Merge "Whitelist the <wbr> element."
[mediawiki.git] / includes / normal / UtfNormalUtil.php
blobe8fec93665a9a229cfce47af3c51ae113b1f7053
1 <?php
2 /**
3 * Some of these functions are adapted from places in MediaWiki.
4 * Should probably merge them for consistency.
6 * Copyright © 2004 Brion Vibber <brion@pobox.com>
7 * http://www.mediawiki.org/
9 * This program is free software; you can redistribute it and/or modify
10 * it under the terms of the GNU General Public License as published by
11 * the Free Software Foundation; either version 2 of the License, or
12 * (at your option) any later version.
14 * This program is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 * GNU General Public License for more details.
19 * You should have received a copy of the GNU General Public License along
20 * with this program; if not, write to the Free Software Foundation, Inc.,
21 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
22 * http://www.gnu.org/copyleft/gpl.html
24 * @file
25 * @ingroup UtfNormal
28 /**
29 * Return UTF-8 sequence for a given Unicode code point.
30 * May die if fed out of range data.
32 * @param $codepoint Integer:
33 * @return String
34 * @public
36 function codepointToUtf8( $codepoint ) {
37 if($codepoint < 0x80) return chr($codepoint);
38 if($codepoint < 0x800) return chr($codepoint >> 6 & 0x3f | 0xc0) .
39 chr($codepoint & 0x3f | 0x80);
40 if($codepoint < 0x10000) return chr($codepoint >> 12 & 0x0f | 0xe0) .
41 chr($codepoint >> 6 & 0x3f | 0x80) .
42 chr($codepoint & 0x3f | 0x80);
43 if($codepoint < 0x110000) return chr($codepoint >> 18 & 0x07 | 0xf0) .
44 chr($codepoint >> 12 & 0x3f | 0x80) .
45 chr($codepoint >> 6 & 0x3f | 0x80) .
46 chr($codepoint & 0x3f | 0x80);
48 echo "Asked for code outside of range ($codepoint)\n";
49 die( -1 );
52 /**
53 * Take a series of space-separated hexadecimal numbers representing
54 * Unicode code points and return a UTF-8 string composed of those
55 * characters. Used by UTF-8 data generation and testing routines.
57 * @param $sequence String
58 * @return String
59 * @private
61 function hexSequenceToUtf8( $sequence ) {
62 $utf = '';
63 foreach( explode( ' ', $sequence ) as $hex ) {
64 $n = hexdec( $hex );
65 $utf .= codepointToUtf8( $n );
67 return $utf;
70 /**
71 * Take a UTF-8 string and return a space-separated series of hex
72 * numbers representing Unicode code points. For debugging.
74 * @param string $str UTF-8 string.
75 * @return string
76 * @private
78 function utf8ToHexSequence( $str ) {
79 $buf = '';
80 foreach ( preg_split( '//u', $str, -1, PREG_SPLIT_NO_EMPTY ) as $cp ) {
81 $buf .= sprintf( '%04x ', utf8ToCodepoint( $cp ) );
83 return rtrim( $buf );
86 /**
87 * Determine the Unicode codepoint of a single-character UTF-8 sequence.
88 * Does not check for invalid input data.
90 * @param $char String
91 * @return Integer
92 * @public
94 function utf8ToCodepoint( $char ) {
95 # Find the length
96 $z = ord( $char[0] );
97 if ( $z & 0x80 ) {
98 $length = 0;
99 while ( $z & 0x80 ) {
100 $length++;
101 $z <<= 1;
103 } else {
104 $length = 1;
107 if ( $length != strlen( $char ) ) {
108 return false;
110 if ( $length == 1 ) {
111 return ord( $char );
114 # Mask off the length-determining bits and shift back to the original location
115 $z &= 0xff;
116 $z >>= $length;
118 # Add in the free bits from subsequent bytes
119 for ( $i=1; $i < $length; $i++ ) {
120 $z <<= 6;
121 $z |= ord( $char[$i] ) & 0x3f;
124 return $z;
128 * Escape a string for inclusion in a PHP single-quoted string literal.
130 * @param string $string string to be escaped.
131 * @return String: escaped string.
132 * @public
134 function escapeSingleString( $string ) {
135 return strtr( $string,
136 array(
137 '\\' => '\\\\',
138 '\'' => '\\\''