Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 69 |
|
0.00% |
0 / 3 |
CRAP | |
0.00% |
0 / 1 |
| GenerateNormalizerDataAr | |
0.00% |
0 / 69 |
|
0.00% |
0 / 3 |
272 | |
0.00% |
0 / 1 |
| __construct | |
0.00% |
0 / 4 |
|
0.00% |
0 / 1 |
2 | |||
| getDbType | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| execute | |
0.00% |
0 / 64 |
|
0.00% |
0 / 1 |
210 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * Generates the normalizer data file for Arabic. |
| 4 | * |
| 5 | * This program is free software; you can redistribute it and/or modify |
| 6 | * it under the terms of the GNU General Public License as published by |
| 7 | * the Free Software Foundation; either version 2 of the License, or |
| 8 | * (at your option) any later version. |
| 9 | * |
| 10 | * This program is distributed in the hope that it will be useful, |
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | * GNU General Public License for more details. |
| 14 | * |
| 15 | * You should have received a copy of the GNU General Public License along |
| 16 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 17 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 18 | * http://www.gnu.org/copyleft/gpl.html |
| 19 | * |
| 20 | * @file |
| 21 | * @ingroup MaintenanceLanguage |
| 22 | */ |
| 23 | |
| 24 | // @codeCoverageIgnoreStart |
| 25 | require_once __DIR__ . '/../Maintenance.php'; |
| 26 | // @codeCoverageIgnoreEnd |
| 27 | |
| 28 | use Wikimedia\StaticArrayWriter; |
| 29 | |
| 30 | /** |
| 31 | * Generates the normalizer data file for Arabic. |
| 32 | * |
| 33 | * This data file is used after normalizing to NFC. |
| 34 | * |
| 35 | * Example usage: |
| 36 | * |
| 37 | * curl 'https://unicode.org/Public/6.0.0/ucd/UnicodeData.txt' > /tmp/UnicodeData.txt |
| 38 | * php generateNormalizerDataAr.php --unicode-data-file /tmp/UnicodeData.txt |
| 39 | * |
| 40 | * @ingroup MaintenanceLanguage |
| 41 | */ |
| 42 | class GenerateNormalizerDataAr extends Maintenance { |
| 43 | public function __construct() { |
| 44 | parent::__construct(); |
| 45 | $this->addDescription( 'Generate the normalizer data file for Arabic' ); |
| 46 | $this->addOption( 'unicode-data-file', 'The local location of the data file ' . |
| 47 | 'from https://unicode.org/Public/6.0.0/ucd/UnicodeData.txt', false, true ); |
| 48 | } |
| 49 | |
| 50 | public function getDbType() { |
| 51 | return Maintenance::DB_NONE; |
| 52 | } |
| 53 | |
| 54 | public function execute() { |
| 55 | if ( !$this->hasOption( 'unicode-data-file' ) ) { |
| 56 | $dataFile = 'UnicodeData.txt'; |
| 57 | if ( !file_exists( $dataFile ) ) { |
| 58 | $this->fatalError( "Unable to find UnicodeData.txt. Please specify " . |
| 59 | "its location with --unicode-data-file=<FILE>" ); |
| 60 | } |
| 61 | } else { |
| 62 | $dataFile = $this->getOption( 'unicode-data-file' ); |
| 63 | if ( !file_exists( $dataFile ) ) { |
| 64 | $this->fatalError( 'Unable to find the specified data file.' ); |
| 65 | } |
| 66 | } |
| 67 | |
| 68 | $file = fopen( $dataFile, 'r' ); |
| 69 | if ( !$file ) { |
| 70 | $this->fatalError( 'Unable to open the data file.' ); |
| 71 | } |
| 72 | |
| 73 | // For the file format, see https://www.unicode.org/reports/tr44/ |
| 74 | $fieldNames = [ |
| 75 | 'Code', |
| 76 | 'Name', |
| 77 | 'General_Category', |
| 78 | 'Canonical_Combining_Class', |
| 79 | 'Bidi_Class', |
| 80 | 'Decomposition_Type_Mapping', |
| 81 | 'Numeric_Type_Value_6', |
| 82 | 'Numeric_Type_Value_7', |
| 83 | 'Numeric_Type_Value_8', |
| 84 | 'Bidi_Mirrored', |
| 85 | 'Unicode_1_Name', |
| 86 | 'ISO_Comment', |
| 87 | 'Simple_Uppercase_Mapping', |
| 88 | 'Simple_Lowercase_Mapping', |
| 89 | 'Simple_Titlecase_Mapping' |
| 90 | ]; |
| 91 | |
| 92 | $pairs = []; |
| 93 | |
| 94 | $lineNum = 0; |
| 95 | // phpcs:ignore Generic.CodeAnalysis.AssignmentInCondition.FoundInWhileCondition |
| 96 | while ( ( $line = fgets( $file ) ) !== false ) { |
| 97 | ++$lineNum; |
| 98 | |
| 99 | # Strip comments |
| 100 | $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) ); |
| 101 | if ( $line === '' ) { |
| 102 | continue; |
| 103 | } |
| 104 | |
| 105 | # Split fields |
| 106 | $numberedData = explode( ';', $line ); |
| 107 | $data = []; |
| 108 | foreach ( $fieldNames as $number => $name ) { |
| 109 | $data[$name] = $numberedData[$number]; |
| 110 | } |
| 111 | |
| 112 | $code = base_convert( $data['Code'], 16, 10 ); |
| 113 | if ( ( $code >= 0xFB50 && $code <= 0xFDFF ) # Arabic presentation forms A |
| 114 | || ( $code >= 0xFE70 && $code <= 0xFEFF ) # Arabic presentation forms B |
| 115 | ) { |
| 116 | if ( $data['Decomposition_Type_Mapping'] === '' ) { |
| 117 | // No decomposition |
| 118 | continue; |
| 119 | } |
| 120 | if ( !preg_match( '/^ *(<\w*>) +([0-9A-F ]*)$/', |
| 121 | $data['Decomposition_Type_Mapping'], $m ) |
| 122 | ) { |
| 123 | $this->error( "Can't parse Decomposition_Type/Mapping on line $lineNum" ); |
| 124 | $this->error( $line ); |
| 125 | continue; |
| 126 | } |
| 127 | |
| 128 | $source = UtfNormal\Utils::hexSequenceToUtf8( $data['Code'] ); |
| 129 | $dest = UtfNormal\Utils::hexSequenceToUtf8( $m[2] ); |
| 130 | $pairs[$source] = $dest; |
| 131 | } |
| 132 | } |
| 133 | |
| 134 | global $IP; |
| 135 | $writer = new StaticArrayWriter(); |
| 136 | file_put_contents( "$IP/includes/languages/data/NormalizeAr.php", $writer->writeClass( |
| 137 | $pairs, |
| 138 | [ |
| 139 | 'header' => 'Generated by generateNormalizerDataAr.php. Do not modify!', |
| 140 | 'namespace' => 'MediaWiki\\Languages\\Data', |
| 141 | 'class' => 'NormalizeAr', |
| 142 | 'const' => 'PAIRS', |
| 143 | ] |
| 144 | ) ); |
| 145 | |
| 146 | echo "ar: " . count( $pairs ) . " pairs written.\n"; |
| 147 | } |
| 148 | } |
| 149 | |
| 150 | // @codeCoverageIgnoreStart |
| 151 | $maintClass = GenerateNormalizerDataAr::class; |
| 152 | require_once RUN_MAINTENANCE_IF_MAIN; |
| 153 | // @codeCoverageIgnoreEnd |