includes/normal/Utf8CaseGenerate.php

   1 <?php
   2 # Copyright (C) 2004,2008 Brion Vibber <brion@pobox.com>
   3 # http://www.mediawiki.org/
   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 /**
  21  * This script generates Utf8Case.inc from the Unicode Character Database
  22  * and supplementary files.
  23  *
  24  * @ingroup UtfNormal
  25  * @access private
  26  */
  27
  28 /** */
  29
  30 if( php_sapi_name() != 'cli' ) {
  31         die( "Run me from the command line please.\n" );
  32 }
  33
  34 require_once 'UtfNormalUtil.php';
  35
  36 $in = fopen("UnicodeData.txt", "rt" );
  37 if( !$in ) {
  38         print "Can't open UnicodeData.txt for reading.\n";
  39         print "If necessary, fetch this file from the internet:\n";
  40         print "http://www.unicode.org/Public/UNIDATA/UnicodeData.txt\n";
  41         exit(-1);
  42 }
  43 $wikiUpperChars = array();
  44 $wikiLowerChars = array();
  45
  46 print "Reading character definitions...\n";
  47 while( false !== ($line = fgets( $in ) ) ) {
  48         $columns = split(';', $line);
  49         $codepoint = $columns[0];
  50         $name = $columns[1];
  51         $simpleUpper = $columns[12];
  52         $simpleLower = $columns[13];
  53
  54         $source = codepointToUtf8( hexdec( $codepoint ) );
  55         if( $simpleUpper ) {
  56                 $wikiUpperChars[$source] = codepointToUtf8( hexdec( $simpleUpper ) );
  57         }
  58         if( $simpleLower ) {
  59                 $wikiLowerChars[$source] = codepointToUtf8( hexdec( $simpleLower ) );
  60         }
  61 }
  62 fclose( $in );
  63
  64 $out = fopen("Utf8Case.php", "wt");
  65 if( $out ) {
  66         $outUpperChars = escapeArray( $wikiUpperChars );
  67         $outLowerChars = escapeArray( $wikiLowerChars );
  68         $outdata = "<" . "?php
  69 /**
  70  * Simple 1:1 upper/lowercase switching arrays for utf-8 text
  71  * Won't get context-sensitive things yet
  72  *
  73  * Hack for bugs in ucfirst() and company
  74  *
  75  * These are pulled from memcached if possible, as this is faster than filling
  76  * up a big array manually.
  77  * @ingroup Language
  78  */
  79
  80 /*
  81  * Translation array to get upper case character
  82  */
  83
  84 \$wikiUpperChars = $outUpperChars;
  85
  86 /*
  87  * Translation array to get lower case character
  88  */
  89 \$wikiLowerChars = $outLowerChars;\n";
  90         fputs( $out, $outdata );
  91         fclose( $out );
  92         print "Wrote out Utf8Case.php\n";
  93 } else {
  94         print "Can't create file Utf8Case.php\n";
  95         exit(-1);
  96 }
  97
  98
  99 function escapeArray( $arr ) {
 100         return "array(\n" .
 101                 implode( ",\n",
 102                         array_map( "escapeLine",
 103                                 array_keys( $arr ),
 104                                 array_values( $arr ) ) ) .
 105                 "\n)";
 106 }
 107
 108 function escapeLine( $key, $val ) {
 109         $encKey = escapeSingleString( $key );
 110         $encVal = escapeSingleString( $val );
 111         return "\t'$encKey' => '$encVal'";
 112 }