includes/normal/RandomTest.php

   1 <?php
   2 /**
   3  * Test feeds random 16-byte strings to both the pure PHP and ICU-based
   4  * UtfNormal::cleanUp() code paths, and checks to see if there's a
   5  * difference. Will run forever until it finds one or you kill it.
   6  *
   7  * Copyright (C) 2004 Brion Vibber <brion@pobox.com>
   8  * http://www.mediawiki.org/
   9  *
  10  * This program is free software; you can redistribute it and/or modify
  11  * it under the terms of the GNU General Public License as published by
  12  * the Free Software Foundation; either version 2 of the License, or
  13  * (at your option) any later version.
  14  *
  15  * This program is distributed in the hope that it will be useful,
  16  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  17  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  18  * GNU General Public License for more details.
  19  *
  20  * You should have received a copy of the GNU General Public License along
  21  * with this program; if not, write to the Free Software Foundation, Inc.,
  22  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  23  * http://www.gnu.org/copyleft/gpl.html
  24  *
  25  * @file
  26  * @ingroup UtfNormal
  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( '../diff/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", UtfNormal::UNORM_NFC ), "\x01" );
  58 }
  59
  60 function showDiffs( $a, $b ) {
  61         $ota = explode( "\n", str_replace( "\r\n", "\n", $a ) );
  62         $nta = explode( "\n", str_replace( "\r\n", "\n", $b ) );
  63
  64         $diffs = new Diff( $ota, $nta );
  65         $formatter = new TableDiffFormatter();
  66         $funky = $formatter->format( $diffs );
  67         $matches = array();
  68         preg_match_all( '/<(?:ins|del) class="diffchange">(.*?)<\/(?:ins|del)>/', $funky, $matches );
  69         foreach( $matches[1] as $bit ) {
  70                 $hex = bin2hex( $bit );
  71                 echo "\t$hex\n";
  72         }
  73 }
  74
  75 $size = 16;
  76 $n = 0;
  77 while( true ) {
  78         $n++;
  79         echo "$n\n";
  80
  81         $str = randomString( $size, true);
  82         $clean = UtfNormal::cleanUp( $str );
  83         $norm = donorm( $str );
  84
  85         echo strlen( $clean ) . ", " . strlen( $norm );
  86         if( $clean == $norm ) {
  87                 echo " (match)\n";
  88         } else {
  89                 echo " (FAIL)\n";
  90                 echo "\traw: " . bin2hex( $str ) . "\n" .
  91                          "\tphp: " . bin2hex( $clean ) . "\n" .
  92                          "\ticu: " . bin2hex( $norm ) . "\n";
  93                 echo "\n\tdiffs:\n";
  94                 showDiffs( $clean, $norm );
  95                 die();
  96         }
  97
  98
  99         $str = '';
 100         $clean = '';
 101         $norm = '';
 102 }