t/inc/Sanitizer.t

   1 #!/usr/bin/env php
   2 <?php
   3
   4 require 'Test.php';
   5
   6 plan( 13 );
   7
   8 require_ok( 'includes/Defines.php' );
   9 require_ok( 'includes/GlobalFunctions.php' );
  10 require_ok( 'includes/Sanitizer.php' );
  11 require_ok( 'includes/normal/UtfNormal.php' );
  12 require_ok( 'includes/ProfilerStub.php' ); # For removeHTMLtags
  13
  14
  15 #
  16 # decodeCharReferences
  17 #
  18
  19 cmp_ok(
  20         Sanitizer::decodeCharReferences( '&eacute;cole' ),
  21         '==',
  22         "\xc3\xa9cole",
  23         'decode named entities'
  24 );
  25
  26 cmp_ok(
  27         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&#233;cole!" ),
  28         '==',
  29         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  30         'decode numeric entities'
  31 );
  32
  33 cmp_ok(
  34         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&eacute;cole!" ),
  35         '==',
  36         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  37         'decode mixed numeric/named entities'
  38 );
  39
  40 cmp_ok(
  41         Sanitizer::decodeCharReferences(
  42                 "&#x108;io bonas dans l'&eacute;cole! (mais pas &amp;#x108;io dans l'&#38;eacute;cole)"
  43         ),
  44         '==',
  45         "\xc4\x88io bonas dans l'\xc3\xa9cole! (mais pas &#x108;io dans l'&eacute;cole)",
  46         'decode mixed complex entities'
  47 );
  48
  49 cmp_ok( Sanitizer::decodeCharReferences( 'a & b' ), '==', 'a & b', 'Invalid ampersand' );
  50
  51 cmp_ok( Sanitizer::decodeCharReferences( '&foo;' ), '==', '&foo;', 'Invalid named entity' );
  52
  53 cmp_ok( Sanitizer::decodeCharReferences( "&#88888888888888;" ), '==', UTF8_REPLACEMENT, 'Invalid numbered entity' );
  54
  55 $wgUseTidy = false;
  56 $wgUserHtml = true;
  57 cmp_ok(
  58         Sanitizer::removeHTMLtags( '<div>Hello world</div />' ),
  59         '==',
  60         '<div>Hello world</div>',
  61         'Self-closing closing div'
  62 );