maintenance/language/generateNormalizerDataAr.php

   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 require_once __DIR__ . '/../Maintenance.php';
  25
  26 /**
  27  * Generates the normalizer data file for Arabic.
  28  *
  29  * This data file is used after normalizing to NFC.
  30  *
  31  * @ingroup MaintenanceLanguage
  32  */
  33 class GenerateNormalizerDataAr extends Maintenance {
  34         public function __construct() {
  35                 parent::__construct();
  36                 $this->addDescription( 'Generate the normalizer data file for Arabic' );
  37                 $this->addOption( 'unicode-data-file', 'The local location of the data file ' .
  38                         'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true );
  39         }
  40
  41         public function getDbType() {
  42                 return Maintenance::DB_NONE;
  43         }
  44
  45         public function execute() {
  46                 if ( !$this->hasOption( 'unicode-data-file' ) ) {
  47                         $dataFile = 'UnicodeData.txt';
  48                         if ( !file_exists( $dataFile ) ) {
  49                                 $this->error( "Unable to find UnicodeData.txt. Please specify " .
  50                                         "its location with --unicode-data-file=<FILE>" );
  51                                 exit( 1 );
  52                         }
  53                 } else {
  54                         $dataFile = $this->getOption( 'unicode-data-file' );
  55                         if ( !file_exists( $dataFile ) ) {
  56                                 $this->error( 'Unable to find the specified data file.' );
  57                                 exit( 1 );
  58                         }
  59                 }
  60
  61                 $file = fopen( $dataFile, 'r' );
  62                 if ( !$file ) {
  63                         $this->error( 'Unable to open the data file.' );
  64                         exit( 1 );
  65                 }
  66
  67                 // For the file format, see http://www.unicode.org/reports/tr44/
  68                 $fieldNames = [
  69                         'Code',
  70                         'Name',
  71                         'General_Category',
  72                         'Canonical_Combining_Class',
  73                         'Bidi_Class',
  74                         'Decomposition_Type_Mapping',
  75                         'Numeric_Type_Value_6',
  76                         'Numeric_Type_Value_7',
  77                         'Numeric_Type_Value_8',
  78                         'Bidi_Mirrored',
  79                         'Unicode_1_Name',
  80                         'ISO_Comment',
  81                         'Simple_Uppercase_Mapping',
  82                         'Simple_Lowercase_Mapping',
  83                         'Simple_Titlecase_Mapping'
  84                 ];
  85
  86                 $pairs = [];
  87
  88                 $lineNum = 0;
  89                 while ( false !== ( $line = fgets( $file ) ) ) {
  90                         ++$lineNum;
  91
  92                         # Strip comments
  93                         $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) );
  94                         if ( $line === '' ) {
  95                                 continue;
  96                         }
  97
  98                         # Split fields
  99                         $numberedData = explode( ';', $line );
 100                         $data = [];
 101                         foreach ( $fieldNames as $number => $name ) {
 102                                 $data[$name] = $numberedData[$number];
 103                         }
 104
 105                         $code = base_convert( $data['Code'], 16, 10 );
 106                         if ( ( $code >= 0xFB50 && $code <= 0xFDFF ) # Arabic presentation forms A
 107                                 || ( $code >= 0xFE70 && $code <= 0xFEFF ) # Arabic presentation forms B
 108                         ) {
 109                                 if ( $data['Decomposition_Type_Mapping'] === '' ) {
 110                                         // No decomposition
 111                                         continue;
 112                                 }
 113                                 if ( !preg_match( '/^ *(<\w*>) +([0-9A-F ]*)$/',
 114                                         $data['Decomposition_Type_Mapping'], $m )
 115                                 ) {
 116                                         $this->error( "Can't parse Decomposition_Type/Mapping on line $lineNum" );
 117                                         $this->error( $line );
 118                                         continue;
 119                                 }
 120
 121                                 $source = UtfNormal\Utils::hexSequenceToUtf8( $data['Code'] );
 122                                 $dest = UtfNormal\Utils::hexSequenceToUtf8( $m[2] );
 123                                 $pairs[$source] = $dest;
 124                         }
 125                 }
 126
 127                 global $IP;
 128                 file_put_contents( "$IP/serialized/normalize-ar.ser", serialize( $pairs ) );
 129                 echo "ar: " . count( $pairs ) . " pairs written.\n";
 130         }
 131 }
 132
 133 $maintClass = 'GenerateNormalizerDataAr';
 134 require_once RUN_MAINTENANCE_IF_MAIN;