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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
|
description("Canonicalization of IPv6 addresses.");
cases = [
["[", ""],
["[:", ""],
["]", ""],
[":]", ""],
["[]", ""],
["[:]", ""],
// Regular IP address is invalid without bounding '[' and ']'.
["2001:db8::1", ""],
["[2001:db8::1", ""],
["2001:db8::1]", ""],
// Regular IP addresses.
["[::]", "[::]"],
["[::1]", "[::1]"],
["[1::]", "[1::]"],
["[::192.168.0.1]", "[::c0a8:1]"],
["[::ffff:192.168.0.1]", "[::ffff:c0a8:1]"],
// Leading zeros should be stripped.
["[000:01:02:003:004:5:6:007]", "[0:1:2:3:4:5:6:7]"],
// Upper case letters should be lowercased.
["[A:b:c:DE:fF:0:1:aC]", "[a:b:c:de:ff:0:1:ac]"],
// The same address can be written with different contractions, but should
// get canonicalized to the same thing.
["[1:0:0:2::3:0]", "[1::2:0:0:3:0]"],
["[1::2:0:0:3:0]", "[1::2:0:0:3:0]"],
// IPv4 addresses
// Only mapped and compat addresses can have IPv4 syntax embedded.
["[::eeee:192.168.0.1]", ""],
["[2001::192.168.0.1]", ""],
["[1:2:192.168.0.1:5:6]", ""],
// IPv4 with last component missing.
["[::ffff:192.1.2]", "[::ffff:c001:2]"],
// IPv4 using hex.
// FIXME: Should this format be disallowed?
["[::ffff:0xC0.0Xa8.0x0.0x1]", "[::ffff:c0a8:1]"],
// There may be zeros surrounding the "::" contraction.
["[0:0::0:0:8]", "[::8]"],
["[2001:db8::1]", "[2001:db8::1]"],
// Can only have one "::" contraction in an IPv6 string literal.
["[2001::db8::1]", ""],
// No more than 2 consecutive ':'s.
["[2001:db8:::1]", ""],
["[:::]", ""],
// Non-IP addresses due to invalid characters.
["[2001::.com]", ""],
// Too many components means not an IP address. Similarly with too few if using IPv4 compat or mapped addresses.
["[::192.168.0.0.1]", ""],
["[::ffff:192.168.0.0.1]", ""],
["[1:2:3:4:5:6:7:8:9]", ""],
// Too many bits (even though 8 comonents, the last one holds 32 bits).
["[0:0:0:0:0:0:0:192.168.0.1]", ""],
// Too many bits specified -- the contraction would have to be zero-length
// to not exceed 128 bits.
["[1:2:3:4:5:6::192.168.0.1]", ""],
// The contraction is for 16 bits of zero.
["[1:2:3:4:5:6::8]", "[1:2:3:4:5:6:0:8]"],
// Cannot have a trailing colon.
["[1:2:3:4:5:6:7:8:]", ""],
["[1:2:3:4:5:6:192.168.0.1:]", ""],
// Cannot have negative numbers.
["[-1:2:3:4:5:6:7:8]", ""],
// Scope ID -- the URL may contain an optional ["%" <scope_id>] section.
// The scope_id should be included in the canonicalized URL, and is an
// unsigned decimal number.
// Don't allow scope-id
["[1::%1]", ""],
["[1::%eth0]", ""],
["[1::%]", ""],
["[%]", ""],
["[::%:]", ""],
// Don't allow leading or trailing colons.
["[:0:0::0:0:8]", ""],
["[0:0::0:0:8:]", ""],
["[:0:0::0:0:8:]", ""],
// Two dots in a row means not an IP address.
["[::192.168..1]", ""],
// Spaces should be rejected.
["[::1 hello]", ""]
];
// We test the empty string individually.
shouldBe("canonicalize('http:///')", "'http:'");
for (var i = 0; i < cases.length; ++i) {
test_vector = cases[i][0];
expected_result = cases[i][1];
if (expected_result === "") {
// We use "" to represent that the test vector ought not to parse.
// It appears that we're supposed to apply a default canonicalization,
// and the escape function escapes too much!
expected_result = test_vector.toLowerCase();
['%', ' '].forEach(function(c){
expected_result = expected_result.replace(c, escape(c));
})
}
shouldBe("canonicalize('http://" + test_vector + "/')",
"'http://" + expected_result + "/'");
}
var successfullyParsed = true;
|
