includes/normal/UtfNormalUtil.php

   1 <?php
   2 # Copyright (C) 2004 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 # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 # Some of these functions are adapted from places in MediaWiki.
  21 # Should probably merge them for consistency.
  22
  23 function codepointToUtf8( $codepoint ) {
  24         if($codepoint <         0x80) return chr($codepoint);
  25         if($codepoint <    0x800) return chr($codepoint >>      6 & 0x3f | 0xc0) .
  26                                                                          chr($codepoint           & 0x3f | 0x80);
  27         if($codepoint <  0x10000) return chr($codepoint >> 12 & 0x0f | 0xe0) .
  28                                                                          chr($codepoint >>      6 & 0x3f | 0x80) .
  29                                                                          chr($codepoint           & 0x3f | 0x80);
  30         if($codepoint < 0x110000) return chr($codepoint >> 18 & 0x07 | 0xf0) .
  31                                                                          chr($codepoint >> 12 & 0x3f | 0x80) .
  32                                                                          chr($codepoint >>      6 & 0x3f | 0x80) .
  33                                                                          chr($codepoint           & 0x3f | 0x80);
  34
  35         die("Asked for code outside of range ($codepoint)\n");
  36 }
  37
  38 function hexSequenceToUtf8( $sequence ) {
  39         $utf = '';
  40         foreach( explode( ' ', $sequence ) as $hex ) {
  41                 $n = hexdec( $hex );
  42                 $utf .= codepointToUtf8( $n );
  43         }
  44         return $utf;
  45 }
  46
  47 function utf8ToCodepoint( $char ) {
  48         # Find the length
  49         $z = ord( $char{0} );
  50         if ( $z & 0x80 ) {
  51                 $length = 0;
  52                 while ( $z & 0x80 ) {
  53                         $length++;
  54                         $z <<= 1;
  55                 }
  56         } else {
  57                 $length = 1;
  58         }
  59
  60         if ( $length != strlen( $char ) ) {
  61                 return false;
  62         }
  63         if ( $length == 1 ) {
  64                 return ord( $char );
  65         }
  66
  67         # Mask off the length-determining bits and shift back to the original location
  68         $z &= 0xff;
  69         $z >>= $length;
  70
  71         # Add in the free bits from subsequent bytes
  72         for ( $i=1; $i<$length; $i++ ) {
  73                 $z <<= 6;
  74                 $z |= ord( $char{$i} ) & 0x3f;
  75         }
  76
  77         # Make entity
  78         return $z;
  79 }
  80
  81 function escapeSingleString( $string ) {
  82         return strtr( $string,
  83                 array(
  84                         '\\' => '\\\\',
  85                         '\'' => '\\\''
  86                 ));
  87 }
  88
  89 ?>