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# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
29if( php_sapi_name() !=
'cli' ) {
30 die(
"Run me from the command line please.\n" );
34require_once(
'UtfNormal.php' );
35require_once(
'../DifferenceEngine.php' );
37dl(
'php_utfnormal.so' );
43 for( $i = 0; $i < $length; $i++ )
44 $out .= chr( mt_rand( $nullOk ? 0 : 1, $ascii ? 127 : 255 ) );
50 # We exclude a few chars that ICU would not.
51 $str = preg_replace(
'/[\x00-\x08\x0b\x0c\x0e-\x1f]/',
UTF8_REPLACEMENT, $str );
55 # UnicodeString constructor fails if the string ends with a head byte.
56 # Add a junk char at the end, we'll strip it off
57 return rtrim( utf8_normalize( $str .
"\x01",
UNORM_NFC ),
"\x01" );
65 $ota = explode(
"\n", str_replace(
"\r\n",
"\n", $a ) );
66 $nta = explode(
"\n", str_replace(
"\r\n",
"\n", $b ) );
68 $diffs =
new Diff( $ota, $nta );
70 $funky = $formatter->format( $diffs );
72 preg_match_all(
'/<(?:ins|del) class="diffchange">(.*?)<\/(?:ins|del)>/', $funky, $matches );
73 foreach( $matches[1] as $bit ) {
74 $hex = bin2hex( $bit );
89 echo strlen( $clean ) .
", " . strlen( $norm );
90 if( $clean == $norm ) {
94 echo
"\traw: " . bin2hex( $str ) .
"\n" .
95 "\tphp: " . bin2hex( $clean ) .
"\n" .
96 "\ticu: " . bin2hex( $norm ) .
"\n";
randomString( $length, $nullOk, $ascii=false)
cleanUp( $string)
The ultimate convenience function! Clean up invalid UTF-8 sequences, and convert to normal form C,...