[Summary view] [Print] [Text view]

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