X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguageConverter.php;h=61a967dc46d9a2367ba61aef496dcd1f0870c455;hb=91ec64c80719f002426ada7aa1ed62b465c66a0a;hp=c5ff9d65a77dde5728c1c1c3ff2382883eadd161;hpb=b5e255e914f0fe70890f8ac61d9d19476699873e;p=lhc%2Fweb%2Fwiklou.git

diff --git a/languages/LanguageConverter.php b/languages/LanguageConverter.php
index c5ff9d65a7..61a967dc46 100644
--- a/languages/LanguageConverter.php
+++ b/languages/LanguageConverter.php
@@ -21,6 +21,7 @@
 use MediaWiki\MediaWikiServices;
 
 use MediaWiki\Logger\LoggerFactory;
+use MediaWiki\Storage\RevisionRecord;
 
 /**
  * Base class for language conversion.
@@ -391,27 +392,30 @@ class LanguageConverter {
 		   IMPORTANT: Beware of failure from pcre.backtrack_limit (T124404).
 		   Minimize use of backtracking where possible.
 		*/
-		$marker = '|' . Parser::MARKER_PREFIX . '[^\x7f]++\x7f';
-
-		// this one is needed when the text is inside an HTML markup
-		$htmlfix = '|<[^>\004]++(?=\004$)|^[^<>]*+>';
-
-		// Optimize for the common case where these tags have
-		// few or no children. Thus try and possesively get as much as
-		// possible, and only engage in backtracking when we hit a '<'.
-
-		// disable convert to variants between <code> tags
-		$codefix = '<code>[^<]*+(?:(?:(?!<\/code>).)[^<]*+)*+<\/code>|';
-		// disable conversion of <script> tags
-		$scriptfix = '<script[^>]*+>[^<]*+(?:(?:(?!<\/script>).)[^<]*+)*+<\/script>|';
-		// disable conversion of <pre> tags
-		$prefix = '<pre[^>]*+>[^<]*+(?:(?:(?!<\/pre>).)[^<]*+)*+<\/pre>|';
-		// The "|.*+)" at the end, is in case we missed some part of html syntax,
-		// we will fail securely (hopefully) by matching the rest of the string.
-		$htmlFullTag = '<(?:[^>=]*+(?>[^>=]*+=\s*+(?:"[^"]*"|\'[^\']*\'|[^\'">\s]*+))*+[^>=]*+>|.*+)|';
-
-		$reg = '/' . $codefix . $scriptfix . $prefix . $htmlFullTag .
-			'&[a-zA-Z#][a-z0-9]++;' . $marker . $htmlfix . '|\004$/s';
+		static $reg;
+		if ( $reg === null ) {
+			$marker = '|' . Parser::MARKER_PREFIX . '[^\x7f]++\x7f';
+
+			// this one is needed when the text is inside an HTML markup
+			$htmlfix = '|<[^>\004]++(?=\004$)|^[^<>]*+>';
+
+			// Optimize for the common case where these tags have
+			// few or no children. Thus try and possesively get as much as
+			// possible, and only engage in backtracking when we hit a '<'.
+
+			// disable convert to variants between <code> tags
+			$codefix = '<code>[^<]*+(?:(?:(?!<\/code>).)[^<]*+)*+<\/code>|';
+			// disable conversion of <script> tags
+			$scriptfix = '<script[^>]*+>[^<]*+(?:(?:(?!<\/script>).)[^<]*+)*+<\/script>|';
+			// disable conversion of <pre> tags
+			$prefix = '<pre[^>]*+>[^<]*+(?:(?:(?!<\/pre>).)[^<]*+)*+<\/pre>|';
+			// The "|.*+)" at the end, is in case we missed some part of html syntax,
+			// we will fail securely (hopefully) by matching the rest of the string.
+			$htmlFullTag = '<(?:[^>=]*+(?>[^>=]*+=\s*+(?:"[^"]*"|\'[^\']*\'|[^\'">\s]*+))*+[^>=]*+>|.*+)|';
+
+			$reg = '/' . $codefix . $scriptfix . $prefix . $htmlFullTag .
+				 '&[a-zA-Z#][a-z0-9]++;' . $marker . $htmlfix . '|\004$/s';
+		}
 		$startPos = 0;
 		$sourceBlob = '';
 		$literalBlob = '';
@@ -426,8 +430,9 @@ class LanguageConverter {
 
 		// We add a marker (\004) at the end of text, to ensure we always match the
 		// entire text (Otherwise, pcre.backtrack_limit might cause silent failure)
+		$textWithMarker = $text . "\004";
 		while ( $startPos < strlen( $text ) ) {
-			if ( preg_match( $reg, $text . "\004", $markupMatches, PREG_OFFSET_CAPTURE, $startPos ) ) {
+			if ( preg_match( $reg, $textWithMarker, $markupMatches, PREG_OFFSET_CAPTURE, $startPos ) ) {
 				$elementPos = $markupMatches[0][1];
 				$element = $markupMatches[0][0];
 				if ( $element === "\004" ) {
@@ -1039,7 +1044,7 @@ class LanguageConverter {
 				$revision = Revision::newFromTitle( $title );
 				if ( $revision ) {
 					if ( $revision->getContentModel() == CONTENT_MODEL_WIKITEXT ) {
-						$txt = $revision->getContent( Revision::RAW )->getText();
+						$txt = $revision->getContent( RevisionRecord::RAW )->getText();
 					}
 
 					// @todo in the future, use a specialized content model, perhaps based on json!