2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com> 
    3 # http://www.mediawiki.org/ 
    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. 
   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. 
   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 
   29 require_once 
'UtfNormalUtil.php';
 
   30 require_once 
'UtfNormal.php';
 
   31 mb_internal_encoding( 
"utf-8" );
 
   34 if( php_sapi_name() != 
'cli' ) {
 
   35         die( 
"Run me from the command line please.\n" );
 
   38 $in = fopen( 
"UTF-8-test.txt", 
"rt" );
 
   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";
 
   47 while( 
false !== ( $line = fgets( 
$in ) ) ) {
 
   49         if( preg_match( 
'/^(Here come the tests:\s*)\|$/', $line, $matches ) ) {
 
   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";
 
   65         # These two lines actually seem to be corrupt
 
   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',
 
   73         # Literal 0xffff, which is illegal
 
   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',
 
   81 # These tests are not in proper subsections 
   89 while( 
false !== ( $line = fgets( 
$in ) ) ) {
 
   91         if( preg_match( 
'/^(\d+)\s+(.*?)\s*\|/', $line, $matches ) ) {
 
   96         if( preg_match( 
'/^(\d+\.\d+\.\d+)\s*/', $line, $matches ) ) {
 
  103                         $line = fgets( 
$in );
 
  104                         for( $line = fgets( 
$in ); !preg_match( 
'/^\s+\|/', $line ); $line = fgets( 
$in ) ) {
 
  114         echo 
"\nFailed $failed tests.\n";
 
  115         echo 
"UTF-8 DECODER TEST FAILED\n";
 
  119 echo 
"UTF-8 DECODER TEST SUCCESS!\n";
 
  125         UtfNormal::quickisNFCVerify( $stripped );
 
  127         $same = ( $line == $stripped );
 
  128         $len = mb_strlen( substr( $stripped, 0, strpos( $stripped, 
'|' ) ) );
 
  130                 $len = strlen( substr( $stripped, 0, strpos( $stripped, 
'|' ) ) );
 
  137         $ok ^= in_array( $test, $exceptions );
 
  139         $ok &= ($columns == $len);
 
  148         if( $verbose || !
$ok ) {
 
  149                 print str_replace( 
"\n", 
"$len\n", $stripped );