From 61bc10203ff076ac0d1e799cabb1f05556c34bfd Mon Sep 17 00:00:00 2001
From: Tim Starling <tstarling@users.mediawiki.org>
Date: Wed, 1 Feb 2006 04:41:53 +0000
Subject: [PATCH] Various improvements to interwiki transclusion. Introduced
 {{raw:..}}, to force raw transclusion when subst: isn't in use. Referer
 header set in wfGetHTTP(), this could be for weak (honour-bound) detection of
 the external site, for statistics or license notices.

---
 RELEASE-NOTES              |   1 +
 includes/HttpFunctions.php |  12 +++-
 includes/MagicWord.php     |   1 +
 includes/Parser.php        | 143 ++++++++++++++++++++++---------------
 includes/Title.php         |  16 ++++-
 languages/Language.php     |   9 +--
 6 files changed, 119 insertions(+), 63 deletions(-)

diff --git a/RELEASE-NOTES b/RELEASE-NOTES
index 695b7441b5..c7cf0fee40 100644
--- a/RELEASE-NOTES
+++ b/RELEASE-NOTES
@@ -258,6 +258,7 @@ Parser:
   character before doing anything with them. This prevents certain kinds of
   spam filter evasion.
 * (bug 4783) : Fix for "{{ns:0}} does not render"
+* Improved support for interwiki transclusion
 
 Upload:
 * (bug 2527) Always set destination filename when new file is selected
diff --git a/includes/HttpFunctions.php b/includes/HttpFunctions.php
index 9dbfe0118d..2c2fd4c0cb 100644
--- a/includes/HttpFunctions.php
+++ b/includes/HttpFunctions.php
@@ -9,7 +9,7 @@
  * if $timeout is 'default', $wgHTTPTimeout is used
  */
 function wfGetHTTP( $url, $timeout = 'default' ) {
-	global $wgHTTPTimeout, $wgHTTPProxy, $wgVersion;
+	global $wgHTTPTimeout, $wgHTTPProxy, $wgVersion, $wgTitle, $wgCommandLineMode;
 
 	# Use curl if available
 	if ( function_exists( 'curl_init' ) ) {
@@ -25,6 +25,16 @@ function wfGetHTTP( $url, $timeout = 'default' ) {
 		}
 		curl_setopt( $c, CURLOPT_TIMEOUT, $timeout );
 		curl_setopt( $c, CURLOPT_USERAGENT, "MediaWiki/$wgVersion" );
+
+		# Set the referer to $wgTitle, even in command-line mode
+		# This is useful for interwiki transclusion, where the foreign
+		# server wants to know what the referring page is.
+		# $_SERVER['REQUEST_URI'] gives a less reliable indication of the 
+		# referring page.
+		if ( is_object( $wgTitle ) ) {
+			curl_setopt( $c, CURLOPT_REFERER, $wgTitle->getFullURL() );
+		}
+
 		ob_start();
 		curl_exec( $c );
 		$text = ob_get_contents();
diff --git a/includes/MagicWord.php b/includes/MagicWord.php
index 2c091654f8..9d0b3bf2fc 100644
--- a/includes/MagicWord.php
+++ b/includes/MagicWord.php
@@ -69,6 +69,7 @@ $magicWords = array(
 	'MAG_UC',
 	'MAG_FULLPAGENAME',
 	'MAG_FULLPAGENAMEE',
+	'MAG_RAW',
 );
 if ( ! defined( 'MEDIAWIKI_INSTALL' ) )
 	wfRunHooks( 'MagicWordMagicWords', array( &$magicWords ) );
diff --git a/includes/Parser.php b/includes/Parser.php
index 5d5c4b4a11..13b5f2e188 100644
--- a/includes/Parser.php
+++ b/includes/Parser.php
@@ -2253,9 +2253,10 @@ class Parser
 	 *
 	 * @param string $tex The text to transform
 	 * @param array $args Key-value pairs representing template parameters to substitute
+	 * @param bool $argsOnly Only do argument (triple-brace) expansion, not double-brace expansion
 	 * @access private
 	 */
-	function replaceVariables( $text, $args = array() ) {
+	function replaceVariables( $text, $args = array(), $argsOnly = false ) {
 		# Prevent too big inclusions
 		if( strlen( $text ) > MAX_INCLUDE_SIZE ) {
 			return $text;
@@ -2268,7 +2269,9 @@ class Parser
 		array_push( $this->mArgStack, $args );
 
 		$braceCallbacks = array();
-		$braceCallbacks[2] = array( &$this, 'braceSubstitution' );
+		if ( !$argsOnly ) {
+			$braceCallbacks[2] = array( &$this, 'braceSubstitution' );
+		}
 		if ( $this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI ) {
 			$braceCallbacks[3] = array( &$this, 'argSubstitution' );
 		}
@@ -2356,12 +2359,16 @@ class Parser
 		$fname = 'Parser::braceSubstitution';
 		wfProfileIn( $fname );
 
-		$found = false;
-		$nowiki = false;
-		$noparse = false;
-		$replaceHeadings = false;
-		$isHTML = false;
+		# Flags 
+		$found = false;             # $text has been filled
+		$nowiki = false;            # wiki markup in $text should be escaped
+		$noparse = false;           # Unsafe HTML tags should not be stripped, etc.
+		$noargs = false;            # Don't replace triple-brace arguments in $text
+		$replaceHeadings = false;   # Make the edit section links go to the template not the article
+		$isHTML = false;            # $text is HTML, armour it against wikitext transformation
+		$forceRawInterwiki = false; # Force interwiki transclusion to be done in raw mode not rendered
 
+		# Title object, where $text came from
 		$title = NULL;
 
 		$linestart = '';
@@ -2378,6 +2385,7 @@ class Parser
 				$text = $replaceWith;
 				$found = true;
 				$noparse = true;
+				$noargs = true;
 			}
 		}
 
@@ -2395,10 +2403,11 @@ class Parser
 				$text = $piece['text'];
 				$found = true;
 				$noparse = true;
+				$noargs = true;
 			}
 		}
 
-		# MSG, MSGNW and INT
+		# MSG, MSGNW, INT and RAW
 		if ( !$found ) {
 			# Check for MSGNW:
 			$mwMsgnw =& MagicWord::get( MAG_MSGNW );
@@ -2409,7 +2418,13 @@ class Parser
 				$mwMsg =& MagicWord::get( MAG_MSG );
 				$mwMsg->matchStartAndRemove( $part1 );
 			}
-
+			
+			# Check for RAW:
+			$mwRaw =& MagicWord::get( MAG_RAW );
+			if ( $mwRaw->matchStartAndRemove( $part1 ) ) {
+				$forceRawInterwiki = true;
+			}
+			
 			# Check if it is an internal message
 			$mwInt =& MagicWord::get( MAG_INT );
 			if ( $mwInt->matchStartAndRemove( $part1 ) ) {
@@ -2515,12 +2530,13 @@ class Parser
 
 		# Did we encounter this template already? If yes, it is in the cache
 		# and we need to check for loops.
-		if ( !$found && isset( $this->mTemplates[$part1] ) ) {
+		if ( !$found && isset( $this->mTemplates[$piece['title']] ) ) {
 			$found = true;
 
 			# Infinite loop test
 			if ( isset( $this->mTemplatePath[$part1] ) ) {
 				$noparse = true;
+				$noargs = true;
 				$found = true;
 				$text = $linestart .
 					'{{' . $part1 . '}}' .
@@ -2528,7 +2544,7 @@ class Parser
 				wfDebug( "$fname: template loop broken at '$part1'\n" );
 			} else {
 				# set $text to cached message.
-				$text = $linestart . $this->mTemplates[$part1];
+				$text = $linestart . $this->mTemplates[$piece['title']];
 			}
 		}
 
@@ -2553,6 +2569,7 @@ class Parser
 							if ( is_string( $text ) ) {
 								$found = true;
 								$noparse = true;
+								$noargs = true;
 								$isHTML = true;
 								$this->disableCache();
 							}
@@ -2571,23 +2588,26 @@ class Parser
 						$text = '[['.$title->getPrefixedText().']]';
 						$found = true;
 					}
-
-					# Template cache array insertion
-					if( $found ) {
-						$this->mTemplates[$part1] = $text;
-						$text = $linestart . $text;
-					}
 				} elseif ( $title->isTrans() ) {
 					// Interwiki transclusion
-					if ( $this->mOutputType == OT_HTML ) {
+					if ( $this->mOutputType == OT_HTML && !$forceRawInterwiki ) {
 						$text = $this->interwikiTransclude( $title, 'render' );
 						$isHTML = true;
 						$noparse = true;
 					} else {
 						$text = $this->interwikiTransclude( $title, 'raw' );
+						$replaceHeadings = true;
 					}
 					$found = true;
 				}
+				
+				# Template cache array insertion
+				# Use the original $piece['title'] not the mangled $part1, so that
+				# modifiers such as RAW: produce separate cache entries
+				if( $found ) {
+					$this->mTemplates[$piece['title']] = $text;
+					$text = $linestart . $text;
+				}
 			}
 		}
 
@@ -2595,51 +2615,60 @@ class Parser
 		# Only for HTML output
 		if ( $nowiki && $found && $this->mOutputType == OT_HTML ) {
 			$text = wfEscapeWikiText( $text );
-		} elseif ( ($this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI) && $found && !$noparse) {
-			# Clean up argument array
-			$assocArgs = array();
-			$index = 1;
-			foreach( $args as $arg ) {
-				$eqpos = strpos( $arg, '=' );
-				if ( $eqpos === false ) {
-					$assocArgs[$index++] = $arg;
-				} else {
-					$name = trim( substr( $arg, 0, $eqpos ) );
-					$value = trim( substr( $arg, $eqpos+1 ) );
-					if ( $value === false ) {
-						$value = '';
-					}
-					if ( $name !== false ) {
-						$assocArgs[$name] = $value;
+		} elseif ( ($this->mOutputType == OT_HTML || $this->mOutputType == OT_WIKI) && $found ) {
+			if ( !$noargs ) {
+				# Clean up argument array
+				$assocArgs = array();
+				$index = 1;
+				foreach( $args as $arg ) {
+					$eqpos = strpos( $arg, '=' );
+					if ( $eqpos === false ) {
+						$assocArgs[$index++] = $arg;
+					} else {
+						$name = trim( substr( $arg, 0, $eqpos ) );
+						$value = trim( substr( $arg, $eqpos+1 ) );
+						if ( $value === false ) {
+							$value = '';
+						}
+						if ( $name !== false ) {
+							$assocArgs[$name] = $value;
+						}
 					}
 				}
-			}
 
-			# Add a new element to the templace recursion path
-			$this->mTemplatePath[$part1] = 1;
-
-			# If there are any <onlyinclude> tags, only include them
-			if ( in_string( '<onlyinclude>', $text ) && in_string( '</onlyinclude>', $text ) ) {
-				preg_match_all( '/<onlyinclude>(.*?)\n?<\/onlyinclude>/s', $text, $m );
-				$text = '';
-				foreach ($m[1] as $piece)
-					$text .= $piece;
+				# Add a new element to the templace recursion path
+				$this->mTemplatePath[$part1] = 1;
 			}
-			# Remove <noinclude> sections and <includeonly> tags
-			$text = preg_replace( '/<noinclude>.*?<\/noinclude>/s', '', $text );
-			$text = strtr( $text, array( '<includeonly>' => '' , '</includeonly>' => '' ) );
 
-			if( $this->mOutputType == OT_HTML ) {
-				# Strip <nowiki>, <pre>, etc.
-				$text = $this->strip( $text, $this->mStripState );
-				$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ), $assocArgs );
-			}
-			$text = $this->replaceVariables( $text, $assocArgs );
+			if ( !$noparse ) {
+				# If there are any <onlyinclude> tags, only include them
+				if ( in_string( '<onlyinclude>', $text ) && in_string( '</onlyinclude>', $text ) ) {
+					preg_match_all( '/<onlyinclude>(.*?)\n?<\/onlyinclude>/s', $text, $m );
+					$text = '';
+					foreach ($m[1] as $piece)
+						$text .= $piece;
+				}
+				# Remove <noinclude> sections and <includeonly> tags
+				$text = preg_replace( '/<noinclude>.*?<\/noinclude>/s', '', $text );
+				$text = strtr( $text, array( '<includeonly>' => '' , '</includeonly>' => '' ) );
+
+				if( $this->mOutputType == OT_HTML ) {
+					# Strip <nowiki>, <pre>, etc.
+					$text = $this->strip( $text, $this->mStripState );
+					$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'replaceVariables' ), $assocArgs );
+				}
+				$text = $this->replaceVariables( $text, $assocArgs );
 
-			# If the template begins with a table or block-level
-			# element, it should be treated as beginning a new line.
-			if (!$piece['lineStart'] && preg_match('/^({\\||:|;|#|\*)/', $text)) {
-				$text = "\n" . $text;
+				# If the template begins with a table or block-level
+				# element, it should be treated as beginning a new line.
+				if (!$piece['lineStart'] && preg_match('/^({\\||:|;|#|\*)/', $text)) {
+					$text = "\n" . $text;
+				}
+			} elseif ( !$noargs ) {
+				# $noparse and !$noargs
+				# Just replace the arguments, not any double-brace items
+				# This is used for rendered interwiki transclusion
+				$text = $this->replaceVariables( $text, $assocArgs, true );
 			}
 		}
 		# Prune lower levels off the recursion check path
diff --git a/includes/Title.php b/includes/Title.php
index 40c0f52a9f..4cbaa14908 100644
--- a/includes/Title.php
+++ b/includes/Title.php
@@ -494,7 +494,7 @@ class Title {
 	function isTrans() {
 		global $wgTitleInterwikiCache, $wgDBname;
 
-		if ($this->mInterwiki == '' || !$this->isLocal())
+		if ($this->mInterwiki == '')
 			return false;
 		# Make sure key is loaded into cache
 		$this->getInterwikiLink( $this->mInterwiki );
@@ -752,6 +752,13 @@ class Title {
 
 		if ( $this->isExternal() ) {
 			$url = $this->getFullURL();
+			if ( $query ) {
+				// This is currently only used for edit section links in the 
+				// context of interwiki transclusion. In theory we should 
+				// append the query to the end of any existing query string,
+				// but interwiki transclusion is already broken in that case.
+				$url .= "?$query";
+			}
 		} else {
 			$dbkey = wfUrlencode( $this->getPrefixedDBkey() );
 			if ( $query == '' ) {
@@ -1344,6 +1351,13 @@ class Title {
 						# Do another namespace split...
 						continue;
 					}
+
+					# If there's an initial colon after the interwiki, that also 
+					# resets the default namespace
+					if ( $t !== '' && $t[0] == ':' ) {
+						$this->mNamespace = NS_MAIN;
+						$t = substr( $t, 1 );
+					}
 				}
 				# If there's no recognized interwiki or namespace,
 				# then let the colon expression be part of the title.
diff --git a/languages/Language.php b/languages/Language.php
index 33e96b4447..1df20e6a8a 100644
--- a/languages/Language.php
+++ b/languages/Language.php
@@ -253,10 +253,11 @@ $wgLanguageNamesEn =& $wgLanguageNames;
 	MAG_PLURAL               => array( 0,    'PLURAL:'                ),
 	MAG_FULLURL              => array( 0,    'FULLURL:'               ),
 	MAG_FULLURLE             => array( 0,    'FULLURLE:'              ),
-	MAG_LCFIRST		 => array( 0,    'LCFIRST:'               ),
-	MAG_UCFIRST		 => array( 0,    'UCFIRST:'               ),
-	MAG_LC			 => array( 0,    'LC:'                    ),
-	MAG_UC			 => array( 0,    'UC:'                    ),
+	MAG_LCFIRST              => array( 0,    'LCFIRST:'               ),
+	MAG_UCFIRST              => array( 0,    'UCFIRST:'               ),
+	MAG_LC                   => array( 0,    'LC:'                    ),
+	MAG_UC                   => array( 0,    'UC:'                    ),
+	MAG_RAW                  => array( 0,    'RAW:'                   ),
 );
 
 if (!$wgCachedMessageArrays) {
-- 
2.20.1