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 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, 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.
29 require_once dirname(__FILE__
).'/UtfNormalDefines.php';
32 * Return UTF-8 sequence for a given Unicode code point.
33 * May die if fed out of range data.
35 * @param $codepoint Integer:
39 function codepointToUtf8( $codepoint ) {
40 if($codepoint < 0x80) return chr($codepoint);
41 if($codepoint < 0x800) return chr($codepoint >> 6 & 0x3f |
0xc0) .
42 chr($codepoint & 0x3f |
0x80);
43 if($codepoint < 0x10000) return chr($codepoint >> 12 & 0x0f |
0xe0) .
44 chr($codepoint >> 6 & 0x3f |
0x80) .
45 chr($codepoint & 0x3f |
0x80);
46 if($codepoint < 0x110000) return chr($codepoint >> 18 & 0x07 |
0xf0) .
47 chr($codepoint >> 12 & 0x3f |
0x80) .
48 chr($codepoint >> 6 & 0x3f |
0x80) .
49 chr($codepoint & 0x3f |
0x80);
51 echo "Asked for code outside of range ($codepoint)\n";
56 * Take a series of space-separated hexadecimal numbers representing
57 * Unicode code points and return a UTF-8 string composed of those
58 * characters. Used by UTF-8 data generation and testing routines.
60 * @param $sequence String
64 function hexSequenceToUtf8( $sequence ) {
66 foreach( explode( ' ', $sequence ) as $hex ) {
68 $utf .= codepointToUtf8( $n );
74 * Take a UTF-8 string and return a space-separated series of hex
75 * numbers representing Unicode code points. For debugging.
77 * @param $str String: UTF-8 string.
81 function utf8ToHexSequence( $str ) {
82 return rtrim( preg_replace( '/(.)/uSe',
83 'sprintf("%04x ", utf8ToCodepoint("$1"))',
88 * Determine the Unicode codepoint of a single-character UTF-8 sequence.
89 * Does not check for invalid input data.
95 function utf8ToCodepoint( $char ) {
100 while ( $z & 0x80 ) {
108 if ( $length != strlen( $char ) ) {
111 if ( $length == 1 ) {
115 # Mask off the length-determining bits and shift back to the original location
119 # Add in the free bits from subsequent bytes
120 for ( $i=1; $i<$length; $i++
) {
122 $z |
= ord( $char{$i} ) & 0x3f;
129 * Escape a string for inclusion in a PHP single-quoted string literal.
131 * @param $string String: string to be escaped.
132 * @return String: escaped string.
135 function escapeSingleString( $string ) {
136 return strtr( $string,