeExternalLink() or maybeMakeExternalImage()
- $url = Sanitizer::decodeCharReferences( $url );
+ $url = Sanitizer::cleanUrl( $url );
# Is this an external image?
$text = $this->maybeMakeExternalImage( $url );
* the URL differently; as a workaround, just use the output for
* statistical records, not for actual linking/output.
*/
- function replaceUnusualEscapes( $url ) {
+ static function replaceUnusualEscapes( $url ) {
return preg_replace_callback( '/%[0-9A-Fa-f]{2}/',
array( 'Parser', 'replaceUnusualEscapesCallback' ), $url );
}
* @static
* @private
*/
- function replaceUnusualEscapesCallback( $matches ) {
+ private static function replaceUnusualEscapesCallback( $matches ) {
$char = urldecode( $matches[0] );
$ord = ord( $char );
// Is it an unsafe or HTTP reserved character according to RFC 1738?
$useLinkPrefixExtension = $wgContLang->linkPrefixExtension();
if( is_null( $this->mTitle ) ) {
- wfDebugDieBacktrace( 'nooo' );
+ throw new MWException( 'nooo' );
}
$nottalk = !$this->mTitle->isTalkPage();
$m[3] = $n[1];
}
# fix up urlencoded title texts
- if(preg_match('/%/', $m[1] ))
+ if(preg_match('/%/', $m[1] ))
# Should anchors '#' also be rejected?
$m[1] = str_replace( array('<', '>'), array('<', '>'), urldecode($m[1]) );
$trail = $m[3];
wfProfileOut( "$fname-image" );
continue;
+ } else {
+ # We still need to record the image's presence on the page
+ $this->mOutput->addImage( $nt->getDBkey() );
}
wfProfileOut( "$fname-image" );
$sortkey = $text;
}
$sortkey = Sanitizer::decodeCharReferences( $sortkey );
+ $sortkey = str_replace( "\n", '', $sortkey );
$sortkey = $wgContLang->convertCategoryKey( $sortkey );
$this->mOutput->addCategory( $nt->getDBkey(), $sortkey );
$s .= $this->makeKnownLinkHolder( $nt, $text, '', $trail, $prefix );
continue;
} elseif( $ns == NS_IMAGE ) {
- $img = Image::newFromTitle( $nt );
+ $img = new Image( $nt );
if( $img->exists() ) {
// Force a blue link if the file exists; may be a remote
// upload on the shared repository, and we want to see its
wfProfileIn( "$fname-paragraph" );
# No prefix (not in list)--go to paragraph mode
// XXX: use a stack for nestable elements like span, table and div
- $openmatch = preg_match('/(<table|<blockquote|<h1|<h2|<h3|<h4|<h5|<h6|<pre|<tr|<p|<ul|<li|<\\/tr|<\\/td|<\\/th)/iS', $t );
+ $openmatch = preg_match('/(<table|<blockquote|<h1|<h2|<h3|<h4|<h5|<h6|<pre|<tr|<p|<ul|<ol|<li|<\\/center|<\\/tr|<\\/td|<\\/th)/iS', $t );
$closematch = preg_match(
'/(<\\/table|<\\/blockquote|<\\/h1|<\\/h2|<\\/h3|<\\/h4|<\\/h5|<\\/h6|'.
- '<td|<th|<div|<\\/div|<hr|<\\/pre|<\\/p|'.$this->mUniqPrefix.'-pre|<\\/li|<\\/ul)/iS', $t );
+ '<td|<th|<div|<\\/div|<hr|<\\/pre|<\\/p|'.$this->mUniqPrefix.'-pre|<\\/li|<\\/ul|<\\/ol|<center)/iS', $t );
if ( $openmatch or $closematch ) {
$paragraphStack = false;
#Â TODO bug 5718: paragraph closed
}
/**
- * Split up a string on ':', ignoring any occurences inside
- * <a>..</a> or <span>...</span>
+ * Split up a string on ':', ignoring any occurences inside tags
+ * to prevent illegal overlapping.
* @param string $str the string to split
* @param string &$before set to everything before the ':'
* @param string &$after set to everything after the ':'
* return string the position of the ':', or false if none found
*/
function findColonNoLinks($str, &$before, &$after) {
- # I wonder if we should make this count all tags, not just <a>
- # and <span>. That would prevent us from matching a ':' that
- # comes in the middle of italics other such formatting....
- # -- Wil
$fname = 'Parser::findColonNoLinks';
wfProfileIn( $fname );
- $pos = 0;
- do {
- $colon = strpos($str, ':', $pos);
-
- if ($colon !== false) {
- $before = substr($str, 0, $colon);
- $after = substr($str, $colon + 1);
-
- # Skip any ':' within <a> or <span> pairs
- $a = substr_count($before, '<a');
- $s = substr_count($before, '<span');
- $ca = substr_count($before, '</a>');
- $cs = substr_count($before, '</span>');
-
- if ($a <= $ca and $s <= $cs) {
- # Tags are balanced before ':'; ok
+
+ $pos = strpos( $str, ':' );
+ if( $pos === false ) {
+ // Nothing to find!
+ wfProfileOut( $fname );
+ return false;
+ }
+
+ $lt = strpos( $str, '<' );
+ if( $lt === false || $lt > $pos ) {
+ // Easy; no tag nesting to worry about
+ $before = substr( $str, 0, $pos );
+ $after = substr( $str, $pos+1 );
+ wfProfileOut( $fname );
+ return $pos;
+ }
+
+ // Ugly state machine to walk through avoiding tags.
+ $state = MW_COLON_STATE_TEXT;
+ $stack = 0;
+ $len = strlen( $str );
+ for( $i = 0; $i < $len; $i++ ) {
+ $c = $str{$i};
+
+ switch( $state ) {
+ // (Using the number is a performance hack for common cases)
+ case 0: // MW_COLON_STATE_TEXT:
+ switch( $c ) {
+ case "<":
+ // Could be either a <start> tag or an </end> tag
+ $state = MW_COLON_STATE_TAGSTART;
+ break;
+ case ":":
+ if( $stack == 0 ) {
+ // We found it!
+ $before = substr( $str, 0, $i );
+ $after = substr( $str, $i + 1 );
+ wfProfileOut( $fname );
+ return $i;
+ }
+ // Embedded in a tag; don't break it.
+ break;
+ default:
+ // Skip ahead looking for something interesting
+ $colon = strpos( $str, ':', $i );
+ if( $colon === false ) {
+ // Nothing else interesting
+ wfProfileOut( $fname );
+ return false;
+ }
+ $lt = strpos( $str, '<', $i );
+ if( $stack === 0 ) {
+ if( $lt === false || $colon < $lt ) {
+ // We found it!
+ $before = substr( $str, 0, $colon );
+ $after = substr( $str, $colon + 1 );
+ wfProfileOut( $fname );
+ return $i;
+ }
+ }
+ if( $lt === false ) {
+ // Nothing else interesting to find; abort!
+ // We're nested, but there's no close tags left. Abort!
+ break 2;
+ }
+ // Skip ahead to next tag start
+ $i = $lt;
+ $state = MW_COLON_STATE_TAGSTART;
+ }
+ break;
+ case 1: // MW_COLON_STATE_TAG:
+ // In a <tag>
+ switch( $c ) {
+ case ">":
+ $stack++;
+ $state = MW_COLON_STATE_TEXT;
+ break;
+ case "/":
+ // Slash may be followed by >?
+ $state = MW_COLON_STATE_TAGSLASH;
+ break;
+ default:
+ // ignore
+ }
+ break;
+ case 2: // MW_COLON_STATE_TAGSTART:
+ switch( $c ) {
+ case "/":
+ $state = MW_COLON_STATE_CLOSETAG;
+ break;
+ case "!":
+ $state = MW_COLON_STATE_COMMENT;
break;
+ case ">":
+ // Illegal early close? This shouldn't happen D:
+ $state = MW_COLON_STATE_TEXT;
+ break;
+ default:
+ $state = MW_COLON_STATE_TAG;
+ }
+ break;
+ case 3: // MW_COLON_STATE_CLOSETAG:
+ // In a </tag>
+ if( $c == ">" ) {
+ $stack--;
+ if( $stack < 0 ) {
+ wfDebug( "Invalid input in $fname; too many close tags\n" );
+ wfProfileOut( $fname );
+ return false;
+ }
+ $state = MW_COLON_STATE_TEXT;
+ }
+ break;
+ case MW_COLON_STATE_TAGSLASH:
+ if( $c == ">" ) {
+ // Yes, a self-closed tag <blah/>
+ $state = MW_COLON_STATE_TEXT;
+ } else {
+ // Probably we're jumping the gun, and this is an attribute
+ $state = MW_COLON_STATE_TAG;
+ }
+ break;
+ case 5: // MW_COLON_STATE_COMMENT:
+ if( $c == "-" ) {
+ $state = MW_COLON_STATE_COMMENTDASH;
+ }
+ break;
+ case MW_COLON_STATE_COMMENTDASH:
+ if( $c == "-" ) {
+ $state = MW_COLON_STATE_COMMENTDASHDASH;
+ } else {
+ $state = MW_COLON_STATE_COMMENT;
+ }
+ break;
+ case MW_COLON_STATE_COMMENTDASHDASH:
+ if( $c == ">" ) {
+ $state = MW_COLON_STATE_TEXT;
+ } else {
+ $state = MW_COLON_STATE_COMMENT;
}
- $pos = $colon + 1;
+ break;
+ default:
+ throw new MWException( "State machine error in $fname" );
}
- } while ($colon !== false);
+ }
+ if( $stack > 0 ) {
+ wfDebug( "Invalid input in $fname; not enough close tags (stack $stack, state $state)\n" );
+ return false;
+ }
wfProfileOut( $fname );
- return $colon;
+ return false;
}
/**
wfRunHooks( 'ParserGetVariableValueTs', array( &$this, &$ts ) );
switch ( $index ) {
- case MAG_CURRENTMONTH:
+ case 'currentmonth':
return $varCache[$index] = $wgContLang->formatNum( date( 'm', $ts ) );
- case MAG_CURRENTMONTHNAME:
+ case 'currentmonthname':
return $varCache[$index] = $wgContLang->getMonthName( date( 'n', $ts ) );
- case MAG_CURRENTMONTHNAMEGEN:
+ case 'currentmonthnamegen':
return $varCache[$index] = $wgContLang->getMonthNameGen( date( 'n', $ts ) );
- case MAG_CURRENTMONTHABBREV:
+ case 'currentmonthabbrev':
return $varCache[$index] = $wgContLang->getMonthAbbreviation( date( 'n', $ts ) );
- case MAG_CURRENTDAY:
+ case 'currentday':
return $varCache[$index] = $wgContLang->formatNum( date( 'j', $ts ) );
- case MAG_CURRENTDAY2:
+ case 'currentday2':
return $varCache[$index] = $wgContLang->formatNum( date( 'd', $ts ) );
- case MAG_PAGENAME:
+ case 'pagename':
return $this->mTitle->getText();
- case MAG_PAGENAMEE:
+ case 'pagenamee':
return $this->mTitle->getPartialURL();
- case MAG_FULLPAGENAME:
+ case 'fullpagename':
return $this->mTitle->getPrefixedText();
- case MAG_FULLPAGENAMEE:
+ case 'fullpagenamee':
return $this->mTitle->getPrefixedURL();
- case MAG_SUBPAGENAME:
+ case 'subpagename':
return $this->mTitle->getSubpageText();
- case MAG_SUBPAGENAMEE:
+ case 'subpagenamee':
return $this->mTitle->getSubpageUrlForm();
- case MAG_BASEPAGENAME:
+ case 'basepagename':
return $this->mTitle->getBaseText();
- case MAG_BASEPAGENAMEE:
+ case 'basepagenamee':
return wfUrlEncode( str_replace( ' ', '_', $this->mTitle->getBaseText() ) );
- case MAG_TALKPAGENAME:
+ case 'talkpagename':
if( $this->mTitle->canTalk() ) {
$talkPage = $this->mTitle->getTalkPage();
return $talkPage->getPrefixedText();
} else {
return '';
}
- case MAG_TALKPAGENAMEE:
+ case 'talkpagenamee':
if( $this->mTitle->canTalk() ) {
$talkPage = $this->mTitle->getTalkPage();
return $talkPage->getPrefixedUrl();
} else {
return '';
}
- case MAG_SUBJECTPAGENAME:
+ case 'subjectpagename':
$subjPage = $this->mTitle->getSubjectPage();
return $subjPage->getPrefixedText();
- case MAG_SUBJECTPAGENAMEE:
+ case 'subjectpagenamee':
$subjPage = $this->mTitle->getSubjectPage();
return $subjPage->getPrefixedUrl();
- case MAG_REVISIONID:
+ case 'revisionid':
return $this->mRevisionId;
- case MAG_NAMESPACE:
+ case 'namespace':
return str_replace('_',' ',$wgContLang->getNsText( $this->mTitle->getNamespace() ) );
- case MAG_NAMESPACEE:
+ case 'namespacee':
return wfUrlencode( $wgContLang->getNsText( $this->mTitle->getNamespace() ) );
- case MAG_TALKSPACE:
+ case 'talkspace':
return $this->mTitle->canTalk() ? str_replace('_',' ',$this->mTitle->getTalkNsText()) : '';
- case MAG_TALKSPACEE:
+ case 'talkspacee':
return $this->mTitle->canTalk() ? wfUrlencode( $this->mTitle->getTalkNsText() ) : '';
- case MAG_SUBJECTSPACE:
+ case 'subjectspace':
return $this->mTitle->getSubjectNsText();
- case MAG_SUBJECTSPACEE:
+ case 'subjectspacee':
return( wfUrlencode( $this->mTitle->getSubjectNsText() ) );
- case MAG_CURRENTDAYNAME:
+ case 'currentdayname':
return $varCache[$index] = $wgContLang->getWeekdayName( date( 'w', $ts ) + 1 );
- case MAG_CURRENTYEAR:
+ case 'currentyear':
return $varCache[$index] = $wgContLang->formatNum( date( 'Y', $ts ), true );
- case MAG_CURRENTTIME:
+ case 'currenttime':
return $varCache[$index] = $wgContLang->time( wfTimestamp( TS_MW, $ts ), false, false );
- case MAG_CURRENTWEEK:
+ case 'currentweek':
// @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
// int to remove the padding
return $varCache[$index] = $wgContLang->formatNum( (int)date( 'W', $ts ) );
- case MAG_CURRENTDOW:
+ case 'currentdow':
return $varCache[$index] = $wgContLang->formatNum( date( 'w', $ts ) );
- case MAG_NUMBEROFARTICLES:
+ case 'numberofarticles':
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfArticles() );
- case MAG_NUMBEROFFILES:
+ case 'numberoffiles':
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfFiles() );
- case MAG_NUMBEROFUSERS:
+ case 'numberofusers':
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfUsers() );
- case MAG_NUMBEROFPAGES:
+ case 'numberofpages':
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfPages() );
- case MAG_CURRENTTIMESTAMP:
+ case 'numberofadmins':
+ return $varCache[$index] = $wgContLang->formatNum( wfNumberOfAdmins() );
+ case 'currenttimestamp':
return $varCache[$index] = wfTimestampNow();
- case MAG_CURRENTVERSION:
+ case 'currentversion':
global $wgVersion;
return $wgVersion;
- case MAG_SITENAME:
+ case 'sitename':
return $wgSitename;
- case MAG_SERVER:
+ case 'server':
return $wgServer;
- case MAG_SERVERNAME:
+ case 'servername':
return $wgServerName;
- case MAG_SCRIPTPATH:
+ case 'scriptpath':
return $wgScriptPath;
- case MAG_DIRECTIONMARK:
+ case 'directionmark':
return $wgContLang->getDirMark();
+ case 'contentlanguage':
+ global $wgContLanguageCode;
+ return $wgContLanguageCode;
default:
$ret = null;
if ( wfRunHooks( 'ParserGetVariableValueSwitch', array( &$this, &$varCache, &$index, &$ret ) ) )
function initialiseVariables() {
$fname = 'Parser::initialiseVariables';
wfProfileIn( $fname );
- global $wgVariableIDs;
+ $variableIDs = MagicWord::getVariableIDs();
+
$this->mVariables = array();
- foreach ( $wgVariableIDs as $id ) {
+ foreach ( $variableIDs as $id ) {
$mw =& MagicWord::get( $id );
$mw->addToArray( $this->mVariables, $id );
}
* @private
*/
function replace_callback ($text, $callbacks) {
+ wfProfileIn( __METHOD__ . '-self' );
$openingBraceStack = array(); # this array will hold a stack of parentheses which are not closed yet
$lastOpeningBrace = -1; # last not closed parentheses
'text' => substr($text, $pieceStart, $pieceEnd - $pieceStart),
'title' => trim($openingBraceStack[$lastOpeningBrace]['title']),
'parts' => $openingBraceStack[$lastOpeningBrace]['parts'],
- 'lineStart' => (($pieceStart > 0) && ($text[$pieceStart-1] == '\n')),
+ 'lineStart' => (($pieceStart > 0) && ($text[$pieceStart-1] == "\n")),
);
# finally we can call a user callback and replace piece of text
+ wfProfileOut( __METHOD__ . '-self' );
$replaceWith = call_user_func( $matchingCallback, $cbArgs );
+ wfProfileIn( __METHOD__ . '-self' );
$text = substr($text, 0, $pieceStart) . $replaceWith . substr($text, $pieceEnd);
$i = $pieceStart + strlen($replaceWith) - 1;
}
}
}
+ wfProfileOut( __METHOD__ . '-self' );
return $text;
}
wfProfileOut( $fname );
return $text;
}
-
+
/**
* Replace magic variables
* @private
$fname = 'Parser::variableSubstitution';
$varname = $matches[1];
wfProfileIn( $fname );
- if ( !$this->mVariables ) {
- $this->initialiseVariables();
- }
$skip = false;
if ( $this->mOutputType == OT_WIKI ) {
# Do only magic variables prefixed by SUBST
- $mwSubst =& MagicWord::get( MAG_SUBST );
+ $mwSubst =& MagicWord::get( 'subst' );
if (!$mwSubst->matchStartAndRemove( $varname ))
$skip = true;
# Note that if we don't substitute the variable below,
# SUBST
if ( !$found ) {
- $mwSubst =& MagicWord::get( MAG_SUBST );
+ $mwSubst =& MagicWord::get( 'subst' );
if ( $mwSubst->matchStartAndRemove( $part1 ) xor ($this->mOutputType == OT_WIKI) ) {
# One of two possibilities is true:
# 1) Found SUBST but not in the PST phase
# MSG, MSGNW, INT and RAW
if ( !$found ) {
# Check for MSGNW:
- $mwMsgnw =& MagicWord::get( MAG_MSGNW );
+ $mwMsgnw =& MagicWord::get( 'msgnw' );
if ( $mwMsgnw->matchStartAndRemove( $part1 ) ) {
$nowiki = true;
} else {
# Remove obsolete MSG:
- $mwMsg =& MagicWord::get( MAG_MSG );
+ $mwMsg =& MagicWord::get( 'msg' );
$mwMsg->matchStartAndRemove( $part1 );
}
# Check for RAW:
- $mwRaw =& MagicWord::get( MAG_RAW );
+ $mwRaw =& MagicWord::get( 'raw' );
if ( $mwRaw->matchStartAndRemove( $part1 ) ) {
$forceRawInterwiki = true;
}
# Check if it is an internal message
- $mwInt =& MagicWord::get( MAG_INT );
+ $mwInt =& MagicWord::get( 'int' );
if ( $mwInt->matchStartAndRemove( $part1 ) ) {
if ( $this->incrementIncludeCount( 'int:'.$part1 ) ) {
$text = $linestart . wfMsgReal( $part1, $args, true );
}
}
- # NS
+ # Parser functions
if ( !$found ) {
- # Check for NS: (namespace expansion)
- $mwNs = MagicWord::get( MAG_NS );
- if ( $mwNs->matchStartAndRemove( $part1 ) ) {
- if ( intval( $part1 ) || $part1 == "0" ) {
- $text = $linestart . $wgContLang->getNsText( intval( $part1 ) );
- $found = true;
+ 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 {
- $index = Namespace::getCanonicalIndex( strtolower( $part1 ) );
- if ( !is_null( $index ) ) {
- $text = $linestart . $wgContLang->getNsText( $index );
- $found = true;
- }
- }
- }
- }
-
- # URLENCODE
- if( !$found ) {
- $urlencode =& MagicWord::get( MAG_URLENCODE );
- if( $urlencode->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . urlencode( $part1 );
- $found = true;
- }
- }
-
- # LCFIRST, UCFIRST, LC and UC
- if ( !$found ) {
- $lcfirst =& MagicWord::get( MAG_LCFIRST );
- $ucfirst =& MagicWord::get( MAG_UCFIRST );
- $lc =& MagicWord::get( MAG_LC );
- $uc =& MagicWord::get( MAG_UC );
- if ( $lcfirst->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $wgContLang->lcfirst( $part1 );
- $found = true;
- } else if ( $ucfirst->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $wgContLang->ucfirst( $part1 );
- $found = true;
- } else if ( $lc->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $wgContLang->lc( $part1 );
- $found = true;
- } else if ( $uc->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $wgContLang->uc( $part1 );
- $found = true;
- }
- }
-
- # LOCALURL and FULLURL
- if ( !$found ) {
- $mwLocal =& MagicWord::get( MAG_LOCALURL );
- $mwLocalE =& MagicWord::get( MAG_LOCALURLE );
- $mwFull =& MagicWord::get( MAG_FULLURL );
- $mwFullE =& MagicWord::get( MAG_FULLURLE );
-
-
- if ( $mwLocal->matchStartAndRemove( $part1 ) ) {
- $func = 'getLocalURL';
- } elseif ( $mwLocalE->matchStartAndRemove( $part1 ) ) {
- $func = 'escapeLocalURL';
- } elseif ( $mwFull->matchStartAndRemove( $part1 ) ) {
- $func = 'getFullURL';
- } elseif ( $mwFullE->matchStartAndRemove( $part1 ) ) {
- $func = 'escapeFullURL';
- } else {
- $func = false;
- }
-
- if ( $func !== false ) {
- $title = Title::newFromText( $part1 );
- # Due to order of execution of a lot of bits, the values might be encoded
- # before arriving here; if that's true, then the title can't be created
- # and the variable will fail. If we can't get a decent title from the first
- # attempt, url-decode and try for a second.
- if( is_null( $title ) )
- $title = Title::newFromUrl( urldecode( $part1 ) );
- if ( !is_null( $title ) ) {
- if ( $argc > 0 ) {
- $text = $linestart . $title->$func( $args[0] );
+ # Case insensitive functions
+ $function = strtolower( $function );
+ if ( isset( $this->mFunctionSynonyms[0][$function] ) ) {
+ $function = $this->mFunctionSynonyms[0][$function];
} else {
- $text = $linestart . $title->$func();
+ $function = false;
}
- $found = true;
}
- }
- }
-
- $lang = $this->mOptions->getInterfaceMessage() ? $wgLang : $wgContLang;
- # GRAMMAR
- if ( !$found && $argc == 1 ) {
- $mwGrammar =& MagicWord::get( MAG_GRAMMAR );
- if ( $mwGrammar->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . $lang->convertGrammar( $args[0], $part1 );
- $found = true;
- }
- }
-
- # PLURAL
- if ( !$found && $argc >= 2 ) {
- $mwPluralForm =& MagicWord::get( MAG_PLURAL );
- if ( $mwPluralForm->matchStartAndRemove( $part1 ) ) {
- if ($argc==2) {$args[2]=$args[1];}
- $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 = "" ;
- $found = true ;
- }
- }
-
- # NUMBEROFPAGES, NUMBEROFUSERS, NUMBEROFARTICLES, and NUMBEROFFILES
- if( !$found ) {
- $mwWordsToCheck = array( MAG_NUMBEROFPAGES => 'wfNumberOfPages',
- 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 ) );
- }
- $found = true;
- }
- }
- }
-
- # Extensions
- if ( !$found && substr( $part1, 0, 1 ) == '#' ) {
- $colonPos = strpos( $part1, ':' );
- if ( $colonPos !== false ) {
- $function = strtolower( substr( $part1, 1, $colonPos - 1 ) );
- if ( isset( $this->mFunctionHooks[$function] ) ) {
+ 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], $funcArgs );
// The text is usually already parsed, doesn't need triple-brace tags expanded, etc.
//$noargs = true;
//$noparse = true;
-
+
if ( is_array( $result ) ) {
- $text = $linestart . $result[0];
- unset( $result[0] );
+ 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.
}
}
}
+ wfProfileOut( __METHOD__ . '-pfunc' );
}
# Template table test
# Load from database
$lastPathLevel = $this->mTemplatePath;
if ( !$found ) {
+ wfProfileIn( __METHOD__ . '-loadtpl' );
$ns = NS_TEMPLATE;
# declaring $subpage directly in the function call
# does not work correctly with references and breaks
}
$title = Title::newFromText( $part1, $ns );
+
if ( !is_null( $title ) ) {
+ $checkVariantLink = sizeof($wgContLang->getVariants())>1;
+ # Check for language variants if the template is not found
+ if($checkVariantLink && $title->getArticleID() == 0){
+ $wgContLang->findVariantLink($part1, $title);
+ }
+
if ( !$title->isExternal() ) {
# Check for excessive inclusion
$dbk = $title->getPrefixedDBkey();
}
$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 ) {
- $this->mTemplates[$piece['title']] = $text;
+ 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' );
}
# Recursive parsing, escaping and link table handling
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
}
}
}
+ wfProfileOut( __METHOD__ . '-placeholders' );
}
# Prune lower levels off the recursion check path
}
}
- $text = wfGetHTTP($url);
+ $text = Http::get($url);
if (!$text)
return wfMsg('scarytranscludefailed', $url);
}
}
+ /**
+ * Detect __NOGALLERY__ magic word and set a placeholder
+ */
+ function stripNoGallery( &$text ) {
+ # if the string __NOGALLERY__ (not case-sensitive) occurs in the HTML,
+ # do not add TOC
+ $mw = MagicWord::get( 'nogallery' );
+ $this->mOutput->mNoGallery = $mw->matchAndRemove( $text ) ;
+ }
+
/**
* Detect __TOC__ magic word and set a placeholder
*/
function stripToc( $text ) {
# if the string __NOTOC__ (not case-sensitive) occurs in the HTML,
# do not add TOC
- $mw = MagicWord::get( MAG_NOTOC );
+ $mw = MagicWord::get( 'notoc' );
if( $mw->matchAndRemove( $text ) ) {
$this->mShowToc = false;
}
-
- $mw = MagicWord::get( MAG_TOC );
+
+ $mw = MagicWord::get( 'toc' );
if( $mw->match( $text ) ) {
$this->mShowToc = true;
$this->mForceTocPosition = true;
-
+
// Set a placeholder. At the end we'll fill it in with the TOC.
$text = $mw->replace( '<!--MWTOC-->', $text, 1 );
-
+
// Only keep the first one.
$text = $mw->replace( '', $text );
}
}
# Inhibit editsection links if requested in the page
- $esw =& MagicWord::get( MAG_NOEDITSECTION );
+ $esw =& MagicWord::get( 'noeditsection' );
if( $esw->matchAndRemove( $text ) ) {
$showEditLink = 0;
}
# Allow user to stipulate that a page should have a "new section"
# link added via __NEWSECTIONLINK__
- $mw =& MagicWord::get( MAG_NEWSECTIONLINK );
+ $mw =& MagicWord::get( 'newsectionlink' );
if( $mw->matchAndRemove( $text ) )
$this->mOutput->setNewSection( true );
# if the string __FORCETOC__ (not case-sensitive) occurs in the HTML,
# override above conditions and always show TOC above first header
- $mw =& MagicWord::get( MAG_FORCETOC );
+ $mw =& MagicWord::get( 'forcetoc' );
if ($mw->matchAndRemove( $text ) ) {
$this->mShowToc = true;
$enoughToc = true;
}
$isbn = $blank = '' ;
- while ( ' ' == $x{0} ) {
+ while ( $x !== '' && ' ' == $x{0} ) {
$blank .= ' ';
$x = substr( $x, 1 );
}
$text .= $keyword . $x;
continue;
}
-
+
$id = $blank = '' ;
/** remove and save whitespaces in $blank */
$url = wfMsg( $urlmsg, $id);
$sk =& $this->mOptions->getSkin();
$la = $sk->getExternalLinkAttributes( $url, $keyword.$id );
- $text .= "<a href='{$url}'{$la}>{$keyword}{$id}</a>{$x}";
+ $text .= "<a href=\"{$url}\"{$la}>{$keyword}{$id}</a>{$x}";
}
/* Check if the next RFC keyword is preceed by [[ */
"\r\n" => "\n",
);
$text = str_replace( array_keys( $pairs ), array_values( $pairs ), $text );
- $text = $this->strip( $text, $stripState, true );
+ $text = $this->strip( $text, $stripState, true, array( 'gallery' ) );
$text = $this->pstPass2( $text, $stripState, $user );
$text = $this->unstrip( $text, $stripState );
$text = $this->unstripNoWiki( $text, $stripState );
# Variable replacement
# 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 );
-
+ $text = $this->strip( $text, $stripState, false, array( 'gallery' ) );
+
# Signatures
$sigText = $this->getUserSig( $user );
$text = strtr( $text, array(
}
# Trim trailing whitespace
- # MAG_END (__END__) tag allows for trailing
+ # __END__ tag allows for trailing
# whitespace to be deliberately included
$text = rtrim( $text );
- $mw =& MagicWord::get( MAG_END );
+ $mw =& MagicWord::get( 'end' );
$mw->matchAndRemove( $text );
return $text;
$username = $user->getName();
$nickname = $user->getOption( 'nickname' );
$nickname = $nickname === '' ? $username : $nickname;
-
+
if( $user->getBoolOption( 'fancysig' ) !== false ) {
# Sig. might contain markup; validate this
if( $this->validateSig( $nickname ) !== false ) {
}
}
+ // Make sure nickname doesnt get a sig in a sig
+ $nickname = $this->cleanSigInSig( $nickname );
+
# If we're still here, make it a link to the user page
$userpage = $user->getUserPage();
return( '[[' . $userpage->getPrefixedText() . '|' . wfEscapeWikiText( $nickname ) . ']]' );
function validateSig( $text ) {
return( wfIsWellFormedXmlFragment( $text ) ? $text : false );
}
-
+
/**
* Clean up signature text
*
- * 1) Strip ~~~, ~~~~ and ~~~~~ out of signatures
+ * 1) Strip ~~~, ~~~~ and ~~~~~ out of signatures @see cleanSigInSig
* 2) Substitute all transclusions
*
* @param string $text
function cleanSig( $text, $parsing = false ) {
global $wgTitle;
$this->startExternalParse( $wgTitle, new ParserOptions(), $parsing ? OT_WIKI : OT_MSG );
-
- $substWord = MagicWord::get( MAG_SUBST );
+
+ $substWord = MagicWord::get( '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->cleanSigInSig( $text );
$text = $this->replaceVariables( $text );
-
- $this->clearState();
+
+ $this->clearState();
return $text;
}
-
+
+ /**
+ * Strip ~~~, ~~~~ and ~~~~~ out of signatures
+ * @param string $text
+ * @return string Signature text with /~{3,5}/ removed
+ */
+ function cleanSigInSig( $text ) {
+ $text = preg_replace( '/~{3,5}/', '', $text );
+ 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
* @return The old value of the mTagHooks array associated with the hook
*/
function setHook( $tag, $callback ) {
+ $tag = strtolower( $tag );
$oldVal = @$this->mTagHooks[$tag];
$this->mTagHooks[$tag] = $callback;
*
* @public
*
- * @param string $name The function name. Function names are case-insensitive.
+ * @param mixed $id The magic word ID
* @param mixed $callback The callback function (and object) to use
+ * @param integer $flags a combination of the following flags:
+ * SFH_NO_HASH No leading hash, i.e. {{plural:...}} instead of {{#if:...}}
*
* @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;
+ function setFunctionHook( $id, $callback, $flags = 0 ) {
+ $oldVal = @$this->mFunctionHooks[$id];
+ $this->mFunctionHooks[$id] = $callback;
+
+ # Add to function cache
+ $mw = MagicWord::get( $id );
+ if ( !$mw ) {
+ throw new MWException( 'The calling convention to Parser::setFunctionHook() has changed, ' .
+ 'it is now required to pass a MagicWord ID as the first parameter.' );
+ }
+
+ $synonyms = $mw->getSynonyms();
+ $sensitive = intval( $mw->isCaseSensitive() );
+
+ foreach ( $synonyms as $syn ) {
+ # Case
+ if ( !$sensitive ) {
+ $syn = strtolower( $syn );
+ }
+ # Add leading hash
+ if ( !( $flags & SFH_NO_HASH ) ) {
+ $syn = '#' . $syn;
+ }
+ # Remove trailing colon
+ if ( substr( $syn, -1, 1 ) == ':' ) {
+ $syn = substr( $syn, 0, -1 );
+ }
+ $this->mFunctionSynonyms[$sensitive][$syn] = $id;
+ }
return $oldVal;
}
return $matches[0];
}
+ /**
+ * Tag hook handler for 'pre'.
+ */
+ function renderPreTag( $text, $attribs, $parser ) {
+ // Backwards-compatibility hack
+ $content = preg_replace( '!<nowiki>(.*?)</nowiki>!is', '\\1', $text );
+
+ $attribs = Sanitizer::validateTagAttributes( $attribs, 'pre' );
+ return wfOpenElement( 'pre', $attribs ) .
+ wfEscapeHTMLTagsOnly( $content ) .
+ '</pre>';
+ }
+
/**
* Renders an image gallery from a text with one line per image.
* text labels may be given by using |-style alternative text. E.g.
* labeled 'The number "1"' and
* 'A tree'.
*/
- function renderImageGallery( $text ) {
- # Setup the parser
- $parserOptions = new ParserOptions;
- $localParser = new Parser();
-
+ function renderImageGallery( $text, $params ) {
$ig = new ImageGallery();
$ig->setShowBytes( false );
$ig->setShowFilename( false );
$ig->setParsing();
- $lines = explode( "\n", $text );
+ $ig->useSkin( $this->mOptions->getSkin() );
+
+ if( isset( $params['caption'] ) )
+ $ig->setCaption( $params['caption'] );
+ $lines = explode( "\n", $text );
foreach ( $lines as $line ) {
# match lines like these:
# Image:someimage.jpg|This is some image
if ( count( $matches ) == 0 ) {
continue;
}
- $nt =& Title::newFromText( $matches[1] );
+ $tp = Title::newFromText( $matches[1] );
+ $nt =& $tp;
if( is_null( $nt ) ) {
# Bogus title. Ignore these so we don't bomb out later.
continue;
$label = '';
}
- $pout = $localParser->parse( $label , $this->mTitle, $parserOptions );
+ $pout = $this->parse( $label,
+ $this->mTitle,
+ $this->mOptions,
+ false, // Strip whitespace...?
+ false // Don't clear state!
+ );
$html = $pout->getText();
$ig->add( new Image( $nt ), $html );
if ( $nt->getNamespace() == NS_IMAGE ) {
$this->mOutput->addImage( $nt->getDBkey() );
}
-
- # Register links with the parent parser
- foreach( $pout->getLinks() as $ns => $keys ) {
- foreach( $keys as $dbk => $id )
- $this->mOutput->addLink( Title::makeTitle( $ns, $dbk ), $id );
- }
-
}
return $ig->toHTML();
}
$part = explode( '|', $options);
- $mwThumb =& MagicWord::get( MAG_IMG_THUMBNAIL );
- $mwManualThumb =& MagicWord::get( MAG_IMG_MANUALTHUMB );
- $mwLeft =& MagicWord::get( MAG_IMG_LEFT );
- $mwRight =& MagicWord::get( MAG_IMG_RIGHT );
- $mwNone =& MagicWord::get( MAG_IMG_NONE );
- $mwWidth =& MagicWord::get( MAG_IMG_WIDTH );
- $mwCenter =& MagicWord::get( MAG_IMG_CENTER );
- $mwFramed =& MagicWord::get( MAG_IMG_FRAMED );
+ $mwThumb =& MagicWord::get( 'img_thumbnail' );
+ $mwManualThumb =& MagicWord::get( 'img_manualthumb' );
+ $mwLeft =& MagicWord::get( 'img_left' );
+ $mwRight =& MagicWord::get( 'img_right' );
+ $mwNone =& MagicWord::get( 'img_none' );
+ $mwWidth =& MagicWord::get( 'img_width' );
+ $mwCenter =& MagicWord::get( 'img_center' );
+ $mwFramed =& MagicWord::get( 'img_framed' );
$caption = '';
$width = $height = $framed = $thumb = false;
# remember to set an alignment, don't render immediately
$align = 'none';
} elseif ( $wgUseImageResize && ! is_null( $match = $mwWidth->matchVariableStartToEnd($val) ) ) {
- wfDebug( "MAG_IMG_WIDTH match: $match\n" );
+ wfDebug( "img_width match: $match\n" );
# $match is the image width in pixels
if ( preg_match( '/^([0-9]*)x([0-9]*)$/', $match, $m ) ) {
$width = intval( $m[1] );
*/
function getTags() { return array_keys( $this->mTagHooks ); }
/**#@-*/
+
+
+ /**
+ * Break wikitext input into sections, and either pull or replace
+ * some particular section's text.
+ *
+ * External callers should use the getSection and replaceSection methods.
+ *
+ * @param $text Page wikitext
+ * @param $section Numbered section. 0 pulls the text before the first
+ * heading; other numbers will pull the given section
+ * along with its lower-level subsections.
+ * @param $mode One of "get" or "replace"
+ * @param $newtext Replacement text for section data.
+ * @return string for "get", the extracted section text.
+ * for "replace", the whole page with the section replaced.
+ */
+ private function extractSections( $text, $section, $mode, $newtext='' ) {
+ # strip NOWIKI etc. to avoid confusion (true-parameter causes HTML
+ # comments to be stripped as well)
+ $striparray = array();
+
+ $oldOutputType = $this->mOutputType;
+ $oldOptions = $this->mOptions;
+ $this->mOptions = new ParserOptions();
+ $this->mOutputType = OT_WIKI;
+
+ $striptext = $this->strip( $text, $striparray, true );
+
+ $this->mOutputType = $oldOutputType;
+ $this->mOptions = $oldOptions;
+
+ # now that we can be sure that no pseudo-sections are in the source,
+ # split it up by section
+ $uniq = preg_quote( $this->uniqPrefix(), '/' );
+ $comment = "(?:$uniq-!--.*?QINU)";
+ $secs = preg_split(
+ /*
+ "/
+ ^(
+ (?:$comment|<\/?noinclude>)* # Initial comments will be stripped
+ (?:
+ (=+) # Should this be limited to 6?
+ .+? # Section title...
+ \\2 # Ending = count must match start
+ |
+ ^
+ <h([1-6])\b.*?>
+ .*?
+ <\/h\\3\s*>
+ )
+ (?:$comment|<\/?noinclude>|\s+)* # Trailing whitespace ok
+ )$
+ /mix",
+ */
+ "/
+ (
+ ^
+ (?:$comment|<\/?noinclude>)* # Initial comments will be stripped
+ (=+) # Should this be limited to 6?
+ .+? # Section title...
+ \\2 # Ending = count must match start
+ (?:$comment|<\/?noinclude>|[ \\t]+)* # Trailing whitespace ok
+ $
+ |
+ <h([1-6])\b.*?>
+ .*?
+ <\/h\\3\s*>
+ )
+ /mix",
+ $striptext, -1,
+ PREG_SPLIT_DELIM_CAPTURE);
+
+ if( $mode == "get" ) {
+ if( $section == 0 ) {
+ // "Section 0" returns the content before any other section.
+ $rv = $secs[0];
+ } else {
+ $rv = "";
+ }
+ } elseif( $mode == "replace" ) {
+ if( $section == 0 ) {
+ $rv = $newtext . "\n\n";
+ $remainder = true;
+ } else {
+ $rv = $secs[0];
+ $remainder = false;
+ }
+ }
+ $count = 0;
+ $sectionLevel = 0;
+ for( $index = 1; $index < count( $secs ); ) {
+ $headerLine = $secs[$index++];
+ if( $secs[$index] ) {
+ // A wiki header
+ $headerLevel = strlen( $secs[$index++] );
+ } else {
+ // An HTML header
+ $index++;
+ $headerLevel = intval( $secs[$index++] );
+ }
+ $content = $secs[$index++];
+
+ $count++;
+ if( $mode == "get" ) {
+ if( $count == $section ) {
+ $rv = $headerLine . $content;
+ $sectionLevel = $headerLevel;
+ } elseif( $count > $section ) {
+ if( $sectionLevel && $headerLevel > $sectionLevel ) {
+ $rv .= $headerLine . $content;
+ } else {
+ // Broke out to a higher-level section
+ break;
+ }
+ }
+ } elseif( $mode == "replace" ) {
+ if( $count < $section ) {
+ $rv .= $headerLine . $content;
+ } elseif( $count == $section ) {
+ $rv .= $newtext . "\n\n";
+ $sectionLevel = $headerLevel;
+ } elseif( $count > $section ) {
+ if( $headerLevel <= $sectionLevel ) {
+ // Passed the section's sub-parts.
+ $remainder = true;
+ }
+ if( $remainder ) {
+ $rv .= $headerLine . $content;
+ }
+ }
+ }
+ }
+ # reinsert stripped tags
+ $rv = $this->unstrip( $rv, $striparray );
+ $rv = $this->unstripNoWiki( $rv, $striparray );
+ $rv = trim( $rv );
+ return $rv;
+ }
+
+ /**
+ * This function returns the text of a section, specified by a number ($section).
+ * A section is text under a heading like == Heading == or \<h1\>Heading\</h1\>, or
+ * the first section before any such heading (section 0).
+ *
+ * If a section contains subsections, these are also returned.
+ *
+ * @param $text String: text to look in
+ * @param $section Integer: section number
+ * @return string text of the requested section
+ */
+ function getSection( $text, $section ) {
+ return $this->extractSections( $text, $section, "get" );
+ }
+
+ function replaceSection( $oldtext, $section, $text ) {
+ return $this->extractSections( $oldtext, $section, "replace", $text );
+ }
+
}
/**
$mExternalLinks, # External link URLs, in the key only
$mHTMLtitle, # Display HTML title
$mSubtitle, # Additional subtitle
- $mNewSection; # Show a new section link?
+ $mNewSection, # Show a new section link?
+ $mNoGallery; # No gallery on category page? (__NOGALLERY__)
function ParserOutput( $text = '', $languageLinks = array(), $categoryLinks = array(),
$containsOldMagic = false, $titletext = '' )
$this->mHTMLtitle = "" ;
$this->mSubtitle = "" ;
$this->mNewSection = false;
+ $this->mNoGallery = false;
}
function getText() { return $this->mText; }
function &getTemplates() { return $this->mTemplates; }
function &getImages() { return $this->mImages; }
function &getExternalLinks() { return $this->mExternalLinks; }
+ function getNoGallery() { return $this->mNoGallery; }
+ function getSubtitle() { return $this->mSubtitle; }
function containsOldMagic() { return $this->mContainsOldMagic; }
function setText( $text ) { return wfSetVar( $this->mText, $text ); }
function setCategoryLinks( $cl ) { return wfSetVar( $this->mCategories, $cl ); }
function setContainsOldMagic( $com ) { return wfSetVar( $this->mContainsOldMagic, $com ); }
function setCacheTime( $t ) { return wfSetVar( $this->mCacheTime, $t ); }
- function setTitleText( $t ) { return wfSetVar ($this->mTitleText, $t); }
+ function setTitleText( $t ) { return wfSetVar($this->mTitleText, $t); }
+ function setSubtitle( $st ) { return wfSetVar( $this->mSubtitle, $st ); }
function addCategory( $c, $sort ) { $this->mCategories[$c] = $sort; }
function addImage( $name ) { $this->mImages[$name] = 1; }
var $mTidy; # Ask for tidy cleanup
var $mInterfaceMessage; # Which lang to call for PLURAL and GRAMMAR
+ var $mUser; # Stored user object, just used to initialise the skin
+
function getUseTeX() { return $this->mUseTeX; }
function getUseDynamicDates() { return $this->mUseDynamicDates; }
function getInterwikiMagic() { return $this->mInterwikiMagic; }
function getAllowExternalImages() { return $this->mAllowExternalImages; }
function getAllowExternalImagesFrom() { return $this->mAllowExternalImagesFrom; }
- function &getSkin() { return $this->mSkin; }
- function getDateFormat() { return $this->mDateFormat; }
function getEditSection() { return $this->mEditSection; }
function getNumberHeadings() { return $this->mNumberHeadings; }
function getAllowSpecialInclusion() { return $this->mAllowSpecialInclusion; }
function getTidy() { return $this->mTidy; }
function getInterfaceMessage() { return $this->mInterfaceMessage; }
+ function &getSkin() {
+ if ( !isset( $this->mSkin ) ) {
+ $this->mSkin = $this->mUser->getSkin();
+ }
+ return $this->mSkin;
+ }
+
+ function getDateFormat() {
+ if ( !isset( $this->mDateFormat ) ) {
+ $this->mDateFormat = $this->mUser->getDatePreference();
+ }
+ return $this->mDateFormat;
+ }
+
function setUseTeX( $x ) { return wfSetVar( $this->mUseTeX, $x ); }
function setUseDynamicDates( $x ) { return wfSetVar( $this->mUseDynamicDates, $x ); }
function setInterwikiMagic( $x ) { return wfSetVar( $this->mInterwikiMagic, $x ); }
function setSkin( &$x ) { $this->mSkin =& $x; }
function setInterfaceMessage( $x ) { return wfSetVar( $this->mInterfaceMessage, $x); }
- function ParserOptions() {
- global $wgUser;
- $this->initialiseFromUser( $wgUser );
+ function ParserOptions( $user = null ) {
+ $this->initialiseFromUser( $user );
}
/**
* Get parser options
* @static
*/
- function newFromUser( &$user ) {
- $popts = new ParserOptions;
- $popts->initialiseFromUser( $user );
- return $popts;
+ static function newFromUser( $user ) {
+ return new ParserOptions( $user );
}
/** Get user options */
- function initialiseFromUser( &$userInput ) {
+ function initialiseFromUser( $userInput ) {
global $wgUseTeX, $wgUseDynamicDates, $wgInterwikiMagic, $wgAllowExternalImages;
global $wgAllowExternalImagesFrom, $wgAllowSpecialInclusion;
$fname = 'ParserOptions::initialiseFromUser';
wfProfileIn( $fname );
if ( !$userInput ) {
- $user = new User;
- $user->setLoaded( true );
+ global $wgUser;
+ if ( isset( $wgUser ) ) {
+ $user = $wgUser;
+ } else {
+ $user = new User;
+ $user->setLoaded( true );
+ }
} else {
$user =& $userInput;
}
+ $this->mUser = $user;
+
$this->mUseTeX = $wgUseTeX;
$this->mUseDynamicDates = $wgUseDynamicDates;
$this->mInterwikiMagic = $wgInterwikiMagic;
$this->mAllowExternalImages = $wgAllowExternalImages;
$this->mAllowExternalImagesFrom = $wgAllowExternalImagesFrom;
- wfProfileIn( $fname.'-skin' );
- $this->mSkin =& $user->getSkin();
- wfProfileOut( $fname.'-skin' );
- $this->mDateFormat = $user->getOption( 'date' );
+ $this->mSkin = null; # Deferred
+ $this->mDateFormat = null; # Deferred
$this->mEditSection = true;
$this->mNumberHeadings = $user->getOption( 'numberheadings' );
$this->mAllowSpecialInclusion = $wgAllowSpecialInclusion;
return (int)$count;
}
+/**
+ * Return the total number of admins
+ *
+ * @return integer
+ */
+function wfNumberOfAdmins() {
+ static $admins = -1;
+ wfProfileIn( 'wfNumberOfAdmins' );
+ if( $admins == -1 ) {
+ $dbr =& wfGetDB( DB_SLAVE );
+ $admins = $dbr->selectField( 'user_groups', 'COUNT(*)', array( 'ug_group' => 'sysop' ), 'wfNumberOfAdmins' );
+ }
+ wfProfileOut( 'wfNumberOfAdmins' );
+ return (int)$admins;
+}
+
+/**
+ * Count the number of pages in a particular namespace
+ *
+ * @param $ns Namespace
+ * @return integer
+ */
+function wfPagesInNs( $ns ) {
+ static $pageCount = array();
+ wfProfileIn( 'wfPagesInNs' );
+ if( !isset( $pageCount[$ns] ) ) {
+ $dbr =& wfGetDB( DB_SLAVE );
+ $pageCount[$ns] = $dbr->selectField( 'page', 'COUNT(*)', array( 'page_namespace' => $ns ), 'wfPagesInNs' );
+ }
+ wfProfileOut( 'wfPagesInNs' );
+ return (int)$pageCount[$ns];
+}
+
/**
* Get various statistics from the database
* @private