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 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, 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  * @ingroup UtfNormal
  25  * @access private
  26  */
  27
  28 /** */
  29 require_once 'UtfNormalUtil.php';
  30 require_once 'UtfNormal.php';
  31 mb_internal_encoding( "utf-8" );
  32
  33 #$verbose = true;
  34 if( php_sapi_name() != 'cli' ) {
  35         die( "Run me from the command line please.\n" );
  36 }
  37
  38 $in = fopen( "UTF-8-test.txt", "rt" );
  39 if( !$in ) {
  40         print "Couldn't open UTF-8-test.txt -- can't run tests.\n";
  41         print "If necessary, manually download this file. It can be obtained at\n";
  42         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt";
  43         exit(-1);
  44 }
  45
  46 $columns = 0;
  47 while( false !== ( $line = fgets( $in ) ) ) {
  48         $matches = array();
  49         if( preg_match( '/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
  50                 $columns = strpos( $line, '|' );
  51                 break;
  52         }
  53 }
  54
  55 if( !$columns ) {
  56         print "Something seems to be wrong; couldn't extract line length.\n";
  57         print "Check that UTF-8-test.txt was downloaded correctly from\n";
  58         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt";
  59         exit(-1);
  60 }
  61
  62 # print "$columns\n";
  63
  64 $ignore = array(
  65         # These two lines actually seem to be corrupt
  66         '2.1.1', '2.2.1' );
  67
  68 $exceptions = array(
  69         # Tests that should mark invalid characters due to using long
  70         # sequences beyond what is now considered legal.
  71         '2.1.5', '2.1.6', '2.2.4', '2.2.5', '2.2.6', '2.3.5',
  72
  73         # Literal 0xffff, which is illegal
  74         '2.2.3' );
  75
  76 $longTests = array(
  77         # These tests span multiple lines
  78         '3.1.9', '3.2.1', '3.2.2', '3.2.3', '3.2.4', '3.2.5',
  79         '3.4' );
  80
  81 # These tests are not in proper subsections
  82 $sectionTests = array( '3.4' );
  83
  84 $section = null;
  85 $test = '';
  86 $failed = 0;
  87 $success = 0;
  88 $total = 0;
  89 while( false !== ( $line = fgets( $in ) ) ) {
  90         $matches = array();
  91         if( preg_match( '/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
  92                 $section = $matches[1];
  93                 print $line;
  94                 continue;
  95         }
  96         if( preg_match( '/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
  97                 $test = $matches[1];
  98
  99                 if( in_array( $test, $ignore ) ) {
 100                         continue;
 101                 }
 102                 if( in_array( $test, $longTests ) ) {
 103                         $line = fgets( $in );
 104                         for( $line = fgets( $in ); !preg_match( '/^\s+\|/', $line ); $line = fgets( $in ) ) {
 105                                 testLine( $test, $line, $total, $success, $failed );
 106                         }
 107                 } else {
 108                         testLine( $test, $line, $total, $success, $failed );
 109                 }
 110         }
 111 }
 112
 113 if( $failed ) {
 114         echo "\nFailed $failed tests.\n";
 115         echo "UTF-8 DECODER TEST FAILED\n";
 116         exit (-1);
 117 }
 118
 119 echo "UTF-8 DECODER TEST SUCCESS!\n";
 120 exit (0);
 121
 122
 123 function testLine( $test, $line, &$total, &$success, &$failed ) {
 124         $stripped = $line;
 125         UtfNormal::quickisNFCVerify( $stripped );
 126
 127         $same = ( $line == $stripped );
 128         $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 129         if( $len == 0 ) {
 130                 $len = strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 131         }
 132
 133         global $columns;
 134         $ok = $same ^ ($test >= 3 );
 135
 136         global $exceptions;
 137         $ok ^= in_array( $test, $exceptions );
 138
 139         $ok &= ($columns == $len);
 140
 141         $total++;
 142         if( $ok ) {
 143                 $success++;
 144         } else {
 145                 $failed++;
 146         }
 147         global $verbose;
 148         if( $verbose || !$ok ) {
 149                 print str_replace( "\n", "$len\n", $stripped );
 150         }
 151 }