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