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.
31 * Return UTF-8 sequence for a given Unicode code point.
32 * May die if fed out of range data.
34 * @param int $codepoint
38 function codepointToUtf8( $codepoint ) {
39 if($codepoint < 0x80) return chr($codepoint);
40 if($codepoint < 0x800) return chr($codepoint >> 6 & 0x3f |
0xc0) .
41 chr($codepoint & 0x3f |
0x80);
42 if($codepoint < 0x10000) return chr($codepoint >> 12 & 0x0f |
0xe0) .
43 chr($codepoint >> 6 & 0x3f |
0x80) .
44 chr($codepoint & 0x3f |
0x80);
45 if($codepoint < 0x110000) return chr($codepoint >> 18 & 0x07 |
0xf0) .
46 chr($codepoint >> 12 & 0x3f |
0x80) .
47 chr($codepoint >> 6 & 0x3f |
0x80) .
48 chr($codepoint & 0x3f |
0x80);
50 die("Asked for code outside of range ($codepoint)\n");
54 * Take a series of space-separated hexadecimal numbers representing
55 * Unicode code points and return a UTF-8 string composed of those
56 * characters. Used by UTF-8 data generation and testing routines.
58 * @param string $sequence
62 function hexSequenceToUtf8( $sequence ) {
64 foreach( explode( ' ', $sequence ) as $hex ) {
66 $utf .= codepointToUtf8( $n );
72 * Take a UTF-8 string and return a space-separated series of hex
73 * numbers representing Unicode code points. For debugging.
79 function utf8ToHexSequence( $str ) {
80 return rtrim( preg_replace( '/(.)/uSe',
81 'sprintf("%04x ", utf8ToCodepoint("$1"))',
86 * Determine the Unicode codepoint of a single-character UTF-8 sequence.
87 * Does not check for invalid input data.
93 function utf8ToCodepoint( $char ) {
106 if ( $length != strlen( $char ) ) {
109 if ( $length == 1 ) {
113 # Mask off the length-determining bits and shift back to the original location
117 # Add in the free bits from subsequent bytes
118 for ( $i=1; $i<$length; $i++
) {
120 $z |
= ord( $char{$i} ) & 0x3f;
127 * Escape a string for inclusion in a PHP single-quoted string literal.
129 * @param string $string
133 function escapeSingleString( $string ) {
134 return strtr( $string,