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