2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com>
3 # http://www.mediawiki.org/
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.
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.
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
21 * Some of these functions are adapted from places in MediaWiki.
22 * Should probably merge them for consistency.
28 function codepointToUtf8( $codepoint ) {
29 if($codepoint < 0x80) return chr($codepoint);
30 if($codepoint < 0x800) return chr($codepoint >> 6 & 0x3f |
0xc0) .
31 chr($codepoint & 0x3f |
0x80);
32 if($codepoint < 0x10000) return chr($codepoint >> 12 & 0x0f |
0xe0) .
33 chr($codepoint >> 6 & 0x3f |
0x80) .
34 chr($codepoint & 0x3f |
0x80);
35 if($codepoint < 0x110000) return chr($codepoint >> 18 & 0x07 |
0xf0) .
36 chr($codepoint >> 12 & 0x3f |
0x80) .
37 chr($codepoint >> 6 & 0x3f |
0x80) .
38 chr($codepoint & 0x3f |
0x80);
40 die("Asked for code outside of range ($codepoint)\n");
43 function hexSequenceToUtf8( $sequence ) {
45 foreach( explode( ' ', $sequence ) as $hex ) {
47 $utf .= codepointToUtf8( $n );
52 function utf8ToCodepoint( $char ) {
65 if ( $length != strlen( $char ) ) {
72 # Mask off the length-determining bits and shift back to the original location
76 # Add in the free bits from subsequent bytes
77 for ( $i=1; $i<$length; $i++
) {
79 $z |
= ord( $char{$i} ) & 0x3f;
86 function escapeSingleString( $string ) {
87 return strtr( $string,