X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguage.php;h=34978774fcba8977b448280016aed2e41b043102;hb=86ddf7cb8a7dba0c9e59a92d754de803c080df7d;hp=4cd4ffa12fdb5766d6a4d334c378f835bd3e002e;hpb=2800ca2db7688802ff61ec38c6a4d7191c5060c3;p=lhc%2Fweb%2Fwiklou.git

diff --git a/languages/Language.php b/languages/Language.php
index 4cd4ffa12f..34978774fc 100644
--- a/languages/Language.php
+++ b/languages/Language.php
@@ -59,7 +59,6 @@ class Language {
 
 	var $mNamespaceIds, $namespaceNames, $namespaceAliases;
 	var $dateFormatStrings = array();
-	var $minSearchLength;
 	var $mExtendedSpecialPageAliases;
 
 	/**
@@ -1687,85 +1686,27 @@ class Language {
 	function hasWordBreaks() {
 		return true;
 	}
-
+	
 	/**
-	 * Some languages have special punctuation to strip out
-	 * or characters which need to be converted for MySQL's
-	 * indexing to grok it correctly. Make such changes here.
-	 *
+	 * Some languages such as Chinese require word segmentation,
+	 * Specify such segmentation when overridden in derived class.
+	 * 
 	 * @param $string String
 	 * @return String
 	 */
-	function stripForSearch( $string, $doStrip = true ) {
-		global $wgDBtype;
-		if ( $wgDBtype != 'mysql' || $doStrip == false ) {
-			return $string;
-		}
-
-		wfProfileIn( __METHOD__ );
-
-		// MySQL fulltext index doesn't grok utf-8, so we
-		// need to fold cases and convert to hex
-		$out = preg_replace_callback(
-			"/([\\xc0-\\xff][\\x80-\\xbf]*)/",
-			array( $this, 'stripForSearchCallback' ),
-			$this->lc( $string ) );
-
-		// And to add insult to injury, the default indexing
-		// ignores short words... Pad them so we can pass them
-		// through without reconfiguring the server...
-		$minLength = $this->minSearchLength();
-		if( $minLength > 1 ) {
-			$n = $minLength-1;
-			$out = preg_replace(
-				"/\b(\w{1,$n})\b/",
-				"$1u800",
-				$out );
-		}
-
-		// Periods within things like hostnames and IP addresses
-		// are also important -- we want a search for "example.com"
-		// or "192.168.1.1" to work sanely.
-		//
-		// MySQL's search seems to ignore them, so you'd match on
-		// "example.wikipedia.com" and "192.168.83.1" as well.
-		$out = preg_replace(
-			"/(\w)\.(\w|\*)/u",
-			"$1u82e$2",
-			$out );
-
-		wfProfileOut( __METHOD__ );
-		return $out;
-	}
-
-	/**
-	 * Armor a case-folded UTF-8 string to get through MySQL's
-	 * fulltext search without being mucked up by funny charset
-	 * settings or anything else of the sort.
-	 */
-	protected function stripForSearchCallback( $matches ) {
-		return 'u8' . bin2hex( $matches[1] );
+	function wordSegmentation( $string ) {
+		return $string;
 	}
 
 	/**
-	 * Check MySQL server's ft_min_word_len setting so we know
-	 * if we need to pad short words...
+	 * Some languages have special punctuation need to be normalized.
+	 * Make such changes here.
+	 *
+	 * @param $string String
+	 * @return String
 	 */
-	protected function minSearchLength() {
-		if( is_null( $this->minSearchLength ) ) {
-			$sql = "show global variables like 'ft\\_min\\_word\\_len'";
-			$dbr = wfGetDB( DB_SLAVE );
-			$result = $dbr->query( $sql );
-			$row = $result->fetchObject();
-			$result->free();
-
-			if( $row && $row->Variable_name == 'ft_min_word_len' ) {
-				$this->minSearchLength = intval( $row->Value );
-			} else {
-				$this->minSearchLength = 0;
-			}
-		}
-		return $this->minSearchLength;
+	function normalizeForSearch( $string ) {
+		return $string;
 	}
 
 	/**
@@ -1778,7 +1719,7 @@ class Language {
 		return $string;
 	}
 
-	protected static function wordSegmentation( $string, $pattern ) {
+	protected static function insertSpace( $string, $pattern ) {
 		$string = preg_replace( $pattern, " $1 ", $string );
 		$string = preg_replace( '/ +/', ' ', $string );
 		return $string;
@@ -2223,6 +2164,7 @@ class Language {
 		if ( strlen( $string ) <= abs( $length ) ) {
 			return $string;
 		}
+		$stringOriginal = $string;
 		if( $length > 0 ) {
 			$string = substr( $string, 0, $length );
 			$char = ord( $string[strlen( $string ) - 1] );
@@ -2236,7 +2178,8 @@ class Language {
 				# We chopped in the middle of a character; remove it
 				$string = $m[1];
 			}
-			return $string . $ellipsis;
+			$string = $string . $ellipsis;
+
 		} else {
 			$string = substr( $string, $length );
 			$char = ord( $string[0] );
@@ -2244,7 +2187,13 @@ class Language {
 				# We chopped in the middle of a character; remove the whole thing
 				$string = preg_replace( '/^[\x80-\xbf]+/', '', $string );
 			}
-			return $ellipsis . $string;
+			$string = $ellipsis . $string;
+		}
+		# Do not truncate if the ellipsis actually make the string longer. Bug 22181
+		if ( strlen( $string ) < strlen( $stringOriginal ) ) {
+			return $string;
+		} else {
+			return $stringOriginal;
 		}
 	}