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  * https://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 if ( PHP_SAPI != 'cli' ) {
  31         die( "Run me from the command line please.\n" );
  32 }
  33
  34 require_once 'UtfNormalDefines.php';
  35 require_once 'UtfNormalUtil.php';
  36 require_once 'UtfNormal.php';
  37 mb_internal_encoding( "utf-8" );
  38
  39 $verbose = false;
  40 #$verbose = true;
  41
  42 $in = fopen( "UTF-8-test.txt", "rt" );
  43 if( !$in ) {
  44         print "Couldn't open UTF-8-test.txt -- can't run tests.\n";
  45         print "If necessary, manually download this file. It can be obtained at\n";
  46         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt\n";
  47         exit(-1);
  48 }
  49
  50 $columns = 0;
  51 while( false !== ( $line = fgets( $in ) ) ) {
  52         $matches = array();
  53         if( preg_match( '/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
  54                 $columns = strpos( $line, '|' );
  55                 break;
  56         }
  57 }
  58
  59 if( !$columns ) {
  60         print "Something seems to be wrong; couldn't extract line length.\n";
  61         print "Check that UTF-8-test.txt was downloaded correctly from\n";
  62         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt\n";
  63         exit(-1);
  64 }
  65
  66 # print "$columns\n";
  67
  68 $ignore = array(
  69         # These two lines actually seem to be corrupt
  70         '2.1.1', '2.2.1' );
  71
  72 $exceptions = array(
  73         # Tests that should mark invalid characters due to using long
  74         # sequences beyond what is now considered legal.
  75         '2.1.5', '2.1.6', '2.2.4', '2.2.5', '2.2.6', '2.3.5',
  76
  77         # Literal 0xffff, which is illegal
  78         '2.2.3' );
  79
  80 $longTests = array(
  81         # These tests span multiple lines
  82         '3.1.9', '3.2.1', '3.2.2', '3.2.3', '3.2.4', '3.2.5',
  83         '3.4' );
  84
  85 # These tests are not in proper subsections
  86 $sectionTests = array( '3.4' );
  87
  88 $section = null;
  89 $test = '';
  90 $failed = 0;
  91 $success = 0;
  92 $total = 0;
  93 while( false !== ( $line = fgets( $in ) ) ) {
  94         $matches = array();
  95         if( preg_match( '/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
  96                 $section = $matches[1];
  97                 print $line;
  98                 continue;
  99         }
 100         if( preg_match( '/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
 101                 $test = $matches[1];
 102
 103                 if( in_array( $test, $ignore ) ) {
 104                         continue;
 105                 }
 106                 if( in_array( $test, $longTests ) ) {
 107                         $line = fgets( $in );
 108                         for( $line = fgets( $in ); !preg_match( '/^\s+\|/', $line ); $line = fgets( $in ) ) {
 109                                 testLine( $test, $line, $total, $success, $failed, $columns, $exceptions, $verbose );
 110                         }
 111                 } else {
 112                         testLine( $test, $line, $total, $success, $failed, $columns, $exceptions, $verbose );
 113                 }
 114         }
 115 }
 116
 117 if( $failed ) {
 118         echo "\nFailed $failed tests.\n";
 119         echo "UTF-8 DECODER TEST FAILED\n";
 120         exit (-1);
 121 }
 122
 123 echo "UTF-8 DECODER TEST SUCCESS!\n";
 124 exit (0);
 125
 126
 127 function testLine( $test, $line, &$total, &$success, &$failed, $columns, $exceptions, $verbose ) {
 128         $stripped = $line;
 129         UtfNormal::quickisNFCVerify( $stripped );
 130
 131         $same = ( $line == $stripped );
 132         $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 133         if( $len == 0 ) {
 134                 $len = strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 135         }
 136
 137         $ok = $same ^ ($test >= 3 );
 138
 139         $ok ^= in_array( $test, $exceptions );
 140
 141         $ok &= ($columns == $len);
 142
 143         $total++;
 144         if( $ok ) {
 145                 $success++;
 146         } else {
 147                 $failed++;
 148         }
 149
 150         if( $verbose || !$ok ) {
 151                 print str_replace( "\n", "$len\n", $stripped );
 152         }
 153 }