includes/normal/Utf8Test.php

   1 <?php
   2 /**
   3  * Runs the UTF-8 decoder test at:
   4  * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
   5  *
   6  * Copyright © 2004 Brion Vibber <brion@pobox.com>
   7  * http://www.mediawiki.org/
   8  *
   9  * This program is free software; you can redistribute it and/or modify
  10  * it under the terms of the GNU General Public License as published by
  11  * the Free Software Foundation; either version 2 of the License, or
  12  * (at your option) any later version.
  13  *
  14  * This program is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  17  * GNU General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU General Public License along
  20  * with this program; if not, write to the Free Software Foundation, Inc.,
  21  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  22  * http://www.gnu.org/copyleft/gpl.html
  23  *
  24  * @file
  25  * @ingroup UtfNormal
  26  */
  27
  28 /** */
  29
  30 require_once 'UtfNormalDefines.php';
  31 require_once 'UtfNormalUtil.php';
  32 require_once 'UtfNormal.php';
  33 mb_internal_encoding( "utf-8" );
  34
  35 $verbose = false;
  36 #$verbose = true;
  37 if( php_sapi_name() != 'cli' ) {
  38         die( "Run me from the command line please.\n" );
  39 }
  40
  41 $in = fopen( "UTF-8-test.txt", "rt" );
  42 if( !$in ) {
  43         print "Couldn't open UTF-8-test.txt -- can't run tests.\n";
  44         print "If necessary, manually download this file. It can be obtained at\n";
  45         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt\n";
  46         exit(-1);
  47 }
  48
  49 $columns = 0;
  50 while( false !== ( $line = fgets( $in ) ) ) {
  51         $matches = array();
  52         if( preg_match( '/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
  53                 $columns = strpos( $line, '|' );
  54                 break;
  55         }
  56 }
  57
  58 if( !$columns ) {
  59         print "Something seems to be wrong; couldn't extract line length.\n";
  60         print "Check that UTF-8-test.txt was downloaded correctly from\n";
  61         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt\n";
  62         exit(-1);
  63 }
  64
  65 # print "$columns\n";
  66
  67 $ignore = array(
  68         # These two lines actually seem to be corrupt
  69         '2.1.1', '2.2.1' );
  70
  71 $exceptions = array(
  72         # Tests that should mark invalid characters due to using long
  73         # sequences beyond what is now considered legal.
  74         '2.1.5', '2.1.6', '2.2.4', '2.2.5', '2.2.6', '2.3.5',
  75
  76         # Literal 0xffff, which is illegal
  77         '2.2.3' );
  78
  79 $longTests = array(
  80         # These tests span multiple lines
  81         '3.1.9', '3.2.1', '3.2.2', '3.2.3', '3.2.4', '3.2.5',
  82         '3.4' );
  83
  84 # These tests are not in proper subsections
  85 $sectionTests = array( '3.4' );
  86
  87 $section = null;
  88 $test = '';
  89 $failed = 0;
  90 $success = 0;
  91 $total = 0;
  92 while( false !== ( $line = fgets( $in ) ) ) {
  93         $matches = array();
  94         if( preg_match( '/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
  95                 $section = $matches[1];
  96                 print $line;
  97                 continue;
  98         }
  99         if( preg_match( '/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
 100                 $test = $matches[1];
 101
 102                 if( in_array( $test, $ignore ) ) {
 103                         continue;
 104                 }
 105                 if( in_array( $test, $longTests ) ) {
 106                         $line = fgets( $in );
 107                         for( $line = fgets( $in ); !preg_match( '/^\s+\|/', $line ); $line = fgets( $in ) ) {
 108                                 testLine( $test, $line, $total, $success, $failed, $columns, $exceptions, $verbose );
 109                         }
 110                 } else {
 111                         testLine( $test, $line, $total, $success, $failed, $columns, $exceptions, $verbose );
 112                 }
 113         }
 114 }
 115
 116 if( $failed ) {
 117         echo "\nFailed $failed tests.\n";
 118         echo "UTF-8 DECODER TEST FAILED\n";
 119         exit (-1);
 120 }
 121
 122 echo "UTF-8 DECODER TEST SUCCESS!\n";
 123 exit (0);
 124
 125
 126 function testLine( $test, $line, &$total, &$success, &$failed, $columns, $exceptions, $verbose ) {
 127         $stripped = $line;
 128         UtfNormal::quickisNFCVerify( $stripped );
 129
 130         $same = ( $line == $stripped );
 131         $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 132         if( $len == 0 ) {
 133                 $len = strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 134         }
 135
 136         $ok = $same ^ ($test >= 3 );
 137
 138         $ok ^= in_array( $test, $exceptions );
 139
 140         $ok &= ($columns == $len);
 141
 142         $total++;
 143         if( $ok ) {
 144                 $success++;
 145         } else {
 146                 $failed++;
 147         }
 148
 149         if( $verbose || !$ok ) {
 150                 print str_replace( "\n", "$len\n", $stripped );
 151         }
 152 }