From 66e64d98d237499b39c358ebabeb46ceb408166b Mon Sep 17 00:00:00 2001 From: Brion Vibber Date: Sun, 14 Nov 2004 21:40:44 +0000 Subject: [PATCH] Test: feeds random strings to both pure PHP and ICU code paths looking for differences. --- includes/normal/RandomTest.php | 106 +++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 includes/normal/RandomTest.php diff --git a/includes/normal/RandomTest.php b/includes/normal/RandomTest.php new file mode 100644 index 0000000000..562ead7b3d --- /dev/null +++ b/includes/normal/RandomTest.php @@ -0,0 +1,106 @@ + +# http://www.mediawiki.org/ +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program; if not, write to the Free Software Foundation, Inc., +# 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +# http://www.gnu.org/copyleft/gpl.html + +/** + * Test feeds random 16-byte strings to both the pure PHP and ICU-based + * UtfNormal::cleanUp() code paths, and checks to see if there's a + * difference. Will run forever until it finds one or you kill it. + * + * @package UtfNormal + * @access private + */ + +if( php_sapi_name() != 'cli' ) { + die( "Run me from the command line please.\n" ); +} + +require_once( 'UtfNormal.php' ); +require_once( '../DifferenceEngine.php' ); + +dl('php_utfnormal.so' ); + +# mt_srand( 99999 ); + +function randomString( $length, $nullOk, $ascii = false ) { + $out = ''; + for( $i = 0; $i < $length; $i++ ) + $out .= chr( mt_rand( $nullOk ? 0 : 1, $ascii ? 127 : 255 ) ); + return $out; +} + +/* Duplicate of the cleanUp() path for ICU usage */ +function donorm( $str ) { + # We exclude a few chars that ICU would not. + $str = preg_replace( '/[\x00-\x08\x0b\x0c\x0e-\x1f]/', UTF8_REPLACEMENT, $str ); + $str = str_replace( UTF8_FFFE, UTF8_REPLACEMENT, $str ); + $str = str_replace( UTF8_FFFF, UTF8_REPLACEMENT, $str ); + + # UnicodeString constructor fails if the string ends with a head byte. + # Add a junk char at the end, we'll strip it off + return rtrim( utf8_normalize( $str . "\x01", UNORM_NFC ), "\x01" ); +} + +function wfMsg($x) { + return $x; +} + +function showDiffs( $a, $b ) { + $ota = explode( "\n", str_replace( "\r\n", "\n", $a ) ); + $nta = explode( "\n", str_replace( "\r\n", "\n", $b ) ); + + $diffs =& new Diff( $ota, $nta ); + $formatter =& new TableDiffFormatter(); + $funky = $formatter->format( $diffs ); + preg_match_all( '/(.*?)<\/span>/', $funky, $matches ); + foreach( $matches[1] as $bit ) { + $hex = bin2hex( $bit ); + echo "\t$hex\n"; + } +} + +$size = 16; +$n = 0; +while( true ) { + $n++; + echo "$n\n"; + + $str = randomString( $size, true); + $clean = UtfNormal::cleanUp( $str ); + $norm = donorm( $str ); + + echo strlen( $clean ) . ", " . strlen( $norm ); + if( $clean == $norm ) { + echo " (match)\n"; + } else { + echo " (FAIL)\n"; + echo "\traw: " . bin2hex( $str ) . "\n" . + "\tphp: " . bin2hex( $clean ) . "\n" . + "\ticu: " . bin2hex( $norm ) . "\n"; + echo "\n\tdiffs:\n"; + showDiffs( $clean, $norm ); + die(); + } + + + $str = ''; + $clean = ''; + $norm = ''; +} + +?> \ No newline at end of file -- 2.20.1