MediaWiki internal link handler

linkextract.php

function replaceInternalLinks2( &$s ) {
  static $tc = FALSE, $e1, $e1_img;
  # the % is needed to support urlencoded titles as well
  if ( !$tc ) {
    $tc = Title::legalChars() . '#%';
    # Match a link having the form [[namespace:link|alternate]]trail
    $e1 = "/^([{$tc}]+)(?:\\|(.+?))?]](.*)\$/sD";
    # Match cases where there is no "]]", which might still be images
    $e1_img = "/^([{$tc}]+)\\|(.*)\$/sD";
  }
 
  $holders = new LinkHolderArray( $this );
 
  # split the entire text string on occurrences of [[
  $a = StringUtils::explode( '[[', ' ' . $s );
  # get the first element (all text up to first [[), and remove the space we added
  $s = $a->current();
  $a->next();
  $line = $a->current(); # Workaround for broken ArrayIterator::next() that returns "void"
  $s = substr( $s, 1 );
 
  $useLinkPrefixExtension = $this->getTargetLanguage()->linkPrefixExtension();
  $e2 = null;
  if ( $useLinkPrefixExtension ) {
     # Match the end of a line for a word that's not followed by whitespace,
     # e.g. in the case of 'The Arab al[[Razi]]', 'al' will be matched
     $e2 = wfMessage( 'linkprefix' )->inContentLanguage()->text();
  }
 
  $nottalk = !$this->mTitle->isTalkPage();
 
  if ( $useLinkPrefixExtension ) {
    $m = array();
    if ( preg_match( $e2, $s, $m ) ) {
      $first_prefix = $m[2];
    } else {
      $first_prefix = false;
    }
  } else {
    $prefix = '';
  }
 
  $useSubpages = $this->areSubpagesAllowed();
  wfProfileOut( __METHOD__ . '-setup' );
 
  # Loop for each link
  for ( ; $line !== false && $line !== null ; $a->next(), $line = $a->current() ) {
    if ( $useLinkPrefixExtension ) {
      wfProfileIn( __METHOD__ . '-prefixhandling' );
      if ( preg_match( $e2, $s, $m ) ) {
        $prefix = $m[2];
        $s = $m[1];
      } else {
        $prefix = '';
      }
      # first link
      if ( $first_prefix ) {
        $prefix = $first_prefix;
        $first_prefix = false;
      }
      wfProfileOut( __METHOD__ . '-prefixhandling' );
    }
 
    $might_be_img = false;
 
    wfProfileIn( __METHOD__ . "-e1" );
    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 !== '' && substr( $m[3], 0, 1 ) === ']' && strpos( $text, '[' ) !== false )
      {
        $text .= ']'; # so that replaceExternalLinks($text) works later
        $m[3] = substr( $m[3], 1 );
      }
      # fix up urlencoded title texts
      if ( strpos( $m[1], '%' ) !== false ) {
        # Should anchors '#' also be rejected?
        $m[1] = str_replace( array('<', '>'), array('&lt;', '&gt;'), rawurldecode( $m[1] ) );
      }
      $trail = $m[3];
   } elseif ( preg_match( $e1_img, $line, $m ) ) { # Invalid, but might be an image with a link in its caption
     $might_be_img = true;
     $text = $m[2];
     if ( strpos( $m[1], '%' ) !== false ) {
       $m[1] = rawurldecode( $m[1] );
     }
     $trail = "";
   } else { # Invalid form; output directly
     $s .= $prefix . '[[' . $line ;
     wfProfileOut( __METHOD__ . "-e1" );
     continue;
   }
   wfProfileOut( __METHOD__ . "-e1" );
   wfProfileIn( __METHOD__ . "-misc" );
 
   # Don't allow internal links to pages containing
   # PROTO: where PROTO is a valid URL protocol; these
   # should be external links.
   if ( preg_match( '/^(?i:' . $this->mUrlProtocols . ')/', $m[1] ) ) {
     $s .= $prefix . '[[' . $line ;
     wfProfileOut( __METHOD__ . "-misc" );
     continue;
   }
 
   # Make subpage if necessary
   if ( $useSubpages ) {
     $link = $this->maybeDoSubpageLink( $m[1], $text );
   } else {
     $link = $m[1];
   }
 
   $noforce = ( substr( $m[1], 0, 1 ) !== ':' );
   if ( !$noforce ) {
     # Strip off leading ':'
     $link = substr( $link, 1 );
   }
 
   wfProfileOut( __METHOD__ . "-misc" );
   wfProfileIn( __METHOD__ . "-title" );
   $nt = Title::newFromText( $this->mStripState->unstripNoWiki( $link ) );
   if ( $nt === null ) {
     $s .= $prefix . '[[' . $line;
     wfProfileOut( __METHOD__ . "-title" );
     continue;
   }
 
   $ns = $nt->getNamespace();
   $iw = $nt->getInterWiki();
   wfProfileOut( __METHOD__ . "-title" );
 
   if ( $might_be_img ) { # if this is actually an invalid link
     wfProfileIn( __METHOD__ . "-might_be_img" );
     if ( $ns == NS_FILE && $noforce ) { # but might be an image
       $found = false;
       while ( true ) {
         # look at the next 'line' to see if we can close it there
         $a->next();
         $next_line = $a->current();
         if ( $next_line === false || $next_line === null ) {
           break;
         }
         $m = explode( ']]', $next_line, 3 );
         if ( count( $m ) == 3 ) {
           # the first ]] closes the inner link, the second the image
           $found = true;
           $text .= "[[{$m[0]}]]{$m[1]}";
           $trail = $m[2];
           break;
         } elseif ( count( $m ) == 2 ) {
           # if there's exactly one ]] that's fine, we'll keep looking
           $text .= "[[{$m[0]}]]{$m[1]}";
         } else {
           # if $next_line is invalid too, we need look no further
           $text .= '[[' . $next_line;
           break;
         }
       }
       if ( !$found ) {
         # we couldn't find the end of this imageLink, so output it raw
         # but don't ignore what might be perfectly normal links in the text we've examined
         $holders->merge( $this->replaceInternalLinks2( $text ) );
         $s .= "{$prefix}[[$link|$text";
         # note: no $trail, because without an end, there *is* no trail
         wfProfileOut( __METHOD__ . "-might_be_img" );
         continue;
       }
     } else {
        # it's not an image, so output it raw
       $s .= "{$prefix}[[$link|$text";
       # note: no $trail, because without an end, there *is* no trail
       wfProfileOut( __METHOD__ . "-might_be_img" );
       continue;
     }
     wfProfileOut( __METHOD__ . "-might_be_img" );
   }
 
   $wasblank = ( $text  == '' );
   if ( $wasblank ) {
     $text = $link;
   } else {
     # Bug 4598 madness. Handle the quotes only if they come from the alternate part
     # [[Lista d''e paise d''o munno]] -> <a href="...">Lista d''e paise d''o munno</a>
     # [[Criticism of Harry Potter|Criticism of ''Harry Potter'']]
     #    -> <a href="Criticism of Harry Potter">Criticism of <i>Harry Potter</i></a>
     $text = $this->doQuotes( $text );
   }
 
   # Link not escaped by : , create the various objects
   if ( $noforce ) {
     # Interwikis
     wfProfileIn( __METHOD__ . "-interwiki" );
     if ( $iw && $this->mOptions->getInterwikiMagic() && $nottalk && Language::fetchLanguageName( $iw, null, 'mw' ) ) {
       // XXX: the above check prevents links to sites with identifiers that are not language codes
 
       # Bug 24502: filter duplicates
       if ( !isset( $this->mLangLinkLanguages[$iw] ) ) {
         $this->mLangLinkLanguages[$iw] = true;
         $this->mOutput->addLanguageLink( $nt->getFullText() );
       }

                   $s = rtrim( $s . $prefix );
                   $s .= trim( $trail, "\n" ) == '' ? '': $prefix . $trail;
                   wfProfileOut( __METHOD__ . "-interwiki" );
                   continue;
           }
           wfProfileOut( __METHOD__ . "-interwiki" );
 
           if ( $ns == NS_FILE ) {
                   wfProfileIn( __METHOD__ . "-image" );
                   if ( !wfIsBadImage( $nt->getDBkey(), $this->mTitle ) ) {
                           if ( $wasblank ) {
                                   # if no parameters were passed, $text
                                   # becomes something like "File:Foo.png",
                                   # which we don't want to pass on to the
                                   # image generator
                                   $text = '';
                           } else {
                                   # 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 );
                                   $holders->merge( $this->replaceInternalLinks2( $text ) );
                           }
                           # cloak any absolute URLs inside the image markup, so replaceExternalLinks() won't touch them
                           $s .= $prefix . $this->armorLinks(
                                   $this->makeImage( $nt, $text, $holders ) ) . $trail;
                   } else {
                           $s .= $prefix . $trail;
                   }
                   wfProfileOut( __METHOD__ . "-image" );
                   continue;
           }
 
           if ( $ns == NS_CATEGORY ) {
                   wfProfileIn( __METHOD__ . "-category" );
                   $s = rtrim( $s . "\n" ); # bug 87
 
                   if ( $wasblank ) {
                           $sortkey = $this->getDefaultSort();
                   } else {
                           $sortkey = $text;
                   }
                   $sortkey = Sanitizer::decodeCharReferences( $sortkey );
                   $sortkey = str_replace( "\n", '', $sortkey );
                   $sortkey = $this->getConverterLanguage()->convertCategoryKey( $sortkey );
                   $this->mOutput->addCategory( $nt->getDBkey(), $sortkey );
 
                   $s .= trim( $prefix . $trail, "\n" ) == '' ? '' : $prefix . $trail;
 
                   wfProfileOut( __METHOD__ . "-category" );
                   continue;
           }
   }
 
   # Self-link checking
   if ( $nt->getFragment() === '' && $ns != NS_SPECIAL ) {
     if ( $nt->equals( $this->mTitle ) || ( !$nt->isKnown() && in_array($this->mTitle->getPrefixedText(),$this->getConverterLanguage()->autoConvertToAllVariants( $nt->getPrefixedText() ),true) ) ) {
       $s .= $prefix . Linker::makeSelfLinkObj( $nt, $text, '', $trail );
       continue;
     }
   }
 
   # NS_MEDIA is a pseudo-namespace for linking directly to a file
   # @todo 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
     $options = array();
     $descQuery = false;
     wfRunHooks( 'BeforeParserFetchFileAndTitle', array( $this, $nt, &$options, &$descQuery ) );
     # Fetch and register the file (file title may be different via hooks)
     list( $file, $nt ) = $this->fetchFileAndTitle( $nt, $options );
     # Cloak with NOPARSE to avoid replacement in replaceExternalLinks
     $s .= $prefix . $this->armorLinks(Linker::makeMediaLinkFile( $nt, $file, $text ) ) . $trail;
     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
   #
   # @todo 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() ) {
     $this->mOutput->addLink( $nt );
     $s .= $this->makeKnownLinkHolder( $nt, $text, array(), $trail, $prefix );
   } else {
     # Links will be added to the output link list after checking
     $s .= $holders->makeHolder( $nt, $text, array(), $trail, $prefix );
   }
   wfProfileOut( __METHOD__ . "-always_known" );
  }
  wfProfileOut( __METHOD__ );
  return $holders;
}