| Index: trunk/phase3/maintenance/cleanupWatchlist.php |
| — | — | @@ -52,9 +52,10 @@ |
| 53 | 53 | } |
| 54 | 54 | |
| 55 | 55 | protected function processRow( $row ) { |
| | 56 | + global $wgContLang; |
| 56 | 57 | $current = Title::makeTitle( $row->wl_namespace, $row->wl_title ); |
| 57 | 58 | $display = $current->getPrefixedText(); |
| 58 | | - $verified = UtfNormal::cleanUp( $display ); |
| | 59 | + $verified = $wgContLang->normalize( $display ); |
| 59 | 60 | $title = Title::newFromText( $verified ); |
| 60 | 61 | |
| 61 | 62 | if( $row->wl_user == 0 || is_null( $title ) || !$title->equals( $current ) ) { |
| Index: trunk/phase3/maintenance/cleanupTitles.php |
| — | — | @@ -37,8 +37,9 @@ |
| 38 | 38 | } |
| 39 | 39 | |
| 40 | 40 | protected function processRow( $row ) { |
| | 41 | + global $wgContLang; |
| 41 | 42 | $display = Title::makeName( $row->page_namespace, $row->page_title ); |
| 42 | | - $verified = UtfNormal::cleanUp( $display ); |
| | 43 | + $verified = $wgContLang->normalize( $display ); |
| 43 | 44 | $title = Title::newFromText( $verified ); |
| 44 | 45 | |
| 45 | 46 | if( !is_null( $title ) |
| Index: trunk/phase3/maintenance/cleanupImages.php |
| — | — | @@ -65,7 +65,7 @@ |
| 66 | 66 | $cleaned = $wgContLang->checkTitleEncoding( $cleaned ); |
| 67 | 67 | |
| 68 | 68 | // Many of remainder look like non-normalized unicode |
| 69 | | - $cleaned = UtfNormal::cleanUp( $cleaned ); |
| | 69 | + $cleaned = $wgContLang->normalize( $cleaned ); |
| 70 | 70 | |
| 71 | 71 | $title = Title::makeTitleSafe( NS_FILE, $cleaned ); |
| 72 | 72 | |
| Index: trunk/phase3/maintenance/language/generateNormalizerData.php |
| — | — | @@ -0,0 +1,137 @@ |
| | 2 | +<?php |
| | 3 | + |
| | 4 | +require_once( dirname( __FILE__ ) . '/../Maintenance.php' ); |
| | 5 | + |
| | 6 | +require_once( dirname( __FILE__ ) . '/../../includes/normal/UtfNormalUtil.php' ); |
| | 7 | + |
| | 8 | +/** |
| | 9 | + * Generates normalizer data files for Arabic and Malayalam. |
| | 10 | + * For NFC see includes/normal. |
| | 11 | + */ |
| | 12 | +class GenerateNormalizerData extends Maintenance { |
| | 13 | + var $dataFile; |
| | 14 | + |
| | 15 | + public function __construct() { |
| | 16 | + parent::__construct(); |
| | 17 | + $this->addOption( 'unicode-data-file', 'The local location of the data file ' . |
| | 18 | + 'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true ); |
| | 19 | + } |
| | 20 | + |
| | 21 | + public function execute() { |
| | 22 | + if ( !$this->hasOption( 'unicode-data-file' ) ) { |
| | 23 | + $this->dataFile = 'UnicodeData.txt'; |
| | 24 | + if ( !file_exists( $this->dataFile ) ) { |
| | 25 | + $this->error( "Unable to find UnicodeData.txt. Please specify its location with --unicode-data-file=<FILE>" ); |
| | 26 | + exit( 1 ); |
| | 27 | + } |
| | 28 | + } else { |
| | 29 | + $this->dataFile = $this->getOption( 'unicode-data-file' ); |
| | 30 | + if ( !file_exists( $this->dataFile ) ) { |
| | 31 | + $this->error( 'Unable to find the specified data file.' ); |
| | 32 | + exit( 1 ); |
| | 33 | + } |
| | 34 | + } |
| | 35 | + |
| | 36 | + $this->generateArabic(); |
| | 37 | + $this->generateMalayalam(); |
| | 38 | + } |
| | 39 | + |
| | 40 | + function generateArabic() { |
| | 41 | + $file = fopen( $this->dataFile, 'r' ); |
| | 42 | + if ( !$file ) { |
| | 43 | + $this->error( 'Unable to open the data file.' ); |
| | 44 | + exit( 1 ); |
| | 45 | + } |
| | 46 | + |
| | 47 | + // For the file format, see http://www.unicode.org/reports/tr44/ |
| | 48 | + $fieldNames = array( |
| | 49 | + 'Code', |
| | 50 | + 'Name', |
| | 51 | + 'General_Category', |
| | 52 | + 'Canonical_Combining_Class', |
| | 53 | + 'Bidi_Class', |
| | 54 | + 'Decomposition_Type_Mapping', |
| | 55 | + 'Numeric_Type_Value', |
| | 56 | + 'Bidi_Mirrored', |
| | 57 | + 'Unicode_1_Name', |
| | 58 | + 'ISO_Comment', |
| | 59 | + 'Simple_Uppercase_Mapping', |
| | 60 | + 'Simple_Lowercase_Mapping', |
| | 61 | + 'Simple_Titlecase_Mapping' |
| | 62 | + ); |
| | 63 | + |
| | 64 | + $pairs = array(); |
| | 65 | + |
| | 66 | + $lineNum = 0; |
| | 67 | + while ( false !== ( $line = fgets( $file ) ) ) { |
| | 68 | + ++$lineNum; |
| | 69 | + |
| | 70 | + # Strip comments |
| | 71 | + $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) ); |
| | 72 | + if ( $line === '' ) { |
| | 73 | + continue; |
| | 74 | + } |
| | 75 | + |
| | 76 | + # Split fields |
| | 77 | + $numberedData = explode( ';', $line ); |
| | 78 | + $data = array(); |
| | 79 | + foreach ( $fieldNames as $number => $name ) { |
| | 80 | + $data[$name] = $numberedData[$number]; |
| | 81 | + } |
| | 82 | + |
| | 83 | + $code = base_convert( $data['Code'], 16, 10 ); |
| | 84 | + if ( ( $code >= 0xFB50 && $code <= 0xFDFF ) # Arabic presentation forms A |
| | 85 | + || ( $code >= 0xFE70 && $code <= 0xFEFF ) ) # Arabic presentation forms B |
| | 86 | + { |
| | 87 | + if ( $data['Decomposition_Type_Mapping'] === '' ) { |
| | 88 | + // No decomposition |
| | 89 | + continue; |
| | 90 | + } |
| | 91 | + if ( !preg_match( '/^ *(<\w*>) +([0-9A-F ]*)$/', |
| | 92 | + $data['Decomposition_Type_Mapping'], $m ) ) |
| | 93 | + { |
| | 94 | + $this->error( "Can't parse Decomposition_Type/Mapping on line $lineNum" ); |
| | 95 | + $this->error( $line ); |
| | 96 | + continue; |
| | 97 | + } |
| | 98 | + |
| | 99 | + $source = hexSequenceToUtf8( $data['Code'] ); |
| | 100 | + $dest = hexSequenceToUtf8( $m[2] ); |
| | 101 | + $pairs[$source] = $dest; |
| | 102 | + } |
| | 103 | + } |
| | 104 | + |
| | 105 | + global $IP; |
| | 106 | + file_put_contents( "$IP/serialized/normalize-ar.ser", serialize( $pairs ) ); |
| | 107 | + echo "ar: " . count( $pairs ) . " pairs written.\n"; |
| | 108 | + } |
| | 109 | + |
| | 110 | + function generateMalayalam() { |
| | 111 | + $hexPairs = array( |
| | 112 | + # From http://unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters |
| | 113 | + '0D23 0D4D 200D' => '0D7A', |
| | 114 | + '0D28 0D4D 200D' => '0D7B', |
| | 115 | + '0D30 0D4D 200D' => '0D7C', |
| | 116 | + '0D32 0D4D 200D' => '0D7D', |
| | 117 | + '0D33 0D4D 200D' => '0D7E', |
| | 118 | + |
| | 119 | + # From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413 |
| | 120 | + '0D15 0D4D 200D' => '0D7F', |
| | 121 | + ); |
| | 122 | + |
| | 123 | + $pairs = array(); |
| | 124 | + foreach ( $hexPairs as $hexSource => $hexDest ) { |
| | 125 | + $source = hexSequenceToUtf8( $hexSource ); |
| | 126 | + $dest = hexSequenceToUtf8( $hexDest ); |
| | 127 | + $pairs[$source] = $dest; |
| | 128 | + } |
| | 129 | + |
| | 130 | + global $IP; |
| | 131 | + file_put_contents( "$IP/serialized/normalize-ml.ser", serialize( $pairs ) ); |
| | 132 | + echo "ml: " . count( $pairs ) . " pairs written.\n"; |
| | 133 | + } |
| | 134 | +} |
| | 135 | + |
| | 136 | +$maintClass = 'GenerateNormalizerData'; |
| | 137 | +require_once( DO_MAINTENANCE ); |
| | 138 | + |
| Property changes on: trunk/phase3/maintenance/language/generateNormalizerData.php |
| ___________________________________________________________________ |
| Added: svn:eol-style |
| 1 | 139 | + native |
| Index: trunk/phase3/maintenance/preprocessorFuzzTest.php |
| — | — | @@ -102,7 +102,8 @@ |
| 103 | 103 | // This resolves a few differences between the old preprocessor and the |
| 104 | 104 | // XML-based one, which doesn't like illegals and converts line endings. |
| 105 | 105 | // It's done by the MW UI, so it's a reasonably legitimate thing to do. |
| 106 | | - $s = UtfNormal::cleanUp( $s ); |
| | 106 | + global $wgContLang; |
| | 107 | + $s = $wgContLang->normalize( $s ); |
| 107 | 108 | return $s; |
| 108 | 109 | } |
| 109 | 110 | |
| Index: trunk/phase3/maintenance/dumpTextPass.php |
| — | — | @@ -236,6 +236,7 @@ |
| 237 | 237 | * May throw a database error if, say, the server dies during query. |
| 238 | 238 | */ |
| 239 | 239 | private function getTextDb( $id ) { |
| | 240 | + global $wgContLang; |
| 240 | 241 | $id = intval( $id ); |
| 241 | 242 | $row = $this->db->selectRow( 'text', |
| 242 | 243 | array( 'old_text', 'old_flags' ), |
| — | — | @@ -246,7 +247,7 @@ |
| 247 | 248 | return false; |
| 248 | 249 | } |
| 249 | 250 | $stripped = str_replace( "\r", "", $text ); |
| 250 | | - $normalized = UtfNormal::cleanUp( $stripped ); |
| | 251 | + $normalized = $wgContLang->normalize( $stripped ); |
| 251 | 252 | return $normalized; |
| 252 | 253 | } |
| 253 | 254 | |
| — | — | @@ -321,6 +322,8 @@ |
| 322 | 323 | } |
| 323 | 324 | |
| 324 | 325 | private function getTextSpawnedOnce( $id ) { |
| | 326 | + global $wgContLang; |
| | 327 | + |
| 325 | 328 | $ok = fwrite( $this->spawnWrite, "$id\n" ); |
| 326 | 329 | //$this->progress( ">> $id" ); |
| 327 | 330 | if( !$ok ) return false; |
| — | — | @@ -351,7 +354,7 @@ |
| 352 | 355 | |
| 353 | 356 | // Do normalization in the dump thread... |
| 354 | 357 | $stripped = str_replace( "\r", "", $text ); |
| 355 | | - $normalized = UtfNormal::cleanUp( $stripped ); |
| | 358 | + $normalized = $wgContLang->normalize( $stripped ); |
| 356 | 359 | return $normalized; |
| 357 | 360 | } |
| 358 | 361 | |
| Index: trunk/phase3/includes/Xml.php |
| — | — | @@ -56,7 +56,7 @@ |
| 57 | 57 | |
| 58 | 58 | /** |
| 59 | 59 | * Format an XML element as with self::element(), but run text through the |
| 60 | | - * UtfNormal::cleanUp() validator first to ensure that no invalid UTF-8 |
| | 60 | + * $wgContLang->normalize() validator first to ensure that no invalid UTF-8 |
| 61 | 61 | * is passed. |
| 62 | 62 | * |
| 63 | 63 | * @param $element String: |
| — | — | @@ -65,12 +65,13 @@ |
| 66 | 66 | * @return string |
| 67 | 67 | */ |
| 68 | 68 | public static function elementClean( $element, $attribs = array(), $contents = '') { |
| | 69 | + global $wgContLang; |
| 69 | 70 | if( $attribs ) { |
| 70 | 71 | $attribs = array_map( array( 'UtfNormal', 'cleanUp' ), $attribs ); |
| 71 | 72 | } |
| 72 | 73 | if( $contents ) { |
| 73 | 74 | wfProfileIn( __METHOD__ . '-norm' ); |
| 74 | | - $contents = UtfNormal::cleanUp( $contents ); |
| | 75 | + $contents = $wgContLang->normalize( $contents ); |
| 75 | 76 | wfProfileOut( __METHOD__ . '-norm' ); |
| 76 | 77 | } |
| 77 | 78 | return self::element( $element, $attribs, $contents ); |
| Index: trunk/phase3/includes/api/ApiResult.php |
| — | — | @@ -304,7 +304,8 @@ |
| 305 | 305 | { |
| 306 | 306 | if(!is_string($s)) |
| 307 | 307 | return; |
| 308 | | - $s = UtfNormal::cleanUp($s); |
| | 308 | + global $wgContLang; |
| | 309 | + $s = $wgContLang->normalize($s); |
| 309 | 310 | } |
| 310 | 311 | |
| 311 | 312 | public function execute() { |
| Index: trunk/phase3/includes/WebRequest.php |
| — | — | @@ -203,7 +203,8 @@ |
| 204 | 204 | $data[$key] = $this->normalizeUnicode( $val ); |
| 205 | 205 | } |
| 206 | 206 | } else { |
| 207 | | - $data = UtfNormal::cleanUp( $data ); |
| | 207 | + global $wgContLang; |
| | 208 | + $data = $wgContLang->normalize( $data ); |
| 208 | 209 | } |
| 209 | 210 | return $data; |
| 210 | 211 | } |
| — | — | @@ -600,6 +601,7 @@ |
| 601 | 602 | * @return string or NULL if no such file. |
| 602 | 603 | */ |
| 603 | 604 | public function getFileName( $key ) { |
| | 605 | + global $wgContLang; |
| 604 | 606 | if( !isset( $_FILES[$key] ) ) { |
| 605 | 607 | return null; |
| 606 | 608 | } |
| — | — | @@ -608,7 +610,7 @@ |
| 609 | 611 | # Safari sends filenames in HTML-encoded Unicode form D... |
| 610 | 612 | # Horrid and evil! Let's try to make some kind of sense of it. |
| 611 | 613 | $name = Sanitizer::decodeCharReferences( $name ); |
| 612 | | - $name = UtfNormal::cleanUp( $name ); |
| | 614 | + $name = $wgContLang->normalize( $name ); |
| 613 | 615 | wfDebug( "WebRequest::getFileName() '" . $_FILES[$key]['name'] . "' normalized to '$name'\n" ); |
| 614 | 616 | return $name; |
| 615 | 617 | } |
| Index: trunk/phase3/includes/DefaultSettings.php |
| — | — | @@ -867,6 +867,19 @@ |
| 868 | 868 | $wgOutputEncoding = 'UTF-8'; |
| 869 | 869 | $wgEditEncoding = ''; |
| 870 | 870 | |
| | 871 | +/** |
| | 872 | + * Set this to true to clean up archaic Unicode sequences in Arabic and |
| | 873 | + * Malayalam text. Currently only works if $wgLanguageCode is set to Arabic |
| | 874 | + * or Malayalam. |
| | 875 | + * |
| | 876 | + * Enabling this is generally a good idea for new wikis, since it fixes a few |
| | 877 | + * technical problems to do with editing these languages. However, if it's |
| | 878 | + * enabled on an existing wiki, pages which contain the problematic characters |
| | 879 | + * in their page titles may become inaccessible. Running maintenance/cleanupTitles.php |
| | 880 | + * after enabling it may fix this. |
| | 881 | + */ |
| | 882 | +$wgFixArchaicUnicode = false; |
| | 883 | + |
| 871 | 884 | /** |
| 872 | 885 | * Locale for LC_CTYPE, to work around http://bugs.php.net/bug.php?id=45132 |
| 873 | 886 | * For Unix-like operating systems, set this to to a locale that has a UTF-8 |
| Index: trunk/phase3/serialized/normalize-ar.ser |
| — | — | @@ -0,0 +1 @@ |
| | 2 | +a:731:{s:3:"ﭐ";s:2:"ٱ";s:3:"ﭑ";s:2:"ٱ";s:3:"ﭒ";s:2:"ٻ";s:3:"ﭓ";s:2:"ٻ";s:3:"ﭔ";s:2:"ٻ";s:3:"ﭕ";s:2:"ٻ";s:3:"ﭖ";s:2:"پ";s:3:"ﭗ";s:2:"پ";s:3:"ﭘ";s:2:"پ";s:3:"ﭙ";s:2:"پ";s:3:"ﭚ";s:2:"ڀ";s:3:"ﭛ";s:2:"ڀ";s:3:"ﭜ";s:2:"ڀ";s:3:"ﭝ";s:2:"ڀ";s:3:"ﭞ";s:2:"ٺ";s:3:"ﭟ";s:2:"ٺ";s:3:"ﭠ";s:2:"ٺ";s:3:"ﭡ";s:2:"ٺ";s:3:"ﭢ";s:2:"ٿ";s:3:"ﭣ";s:2:"ٿ";s:3:"ﭤ";s:2:"ٿ";s:3:"ﭥ";s:2:"ٿ";s:3:"ﭦ";s:2:"ٹ";s:3:"ﭧ";s:2:"ٹ";s:3:"ﭨ";s:2:"ٹ";s:3:"ﭩ";s:2:"ٹ";s:3:"ﭪ";s:2:"ڤ";s:3:"ﭫ";s:2:"ڤ";s:3:"ﭬ";s:2:"ڤ";s:3:"ﭭ";s:2:"ڤ";s:3:"ﭮ";s:2:"ڦ";s:3:"ﭯ";s:2:"ڦ";s:3:"ﭰ";s:2:"ڦ";s:3:"ﭱ";s:2:"ڦ";s:3:"ﭲ";s:2:"ڄ";s:3:"ﭳ";s:2:"ڄ";s:3:"ﭴ";s:2:"ڄ";s:3:"ﭵ";s:2:"ڄ";s:3:"ﭶ";s:2:"ڃ";s:3:"ﭷ";s:2:"ڃ";s:3:"ﭸ";s:2:"ڃ";s:3:"ﭹ";s:2:"ڃ";s:3:"ﭺ";s:2:"چ";s:3:"ﭻ";s:2:"چ";s:3:"ﭼ";s:2:"چ";s:3:"ﭽ";s:2:"چ";s:3:"ﭾ";s:2:"ڇ";s:3:"ﭿ";s:2:"ڇ";s:3:"ﮀ";s:2:"ڇ";s:3:"ﮁ";s:2:"ڇ";s:3:"ﮂ";s:2:"ڍ";s:3:"ﮃ";s:2:"ڍ";s:3:"ﮄ";s:2:"ڌ";s:3:"ﮅ";s:2:"ڌ";s:3:"ﮆ";s:2:"ڎ";s:3:"ﮇ";s:2:"ڎ";s:3:"ﮈ";s:2:"ڈ";s:3:"ﮉ";s:2:"ڈ";s:3:"ﮊ";s:2:"ژ";s:3:"ﮋ";s:2:"ژ";s:3:"ﮌ";s:2:"ڑ";s:3:"ﮍ";s:2:"ڑ";s:3:"ﮎ";s:2:"ک";s:3:"ﮏ";s:2:"ک";s:3:"ﮐ";s:2:"ک";s:3:"ﮑ";s:2:"ک";s:3:"ﮒ";s:2:"گ";s:3:"ﮓ";s:2:"گ";s:3:"ﮔ";s:2:"گ";s:3:"ﮕ";s:2:"گ";s:3:"ﮖ";s:2:"ڳ";s:3:"ﮗ";s:2:"ڳ";s:3:"ﮘ";s:2:"ڳ";s:3:"ﮙ";s:2:"ڳ";s:3:"ﮚ";s:2:"ڱ";s:3:"ﮛ";s:2:"ڱ";s:3:"ﮜ";s:2:"ڱ";s:3:"ﮝ";s:2:"ڱ";s:3:"ﮞ";s:2:"ں";s:3:"ﮟ";s:2:"ں";s:3:"ﮠ";s:2:"ڻ";s:3:"ﮡ";s:2:"ڻ";s:3:"ﮢ";s:2:"ڻ";s:3:"ﮣ";s:2:"ڻ";s:3:"ﮤ";s:2:"ۀ";s:3:"ﮥ";s:2:"ۀ";s:3:"ﮦ";s:2:"ہ";s:3:"ﮧ";s:2:"ہ";s:3:"ﮨ";s:2:"ہ";s:3:"ﮩ";s:2:"ہ";s:3:"ﮪ";s:2:"ھ";s:3:"ﮫ";s:2:"ھ";s:3:"ﮬ";s:2:"ھ";s:3:"ﮭ";s:2:"ھ";s:3:"ﮮ";s:2:"ے";s:3:"ﮯ";s:2:"ے";s:3:"ﮰ";s:2:"ۓ";s:3:"ﮱ";s:2:"ۓ";s:3:"ﯓ";s:2:"ڭ";s:3:"ﯔ";s:2:"ڭ";s:3:"ﯕ";s:2:"ڭ";s:3:"ﯖ";s:2:"ڭ";s:3:"ﯗ";s:2:"ۇ";s:3:"ﯘ";s:2:"ۇ";s:3:"ﯙ";s:2:"ۆ";s:3:"ﯚ";s:2:"ۆ";s:3:"ﯛ";s:2:"ۈ";s:3:"ﯜ";s:2:"ۈ";s:3:"ﯝ";s:2:"ٷ";s:3:"ﯞ";s:2:"ۋ";s:3:"ﯟ";s:2:"ۋ";s:3:"ﯠ";s:2:"ۅ";s:3:"ﯡ";s:2:"ۅ";s:3:"ﯢ";s:2:"ۉ";s:3:"ﯣ";s:2:"ۉ";s:3:"ﯤ";s:2:"ې";s:3:"ﯥ";s:2:"ې";s:3:"ﯦ";s:2:"ې";s:3:"ﯧ";s:2:"ې";s:3:"ﯨ";s:2:"ى";s:3:"ﯩ";s:2:"ى";s:3:"ﯪ";s:4:"ئا";s:3:"ﯫ";s:4:"ئا";s:3:"ﯬ";s:4:"ئە";s:3:"ﯭ";s:4:"ئە";s:3:"ﯮ";s:4:"ئو";s:3:"ﯯ";s:4:"ئو";s:3:"ﯰ";s:4:"ئۇ";s:3:"ﯱ";s:4:"ئۇ";s:3:"ﯲ";s:4:"ئۆ";s:3:"ﯳ";s:4:"ئۆ";s:3:"ﯴ";s:4:"ئۈ";s:3:"ﯵ";s:4:"ئۈ";s:3:"ﯶ";s:4:"ئې";s:3:"ﯷ";s:4:"ئې";s:3:"ﯸ";s:4:"ئې";s:3:"ﯹ";s:4:"ئى";s:3:"ﯺ";s:4:"ئى";s:3:"ﯻ";s:4:"ئى";s:3:"ﯼ";s:2:"ی";s:3:"ﯽ";s:2:"ی";s:3:"ﯾ";s:2:"ی";s:3:"ﯿ";s:2:"ی";s:3:"ﰀ";s:4:"ئج";s:3:"ﰁ";s:4:"ئح";s:3:"ﰂ";s:4:"ئم";s:3:"ﰃ";s:4:"ئى";s:3:"ﰄ";s:4:"ئي";s:3:"ﰅ";s:4:"بج";s:3:"ﰆ";s:4:"بح";s:3:"ﰇ";s:4:"بخ";s:3:"ﰈ";s:4:"بم";s:3:"ﰉ";s:4:"بى";s:3:"ﰊ";s:4:"بي";s:3:"ﰋ";s:4:"تج";s:3:"ﰌ";s:4:"تح";s:3:"ﰍ";s:4:"تخ";s:3:"ﰎ";s:4:"تم";s:3:"ﰏ";s:4:"تى";s:3:"ﰐ";s:4:"تي";s:3:"ﰑ";s:4:"ثج";s:3:"ﰒ";s:4:"ثم";s:3:"ﰓ";s:4:"ثى";s:3:"ﰔ";s:4:"ثي";s:3:"ﰕ";s:4:"جح";s:3:"ﰖ";s:4:"جم";s:3:"ﰗ";s:4:"حج";s:3:"ﰘ";s:4:"حم";s:3:"ﰙ";s:4:"خج";s:3:"ﰚ";s:4:"خح";s:3:"ﰛ";s:4:"خم";s:3:"ﰜ";s:4:"سج";s:3:"ﰝ";s:4:"سح";s:3:"ﰞ";s:4:"سخ";s:3:"ﰟ";s:4:"سم";s:3:"ﰠ";s:4:"صح";s:3:"ﰡ";s:4:"صم";s:3:"ﰢ";s:4:"ضج";s:3:"ﰣ";s:4:"ضح";s:3:"ﰤ";s:4:"ضخ";s:3:"ﰥ";s:4:"ضم";s:3:"ﰦ";s:4:"طح";s:3:"ﰧ";s:4:"طم";s:3:"ﰨ";s:4:"ظم";s:3:"ﰩ";s:4:"عج";s:3:"ﰪ";s:4:"عم";s:3:"ﰫ";s:4:"غج";s:3:"ﰬ";s:4:"غم";s:3:"ﰭ";s:4:"فج";s:3:"ﰮ";s:4:"فح";s:3:"ﰯ";s:4:"فخ";s:3:"ﰰ";s:4:"فم";s:3:"ﰱ";s:4:"فى";s:3:"ﰲ";s:4:"في";s:3:"ﰳ";s:4:"قح";s:3:"ﰴ";s:4:"قم";s:3:"ﰵ";s:4:"قى";s:3:"ﰶ";s:4:"قي";s:3:"ﰷ";s:4:"كا";s:3:"ﰸ";s:4:"كج";s:3:"ﰹ";s:4:"كح";s:3:"ﰺ";s:4:"كخ";s:3:"ﰻ";s:4:"كل";s:3:"ﰼ";s:4:"كم";s:3:"ﰽ";s:4:"كى";s:3:"ﰾ";s:4:"كي";s:3:"ﰿ";s:4:"لج";s:3:"ﱀ";s:4:"لح";s:3:"ﱁ";s:4:"لخ";s:3:"ﱂ";s:4:"لم";s:3:"ﱃ";s:4:"لى";s:3:"ﱄ";s:4:"لي";s:3:"ﱅ";s:4:"مج";s:3:"ﱆ";s:4:"مح";s:3:"ﱇ";s:4:"مخ";s:3:"ﱈ";s:4:"مم";s:3:"ﱉ";s:4:"مى";s:3:"ﱊ";s:4:"مي";s:3:"ﱋ";s:4:"نج";s:3:"ﱌ";s:4:"نح";s:3:"ﱍ";s:4:"نخ";s:3:"ﱎ";s:4:"نم";s:3:"ﱏ";s:4:"نى";s:3:"ﱐ";s:4:"ني";s:3:"ﱑ";s:4:"هج";s:3:"ﱒ";s:4:"هم";s:3:"ﱓ";s:4:"هى";s:3:"ﱔ";s:4:"هي";s:3:"ﱕ";s:4:"يج";s:3:"ﱖ";s:4:"يح";s:3:"ﱗ";s:4:"يخ";s:3:"ﱘ";s:4:"يم";s:3:"ﱙ";s:4:"يى";s:3:"ﱚ";s:4:"يي";s:3:"ﱛ";s:4:"ذٰ";s:3:"ﱜ";s:4:"رٰ";s:3:"ﱝ";s:4:"ىٰ";s:3:"ﱞ";s:5:" ٌّ";s:3:"ﱟ";s:5:" ٍّ";s:3:"ﱠ";s:5:" َّ";s:3:"ﱡ";s:5:" ُّ";s:3:"ﱢ";s:5:" ِّ";s:3:"ﱣ";s:5:" ّٰ";s:3:"ﱤ";s:4:"ئر";s:3:"ﱥ";s:4:"ئز";s:3:"ﱦ";s:4:"ئم";s:3:"ﱧ";s:4:"ئن";s:3:"ﱨ";s:4:"ئى";s:3:"ﱩ";s:4:"ئي";s:3:"ﱪ";s:4:"بر";s:3:"ﱫ";s:4:"بز";s:3:"ﱬ";s:4:"بم";s:3:"ﱭ";s:4:"بن";s:3:"ﱮ";s:4:"بى";s:3:"ﱯ";s:4:"بي";s:3:"ﱰ";s:4:"تر";s:3:"ﱱ";s:4:"تز";s:3:"ﱲ";s:4:"تم";s:3:"ﱳ";s:4:"تن";s:3:"ﱴ";s:4:"تى";s:3:"ﱵ";s:4:"تي";s:3:"ﱶ";s:4:"ثر";s:3:"ﱷ";s:4:"ثز";s:3:"ﱸ";s:4:"ثم";s:3:"ﱹ";s:4:"ثن";s:3:"ﱺ";s:4:"ثى";s:3:"ﱻ";s:4:"ثي";s:3:"ﱼ";s:4:"فى";s:3:"ﱽ";s:4:"في";s:3:"ﱾ";s:4:"قى";s:3:"ﱿ";s:4:"قي";s:3:"ﲀ";s:4:"كا";s:3:"ﲁ";s:4:"كل";s:3:"ﲂ";s:4:"كم";s:3:"ﲃ";s:4:"كى";s:3:"ﲄ";s:4:"كي";s:3:"ﲅ";s:4:"لم";s:3:"ﲆ";s:4:"لى";s:3:"ﲇ";s:4:"لي";s:3:"ﲈ";s:4:"ما";s:3:"ﲉ";s:4:"مم";s:3:"ﲊ";s:4:"نر";s:3:"ﲋ";s:4:"نز";s:3:"ﲌ";s:4:"نم";s:3:"ﲍ";s:4:"نن";s:3:"ﲎ";s:4:"نى";s:3:"ﲏ";s:4:"ني";s:3:"ﲐ";s:4:"ىٰ";s:3:"ﲑ";s:4:"ير";s:3:"ﲒ";s:4:"يز";s:3:"ﲓ";s:4:"يم";s:3:"ﲔ";s:4:"ين";s:3:"ﲕ";s:4:"يى";s:3:"ﲖ";s:4:"يي";s:3:"ﲗ";s:4:"ئج";s:3:"ﲘ";s:4:"ئح";s:3:"ﲙ";s:4:"ئخ";s:3:"ﲚ";s:4:"ئم";s:3:"ﲛ";s:4:"ئه";s:3:"ﲜ";s:4:"بج";s:3:"ﲝ";s:4:"بح";s:3:"ﲞ";s:4:"بخ";s:3:"ﲟ";s:4:"بم";s:3:"ﲠ";s:4:"به";s:3:"ﲡ";s:4:"تج";s:3:"ﲢ";s:4:"تح";s:3:"ﲣ";s:4:"تخ";s:3:"ﲤ";s:4:"تم";s:3:"ﲥ";s:4:"ته";s:3:"ﲦ";s:4:"ثم";s:3:"ﲧ";s:4:"جح";s:3:"ﲨ";s:4:"جم";s:3:"ﲩ";s:4:"حج";s:3:"ﲪ";s:4:"حم";s:3:"ﲫ";s:4:"خج";s:3:"ﲬ";s:4:"خم";s:3:"ﲭ";s:4:"سج";s:3:"ﲮ";s:4:"سح";s:3:"ﲯ";s:4:"سخ";s:3:"ﲰ";s:4:"سم";s:3:"ﲱ";s:4:"صح";s:3:"ﲲ";s:4:"صخ";s:3:"ﲳ";s:4:"صم";s:3:"ﲴ";s:4:"ضج";s:3:"ﲵ";s:4:"ضح";s:3:"ﲶ";s:4:"ضخ";s:3:"ﲷ";s:4:"ضم";s:3:"ﲸ";s:4:"طح";s:3:"ﲹ";s:4:"ظم";s:3:"ﲺ";s:4:"عج";s:3:"ﲻ";s:4:"عم";s:3:"ﲼ";s:4:"غج";s:3:"ﲽ";s:4:"غم";s:3:"ﲾ";s:4:"فج";s:3:"ﲿ";s:4:"فح";s:3:"ﳀ";s:4:"فخ";s:3:"ﳁ";s:4:"فم";s:3:"ﳂ";s:4:"قح";s:3:"ﳃ";s:4:"قم";s:3:"ﳄ";s:4:"كج";s:3:"ﳅ";s:4:"كح";s:3:"ﳆ";s:4:"كخ";s:3:"ﳇ";s:4:"كل";s:3:"ﳈ";s:4:"كم";s:3:"ﳉ";s:4:"لج";s:3:"ﳊ";s:4:"لح";s:3:"ﳋ";s:4:"لخ";s:3:"ﳌ";s:4:"لم";s:3:"ﳍ";s:4:"له";s:3:"ﳎ";s:4:"مج";s:3:"ﳏ";s:4:"مح";s:3:"ﳐ";s:4:"مخ";s:3:"ﳑ";s:4:"مم";s:3:"ﳒ";s:4:"نج";s:3:"ﳓ";s:4:"نح";s:3:"ﳔ";s:4:"نخ";s:3:"ﳕ";s:4:"نم";s:3:"ﳖ";s:4:"نه";s:3:"ﳗ";s:4:"هج";s:3:"ﳘ";s:4:"هم";s:3:"ﳙ";s:4:"هٰ";s:3:"ﳚ";s:4:"يج";s:3:"ﳛ";s:4:"يح";s:3:"ﳜ";s:4:"يخ";s:3:"ﳝ";s:4:"يم";s:3:"ﳞ";s:4:"يه";s:3:"ﳟ";s:4:"ئم";s:3:"ﳠ";s:4:"ئه";s:3:"ﳡ";s:4:"بم";s:3:"ﳢ";s:4:"به";s:3:"ﳣ";s:4:"تم";s:3:"ﳤ";s:4:"ته";s:3:"ﳥ";s:4:"ثم";s:3:"ﳦ";s:4:"ثه";s:3:"ﳧ";s:4:"سم";s:3:"ﳨ";s:4:"سه";s:3:"ﳩ";s:4:"شم";s:3:"ﳪ";s:4:"شه";s:3:"ﳫ";s:4:"كل";s:3:"ﳬ";s:4:"كم";s:3:"ﳭ";s:4:"لم";s:3:"ﳮ";s:4:"نم";s:3:"ﳯ";s:4:"نه";s:3:"ﳰ";s:4:"يم";s:3:"ﳱ";s:4:"يه";s:3:"ﳲ";s:6:"ـَّ";s:3:"ﳳ";s:6:"ـُّ";s:3:"ﳴ";s:6:"ـِّ";s:3:"ﳵ";s:4:"طى";s:3:"ﳶ";s:4:"طي";s:3:"ﳷ";s:4:"عى";s:3:"ﳸ";s:4:"عي";s:3:"ﳹ";s:4:"غى";s:3:"ﳺ";s:4:"غي";s:3:"ﳻ";s:4:"سى";s:3:"ﳼ";s:4:"سي";s:3:"ﳽ";s:4:"شى";s:3:"ﳾ";s:4:"شي";s:3:"ﳿ";s:4:"حى";s:3:"ﴀ";s:4:"حي";s:3:"ﴁ";s:4:"جى";s:3:"ﴂ";s:4:"جي";s:3:"ﴃ";s:4:"خى";s:3:"ﴄ";s:4:"خي";s:3:"ﴅ";s:4:"صى";s:3:"ﴆ";s:4:"صي";s:3:"ﴇ";s:4:"ضى";s:3:"ﴈ";s:4:"ضي";s:3:"ﴉ";s:4:"شج";s:3:"ﴊ";s:4:"شح";s:3:"ﴋ";s:4:"شخ";s:3:"ﴌ";s:4:"شم";s:3:"ﴍ";s:4:"شر";s:3:"ﴎ";s:4:"سر";s:3:"ﴏ";s:4:"صر";s:3:"ﴐ";s:4:"ضر";s:3:"ﴑ";s:4:"طى";s:3:"ﴒ";s:4:"طي";s:3:"ﴓ";s:4:"عى";s:3:"ﴔ";s:4:"عي";s:3:"ﴕ";s:4:"غى";s:3:"ﴖ";s:4:"غي";s:3:"ﴗ";s:4:"سى";s:3:"ﴘ";s:4:"سي";s:3:"ﴙ";s:4:"شى";s:3:"ﴚ";s:4:"شي";s:3:"ﴛ";s:4:"حى";s:3:"ﴜ";s:4:"حي";s:3:"ﴝ";s:4:"جى";s:3:"ﴞ";s:4:"جي";s:3:"ﴟ";s:4:"خى";s:3:"ﴠ";s:4:"خي";s:3:"ﴡ";s:4:"صى";s:3:"ﴢ";s:4:"صي";s:3:"ﴣ";s:4:"ضى";s:3:"ﴤ";s:4:"ضي";s:3:"ﴥ";s:4:"شج";s:3:"ﴦ";s:4:"شح";s:3:"ﴧ";s:4:"شخ";s:3:"ﴨ";s:4:"شم";s:3:"ﴩ";s:4:"شر";s:3:"ﴪ";s:4:"سر";s:3:"ﴫ";s:4:"صر";s:3:"ﴬ";s:4:"ضر";s:3:"ﴭ";s:4:"شج";s:3:"ﴮ";s:4:"شح";s:3:"ﴯ";s:4:"شخ";s:3:"ﴰ";s:4:"شم";s:3:"ﴱ";s:4:"سه";s:3:"ﴲ";s:4:"شه";s:3:"ﴳ";s:4:"طم";s:3:"ﴴ";s:4:"سج";s:3:"ﴵ";s:4:"سح";s:3:"ﴶ";s:4:"سخ";s:3:"ﴷ";s:4:"شج";s:3:"ﴸ";s:4:"شح";s:3:"ﴹ";s:4:"شخ";s:3:"ﴺ";s:4:"طم";s:3:"ﴻ";s:4:"ظم";s:3:"ﴼ";s:4:"اً";s:3:"ﴽ";s:4:"اً";s:3:"ﵐ";s:6:"تجم";s:3:"ﵑ";s:6:"تحج";s:3:"ﵒ";s:6:"تحج";s:3:"ﵓ";s:6:"تحم";s:3:"ﵔ";s:6:"تخم";s:3:"ﵕ";s:6:"تمج";s:3:"ﵖ";s:6:"تمح";s:3:"ﵗ";s:6:"تمخ";s:3:"ﵘ";s:6:"جمح";s:3:"ﵙ";s:6:"جمح";s:3:"ﵚ";s:6:"حمي";s:3:"ﵛ";s:6:"حمى";s:3:"ﵜ";s:6:"سحج";s:3:"ﵝ";s:6:"سجح";s:3:"ﵞ";s:6:"سجى";s:3:"ﵟ";s:6:"سمح";s:3:"ﵠ";s:6:"سمح";s:3:"ﵡ";s:6:"سمج";s:3:"ﵢ";s:6:"سمم";s:3:"ﵣ";s:6:"سمم";s:3:"ﵤ";s:6:"صحح";s:3:"ﵥ";s:6:"صحح";s:3:"ﵦ";s:6:"صمم";s:3:"ﵧ";s:6:"شحم";s:3:"ﵨ";s:6:"شحم";s:3:"ﵩ";s:6:"شجي";s:3:"ﵪ";s:6:"شمخ";s:3:"ﵫ";s:6:"شمخ";s:3:"ﵬ";s:6:"شمم";s:3:"ﵭ";s:6:"شمم";s:3:"ﵮ";s:6:"ضحى";s:3:"ﵯ";s:6:"ضخم";s:3:"ﵰ";s:6:"ضخم";s:3:"ﵱ";s:6:"طمح";s:3:"ﵲ";s:6:"طمح";s:3:"ﵳ";s:6:"طمم";s:3:"ﵴ";s:6:"طمي";s:3:"ﵵ";s:6:"عجم";s:3:"ﵶ";s:6:"عمم";s:3:"ﵷ";s:6:"عمم";s:3:"ﵸ";s:6:"عمى";s:3:"ﵹ";s:6:"غمم";s:3:"ﵺ";s:6:"غمي";s:3:"ﵻ";s:6:"غمى";s:3:"ﵼ";s:6:"فخم";s:3:"ﵽ";s:6:"فخم";s:3:"ﵾ";s:6:"قمح";s:3:"ﵿ";s:6:"قمم";s:3:"ﶀ";s:6:"لحم";s:3:"ﶁ";s:6:"لحي";s:3:"ﶂ";s:6:"لحى";s:3:"ﶃ";s:6:"لجج";s:3:"ﶄ";s:6:"لجج";s:3:"ﶅ";s:6:"لخم";s:3:"ﶆ";s:6:"لخم";s:3:"ﶇ";s:6:"لمح";s:3:"ﶈ";s:6:"لمح";s:3:"ﶉ";s:6:"محج";s:3:"ﶊ";s:6:"محم";s:3:"ﶋ";s:6:"محي";s:3:"ﶌ";s:6:"مجح";s:3:"ﶍ";s:6:"مجم";s:3:"ﶎ";s:6:"مخج";s:3:"ﶏ";s:6:"مخم";s:3:"ﶒ";s:6:"مجخ";s:3:"ﶓ";s:6:"همج";s:3:"ﶔ";s:6:"همم";s:3:"ﶕ";s:6:"نحم";s:3:"ﶖ";s:6:"نحى";s:3:"ﶗ";s:6:"نجم";s:3:"ﶘ";s:6:"نجم";s:3:"ﶙ";s:6:"نجى";s:3:"ﶚ";s:6:"نمي";s:3:"ﶛ";s:6:"نمى";s:3:"ﶜ";s:6:"يمم";s:3:"ﶝ";s:6:"يمم";s:3:"ﶞ";s:6:"بخي";s:3:"ﶟ";s:6:"تجي";s:3:"ﶠ";s:6:"تجى";s:3:"ﶡ";s:6:"تخي";s:3:"ﶢ";s:6:"تخى";s:3:"ﶣ";s:6:"تمي";s:3:"ﶤ";s:6:"تمى";s:3:"ﶥ";s:6:"جمي";s:3:"ﶦ";s:6:"جحى";s:3:"ﶧ";s:6:"جمى";s:3:"ﶨ";s:6:"سخى";s:3:"ﶩ";s:6:"صحي";s:3:"ﶪ";s:6:"شحي";s:3:"ﶫ";s:6:"ضحي";s:3:"ﶬ";s:6:"لجي";s:3:"ﶭ";s:6:"لمي";s:3:"ﶮ";s:6:"يحي";s:3:"ﶯ";s:6:"يجي";s:3:"ﶰ";s:6:"يمي";s:3:"ﶱ";s:6:"ممي";s:3:"ﶲ";s:6:"قمي";s:3:"ﶳ";s:6:"نحي";s:3:"ﶴ";s:6:"قمح";s:3:"ﶵ";s:6:"لحم";s:3:"ﶶ";s:6:"عمي";s:3:"ﶷ";s:6:"كمي";s:3:"ﶸ";s:6:"نجح";s:3:"ﶹ";s:6:"مخي";s:3:"ﶺ";s:6:"لجم";s:3:"ﶻ";s:6:"كمم";s:3:"ﶼ";s:6:"لجم";s:3:"ﶽ";s:6:"نجح";s:3:"ﶾ";s:6:"جحي";s:3:"ﶿ";s:6:"حجي";s:3:"ﷀ";s:6:"مجي";s:3:"ﷁ";s:6:"فمي";s:3:"ﷂ";s:6:"بحي";s:3:"ﷃ";s:6:"كمم";s:3:"ﷄ";s:6:"عجم";s:3:"ﷅ";s:6:"صمم";s:3:"ﷆ";s:6:"سخي";s:3:"ﷇ";s:6:"نجي";s:3:"ﷰ";s:6:"صلے";s:3:"ﷱ";s:6:"قلے";s:3:"ﷲ";s:8:"الله";s:3:"ﷳ";s:8:"اكبر";s:3:"ﷴ";s:8:"محمد";s:3:"ﷵ";s:8:"صلعم";s:3:"ﷶ";s:8:"رسول";s:3:"ﷷ";s:8:"عليه";s:3:"ﷸ";s:8:"وسلم";s:3:"ﷹ";s:6:"صلى";s:3:"ﷺ";s:33:"صلى الله عليه وسلم";s:3:"ﷻ";s:15:"جل جلاله";s:3:"﷼";s:8:"ریال";s:3:"ﹰ";s:3:" ً";s:3:"ﹱ";s:4:"ـً";s:3:"ﹲ";s:3:" ٌ";s:3:"ﹴ";s:3:" ٍ";s:3:"ﹶ";s:3:" َ";s:3:"ﹷ";s:4:"ـَ";s:3:"ﹸ";s:3:" ُ";s:3:"ﹹ";s:4:"ـُ";s:3:"ﹺ";s:3:" ِ";s:3:"ﹻ";s:4:"ـِ";s:3:"ﹼ";s:3:" ّ";s:3:"ﹽ";s:4:"ـّ";s:3:"ﹾ";s:3:" ْ";s:3:"ﹿ";s:4:"ـْ";s:3:"ﺀ";s:2:"ء";s:3:"ﺁ";s:2:"آ";s:3:"ﺂ";s:2:"آ";s:3:"ﺃ";s:2:"أ";s:3:"ﺄ";s:2:"أ";s:3:"ﺅ";s:2:"ؤ";s:3:"ﺆ";s:2:"ؤ";s:3:"ﺇ";s:2:"إ";s:3:"ﺈ";s:2:"إ";s:3:"ﺉ";s:2:"ئ";s:3:"ﺊ";s:2:"ئ";s:3:"ﺋ";s:2:"ئ";s:3:"ﺌ";s:2:"ئ";s:3:"ﺍ";s:2:"ا";s:3:"ﺎ";s:2:"ا";s:3:"ﺏ";s:2:"ب";s:3:"ﺐ";s:2:"ب";s:3:"ﺑ";s:2:"ب";s:3:"ﺒ";s:2:"ب";s:3:"ﺓ";s:2:"ة";s:3:"ﺔ";s:2:"ة";s:3:"ﺕ";s:2:"ت";s:3:"ﺖ";s:2:"ت";s:3:"ﺗ";s:2:"ت";s:3:"ﺘ";s:2:"ت";s:3:"ﺙ";s:2:"ث";s:3:"ﺚ";s:2:"ث";s:3:"ﺛ";s:2:"ث";s:3:"ﺜ";s:2:"ث";s:3:"ﺝ";s:2:"ج";s:3:"ﺞ";s:2:"ج";s:3:"ﺟ";s:2:"ج";s:3:"ﺠ";s:2:"ج";s:3:"ﺡ";s:2:"ح";s:3:"ﺢ";s:2:"ح";s:3:"ﺣ";s:2:"ح";s:3:"ﺤ";s:2:"ح";s:3:"ﺥ";s:2:"خ";s:3:"ﺦ";s:2:"خ";s:3:"ﺧ";s:2:"خ";s:3:"ﺨ";s:2:"خ";s:3:"ﺩ";s:2:"د";s:3:"ﺪ";s:2:"د";s:3:"ﺫ";s:2:"ذ";s:3:"ﺬ";s:2:"ذ";s:3:"ﺭ";s:2:"ر";s:3:"ﺮ";s:2:"ر";s:3:"ﺯ";s:2:"ز";s:3:"ﺰ";s:2:"ز";s:3:"ﺱ";s:2:"س";s:3:"ﺲ";s:2:"س";s:3:"ﺳ";s:2:"س";s:3:"ﺴ";s:2:"س";s:3:"ﺵ";s:2:"ش";s:3:"ﺶ";s:2:"ش";s:3:"ﺷ";s:2:"ش";s:3:"ﺸ";s:2:"ش";s:3:"ﺹ";s:2:"ص";s:3:"ﺺ";s:2:"ص";s:3:"ﺻ";s:2:"ص";s:3:"ﺼ";s:2:"ص";s:3:"ﺽ";s:2:"ض";s:3:"ﺾ";s:2:"ض";s:3:"ﺿ";s:2:"ض";s:3:"ﻀ";s:2:"ض";s:3:"ﻁ";s:2:"ط";s:3:"ﻂ";s:2:"ط";s:3:"ﻃ";s:2:"ط";s:3:"ﻄ";s:2:"ط";s:3:"ﻅ";s:2:"ظ";s:3:"ﻆ";s:2:"ظ";s:3:"ﻇ";s:2:"ظ";s:3:"ﻈ";s:2:"ظ";s:3:"ﻉ";s:2:"ع";s:3:"ﻊ";s:2:"ع";s:3:"ﻋ";s:2:"ع";s:3:"ﻌ";s:2:"ع";s:3:"ﻍ";s:2:"غ";s:3:"ﻎ";s:2:"غ";s:3:"ﻏ";s:2:"غ";s:3:"ﻐ";s:2:"غ";s:3:"ﻑ";s:2:"ف";s:3:"ﻒ";s:2:"ف";s:3:"ﻓ";s:2:"ف";s:3:"ﻔ";s:2:"ف";s:3:"ﻕ";s:2:"ق";s:3:"ﻖ";s:2:"ق";s:3:"ﻗ";s:2:"ق";s:3:"ﻘ";s:2:"ق";s:3:"ﻙ";s:2:"ك";s:3:"ﻚ";s:2:"ك";s:3:"ﻛ";s:2:"ك";s:3:"ﻜ";s:2:"ك";s:3:"ﻝ";s:2:"ل";s:3:"ﻞ";s:2:"ل";s:3:"ﻟ";s:2:"ل";s:3:"ﻠ";s:2:"ل";s:3:"ﻡ";s:2:"م";s:3:"ﻢ";s:2:"م";s:3:"ﻣ";s:2:"م";s:3:"ﻤ";s:2:"م";s:3:"ﻥ";s:2:"ن";s:3:"ﻦ";s:2:"ن";s:3:"ﻧ";s:2:"ن";s:3:"ﻨ";s:2:"ن";s:3:"ﻩ";s:2:"ه";s:3:"ﻪ";s:2:"ه";s:3:"ﻫ";s:2:"ه";s:3:"ﻬ";s:2:"ه";s:3:"ﻭ";s:2:"و";s:3:"ﻮ";s:2:"و";s:3:"ﻯ";s:2:"ى";s:3:"ﻰ";s:2:"ى";s:3:"ﻱ";s:2:"ي";s:3:"ﻲ";s:2:"ي";s:3:"ﻳ";s:2:"ي";s:3:"ﻴ";s:2:"ي";s:3:"ﻵ";s:4:"لآ";s:3:"ﻶ";s:4:"لآ";s:3:"ﻷ";s:4:"لأ";s:3:"ﻸ";s:4:"لأ";s:3:"ﻹ";s:4:"لإ";s:3:"ﻺ";s:4:"لإ";s:3:"ﻻ";s:4:"لا";s:3:"ﻼ";s:4:"لا";} |
| \ No newline at end of file |
| Index: trunk/phase3/serialized/normalize-ml.ser |
| — | — | @@ -0,0 +1 @@ |
| | 2 | +a:6:{s:9:"ണ്";s:3:"ൺ";s:9:"ന്";s:3:"ൻ";s:9:"ര്";s:3:"ർ";s:9:"ല്";s:3:"ൽ";s:9:"ള്";s:3:"ൾ";s:9:"ക്";s:3:"ൿ";} |
| \ No newline at end of file |
| Index: trunk/phase3/languages/Language.php |
| — | — | @@ -62,6 +62,11 @@ |
| 63 | 63 | var $minSearchLength; |
| 64 | 64 | var $mExtendedSpecialPageAliases; |
| 65 | 65 | |
| | 66 | + /** |
| | 67 | + * ReplacementArray object caches |
| | 68 | + */ |
| | 69 | + var $transformData = array(); |
| | 70 | + |
| 66 | 71 | static public $dataCache; |
| 67 | 72 | static public $mLangObjCache = array(); |
| 68 | 73 | |
| — | — | @@ -1866,6 +1871,36 @@ |
| 1867 | 1872 | } |
| 1868 | 1873 | |
| 1869 | 1874 | /** |
| | 1875 | + * Convert a UTF-8 string to normal form C. In Malayalam and Arabic, this |
| | 1876 | + * also cleans up certain backwards-compatible sequences, converting them |
| | 1877 | + * to the modern Unicode equivalent. |
| | 1878 | + * |
| | 1879 | + * This is language-specific for performance reasons only. |
| | 1880 | + */ |
| | 1881 | + function normalize( $s ) { |
| | 1882 | + return UtfNormal::cleanUp( $s ); |
| | 1883 | + } |
| | 1884 | + |
| | 1885 | + /** |
| | 1886 | + * Transform a string using serialized data stored in the given file (which |
| | 1887 | + * must be in the serialized subdirectory of $IP). The file contains pairs |
| | 1888 | + * mapping source characters to destination characters. |
| | 1889 | + * |
| | 1890 | + * The data is cached in process memory. This will go faster if you have the |
| | 1891 | + * FastStringSearch extension. |
| | 1892 | + */ |
| | 1893 | + function transformUsingPairFile( $file, $string ) { |
| | 1894 | + if ( !isset( $this->transformData[$file] ) ) { |
| | 1895 | + $data = wfGetPrecompiledData( $file ); |
| | 1896 | + if ( $data === false ) { |
| | 1897 | + throw new MWException( __METHOD__.": The transformation file $file is missing" ); |
| | 1898 | + } |
| | 1899 | + $this->transformData[$file] = new ReplacementArray( $data ); |
| | 1900 | + } |
| | 1901 | + return $this->transformData[$file]->replace( $string ); |
| | 1902 | + } |
| | 1903 | + |
| | 1904 | + /** |
| 1870 | 1905 | * For right-to-left language support |
| 1871 | 1906 | * |
| 1872 | 1907 | * @return bool |
| Index: trunk/phase3/languages/classes/LanguageAr.php |
| — | — | @@ -6,6 +6,7 @@ |
| 7 | 7 | * @author Niklas Laxström |
| 8 | 8 | */ |
| 9 | 9 | class LanguageAr extends Language { |
| | 10 | + var $normalizeArray; |
| 10 | 11 | |
| 11 | 12 | function convertPlural( $count, $forms ) { |
| 12 | 13 | if ( !count($forms) ) { return ''; } |
| — | — | @@ -26,4 +27,20 @@ |
| 27 | 28 | } |
| 28 | 29 | return $forms[$index]; |
| 29 | 30 | } |
| | 31 | + |
| | 32 | + /** |
| | 33 | + * Temporary hack for bug 9413: replace Arabic presentation forms with their |
| | 34 | + * standard equivalents. |
| | 35 | + * |
| | 36 | + * FIXME: This is language-specific for now only to avoid the negative |
| | 37 | + * performance impact of enabling it for all languages. |
| | 38 | + */ |
| | 39 | + function normalize( $s ) { |
| | 40 | + global $wgFixArchaicUnicode; |
| | 41 | + $s = parent::normalize( $s ); |
| | 42 | + if ( $wgFixArchaicUnicode ) { |
| | 43 | + $s = $this->transformUsingPairFile( 'normalize-ar.ser', $s ); |
| | 44 | + } |
| | 45 | + return $s; |
| | 46 | + } |
| 30 | 47 | } |
| Index: trunk/phase3/languages/classes/LanguageMl.php |
| — | — | @@ -0,0 +1,22 @@ |
| | 2 | +<?php |
| | 3 | + |
| | 4 | +class LanguageMl extends Language { |
| | 5 | + /** |
| | 6 | + * Temporary hack for the issue described at |
| | 7 | + * http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46396 |
| | 8 | + * Convert Unicode 5.0 style Malayalam input to Unicode 5.1. Similar to |
| | 9 | + * bug 9413. Also fixes miscellaneous problems due to mishandling of ZWJ, |
| | 10 | + * e.g. bug 11162. |
| | 11 | + * |
| | 12 | + * FIXME: This is language-specific for now only to avoid the negative |
| | 13 | + * performance impact of enabling it for all languages. |
| | 14 | + */ |
| | 15 | + function normalize( $s ) { |
| | 16 | + global $wgFixArchaicUnicode; |
| | 17 | + $s = parent::normalize( $s ); |
| | 18 | + if ( $wgFixArchaicUnicode ) { |
| | 19 | + $s = $this->transformUsingPairFile( 'normalize-ml.ser', $s ); |
| | 20 | + } |
| | 21 | + return $s; |
| | 22 | + } |
| | 23 | +} |
| Property changes on: trunk/phase3/languages/classes/LanguageMl.php |
| ___________________________________________________________________ |
| Added: svn:eol-style |
| 1 | 24 | + native |
| Index: trunk/phase3/RELEASE-NOTES |
| — | — | @@ -283,6 +283,9 @@ |
| 284 | 284 | * (bug 19791) Add URL of file source as comment to thumbs (for ImageMagick) |
| 285 | 285 | * (bug 21946) Sorted wikitables do not properly handle minus signs |
| 286 | 286 | * (bug 18885) Red links for media files do not support shared repositories |
| | 287 | +* Added $wgFixArchaicUnicode, which, if enabled, converts some deprecated |
| | 288 | + Unicode sequences in Arabic and Malayalam text to their Unicode 5.1 |
| | 289 | + equivalents. |
| 287 | 290 | |
| 288 | 291 | === Bug fixes in 1.16 === |
| 289 | 292 | |