* File for Parser and related classes
*
* @package MediaWiki
+ * @subpackage Parser
*/
/** */
require_once( 'Sanitizer.php' );
+require_once( 'HttpFunctions.php' );
/**
* Update this version number when the ParserOutput format
define( 'UNIQ_PREFIX', 'NaodW29');
# Constants needed for external link processing
-define( 'URL_PROTOCOLS', 'http|https|ftp|irc|gopher|news|mailto' );
-define( 'HTTP_PROTOCOLS', 'http|https' );
+define( 'URL_PROTOCOLS', 'http:\/\/|https:\/\/|ftp:\/\/|irc:\/\/|gopher:\/\/|news:|mailto:' );
+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]' );
define( 'EXT_IMAGE_FNAME_CLASS', '[A-Za-z0-9_.,~%\\-+&;#*?!=()@\\x80-\\xFF]' );
define( 'EXT_IMAGE_EXTENSIONS', 'gif|png|jpg|jpeg' );
-define( 'EXT_LINK_BRACKETED', '/\[(\b('.URL_PROTOCOLS.'):'.EXT_LINK_URL_CLASS.'+) *('.EXT_LINK_TEXT_CLASS.'*?)\]/S' );
+define( 'EXT_LINK_BRACKETED', '/\[(\b('.URL_PROTOCOLS.')'.EXT_LINK_URL_CLASS.'+) *('.EXT_LINK_TEXT_CLASS.'*?)\]/S' );
define( 'EXT_IMAGE_REGEX',
- '/^('.HTTP_PROTOCOLS.':)'. # Protocol
+ '/^('.HTTP_PROTOCOLS.')'. # Protocol
'('.EXT_LINK_URL_CLASS.'+)\\/'. # Hostname and path
'('.EXT_IMAGE_FNAME_CLASS.'+)\\.((?i)'.EXT_IMAGE_EXTENSIONS.')$/S' # Filename
);
/**
* PHP Parser
- *
+ *
* Processes wiki markup
*
* <pre>
* performs brace substitution on MediaWiki messages
*
* Globals used:
- * objects: $wgLang, $wgDateFormatter, $wgLinkCache
+ * objects: $wgLang, $wgLinkCache
*
* NOT $wgArticle, $wgUser or $wgTitle. Keep them away!
*
* settings:
* $wgUseTex*, $wgUseDynamicDates*, $wgInterwikiMagic*,
* $wgNamespacesWithSubpages, $wgAllowExternalImages*,
- * $wgLocaltimezone
+ * $wgLocaltimezone, $wgAllowSpecialInclusion*
*
* * only within ParserOptions
* </pre>
# Cleared with clearState():
var $mOutput, $mAutonumber, $mDTopen, $mStripState = array();
var $mVariables, $mIncludeCount, $mArgStack, $mLastSection, $mInPre;
+ var $mInterwikiLinkHolders, $mLinkHolders;
# Temporary:
var $mOptions, $mTitle, $mOutputType,
$mTemplatePath; // stores an unsorted hash of all the templates already loaded
// in this path. Used for loop detection.
+ var $mIWTransData = array();
+
/**#@-*/
/**
* Constructor
- *
+ *
* @access public
*/
function Parser() {
+ global $wgContLang;
$this->mTemplates = array();
$this->mTemplatePath = array();
$this->mTagHooks = array();
$this->mStripState = array();
$this->mArgStack = array();
$this->mInPre = false;
+ $this->mInterwikiLinkHolders = array(
+ 'texts' => array(),
+ 'titles' => array()
+ );
+ $this->mLinkHolders = array(
+ 'namespaces' => array(),
+ 'dbkeys' => array(),
+ 'queries' => array(),
+ 'texts' => array(),
+ 'titles' => array()
+ );
}
/**
$this->mTitle =& $title;
$this->mOutputType = OT_HTML;
- $stripState = NULL;
- global $fnord; $fnord = 1;
+ $this->mStripState = NULL;
+
//$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 ) );
- $text = $this->internalParse( $text, $linestart );
+ $text = $this->internalParse( $text );
- $dashReplace = array(
- '/ - /' => " – ", # N dash
- '/(?<=[0-9])-(?=[0-9])/' => "–", # N dash between numbers
- '/ -- /' => " — " # M dash
- );
- $text = preg_replace( array_keys($dashReplace), array_values($dashReplace), $text );
-
-
$text = $this->unstrip( $text, $this->mStripState );
+
# Clean up special characters, only run once, next-to-last before doBlockLevels
- global $wgUseTidy;
- if(!$wgUseTidy) {
- $fixtags = array(
- # french spaces, last one Guillemet-left
- # only if there is something before the space
- '/(.) (?=\\?|:|;|!|\\302\\273)/' => '\\1 \\2',
- # french spaces, Guillemet-right
- '/(\\302\\253) /' => '\\1 ',
- '/<hr *>/i' => '<hr />',
- '/<br *>/i' => '<br />',
- '/<center *>/i' => '<div class="center">',
- '/<\\/center *>/i' => '</div>',
- );
- $text = preg_replace( array_keys($fixtags), array_values($fixtags), $text );
- $text = Sanitizer::normalizeCharReferences( $text );
- } else {
- $fixtags = array(
- # french spaces, last one Guillemet-left
- '/ (\\?|:|;|!|\\302\\273)/' => ' \\1',
- # french spaces, Guillemet-right
- '/(\\302\\253) /' => '\\1 ',
- '/<center *>/i' => '<div class="center">',
- '/<\\/center *>/i' => '</div>'
- );
- $text = preg_replace( array_keys($fixtags), array_values($fixtags), $text );
- }
+ $fixtags = array(
+ # french spaces, last one Guillemet-left
+ # only if there is something before the space
+ '/(.) (?=\\?|:|;|!|\\302\\273)/' => '\\1 \\2',
+ # french spaces, Guillemet-right
+ '/(\\302\\253) /' => '\\1 ',
+ '/<center *>/i' => '<div class="center">',
+ '/<\\/center *>/i' => '</div>',
+ );
+ $text = preg_replace( array_keys($fixtags), array_values($fixtags), $text );
+
# only once and last
$text = $this->doBlockLevels( $text, $linestart );
$this->replaceLinkHolders( $text );
+
+ # the position of the convert() call should not be changed. it
+ # assumes that the links are all replaces and the only thing left
+ # is the <nowiki> mark.
$text = $wgContLang->convert($text);
+ $this->mOutput->setTitleText($wgContLang->getParsedTitle());
$text = $this->unstripNoWiki( $text, $this->mStripState );
+
+ wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
+
+ $text = Sanitizer::normalizeCharReferences( $text );
+ global $wgUseTidy;
if ($wgUseTidy) {
$text = Parser::tidy($text);
}
+ wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
+
$this->mOutput->setText( $text );
wfProfileOut( $fname );
return $this->mOutput;
return dechex(mt_rand(0, 0x7fffffff)) . dechex(mt_rand(0, 0x7fffffff));
}
- /**
+ /**
* Replaces all occurrences of <$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.
- *
+ *
* If $content is already set, the additional entries will be appended
* If $tag is set to STRIP_COMMENTS, the function will extract
* <!-- HTML comments -->
* @access private
* @static
*/
- function extractTags($tag, $text, &$content, $uniq_prefix = ''){
+ function extractTagsAndParams($tag, $text, &$content, &$tags, &$params, $uniq_prefix = ''){
$rnd = $uniq_prefix . '-' . $tag . Parser::getRandomString();
if ( !$content ) {
$content = array( );
$n = 1;
$stripped = '';
+ if ( !$tags ) {
+ $tags = array( );
+ }
+
+ if ( !$params ) {
+ $params = array( );
+ }
+
+ if( $tag == STRIP_COMMENTS ) {
+ $start = '/<!--()/';
+ $end = '/-->/';
+ } else {
+ $start = "/<$tag(\\s+[^>]*|\\s*)>/i";
+ $end = "/<\\/$tag\\s*>/i";
+ }
+
while ( '' != $text ) {
- if($tag==STRIP_COMMENTS) {
- $p = preg_split( '/<!--/', $text, 2 );
- } else {
- $p = preg_split( "/<\\s*$tag\\s*>/i", $text, 2 );
- }
+ $p = preg_split( $start, $text, 2, PREG_SPLIT_DELIM_CAPTURE );
$stripped .= $p[0];
- if ( ( count( $p ) < 2 ) || ( '' == $p[1] ) ) {
- $text = '';
+ if( count( $p ) < 3 ) {
+ break;
+ }
+ $attributes = $p[1];
+ $inside = $p[2];
+
+ $marker = $rnd . sprintf('%08X', $n++);
+ $stripped .= $marker;
+
+ $tags[$marker] = "<$tag$attributes>";
+ $params[$marker] = Sanitizer::decodeTagAttributes( $attributes );
+
+ $q = preg_split( $end, $inside, 2 );
+ $content[$marker] = $q[0];
+ if( count( $q ) < 1 ) {
+ # No end tag -- let it run out to the end of the text.
+ break;
} else {
- if($tag==STRIP_COMMENTS) {
- $q = preg_split( '/-->/i', $p[1], 2 );
- } else {
- $q = preg_split( "/<\\/\\s*$tag\\s*>/i", $p[1], 2 );
- }
- $marker = $rnd . sprintf('%08X', $n++);
- $content[$marker] = $q[0];
- $stripped .= $marker;
$text = $q[1];
}
}
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>
+ *
+ * @access 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
$pre_content = array();
$comment_content = array();
$ext_content = array();
+ $ext_tags = array();
+ $ext_params = array();
$gallery_content = array();
# Replace any instances of the placeholders
#$text = str_replace( $uniq_prefix, wfHtmlEscapeFirst( $uniq_prefix ), $text );
# html
- global $wgRawHtml, $wgWhitelistEdit;
- if( $wgRawHtml && $wgWhitelistEdit ) {
+ global $wgRawHtml;
+ if( $wgRawHtml ) {
$text = Parser::extractTags('html', $text, $html_content, $uniq_prefix);
foreach( $html_content as $marker => $content ) {
if ($render ) {
# Extensions
foreach ( $this->mTagHooks as $tag => $callback ) {
- $ext_contents[$tag] = array();
- $text = Parser::extractTags( $tag, $text, $ext_content[$tag], $uniq_prefix );
+ $ext_content[$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] = $callback( $content );
+ $ext_content[$tag][$marker] = $callback( $content, $params );
} else {
- $ext_content[$tag][$marker] = "<$tag>$content</$tag>";
+ $ext_content[$tag][$marker] = "$full_tag$content</$tag>";
}
}
}
'html' => array(),
'nowiki' => array(),
'math' => array(),
- 'pre' => array()
+ 'pre' => array(),
+ 'comment' => array(),
+ 'gallery' => array(),
);
}
$state['item'][$rnd] = $text;
}
/**
- * interface with html tidy, used if $wgUseTidy = true
+ * Interface with html tidy, used if $wgUseTidy = true.
+ * If tidy isn't able to correct the markup, the original will be
+ * returned in all its glory with a warning comment appended.
*
+ * Either the external tidy program or the in-process tidy extension
+ * will be used depending on availability. Override the default
+ * $wgTidyInternal setting to disable the internal if it's not working.
+ *
+ * @param string $text Hideous HTML input
+ * @return string Corrected HTML output
* @access public
* @static
*/
- function tidy ( $text ) {
+ function tidy( $text ) {
+ global $wgTidyInternal;
+ $wrappedtext = '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'.
+' "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"><html>'.
+'<head><title>test</title></head><body>'.$text.'</body></html>';
+ if( $wgTidyInternal ) {
+ $correctedtext = Parser::internalTidy( $wrappedtext );
+ } else {
+ $correctedtext = Parser::externalTidy( $wrappedtext );
+ }
+ if( is_null( $correctedtext ) ) {
+ wfDebug( "Tidy error detected!\n" );
+ return $text . "\n<!-- Tidy found serious XHTML errors -->\n";
+ }
+ return $correctedtext;
+ }
+
+ /**
+ * Spawn an external HTML tidy process and get corrected markup back from it.
+ *
+ * @access private
+ * @static
+ */
+ function externalTidy( $text ) {
global $wgTidyConf, $wgTidyBin, $wgTidyOpts;
- global $wgInputEncoding, $wgOutputEncoding;
- $fname = 'Parser::tidy';
+ $fname = 'Parser::externalTidy';
wfProfileIn( $fname );
$cleansource = '';
- $opts = '';
- switch(strtoupper($wgOutputEncoding)) {
- case 'ISO-8859-1':
- $opts .= ($wgInputEncoding == $wgOutputEncoding)? ' -latin1':' -raw';
- break;
- case 'UTF-8':
- $opts .= ($wgInputEncoding == $wgOutputEncoding)? ' -utf8':' -raw';
- break;
- default:
- $opts .= ' -raw';
- }
+ $opts = ' -utf8';
- $wrappedtext = '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'.
-' "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"><html>'.
-'<head><title>test</title></head><body>'.$text.'</body></html>';
$descriptorspec = array(
0 => array('pipe', 'r'),
1 => array('pipe', 'w'),
2 => array('file', '/dev/null', 'a')
);
+ $pipes = array();
$process = proc_open("$wgTidyBin -config $wgTidyConf $wgTidyOpts$opts", $descriptorspec, $pipes);
if (is_resource($process)) {
- fwrite($pipes[0], $wrappedtext);
+ fwrite($pipes[0], $text);
fclose($pipes[0]);
while (!feof($pipes[1])) {
$cleansource .= fgets($pipes[1], 1024);
}
fclose($pipes[1]);
- $return_value = proc_close($process);
+ proc_close($process);
}
wfProfileOut( $fname );
if( $cleansource == '' && $text != '') {
- wfDebug( "Tidy error detected!\n" );
- return $text . "\n<!-- Tidy found serious XHTML errors -->\n";
+ // Some kind of error happened, so we couldn't get the corrected text.
+ // Just give up; we'll use the source text and append a warning.
+ return null;
} else {
return $cleansource;
}
}
+ /**
+ * Use the HTML tidy PECL extension to use the tidy library in-process,
+ * saving the overhead of spawning a new process. Currently written to
+ * the PHP 4.3.x version of the extension, may not work on PHP 5.
+ *
+ * 'pear install tidy' should be able to compile the extension module.
+ *
+ * @access private
+ * @static
+ */
+ function internalTidy( $text ) {
+ global $wgTidyConf;
+ $fname = 'Parser::internalTidy';
+ wfProfileIn( $fname );
+
+ tidy_load_config( $wgTidyConf );
+ tidy_set_encoding( 'utf8' );
+ tidy_parse_string( $text );
+ tidy_clean_repair();
+ if( tidy_get_status() == 2 ) {
+ // 2 is magic number for fatal error
+ // http://www.php.net/manual/en/function.tidy-get-status.php
+ $cleansource = null;
+ } else {
+ $cleansource = tidy_get_output();
+ }
+ wfProfileOut( $fname );
+ return $cleansource;
+ }
+
/**
* parse the wiki syntax used to render tables
*
$fc = substr ( $x , 0 , 1 ) ;
if ( preg_match( '/^(:*)\{\|(.*)$/', $x, $matches ) ) {
$indent_level = strlen( $matches[1] );
- $t[$k] = "\n" .
- str_repeat( '<dl><dd>', $indent_level ) .
+ $t[$k] = str_repeat( '<dl><dd>', $indent_level ) .
'<table' . Sanitizer::fixTagAttributes ( $matches[2], 'table' ) . '>' ;
array_push ( $td , false ) ;
array_push ( $ltd , '' ) ;
}
else if ( count ( $td ) == 0 ) { } # Don't do any of the following
else if ( '|}' == substr ( $x , 0 , 2 ) ) {
- $z = "</table>" . substr ( $x , 2) . "\n";
+ $z = "</table>" . substr ( $x , 2);
$l = array_pop ( $ltd ) ;
if ( array_pop ( $tr ) ) $z = '</tr>' . $z ;
if ( array_pop ( $td ) ) $z = '</'.$l.'>' . $z ;
}
$t = implode ( "\n" , $t ) ;
- # $t = Sanitizer::removeHTMLtags( $t );
wfProfileOut( $fname );
return $t ;
}
*
* @access private
*/
- function internalParse( $text, $linestart, $args = array(), $isMain=true ) {
+ function internalParse( $text ) {
global $wgContLang;
-
+ $args = array();
+ $isMain = true;
$fname = 'Parser::internalParse';
wfProfileIn( $fname );
- $text = Sanitizer::removeHTMLtags( $text );
+ $text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ) );
$text = $this->replaceVariables( $text, $args );
$text = preg_replace( '/(^|\n)-----*/', '\\1<hr />', $text );
$text = $this->doHeadings( $text );
if($this->mOptions->getUseDynamicDates()) {
- global $wgDateFormatter;
- $text = $wgDateFormatter->reformat( $this->mOptions->getDateFormat(), $text );
+ $df =& DateFormatter::getInstance();
+ $text = $df->reformat( $this->mOptions->getDateFormat(), $text );
}
$text = $this->doAllQuotes( $text );
$text = $this->replaceInternalLinks( $text );
- $text = $this->replaceExternalLinks( $text );
-
+ $text = $this->replaceExternalLinks( $text );
+
# replaceInternalLinks may sometimes leave behind
# absolute URLs, which have to be masked to hide them from replaceExternalLinks
$text = str_replace("http-noparse://","http://",$text);
-
+
$text = $this->doMagicLinks( $text );
$text = $this->doTableStuff( $text );
$text = $this->formatHeadings( $text, $isMain );
+ $regex = '/<!--IW_TRANSCLUDE (\d+)-->/';
+ $text = preg_replace_callback($regex, array(&$this, 'scarySubstitution'), $text);
+
wfProfileOut( $fname );
return $text;
}
+ function scarySubstitution($matches) {
+# return "[[".$matches[0]."]]";
+ return $this->mIWTransData[(int)$matches[0]];
+ }
+
/**
* Replace special strings like "ISBN xxx" and "RFC xxx" with
* magic external links.
* @access private
*/
function replaceExternalLinks( $text ) {
+ global $wgContLang;
$fname = 'Parser::replaceExternalLinks';
wfProfileIn( $fname );
$sk =& $this->mOptions->getSkin();
- global $wgContLang;
- $linktrail = $wgContLang->linkTrail();
-
+
$bits = preg_split( EXT_LINK_BRACKETED, $text, -1, PREG_SPLIT_DELIM_CAPTURE );
$s = $this->replaceFreeExternalLinks( array_shift( $bits ) );
# If the link text is an image URL, replace it with an <img> tag
# This happened by accident in the original parser, but some people used it extensively
- $img = $this->maybeMakeImageLink( $text );
+ $img = $this->maybeMakeExternalImage( $text );
if ( $img !== false ) {
$text = $img;
}
# No link text, e.g. [http://domain.tld/some.link]
if ( $text == '' ) {
# Autonumber if allowed
- if ( strpos( HTTP_PROTOCOLS, $protocol ) !== false ) {
+ if ( strpos( HTTP_PROTOCOLS, str_replace('/','\/', $protocol) ) !== false ) {
$text = '[' . ++$this->mAutonumber . ']';
$linktype = 'autonumber';
} else {
} else {
# Have link text, e.g. [http://domain.tld/some.link text]s
# Check for trail
- if ( preg_match( $linktrail, $trail, $m2 ) ) {
- $dtrail = $m2[1];
- $trail = $m2[2];
- }
+ list( $dtrail, $trail ) = Linker::splitTrail( $trail );
}
+ $text = $wgContLang->markNoConversion($text);
+
# Replace & from obsolete syntax with &.
# All HTML entities will be escaped by makeExternalLink()
- # or maybeMakeImageLink()
+ # or maybeMakeExternalImage()
$url = str_replace( '&', '&', $url );
# Process the trail (i.e. everything after this link up until start of the next link),
# replacing any non-bracketed links
$trail = $this->replaceFreeExternalLinks( $trail );
+
# Use the encoded URL
# This means that users can paste URLs directly into the text
# Funny characters like ö aren't valid in URLs anyway
* @access private
*/
function replaceFreeExternalLinks( $text ) {
+ global $wgContLang;
$fname = 'Parser::replaceFreeExternalLinks';
wfProfileIn( $fname );
-
- $bits = preg_split( '/(\b(?:'.URL_PROTOCOLS.'):)/S', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
+
+ $bits = preg_split( '/(\b(?:'.URL_PROTOCOLS.'))/S', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
$s = array_shift( $bits );
$i = 0;
# Replace & from obsolete syntax with &.
# All HTML entities will be escaped by makeExternalLink()
- # or maybeMakeImageLink()
+ # or maybeMakeExternalImage()
$url = str_replace( '&', '&', $url );
# Is this an external image?
- $text = $this->maybeMakeImageLink( $url );
+ $text = $this->maybeMakeExternalImage( $url );
if ( $text === false ) {
# Not an image, make a link
- $text = $sk->makeExternalLink( $url, $url, true, 'free' );
+ $text = $sk->makeExternalLink( $url, $wgContLang->markNoConversion($url), true, 'free' );
}
$s .= $text . $trail;
} else {
* make an image if it's allowed
* @access private
*/
- function maybeMakeImageLink( $url ) {
+ function maybeMakeExternalImage( $url ) {
$sk =& $this->mOptions->getSkin();
$text = false;
if ( $this->mOptions->getAllowExternalImages() ) {
if ( preg_match( EXT_IMAGE_REGEX, $url ) ) {
# Image found
- $text = $sk->makeImage( htmlspecialchars( $url ) );
+ $text = $sk->makeExternalImage( htmlspecialchars( $url ) );
}
}
return $text;
}
-
+
/**
* Process [[ ]] wikilinks
*
* @access private
*/
function replaceInternalLinks( $s ) {
- global $wgLang, $wgContLang, $wgLinkCache;
- global $wgDisableLangConversion;
+ global $wgContLang, $wgLinkCache;
static $fname = 'Parser::replaceInternalLinks' ;
wfProfileIn( $fname );
static $tc = FALSE;
# the % is needed to support urlencoded titles as well
if ( !$tc ) { $tc = Title::legalChars() . '#%'; }
-
- $sk =& $this->mOptions->getSkin();
- global $wgUseOldExistenceCheck;
- # "Post-parse link colour check" works only on wiki text since it's now
- # in Parser. Enable it, then disable it when we're done.
- $saveParseColour = $sk->postParseLinkColour( !$wgUseOldExistenceCheck );
- $redirect = MagicWord::get ( MAG_REDIRECT ) ;
+ $sk =& $this->mOptions->getSkin();
#split the entire text string on occurences of [[
$a = explode( '[[', ' ' . $s );
$checkVariantLink = sizeof($wgContLang->getVariants())>1;
$useSubpages = $this->areSubpagesAllowed();
-
+
# Loop for each link
for ($k = 0; isset( $a[$k] ); $k++) {
$line = $a[$k];
}
$might_be_img = false;
-
+
if ( preg_match( $e1, $line, $m ) ) { # page with normal text or alt
$text = $m[2];
+ # If we get a ] at the beginning of $m[3] that means we have a link that's something like:
+ # [[Image:Foo.jpg|[http://example.com desc]]] <- having three ] in a row fucks up,
+ # the real problem is with the $e1 regex
+ # See bug 1300.
+ #
+ # Still some problems for cases where the ] is meant to be outside punctuation,
+ # and no image is in sight. See bug 2095.
+ #
+ if( $text !== '' && preg_match( "/^\](.*)/s", $m[3], $n ) ) {
+ $text .= ']'; # so that replaceExternalLinks($text) works later
+ $m[3] = $n[1];
+ }
# fix up urlencoded title texts
if(preg_match('/%/', $m[1] )) $m[1] = urldecode($m[1]);
$trail = $m[3];
# Don't allow internal links to pages containing
# PROTO: where PROTO is a valid URL protocol; these
# should be external links.
- if (preg_match('/^(\b(?:'.URL_PROTOCOLS.'):)/', $m[1])) {
+ if (preg_match('/^(\b(?:'.URL_PROTOCOLS.'))/', $m[1])) {
$s .= $prefix . '[[' . $line ;
continue;
}
# Strip off leading ':'
$link = substr($link, 1);
}
-
+
$nt =& Title::newFromText( $this->unstripNoWiki($link, $this->mStripState) );
if( !$nt ) {
$s .= $prefix . '[[' . $line;
$ns = $nt->getNamespace();
$iw = $nt->getInterWiki();
-
+
if ($might_be_img) { # if this is actually an invalid link
if ($ns == NS_IMAGE && $noforce) { #but might be an image
$found = false;
$wasblank = ( '' == $text );
if( $wasblank ) $text = $link;
-
+
# Link not escaped by : , create the various objects
if( $noforce ) {
# Interwikis
if( $iw && $this->mOptions->getInterwikiMagic() && $nottalk && $wgContLang->getLanguageName( $iw ) ) {
array_push( $this->mOutput->mLanguageLinks, $nt->getFullText() );
- $tmp = $prefix . $trail ;
- $s .= (trim($tmp) == '')? '': $tmp;
+ $s = rtrim($s . "\n");
+ $s .= trim($prefix . $trail, "\n") == '' ? '': $prefix . $trail;
continue;
}
-
+
if ( $ns == NS_IMAGE ) {
wfProfileIn( "$fname-image" );
-
- # 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
- $text = $this->replaceExternalLinks($text);
- $text = $this->replaceInternalLinks($text);
-
- # cloak any absolute URLs inside the image markup, so replaceExternalLinks() won't touch them
- $s .= $prefix . str_replace('http://', 'http-noparse://', $sk->makeImageLinkObj( $nt, $text ) ) . $trail;
- $wgLinkCache->addImageLinkObj( $nt );
-
+ if ( !wfIsBadImage( $nt->getDBkey() ) ) {
+ # 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
+ $text = $this->replaceExternalLinks($text);
+ $text = $this->replaceInternalLinks($text);
+
+ # cloak any absolute URLs inside the image markup, so replaceExternalLinks() won't touch them
+ $s .= $prefix . str_replace('http://', 'http-noparse://', $this->makeImage( $nt, $text ) ) . $trail;
+ $wgLinkCache->addImageLinkObj( $nt );
+
+ wfProfileOut( "$fname-image" );
+ continue;
+ }
wfProfileOut( "$fname-image" );
- continue;
+
}
-
+
if ( $ns == NS_CATEGORY ) {
wfProfileIn( "$fname-category" );
- $t = $nt->getText();
+ $t = $wgContLang->convertHtml( $nt->getText() );
+ $s = rtrim($s . "\n"); # bug 87
$wgLinkCache->suspend(); # Don't save in links/brokenlinks
- $pPLC=$sk->postParseLinkColour();
- $sk->postParseLinkColour( false );
$t = $sk->makeLinkObj( $nt, $t, '', '' , $prefix );
- $sk->postParseLinkColour( $pPLC );
$wgLinkCache->resume();
if ( $wasblank ) {
} else {
$sortkey = $text;
}
+ $sortkey = $wgContLang->convertCategoryKey( $sortkey );
$wgLinkCache->addCategoryLinkObj( $nt, $sortkey );
$this->mOutput->addCategoryLink( $t );
- $s .= $prefix . $trail ;
-
+
+ /**
+ * Strip the whitespace Category links produce, see bug 87
+ * @todo We might want to use trim($tmp, "\n") here.
+ */
+ $s .= trim($prefix . $trail, "\n") == '' ? '': $prefix . $trail;
+
wfProfileOut( "$fname-category" );
continue;
}
$s .= $prefix . $sk->makeKnownLinkObj( $nt, $text, '', $trail );
continue;
}
- $s .= $sk->makeLinkObj( $nt, $text, '', $trail, $prefix );
+ if( !$nt->isExternal() && $nt->isAlwaysKnown() ) {
+ /**
+ * Skip lookups for special pages and self-links.
+ * External interwiki links are not included here because
+ * the HTTP urls would break output in the next parse step;
+ * they will have placeholders kept.
+ */
+ $s .= $sk->makeKnownLinkObj( $nt, $text, '', $trail, $prefix );
+ } else {
+ /**
+ * Add a link placeholder
+ * Later, this will be replaced by a real link, after the existence or
+ * non-existence of all the links is known
+ */
+ $s .= $this->makeLinkHolder( $nt, $text, '', $trail, $prefix );
+ }
}
- $sk->postParseLinkColour( $saveParseColour );
wfProfileOut( $fname );
return $s;
}
+ /**
+ * Make a link placeholder. The text returned can be later resolved to a real link with
+ * replaceLinkHolders(). This is done for two reasons: firstly to avoid further
+ * parsing of interwiki links, and secondly to allow all extistence checks and
+ * article length checks (for stub links) to be bundled into a single query.
+ *
+ */
+ function makeLinkHolder( &$nt, $text = '', $query = '', $trail = '', $prefix = '' ) {
+ if ( ! is_object($nt) ) {
+ # Fail gracefully
+ $retVal = "<!-- ERROR -->{$prefix}{$text}{$trail}";
+ } else {
+ # Separate the link trail from the rest of the link
+ list( $inside, $trail ) = Linker::splitTrail( $trail );
+
+ if ( $nt->isExternal() ) {
+ $nr = array_push( $this->mInterwikiLinkHolders['texts'], $prefix.$text.$inside );
+ $this->mInterwikiLinkHolders['titles'][] = $nt;
+ $retVal = '<!--IWLINK '. ($nr-1) ."-->{$trail}";
+ } else {
+ $nr = array_push( $this->mLinkHolders['namespaces'], $nt->getNamespace() );
+ $this->mLinkHolders['dbkeys'][] = $nt->getDBkey();
+ $this->mLinkHolders['queries'][] = $query;
+ $this->mLinkHolders['texts'][] = $prefix.$text.$inside;
+ $this->mLinkHolders['titles'][] = $nt;
+
+ $retVal = '<!--LINK '. ($nr-1) ."-->{$trail}";
+ }
+ }
+ return $retVal;
+ }
+
/**
* Return true if subpage links should be expanded on this page.
* @return bool
global $wgNamespacesWithSubpages;
return !empty($wgNamespacesWithSubpages[$this->mTitle->getNamespace()]);
}
-
+
/**
* Handle link to subpage if necessary
* @param string $target the source of the link
$fname = 'Parser::maybeDoSubpageLink';
wfProfileIn( $fname );
$ret = $target; # default return value is no change
-
- # Some namespaces don't allow subpages,
+
+ # Some namespaces don't allow subpages,
# so only perform processing if subpages are allowed
- if( $this->areSubpagesAllowed() ) {
+ if( $this->areSubpagesAllowed() ) {
# Look at the first character
if( $target != '' && $target{0} == '/' ) {
# / at end means we don't want the slash to be shown
} else {
$noslash = substr( $target, 1 );
}
-
+
$ret = $this->mTitle->getPrefixedText(). '/' . trim($noslash);
if( '' === $text ) {
$text = $target;
#
$textLines = explode( "\n", $text );
- $lastPrefix = $output = $lastLine = '';
+ $lastPrefix = $output = '';
$this->mDTopen = $inBlockElem = false;
$prefixLength = 0;
$paragraphStack = false;
# ; title : definition text
# So we check for : in the remainder text to split up the
# title and definition, without b0rking links.
+ $term = $t2 = '';
if ($this->findColonNoLinks($t, $term, $t2) !== false) {
$t = $t2;
$output .= $term . $this->nextItem( ':' );
* @access private
*/
function getVariableValue( $index ) {
- global $wgContLang, $wgSitename, $wgServer, $wgArticle;
-
+ global $wgContLang, $wgSitename, $wgServer, $wgServerName, $wgArticle, $wgScriptPath;
+
/**
* Some of these require message or data lookups and can be
* expensive to check many times.
*/
static $varCache = array();
if( isset( $varCache[$index] ) ) return $varCache[$index];
-
+
switch ( $index ) {
case MAG_CURRENTMONTH:
return $varCache[$index] = $wgContLang->formatNum( date( 'm' ) );
case MAG_CURRENTDAYNAME:
return $varCache[$index] = $wgContLang->getWeekdayName( date('w')+1 );
case MAG_CURRENTYEAR:
- return $varCache[$index] = $wgContLang->formatNum( date( 'Y' ) );
+ return $varCache[$index] = $wgContLang->formatNum( date( 'Y' ), true );
case MAG_CURRENTTIME:
return $varCache[$index] = $wgContLang->time( wfTimestampNow(), false );
case MAG_CURRENTWEEK:
return $varCache[$index] = $wgContLang->formatNum( date('w') );
case MAG_NUMBEROFARTICLES:
return $varCache[$index] = $wgContLang->formatNum( wfNumberOfArticles() );
+ case MAG_NUMBEROFFILES:
+ return $varCache[$index] = $wgContLang->formatNum( wfNumberOfFiles() );
case MAG_SITENAME:
return $wgSitename;
case MAG_SERVER:
return $wgServer;
+ case MAG_SERVERNAME:
+ return $wgServerName;
+ case MAG_SCRIPTPATH:
+ return $wgScriptPath;
default:
return NULL;
}
* OT_WIKI: only {{subst:}} templates
* OT_MSG: only magic variables
* OT_HTML: all templates and magic variables
- *
+ *
* @param string $tex The text to transform
* @param array $args Key-value pairs representing template parameters to substitute
* @access private
*/
function replaceVariables( $text, $args = array() ) {
- global $wgLang, $wgScript, $wgArticlePath;
# Prevent too big inclusions
if( strlen( $text ) > MAX_INCLUDE_SIZE ) {
# Variable substitution
$text = preg_replace_callback( "/{{([$titleChars]*?)}}/", array( &$this, 'variableSubstitution' ), $text );
-
+
if ( $this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI ) {
# Argument substitution
$text = preg_replace_callback( "/{{{([$titleChars]*?)}}}/", array( &$this, 'argSubstitution' ), $text );
# merged with the next arg because the '|' character between belongs
# to the link syntax and not the template parameter syntax.
$argc = count($args);
- $i = 0;
+
for ( $i = 0; $i < $argc-1; $i++ ) {
if ( substr_count ( $args[$i], '[[' ) != substr_count ( $args[$i], ']]' ) ) {
$args[$i] .= '|'.$args[$i+1];
global $wgLinkCache, $wgContLang;
$fname = 'Parser::braceSubstitution';
wfProfileIn( $fname );
-
+
$found = false;
$nowiki = false;
$noparse = false;
}
# Load from database
- $itcamefromthedatabase = false;
+ $replaceHeadings = false;
+ $isHTML = false;
$lastPathLevel = $this->mTemplatePath;
if ( !$found ) {
$ns = NS_TEMPLATE;
$ns = $this->mTitle->getNamespace();
}
$title = Title::newFromText( $part1, $ns );
+
+ if ($title) {
+ $interwiki = Title::getInterwikiLink($title->getInterwiki());
+ if ($interwiki != '' && $title->isTrans()) {
+ return $this->scarytransclude($title, $interwiki);
+ }
+ }
+
if ( !is_null( $title ) && !$title->isExternal() ) {
# Check for excessive inclusion
$dbk = $title->getPrefixedDBkey();
if ( $this->incrementIncludeCount( $dbk ) ) {
- # This should never be reached.
- $article = new Article( $title );
- $articleContent = $article->getContentWithoutUsingSoManyDamnGlobals();
- if ( $articleContent !== false ) {
- $found = true;
- $text = $linestart . $articleContent;
- $itcamefromthedatabase = true;
+ if ( $title->getNamespace() == NS_SPECIAL && $this->mOptions->getAllowSpecialInclusion() ) {
+ # Capture special page output
+ $text = SpecialPage::capturePath( $title );
+ if ( $text && !is_object( $text ) ) {
+ $found = true;
+ $noparse = true;
+ $isHTML = true;
+ $this->mOutput->setCacheTime( -1 );
+ }
+ } else {
+ $article = new Article( $title );
+ $articleContent = $article->getContentWithoutUsingSoManyDamnGlobals();
+ if ( $articleContent !== false ) {
+ $found = true;
+ $text = $articleContent;
+ $replaceHeadings = true;
+ }
}
}
# If the title is valid but undisplayable, make a link to it
if ( $this->mOutputType == OT_HTML && !$found ) {
- $text = $linestart . '[['.$title->getPrefixedText().']]';
+ $text = '[['.$title->getPrefixedText().']]';
$found = true;
}
# Template cache array insertion
if( $found ) {
$this->mTemplates[$part1] = $text;
+ $text = $linestart . $text;
}
}
}
# Add a new element to the templace recursion path
$this->mTemplatePath[$part1] = 1;
- $text = $this->strip( $text, $this->mStripState );
- $text = Sanitizer::removeHTMLtags( $text );
+ if( $this->mOutputType == OT_HTML ) {
+ $text = $this->strip( $text, $this->mStripState );
+ $text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ), $assocArgs );
+ }
$text = $this->replaceVariables( $text, $assocArgs );
# Resume the link cache and register the inclusion as a link
}
# Prune lower levels off the recursion check path
$this->mTemplatePath = $lastPathLevel;
-
+
if ( !$found ) {
wfProfileOut( $fname );
return $matches[0];
} else {
- # replace ==section headers==
- # XXX this needs to go away once we have a better parser.
- if ( $this->mOutputType != OT_WIKI && $itcamefromthedatabase ) {
- if( !is_null( $title ) )
- $encodedname = base64_encode($title->getPrefixedDBkey());
- else
- $encodedname = base64_encode("");
- $m = preg_split('/(^={1,6}.*?={1,6}\s*?$)/m', $text, -1,
- PREG_SPLIT_DELIM_CAPTURE);
- $text = '';
- $nsec = 0;
- for( $i = 0; $i < count($m); $i += 2 ) {
- $text .= $m[$i];
- if (!isset($m[$i + 1]) || $m[$i + 1] == "") continue;
- $hl = $m[$i + 1];
- if( strstr($hl, "<!--MWTEMPLATESECTION") ) {
- $text .= $hl;
- continue;
+ if ( $isHTML ) {
+ # Replace raw HTML by a placeholder
+ # Add a blank line preceding, to prevent it from mucking up
+ # immediately preceding headings
+ $text = "\n\n" . $this->insertStripItem( $text, $this->mStripState );
+ } else {
+ # replace ==section headers==
+ # XXX this needs to go away once we have a better parser.
+ if ( $this->mOutputType != OT_WIKI && $replaceHeadings ) {
+ if( !is_null( $title ) )
+ $encodedname = base64_encode($title->getPrefixedDBkey());
+ else
+ $encodedname = base64_encode("");
+ $m = preg_split('/(^={1,6}.*?={1,6}\s*?$)/m', $text, -1,
+ PREG_SPLIT_DELIM_CAPTURE);
+ $text = '';
+ $nsec = 0;
+ for( $i = 0; $i < count($m); $i += 2 ) {
+ $text .= $m[$i];
+ if (!isset($m[$i + 1]) || $m[$i + 1] == "") continue;
+ $hl = $m[$i + 1];
+ if( strstr($hl, "<!--MWTEMPLATESECTION") ) {
+ $text .= $hl;
+ continue;
+ }
+ preg_match('/^(={1,6})(.*?)(={1,6})\s*?$/m', $hl, $m2);
+ $text .= $m2[1] . $m2[2] . "<!--MWTEMPLATESECTION="
+ . $encodedname . "&" . base64_encode("$nsec") . "-->" . $m2[3];
+
+ $nsec++;
}
- preg_match('/^(={1,6})(.*?)(={1,6})\s*?$/m', $hl, $m2);
- $text .= $m2[1] . $m2[2] . "<!--MWTEMPLATESECTION="
- . $encodedname . "&" . base64_encode("$nsec") . "-->" . $m2[3];
-
- $nsec++;
}
}
}
+
# Prune lower levels off the recursion check path
$this->mTemplatePath = $lastPathLevel;
-
+
if ( !$found ) {
wfProfileOut( $fname );
return $matches[0];
}
}
+ /**
+ * Translude an interwiki link.
+ */
+ function scarytransclude($title, $interwiki) {
+ global $wgEnableScaryTranscluding;
+
+ if (!$wgEnableScaryTranscluding)
+ return wfMsg('scarytranscludedisabled');
+
+ $articlename = "Template:" . $title->getDBkey();
+ $url = str_replace('$1', urlencode($articlename), $interwiki);
+ if (strlen($url) > 255)
+ return wfMsg('scarytranscludetoolong');
+ $text = $this->fetchScaryTemplateMaybeFromCache($url);
+ $this->mIWTransData[] = $text;
+ return "<!--IW_TRANSCLUDE ".(count($this->mIWTransData) - 1)."-->";
+ }
+
+ function fetchScaryTemplateMaybeFromCache($url) {
+ $dbr = wfGetDB(DB_SLAVE);
+ $obj = $dbr->selectRow('transcache', array('tc_time', 'tc_contents'),
+ array('tc_url' => $url));
+ if ($obj) {
+ $time = $obj->tc_time;
+ $text = $obj->tc_contents;
+ if ($time && $time < (time() + (60*60))) {
+ return $text;
+ }
+ }
+
+ $text = wfGetHTTP($url . '?action=render');
+ if (!$text)
+ return wfMsg('scarytranscludefailed', $url);
+
+ $dbw = wfGetDB(DB_MASTER);
+ $dbw->replace('transcache', array(), array(
+ 'tc_url' => $url,
+ 'tc_time' => time(),
+ 'tc_contents' => $text));
+ return $text;
+ }
+
+
/**
* Triple brace replacement -- used for template arguments
* @access private
* 2) Add an [edit] link to sections for logged in users who have enabled the option
* 3) Add a Table of contents on the top for users who have enabled the option
* 4) Auto-anchor headings
- *
+ *
* It loops through all headlines, collects the necessary data, then splits up the
* string and re-inserts the newly formatted headlines.
- *
+ *
* @param string $text
* @param boolean $isMain
* @access private
*/
function formatHeadings( $text, $isMain=true ) {
- global $wgInputEncoding, $wgMaxTocLevel, $wgContLang, $wgLinkHolders, $wgInterwikiLinkHolders;
+ global $wgMaxTocLevel, $wgContLang, $wgLinkHolders, $wgInterwikiLinkHolders;
$doNumberHeadings = $this->mOptions->getNumberHeadings();
$doShowToc = true;
$prevtoclevel = $toclevel;
}
$level = $matches[1][$headlineCount];
-
+
if( $doNumberHeadings || $doShowToc ) {
-
+
if ( $level > $prevlevel ) {
# Increase TOC level
$toclevel++;
# No change in level, end TOC line
$toc .= $sk->tocLineEnd();
}
-
+
$levelCount[$toclevel] = $level;
# count number of headlines for each level
# Remove link placeholders by the link text.
# <!--LINK number-->
- # turns into
+ # turns into
# link text with suffix
$canonized_headline = preg_replace( '/<!--LINK ([0-9]*)-->/e',
- "\$wgLinkHolders['texts'][\$1]",
+ "\$this->mLinkHolders['texts'][\$1]",
$canonized_headline );
$canonized_headline = preg_replace( '/<!--IWLINK ([0-9]*)-->/e',
- "\$wgInterwikiLinkHolders[\$1]",
+ "\$this->mInterwikiLinkHolders['texts'][\$1]",
$canonized_headline );
# strip out HTML
$canonized_headline = preg_replace( '/<.*?' . '>/','',$canonized_headline );
$tocline = trim( $canonized_headline );
- $canonized_headline = urlencode( do_html_entity_decode( str_replace(' ', '_', $tocline), ENT_COMPAT, $wgInputEncoding ) );
+ $canonized_headline = urlencode( Sanitizer::decodeCharReferences( str_replace(' ', '_', $tocline) ) );
$replacearray = array(
'%3A' => ':',
'%' => '.'
);
$canonized_headline = str_replace(array_keys($replacearray),array_values($replacearray),$canonized_headline);
- $refer[$headlineCount] = $canonized_headline;
+ $refers[$headlineCount] = $canonized_headline;
# count how many in assoc. array so we can track dupes in anchors
@$refers[$canonized_headline]++;
}
if( $doShowToc ) {
- $toclines = $headlineCount;
$toc .= $sk->tocUnindent( $toclevel - 1 );
$toc = $sk->tocList( $toc );
}
* @access private
*/
function magicISBN( $text ) {
- global $wgLang;
$fname = 'Parser::magicISBN';
wfProfileIn( $fname );
return $text;
}
$text = substr( array_shift( $a ), 1);
- $valid = '0123456789-ABCDEFGHIJKLMNOPQRSTUVWXYZ';
+ $valid = '0123456789-Xx';
foreach ( $a as $x ) {
$isbn = $blank = '' ;
}
$num = str_replace( '-', '', $isbn );
$num = str_replace( ' ', '', $num );
+ $num = str_replace( 'x', 'X', $num );
if ( '' == $num ) {
$text .= "ISBN $blank$x";
/**
* Return an HTML link for the "RFC 1234" text
+ *
* @access private
- * @param string $text text to be processed
+ * @param string $text Text to be processed
+ * @param string $keyword Magic keyword to use (default RFC)
+ * @param string $urlmsg Interface message to use (default rfcurl)
+ * @return string
*/
function magicRFC( $text, $keyword='RFC ', $urlmsg='rfcurl' ) {
- global $wgLang;
-
+
$valid = '0123456789';
$internal = false;
return $text;
}
$text = substr( array_shift( $a ), 1);
-
+
/* Check if keyword is preceed by [[.
* This test is made here cause of the array_shift above
* that prevent the test to be done in the foreach.
$text .= $keyword.$id.$x;
} else {
/* build the external link*/
- $url = wfmsg( $urlmsg );
- $url = str_replace( '$1', $id, $url);
+ $url = wfMsg( $urlmsg, $id);
$sk =& $this->mOptions->getSkin();
$la = $sk->getExternalLinkAttributes( $url, $keyword.$id );
$text .= "<a href='{$url}'{$la}>{$keyword}{$id}</a>{$x}";
}
-
+
/* Check if the next RFC keyword is preceed by [[ */
$internal = ( substr($x,-2) == '[[' );
}
$stripState = false;
$pairs = array(
"\r\n" => "\n",
- );
+ );
$text = str_replace( array_keys( $pairs ), array_values( $pairs ), $text );
$text = $this->strip( $text, $stripState, false );
$text = $this->pstPass2( $text, $user );
* @access private
*/
function pstPass2( $text, &$user ) {
- global $wgLang, $wgContLang, $wgLocaltimezone;
+ global $wgContLang, $wgLocaltimezone;
# Variable replacement
# Because mOutputType is OT_WIKI, this will only process {{subst:xxx}} type tags
$oldtz = getenv( 'TZ' );
putenv( 'TZ='.$wgLocaltimezone );
}
- /* Note: this is an ugly timezone hack for the European wikis */
- $d = $wgContLang->timeanddate( date( 'YmdHis' ), false ) .
+
+ /* Note: This is the timestamp saved as hardcoded wikitext to
+ * the database, we use $wgContLang here in order to give
+ * everyone the same signiture and use the default one rather
+ * than the one selected in each users preferences.
+ */
+ $d = $wgContLang->timeanddate( date( 'YmdHis' ), false, false) .
' (' . date( 'T' ) . ')';
if ( isset( $wgLocaltimezone ) ) {
- putenv( 'TZ='.$oldtzs );
+ putenv( 'TZ='.$oldtz );
}
if( $user->getOption( 'fancysig' ) ) {
/**
* Transform a MediaWiki message by replacing magic variables.
- *
+ *
* @param string $text the text to transform
* @param ParserOptions $options options
* @return string the text with variables substituted
* $options is a bit field, RLH_FOR_UPDATE to select for update
*/
function replaceLinkHolders( &$text, $options = 0 ) {
- global $wgUser, $wgLinkCache, $wgUseOldExistenceCheck, $wgLinkHolders;
- global $wgInterwikiLinkHolders;
- global $outputReplace;
-
- if ( $wgUseOldExistenceCheck ) {
- return array();
- }
+ global $wgUser, $wgLinkCache;
+ global $wgOutputReplace;
$fname = 'Parser::replaceLinkHolders';
wfProfileIn( $fname );
$pdbks = array();
$colours = array();
-
- #if ( !empty( $tmpLinks[0] ) ) { #TODO
- if ( !empty( $wgLinkHolders['namespaces'] ) ) {
+ $sk = $this->mOptions->getSkin();
+
+ if ( !empty( $this->mLinkHolders['namespaces'] ) ) {
wfProfileIn( $fname.'-check' );
$dbr =& wfGetDB( DB_SLAVE );
$page = $dbr->tableName( 'page' );
- $sk = $wgUser->getSkin();
$threshold = $wgUser->getOption('stubthreshold');
-
+
# Sort by namespace
- asort( $wgLinkHolders['namespaces'] );
-
+ asort( $this->mLinkHolders['namespaces'] );
+
# Generate query
$query = false;
- foreach ( $wgLinkHolders['namespaces'] as $key => $val ) {
+ foreach ( $this->mLinkHolders['namespaces'] as $key => $val ) {
# Make title object
- $title = $wgLinkHolders['titles'][$key];
+ $title = $this->mLinkHolders['titles'][$key];
# Skip invalid entries.
# Result will be ugly, but prevents crash.
} else {
$query .= ', ';
}
-
- $query .= $dbr->addQuotes( $wgLinkHolders['dbkeys'][$key] );
+
+ $query .= $dbr->addQuotes( $this->mLinkHolders['dbkeys'][$key] );
}
}
if ( $query ) {
if ( $options & RLH_FOR_UPDATE ) {
$query .= ' FOR UPDATE';
}
-
+
$res = $dbr->query( $query, $fname );
-
+
# Fetch data and form into an associative array
# non-existent = broken
# 1 = known
while ( $s = $dbr->fetchObject($res) ) {
$title = Title::makeTitle( $s->page_namespace, $s->page_title );
$pdbk = $title->getPrefixedDBkey();
- $wgLinkCache->addGoodLink( $s->page_id, $pdbk );
-
+ $wgLinkCache->addGoodLinkObj( $s->page_id, $title );
+
if ( $threshold > 0 ) {
$size = $s->page_len;
if ( $s->page_is_redirect || $s->page_namespace != 0 || $size >= $threshold ) {
}
}
wfProfileOut( $fname.'-check' );
-
+
# Construct search and replace arrays
wfProfileIn( $fname.'-construct' );
- $outputReplace = array();
- foreach ( $wgLinkHolders['namespaces'] as $key => $ns ) {
+ $wgOutputReplace = array();
+ foreach ( $this->mLinkHolders['namespaces'] as $key => $ns ) {
$pdbk = $pdbks[$key];
- $searchkey = '<!--LINK '.$key.'-->';
- $title = $wgLinkHolders['titles'][$key];
+ $searchkey = "<!--LINK $key-->";
+ $title = $this->mLinkHolders['titles'][$key];
if ( empty( $colours[$pdbk] ) ) {
- $wgLinkCache->addBadLink( $pdbk );
+ $wgLinkCache->addBadLinkObj( $title );
$colours[$pdbk] = 0;
- $outputReplace[$searchkey] = $sk->makeBrokenLinkObj( $title,
- $wgLinkHolders['texts'][$key],
- $wgLinkHolders['queries'][$key] );
+ $wgOutputReplace[$searchkey] = $sk->makeBrokenLinkObj( $title,
+ $this->mLinkHolders['texts'][$key],
+ $this->mLinkHolders['queries'][$key] );
} elseif ( $colours[$pdbk] == 1 ) {
- $outputReplace[$searchkey] = $sk->makeKnownLinkObj( $title,
- $wgLinkHolders['texts'][$key],
- $wgLinkHolders['queries'][$key] );
+ $wgOutputReplace[$searchkey] = $sk->makeKnownLinkObj( $title,
+ $this->mLinkHolders['texts'][$key],
+ $this->mLinkHolders['queries'][$key] );
} elseif ( $colours[$pdbk] == 2 ) {
- $outputReplace[$searchkey] = $sk->makeStubLinkObj( $title,
- $wgLinkHolders['texts'][$key],
- $wgLinkHolders['queries'][$key] );
+ $wgOutputReplace[$searchkey] = $sk->makeStubLinkObj( $title,
+ $this->mLinkHolders['texts'][$key],
+ $this->mLinkHolders['queries'][$key] );
}
}
wfProfileOut( $fname.'-construct' );
# Do the thing
wfProfileIn( $fname.'-replace' );
-
+
$text = preg_replace_callback(
'/(<!--LINK .*?-->)/',
- "outputReplaceMatches",
+ "wfOutputReplaceMatches",
$text);
+
wfProfileOut( $fname.'-replace' );
}
- if ( !empty( $wgInterwikiLinkHolders ) ) {
+ # Now process interwiki link holders
+ # This is quite a bit simpler than internal links
+ if ( !empty( $this->mInterwikiLinkHolders['texts'] ) ) {
wfProfileIn( $fname.'-interwiki' );
- $outputReplace = $wgInterwikiLinkHolders;
+ # Make interwiki link HTML
+ $wgOutputReplace = array();
+ foreach( $this->mInterwikiLinkHolders['texts'] as $key => $link ) {
+ $title = $this->mInterwikiLinkHolders['titles'][$key];
+ $wgOutputReplace[$key] = $sk->makeLinkObj( $title, $link );
+ }
+
$text = preg_replace_callback(
'/<!--IWLINK (.*?)-->/',
- "outputReplaceMatches",
+ "wfOutputReplaceMatches",
$text );
wfProfileOut( $fname.'-interwiki' );
}
return $colours;
}
+ /**
+ * Replace <!--LINK--> link placeholders with plain text of links
+ * (not HTML-formatted).
+ * @param string $text
+ * @return string
+ */
+ function replaceLinkHoldersText( $text ) {
+ global $wgUser, $wgLinkCache;
+ global $wgOutputReplace;
+
+ $fname = 'Parser::replaceLinkHoldersText';
+ wfProfileIn( $fname );
+
+ $text = preg_replace_callback(
+ '/<!--(LINK|IWLINK) (.*?)-->/',
+ array( &$this, 'replaceLinkHoldersTextCallback' ),
+ $text );
+
+ wfProfileOut( $fname );
+ return $text;
+ }
+
+ /**
+ * @param array $matches
+ * @return string
+ * @access private
+ */
+ function replaceLinkHoldersTextCallback( $matches ) {
+ $type = $matches[1];
+ $key = $matches[2];
+ if( $type == 'LINK' ) {
+ if( isset( $this->mLinkHolders['texts'][$key] ) ) {
+ return $this->mLinkHolders['texts'][$key];
+ }
+ } elseif( $type == 'IWLINK' ) {
+ if( isset( $this->mInterwikiLinkHolders['texts'][$key] ) ) {
+ return $this->mInterwikiLinkHolders['texts'][$key];
+ }
+ }
+ return $matches[0];
+ }
+
/**
* Renders an image gallery from a text with one line per image.
* text labels may be given by using |-style alternative text. E.g.
* given as text will return the HTML of a gallery with two images,
* labeled 'The number "1"' and
* 'A tree'.
+ *
+ * @static
*/
function renderImageGallery( $text ) {
+ # Setup the parser
+ global $wgUser, $wgTitle;
+ $parserOptions = ParserOptions::newFromUser( $wgUser );
+ $localParser = new Parser();
+
global $wgLinkCache;
$ig = new ImageGallery();
$ig->setShowBytes( false );
} else {
$label = '';
}
-
- # FIXME: Use the full wiki parser and add its links
- # to the page's links.
- $html = $this->mOptions->mSkin->formatComment( $label );
-
- $ig->add( Image::newFromTitle( $nt ), $html );
+
+ $html = $localParser->parse( $label , $wgTitle, $parserOptions );
+ $html = $html->mText;
+
+ $ig->add( new Image( $nt ), $html );
$wgLinkCache->addImageLinkObj( $nt );
}
return $ig->toHTML();
}
+
+ /**
+ * Parse image options text and use it to make an image
+ */
+ function makeImage( &$nt, $options ) {
+ global $wgContLang, $wgUseImageResize;
+ global $wgUser, $wgThumbLimits;
+
+ $align = '';
+
+ # Check if the options text is of the form "options|alt text"
+ # Options are:
+ # * thumbnail make a thumbnail with enlarge-icon and caption, alignment depends on lang
+ # * left no resizing, just left align. label is used for alt= only
+ # * right same, but right aligned
+ # * none same, but not aligned
+ # * ___px scale to ___ pixels width, no aligning. e.g. use in taxobox
+ # * center center the image
+ # * framed Keep original image size, no magnify-button.
+
+ $part = explode( '|', $options);
+
+ $mwThumb =& MagicWord::get( MAG_IMG_THUMBNAIL );
+ $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 );
+ $caption = '';
+
+ $width = $height = $framed = $thumb = false;
+ $manual_thumb = '' ;
+
+ foreach( $part as $key => $val ) {
+ $val_parts = explode ( '=' , $val , 2 ) ;
+ $left_part = array_shift ( $val_parts ) ;
+ if ( $wgUseImageResize && ! is_null( $mwThumb->matchVariableStartToEnd($val) ) ) {
+ $thumb=true;
+ } elseif ( $wgUseImageResize && count ( $val_parts ) == 1 && ! is_null( $mwThumb->matchVariableStartToEnd($left_part) ) ) {
+ # use manually specified thumbnail
+ $thumb=true;
+ $manual_thumb = array_shift ( $val_parts ) ;
+ } elseif ( ! is_null( $mwRight->matchVariableStartToEnd($val) ) ) {
+ # remember to set an alignment, don't render immediately
+ $align = 'right';
+ } elseif ( ! is_null( $mwLeft->matchVariableStartToEnd($val) ) ) {
+ # remember to set an alignment, don't render immediately
+ $align = 'left';
+ } elseif ( ! is_null( $mwCenter->matchVariableStartToEnd($val) ) ) {
+ # remember to set an alignment, don't render immediately
+ $align = 'center';
+ } elseif ( ! is_null( $mwNone->matchVariableStartToEnd($val) ) ) {
+ # 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" );
+ # $match is the image width in pixels
+ if ( preg_match( '/^([0-9]*)x([0-9]*)$/', $match, $m ) ) {
+ $width = intval( $m[1] );
+ $height = intval( $m[2] );
+ } else {
+ $width = intval($match);
+ }
+ } elseif ( ! is_null( $mwFramed->matchVariableStartToEnd($val) ) ) {
+ $framed=true;
+ } else {
+ $caption = $val;
+ }
+ }
+ # Strip bad stuff out of the alt text
+ $alt = $this->replaceLinkHoldersText( $caption );
+ $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 );
+ }
}
/**
class ParserOutput
{
var $mText, $mLanguageLinks, $mCategoryLinks, $mContainsOldMagic;
- var $mCacheTime; # Used in ParserCache
+ var $mCacheTime; # Timestamp on this article, or -1 for uncacheable. Used in ParserCache.
var $mVersion; # Compatibility check
+ var $mTitleText; # title text of the chosen language variant
function ParserOutput( $text = '', $languageLinks = array(), $categoryLinks = array(),
- $containsOldMagic = false )
+ $containsOldMagic = false, $titletext = '' )
{
$this->mText = $text;
$this->mLanguageLinks = $languageLinks;
$this->mContainsOldMagic = $containsOldMagic;
$this->mCacheTime = '';
$this->mVersion = MW_PARSER_VERSION;
+ $this->mTitleText = $titletext;
}
function getText() { return $this->mText; }
function getLanguageLinks() { return $this->mLanguageLinks; }
function getCategoryLinks() { return array_keys( $this->mCategoryLinks ); }
function getCacheTime() { return $this->mCacheTime; }
+ function getTitleText() { return $this->mTitleText; }
function containsOldMagic() { return $this->mContainsOldMagic; }
function setText( $text ) { return wfSetVar( $this->mText, $text ); }
function setLanguageLinks( $ll ) { return wfSetVar( $this->mLanguageLinks, $ll ); }
function setCategoryLinks( $cl ) { return wfSetVar( $this->mCategoryLinks, $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 addCategoryLink( $c ) { $this->mCategoryLinks[$c] = 1; }
function merge( $other ) {
*/
function expired( $touched ) {
global $wgCacheEpoch;
- return $this->getCacheTime() <= $touched ||
+ return $this->getCacheTime() == -1 || // parser says it's uncacheable
+ $this->getCacheTime() <= $touched ||
$this->getCacheTime() <= $wgCacheEpoch ||
!isset( $this->mVersion ) ||
version_compare( $this->mVersion, MW_PARSER_VERSION, "lt" );
{
# All variables are private
var $mUseTeX; # Use texvc to expand <math> tags
- var $mUseDynamicDates; # Use $wgDateFormatter to format dates
+ var $mUseDynamicDates; # Use DateFormatter to format dates
var $mInterwikiMagic; # Interlanguage links are removed and returned in an array
var $mAllowExternalImages; # Allow external images inline
var $mSkin; # Reference to the preferred skin
var $mDateFormat; # Date format index
var $mEditSection; # Create "edit section" links
var $mNumberHeadings; # Automatically number headings
+ var $mAllowSpecialInclusion; # Allow inclusion of special pages
function getUseTeX() { return $this->mUseTeX; }
function getUseDynamicDates() { return $this->mUseDynamicDates; }
function getDateFormat() { return $this->mDateFormat; }
function getEditSection() { return $this->mEditSection; }
function getNumberHeadings() { return $this->mNumberHeadings; }
+ function getAllowSpecialInclusion() { return $this->mAllowSpecialInclusion; }
+
function setUseTeX( $x ) { return wfSetVar( $this->mUseTeX, $x ); }
function setUseDynamicDates( $x ) { return wfSetVar( $this->mUseDynamicDates, $x ); }
function setDateFormat( $x ) { return wfSetVar( $this->mDateFormat, $x ); }
function setEditSection( $x ) { return wfSetVar( $this->mEditSection, $x ); }
function setNumberHeadings( $x ) { return wfSetVar( $this->mNumberHeadings, $x ); }
+ function setAllowSpecialInclusion( $x ) { return wfSetVar( $this->mAllowSpecialInclusion, $x ); }
function setSkin( &$x ) { $this->mSkin =& $x; }
+ function ParserOptions() {
+ global $wgUser;
+ $this->initialiseFromUser( $wgUser );
+ }
+
/**
* Get parser options
* @static
/** Get user options */
function initialiseFromUser( &$userInput ) {
- global $wgUseTeX, $wgUseDynamicDates, $wgInterwikiMagic, $wgAllowExternalImages;
+ global $wgUseTeX, $wgUseDynamicDates, $wgInterwikiMagic, $wgAllowExternalImages,
+ $wgAllowSpecialInclusion;
$fname = 'ParserOptions::initialiseFromUser';
wfProfileIn( $fname );
if ( !$userInput ) {
$this->mSkin =& $user->getSkin();
wfProfileOut( $fname.'-skin' );
$this->mDateFormat = $user->getOption( 'date' );
- $this->mEditSection = $user->getOption( 'editsection' );
+ $this->mEditSection = true;
$this->mNumberHeadings = $user->getOption( 'numberheadings' );
+ $this->mAllowSpecialInclusion = $wgAllowSpecialInclusion;
wfProfileOut( $fname );
}
}
* Callback function used by Parser::replaceLinkHolders()
* to substitute link placeholders.
*/
-function &outputReplaceMatches( $matches ) {
- global $outputReplace;
- return $outputReplace[$matches[1]];
+function &wfOutputReplaceMatches( $matches ) {
+ global $wgOutputReplace;
+ return $wgOutputReplace[$matches[1]];
}
/**
return $wgNumberOfArticles;
}
+/**
+ * Return the number of files
+ */
+function wfNumberOfFiles() {
+ $fname = 'Parser::wfNumberOfFiles';
+
+ wfProfileIn( $fname );
+ $dbr =& wfGetDB( DB_SLAVE );
+ $res = $dbr->selectField('image', 'COUNT(*)', array(), $fname );
+ wfProfileOut( $fname );
+
+ return $res;
+}
+
/**
* Get various statistics from the database
* @private
/**
* Escape html tags
* Basicly replacing " > and < with HTML entities ( ", >, <)
- *
+ *
* @param string $in Text that might contain HTML tags
* @return string Escaped string
*/