ILIAS  release_5-1 Revision 5.0.0-5477-g43f3e3fab5f
UtfNormalUtil.php
Go to the documentation of this file.
1<?php
2# Copyright (C) 2004 Brion Vibber <brion@pobox.com>
3# http://www.mediawiki.org/
4#
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.
9#
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.
14#
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
19
38function 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($codepoint & 0x3f | 0x80);
49
50 die("Asked for code outside of range ($codepoint)\n");
51}
52
62function hexSequenceToUtf8( $sequence ) {
63 $utf = '';
64 foreach( explode( ' ', $sequence ) as $hex ) {
65 $n = hexdec( $hex );
66 $utf .= codepointToUtf8( $n );
67 }
68 return $utf;
69}
70
79function utf8ToHexSequence( $str ) {
80 return rtrim(preg_replace_callback(
81 '/(.)/uS',
82 function($hit) {
83 return sprintf("%04x ", utf8ToCodepoint($hit[1]));
84 },
85 $str));
86}
87
96function utf8ToCodepoint( $char ) {
97 # Find the length
98 $z = ord( $char{0} );
99 if ( $z & 0x80 ) {
100 $length = 0;
101 while ( $z & 0x80 ) {
102 $length++;
103 $z <<= 1;
104 }
105 } else {
106 $length = 1;
107 }
108
109 if ( $length != strlen( $char ) ) {
110 return false;
111 }
112 if ( $length == 1 ) {
113 return ord( $char );
114 }
115
116 # Mask off the length-determining bits and shift back to the original location
117 $z &= 0xff;
118 $z >>= $length;
119
120 # Add in the free bits from subsequent bytes
121 for ( $i=1; $i<$length; $i++ ) {
122 $z <<= 6;
123 $z |= ord( $char{$i} ) & 0x3f;
124 }
125
126 return $z;
127}
128
136function escapeSingleString( $string ) {
137 return strtr( $string,
138 array(
139 '\\' => '\\\\',
140 '\'' => '\\\''
141 ));
142}
143
144?>
$n
Definition: RandomTest.php:80
utf8ToCodepoint( $char)
Determine the Unicode codepoint of a single-character UTF-8 sequence.
escapeSingleString( $string)
Escape a string for inclusion in a PHP single-quoted string literal.
hexSequenceToUtf8( $sequence)
Take a series of space-separated hexadecimal numbers representing Unicode code points and return a UT...
utf8ToHexSequence( $str)
Take a UTF-8 string and return a space-separated series of hex numbers representing Unicode code poin...
codepointToUtf8( $codepoint)
Return UTF-8 sequence for a given Unicode code point.