From: X! <soxred93@users.mediawiki.org>
Date: Sun, 2 Jan 2011 15:54:18 +0000 (+0000)
Subject: Followup to r79463: Move fallback functions to new Fallback class
X-Git-Tag: 1.31.0-rc.0~32878
X-Git-Url: http://git.cyclocoop.org/%40spipnet%40?a=commitdiff_plain;h=cbff3fe980bf5c7f5349d0748272def34c19b1b0;p=lhc%2Fweb%2Fwiklou.git

Followup to r79463: Move fallback functions to new Fallback class
---

diff --git a/includes/AutoLoader.php b/includes/AutoLoader.php
index 2c7bfcabb0..73c64255b1 100644
--- a/includes/AutoLoader.php
+++ b/includes/AutoLoader.php
@@ -86,6 +86,7 @@ $wgAutoloadLocalClasses = array(
 	'FatalError' => 'includes/Exception.php',
 	'FakeTitle' => 'includes/FakeTitle.php',
 	'FakeMemCachedClient' => 'includes/ObjectCache.php',
+	'Fallback' => 'includes/Fallback.php',
 	'FauxRequest' => 'includes/WebRequest.php',
 	'FauxResponse' => 'includes/WebResponse.php',
 	'FeedItem' => 'includes/Feed.php',
diff --git a/includes/Fallback.php b/includes/Fallback.php
new file mode 100644
index 0000000000..422ea8a27e
--- /dev/null
+++ b/includes/Fallback.php
@@ -0,0 +1,177 @@
+<?php
+
+/**
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ */
+
+/**
+ * Fallback functions for PHP installed without mbstring support
+ */
+class Fallback {
+	
+	public static function fallback_iconv( $from, $to, $string ) {
+		if ( substr( $to, -8 ) == '//IGNORE' ) {
+			$to = substr( $to, 0, strlen( $to ) - 8 );
+		}
+		if( strcasecmp( $from, $to ) == 0 ) {
+			return $string;
+		}
+		if( strcasecmp( $from, 'utf-8' ) == 0 ) {
+			return utf8_decode( $string );
+		}
+		if( strcasecmp( $to, 'utf-8' ) == 0 ) {
+			return utf8_encode( $string );
+		}
+		return $string;
+	}	
+	
+	/**
+	 * Fallback implementation for mb_substr, hardcoded to UTF-8.
+	 * Attempts to be at least _moderately_ efficient; best optimized
+	 * for relatively small offset and count values -- about 5x slower
+	 * than native mb_string in my testing.
+	 *
+	 * Larger offsets are still fairly efficient for Latin text, but
+	 * can be up to 100x slower than native if the text is heavily
+	 * multibyte and we have to slog through a few hundred kb.
+	 */
+	public static function fallback_mb_substr( $str, $start, $count='end' ) {
+		if( $start != 0 ) {
+			$split = self::fallback_mb_substr_split_unicode( $str, intval( $start ) );
+			$str = substr( $str, $split );
+		}
+	
+		if( $count !== 'end' ) {
+			$split = self::fallback_mb_substr_split_unicode( $str, intval( $count ) );
+			$str = substr( $str, 0, $split );
+		}
+	
+		return $str;
+	}
+	
+	public static function fallback_mb_substr_split_unicode( $str, $splitPos ) {
+		if( $splitPos == 0 ) {
+			return 0;
+		}
+	
+		$byteLen = strlen( $str );
+	
+		if( $splitPos > 0 ) {
+			if( $splitPos > 256 ) {
+				// Optimize large string offsets by skipping ahead N bytes.
+				// This will cut out most of our slow time on Latin-based text,
+				// and 1/2 to 1/3 on East European and Asian scripts.
+				$bytePos = $splitPos;
+				while ( $bytePos < $byteLen && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
+					++$bytePos;
+				}
+				$charPos = mb_strlen( substr( $str, 0, $bytePos ) );
+			} else {
+				$charPos = 0;
+				$bytePos = 0;
+			}
+	
+			while( $charPos++ < $splitPos ) {
+				++$bytePos;
+				// Move past any tail bytes
+				while ( $bytePos < $byteLen && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
+					++$bytePos;
+				}
+			}
+		} else {
+			$splitPosX = $splitPos + 1;
+			$charPos = 0; // relative to end of string; we don't care about the actual char position here
+			$bytePos = $byteLen;
+			while( $bytePos > 0 && $charPos-- >= $splitPosX ) {
+				--$bytePos;
+				// Move past any tail bytes
+				while ( $bytePos > 0 && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
+					--$bytePos;
+				}
+			}
+		}
+	
+		return $bytePos;
+	}
+	
+	/**
+	 * Fallback implementation of mb_strlen, hardcoded to UTF-8.
+	 * @param string $str
+	 * @param string $enc optional encoding; ignored
+	 * @return int
+	 */
+	public static function fallback_mb_strlen( $str, $enc = '' ) {
+		$counts = count_chars( $str );
+		$total = 0;
+	
+		// Count ASCII bytes
+		for( $i = 0; $i < 0x80; $i++ ) {
+			$total += $counts[$i];
+		}
+	
+		// Count multibyte sequence heads
+		for( $i = 0xc0; $i < 0xff; $i++ ) {
+			$total += $counts[$i];
+		}
+		return $total;
+	}
+	
+	
+	/**
+	 * Fallback implementation of mb_strpos, hardcoded to UTF-8.
+	 * @param $haystack String
+	 * @param $needle String
+	 * @param $offset String: optional start position
+	 * @param $encoding String: optional encoding; ignored
+	 * @return int
+	 */
+	public static function fallback_mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
+		$needle = preg_quote( $needle, '/' );
+	
+		$ar = array();
+		preg_match( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
+	
+		if( isset( $ar[0][1] ) ) {
+			return $ar[0][1];
+		} else {
+			return false;
+		}
+	}	
+	
+	/**
+	 * Fallback implementation of mb_strrpos, hardcoded to UTF-8.
+	 * @param $haystack String
+	 * @param $needle String
+	 * @param $offset String: optional start position
+	 * @param $encoding String: optional encoding; ignored
+	 * @return int
+	 */
+	public static function fallback_mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
+		$needle = preg_quote( $needle, '/' );
+	
+		$ar = array();
+		preg_match_all( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
+	
+		if( isset( $ar[0] ) && count( $ar[0] ) > 0 &&
+			isset( $ar[0][count( $ar[0] ) - 1][1] ) ) {
+			return $ar[0][count( $ar[0] ) - 1][1];
+		} else {
+			return false;
+		}
+	}
+		
+}
\ No newline at end of file
diff --git a/includes/GlobalFunctions.php b/includes/GlobalFunctions.php
index d9f5585ea2..d4a816b2f8 100644
--- a/includes/GlobalFunctions.php
+++ b/includes/GlobalFunctions.php
@@ -21,201 +21,39 @@ require_once dirname( __FILE__ ) . '/normal/UtfNormalUtil.php';
  * PHP extensions may be included here.
  */
 
-# iconv support is not in the default configuration and so may not be present.
-# Assume will only ever use utf-8 and iso-8859-1.
-# This will *not* work in all circumstances.
-function fallback_iconv( $from, $to, $string ) {
-	if ( substr( $to, -8 ) == '//IGNORE' ) {
-		$to = substr( $to, 0, strlen( $to ) - 8 );
-	}
-	if( strcasecmp( $from, $to ) == 0 ) {
-		return $string;
-	}
-	if( strcasecmp( $from, 'utf-8' ) == 0 ) {
-		return utf8_decode( $string );
-	}
-	if( strcasecmp( $to, 'utf-8' ) == 0 ) {
-		return utf8_encode( $string );
-	}
-	return $string;
-}
-
 if( !function_exists( 'iconv' ) ) {
 	function iconv( $from, $to, $string ) {
-		return fallback_iconv( $from, $to, $string );
-	}
-}
-
-
-
-
-/**
- * Fallback implementation for mb_substr, hardcoded to UTF-8.
- * Attempts to be at least _moderately_ efficient; best optimized
- * for relatively small offset and count values -- about 5x slower
- * than native mb_string in my testing.
- *
- * Larger offsets are still fairly efficient for Latin text, but
- * can be up to 100x slower than native if the text is heavily
- * multibyte and we have to slog through a few hundred kb.
- */
-function fallback_mb_substr( $str, $start, $count='end' ) {
-	if( $start != 0 ) {
-		$split = fallback_mb_substr_split_unicode( $str, intval( $start ) );
-		$str = substr( $str, $split );
-	}
-
-	if( $count !== 'end' ) {
-		$split = fallback_mb_substr_split_unicode( $str, intval( $count ) );
-		$str = substr( $str, 0, $split );
-	}
-
-	return $str;
-}
-
-function fallback_mb_substr_split_unicode( $str, $splitPos ) {
-	if( $splitPos == 0 ) {
-		return 0;
-	}
-
-	$byteLen = strlen( $str );
-
-	if( $splitPos > 0 ) {
-		if( $splitPos > 256 ) {
-			// Optimize large string offsets by skipping ahead N bytes.
-			// This will cut out most of our slow time on Latin-based text,
-			// and 1/2 to 1/3 on East European and Asian scripts.
-			$bytePos = $splitPos;
-			while ( $bytePos < $byteLen && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
-				++$bytePos;
-			}
-			$charPos = mb_strlen( substr( $str, 0, $bytePos ) );
-		} else {
-			$charPos = 0;
-			$bytePos = 0;
-		}
-
-		while( $charPos++ < $splitPos ) {
-			++$bytePos;
-			// Move past any tail bytes
-			while ( $bytePos < $byteLen && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
-				++$bytePos;
-			}
-		}
-	} else {
-		$splitPosX = $splitPos + 1;
-		$charPos = 0; // relative to end of string; we don't care about the actual char position here
-		$bytePos = $byteLen;
-		while( $bytePos > 0 && $charPos-- >= $splitPosX ) {
-			--$bytePos;
-			// Move past any tail bytes
-			while ( $bytePos > 0 && $str{$bytePos} >= "\x80" && $str{$bytePos} < "\xc0" ) {
-				--$bytePos;
-			}
-		}
+		return Fallback::fallback_iconv( $from, $to, $string );
 	}
-
-	return $bytePos;
 }
 
 if ( !function_exists( 'mb_substr' ) ) {
 	function mb_substr( $str, $start, $count='end' ) {
-		return fallback_mb_substr( $str, $start, $count );
+		return Fallback::fallback_mb_substr( $str, $start, $count );
 	}
 
 	function mb_substr_split_unicode( $str, $splitPos ) {
-		return fallback_mb_substr_split_unicode( $str, $splitPos );
-	}
-}
-
-
-
-/**
- * Fallback implementation of mb_strlen, hardcoded to UTF-8.
- * @param string $str
- * @param string $enc optional encoding; ignored
- * @return int
- */
-function fallback_mb_strlen( $str, $enc = '' ) {
-	$counts = count_chars( $str );
-	$total = 0;
-
-	// Count ASCII bytes
-	for( $i = 0; $i < 0x80; $i++ ) {
-		$total += $counts[$i];
+		return Fallback::fallback_mb_substr_split_unicode( $str, $splitPos );
 	}
-
-	// Count multibyte sequence heads
-	for( $i = 0xc0; $i < 0xff; $i++ ) {
-		$total += $counts[$i];
-	}
-	return $total;
 }
 
 if ( !function_exists( 'mb_strlen' ) ) {
 	function mb_strlen( $str, $enc = '' ) {
-		return fallback_mb_strlen( $str, $enc );
-	}
-}
-
-
-
-/**
- * Fallback implementation of mb_strpos, hardcoded to UTF-8.
- * @param $haystack String
- * @param $needle String
- * @param $offset String: optional start position
- * @param $encoding String: optional encoding; ignored
- * @return int
- */
-function fallback_mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
-	$needle = preg_quote( $needle, '/' );
-
-	$ar = array();
-	preg_match( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
-
-	if( isset( $ar[0][1] ) ) {
-		return $ar[0][1];
-	} else {
-		return false;
+		return Fallback::fallback_mb_strlen( $str, $enc );
 	}
 }
 
 if( !function_exists( 'mb_strpos' ) ) {
 	
 	function mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
-		return fallback_mb_strpos( $haystack, $needle, $offset, $encoding );
+		return Fallback::fallback_mb_strpos( $haystack, $needle, $offset, $encoding );
 	}
 	
 }
 
-
-
-/**
- * Fallback implementation of mb_strrpos, hardcoded to UTF-8.
- * @param $haystack String
- * @param $needle String
- * @param $offset String: optional start position
- * @param $encoding String: optional encoding; ignored
- * @return int
- */
-function fallback_mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
-	$needle = preg_quote( $needle, '/' );
-
-	$ar = array();
-	preg_match_all( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
-
-	if( isset( $ar[0] ) && count( $ar[0] ) > 0 &&
-		isset( $ar[0][count( $ar[0] ) - 1][1] ) ) {
-		return $ar[0][count( $ar[0] ) - 1][1];
-	} else {
-		return false;
-	}
-}
-
 if( !function_exists( 'mb_strrpos' ) ) {
 	function mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
-		return fallback_mb_strrpos( $haystack, $needle, $offset, $encoding );
+		return Fallback::fallback_mb_strrpos( $haystack, $needle, $offset, $encoding );
 	}
 }
 
diff --git a/tests/phpunit/includes/GlobalTest.php b/tests/phpunit/includes/GlobalTest.php
index cdea1fe071..ecaa8d3e8a 100644
--- a/tests/phpunit/includes/GlobalTest.php
+++ b/tests/phpunit/includes/GlobalTest.php
@@ -422,7 +422,7 @@ class GlobalTest extends MediaWikiTestCase {
 			
 			$this->assertEquals(
 				call_user_func_array( 'mb_substr', $param_set ),
-				call_user_func_array( 'fallback_mb_substr', $param_set ),
+				call_user_func_array( array( 'Fallback', 'fallback_mb_substr' ), $param_set ),
 				'Fallback mb_substr with params ' . implode( ', ', $old_param_set )
 			);			
 		}
@@ -431,7 +431,7 @@ class GlobalTest extends MediaWikiTestCase {
 		//mb_strlen
 		$this->assertEquals(
 			mb_strlen( $sampleUTF ),
-			fallback_mb_strlen( $sampleUTF ),
+			Fallback::fallback_mb_strlen( $sampleUTF ),
 			'Fallback mb_strlen'
 		);			
 		
@@ -452,13 +452,13 @@ class GlobalTest extends MediaWikiTestCase {
 			
 			$this->assertEquals(
 				call_user_func_array( 'mb_strpos', $param_set ),
-				call_user_func_array( 'fallback_mb_strpos', $param_set ),
+				call_user_func_array( array( 'Fallback', 'fallback_mb_strpos' ), $param_set ),
 				'Fallback mb_strpos with params ' . implode( ', ', $old_param_set )
 			);		
 			
 			$this->assertEquals(
 				call_user_func_array( 'mb_strrpos', $param_set ),
-				call_user_func_array( 'fallback_mb_strrpos', $param_set ),
+				call_user_func_array( array( 'Fallback', 'fallback_mb_strrpos' ), $param_set ),
 				'Fallback mb_strrpos with params ' . implode( ', ', $old_param_set )
 			);	
 		}