X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguageConverter.php;h=f611358d94c09b5e2faa3d91b05b297cfccb397e;hb=fac144565411ba560c96b5913b2b054e48deadd7;hp=8e98abd618e4ffce26201919b1f0e7c38813f99c;hpb=f600b4ede9a6390cc5e929d2a48ed98af2edbc60;p=lhc%2Fweb%2Fwiklou.git

diff --git a/languages/LanguageConverter.php b/languages/LanguageConverter.php
index 8e98abd618..f611358d94 100644
--- a/languages/LanguageConverter.php
+++ b/languages/LanguageConverter.php
@@ -39,6 +39,7 @@ class LanguageConverter {
 	 */
 	static public $languagesWithVariants = [
 		'en',
+		'crh',
 		'gan',
 		'iu',
 		'kk',
@@ -162,6 +163,8 @@ class LanguageConverter {
 
 		$req = $this->getURLVariant();
 
+		Hooks::run( 'GetLangPreferredVariant', [ &$req ] );
+
 		if ( $wgUser->isSafeToLoad() && $wgUser->isLoggedIn() && !$req ) {
 			$req = $this->getUserVariant();
 		} elseif ( !$req ) {
@@ -353,7 +356,6 @@ class LanguageConverter {
 		if ( $this->guessVariant( $text, $toVariant ) ) {
 			return $text;
 		}
-
 		/* we convert everything except:
 		   1. HTML markups (anything between < and >)
 		   2. HTML entities
@@ -389,6 +391,7 @@ class LanguageConverter {
 		// Guard against delimiter nulls in the input
 		// (should never happen: see T159174)
 		$text = str_replace( "\000", '', $text );
+		$text = str_replace( "\004", '', $text );
 
 		$markupMatches = null;
 		$elementMatches = null;
@@ -403,6 +406,13 @@ class LanguageConverter {
 					// We hit the end.
 					$elementPos = strlen( $text );
 					$element = '';
+				} elseif ( substr( $element, -1 ) === "\004" ) {
+					// This can sometimes happen if we have
+					// unclosed html tags (For example
+					// when converting a title attribute
+					// during a recursive call that contains
+					// a &lt; e.g. <div title="&lt;">.
+					$element = substr( $element, 0, -1 );
 				}
 			} else {
 				// If we hit here, then Language Converter could be tricked
@@ -430,7 +440,14 @@ class LanguageConverter {
 			if ( $element !== ''
 				&& preg_match( '/^(<[^>\s]*+)\s([^>]*+)(.*+)$/', $element, $elementMatches )
 			) {
+				// FIXME, this decodes entities, so if you have something
+				// like <div title="foo&lt;bar"> the bar won't get
+				// translated since after entity decoding it looks like
+				// unclosed html and we call this method recursively
+				// on attributes.
 				$attrs = Sanitizer::decodeTagAttributes( $elementMatches[2] );
+				// Ensure self-closing tags stay self-closing.
+				$close = substr( $elementMatches[2], -1 ) === '/' ? ' /' : '';
 				$changed = false;
 				foreach ( [ 'title', 'alt' ] as $attrName ) {
 					if ( !isset( $attrs[$attrName] ) ) {
@@ -449,7 +466,7 @@ class LanguageConverter {
 				}
 				if ( $changed ) {
 					$element = $elementMatches[1] . Html::expandAttributes( $attrs ) .
-						$elementMatches[3];
+						$close . $elementMatches[3];
 				}
 			}
 			$literalBlob .= $element . "\000";
@@ -665,9 +682,8 @@ class LanguageConverter {
 
 		$noScript = '<script.*?>.*?<\/script>(*SKIP)(*FAIL)';
 		$noStyle = '<style.*?>.*?<\/style>(*SKIP)(*FAIL)';
-		// @codingStandardsIgnoreStart Generic.Files.LineLength.TooLong
+		// phpcs:ignore Generic.Files.LineLength
 		$noHtml = '<(?:[^>=]*+(?>[^>=]*+=\s*+(?:"[^"]*"|\'[^\']*\'|[^\'">\s]*+))*+[^>=]*+>|.*+)(*SKIP)(*FAIL)';
-		// @codingStandardsIgnoreEnd
 		while ( $startPos < $length && $continue ) {
 			$continue = preg_match(
 				// Only match -{ outside of html.