testing/web-platform/tests/encoding/utf-32-from-win1252.html

   1 <!DOCTYPE html>
   2 <meta charset=windows-1252>
   3 <title>Character Decoding: UTF-32 (not supported) subresource of windows-1252 document</title>
   4 <script src="/resources/testharness.js"></script>
   5 <script src="/resources/testharnessreport.js"></script>
   6 <body>
   7 <script>
   8
   9 // Since UTF-32 is not supported:
  10 //  * HTML resources will use the parent encoding (windows-1252)
  11 //  * XML resources will default to UTF-8
  12 // ... except for the UTF-32LE-with-BOM case, where the UTF-32
  13 // BOM will be mistaken for a UTF-16LE BOM (FF FE 00 00), in which
  14 // case it will be interpreted as UTF-16LE.
  15
  16 const samples = [
  17   {file: 'resources/utf-32-big-endian-bom.html',
  18    characterSet: 'windows-1252',
  19    contentType: 'text/html'
  20   },
  21   {file: 'resources/utf-32-big-endian-bom.xml',
  22    characterSet: 'UTF-8',
  23    contentType: 'application/xml'
  24   },
  25   {file: 'resources/utf-32-big-endian-nobom.html',
  26    characterSet: 'windows-1252',
  27    contentType: 'text/html'
  28   },
  29   {file: 'resources/utf-32-big-endian-nobom.xml',
  30    characterSet: 'UTF-8',
  31    contentType: 'application/xml'
  32   },
  33
  34   {file: 'resources/utf-32-little-endian-bom.html',
  35    characterSet: 'UTF-16LE',
  36    contentType: 'text/html'
  37   },
  38   {file: 'resources/utf-32-little-endian-bom.xml',
  39    characterSet: 'UTF-16LE',
  40    contentType: 'application/xml'
  41   },
  42   {file: 'resources/utf-32-little-endian-nobom.html',
  43    characterSet: 'windows-1252',
  44    contentType: 'text/html'
  45   },
  46   {file: 'resources/utf-32-little-endian-nobom.xml',
  47    characterSet: 'UTF-8',
  48    contentType: 'application/xml'
  49   }
  50 ];
  51
  52 samples.forEach(expected => async_test(t => {
  53   const iframe = document.createElement('iframe');
  54   iframe.src = expected.file;
  55   iframe.onload = t.step_func_done(() => {
  56     const doc = iframe.contentDocument;
  57     assert_equals(doc.contentType, expected.contentType);
  58     assert_equals(doc.characterSet, expected.characterSet);
  59     // The following is a little quirky as non-well-formed XML isn't defined in sufficient detail to
  60     // be able to use more precise assertions.
  61     assert_true(
  62       !('dataset' in doc.documentElement) ||
  63       doc.documentElement.dataset['parsed'] !== 'yes',
  64       'Should not have parsed as (X)HTML');
  65   });
  66   document.body.appendChild(iframe);
  67   t.add_cleanup(() => iframe.remove());
  68 }, `Expect ${expected.file} to parse as ${expected.characterSet}`));
  69
  70 </script>
  71 </body>