2# Copyright (C) 2004 Brion Vibber <brion@pobox.com>
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.
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");
64 foreach( explode(
' ', $sequence ) as $hex ) {
80 return rtrim(preg_replace_callback(
101 while ( $z & 0x80 ) {
109 if ( $length != strlen( $char ) ) {
112 if ( $length == 1 ) {
116 # Mask off the length-determining bits and shift back to the original location
120 # Add in the free bits from subsequent bytes
121 for ( $i=1; $i<$length; $i++ ) {
123 $z |= ord( $char{$i} ) & 0x3f;
137 return strtr( $string,
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.