includes/normal/RandomTest.php

   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 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  * Test feeds random 16-byte strings to both the pure PHP and ICU-based
  22  * UtfNormal::cleanUp() code paths, and checks to see if there's a
  23  * difference. Will run forever until it finds one or you kill it.
  24  *
  25  * @addtogroup UtfNormal
  26  * @access private
  27  */
  28
  29 if( php_sapi_name() != 'cli' ) {
  30         die( "Run me from the command line please.\n" );
  31 }
  32
  33 /** */
  34 require_once( 'UtfNormal.php' );
  35 require_once( '../DifferenceEngine.php' );
  36
  37 dl('php_utfnormal.so' );
  38
  39 # mt_srand( 99999 );
  40
  41 function randomString( $length, $nullOk, $ascii = false ) {
  42         $out = '';
  43         for( $i = 0; $i < $length; $i++ )
  44                 $out .= chr( mt_rand( $nullOk ? 0 : 1, $ascii ? 127 : 255 ) );
  45         return $out;
  46 }
  47
  48 /* Duplicate of the cleanUp() path for ICU usage */
  49 function donorm( $str ) {
  50         # We exclude a few chars that ICU would not.
  51         $str = preg_replace( '/[\x00-\x08\x0b\x0c\x0e-\x1f]/', UTF8_REPLACEMENT, $str );
  52         $str = str_replace( UTF8_FFFE, UTF8_REPLACEMENT, $str );
  53         $str = str_replace( UTF8_FFFF, UTF8_REPLACEMENT, $str );
  54
  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( $str . "\x01", UNORM_NFC ), "\x01" );
  58 }
  59
  60 function wfMsg($x) {
  61         return $x;
  62 }
  63
  64 function showDiffs( $a, $b ) {
  65         $ota = explode( "\n", str_replace( "\r\n", "\n", $a ) );
  66         $nta = explode( "\n", str_replace( "\r\n", "\n", $b ) );
  67
  68         $diffs = new Diff( $ota, $nta );
  69         $formatter = new TableDiffFormatter();
  70         $funky = $formatter->format( $diffs );
  71         $matches = array();
  72         preg_match_all( '/<span class="diffchange">(.*?)<\/span>/', $funky, $matches );
  73         foreach( $matches[1] as $bit ) {
  74                 $hex = bin2hex( $bit );
  75                 echo "\t$hex\n";
  76         }
  77 }
  78
  79 $size = 16;
  80 $n = 0;
  81 while( true ) {
  82         $n++;
  83         echo "$n\n";
  84
  85         $str = randomString( $size, true);
  86         $clean = UtfNormal::cleanUp( $str );
  87         $norm = donorm( $str );
  88
  89         echo strlen( $clean ) . ", " . strlen( $norm );
  90         if( $clean == $norm ) {
  91                 echo " (match)\n";
  92         } else {
  93                 echo " (FAIL)\n";
  94                 echo "\traw: " . bin2hex( $str ) . "\n" .
  95                          "\tphp: " . bin2hex( $clean ) . "\n" .
  96                          "\ticu: " . bin2hex( $norm ) . "\n";
  97                 echo "\n\tdiffs:\n";
  98                 showDiffs( $clean, $norm );
  99                 die();
 100         }
 101
 102
 103         $str = '';
 104         $clean = '';
 105         $norm = '';
 106 }
 107
 108 ?>