maintenance/language/generateNormalizerDataMl.php

   1 <?php
   2 /**
   3  * Generates the normalizer data file for Malayalam.
   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 use Wikimedia\StaticArrayWriter;
  27
  28 /**
  29  * Generates the normalizer data file for Malayalam.
  30  *
  31  * This data file is used after normalizing to NFC.
  32  *
  33  * @ingroup MaintenanceLanguage
  34  */
  35 class GenerateNormalizerDataMl extends Maintenance {
  36         public function __construct() {
  37                 parent::__construct();
  38                 $this->addDescription( 'Generate the normalizer data file for Malayalam' );
  39         }
  40
  41         public function getDbType() {
  42                 return Maintenance::DB_NONE;
  43         }
  44
  45         public function execute() {
  46                 $hexPairs = [
  47                         # From https://www.unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters
  48                         '0D23 0D4D 200D' => '0D7A',
  49                         '0D28 0D4D 200D' => '0D7B',
  50                         '0D30 0D4D 200D' => '0D7C',
  51                         '0D32 0D4D 200D' => '0D7D',
  52                         '0D33 0D4D 200D' => '0D7E',
  53
  54                         # From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413
  55                         '0D15 0D4D 200D' => '0D7F',
  56                 ];
  57
  58                 $pairs = [];
  59                 foreach ( $hexPairs as $hexSource => $hexDest ) {
  60                         $source = UtfNormal\Utils::hexSequenceToUtf8( $hexSource );
  61                         $dest = UtfNormal\Utils::hexSequenceToUtf8( $hexDest );
  62                         $pairs[$source] = $dest;
  63                 }
  64
  65                 global $IP;
  66                 $writer = new StaticArrayWriter();
  67                 file_put_contents( "$IP/languages/data/normalize-ml.php", $writer->create(
  68                         $pairs,
  69                         'File created by generateNormalizerDataMl.php'
  70                 ) );
  71
  72                 echo "ml: " . count( $pairs ) . " pairs written.\n";
  73         }
  74 }
  75
  76 $maintClass = GenerateNormalizerDataMl::class;
  77 require_once RUN_MAINTENANCE_IF_MAIN;