define( 'OT_HTML', 1 );
define( 'OT_WIKI', 2 );
define( 'OT_MSG' , 3 );
+define( 'OT_PREPROCESS', 4 );
# Flags for setFunctionHook
define( 'SFH_NO_HASH', 1 );
* Processes wiki markup
*
* <pre>
- * There are three main entry points into the Parser class:
+ * There are four main entry points into the Parser class:
* parse()
* produces HTML output
* preSaveTransform().
* produces altered wiki markup.
* transformMsg()
* performs brace substitution on MediaWiki messages
+ * preprocess()
+ * removes HTML comments and expands templates
*
* Globals used:
* objects: $wgLang, $wgContLang
* settings:
* $wgUseTex*, $wgUseDynamicDates*, $wgInterwikiMagic*,
* $wgNamespacesWithSubpages, $wgAllowExternalImages*,
- * $wgLocaltimezone, $wgAllowSpecialInclusion*,
+ * $wgLocaltimezone, $wgAllowSpecialInclusion*,
* $wgMaxArticleSize*
*
* * only within ParserOptions
var $mTagHooks, $mFunctionHooks, $mFunctionSynonyms, $mVariables;
# Cleared with clearState():
- var $mOutput, $mAutonumber, $mDTopen, $mStripState = array();
+ var $mOutput, $mAutonumber, $mDTopen, $mStripState;
var $mIncludeCount, $mArgStack, $mLastSection, $mInPre;
var $mInterwikiLinkHolders, $mLinkHolders, $mUniqPrefix;
var $mIncludeSizes;
var $mOptions, // ParserOptions object
$mTitle, // Title context, used for self-link rendering and similar things
$mOutputType, // Output type, one of the OT_xxx constants
- $mRevisionId; // ID to display in {{REVISIONID}} tags
+ $ot, // Shortcut alias, see setOutputType()
+ $mRevisionId, // ID to display in {{REVISIONID}} tags
+ $mRevisionTimestamp, // The timestamp of the specified revision ID
+ $mRevIdForTs; // The revision ID which was used to fetch the timestamp
/**#@-*/
$this->setHook( 'pre', array( $this, 'renderPreTag' ) );
+ $this->setFunctionHook( 'int', array( 'CoreParserFunctions', 'intFunction' ), SFH_NO_HASH );
$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( '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 );
+ $this->setFunctionHook( 'padleft', array( 'CoreParserFunctions', 'padleft' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'padright', array( 'CoreParserFunctions', 'padright' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'anchorencode', array( 'CoreParserFunctions', 'anchorencode' ), SFH_NO_HASH );
+ $this->setFunctionHook( 'special', array( 'CoreParserFunctions', 'special' ) );
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->initialiseVariables();
$this->mFirstCall = false;
wfProfileOut( __METHOD__ );
- }
+ }
/**
* Clear Parser state
$this->mLastSection = '';
$this->mDTopen = false;
$this->mIncludeCount = array();
- $this->mStripState = array();
+ $this->mStripState = new StripState;
$this->mArgStack = array();
$this->mInPre = false;
$this->mInterwikiLinkHolders = array(
'texts' => array(),
'titles' => array()
);
- $this->mRevisionId = null;
+ $this->mRevisionTimestamp = $this->mRevisionId = null;
/**
* Prefix for temporary replacement strings for the multipass parser.
wfProfileOut( __METHOD__ );
}
+ function setOutputType( $ot ) {
+ $this->mOutputType = $ot;
+ // Shortcut alias
+ $this->ot = array(
+ 'html' => $ot == OT_HTML,
+ 'wiki' => $ot == OT_WIKI,
+ 'msg' => $ot == OT_MSG,
+ 'pre' => $ot == OT_PREPROCESS,
+ );
+ }
+
/**
* Accessor for mUniqPrefix.
*
*/
global $wgUseTidy, $wgAlwaysUseTidy, $wgContLang;
- $fname = 'Parser::parse';
+ $fname = 'Parser::parse-' . wfGetCaller();
+ wfProfileIn( __METHOD__ );
wfProfileIn( $fname );
if ( $clearState ) {
$this->mOptions = $options;
$this->mTitle =& $title;
$oldRevisionId = $this->mRevisionId;
+ $oldRevisionTimestamp = $this->mRevisionTimestamp;
if( $revid !== null ) {
$this->mRevisionId = $revid;
+ $this->mRevisionTimestamp = null;
}
- $this->mOutputType = OT_HTML;
-
- //$text = $this->strip( $text, $this->mStripState );
- // VOODOO MAGIC FIX! Sometimes the above segfaults in PHP5.
- $x =& $this->mStripState;
-
- wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$x ) );
- $text = $this->strip( $text, $x );
- wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$x ) );
-
+ $this->setOutputType( OT_HTML );
+ wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
+ $text = $this->strip( $text, $this->mStripState );
+ wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
$text = $this->internalParse( $text );
-
- $text = $this->unstrip( $text, $this->mStripState );
+ $text = $this->mStripState->unstripGeneral( $text );
# Clean up special characters, only run once, next-to-last before doBlockLevels
$fixtags = array(
# Side-effects: this calls $this->mOutput->setTitleText()
$text = $wgContLang->parserConvert( $text, $this );
- $text = $this->unstripNoWiki( $text, $this->mStripState );
+ $text = $this->mStripState->unstripNoWiki( $text );
wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
}
$this->mOutput->setText( $text );
$this->mRevisionId = $oldRevisionId;
+ $this->mRevisionTimestamp = $oldRevisionTimestamp;
wfProfileOut( $fname );
+ wfProfileOut( __METHOD__ );
return $this->mOutput;
}
*/
function recursiveTagParse( $text ) {
wfProfileIn( __METHOD__ );
- $x =& $this->mStripState;
- wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$x ) );
- $text = $this->strip( $text, $x );
- wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$x ) );
+ wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
+ $text = $this->strip( $text, $this->mStripState );
+ wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
$text = $this->internalParse( $text );
wfProfileOut( __METHOD__ );
return $text;
}
+ /**
+ * Expand templates and variables in the text, producing valid, static wikitext.
+ * Also removes comments.
+ */
+ function preprocess( $text, $title, $options ) {
+ wfProfileIn( __METHOD__ );
+ $this->clearState();
+ $this->setOutputType( OT_PREPROCESS );
+ $this->mOptions = $options;
+ $this->mTitle = $title;
+ wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
+ $text = $this->strip( $text, $this->mStripState );
+ wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
+ if ( $this->mOptions->getRemoveComments() ) {
+ $text = Sanitizer::removeHTMLcomments( $text );
+ }
+ $text = $this->replaceVariables( $text );
+ $text = $this->mStripState->unstripBoth( $text );
+ wfProfileOut( __METHOD__ );
+ return $text;
+ }
+
/**
* Get a random string
*
$text = $q[2];
}
}
-
+
$matches[$marker] = array( $element,
$content,
Sanitizer::decodeTagAttributes( $attributes ),
* Strips and renders nowiki, pre, math, hiero
* If $render is set, performs necessary rendering operations on plugins
* Returns the text, and fills an array with data needed in unstrip()
- * If the $state is already a valid strip state, it adds to the state
+ *
+ * @param StripState $state
*
* @param bool $stripcomments when set, HTML comments <!-- like this -->
* 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 , $dontstrip = array () ) {
+ function strip( $text, $state, $stripcomments = false , $dontstrip = array () ) {
+ global $wgContLang;
wfProfileIn( __METHOD__ );
$render = ($this->mOutputType == OT_HTML);
- # Replace any instances of the placeholders
$uniq_prefix = $this->mUniqPrefix;
- #$text = str_replace( $uniq_prefix, wfHtmlEscapeFirst( $uniq_prefix ), $text );
- $commentState = array();
-
+ $commentState = new ReplacementArray;
+
$elements = array_merge(
array( 'nowiki', 'gallery' ),
array_keys( $this->mTagHooks ) );
if( $this->mOptions->getUseTeX() ) {
$elements[] = 'math';
}
-
+
# 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] );
}
-
+
$matches = array();
$text = Parser::extractTagsAndParams( $elements, $text, $matches, $uniq_prefix );
}
// Shouldn't happen otherwise. :)
case 'nowiki':
- $output = wfEscapeHTMLTagsOnly( $content );
+ $output = Xml::escapeTagsOnly( $content );
break;
case 'math':
- $output = MathRenderer::renderMath( $content );
+ $output = $wgContLang->armourMath( MathRenderer::renderMath( $content ) );
break;
case 'gallery':
$output = $this->renderImageGallery( $content, $params );
$output = $tag;
}
- // Unstrip the output, because unstrip() is no longer recursive so
+ // Unstrip the output, because unstrip() is no longer recursive so
// it won't do it itself
- $output = $this->unstrip( $output, $state );
+ $output = $state->unstripBoth( $output );
if( !$stripcomments && $element == '!--' ) {
- $commentState[$marker] = $output;
+ $commentState->setPair( $marker, $output );
} elseif ( $element == 'html' || $element == 'nowiki' ) {
- $state['nowiki'][$marker] = $output;
+ $state->nowiki->setPair( $marker, $output );
} else {
- $state['general'][$marker] = $output;
+ $state->general->setPair( $marker, $output );
}
}
# a comment.)
if ( !$stripcomments ) {
// Put them all back and forget them
- $text = strtr( $text, $commentState );
+ $text = $commentState->replace( $text );
}
wfProfileOut( __METHOD__ );
*
* always call unstripNoWiki() after this one
* @private
+ * @deprecated use $this->mStripState->unstrip()
*/
- function unstrip( $text, &$state ) {
- if ( !isset( $state['general'] ) ) {
- return $text;
- }
-
- wfProfileIn( __METHOD__ );
- # TODO: good candidate for FSS
- $text = strtr( $text, $state['general'] );
- wfProfileOut( __METHOD__ );
- return $text;
+ function unstrip( $text, $state ) {
+ return $state->unstripGeneral( $text );
}
/**
* Always call this after unstrip() to preserve the order
*
* @private
+ * @deprecated use $this->mStripState->unstrip()
*/
- function unstripNoWiki( $text, &$state ) {
- if ( !isset( $state['nowiki'] ) ) {
- return $text;
- }
+ function unstripNoWiki( $text, $state ) {
+ return $state->unstripNoWiki( $text );
+ }
- wfProfileIn( __METHOD__ );
- # TODO: good candidate for FSS
- $text = strtr( $text, $state['nowiki'] );
- wfProfileOut( __METHOD__ );
-
- return $text;
+ /**
+ * @deprecated use $this->mStripState->unstripBoth()
+ */
+ function unstripForHTML( $text ) {
+ return $this->mStripState->unstripBoth( $text );
}
/**
*/
function insertStripItem( $text, &$state ) {
$rnd = $this->mUniqPrefix . '-item' . Parser::getRandomString();
- if ( !$state ) {
- $state = array();
- }
- $state['general'][$rnd] = $text;
+ $state->general->setPair( $rnd, $text );
return $rnd;
}
*
* @private
*/
- function doTableStuff ( $t ) {
+ function doTableStuff ( $text ) {
$fname = 'Parser::doTableStuff';
wfProfileIn( $fname );
- $t = explode ( "\n" , $t ) ;
- $td = array () ; # Is currently a td tag open?
- $ltd = array () ; # Was it TD or TH?
- $tr = array () ; # Is currently a tr tag open?
- $ltr = array () ; # tr attributes
- $has_opened_tr = array(); # Did this table open a <tr> element?
- $indent_level = 0; # indent level of the table
- foreach ( $t AS $k => $x )
+ $lines = explode ( "\n" , $text );
+ $td_history = array (); // Is currently a td tag open?
+ $last_tag_history = array (); // Save history of last lag activated (td, th or caption)
+ $tr_history = array (); // Is currently a tr tag open?
+ $tr_attributes = array (); // history of tr attributes
+ $has_opened_tr = array(); // Did this table open a <tr> element?
+ $indent_level = 0; // indent level of the table
+ foreach ( $lines as $key => $line )
{
- $x = trim ( $x ) ;
- $fc = substr ( $x , 0 , 1 ) ;
- if ( preg_match( '/^(:*)\{\|(.*)$/', $x, $matches ) ) {
+ $line = trim ( $line );
+
+ if( $line == '' ) { // empty line, go to next line
+ continue;
+ }
+ $first_character = $line{0};
+ $matches = array();
+
+ if ( preg_match( '/^(:*)\{\|(.*)$/' , $line , $matches ) ) {
+ // First check if we are starting a new table
$indent_level = strlen( $matches[1] );
- $attributes = $this->unstripForHTML( $matches[2] );
+ $attributes = $this->mStripState->unstripBoth( $matches[2] );
+ $attributes = Sanitizer::fixTagAttributes ( $attributes , 'table' );
+
+ $lines[$key] = str_repeat( '<dl><dd>' , $indent_level ) . "<table{$attributes}>";
+ array_push ( $td_history , false );
+ array_push ( $last_tag_history , '' );
+ array_push ( $tr_history , false );
+ array_push ( $tr_attributes , '' );
+ array_push ( $has_opened_tr , false );
+ } else if ( count ( $td_history ) == 0 ) {
+ // Don't do any of the following
+ continue;
+ } else if ( substr ( $line , 0 , 2 ) == '|}' ) {
+ // We are ending a table
+ $line = '</table>' . substr ( $line , 2 );
+ $last_tag = array_pop ( $last_tag_history );
- $t[$k] = str_repeat( '<dl><dd>', $indent_level ) .
- '<table' . Sanitizer::fixTagAttributes ( $attributes, 'table' ) . '>' ;
- array_push ( $td , false ) ;
- array_push ( $ltd , '' ) ;
- array_push ( $tr , false ) ;
- array_push ( $ltr , '' ) ;
- array_push ( $has_opened_tr, false );
- }
- else if ( count ( $td ) == 0 ) { } # Don't do any of the following
- else if ( '|}' == substr ( $x , 0 , 2 ) ) {
- $z = "</table>" . substr ( $x , 2);
- $l = array_pop ( $ltd ) ;
- if ( !array_pop ( $has_opened_tr ) ) $z = "<tr><td></td></tr>" . $z ;
- if ( array_pop ( $tr ) ) $z = '</tr>' . $z ;
- if ( array_pop ( $td ) ) $z = '</'.$l.'>' . $z ;
- array_pop ( $ltr ) ;
- $t[$k] = $z . str_repeat( '</dd></dl>', $indent_level );
- }
- else if ( '|-' == substr ( $x , 0 , 2 ) ) { # Allows for |---------------
- $x = substr ( $x , 1 ) ;
- while ( $x != '' && substr ( $x , 0 , 1 ) == '-' ) $x = substr ( $x , 1 ) ;
- $z = '' ;
- $l = array_pop ( $ltd ) ;
+ if ( !array_pop ( $has_opened_tr ) ) {
+ $line = "<tr><td></td></tr>{$line}";
+ }
+
+ if ( array_pop ( $tr_history ) ) {
+ $line = "</tr>{$line}";
+ }
+
+ if ( array_pop ( $td_history ) ) {
+ $line = "</{$last_tag}>{$line}";
+ }
+ array_pop ( $tr_attributes );
+ $lines[$key] = $line . str_repeat( '</dd></dl>' , $indent_level );
+ } else if ( substr ( $line , 0 , 2 ) == '|-' ) {
+ // Now we have a table row
+ $line = preg_replace( '#^\|-+#', '', $line );
+
+ // Whats after the tag is now only attributes
+ $attributes = $this->mStripState->unstripBoth( $line );
+ $attributes = Sanitizer::fixTagAttributes ( $attributes , 'tr' );
+ array_pop ( $tr_attributes );
+ array_push ( $tr_attributes , $attributes );
+
+ $line = '';
+ $last_tag = array_pop ( $last_tag_history );
array_pop ( $has_opened_tr );
- array_push ( $has_opened_tr , true ) ;
- if ( array_pop ( $tr ) ) $z = '</tr>' . $z ;
- if ( array_pop ( $td ) ) $z = '</'.$l.'>' . $z ;
- array_pop ( $ltr ) ;
- $t[$k] = $z ;
- array_push ( $tr , false ) ;
- array_push ( $td , false ) ;
- array_push ( $ltd , '' ) ;
- $attributes = $this->unstripForHTML( $x );
- array_push ( $ltr , Sanitizer::fixTagAttributes ( $attributes, 'tr' ) ) ;
+ array_push ( $has_opened_tr , true );
+
+ if ( array_pop ( $tr_history ) ) {
+ $line = '</tr>';
+ }
+
+ if ( array_pop ( $td_history ) ) {
+ $line = "</{$last_tag}>{$line}";
+ }
+
+ $lines[$key] = $line;
+ array_push ( $tr_history , false );
+ array_push ( $td_history , false );
+ array_push ( $last_tag_history , '' );
}
- else if ( '|' == $fc || '!' == $fc || '|+' == substr ( $x , 0 , 2 ) ) { # Caption
- # $x is a table row
- if ( '|+' == substr ( $x , 0 , 2 ) ) {
- $fc = '+' ;
- $x = substr ( $x , 1 ) ;
+ else if ( $first_character == '|' || $first_character == '!' || substr ( $line , 0 , 2 ) == '|+' ) {
+ // This might be cell elements, td, th or captions
+ if ( substr ( $line , 0 , 2 ) == '|+' ) {
+ $first_character = '+';
+ $line = substr ( $line , 1 );
+ }
+
+ $line = substr ( $line , 1 );
+
+ if ( $first_character == '!' ) {
+ $line = str_replace ( '!!' , '||' , $line );
}
- $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
+ // 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 );
+ $cells = StringUtils::explodeMarkup( '||' , $line );
- $t[$k] = '' ;
+ $lines[$key] = '';
- # Loop through each table cell
- foreach ( $after AS $theline )
+ // Loop through each table cell
+ foreach ( $cells as $cell )
{
- $z = '' ;
- if ( $fc != '+' )
+ $previous = '';
+ if ( $first_character != '+' )
{
- $tra = array_pop ( $ltr ) ;
- if ( !array_pop ( $tr ) ) $z = '<tr'.$tra.">\n" ;
- array_push ( $tr , true ) ;
- array_push ( $ltr , '' ) ;
+ $tr_after = array_pop ( $tr_attributes );
+ if ( !array_pop ( $tr_history ) ) {
+ $previous = "<tr{$tr_after}>\n";
+ }
+ array_push ( $tr_history , true );
+ array_push ( $tr_attributes , '' );
array_pop ( $has_opened_tr );
- array_push ( $has_opened_tr , true ) ;
+ array_push ( $has_opened_tr , true );
+ }
+
+ $last_tag = array_pop ( $last_tag_history );
+
+ if ( array_pop ( $td_history ) ) {
+ $previous = "</{$last_tag}>{$previous}";
}
- $l = array_pop ( $ltd ) ;
- if ( array_pop ( $td ) ) $z = '</'.$l.'>' . $z ;
- if ( $fc == '|' ) $l = 'td' ;
- else if ( $fc == '!' ) $l = 'th' ;
- else if ( $fc == '+' ) $l = 'caption' ;
- else $l = '' ;
- array_push ( $ltd , $l ) ;
-
- # Cell parameters
- $y = explode ( '|' , $theline , 2 ) ;
- # Note that a '|' inside an invalid link should not
- # be mistaken as delimiting cell parameters
- if ( strpos( $y[0], '[[' ) !== false ) {
- $y = array ($theline);
+ if ( $first_character == '|' ) {
+ $last_tag = 'td';
+ } else if ( $first_character == '!' ) {
+ $last_tag = 'th';
+ } else if ( $first_character == '+' ) {
+ $last_tag = 'caption';
+ } else {
+ $last_tag = '';
}
- if ( count ( $y ) == 1 )
- $y = "{$z}<{$l}>{$y[0]}" ;
+
+ array_push ( $last_tag_history , $last_tag );
+
+ // A cell could contain both parameters and data
+ $cell_data = explode ( '|' , $cell , 2 );
+
+ // Bug 553: Note that a '|' inside an invalid link should not
+ // be mistaken as delimiting cell parameters
+ if ( strpos( $cell_data[0], '[[' ) !== false ) {
+ $cell = "{$previous}<{$last_tag}>{$cell}";
+ } else if ( count ( $cell_data ) == 1 )
+ $cell = "{$previous}<{$last_tag}>{$cell_data[0]}";
else {
- $attributes = $this->unstripForHTML( $y[0] );
- $y = "{$z}<{$l}".Sanitizer::fixTagAttributes($attributes, $l).">{$y[1]}" ;
+ $attributes = $this->mStripState->unstripBoth( $cell_data[0] );
+ $attributes = Sanitizer::fixTagAttributes( $attributes , $last_tag );
+ $cell = "{$previous}<{$last_tag}{$attributes}>{$cell_data[1]}";
}
- $t[$k] .= $y ;
- array_push ( $td , true ) ;
+
+ $lines[$key] .= $cell;
+ array_push ( $td_history , true );
}
}
}
- # Closing open td, tr && table
- while ( count ( $td ) > 0 )
+ // Closing open td, tr && table
+ while ( count ( $td_history ) > 0 )
{
- $l = array_pop ( $ltd ) ;
- if ( array_pop ( $td ) ) $t[] = '</td>' ;
- if ( array_pop ( $tr ) ) $t[] = '</tr>' ;
- if ( !array_pop ( $has_opened_tr ) ) $t[] = "<tr><td></td></tr>" ;
- $t[] = '</table>' ;
+ if ( array_pop ( $td_history ) ) {
+ $lines[] = '</td>' ;
+ }
+ if ( array_pop ( $tr_history ) ) {
+ $lines[] = '</tr>' ;
+ }
+ if ( !array_pop ( $has_opened_tr ) ) {
+ $lines[] = "<tr><td></td></tr>" ;
+ }
+
+ $lines[] = '</table>' ;
+ }
+
+ $output = implode ( "\n" , $lines ) ;
+
+ // special case: don't return empty table
+ if( $output == "<table>\n<tr><td></td></tr>\n</table>" ) {
+ $output = '';
}
- $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 ;
+
+ return $output;
}
/**
wfProfileIn( $fname );
# Hook to suspend the parser in this state
- if ( !wfRunHooks( 'ParserBeforeInternalParse', array( &$this, &$text, &$x ) ) ) {
+ if ( !wfRunHooks( 'ParserBeforeInternalParse', array( &$this, &$text, &$this->mStripState ) ) ) {
wfProfileOut( $fname );
return $text ;
}
# Remove <noinclude> tags and <includeonly> sections
$text = strtr( $text, array( '<onlyinclude>' => '' , '</onlyinclude>' => '' ) );
$text = strtr( $text, array( '<noinclude>' => '', '</noinclude>' => '') );
- $text = preg_replace( '/<includeonly>.*?<\/includeonly>/s', '', $text );
+ $text = StringUtils::delimiterReplace( '<includeonly>', '</includeonly>', '', $text );
$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'attributeStripCallback' ) );
*/
function &doMagicLinks( &$text ) {
wfProfileIn( __METHOD__ );
- $text = preg_replace_callback(
+ $text = preg_replace_callback(
'!(?: # Start cases
- <a.*?</a> # Skip link text
+ <a.*?</a> | # Skip link text
<.*?> | # Skip stuff inside HTML elements
(?:RFC|PMID)\s+([0-9]+) | # RFC or PMID, capture number as m[1]
- ISBN\s+([0-9Xx-]+) # ISBN, capture number as m[2]
+ ISBN\s+(\b[0-9Xx\ \-]+) # ISBN, capture number as m[2]
)!x', array( &$this, 'magicLinkCallback' ), $text );
wfProfileOut( __METHOD__ );
- return $text;
+ return $text;
}
function magicLinkCallback( $m ) {
return $m[0];
} elseif ( substr( $m[0], 0, 4 ) == 'ISBN' ) {
$isbn = $m[2];
- $num = strtr( $isbn, array(
+ $num = strtr( $isbn, array(
'-' => '',
' ' => '',
'x' => 'X',
));
- $titleObj = Title::makeTitle( NS_SPECIAL, 'Booksources' );
+ $titleObj = SpecialPage::getTitleFor( 'Booksources' );
$text = '<a href="' .
$titleObj->escapeLocalUrl( "isbn=$num" ) .
"\" class=\"internal\">ISBN $isbn</a>";
$urlmsg = 'pubmedurl';
$id = $m[1];
} else {
- throw new MWException( __METHOD__.': unrecognised match type "' .
+ throw new MWException( __METHOD__.': unrecognised match type "' .
substr($m[0], 0, 20 ) . '"' );
}
-
+
$url = wfMsg( $urlmsg, $id);
$sk =& $this->mOptions->getSkin();
$la = $sk->getExternalLinkAttributes( $url, $keyword.$id );
}
# Count the number of occurrences of bold and italics mark-ups.
# We are not counting sequences of five apostrophes.
- if ( strlen( $arr[$i] ) == 2 ) $numitalics++; else
- if ( strlen( $arr[$i] ) == 3 ) $numbold++; else
- if ( strlen( $arr[$i] ) == 5 ) { $numitalics++; $numbold++; }
+ if ( strlen( $arr[$i] ) == 2 ) { $numitalics++; }
+ else if ( strlen( $arr[$i] ) == 3 ) { $numbold++; }
+ else if ( strlen( $arr[$i] ) == 5 ) { $numitalics++; $numbold++; }
}
$i++;
}
# The characters '<' and '>' (which were escaped by
# removeHTMLtags()) should not be included in
# URLs, per RFC 2396.
+ $m2 = array();
if (preg_match('/&(lt|gt);/', $url, $m2, PREG_OFFSET_CAPTURE)) {
$text = substr($url, $m2[0][1]) . ' ' . $text;
$url = substr($url, 0, $m2[0][1]);
}
$text = $wgContLang->markNoConversion($text);
-
+
$url = Sanitizer::cleanUrl( $url );
# Process the trail (i.e. everything after this link up until start of the next link),
$protocol = $bits[$i++];
$remainder = $bits[$i++];
+ $m = array();
if ( preg_match( '/^('.EXT_LINK_URL_CLASS.'+)(.*)$/s', $remainder, $m ) ) {
# Found some characters after the protocol that look promising
$url = $protocol . $m[1];
# special case: handle urls as url args:
# http://www.example.com/foo?=http://www.example.com/bar
- if(strlen($trail) == 0 &&
+ if(strlen($trail) == 0 &&
isset($bits[$i]) &&
preg_match('/^'. wfUrlProtocols() . '$/S', $bits[$i]) &&
- preg_match( '/^('.EXT_LINK_URL_CLASS.'+)(.*)$/s', $bits[$i + 1], $m ))
+ preg_match( '/^('.EXT_LINK_URL_CLASS.'+)(.*)$/s', $bits[$i + 1], $m ))
{
# add protocol, arg
$url .= $bits[$i] . $m[1]; # protocol, url as arg to previous link
# The characters '<' and '>' (which were escaped by
# removeHTMLtags()) should not be included in
# URLs, per RFC 2396.
+ $m2 = array();
if (preg_match('/&(lt|gt);/', $url, $m2, PREG_OFFSET_CAPTURE)) {
$trail = substr($url, $m2[0][1]) . $trail;
$url = substr($url, 0, $m2[0][1]);
$nottalk = !$this->mTitle->isTalkPage();
if ( $useLinkPrefixExtension ) {
+ $m = array();
if ( preg_match( $e2, $s, $m ) ) {
$first_prefix = $m[2];
} else {
}
$selflink = $this->mTitle->getPrefixedText();
- $checkVariantLink = sizeof($wgContLang->getVariants())>1;
$useSubpages = $this->areSubpagesAllowed();
wfProfileOut( $fname.'-setup' );
# Still some problems for cases where the ] is meant to be outside punctuation,
# and no image is in sight. See bug 2095.
#
- if( $text !== '' &&
- substr( $m[3], 0, 1 ) === ']' &&
- strpos($text, '[') !== false
- )
+ if( $text !== '' &&
+ substr( $m[3], 0, 1 ) === ']' &&
+ strpos($text, '[') !== false
+ )
{
$text .= ']'; # so that replaceExternalLinks($text) works later
$m[3] = substr( $m[3], 1 );
wfProfileOut( "$fname-misc" );
wfProfileIn( "$fname-title" );
- $nt = Title::newFromText( $this->unstripNoWiki($link, $this->mStripState) );
+ $nt = Title::newFromText( $this->mStripState->unstripNoWiki($link) );
if( !$nt ) {
$s .= $prefix . '[[' . $line;
wfProfileOut( "$fname-title" );
continue;
}
- #check other language variants of the link
- #if the article does not exist
- if( $checkVariantLink
- && $nt->getArticleID() == 0 ) {
- $wgContLang->findVariantLink($link, $nt);
- }
-
$ns = $nt->getNamespace();
$iw = $nt->getInterWiki();
wfProfileOut( "$fname-title" );
-
+
if ($might_be_img) { # if this is actually an invalid link
wfProfileIn( "$fname-might_be_img" );
if ($ns == NS_IMAGE && $noforce) { #but might be an image
if ( $ns == NS_IMAGE ) {
wfProfileIn( "$fname-image" );
- if ( !wfIsBadImage( $nt->getDBkey() ) ) {
+ if ( !wfIsBadImage( $nt->getDBkey(), $this->mTitle ) ) {
# recursively parse links inside the image caption
# actually, this will parse them in any other parameters, too,
# but it might be hard to fix that, and it doesn't matter ATM
// upload on the shared repository, and we want to see its
// auto-generated page.
$s .= $this->makeKnownLinkHolder( $nt, $text, '', $trail, $prefix );
+ $this->mOutput->addLink( $nt );
continue;
}
}
* @return string less-or-more HTML with NOPARSE bits
*/
function armorLinks( $text ) {
- return preg_replace( "/\b(" . wfUrlProtocols() . ')/',
+ return preg_replace( '/\b(' . wfUrlProtocols() . ')/',
"{$this->mUniqPrefix}NOPARSE$1", $text );
}
wfProfileIn( $fname );
$ret = $target; # default return value is no change
+ # bug 7425
+ $target = trim( $target );
+
# Some namespaces don't allow subpages,
# so only perform processing if subpages are allowed
if( $this->areSubpagesAllowed() ) {
* expensive to check many times.
*/
static $varCache = array();
- if ( wfRunHooks( 'ParserGetVariableValueVarCache', array( &$this, &$varCache ) ) )
- if ( isset( $varCache[$index] ) )
+ if ( wfRunHooks( 'ParserGetVariableValueVarCache', array( &$this, &$varCache ) ) ) {
+ if ( isset( $varCache[$index] ) ) {
return $varCache[$index];
+ }
+ }
$ts = time();
wfRunHooks( 'ParserGetVariableValueTs', array( &$this, &$ts ) );
+ # Use the time zone
+ global $wgLocaltimezone;
+ if ( isset( $wgLocaltimezone ) ) {
+ $oldtz = getenv( 'TZ' );
+ putenv( 'TZ='.$wgLocaltimezone );
+ }
+ $localTimestamp = date( 'YmdHis', $ts );
+ $localMonth = date( 'm', $ts );
+ $localMonthName = date( 'n', $ts );
+ $localDay = date( 'j', $ts );
+ $localDay2 = date( 'd', $ts );
+ $localDayOfWeek = date( 'w', $ts );
+ $localWeek = date( 'W', $ts );
+ $localYear = date( 'Y', $ts );
+ $localHour = date( 'H', $ts );
+ if ( isset( $wgLocaltimezone ) ) {
+ putenv( 'TZ='.$oldtz );
+ }
+
switch ( $index ) {
case 'currentmonth':
return $varCache[$index] = $wgContLang->formatNum( date( 'm', $ts ) );
return $varCache[$index] = $wgContLang->formatNum( date( 'j', $ts ) );
case 'currentday2':
return $varCache[$index] = $wgContLang->formatNum( date( 'd', $ts ) );
+ case 'localmonth':
+ return $varCache[$index] = $wgContLang->formatNum( $localMonth );
+ case 'localmonthname':
+ return $varCache[$index] = $wgContLang->getMonthName( $localMonthName );
+ case 'localmonthnamegen':
+ return $varCache[$index] = $wgContLang->getMonthNameGen( $localMonthName );
+ case 'localmonthabbrev':
+ return $varCache[$index] = $wgContLang->getMonthAbbreviation( $localMonthName );
+ case 'localday':
+ return $varCache[$index] = $wgContLang->formatNum( $localDay );
+ case 'localday2':
+ return $varCache[$index] = $wgContLang->formatNum( $localDay2 );
case 'pagename':
return $this->mTitle->getText();
case 'pagenamee':
return $subjPage->getPrefixedUrl();
case 'revisionid':
return $this->mRevisionId;
+ case 'revisionday':
+ return intval( substr( $this->getRevisionTimestamp(), 6, 2 ) );
+ case 'revisionday2':
+ return substr( $this->getRevisionTimestamp(), 6, 2 );
+ case 'revisionmonth':
+ return intval( substr( $this->getRevisionTimestamp(), 4, 2 ) );
+ case 'revisionyear':
+ return substr( $this->getRevisionTimestamp(), 0, 4 );
+ case 'revisiontimestamp':
+ return $this->getRevisionTimestamp();
case 'namespace':
return str_replace('_',' ',$wgContLang->getNsText( $this->mTitle->getNamespace() ) );
case 'namespacee':
return $varCache[$index] = $wgContLang->formatNum( date( 'Y', $ts ), true );
case 'currenttime':
return $varCache[$index] = $wgContLang->time( wfTimestamp( TS_MW, $ts ), false, false );
+ case 'currenthour':
+ return $varCache[$index] = $wgContLang->formatNum( date( 'H', $ts ), true );
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 'currentdow':
return $varCache[$index] = $wgContLang->formatNum( date( 'w', $ts ) );
+ case 'localdayname':
+ return $varCache[$index] = $wgContLang->getWeekdayName( $localDayOfWeek + 1 );
+ case 'localyear':
+ return $varCache[$index] = $wgContLang->formatNum( $localYear, true );
+ case 'localtime':
+ return $varCache[$index] = $wgContLang->time( $localTimestamp, false, false );
+ case 'localhour':
+ return $varCache[$index] = $wgContLang->formatNum( $localHour, true );
+ case 'localweek':
+ // @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
+ // int to remove the padding
+ return $varCache[$index] = $wgContLang->formatNum( (int)$localWeek );
+ case 'localdow':
+ return $varCache[$index] = $wgContLang->formatNum( $localDayOfWeek );
case 'numberofarticles':
- return $varCache[$index] = $wgContLang->formatNum( wfNumberOfArticles() );
+ return $varCache[$index] = $wgContLang->formatNum( SiteStats::articles() );
case 'numberoffiles':
- return $varCache[$index] = $wgContLang->formatNum( wfNumberOfFiles() );
+ return $varCache[$index] = $wgContLang->formatNum( SiteStats::images() );
case 'numberofusers':
- return $varCache[$index] = $wgContLang->formatNum( wfNumberOfUsers() );
+ return $varCache[$index] = $wgContLang->formatNum( SiteStats::users() );
case 'numberofpages':
- return $varCache[$index] = $wgContLang->formatNum( wfNumberOfPages() );
+ return $varCache[$index] = $wgContLang->formatNum( SiteStats::pages() );
case 'numberofadmins':
- return $varCache[$index] = $wgContLang->formatNum( wfNumberOfAdmins() );
+ return $varCache[$index] = $wgContLang->formatNum( SiteStats::admins() );
case 'currenttimestamp':
return $varCache[$index] = wfTimestampNow();
+ case 'localtimestamp':
+ return $varCache[$index] = $localTimestamp;
case 'currentversion':
- global $wgVersion;
- return $wgVersion;
+ return $varCache[$index] = SpecialVersion::getVersion();
case 'sitename':
return $wgSitename;
case 'server':
$lastOpeningBrace = -1; # last not closed parentheses
$validOpeningBraces = implode( '', array_keys( $callbacks ) );
-
+
$i = 0;
while ( $i < strlen( $text ) ) {
# Find next opening brace, closing brace or pipe
$found = 'pipe';
} elseif ( $text[$i] == $currentClosing ) {
$found = 'close';
- } else {
+ } elseif ( isset( $callbacks[$text[$i]] ) ) {
$found = 'open';
$rule = $callbacks[$text[$i]];
+ } else {
+ # Some versions of PHP have a strcspn which stops on null characters
+ # Ignore and continue
+ ++$i;
+ continue;
}
} else {
# All done
$maxCount = $openingBraceStack[$lastOpeningBrace]['count'];
$count = strspn( $text, $text[$i], $i, $maxCount );
- # check for maximum matching characters (if there are 5 closing
+ # check for maximum matching characters (if there are 5 closing
# characters, we will probably need only 3 - depending on the rules)
$matchingCount = 0;
$matchingCallback = null;
$cbType = $callbacks[$openingBraceStack[$lastOpeningBrace]['brace']];
if ( $count > $cbType['max'] ) {
- # The specified maximum exists in the callback array, unless the caller
+ # The specified maximum exists in the callback array, unless the caller
# has made an error
$matchingCount = $cbType['max'];
} else {
# let's set a title or last part (if '|' was found)
if (null === $openingBraceStack[$lastOpeningBrace]['parts']) {
- $openingBraceStack[$lastOpeningBrace]['title'] =
- substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
+ $openingBraceStack[$lastOpeningBrace]['title'] =
+ substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
$i - $openingBraceStack[$lastOpeningBrace]['partStart']);
} else {
- $openingBraceStack[$lastOpeningBrace]['parts'][] =
- substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
+ $openingBraceStack[$lastOpeningBrace]['parts'][] =
+ substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
$i - $openingBraceStack[$lastOpeningBrace]['partStart']);
}
} elseif ( $found == 'pipe' ) {
# lets set a title if it is a first separator, or next part otherwise
if (null === $openingBraceStack[$lastOpeningBrace]['parts']) {
- $openingBraceStack[$lastOpeningBrace]['title'] =
- substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
+ $openingBraceStack[$lastOpeningBrace]['title'] =
+ substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
$i - $openingBraceStack[$lastOpeningBrace]['partStart']);
$openingBraceStack[$lastOpeningBrace]['parts'] = array();
} else {
- $openingBraceStack[$lastOpeningBrace]['parts'][] =
- substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
+ $openingBraceStack[$lastOpeningBrace]['parts'][] =
+ substr($text, $openingBraceStack[$lastOpeningBrace]['partStart'],
$i - $openingBraceStack[$lastOpeningBrace]['partStart']);
}
$openingBraceStack[$lastOpeningBrace]['partStart'] = ++$i;
if ( !$argsOnly ) {
$braceCallbacks[2] = array( &$this, 'braceSubstitution' );
}
- if ( $this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI ) {
+ if ( $this->mOutputType != OT_MSG ) {
$braceCallbacks[3] = array( &$this, 'argSubstitution' );
}
if ( $braceCallbacks ) {
- $callbacks = array(
+ $callbacks = array(
'{' => array(
'end' => '}',
'cb' => $braceCallbacks,
'min' => $argsOnly ? 3 : 2,
'max' => isset( $braceCallbacks[3] ) ? 3 : 2,
),
- '[' => array(
- 'end' => ']',
+ '[' => array(
+ 'end' => ']',
'cb' => array(2=>null),
'min' => 2,
'max' => 2,
* @private
*/
function variableSubstitution( $matches ) {
+ global $wgContLang;
$fname = 'Parser::variableSubstitution';
- $varname = $matches[1];
+ $varname = $wgContLang->lc($matches[1]);
wfProfileIn( $fname );
$skip = false;
if ( $this->mOutputType == OT_WIKI ) {
}
if ( !$skip && array_key_exists( $varname, $this->mVariables ) ) {
$id = $this->mVariables[$varname];
- $text = $this->getVariableValue( $id );
- $this->mOutput->mContainsOldMagic = true;
+ # 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];
}
return $text;
}
- # Split template arguments
- function getTemplateArgs( $argsString ) {
- if ( $argsString === '' ) {
- return array();
- }
-
- $args = explode( '|', substr( $argsString, 1 ) );
-
- # If any of the arguments contains a '[[' but no ']]', it needs to be
- # merged with the next arg because the '|' character between belongs
- # to the link syntax and not the template parameter syntax.
- $argc = count($args);
-
- for ( $i = 0; $i < $argc-1; $i++ ) {
- if ( substr_count ( $args[$i], '[[' ) != substr_count ( $args[$i], ']]' ) ) {
- $args[$i] .= '|'.$args[$i+1];
- array_splice($args, $i+1, 1);
- $i--;
- $argc--;
- }
- }
-
- return $args;
- }
-
/**
* Return the text of a template, after recursively
* replacing any variables or templates within the template.
* @private
*/
function braceSubstitution( $piece ) {
- global $wgContLang, $wgLang, $wgAllowDisplayTitle, $action;
+ global $wgContLang, $wgLang, $wgAllowDisplayTitle;
$fname = __METHOD__ /*. '-L' . count( $this->mArgStack )*/;
wfProfileIn( $fname );
wfProfileIn( __METHOD__.'-setup' );
$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
$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
- $part1 = $piece['title'];
+ $titleText = $part1 = $piece['title'];
# If the third subpattern matched anything, it will start with |
if (null == $piece['parts']) {
}
$args = (null == $piece['parts']) ? array() : $piece['parts'];
- $argc = count( $args );
wfProfileOut( __METHOD__.'-setup' );
# SUBST
wfProfileIn( __METHOD__.'-modifiers' );
if ( !$found ) {
$mwSubst =& MagicWord::get( 'subst' );
- if ( $mwSubst->matchStartAndRemove( $part1 ) xor ($this->mOutputType == OT_WIKI) ) {
+ if ( $mwSubst->matchStartAndRemove( $part1 ) xor $this->ot['wiki'] ) {
# One of two possibilities is true:
# 1) Found SUBST but not in the PST phase
# 2) Didn't find SUBST and in the PST phase
}
}
- # MSG, MSGNW, INT and RAW
+ # MSG, MSGNW and RAW
if ( !$found ) {
# Check for MSGNW:
$mwMsgnw =& MagicWord::get( 'msgnw' );
$mwMsg =& MagicWord::get( 'msg' );
$mwMsg->matchStartAndRemove( $part1 );
}
-
+
# Check for RAW:
$mwRaw =& MagicWord::get( 'raw' );
if ( $mwRaw->matchStartAndRemove( $part1 ) ) {
$forceRawInterwiki = true;
}
-
- # Check if it is an internal message
- $mwInt =& MagicWord::get( 'int' );
- if ( $mwInt->matchStartAndRemove( $part1 ) ) {
- $text = $linestart . wfMsgReal( $part1, $args, true );
- $found = true;
- }
}
wfProfileOut( __METHOD__.'-modifiers' );
# Parser functions
if ( !$found ) {
wfProfileIn( __METHOD__ . '-pfunc' );
-
+
$colonPos = strpos( $part1, ':' );
if ( $colonPos !== false ) {
# Case sensitive functions
$noargs = true;
$found = true;
$text = $linestart .
- '{{' . $part1 . '}}' .
- '<!-- WARNING: template loop detected -->';
+ "[[$part1]]<!-- WARNING: template loop detected -->";
wfDebug( __METHOD__.": template loop broken at '$part1'\n" );
} else {
# set $text to cached message.
if ( !is_null( $title ) ) {
- $checkVariantLink = sizeof($wgContLang->getVariants())>1;
+ $titleText = $title->getPrefixedText();
# Check for language variants if the template is not found
- if($checkVariantLink && $title->getArticleID() == 0){
+ if($wgContLang->hasVariants() && $title->getArticleID() == 0){
$wgContLang->findVariantLink($part1, $title);
}
if ( !$title->isExternal() ) {
- if ( $title->getNamespace() == NS_SPECIAL && $this->mOptions->getAllowSpecialInclusion() && $this->mOutputType != OT_WIKI ) {
+ if ( $title->getNamespace() == NS_SPECIAL && $this->mOptions->getAllowSpecialInclusion() && $this->ot['html'] ) {
$text = SpecialPage::capturePath( $title );
if ( is_string( $text ) ) {
$found = true;
}
# If the title is valid but undisplayable, make a link to it
- if ( $this->mOutputType == OT_HTML && !$found ) {
- $text = '[['.$title->getPrefixedText().']]';
+ if ( !$found && ( $this->ot['html'] || $this->ot['pre'] ) ) {
+ $text = "[[:$titleText]]";
$found = true;
}
} elseif ( $title->isTrans() ) {
// Interwiki transclusion
- if ( $this->mOutputType == OT_HTML && !$forceRawInterwiki ) {
+ if ( $this->ot['html'] && !$forceRawInterwiki ) {
$text = $this->interwikiTransclude( $title, 'render' );
$isHTML = true;
$noparse = true;
if ( $found && !$this->incrementIncludeSize( 'pre-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
$text = $linestart .
- '{{' . $part1 . '}}' .
- '<!-- WARNING: template omitted, pre-expand include size too large -->';
+ "[[$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->mOutputType == OT_HTML ) {
+ if ( $nowiki && $found && ( $this->ot['html'] || $this->ot['pre'] ) ) {
$text = wfEscapeWikiText( $text );
- } elseif ( ($this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI) && $found ) {
+ } elseif ( !$this->ot['msg'] && $found ) {
if ( $noargs ) {
$assocArgs = array();
} else {
if ( !$noparse ) {
# If there are any <onlyinclude> tags, only include them
if ( in_string( '<onlyinclude>', $text ) && in_string( '</onlyinclude>', $text ) ) {
- preg_match_all( '/<onlyinclude>(.*?)\n?<\/onlyinclude>/s', $text, $m );
- $text = '';
- foreach ($m[1] as $piece)
- $text .= $piece;
+ $replacer = new OnlyIncludeReplacer;
+ StringUtils::delimiterReplaceCallback( '<onlyinclude>', '</onlyinclude>',
+ array( &$replacer, 'replace' ), $text );
+ $text = $replacer->output;
}
# Remove <noinclude> sections and <includeonly> tags
- $text = preg_replace( '/<noinclude>.*?<\/noinclude>/s', '', $text );
+ $text = StringUtils::delimiterReplace( '<noinclude>', '</noinclude>', '', $text );
$text = strtr( $text, array( '<includeonly>' => '' , '</includeonly>' => '' ) );
- if( $this->mOutputType == OT_HTML ) {
+ if( $this->ot['html'] || $this->ot['pre'] ) {
# Strip <nowiki>, <pre>, etc.
$text = $this->strip( $text, $this->mStripState );
- $text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ), $assocArgs );
+ 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('/^({\\||:|;|#|\*)/', $text)) {
+ if (!$piece['lineStart'] && preg_match('/^({\\||:|;|#|\*)/', $text)) /*}*/{
$text = "\n" . $text;
}
} elseif ( !$noargs ) {
if ( $found && !$this->incrementIncludeSize( 'post-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
$text = $linestart .
- '{{' . $part1 . '}}' .
- '<!-- WARNING: template omitted, post-expand include size too large -->';
+ "[[$titleText]]<!-- WARNING: template omitted, post-expand include size too large -->";
$noparse = true;
$noargs = true;
}
} else {
# replace ==section headers==
# XXX this needs to go away once we have a better parser.
- if ( $this->mOutputType != OT_WIKI && $replaceHeadings ) {
+ if ( !$this->ot['wiki'] && !$this->ot['pre'] && $replaceHeadings ) {
if( !is_null( $title ) )
$encodedname = base64_encode($title->getPrefixedDBkey());
else
$m = preg_split('/(^={1,6}.*?={1,6}\s*?$)/m', $text, -1,
PREG_SPLIT_DELIM_CAPTURE);
$text = '';
- $nsec = 0;
+ $nsec = $headingOffset;
for( $i = 0; $i < count($m); $i += 2 ) {
$text .= $m[$i];
if (!isset($m[$i + 1]) || $m[$i + 1] == "") continue;
$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];
if ( array_key_exists( $arg, $inputArgs ) ) {
$text = $inputArgs[$arg];
- } else if ($this->mOutputType == OT_HTML && null != $matches['parts'] && count($matches['parts']) > 0) {
+ } 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 ) ) ) {
# Get all headlines for numbering them and adding funky stuff like [edit]
# links - this is for later, but we need the number of headlines right now
+ $matches = array();
$numMatches = preg_match_all( '/<H([1-6])(.*?'.'>)(.*?)<\/H[1-6] *>/i', $text, $matches );
# if there are fewer than 4 headlines in the article, do not show TOC
$templatetitle = '';
$templatesection = 0;
$numbering = '';
-
+ $mat = array();
if (preg_match("/<!--MWTEMPLATESECTION=([^&]+)&([^_]+)-->/", $headline, $mat)) {
$istemplate = 1;
$templatetitle = base64_decode($mat[1]);
# The canonized header is a version of the header text safe to use for links
# Avoid insertion of weird stuff like <math> by expanding the relevant sections
- $canonized_headline = $this->unstrip( $headline, $this->mStripState );
- $canonized_headline = $this->unstripNoWiki( $canonized_headline, $this->mStripState );
+ $canonized_headline = $this->mStripState->unstripBoth( $headline );
# Remove link placeholders by the link text.
# <!--LINK number-->
$refers[$headlineCount] = $canonized_headline;
# count how many in assoc. array so we can track dupes in anchors
- @$refers[$canonized_headline]++;
+ isset( $refers[$canonized_headline] ) ? $refers[$canonized_headline]++ : $refers[$canonized_headline] = 1;
$refcount[$headlineCount]=$refers[$canonized_headline];
# Don't number the heading if it is the only one (looks silly)
if( $enoughToc && ( !isset($wgMaxTocLevel) || $toclevel<$wgMaxTocLevel ) ) {
$toc .= $sk->tocLine($anchor, $tocline, $numbering, $toclevel);
}
+ # give headline the correct <h#> tag
+ $head[$headlineCount] = "<a name=\"$anchor\"></a><h".$level.$matches[2][$headlineCount];
+
if( $showEditLink && ( !$istemplate || $templatetitle !== "" ) ) {
if ( empty( $head[$headlineCount] ) ) {
$head[$headlineCount] = '';
else
$head[$headlineCount] .= $sk->editSectionLink($this->mTitle, $sectionCount+1, $headline_hint);
}
-
- # give headline the correct <h#> tag
- @$head[$headlineCount] .= "<a name=\"$anchor\"></a><h".$level.$matches[2][$headlineCount] .$headline.'</h'.$level.'>';
+ // Yes, the headline logically goes before the edit section. Why isn't it there
+ // in source? Ask the CSS people. The float gets screwed up if you do that.
+ // This might be moved to before the editsection at some point so that it will
+ // display a bit more prettily without CSS, so please don't rely on the order.
+ $head[$headlineCount] .= ' <span class="mw-headline">'.$headline.'</span></h'.$level.'>';
$headlineCount++;
if( !$istemplate )
* @return string the altered wiki markup
* @public
*/
- function preSaveTransform( $text, &$title, &$user, $options, $clearState = true ) {
+ function preSaveTransform( $text, &$title, $user, $options, $clearState = true ) {
$this->mOptions = $options;
$this->mTitle =& $title;
- $this->mOutputType = OT_WIKI;
+ $this->setOutputType( OT_WIKI );
if ( $clearState ) {
$this->clearState();
}
- $stripState = false;
+ $stripState = new StripState;
$pairs = array(
"\r\n" => "\n",
);
$text = str_replace( array_keys( $pairs ), array_values( $pairs ), $text );
$text = $this->strip( $text, $stripState, true, array( 'gallery' ) );
$text = $this->pstPass2( $text, $stripState, $user );
- $text = $this->unstrip( $text, $stripState );
- $text = $this->unstripNoWiki( $text, $stripState );
+ $text = $stripState->unstripBoth( $text );
return $text;
}
* Pre-save transform helper function
* @private
*/
- function pstPass2( $text, &$stripState, &$user ) {
+ function pstPass2( $text, &$stripState, $user ) {
global $wgContLang, $wgLocaltimezone;
/* Note: This is the timestamp saved as hardcoded wikitext to
#
global $wgLegalTitleChars;
$tc = "[$wgLegalTitleChars]";
+ $nc = '[ _0-9A-Za-z\x80-\xff]'; # Namespaces can use non-ascii!
- $namespacechar = '[ _0-9A-Za-z\x80-\xff]'; # Namespaces can use non-ascii!
- $conpat = "/^{$tc}+?( \\({$tc}+\\)|)$/";
-
- $p1 = "/\[\[(:?$namespacechar+:|:|)({$tc}+?)( \\({$tc}+\\)|)\\|]]/"; # [[ns:page (context)|]]
- $p2 = "/\[\[\\|({$tc}+)]]/"; # [[|page]]
+ $p1 = "/\[\[(:?$nc+:|:|)($tc+?)( \\($tc+\\))\\|]]/"; # [[ns:page (context)|]]
+ $p3 = "/\[\[(:?$nc+:|:|)($tc+?)( \\($tc+\\)|)(, $tc+|)\\|]]/"; # [[ns:page (context), context|]]
+ $p2 = "/\[\[\\|($tc+)]]/"; # [[|page]]
+ # try $p1 first, to turn "[[A, B (C)|]]" into "[[A, B (C)|A, B]]"
$text = preg_replace( $p1, '[[\\1\\2\\3|\\2]]', $text );
+ $text = preg_replace( $p3, '[[\\1\\2\\3\\4|\\2]]', $text );
$t = $this->mTitle->getText();
- if ( preg_match( $conpat, $t, $m ) && '' != $m[1] ) {
- $text = preg_replace( $p2, "[[\\1{$m[1]}|\\1]]", $text );
+ $m = array();
+ if ( preg_match( "/^($nc+:|)$tc+?( \\($tc+\\))$/", $t, $m ) ) {
+ $text = preg_replace( $p2, "[[$m[1]\\1$m[2]|\\1]]", $text );
+ } elseif ( preg_match( "/^($nc+:|)$tc+?(, $tc+|)$/", $t, $m ) && '' != "$m[1]$m[2]" ) {
+ $text = preg_replace( $p2, "[[$m[1]\\1$m[2]|\\1]]", $text );
} else {
- # if $m[1] is empty, don't bother duplicating the title
+ # if there's no context, don't bother duplicating the title
$text = preg_replace( $p2, '[[\\1]]', $text );
}
function startExternalParse( &$title, $options, $outputType, $clearState = true ) {
$this->mTitle =& $title;
$this->mOptions = $options;
- $this->mOutputType = $outputType;
+ $this->setOutputType( $outputType );
if ( $clearState ) {
$this->clearState();
}
wfProfileIn($fname);
- $this->mTitle = $wgTitle;
+ if ( $wgTitle ) {
+ $this->mTitle = $wgTitle;
+ } else {
+ $this->mTitle = Title::newFromText('msg');
+ }
$this->mOptions = $options;
- $this->mOutputType = OT_MSG;
+ $this->setOutputType( OT_MSG );
$this->clearState();
$text = $this->replaceVariables( $text );
*/
function setHook( $tag, $callback ) {
$tag = strtolower( $tag );
- $oldVal = @$this->mTagHooks[$tag];
+ $oldVal = isset( $this->mTagHooks[$tag] ) ? $this->mTagHooks[$tag] : null;
$this->mTagHooks[$tag] = $callback;
return $oldVal;
* The callback function should have the form:
* function myParserFunction( &$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
+ * 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
+ * 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.
*
* @param string $id The magic word ID
* @param mixed $callback The callback function (and object) to use
- * @param integer $flags a combination of the following flags:
+ * @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( $id, $callback, $flags = 0 ) {
- $oldVal = @$this->mFunctionHooks[$id];
+ $oldVal = isset( $this->mFunctionHooks[$id] ) ? $this->mFunctionHooks[$id] : null;
$this->mFunctionHooks[$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.' );
- }
+ if( !$mw )
+ throw new MWException( 'Parser::setFunctionHook() expecting a magic word identifier.' );
$synonyms = $mw->getSynonyms();
$sensitive = intval( $mw->isCaseSensitive() );
return $oldVal;
}
+ /**
+ * Get all registered function hook identifiers
+ *
+ * @return array
+ */
+ function getFunctionHooks() {
+ return array_keys( $this->mFunctionHooks );
+ }
+
/**
* Replace <!--LINK--> link placeholders with actual links, in the buffer
* Placeholders created in Skin::makeLinkObj()
*/
function replaceLinkHolders( &$text, $options = 0 ) {
global $wgUser;
- global $wgOutputReplace;
+ global $wgContLang;
$fname = 'Parser::replaceLinkHolders';
wfProfileIn( $fname );
# Generate query
$query = false;
+ $current = null;
foreach ( $this->mLinkHolders['namespaces'] as $key => $ns ) {
# Make title object
$title = $this->mLinkHolders['titles'][$key];
}
wfProfileOut( $fname.'-check' );
+ # Do a second query for different language variants of links and categories
+ if($wgContLang->hasVariants()){
+ $linkBatch = new LinkBatch();
+ $variantMap = array(); // maps $pdbkey_Variant => $keys (of link holders)
+ $categoryMap = array(); // maps $category_variant => $category (dbkeys)
+ $varCategories = array(); // category replacements oldDBkey => newDBkey
+
+ $categories = $this->mOutput->getCategoryLinks();
+
+ // Add variants of links to link batch
+ foreach ( $this->mLinkHolders['namespaces'] as $key => $ns ) {
+ $title = $this->mLinkHolders['titles'][$key];
+ if ( is_null( $title ) )
+ continue;
+
+ $pdbk = $title->getPrefixedDBkey();
+ $titleText = $title->getText();
+
+ // generate all variants of the link title text
+ $allTextVariants = $wgContLang->convertLinkToAllVariants($titleText);
+
+ // if link was not found (in first query), add all variants to query
+ if ( !isset($colours[$pdbk]) ){
+ foreach($allTextVariants as $textVariant){
+ if($textVariant != $titleText){
+ $variantTitle = Title::makeTitle( $ns, $textVariant );
+ if(is_null($variantTitle)) continue;
+ $linkBatch->addObj( $variantTitle );
+ $variantMap[$variantTitle->getPrefixedDBkey()][] = $key;
+ }
+ }
+ }
+ }
+
+ // process categories, check if a category exists in some variant
+ foreach( $categories as $category){
+ $variants = $wgContLang->convertLinkToAllVariants($category);
+ foreach($variants as $variant){
+ $variantTitle = Title::newFromDBkey( Title::makeName(NS_CATEGORY,$variant) );
+ if(is_null($variantTitle)) continue;
+ $linkBatch->addObj( $variantTitle );
+ $categoryMap[$variant] = $category;
+ }
+ }
+
+
+ if(!$linkBatch->isEmpty()){
+ // construct query
+ $titleClause = $linkBatch->constructSet('page', $dbr);
+
+ $variantQuery = "SELECT page_id, page_namespace, page_title";
+ if ( $threshold > 0 ) {
+ $variantQuery .= ', page_len, page_is_redirect';
+ }
+
+ $variantQuery .= " FROM $page WHERE $titleClause";
+ if ( $options & RLH_FOR_UPDATE ) {
+ $variantQuery .= ' FOR UPDATE';
+ }
+
+ $varRes = $dbr->query( $variantQuery, $fname );
+
+ // for each found variants, figure out link holders and replace
+ while ( $s = $dbr->fetchObject($varRes) ) {
+
+ $variantTitle = Title::makeTitle( $s->page_namespace, $s->page_title );
+ $varPdbk = $variantTitle->getPrefixedDBkey();
+ $vardbk = $variantTitle->getDBkey();
+ $linkCache->addGoodLinkObj( $s->page_id, $variantTitle );
+ $this->mOutput->addLink( $variantTitle, $s->page_id );
+
+ $holderKeys = array();
+ if(isset($variantMap[$varPdbk]))
+ $holderKeys = $variantMap[$varPdbk];
+
+ // loop over link holders
+ foreach($holderKeys as $key){
+ $title = $this->mLinkHolders['titles'][$key];
+ if ( is_null( $title ) ) continue;
+
+ $pdbk = $title->getPrefixedDBkey();
+
+ if(!isset($colours[$pdbk])){
+ // found link in some of the variants, replace the link holder data
+ $this->mLinkHolders['titles'][$key] = $variantTitle;
+ $this->mLinkHolders['dbkeys'][$key] = $variantTitle->getDBkey();
+
+ // set pdbk and colour
+ $pdbks[$key] = $varPdbk;
+ if ( $threshold > 0 ) {
+ $size = $s->page_len;
+ if ( $s->page_is_redirect || $s->page_namespace != 0 || $size >= $threshold ) {
+ $colours[$varPdbk] = 1;
+ } else {
+ $colours[$varPdbk] = 2;
+ }
+ }
+ else {
+ $colours[$varPdbk] = 1;
+ }
+ }
+ }
+
+ // check if the object is a variant of a category
+ if(isset($categoryMap[$vardbk])){
+ $oldkey = $categoryMap[$vardbk];
+ if($oldkey != $vardbk)
+ $varCategories[$oldkey]=$vardbk;
+ }
+ }
+
+ // rebuild the categories in original order (if there are replacements)
+ if(count($varCategories)>0){
+ $newCats = array();
+ $originalCats = $this->mOutput->getCategories();
+ foreach($originalCats as $cat => $sortkey){
+ // make the replacement
+ if( array_key_exists($cat,$varCategories) )
+ $newCats[$varCategories[$cat]] = $sortkey;
+ else $newCats[$cat] = $sortkey;
+ }
+ $this->mOutput->setCategoryLinks($newCats);
+ }
+ }
+ }
+
# Construct search and replace arrays
wfProfileIn( $fname.'-construct' );
- $wgOutputReplace = array();
+ $replacePairs = array();
foreach ( $this->mLinkHolders['namespaces'] as $key => $ns ) {
$pdbk = $pdbks[$key];
$searchkey = "<!--LINK $key-->";
$linkCache->addBadLinkObj( $title );
$colours[$pdbk] = 0;
$this->mOutput->addLink( $title, 0 );
- $wgOutputReplace[$searchkey] = $sk->makeBrokenLinkObj( $title,
+ $replacePairs[$searchkey] = $sk->makeBrokenLinkObj( $title,
$this->mLinkHolders['texts'][$key],
$this->mLinkHolders['queries'][$key] );
} elseif ( $colours[$pdbk] == 1 ) {
- $wgOutputReplace[$searchkey] = $sk->makeKnownLinkObj( $title,
+ $replacePairs[$searchkey] = $sk->makeKnownLinkObj( $title,
$this->mLinkHolders['texts'][$key],
$this->mLinkHolders['queries'][$key] );
} elseif ( $colours[$pdbk] == 2 ) {
- $wgOutputReplace[$searchkey] = $sk->makeStubLinkObj( $title,
+ $replacePairs[$searchkey] = $sk->makeStubLinkObj( $title,
$this->mLinkHolders['texts'][$key],
$this->mLinkHolders['queries'][$key] );
}
}
+ $replacer = new HashtableReplacer( $replacePairs, 1 );
wfProfileOut( $fname.'-construct' );
# Do the thing
wfProfileIn( $fname.'-replace' );
-
$text = preg_replace_callback(
'/(<!--LINK .*?-->)/',
- "wfOutputReplaceMatches",
+ $replacer->cb(),
$text);
wfProfileOut( $fname.'-replace' );
if ( !empty( $this->mInterwikiLinkHolders['texts'] ) ) {
wfProfileIn( $fname.'-interwiki' );
# Make interwiki link HTML
- $wgOutputReplace = array();
+ $replacePairs = array();
foreach( $this->mInterwikiLinkHolders['texts'] as $key => $link ) {
$title = $this->mInterwikiLinkHolders['titles'][$key];
- $wgOutputReplace[$key] = $sk->makeLinkObj( $title, $link );
+ $replacePairs[$key] = $sk->makeLinkObj( $title, $link );
}
+ $replacer = new HashtableReplacer( $replacePairs, 1 );
$text = preg_replace_callback(
'/<!--IWLINK (.*?)-->/',
- "wfOutputReplaceMatches",
+ $replacer->cb(),
$text );
wfProfileOut( $fname.'-interwiki' );
}
/**
* Tag hook handler for 'pre'.
*/
- function renderPreTag( $text, $attribs, $parser ) {
+ function renderPreTag( $text, $attribs ) {
// Backwards-compatibility hack
- $content = preg_replace( '!<nowiki>(.*?)</nowiki>!is', '\\1', $text );
+ $content = StringUtils::delimiterReplace( '<nowiki>', '</nowiki>', '$1', $text, 'i' );
$attribs = Sanitizer::validateTagAttributes( $attribs, 'pre' );
return wfOpenElement( 'pre', $attribs ) .
- wfEscapeHTMLTagsOnly( $content ) .
+ Xml::escapeTagsOnly( $content ) .
'</pre>';
}
foreach ( $lines as $line ) {
# match lines like these:
# Image:someimage.jpg|This is some image
+ $matches = array();
preg_match( "/^([^|]+)(\\|(.*))?$/", $line, $matches );
# Skip empty lines
if ( count( $matches ) == 0 ) {
/**
* Parse image options text and use it to make an image
*/
- function makeImage( &$nt, $options ) {
- global $wgUseImageResize;
+ function makeImage( $nt, $options ) {
+ global $wgUseImageResize, $wgDjvuRenderer;
$align = '';
$mwWidth =& MagicWord::get( 'img_width' );
$mwCenter =& MagicWord::get( 'img_center' );
$mwFramed =& MagicWord::get( 'img_framed' );
+ $mwPage =& MagicWord::get( 'img_page' );
$caption = '';
$width = $height = $framed = $thumb = false;
+ $page = null;
$manual_thumb = '' ;
- foreach( $part as $key => $val ) {
+ foreach( $part as $val ) {
if ( $wgUseImageResize && ! is_null( $mwThumb->matchVariableStartToEnd($val) ) ) {
$thumb=true;
} elseif ( ! is_null( $match = $mwManualThumb->matchVariableStartToEnd($val) ) ) {
} elseif ( ! is_null( $mwNone->matchVariableStartToEnd($val) ) ) {
# remember to set an alignment, don't render immediately
$align = 'none';
+ } elseif ( isset( $wgDjvuRenderer ) && $wgDjvuRenderer
+ && ! is_null( $match = $mwPage->matchVariableStartToEnd($val) ) ) {
+ # Select a page in a multipage document
+ $page = $match;
} elseif ( $wgUseImageResize && ! is_null( $match = $mwWidth->matchVariableStartToEnd($val) ) ) {
wfDebug( "img_width match: $match\n" );
# $match is the image width in pixels
+ $m = array();
if ( preg_match( '/^([0-9]*)x([0-9]*)$/', $match, $m ) ) {
$width = intval( $m[1] );
$height = intval( $m[2] );
# 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 = $this->mStripState->unstripBoth( $alt );
$alt = Sanitizer::stripAllTags( $alt );
# Linker does the rest
$sk =& $this->mOptions->getSkin();
- return $sk->makeImageLinkObj( $nt, $caption, $alt, $align, $width, $height, $framed, $thumb, $manual_thumb );
+ return $sk->makeImageLinkObj( $nt, $caption, $alt, $align, $width, $height, $framed, $thumb, $manual_thumb, $page );
}
/**
*/
function attributeStripCallback( &$text, $args ) {
$text = $this->replaceVariables( $text, $args );
- $text = $this->unstripForHTML( $text );
+ $text = $this->mStripState->unstripBoth( $text );
return $text;
}
- function unstripForHTML( $text ) {
- $text = $this->unstrip( $text, $this->mStripState );
- $text = $this->unstripNoWiki( $text, $this->mStripState );
- return $text;
- }
/**#@-*/
/**#@+
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();
+ $stripState = new StripState;
$oldOutputType = $this->mOutputType;
$oldOptions = $this->mOptions;
$this->mOptions = new ParserOptions();
- $this->mOutputType = OT_WIKI;
+ $this->setOutputType( OT_WIKI );
- $striptext = $this->strip( $text, $striparray, true );
+ $striptext = $this->strip( $text, $stripState, true );
- $this->mOutputType = $oldOutputType;
+ $this->setOutputType( $oldOutputType );
$this->mOptions = $oldOptions;
# now that we can be sure that no pseudo-sections are in the source,
}
}
# reinsert stripped tags
- $rv = $this->unstrip( $rv, $striparray );
- $rv = $this->unstripNoWiki( $rv, $striparray );
- $rv = trim( $rv );
+ $rv = trim( $stripState->unstripBoth( $rv ) );
return $rv;
}
return $this->extractSections( $oldtext, $section, "replace", $text );
}
+ /**
+ * Get the timestamp associated with the current revision, adjusted for
+ * the default server-local timestamp
+ */
+ function getRevisionTimestamp() {
+ if ( is_null( $this->mRevisionTimestamp ) ) {
+ wfProfileIn( __METHOD__ );
+ global $wgContLang;
+ $dbr =& wfGetDB( DB_SLAVE );
+ $timestamp = $dbr->selectField( 'revision', 'rev_timestamp',
+ array( 'rev_id' => $this->mRevisionId ), __METHOD__ );
+
+ // Normalize timestamp to internal MW format for timezone processing.
+ // This has the added side-effect of replacing a null value with
+ // the current time, which gives us more sensible behavior for
+ // previews.
+ $timestamp = wfTimestamp( TS_MW, $timestamp );
+
+ // The cryptic '' timezone parameter tells to use the site-default
+ // timezone offset instead of the user settings.
+ //
+ // Since this value will be saved into the parser cache, served
+ // to other users, and potentially even used inside links and such,
+ // it needs to be consistent for all visitors.
+ $this->mRevisionTimestamp = $wgContLang->userAdjust( $timestamp, '' );
+
+ wfProfileOut( __METHOD__ );
+ }
+ return $this->mRevisionTimestamp;
+ }
}
/**
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;
}
return (bool)$this->mNewSection;
}
- function addLink( $title, $id ) {
+ function addLink( $title, $id = null ) {
$ns = $title->getNamespace();
$dbk = $title->getDBkey();
if ( !isset( $this->mLinks[$ns] ) ) {
$this->mLinks[$ns] = array();
}
+ if ( is_null( $id ) ) {
+ $id = $title->getArticleID();
+ }
$this->mLinks[$ns][$dbk] = $id;
}
*/
class ParserOptions
{
- # All variables are private
+ # All variables are supposed to be private in theory, although in practise this is not the case.
var $mUseTeX; # Use texvc to expand <math> tags
var $mUseDynamicDates; # Use DateFormatter to format dates
var $mInterwikiMagic; # Interlanguage links are removed and returned in an array
var $mTidy; # Ask for tidy cleanup
var $mInterfaceMessage; # Which lang to call for PLURAL and GRAMMAR
var $mMaxIncludeSize; # Maximum size of template expansions, in bytes
+ var $mRemoveComments; # Remove HTML comments. ONLY APPLIES TO PREPROCESS OPERATIONS
var $mUser; # Stored user object, just used to initialise the skin
function getTidy() { return $this->mTidy; }
function getInterfaceMessage() { return $this->mInterfaceMessage; }
function getMaxIncludeSize() { return $this->mMaxIncludeSize; }
+ function getRemoveComments() { return $this->mRemoveComments; }
function &getSkin() {
if ( !isset( $this->mSkin ) ) {
return $this->mSkin;
}
- function getDateFormat() {
+ function getDateFormat() {
if ( !isset( $this->mDateFormat ) ) {
$this->mDateFormat = $this->mUser->getDatePreference();
}
function setNumberHeadings( $x ) { return wfSetVar( $this->mNumberHeadings, $x ); }
function setAllowSpecialInclusion( $x ) { return wfSetVar( $this->mAllowSpecialInclusion, $x ); }
function setTidy( $x ) { return wfSetVar( $this->mTidy, $x); }
- function setSkin( &$x ) { $this->mSkin =& $x; }
+ function setSkin( $x ) { $this->mSkin = $x; }
function setInterfaceMessage( $x ) { return wfSetVar( $this->mInterfaceMessage, $x); }
function setMaxIncludeSize( $x ) { return wfSetVar( $this->mMaxIncludeSize, $x ); }
+ function setRemoveComments( $x ) { return wfSetVar( $this->mRemoveComments, $x ); }
function ParserOptions( $user = null ) {
$this->initialiseFromUser( $user );
$user = $wgUser;
} else {
$user = new User;
- $user->setLoaded( true );
}
} else {
$user =& $userInput;
$this->mTidy = false;
$this->mInterfaceMessage = false;
$this->mMaxIncludeSize = $wgMaxArticleSize * 1024;
+ $this->mRemoveComments = true;
wfProfileOut( $fname );
}
}
-/**
- * Callback function used by Parser::replaceLinkHolders()
- * to substitute link placeholders.
- */
-function &wfOutputReplaceMatches( $matches ) {
- global $wgOutputReplace;
- return $wgOutputReplace[$matches[1]];
-}
-
-/**
- * Return the total number of articles
- */
-function wfNumberOfArticles() {
- global $wgNumberOfArticles;
-
- wfLoadSiteStats();
- return $wgNumberOfArticles;
-}
+class OnlyIncludeReplacer {
+ var $output = '';
-/**
- * Return the number of files
- */
-function wfNumberOfFiles() {
- $fname = 'wfNumberOfFiles';
-
- wfProfileIn( $fname );
- $dbr =& wfGetDB( DB_SLAVE );
- $numImages = $dbr->selectField('site_stats', 'ss_images', array(), $fname );
- wfProfileOut( $fname );
-
- 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;
+ function replace( $matches ) {
+ if ( substr( $matches[1], -1 ) == "\n" ) {
+ $this->output .= substr( $matches[1], 0, -1 );
+ } else {
+ $this->output .= $matches[1];
+ }
+ }
}
-/**
- * Return the total number of pages
- * @return integer
- */
-function wfNumberOfPages() {
- wfProfileIn( 'wfNumberOfPages' );
- $dbr =& wfGetDB( DB_SLAVE );
- $count = $dbr->selectField( 'site_stats', 'ss_total_pages', array(), 'wfNumberOfPages' );
- wfProfileOut( 'wfNumberOfPages' );
- return (int)$count;
-}
+class StripState {
+ var $general, $nowiki;
-/**
- * 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' );
+ function __construct() {
+ $this->general = new ReplacementArray;
+ $this->nowiki = new ReplacementArray;
}
- wfProfileOut( 'wfNumberOfAdmins' );
- return (int)$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' );
+ function unstripGeneral( $text ) {
+ wfProfileIn( __METHOD__ );
+ $text = $this->general->replace( $text );
+ wfProfileOut( __METHOD__ );
+ return $text;
}
- wfProfileOut( 'wfPagesInNs' );
- return (int)$pageCount[$ns];
-}
-/**
- * Get various statistics from the database
- * @private
- */
-function wfLoadSiteStats() {
- global $wgNumberOfArticles, $wgTotalViews, $wgTotalEdits;
- $fname = 'wfLoadSiteStats';
-
- if ( -1 != $wgNumberOfArticles ) return;
- $dbr =& wfGetDB( DB_SLAVE );
- $s = $dbr->selectRow( 'site_stats',
- array( 'ss_total_views', 'ss_total_edits', 'ss_good_articles' ),
- array( 'ss_row_id' => 1 ), $fname
- );
-
- if ( $s === false ) {
- return;
- } else {
- $wgTotalViews = $s->ss_total_views;
- $wgTotalEdits = $s->ss_total_edits;
- $wgNumberOfArticles = $s->ss_good_articles;
+ function unstripNoWiki( $text ) {
+ wfProfileIn( __METHOD__ );
+ $text = $this->nowiki->replace( $text );
+ wfProfileOut( __METHOD__ );
+ return $text;
}
-}
-/**
- * Escape html tags
- * Basically replacing " > and < with HTML entities ( ", >, <)
- *
- * @param $in String: text that might contain HTML tags.
- * @return string Escaped string
- */
-function wfEscapeHTMLTagsOnly( $in ) {
- return str_replace(
- array( '"', '>', '<' ),
- array( '"', '>', '<' ),
- $in );
+ function unstripBoth( $text ) {
+ wfProfileIn( __METHOD__ );
+ $text = $this->general->replace( $text );
+ $text = $this->nowiki->replace( $text );
+ wfProfileOut( __METHOD__ );
+ return $text;
+ }
}
?>