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
|
<!DOCTYPE html>
<title>Encoding API: Invalid UTF-16 surrogates with UTF-8 encoding</title>
<script src="/resources/testharness.js"></script>
<script src="/resources/testharnessreport.js"></script>
<script>
var badStrings = [
{
input: 'abc123',
expected: [0x61, 0x62, 0x63, 0x31, 0x32, 0x33],
decoded: 'abc123',
name: 'Sanity check'
},
{
input: '\uD800',
expected: [0xef, 0xbf, 0xbd],
decoded: '\uFFFD',
name: 'Surrogate half (low)'
},
{
input: '\uDC00',
expected: [0xef, 0xbf, 0xbd],
decoded: '\uFFFD',
name: 'Surrogate half (high)'
},
{
input: 'abc\uD800123',
expected: [0x61, 0x62, 0x63, 0xef, 0xbf, 0xbd, 0x31, 0x32, 0x33],
decoded: 'abc\uFFFD123',
name: 'Surrogate half (low), in a string'
},
{
input: 'abc\uDC00123',
expected: [0x61, 0x62, 0x63, 0xef, 0xbf, 0xbd, 0x31, 0x32, 0x33],
decoded: 'abc\uFFFD123',
name: 'Surrogate half (high), in a string'
},
{
input: '\uDC00\uD800',
expected: [0xef, 0xbf, 0xbd, 0xef, 0xbf, 0xbd],
decoded: '\uFFFD\uFFFD',
name: 'Wrong order'
}
];
badStrings.forEach(function(t) {
test(function() {
var encoded = new TextEncoder().encode(t.input);
assert_array_equals([].slice.call(encoded), t.expected);
assert_equals(new TextDecoder('utf-8').decode(encoded), t.decoded);
}, 'Invalid surrogates encoded into UTF-8: ' + t.name);
});
</script>
|