$text = Sanitizer::normalizeCharReferences( $text );
- if (($wgUseTidy and $this->mOptions->mTidy) or $wgAlwaysUseTidy) {
- $text = self::tidy($text);
+ if ( ( $wgUseTidy && $this->mOptions->mTidy ) || $wgAlwaysUseTidy ) {
+ $text = MWTidy::tidy( $text );
} else {
# attempt to sanitize at least some nesting problems
# (bug #2702 and quite a few others)
$this->mStripState->general->setPair( $rnd, $text );
return $rnd;
}
-
- /**
- * 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
- * @public
- * @static
- */
- 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>';
-
- # Tidy is known to clobber tabs; convert 'em to entities
- $wrappedtext = str_replace("\t", '	', $wrappedtext);
-
- if( $wgTidyInternal ) {
- $correctedtext = self::internalTidy( $wrappedtext );
- } else {
- $correctedtext = self::externalTidy( $wrappedtext );
- }
- if( is_null( $correctedtext ) ) {
- wfDebug( "Tidy error detected!\n" );
- return $text . "\n<!-- Tidy found serious XHTML errors -->\n";
- }
-
- # Convert the tabs back from entities
- $correctedtext = str_replace('	', "\t", $correctedtext);
-
- return $correctedtext;
- }
-
- /**
- * Spawn an external HTML tidy process and get corrected markup back from it.
- *
- * @private
- * @static
- */
- function externalTidy( $text ) {
- global $wgTidyConf, $wgTidyBin, $wgTidyOpts;
- wfProfileIn( __METHOD__ );
-
- $cleansource = '';
- $opts = ' -utf8';
-
- $descriptorspec = array(
- 0 => array('pipe', 'r'),
- 1 => array('pipe', 'w'),
- 2 => array('file', wfGetNull(), 'a')
- );
- $pipes = array();
- if( function_exists('proc_open') ) {
- $process = proc_open("$wgTidyBin -config $wgTidyConf $wgTidyOpts$opts", $descriptorspec, $pipes);
- if (is_resource($process)) {
- // Theoretically, this style of communication could cause a deadlock
- // here. If the stdout buffer fills up, then writes to stdin could
- // block. This doesn't appear to happen with tidy, because tidy only
- // writes to stdout after it's finished reading from stdin. Search
- // for tidyParseStdin and tidySaveStdout in console/tidy.c
- fwrite($pipes[0], $text);
- fclose($pipes[0]);
- while (!feof($pipes[1])) {
- $cleansource .= fgets($pipes[1], 1024);
- }
- fclose($pipes[1]);
- proc_close($process);
- }
- }
-
- wfProfileOut( __METHOD__ );
-
- if( $cleansource == '' && $text != '') {
- // 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.
- *
- * 'pear install tidy' should be able to compile the extension module.
- *
- * @private
- * @static
+ * Interface with html tidy
+ * @deprecated Use MWTidy::tidy()
*/
- function internalTidy( $text ) {
- global $wgTidyConf, $IP, $wgDebugTidy;
- wfProfileIn( __METHOD__ );
-
- $tidy = new tidy;
- $tidy->parseString( $text, $wgTidyConf, 'utf8' );
- $tidy->cleanRepair();
- if( $tidy->getStatus() == 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( $tidy );
- }
- if ( $wgDebugTidy && $tidy->getStatus() > 0 ) {
- $cleansource .= "<!--\nTidy reports:\n" .
- str_replace( '-->', '-->', $tidy->errorBuffer ) .
- "\n-->";
- }
-
- wfProfileOut( __METHOD__ );
- return $cleansource;
+ public static function tidy( $text ) {
+ wfDeprecated( __METHOD__ );
+ return MWTidy::tidy( $text );
}
/**
$text = $this->doDoubleUnderscore( $text );
$text = $this->doHeadings( $text );
- if($this->mOptions->getUseDynamicDates()) {
+ if( $this->mOptions->getUseDynamicDates() ) {
$df = DateFormatter::getInstance();
$text = $df->reformat( $this->mOptions->getDateFormat(), $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);
+ $text = str_replace($this->mUniqPrefix.'NOPARSE', '', $text);
$text = $this->doMagicLinks( $text );
$text = $this->formatHeadings( $text, $isMain );
}
function magicLinkCallback( $m ) {
- if ( isset( $m[1] ) && strval( $m[1] ) !== '' ) {
+ if ( isset( $m[1] ) && $m[1] !== '' ) {
# Skip anchor
return $m[0];
- } elseif ( isset( $m[2] ) && strval( $m[2] ) !== '' ) {
+ } elseif ( isset( $m[2] ) && $m[2] !== '' ) {
# Skip HTML element
return $m[0];
- } elseif ( isset( $m[3] ) && strval( $m[3] ) !== '' ) {
+ } elseif ( isset( $m[3] ) && $m[3] !== '' ) {
# Free external link
return $this->makeFreeExternalLink( $m[0] );
- } elseif ( isset( $m[4] ) && strval( $m[4] ) !== '' ) {
+ } elseif ( isset( $m[4] ) && $m[4] !== '' ) {
# RFC or PMID
if ( substr( $m[0], 0, 3 ) === 'RFC' ) {
$keyword = 'RFC';
$sk = $this->mOptions->getSkin();
$la = $sk->getExternalLinkAttributes( $url, $keyword.$id );
return "<a href=\"{$url}\"{$la}>{$keyword} {$id}</a>";
- } elseif ( isset( $m[5] ) && strval( $m[5] ) !== '' ) {
+ } elseif ( isset( $m[5] ) && $m[5] !== '' ) {
# ISBN
$isbn = $m[5];
$num = strtr( $isbn, array(
if ( $text === false ) {
# Not an image, make a link
$text = $sk->makeExternalLink( $url, $wgContLang->markNoConversion($url), true, 'free',
- $this->getExternalLinkAttribs() );
+ $this->getExternalLinkAttribs( $url ) );
# Register it in the output object...
# Replace unnecessary URL escape codes with their equivalent characters
$pasteurized = self::replaceUnusualEscapes( $url );
$url = Sanitizer::cleanUrl( $url );
- if ( $this->mOptions->mExternalLinkTarget ) {
- $attribs = array( 'target' => $this->mOptions->mExternalLinkTarget );
- } else {
- $attribs = array();
- }
-
# 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
# This was changed in August 2004
- $s .= $sk->makeExternalLink( $url, $text, false, $linktype, $this->getExternalLinkAttribs() )
- . $dtrail . $trail;
+ $s .= $sk->makeExternalLink( $url, $text, false, $linktype,
+ $this->getExternalLinkAttribs( $url ) ) . $dtrail . $trail;
# Register link in the output object.
# Replace unnecessary URL escape codes with the referenced character
return $s;
}
- function getExternalLinkAttribs() {
+ /**
+ * Get an associative array of additional HTML attributes appropriate for a
+ * particular external link. This currently may include rel => nofollow
+ * (depending on configuration, namespace, and the URL's domain) and/or a
+ * target attribute (depending on configuration).
+ *
+ * @param string $url Optional URL, to extract the domain from for rel =>
+ * nofollow if appropriate
+ * @return array Associative array of HTML attributes
+ */
+ function getExternalLinkAttribs( $url = false ) {
$attribs = array();
global $wgNoFollowLinks, $wgNoFollowNsExceptions;
$ns = $this->mTitle->getNamespace();
if( $wgNoFollowLinks && !in_array($ns, $wgNoFollowNsExceptions) ) {
$attribs['rel'] = 'nofollow';
+
+ global $wgNoFollowDomainExceptions;
+ if ( $wgNoFollowDomainExceptions ) {
+ $bits = wfParseUrl( $url );
+ if ( is_array( $bits ) && isset( $bits['host'] ) ) {
+ foreach ( $wgNoFollowDomainExceptions as $domain ) {
+ if( substr( $bits['host'], -strlen( $domain ) )
+ == $domain ) {
+ unset( $attribs['rel'] );
+ break;
+ }
+ }
+ }
+ }
}
if ( $this->mOptions->getExternalLinkTarget() ) {
$attribs['target'] = $this->mOptions->getExternalLinkTarget();
wfProfileOut( __METHOD__."-misc" );
wfProfileIn( __METHOD__."-title" );
$nt = Title::newFromText( $this->mStripState->unstripNoWiki($link) );
- if( !$nt ) {
+ if( $nt === NULL ) {
$s .= $prefix . '[[' . $line;
wfProfileOut( __METHOD__."-title" );
continue;
# NS_MEDIA is a pseudo-namespace for linking directly to a file
# FIXME: Should do batch file existence checks, see comment below
if( $ns == NS_MEDIA ) {
+ wfProfileIn( __METHOD__."-media" );
# Give extensions a chance to select the file revision for us
$skip = $time = false;
wfRunHooks( 'BeforeParserMakeImageLinkObj', array( &$this, &$nt, &$skip, &$time ) );
# Cloak with NOPARSE to avoid replacement in replaceExternalLinks
$s .= $prefix . $this->armorLinks( $link ) . $trail;
$this->mOutput->addImage( $nt->getDBkey() );
+ wfProfileOut( __METHOD__."-media" );
continue;
}
+ wfProfileIn( __METHOD__."-always_known" );
# Some titles, such as valid special pages or files in foreign repos, should
# be shown as bluelinks even though they're not included in the page table
#
# FIXME: isAlwaysKnown() can be expensive for file links; we should really do
# batch file existence checks for NS_FILE and NS_MEDIA
if( $iw == '' && $nt->isAlwaysKnown() ) {
- # Need to add file links to parser output here or else they won't end up
- # in the pagelinks table later
- if( $ns == NS_FILE ) {
- $this->mOutput->addLink( $nt );
- }
+ $this->mOutput->addLink( $nt );
$s .= $this->makeKnownLinkHolder( $nt, $text, '', $trail, $prefix );
} else {
+ # Links will be added to the output link list after checking
$s .= $holders->makeHolder( $nt, $text, '', $trail, $prefix );
}
+ wfProfileOut( __METHOD__."-always_known" );
}
wfProfileOut( __METHOD__ );
return $holders;
$inBlockElem = true;
}
} else if ( !$inBlockElem && !$this->mInPre ) {
- if ( ' ' == $t{0} and ( $this->mLastSection === 'pre' or trim($t) != '' ) ) {
+ if ( ' ' == substr( $t, 0, 1 ) and ( $this->mLastSection === 'pre' or trim($t) != '' ) ) {
// pre
if ($this->mLastSection !== 'pre') {
$paragraphStack = false;
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONTIMESTAMP}} used, setting vary-revision...\n" );
return $this->getRevisionTimestamp();
+ case 'revisionuser':
+ // Let the edit saving system know we should parse the page
+ // *after* a revision ID has been assigned. This is for null edits.
+ $this->mOutput->setFlag( 'vary-revision' );
+ wfDebug( __METHOD__ . ": {{REVISIONUSER}} used, setting vary-revision...\n" );
+ return $this->getRevisionUser();
case 'namespace':
return str_replace('_',' ',$wgContLang->getNsText( $this->mTitle->getNamespace() ) );
case 'namespacee':
return $this->mVarCache[$index] = $wgContLang->formatNum( SiteStats::images() );
case 'numberofusers':
return $this->mVarCache[$index] = $wgContLang->formatNum( SiteStats::users() );
+ case 'numberofactiveusers':
+ return $this->mVarCache[$index] = $wgContLang->formatNum( SiteStats::activeUsers() );
case 'numberofpages':
return $this->mVarCache[$index] = $wgContLang->formatNum( SiteStats::pages() );
case 'numberofadmins':
* @private
*/
function replaceVariables( $text, $frame = false, $argsOnly = false ) {
- # Prevent too big inclusions
- if( strlen( $text ) > $this->mOptions->getMaxIncludeSize() ) {
+ # Is there any text? Also, Prevent too big inclusions!
+ if ( strlen( $text ) < 1 || strlen( $text ) > $this->mOptions->getMaxIncludeSize() ) {
return $text;
}
-
wfProfileIn( __METHOD__ );
if ( $frame === false ) {
* @private
*/
function braceSubstitution( $piece, $frame ) {
- global $wgContLang, $wgAllowDisplayTitle, $wgNonincludableNamespaces;
+ global $wgContLang, $wgNonincludableNamespaces;
wfProfileIn( __METHOD__ );
wfProfileIn( __METHOD__.'-setup' );
throw new MWException( '<html> extension tag encountered unexpectedly' );
}
case 'nowiki':
+ $content = strtr($content, array('-{' => '-{', '}-' => '}-'));
$output = Xml::escapeTagsOnly( $content );
break;
case 'math':
* Fills $this->mDoubleUnderscores, returns the modified text
*/
function doDoubleUnderscore( $text ) {
+ wfProfileIn( __METHOD__ );
// The position of __TOC__ needs to be recorded
$mw = MagicWord::get( 'toc' );
if( $mw->match( $text ) ) {
} elseif( isset( $this->mDoubleUnderscores['index'] ) ) {
$this->mOutput->setIndexPolicy( 'index' );
}
-
+ wfProfileOut( __METHOD__ );
return $text;
}
}
# Inhibit editsection links if requested in the page
- if ( isset( $this->mDoubleUnderscores['noeditsection'] ) ) {
+ if ( isset( $this->mDoubleUnderscores['noeditsection'] ) || $this->mOptions->getIsPrintable() ) {
$showEditLink = 0;
}
$this->mOutput->setNewSection( true );
}
+ # Allow user to remove the "new section"
+ # link via __NONEWSECTIONLINK__
+ if ( isset( $this->mDoubleUnderscores['nonewsectionlink'] ) ) {
+ $this->mOutput->hideNewSection( true );
+ }
+
# if the string __FORCETOC__ (not case-sensitive) occurs in the HTML,
# override above conditions and always show TOC above first header
if ( isset( $this->mDoubleUnderscores['forcetoc'] ) ) {
# Save headline for section edit hint before it's escaped
$headlineHint = $safeHeadline;
- $safeHeadline = Sanitizer::escapeId( $safeHeadline,
- $wgEnforceHtmlIds ? array() : 'xml' );
- # HTML names must be case-insensitively unique (bug 10721)
+
+ if ( $wgEnforceHtmlIds ) {
+ $legacyHeadline = false;
+ $safeHeadline = Sanitizer::escapeId( $safeHeadline,
+ 'noninitial' );
+ } else {
+ # For reverse compatibility, provide an id that's
+ # HTML4-compatible, like we used to.
+ #
+ # It may be worth noting, academically, that it's possible for
+ # the legacy anchor to conflict with a non-legacy headline
+ # anchor on the page. In this case likely the "correct" thing
+ # would be to either drop the legacy anchors or make sure
+ # they're numbered first. However, this would require people
+ # to type in section names like "abc_.D7.93.D7.90.D7.A4"
+ # manually, so let's not bother worrying about it.
+ $legacyHeadline = Sanitizer::escapeId( $safeHeadline,
+ 'noninitial' );
+ $safeHeadline = Sanitizer::escapeId( $safeHeadline, 'xml' );
+
+ if ( $legacyHeadline == $safeHeadline ) {
+ # No reason to have both (in fact, we can't)
+ $legacyHeadline = false;
+ } elseif ( $legacyHeadline != Sanitizer::escapeId(
+ $legacyHeadline, 'xml' ) ) {
+ # The legacy id is invalid XML. We used to allow this, but
+ # there's no reason to do so anymore. Backward
+ # compatibility will fail slightly in this case, but it's
+ # no big deal.
+ $legacyHeadline = false;
+ }
+ }
+
+ # HTML names must be case-insensitively unique (bug 10721). FIXME:
+ # Does this apply to Unicode characters? Because we aren't
+ # handling those here.
$arrayKey = strtolower( $safeHeadline );
+ if ( $legacyHeadline === false ) {
+ $legacyArrayKey = false;
+ } else {
+ $legacyArrayKey = strtolower( $legacyHeadline );
+ }
# count how many in assoc. array so we can track dupes in anchors
- isset( $refers[$arrayKey] ) ? $refers[$arrayKey]++ : $refers[$arrayKey] = 1;
- $refcount[$headlineCount] = $refers[$arrayKey];
+ if ( isset( $refers[$arrayKey] ) ) {
+ $refers[$arrayKey]++;
+ } else {
+ $refers[$arrayKey] = 1;
+ }
+ if ( isset( $refers[$legacyArrayKey] ) ) {
+ $refers[$legacyArrayKey]++;
+ } else {
+ $refers[$legacyArrayKey] = 1;
+ }
# Don't number the heading if it is the only one (looks silly)
if( $doNumberHeadings && count( $matches[3] ) > 1) {
# Create the anchor for linking from the TOC to the section
$anchor = $safeHeadline;
- if($refcount[$headlineCount] > 1 ) {
- $anchor .= '_' . $refcount[$headlineCount];
+ $legacyAnchor = $legacyHeadline;
+ if ( $refers[$arrayKey] > 1 ) {
+ $anchor .= '_' . $refers[$arrayKey];
+ }
+ if ( $legacyHeadline !== false && $refers[$legacyArrayKey] > 1 ) {
+ $legacyAnchor .= '_' . $refers[$legacyArrayKey];
}
if( $enoughToc && ( !isset($wgMaxTocLevel) || $toclevel<$wgMaxTocLevel ) ) {
$toc .= $sk->tocLine($anchor, $tocline, $numbering, $toclevel);
} else {
$editlink = '';
}
- $head[$headlineCount] = $sk->makeHeadline( $level, $matches['attrib'][$headlineCount], $anchor, $headline, $editlink );
+ $head[$headlineCount] = $sk->makeHeadline( $level,
+ $matches['attrib'][$headlineCount], $anchor, $headline,
+ $editlink, $legacyAnchor );
$headlineCount++;
}
putenv( 'TZ='.$wgLocaltimezone );
$ts = date( 'YmdHis', $unixts );
$tz = date( 'T', $unixts ); # might vary on DST changeover!
+
+ /* Allow translation of timezones trough wiki. date() can return
+ * whatever crap the system uses, localised or not, so we cannot
+ * ship premade translations.
+ */
+ $key = 'timezone-' . strtolower( trim( $tz ) );
+ $value = wfMsgForContent( $key );
+ if ( !wfEmptyMsg( $key, $value ) ) $tz = $value;
+
putenv( 'TZ='.$oldtz );
}
// Output the replacement text
// Add two newlines on -- trailing whitespace in $newText is conventionally
// stripped by the editor, so we need both newlines to restore the paragraph gap
- $outText .= $newText . "\n\n";
+ // Only add trailing whitespace if there is newText
+ if($newText != "") {
+ $outText .= $newText . "\n\n";
+ }
+
while ( $node ) {
$outText .= $frame->expand( $node, PPFrame::RECOVER_ORIG );
$node = $node->getNextSibling();
return $this->mRevisionTimestamp;
}
+ /**
+ * Get the name of the user that edited the last revision
+ */
+ function getRevisionUser() {
+ // if this template is subst: the revision id will be blank,
+ // so just use the current user's name
+ if( $this->mRevisionId ) {
+ $revision = Revision::newFromId( $this->mRevisionId );
+ $revuser = $revision->getUserText();
+ } else {
+ global $wgUser;
+ $revuser = $wgUser->getName();
+ }
+ return $revuser;
+ }
+
/**
* Mutator for $mDefaultSort
*
}
return $out;
}
+
+ function serialiseHalfParsedText( $text ) {
+ $data = array();
+ $data['text'] = $text;
+
+ // First, find all strip markers, and store their
+ // data in an array.
+ $stripState = new StripState;
+ $pos = 0;
+ while( ( $start_pos = strpos( $text, $this->mUniqPrefix, $pos ) ) && ( $end_pos = strpos( $text, self::MARKER_SUFFIX, $pos ) ) ) {
+ $end_pos += strlen( self::MARKER_SUFFIX );
+ $marker = substr( $text, $start_pos, $end_pos-$start_pos );
+
+ if ( !empty( $this->mStripState->general->data[$marker] ) ) {
+ $replaceArray = $stripState->general;
+ $stripText = $this->mStripState->general->data[$marker];
+ } elseif ( !empty( $this->mStripState->nowiki->data[$marker] ) ) {
+ $replaceArray = $stripState->nowiki;
+ $stripText = $this->mStripState->nowiki->data[$marker];
+ } else {
+ throw new MWException( "Hanging strip marker: '$marker'." );
+ }
+
+ $replaceArray->setPair( $marker, $stripText );
+ $pos = $end_pos;
+ }
+ $data['stripstate'] = $stripState;
+
+ // Now, find all of our links, and store THEIR
+ // data in an array! :)
+ $links = array( 'internal' => array(), 'interwiki' => array() );
+ $pos = 0;
+
+ // Internal links
+ while( ( $start_pos = strpos( $text, '<!--LINK ', $pos ) ) ) {
+ list( $ns, $trail ) = explode( ':', substr( $text, $start_pos + strlen( '<!--LINK ' ) ), 2 );
+
+ $ns = trim($ns);
+ if (empty( $links['internal'][$ns] )) {
+ $links['internal'][$ns] = array();
+ }
+
+ $key = trim( substr( $trail, 0, strpos( $trail, '-->' ) ) );
+ $links['internal'][$ns][] = $this->mLinkHolders->internals[$ns][$key];
+ $pos = $start_pos + strlen( "<!--LINK $ns:$key-->" );
+ }
+
+ $pos = 0;
+
+ // Interwiki links
+ while( ( $start_pos = strpos( $text, '<!--IWLINK ', $pos ) ) ) {
+ $data = substr( $text, $start_pos );
+ $key = trim( substr( $data, 0, strpos( $data, '-->' ) ) );
+ $links['interwiki'][] = $this->mLinkHolders->interwiki[$key];
+ $pos = $start_pos + strlen( "<!--IWLINK $key-->" );
+ }
+
+ $data['linkholder'] = $links;
+
+ return $data;
+ }
+
+ function unserialiseHalfParsedText( $data, $intPrefix = null /* Unique identifying prefix */ ) {
+ if (!$intPrefix)
+ $intPrefix = $this->getRandomString();
+
+ // First, extract the strip state.
+ $stripState = $data['stripstate'];
+ $this->mStripState->general->merge( $stripState->general );
+ $this->mStripState->nowiki->merge( $stripState->nowiki );
+
+ // Now, extract the text, and renumber links
+ $text = $data['text'];
+ $links = $data['linkholder'];
+
+ // Internal...
+ foreach( $links['internal'] as $ns => $nsLinks ) {
+ foreach( $nsLinks as $key => $entry ) {
+ $newKey = $intPrefix . '-' . $key;
+ $this->mLinkHolders->internals[$ns][$newKey] = $entry;
+
+ $text = str_replace( "<!--LINK $ns:$key-->", "<!--LINK $ns:$newKey-->", $text );
+ }
+ }
+
+ // Interwiki...
+ foreach( $links['interwiki'] as $key => $entry ) {
+ $newKey = "$intPrefix-$key";
+ $this->mLinkHolders->interwikis[$newKey] = $entry;
+
+ $text = str_replace( "<!--IWLINK $key-->", "<!--IWLINK $newKey-->", $text );
+ }
+
+ // Should be good to go.
+ return $text;
+ }
}
/**
dépôts / lhc / web / wiklou.git / blobdiff