includes/normal/Utf8Test.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 # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  * Runs the UTF-8 decoder test at:
  22  * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
  23  *
  24  * @package MediaWiki
  25  */
  26
  27 /** */
  28 require_once 'UtfNormalUtil.php';
  29 require_once 'UtfNormal.php';
  30 mb_internal_encoding( "utf-8" );
  31
  32 #$verbose = true;
  33 if( php_sapi_name() != 'cli' ) {
  34         die( "Run me from the command line please.\n" );
  35 }
  36
  37 $in = fopen( "UTF-8-test.txt", "rt" );
  38 if( !$in ) {
  39         print "Couldn't open UTF-8-test.txt -- can't run tests.\n";
  40         print "If necessary, manually download this file. It can be obtained at\n";
  41         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt";
  42         exit(-1);
  43 }
  44
  45 $columns = 0;
  46 while( false !== ( $line = fgets( $in ) ) ) {
  47         if( preg_match( '/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
  48                 $columns = strpos( $line, '|' );
  49                 break;
  50         }
  51 }
  52
  53 if( !$columns ) {
  54         print "Something seems to be wrong; couldn't extract line length.\n";
  55         print "Check that UTF-8-test.txt was downloaded correctly from\n";
  56         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt";
  57         exit(-1);
  58 }
  59
  60 # print "$columns\n";
  61
  62 $ignore = array(
  63         # These two lines actually seem to be corrupt
  64         '2.1.1', '2.2.1' );
  65
  66 $exceptions = array(
  67         # Tests that should mark invalid characters due to using long
  68         # sequences beyond what is now considered legal.
  69         '2.1.5', '2.1.6', '2.2.4', '2.2.5', '2.2.6', '2.3.5',
  70
  71         # Literal 0xffff, which is illegal
  72         '2.2.3' );
  73
  74 $longTests = array(
  75         # These tests span multiple lines
  76         '3.1.9', '3.2.1', '3.2.2', '3.2.3', '3.2.4', '3.2.5',
  77         '3.4' );
  78
  79 # These tests are not in proper subsections
  80 $sectionTests = array( '3.4' );
  81
  82 $section = NULL;
  83 $test = '';
  84 $failed = 0;
  85 $success = 0;
  86 $total = 0;
  87 while( false !== ( $line = fgets( $in ) ) ) {
  88         if( preg_match( '/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
  89                 $section = $matches[1];
  90                 print $line;
  91                 continue;
  92         }
  93         if( preg_match( '/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
  94                 $test = $matches[1];
  95
  96                 if( in_array( $test, $ignore ) ) {
  97                         continue;
  98                 }
  99                 if( in_array( $test, $longTests ) ) {
 100                         $line = fgets( $in );
 101                         for( $line = fgets( $in ); !preg_match( '/^\s+\|/', $line ); $line = fgets( $in ) ) {
 102                                 testLine( $test, $line, $total, $success, $failed );
 103                         }
 104                 } else {
 105                         testLine( $test, $line, $total, $success, $failed );
 106                 }
 107         }
 108 }
 109
 110 if( $failed ) {
 111         echo "\nFailed $failed tests.\n";
 112         echo "UTF-8 DECODER TEST FAILED\n";
 113         exit (-1);
 114 }
 115
 116 echo "UTF-8 DECODER TEST SUCCESS!\n";
 117 exit (0);
 118
 119
 120 function testLine( $test, $line, &$total, &$success, &$failed ) {
 121         $stripped = $line;
 122         UtfNormal::quickisNFCVerify( $stripped );
 123
 124         $same = ( $line == $stripped );
 125         $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 126         if( $len == 0 ) {
 127                 $len = strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 128         }
 129
 130         global $columns;
 131         $ok = $same ^ ($test >= 3 );
 132
 133         global $exceptions;
 134         $ok ^= in_array( $test, $exceptions );
 135
 136         $ok &= ($columns == $len);
 137
 138         $total++;
 139         if( $ok ) {
 140                 $success++;
 141         } else {
 142                 $failed++;
 143         }
 144         global $verbose;
 145         if( $verbose || !$ok ) {
 146                 print str_replace( "\n", "$len\n", $stripped );
 147         }
 148 }
 149
 150 ?>