maintenance/language/generateUtf8Case.php

   1 <?php
   2 /**
   3  * Generates Utf8Case.ser from the Unicode Character Database and
   4  * supplementary files.
   5  *
   6  * Copyright © 2004, 2008 Brion Vibber <brion@pobox.com>
   7  * https://www.mediawiki.org/
   8  *
   9  * This program is free software; you can redistribute it and/or modify
  10  * it under the terms of the GNU General Public License as published by
  11  * the Free Software Foundation; either version 2 of the License, or
  12  * (at your option) any later version.
  13  *
  14  * This program is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  17  * GNU General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU General Public License along
  20  * with this program; if not, write to the Free Software Foundation, Inc.,
  21  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  22  * http://www.gnu.org/copyleft/gpl.html
  23  *
  24  * @file
  25  * @ingroup MaintenanceLanguage
  26  */
  27
  28 require_once __DIR__ . '/../Maintenance.php';
  29
  30 /**
  31  * Generates Utf8Case.ser from the Unicode Character Database and
  32  * supplementary files.
  33  *
  34  * @ingroup MaintenanceLanguage
  35  */
  36 class GenerateUtf8Case extends Maintenance {
  37
  38         public function __construct() {
  39                 parent::__construct();
  40                 $this->mDescription = 'Generate Utf8Case.ser from the Unicode Character Database ' .
  41                         'and supplementary files';
  42                 $this->addOption( 'unicode-data-file', 'The local location of the data file ' .
  43                         'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true );
  44         }
  45
  46         public function getDbType() {
  47                 return Maintenance::DB_NONE;
  48         }
  49
  50         public function execute() {
  51                 if ( !$this->hasOption( 'unicode-data-file' ) ) {
  52                         $dataFile = 'UnicodeData.txt';
  53                         if ( !file_exists( $dataFile ) ) {
  54                                 $this->error( "Unable to find UnicodeData.txt. Please specify " .
  55                                         "its location with --unicode-data-file=<FILE>" );
  56                                 exit( 1 );
  57                         }
  58                 } else {
  59                         $dataFile = $this->getOption( 'unicode-data-file' );
  60                         if ( !file_exists( $dataFile ) ) {
  61                                 $this->error( 'Unable to find the specified data file.' );
  62                                 exit( 1 );
  63                         }
  64                 }
  65
  66                 $file = fopen( $dataFile, 'r' );
  67                 if ( !$file ) {
  68                         $this->error( 'Unable to open the data file.' );
  69                         exit( 1 );
  70                 }
  71
  72                 // For the file format, see http://www.unicode.org/reports/tr44/
  73                 $fieldNames = array(
  74                         'Code',
  75                         'Name',
  76                         'General_Category',
  77                         'Canonical_Combining_Class',
  78                         'Bidi_Class',
  79                         'Decomposition_Type_Mapping',
  80                         'Numeric_Type_Value_6',
  81                         'Numeric_Type_Value_7',
  82                         'Numeric_Type_Value_8',
  83                         'Bidi_Mirrored',
  84                         'Unicode_1_Name',
  85                         'ISO_Comment',
  86                         'Simple_Uppercase_Mapping',
  87                         'Simple_Lowercase_Mapping',
  88                         'Simple_Titlecase_Mapping'
  89                 );
  90
  91                 $upper = array();
  92                 $lower = array();
  93
  94                 $lineNum = 0;
  95                 while ( false !== ( $line = fgets( $file ) ) ) {
  96                         ++$lineNum;
  97
  98                         # Strip comments
  99                         $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) );
 100                         if ( $line === '' ) {
 101                                 continue;
 102                         }
 103
 104                         # Split fields
 105                         $numberedData = explode( ';', $line );
 106                         $data = array();
 107                         foreach ( $fieldNames as $number => $name ) {
 108                                 $data[$name] = $numberedData[$number];
 109                         }
 110
 111                         $source = hexSequenceToUtf8( $data['Code'] );
 112                         if ( $data['Simple_Uppercase_Mapping'] ) {
 113                                 $upper[$source] = hexSequenceToUtf8( $data['Simple_Uppercase_Mapping'] );
 114                         }
 115                         if ( $data['Simple_Lowercase_Mapping'] ) {
 116                                 $lower[$source] = hexSequenceToUtf8( $data['Simple_Lowercase_Mapping'] );
 117                         }
 118                 }
 119
 120                 global $IP;
 121                 file_put_contents( "$IP/serialized/Utf8Case.ser", serialize( array(
 122                         'wikiUpperChars' => $upper,
 123                         'wikiLowerChars' => $lower,
 124                 ) ) );
 125         }
 126 }
 127
 128 $maintClass = 'GenerateUtf8Case';
 129 require_once RUN_MAINTENANCE_IF_MAIN;