summaryrefslogtreecommitdiffstats
path: root/testing/web-platform/tests/dom/nodes/Document-characterSet-normalization-2.html
blob: 7c7691bdc16539be206b3991f0a414c9e5022f1f (plain)
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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
<!doctype html>
<title>document.characterSet (inputEncoding and charset as aliases) normalization tests</title>
<link rel=author title="Aryeh Gregor" href=ayg@aryeh.name>
<meta name=timeout content=long>
<div id=log></div>
<script src=/resources/testharness.js></script>
<script src=/resources/testharnessreport.js></script>
<script src="./characterset-helper.js"></script>
<style>iframe { display: none }</style>
<script>
"use strict";

// Taken straight from https://encoding.spec.whatwg.org/
var encodingMap = {
  "KOI8-R": [
    "cskoi8r",
    "koi",
    "koi8",
    "koi8-r",
    "koi8_r",
  ],
  "KOI8-U": [
    "koi8-ru",
    "koi8-u",
  ],
  "macintosh": [
    "csmacintosh",
    "mac",
    "macintosh",
    "x-mac-roman",
  ],
  "windows-874": [
    "dos-874",
    "iso-8859-11",
    "iso8859-11",
    "iso885911",
    "tis-620",
    "windows-874",
  ],
  "windows-1250": [
    "cp1250",
    "windows-1250",
    "x-cp1250",
  ],
  "windows-1251": [
    "cp1251",
    "windows-1251",
    "x-cp1251",
  ],
  "windows-1252": [
    "ansi_x3.4-1968",
    "ascii",
    "cp1252",
    "cp819",
    "csisolatin1",
    "ibm819",
    "iso-8859-1",
    "iso-ir-100",
    "iso8859-1",
    "iso88591",
    "iso_8859-1",
    "iso_8859-1:1987",
    "l1",
    "latin1",
    "us-ascii",
    "windows-1252",
    "x-cp1252",
    // As we use <meta>, x-user-defined will map to windows-1252 per
    // https://html.spec.whatwg.org/multipage/#documentEncoding
    "x-user-defined"
  ],
  "windows-1253": [
    "cp1253",
    "windows-1253",
    "x-cp1253",
  ],
  "windows-1254": [
    "cp1254",
    "csisolatin5",
    "iso-8859-9",
    "iso-ir-148",
    "iso8859-9",
    "iso88599",
    "iso_8859-9",
    "iso_8859-9:1989",
    "l5",
    "latin5",
    "windows-1254",
    "x-cp1254",
  ],
  "windows-1255": [
    "cp1255",
    "windows-1255",
    "x-cp1255",
  ],
  "windows-1256": [
    "cp1256",
    "windows-1256",
    "x-cp1256",
  ],
  "windows-1257": [
    "cp1257",
    "windows-1257",
    "x-cp1257",
  ],
  "windows-1258": [
    "cp1258",
    "windows-1258",
    "x-cp1258",
  ],
  "x-mac-cyrillic": [
    "x-mac-cyrillic",
    "x-mac-ukrainian",
  ],
  "GBK": [
    "chinese",
    "csgb2312",
    "csiso58gb231280",
    "gb2312",
    "gb_2312",
    "gb_2312-80",
    "gbk",
    "iso-ir-58",
    "x-gbk",
  ],
  "gb18030": [
    "gb18030",
  ],
  "Big5": [
    "big5",
    "big5-hkscs",
    "cn-big5",
    "csbig5",
    "x-x-big5",
  ],
  "EUC-JP": [
    "cseucpkdfmtjapanese",
    "euc-jp",
    "x-euc-jp",
  ],
  "ISO-2022-JP": [
    "csiso2022jp",
    "iso-2022-jp",
  ],
  "Shift_JIS": [
    "csshiftjis",
    "ms932",
    "ms_kanji",
    "shift-jis",
    "shift_jis",
    "sjis",
    "windows-31j",
    "x-sjis",
  ],
  "EUC-KR": [
    "cseuckr",
    "csksc56011987",
    "euc-kr",
    "iso-ir-149",
    "korean",
    "ks_c_5601-1987",
    "ks_c_5601-1989",
    "ksc5601",
    "ksc_5601",
    "windows-949",
  ],
  "replacement": [
    "csiso2022kr",
    "hz-gb-2312",
    "iso-2022-cn",
    "iso-2022-cn-ext",
    "iso-2022-kr",
  ],
};

runCharacterSetTests(encodingMap);

</script>
<!-- vim: set expandtab tabstop=2 shiftwidth=2: -->