Fix regression in even sizing of diff columns; forgot to restore a couple bits I...
[mediawiki.git] / includes / normal / UtfNormalUtil.php
blob4ba056937468e27fee06dbe62c2f029d2959a59d
1 <?php
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
20 /**
21 * Some of these functions are adapted from places in MediaWiki.
22 * Should probably merge them for consistency.
24 * @addtogroup UtfNormal
25 * @public
28 /** */
30 /**
31 * Return UTF-8 sequence for a given Unicode code point.
32 * May die if fed out of range data.
34 * @param $codepoint Integer:
35 * @return String
36 * @public
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($codepoint & 0x3f | 0x80);
50 echo "Asked for code outside of range ($codepoint)\n";
51 die( -1 );
54 /**
55 * Take a series of space-separated hexadecimal numbers representing
56 * Unicode code points and return a UTF-8 string composed of those
57 * characters. Used by UTF-8 data generation and testing routines.
59 * @param $sequence String
60 * @return String
61 * @private
63 function hexSequenceToUtf8( $sequence ) {
64 $utf = '';
65 foreach( explode( ' ', $sequence ) as $hex ) {
66 $n = hexdec( $hex );
67 $utf .= codepointToUtf8( $n );
69 return $utf;
72 /**
73 * Take a UTF-8 string and return a space-separated series of hex
74 * numbers representing Unicode code points. For debugging.
76 * @param $str String: UTF-8 string.
77 * @return string
78 * @private
80 function utf8ToHexSequence( $str ) {
81 return rtrim( preg_replace( '/(.)/uSe',
82 'sprintf("%04x ", utf8ToCodepoint("$1"))',
83 $str ) );
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 '\'' => '\\\''