tests/phpunit/includes/libs/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 class Utf8Test extends PHPUnit_Framework_TestCase {
  29         public static function provideLines() {
  30                 global $IP;
  31                 $in = fopen( "$IP/tests/phpunit/data/normal/UTF-8-test.txt", "rt" );
  32
  33                 $columns = 0;
  34                 while ( false !== ( $line = fgets( $in ) ) ) {
  35                         $matches = array();
  36                         if ( preg_match( '/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
  37                                 $columns = strpos( $line, '|' );
  38                                 break;
  39                         }
  40                 }
  41
  42                 if ( !$columns ) {
  43                         print "Something seems to be wrong; couldn't extract line length.\n";
  44                         print "Check that UTF-8-test.txt was downloaded correctly from\n";
  45                         print "http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt\n";
  46                         exit( -1 );
  47                 }
  48
  49
  50                 $ignore = array(
  51                         # These two lines actually seem to be corrupt
  52                         '2.1.1', '2.2.1' );
  53
  54                 $exceptions = array(
  55                         # Tests that should mark invalid characters due to using long
  56                         # sequences beyond what is now considered legal.
  57                         '2.1.5', '2.1.6', '2.2.4', '2.2.5', '2.2.6', '2.3.5',
  58
  59                         # Literal 0xffff, which is illegal
  60                         '2.2.3' );
  61
  62                 $longTests = array(
  63                         # These tests span multiple lines
  64                         '3.1.9', '3.2.1', '3.2.2', '3.2.3', '3.2.4', '3.2.5',
  65                         '3.4' );
  66
  67                 $testCases = array();
  68
  69                 $section = null;
  70                 while ( false !== ( $line = fgets( $in ) ) ) {
  71                         $matches = array();
  72                         if ( preg_match( '/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
  73                                 continue;
  74                         }
  75                         if ( preg_match( '/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
  76                                 $test = $matches[1];
  77
  78                                 if ( in_array( $test, $ignore ) ) {
  79                                         continue;
  80                                 }
  81                                 if ( in_array( $test, $longTests ) ) {
  82                                         fgets( $in );
  83
  84                                         // @codingStandardsIgnoreStart Generic.CodeAnalysis.ForLoopWithTestFunctionCall.NotAllowed
  85                                         for ( $line = fgets( $in ); !preg_match( '/^\s+\|/', $line ); $line = fgets( $in ) ) {
  86                                                 // @codingStandardsIgnoreEnd
  87
  88                                                 $testCases[] = array( $test, $line, $columns, $exceptions );
  89                                         }
  90                                 } else {
  91                                         $testCases[] = array( $test, $line, $columns, $exceptions );
  92                                 }
  93                         }
  94                 }
  95
  96                 return $testCases;
  97         }
  98
  99
 100         /**
 101          * @dataProvider provideLines
 102          * @covers UtfNormal::quickisNFCVerify
 103          */
 104         function testLine( $test, $line, $columns, $exceptions ) {
 105                 $stripped = $line;
 106                 UtfNormal::quickisNFCVerify( $stripped );
 107
 108                 $same = ( $line == $stripped );
 109                 $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 110                 if ( $len == 0 ) {
 111                         $len = strlen( substr( $stripped, 0, strpos( $stripped, '|' ) ) );
 112                 }
 113
 114                 $ok = $same ^ ( $test >= 3 );
 115
 116                 $ok ^= in_array( $test, $exceptions );
 117
 118                 $ok &= ( $columns == $len );
 119
 120                 $this->assertEquals( 1, $ok );
 121         }
 122
 123 }