summaryrefslogtreecommitdiffstats
path: root/netwerk/test/unit/test_idn_urls.js
blob: 358854093f6591ef5cc61a553a1d2744ac1df902 (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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
// Test algorithm for unicode display of IDNA URL (bug 722299)
const testcases = [
    //  Original             Punycode or         Expected UTF-8 by profile
    //    URL              normalized form      ASCII-Only, High, Moderate
    //
    // Latin script
    ["cuillère", "xn--cuillre-6xa",                  false, true,  true],

    // repeated non-spacing marks
    ["gruz̀̀ere",  "xn--gruzere-ogea",                 false, false, false],

    // non-XID character
    ["I♥NY",     "xn--iny-zx5a",                     false, false, false],

/*
  Behaviour of this test changed in IDNA2008, replacing the non-XID
  character with U+FFFD replacement character - when all platforms use
  IDNA2008 it can be uncommented and the punycode URL changed to
   "xn--mgbl3eb85703a"

    // new non-XID character in Unicode 6.3
    ["حلا\u061cل", "xn--bgbvr6gc",                    false, false, false],
*/

    // U+30FB KATAKANA MIDDLE DOT is excluded from non-XID characters (bug 857490)
    ["乾燥肌・石けん", "xn--08j4gylj12hz80b0uhfup",     false, true,  true],

    // Cyrillic alone
    ["толсто́й",  "xn--lsa83dealbred",                false, true,  true],

    // Mixed script Cyrillic/Latin
    ["толсто́й-in-Russian",
                 "xn---in-russian-1jg071b0a8bb4cpd", false, false, false],

    // Mixed script Latin/Cyrillic
    ["war-and-миръ", "xn--war-and--b9g3b7b3h",       false, false, false],

    // Cherokee (Restricted script)
    ["ᏣᎳᎩ",     "xn--f9dt7l",                        false, false, false],

    // Yi (former Aspirational script, now Restricted per Unicode 10.0 update to UAX 31)
    ["ꆈꌠꁱꂷ", "xn--4o7a6e1x64c",                  false, false,  false],

    // Greek alone
    ["πλάτων",   "xn--hxa3ahjw4a",                   false, true,  true],

    // Mixed script Greek/Latin
    ["πλάτωνicrelationship",
                 "xn--icrelationship-96j4t9a3cwe2e", false, false, false],

    // Mixed script Latin/Greek
    ["spaceὈδύσσεια", "xn--space-h9dui0b0ga2j1562b", false, false, false],

    // Devanagari alone
    ["मराठी",    "xn--d2b1ag0dl",                    false, true,  true],

    // Devanagari with Armenian
    ["मराठीՀայաստան",
                 "xn--y9aaa1d0ai1cq964f8dwa2o1a",    false, false, false],

    // Devanagari with common
    ["मराठी123", "xn--123-mhh3em2hra",               false, true,  true],

    // Common with Devanagari
    ["123मराठी", "xn--123-phh3em2hra",               false, true,  true],

    // Latin with Han
    ["chairman毛",
                 "xn--chairman-k65r",                false, true,  true],

    // Han with Latin
    ["山葵sauce", "xn--sauce-6j9ii40v",              false, true,  true],

    // Latin with Han, Hiragana and Katakana
    ["van語ではドイ", "xn--van-ub4bpb6w0in486d",     false, true,  true],

    // Latin with Han, Katakana and Hiragana
    ["van語ドイでは", "xn--van-ub4bpb4w0ip486d",     false, true,  true],

    // Latin with Hiragana, Han and Katakana
    ["vanでは語ドイ", "xn--van-ub4bpb6w0ip486d",     false, true,  true],

    // Latin with Hiragana, Katakana and Han
    ["vanではドイ語", "xn--van-ub4bpb6w0ir486d",     false, true,  true],

    // Latin with Katakana, Han and Hiragana
    ["vanドイ語では", "xn--van-ub4bpb4w0ir486d",     false, true,  true],

    // Latin with Katakana, Hiragana and Han
    ["vanドイでは語", "xn--van-ub4bpb4w0it486d",     false, true,  true],

    // Han with Latin, Hiragana and Katakana
    ["語vanではドイ", "xn--van-ub4bpb6w0ik486d",     false, true,  true],

    // Han with Latin, Katakana and Hiragana
    ["語vanドイでは", "xn--van-ub4bpb4w0im486d",     false, true,  true],

    // Han with Hiragana, Latin and Katakana
    ["語ではvanドイ", "xn--van-rb4bpb9w0ik486d",     false, true,  true],

    // Han with Hiragana, Katakana and Latin
    ["語ではドイvan", "xn--van-rb4bpb6w0in486d",     false, true,  true],

    // Han with Katakana, Latin and Hiragana
    ["語ドイvanでは", "xn--van-ub4bpb1w0ip486d",     false, true,  true],

    // Han with Katakana, Hiragana and Latin
    ["語ドイではvan", "xn--van-rb4bpb4w0ip486d",     false, true,  true],

    // Hiragana with Latin, Han and Katakana
    ["イツvan語ではド", "xn--van-ub4bpb1wvhsbx330n", false, true,  true],

    // Hiragana with Latin, Katakana and Han
    ["ではvanドイ語", "xn--van-rb4bpb9w0ir486d",     false, true,  true],

    // Hiragana with Han, Latin and Katakana
    ["では語vanドイ", "xn--van-rb4bpb9w0im486d",     false, true,  true],

    // Hiragana with Han, Katakana and Latin
    ["では語ドイvan", "xn--van-rb4bpb6w0ip486d",     false, true,  true],

    // Hiragana with Katakana, Latin and Han
    ["ではドイvan語", "xn--van-rb4bpb6w0iu486d",     false, true,  true],

    // Hiragana with Katakana, Han and Latin
    ["ではドイ語van", "xn--van-rb4bpb6w0ir486d",     false, true,  true],

    // Katakana with Latin, Han and Hiragana
    ["ドイvan語では", "xn--van-ub4bpb1w0iu486d",     false, true,  true],

    // Katakana with Latin, Hiragana and Han
    ["ドイvanでは語", "xn--van-ub4bpb1w0iw486d",     false, true,  true],

    // Katakana with Han, Latin and Hiragana
    ["ドイ語vanでは", "xn--van-ub4bpb1w0ir486d",     false, true,  true],

    // Katakana with Han, Hiragana and Latin
    ["ドイ語ではvan", "xn--van-rb4bpb4w0ir486d",     false, true,  true],

    // Katakana with Hiragana, Latin and Han
    ["ドイではvan語", "xn--van-rb4bpb4w0iw486d",     false, true,  true],

    // Katakana with Hiragana, Han and Latin
    ["ドイでは語van", "xn--van-rb4bpb4w0it486d",     false, true,  true],

    // Han with common
    ["中国123",   "xn--123-u68dy61b",                false, true,  true],

    // common with Han
    ["123中国",   "xn--123-x68dy61b",                false, true,  true],

    // Characters that normalize to permitted characters
    //  (also tests Plane 1 supplementary characters)
    ["super𝟖",   "super8",                           true,  true,  true],

    // Han from Plane 2
    ["𠀀𠀁𠀂", "xn--j50icd",                         false, true,  true],

    // Han from Plane 2 with js (UTF-16) escapes
    ["\uD840\uDC00\uD840\uDC01\uD840\uDC02",
            "xn--j50icd",                            false, true,  true],

    // Same with a lone high surrogate at the end
    ["\uD840\uDC00\uD840\uDC01\uD840",
            "xn--zn7c0336bda",                       false, false, false],

    // Latin text and Bengali digits
    ["super৪",   "xn--super-k2l",                    false, false, true],

    // Bengali digits and Latin text
    ["৫ab",   "xn--ab-x5f",                          false, false, true],

    // Bengali text and Latin digits
    ["অঙ্কুর8",    "xn--8-70d2cp0j6dtd",               false, true,  true],

    // Latin digits and Bengali text
    ["5াব",        "xn--5-h3d7c",                    false, true,  true],

    // Mixed numbering systems
    ["٢٠۰٠",     "xn--8hbae38c",                     false, false, false],

    // Traditional Chinese
    ["萬城",     "xn--uis754h",                      false, true,  true],

    // Simplified Chinese
    ["万城",     "xn--chq31v",                       false, true,  true],

    // Simplified-only and Traditional-only Chinese in the same label
    ["万萬城",   "xn--chq31vsl1b",                   false, true,  true],

    // Traditional-only and Simplified-only Chinese in the same label
    ["萬万城",   "xn--chq31vrl1b",                   false, true,  true],

    // Han and Latin and Bopomofo
    ["注音符号bopomofoㄅㄆㄇㄈ",
                 "xn--bopomofo-hj5gkalm1637i876cuw0brk5f",
                                                     false, true,  true],

    // Han, bopomofo, Latin
    ["注音符号ㄅㄆㄇㄈbopomofo",
                 "xn--bopomofo-8i5gkalm9637i876cuw0brk5f",
                                                     false, true,  true],

    // Latin, Han, Bopomofo
    ["bopomofo注音符号ㄅㄆㄇㄈ",
                 "xn--bopomofo-hj5gkalm9637i876cuw0brk5f",
                                                     false, true,  true],

    // Latin, Bopomofo, Han
    ["bopomofoㄅㄆㄇㄈ注音符号",
                 "xn--bopomofo-hj5gkalm3737i876cuw0brk5f",
                                                     false, true,  true],

    // Bopomofo, Han, Latin
    ["ㄅㄆㄇㄈ注音符号bopomofo",
                 "xn--bopomofo-8i5gkalm3737i876cuw0brk5f",
                                                     false, true,  true],

    // Bopomofo, Latin, Han
    ["ㄅㄆㄇㄈbopomofo注音符号",
                 "xn--bopomofo-8i5gkalm1837i876cuw0brk5f",
                                                     false, true,  true],

    // Han, bopomofo and katakana
    ["注音符号ㄅㄆㄇㄈボポモフォ",
                 "xn--jckteuaez1shij0450gylvccz9asi4e",
                                                     false, false, false],

    // Han, katakana, bopomofo
    ["注音符号ボポモフォㄅㄆㄇㄈ",
                 "xn--jckteuaez6shij5350gylvccz9asi4e",
                                                     false, false, false],

    // bopomofo, han, katakana
    ["ㄅㄆㄇㄈ注音符号ボポモフォ",
                 "xn--jckteuaez1shij4450gylvccz9asi4e",
                                                     false, false, false],

    // bopomofo, katakana, han
    ["ㄅㄆㄇㄈボポモフォ注音符号",
                 "xn--jckteuaez1shij9450gylvccz9asi4e",
                                                     false, false, false],

    // katakana, Han, bopomofo
    ["ボポモフォ注音符号ㄅㄆㄇㄈ",
                 "xn--jckteuaez6shij0450gylvccz9asi4e",
                                                     false, false, false],

    // katakana, bopomofo, Han
    ["ボポモフォㄅㄆㄇㄈ注音符号",
                 "xn--jckteuaez6shij4450gylvccz9asi4e",
                                                     false, false, false],

    // Han, Hangul and Latin
    ["韓한글hangul",
                 "xn--hangul-2m5ti09k79ze",          false, true,  true],

    // Han, Latin and Hangul
    ["韓hangul한글",
                 "xn--hangul-2m5to09k79ze",          false, true,  true],

    // Hangul, Han and Latin
    ["한글韓hangul",
                 "xn--hangul-2m5th09k79ze",          false, true,  true],

    // Hangul, Latin and Han
    ["한글hangul韓",
                 "xn--hangul-8m5t898k79ze",          false, true,  true],

    // Latin, Han and Hangul
    ["hangul韓한글",
                 "xn--hangul-8m5ti09k79ze",          false, true,  true],

    // Latin, Hangul and Han
    ["hangul한글韓",
                 "xn--hangul-8m5th09k79ze",          false, true,  true],

    // Hangul and katakana
    ["한글ハングル",
                 "xn--qck1c2d4a9266lkmzb",           false, false, false],

    // Katakana and Hangul
    ["ハングル한글",
                 "xn--qck1c2d4a2366lkmzb",           false, false, false],

    // Thai (also tests that node with over 63 UTF-8 octets doesn't fail)
    ["เครื่องทําน้ําทําน้ําแข็ง",
                 "xn--22cdjb2fanb9fyepcbbb9dwh4a3igze4fdcd",
                                                     false, true, true]
];


const profiles = ["ASCII", "high", "moderate"];

function run_test() {
    var pbi = Cc["@mozilla.org/preferences-service;1"].getService(Ci.nsIPrefBranch);
    var oldProfile = pbi.getCharPref("network.IDN.restriction_profile", "moderate");
    var oldWhitelistCom = pbi.getBoolPref("network.IDN.whitelist.com", false);
    var idnService = Cc["@mozilla.org/network/idn-service;1"].getService(Ci.nsIIDNService);

    for (var i = 0; i < profiles.length; ++i) {
        pbi.setCharPref("network.IDN.restriction_profile", profiles[i]);
        pbi.setBoolPref("network.IDN.whitelist.com", false);

        dump("testing " + profiles[i] + " profile");

        for (var j = 0; j < testcases.length; ++j) {
            var test = testcases[j];
            var URL = test[0] + ".com";
            var punycodeURL = test[1] + ".com";
            var expectedUnicode = test[2 + i];
            var isASCII = {};

	    var result;
	    try {
		result = idnService.convertToDisplayIDN(URL, isASCII);
	    } catch(e) {
		result = ".com";
	    }
            if (punycodeURL.substr(0, 4) == "xn--") {
                // test convertToDisplayIDN with a Unicode URL and with a
                //  Punycode URL if we have one
                do_check_eq(escape(result),
                            expectedUnicode ? escape(URL) : escape(punycodeURL));

                result = idnService.convertToDisplayIDN(punycodeURL, isASCII);
                do_check_eq(escape(result),
                            expectedUnicode ? escape(URL) : escape(punycodeURL));
            } else {
                // The "punycode" URL isn't punycode. This happens in testcases
                // where the Unicode URL has become normalized to an ASCII URL,
                // so, even though expectedUnicode is true, the expected result
                // is equal to punycodeURL
                do_check_eq(escape(result), escape(punycodeURL));
            }
        }
    }
    pbi.setBoolPref("network.IDN.whitelist.com", oldWhitelistCom);
    pbi.setCharPref("network.IDN.restriction_profile", oldProfile);
}