http://www.mediawiki.org/wiki/Special:Code/MediaWiki/73595
Revision: 73595
Author: aj
Date: 2010-09-23 06:49:42 +0000 (Thu, 23 Sep 2010)
Log Message:
-----------
added mediawiki patch
Added Paths:
-----------
trunk/parsers/libmwparser/mediawiki.patch
Added: trunk/parsers/libmwparser/mediawiki.patch
===================================================================
--- trunk/parsers/libmwparser/mediawiki.patch (rev 0)
+++ trunk/parsers/libmwparser/mediawiki.patch 2010-09-23 06:49:42 UTC (rev
73595)
@@ -0,0 +1,478 @@
+Index: includes/parser/Parser.php
+===================================================================
+--- includes/parser/Parser.php (revision 69308)
++++ includes/parser/Parser.php (arbetskopia)
+@@ -7,6 +7,9 @@
+ * File for Parser and related classes
+ */
+
++include_once('MediaWiki/mwp.php');
++include_once('LinkResolver.php');
++define('USE_LIBMWPARSER', true);
+
+ /**
+ * PHP Parser - Processes wiki markup (which uses a more user-friendly
+@@ -114,6 +117,7 @@
+ var $mRevisionTimestamp; # The timestamp of the specified revision ID
+ var $mRevIdForTs; # The revision ID which was used to fetch the
timestamp
+
++
+ /**
+ * Constructor
+ *
+@@ -262,13 +266,17 @@
+ wfProfileIn( __METHOD__ );
+ wfProfileIn( $fname );
+
++
+ if ( $clearState ) {
+ $this->clearState();
+ }
+
+ $this->mOptions = $options;
+ $this->setTitle( $title ); # Page title has to be set for the
pre-processor
++ $rawTitle = $title;
+
++ $rawText = $text;
++
+ $oldRevisionId = $this->mRevisionId;
+ $oldRevisionTimestamp = $this->mRevisionTimestamp;
+ if ( $revid !== null ) {
+@@ -281,143 +289,156 @@
+ wfRunHooks( 'ParserAfterStrip', array( &$this, &$text,
&$this->mStripState ) );
+ $text = $this->internalParse( $text );
+
+- $text = $this->mStripState->unstripGeneral( $text );
++ if (!USE_LIBMWPARSER) {
++ $text = $this->mStripState->unstripGeneral( $text );
+
+- # Clean up special characters, only run once, next-to-last
before doBlockLevels
+- $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 ',
+- '/ (!\s*important)/' => ' \\1', # Beware of CSS
magic word !important, bug #11874.
+- );
+- $text = preg_replace( array_keys( $fixtags ), array_values(
$fixtags ), $text );
++ # Clean up special characters, only run once,
next-to-last before doBlockLevels
++ $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 ',
++ '/ (!\s*important)/' => ' \\1',
# Beware of CSS magic word !important, bug #11874.
++ );
++ $text = preg_replace( array_keys( $fixtags ),
array_values( $fixtags ), $text );
+
+- $text = $this->doBlockLevels( $text, $linestart );
++ $text = $this->doBlockLevels( $text, $linestart );
+
+- $this->replaceLinkHolders( $text );
++ $this->replaceLinkHolders( $text );
+
+- /**
+- * The page doesn't get language converted if
+- * a) It's disabled
+- * b) Content isn't converted
+- * c) It's a conversion table
+- */
+- if ( !( $wgDisableLangConversion
+- || isset(
$this->mDoubleUnderscores['nocontentconvert'] )
+- || $this->mTitle->isConversionTable() ) ) {
++ /**
++ * The page doesn't get language converted if
++ * a) It's disabled
++ * b) Content isn't converted
++ * c) It's a conversion table
++ */
++ if ( !( $wgDisableLangConversion
++ || isset(
$this->mDoubleUnderscores['nocontentconvert'] )
++ || $this->mTitle->isConversionTable() ) ) {
+
+ # The position of the convert() call should not be
changed. it
+- # assumes that the links are all replaced and the only
thing left
+- # is the <nowiki> mark.
++ # assumes that the links are all replaced and the
only thing left
++ # is the <nowiki> mark.
+
+- $text = $wgContLang->convert( $text );
+- }
++ $text = $wgContLang->convert( $text );
++ }
+
+- /**
+- * A page get its title converted except:
+- * a) Language conversion is globally disabled
+- * b) Title convert is globally disabled
+- * c) The page is a redirect page
+- * d) User request with a "linkconvert" set to "no"
+- * e) A "nocontentconvert" magic word has been set
+- * f) A "notitleconvert" magic word has been set
+- * g) User sets "noconvertlink" in his/her preference
+- *
+- * Note that if a user tries to set a title in a conversion
+- * rule but content conversion was not done, then the parser
+- * won't pick it up. This is probably expected behavior.
+- */
+- if ( !( $wgDisableLangConversion
+- || $wgDisableTitleConversion
+- || isset(
$this->mDoubleUnderscores['nocontentconvert'] )
+- || isset(
$this->mDoubleUnderscores['notitleconvert'] )
+- || $this->mOutput->getDisplayTitle() !== false
) )
+- {
+- $convruletitle = $wgContLang->getConvRuleTitle();
+- if ( $convruletitle ) {
++ /**
++ * A page get its title converted except:
++ * a) Language conversion is globally disabled
++ * b) Title convert is globally disabled
++ * c) The page is a redirect page
++ * d) User request with a "linkconvert" set to "no"
++ * e) A "nocontentconvert" magic word has been set
++ * f) A "notitleconvert" magic word has been set
++ * g) User sets "noconvertlink" in his/her preference
++ *
++ * Note that if a user tries to set a title in a
conversion
++ * rule but content conversion was not done, then the
parser
++ * won't pick it up. This is probably expected behavior.
++ */
++ if ( !( $wgDisableLangConversion
++ || $wgDisableTitleConversion
++ || isset(
$this->mDoubleUnderscores['nocontentconvert'] )
++ || isset(
$this->mDoubleUnderscores['notitleconvert'] )
++ || $this->mOutput->getDisplayTitle() !== false )
)
++ {
++ $convruletitle = $wgContLang->getConvRuleTitle();
++ if ( $convruletitle ) {
+ $this->mOutput->setTitleText( $convruletitle );
+- } else {
++ } else {
+ $titleText = $wgContLang->convertTitle( $title
);
+ $this->mOutput->setTitleText( $titleText );
+- }
+- }
++ }
++ }
+
+- $text = $this->mStripState->unstripNoWiki( $text );
++ $text = $this->mStripState->unstripNoWiki( $text );
+
+- wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
++ wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
+
+-//!JF Move to its own function
++ //!JF Move to its own function
+
+- $uniq_prefix = $this->mUniqPrefix;
+- $matches = array();
+- $elements = array_keys( $this->mTransparentTagHooks );
+- $text = self::extractTagsAndParams( $elements, $text, $matches,
$uniq_prefix );
++ $uniq_prefix = $this->mUniqPrefix;
++ $matches = array();
++ $elements = array_keys( $this->mTransparentTagHooks );
++ $text = self::extractTagsAndParams( $elements, $text,
$matches, $uniq_prefix );
+
+- foreach ( $matches as $marker => $data ) {
++ foreach ( $matches as $marker => $data ) {
+ list( $element, $content, $params, $tag ) = $data;
+ $tagName = strtolower( $element );
+ if ( isset( $this->mTransparentTagHooks[$tagName] ) ) {
+- $output = call_user_func_array(
$this->mTransparentTagHooks[$tagName], array( $content, $params, $this ) );
++ $output = call_user_func_array(
$this->mTransparentTagHooks[$tagName], array( $content, $params, $this ) );
+ } else {
+- $output = $tag;
++ $output = $tag;
+ }
+ $this->mStripState->general->setPair( $marker, $output
);
+- }
+- $text = $this->mStripState->unstripGeneral( $text );
++ }
++ $text = $this->mStripState->unstripGeneral( $text );
+
+- $text = Sanitizer::normalizeCharReferences( $text );
++ $text = Sanitizer::normalizeCharReferences( $text );
+
+- if ( ( $wgUseTidy && $this->mOptions->mTidy ) ||
$wgAlwaysUseTidy ) {
++ if ( ( $wgUseTidy && $this->mOptions->mTidy ) ||
$wgAlwaysUseTidy ) {
+ $text = MWTidy::tidy( $text );
+- } else {
++ } else {
+ # attempt to sanitize at least some nesting problems
+- # (bug #2702 and quite a few others)
+- $tidyregs = array(
+- # ''Something [http://www.cool.com cool''] -->
+- # <i>Something</i><a
href="http://www.cool.com";..><i>cool></i></a>
+-
'/(<([bi])>)(<([bi])>)?([^<]*)(<\/?a[^<]*>)([^<]*)(<\/\\4>)?(<\/\\2>)/' =>
+- '\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9',
+- # fix up an anchor inside another anchor, only
+- # at least for a single single nested link (bug
3695)
+-
'/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
+- '\\1\\2</a>\\3</a>\\1\\4</a>',
+- # fix div inside inline elements- doBlockLevels
won't wrap a line which
+- # contains a div, so fix it up here; replace
+- # div with escaped text
+- '/(<([aib])
[^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\/div>)([^<]*)(<\/\\2>)/' =>
+- '\\1\\3<div\\5>\\6</div>\\8\\9',
+- # remove empty italic or bold tag pairs, some
+- # introduced by rules above
+- '/<([bi])><\/\\1>/' => '',
+- );
++ # (bug #2702 and quite a few others)
++ $tidyregs = array(
++ # ''Something
[http://www.cool.com cool''] -->
++ # <i>Something</i><a
href="http://www.cool.com";..><i>cool></i></a>
++
'/(<([bi])>)(<([bi])>)?([^<]*)(<\/?a[^<]*>)([^<]*)(<\/\\4>)?(<\/\\2>)/' =>
++
'\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9',
++ # fix up an anchor inside
another anchor, only
++ # at least for a single single
nested link (bug 3695)
++
'/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
++ '\\1\\2</a>\\3</a>\\1\\4</a>',
++ # fix div inside inline
elements- doBlockLevels won't wrap a line which
++ # contains a div, so fix it up
here; replace
++ # div with escaped text
++ '/(<([aib])
[^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\/div>)([^<]*)(<\/\\2>)/' =>
++
'\\1\\3<div\\5>\\6</div>\\8\\9',
++ # remove empty italic or bold
tag pairs, some
++ # introduced by rules above
++ '/<([bi])><\/\\1>/' => '',
++ );
+
+ $text = preg_replace(
+- array_keys( $tidyregs ),
+- array_values( $tidyregs ),
+- $text );
+- }
+- global $wgExpensiveParserFunctionLimit;
+- if ( $this->mExpensiveFunctionCount >
$wgExpensiveParserFunctionLimit ) {
++ array_keys( $tidyregs ),
++ array_values( $tidyregs ),
++ $text );
++ }
++ global $wgExpensiveParserFunctionLimit;
++ if ( $this->mExpensiveFunctionCount >
$wgExpensiveParserFunctionLimit ) {
+ $this->limitationWarn( 'expensive-parserfunction',
$this->mExpensiveFunctionCount, $wgExpensiveParserFunctionLimit );
+- }
++ }
+
+- wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
++ wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
+
+- # Information on include size limits, for the benefit of users
who try to skirt them
+- if ( $this->mOptions->getEnableLimitReport() ) {
+- $max = $this->mOptions->getMaxIncludeSize();
+- $PFreport = "Expensive parser function count:
{$this->mExpensiveFunctionCount}/$wgExpensiveParserFunctionLimit\n";
+- $limitReport =
+- "NewPP limit report\n" .
+- "Preprocessor node count:
{$this->mPPNodeCount}/{$this->mOptions->mMaxPPNodeCount}\n" .
+- "Post-expand include size:
{$this->mIncludeSizes['post-expand']}/$max bytes\n" .
+- "Template argument size:
{$this->mIncludeSizes['arg']}/$max bytes\n".
+- $PFreport;
+- wfRunHooks( 'ParserLimitReport', array( $this,
&$limitReport ) );
+- $text .= "\n<!-- \n$limitReport-->\n";
+- }
++ # Information on include size limits, for the benefit of
users who try to skirt them
++ if ( $this->mOptions->getEnableLimitReport() ) {
++ $max = $this->mOptions->getMaxIncludeSize();
++ $PFreport = "Expensive parser function count:
{$this->mExpensiveFunctionCount}/$wgExpensiveParserFunctionLimit\n";
++ $limitReport =
++ "NewPP limit report\n" .
++ "Preprocessor node count:
{$this->mPPNodeCount}/{$this->mOptions->mMaxPPNodeCount}\n" .
++ "Post-expand include size:
{$this->mIncludeSizes['post-expand']}/$max bytes\n" .
++ "Template argument size:
{$this->mIncludeSizes['arg']}/$max bytes\n".
++ $PFreport;
++ wfRunHooks( 'ParserLimitReport', array( $this,
&$limitReport ) );
++ $text .= "\n<!-- \n$limitReport-->\n";
++ }
++ } else {
++ # libmwparse
++ $istream = new_MWParserInput($text);
++
++ $parser = new_MWParser($istream);
++
++ $text = implode('', MWParseArticle($parser));
++ delete_MWParser($parser);
++ delete_MWParserInput($istream);
++
++ }
++
+ $this->mOutput->setText( $text );
+
+ $this->mRevisionId = $oldRevisionId;
+@@ -1051,38 +1072,42 @@
+ $text = $frame->expand( $dom );
+ } else {
+ # if $frame is not provided, then use old-style
replaceVariables
+- $text = $this->replaceVariables( $text );
++ if (!USE_LIBMWPARSER) {
++ $text = $this->replaceVariables( $text );
++ }
+ }
+
+- $text = Sanitizer::removeHTMLtags( $text, array( &$this,
'attributeStripCallback' ), false, array_keys( $this->mTransparentTagHooks ) );
+- wfRunHooks( 'InternalParseBeforeLinks', array( &$this, &$text,
&$this->mStripState ) );
++ if (!USE_LIBMWPARSER) {
++ $text = Sanitizer::removeHTMLtags( $text, array( &$this,
'attributeStripCallback' ), false, array_keys( $this->mTransparentTagHooks ) );
++ wfRunHooks( 'InternalParseBeforeLinks', array( &$this,
&$text, &$this->mStripState ) );
+
+- # Tables need to come after variable replacement for things to
work
+- # properly; putting them before other transformations should
keep
+- # exciting things like link expansions from showing up in
surprising
+- # places.
+- $text = $this->doTableStuff( $text );
++ # Tables need to come after variable replacement for
things to work
++
# properly; putting them before other transformations should keep
++
# exciting things like link expansions from showing up in
surprising
++
# places.
++
$text = $this->doTableStuff( $text );
+
+- $text = preg_replace( '/(^|\n)-----*/', '\\1<hr />', $text );
+-
++ $text = preg_replace( '/(^|\n)-----*'.'/', '\\1<hr />',
$text );
++ }
+ $text = $this->doDoubleUnderscore( $text );
+-
+- $text = $this->doHeadings( $text );
+- if ( $this->mOptions->getUseDynamicDates() ) {
++ if (!USE_LIBMWPARSER) {
++ $text = $this->doHeadings( $text );
++ if ( $this->mOptions->getUseDynamicDates() ) {
+ $df = DateFormatter::getInstance();
+ $text = $df->reformat(
$this->mOptions->getDateFormat(), $text );
+- }
+- $text = $this->replaceInternalLinks( $text );
+- $text = $this->doAllQuotes( $text );
+- $text = $this->replaceExternalLinks( $text );
++ }
++ $text = $this->replaceInternalLinks( $text );
++ $text = $this->doAllQuotes( $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( $this->mUniqPrefix.'NOPARSE', '', $text );
++ # replaceInternalLinks may sometimes leave behind
++ # absolute URLs, which have to be masked to hide them
from replaceExternalLinks
++ $text = str_replace( $this->mUniqPrefix.'NOPARSE',
'', $text );
+
+- $text = $this->doMagicLinks( $text );
+- $text = $this->formatHeadings( $text, $origText, $isMain );
+-
++ $text = $this->doMagicLinks( $text );
++ $text = $this->formatHeadings( $text, $origText, $isMain
);
++
++ }
+ wfProfileOut( __METHOD__ );
+ return $text;
+ }
+Index: includes/parser/LinkResolver.php
+===================================================================
+--- includes/parser/LinkResolver.php (revision 0)
++++ includes/parser/LinkResolver.php (revision 0)
+@@ -0,0 +1,103 @@
++<?php
++
++include_once('MediaWiki/mwp.php');
++
++# TODO add support for GetLinkColors hook here
++
++function MWParserLinkResolverCallback($linkCollection) {
++ $lcKeys = MWLinkCollectionGet($linkCollection);
++ $linkCache = LinkCache::singleton();
++ $dbr = wfGetDB( DB_SLAVE );
++ $page = $dbr->tableName( 'page' );
++
++ $links = array();
++
++ foreach ($lcKeys as $lcKey) {
++ $type = MWLCKeyGetLinkType($lcKey);
++ if ($type == MWLT_EXTERNAL) {
++ continue;
++ }
++ $title = Title::newFromText(MWLCKeyGetLinkTitle($lcKey));
++ if ($type == MWLT_INTERNAL) {
++ $ns = $title->getNamespace();
++ $links[$title->getDBKey()] = $lcKey;
++
++ # Not in the link cache, add it to the query
++ if ( !isset( $current ) ) {
++ $current = $ns;
++ $query = "SELECT page_id,
page_namespace, page_title, page_is_redirect, page_len, page_latest";
++ $query .= " FROM $page WHERE
(page_namespace=$ns AND page_title IN(";
++ } elseif ( $current != $ns ) {
++ $current = $ns;
++ $query .= ")) OR (page_namespace=$ns AND
page_title IN(";
++ } else {
++ $query .= ', ';
++ }
++
++ $query .= $dbr->addQuotes( $title->getDBkey() );
++ } elseif ($type == MWLT_MEDIA) {
++ $linkResolution = new_MWLINKRESOLUTION();
++ $time = false;
++ // TODO File hook
++ $img = wfFindFile( $title, array( 'time' => $time )
);
++ $alt = htmlspecialchars( $title->getText(),
ENT_QUOTES );
++ MWLINKRESOLUTION_alt_set($linkResolution, $alt);
++ MWLINKRESOLUTION_url_set($linkResolution,
$title->getLocalURL() );
++ if ($img) {
++
MWLINKRESOLUTION_imageUrl_set($linkResolution,
htmlspecialchars($img->getURL()));
++ MWLINKRESOLUTION_c_class_set($linkResolution,
'internal');
++ if ($img->getWidth()) {
++
MWLINKRESOLUTION_imageWidth_set($linkResolution, $img->getWidth());
++ }
++ if ($img->getHeight()) {
++
MWLINKRESOLUTION_imageHeight_set($linkResolution, $img->getHeight());
++ }
++ } else {
++ MWLINKRESOLUTION_c_class_set($linkResolution,
'new');
++ }
++ MWLinkCollectionResolve($linkCollection, $lcKey,
$linkResolution);
++ }
++ }
++
++ if ( $query ) {
++ $query .= '))';
++
++ wfDebugLog('linkresolver', "Link resolver callback query:
'$query'");
++ $res = $dbr->query( $query, __METHOD__ );
++
++ # Fetch data and form into an associative array
++ # non-existent = broken
++ while ( $s = $dbr->fetchObject($res) ) {
++ $title = Title::makeTitle( $s->page_namespace,
$s->page_title );
++ $lcKey = $links[$title->getDBKey()];
++ unset($links[$title->getDBKey()]);
++ wfDebugLog('linkresolver', 'Resolving ' .
MWLCKeyGetLinkTitle($lcKey) . ' to ' . $title->getLocalURL());
++ $linkResolution = new_MWLINKRESOLUTION();
++ MWLINKRESOLUTION_url_set($linkResolution,
$title->getLocalURL());
++ $linkCache->addGoodLinkObj( $s->page_id, $title,
$s->page_len, $s->page_is_redirect, $s->page_latest );
++ MWLINKRESOLUTION_color_set($linkResolution,
MWLINKCOLOR_BLUE);
++ MWLinkCollectionResolve($linkCollection, $lcKey,
$linkResolution);
++ }
++ unset( $res );
++ }
++
++ foreach ($links as $lcKey) {
++ $title = Title::newFromText(MWLCKeyGetLinkTitle($lcKey));
++ $linkResolution = new_MWLINKRESOLUTION();
++
++ if ($title->isKnown()) {
++ MWLINKRESOLUTION_url_set($linkResolution,
$title->getLocalURL());
++ MWLINKRESOLUTION_color_set($linkResolution,
MWLINKCOLOR_BLUE);
++ } else {
++ MWLINKRESOLUTION_url_set($linkResolution,
$title->getLocalURL('action=edit&redlink=1'));
++ MWLINKRESOLUTION_color_set($linkResolution,
MWLINKCOLOR_RED);
++ }
++ MWLinkCollectionResolve($linkCollection, $lcKey,
$linkResolution);
++ }
++
++
++ wfProfileOut( __METHOD__ );
++
++}
++
++?>
+\ No newline at end of file
_______________________________________________
MediaWiki-CVS mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-cvs
