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