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