The Tor Browser / file comparison
comparison: netwerk/test/unit/test_idn_urls.js
netwerk/test/unit/test_idn_urls.js
- changeset 1
- ca08bd8f51b2
equal
deleted
inserted
replaced
| -1:000000000000 | 0:56f17d94eb17 |
|---|---|
| 1 // Test algorithm for unicode display of IDNA URL (bug 722299) | |
| 2 const testcases = [ | |
| 3 // Original Punycode or Expected UTF-8 by profile | |
| 4 // URL normalized form ASCII-Only, High, Moderate | |
| 5 // | |
| 6 // Latin script | |
| 7 ["cuillère", "xn--cuillre-6xa", false, true, true], | |
| 8 | |
| 9 // repeated non-spacing marks | |
| 10 ["gruz̀̀ere", "xn--gruzere-ogea", false, false, false], | |
| 11 | |
| 12 // non-XID character | |
| 13 ["I♥NY", "xn--iny-zx5a", false, false, false], | |
| 14 | |
| 15 // new non-XID character in Unicode 6.3 | |
| 16 ["حلا\u061cل", "xn--bgbvr6gc", false, false, false], | |
| 17 | |
| 18 // U+30FB KATAKANA MIDDLE DOT is excluded from non-XID characters (bug 857490) | |
| 19 ["乾燥肌・石けん", "xn--08j4gylj12hz80b0uhfup", false, true, true], | |
| 20 | |
| 21 // Cyrillic alone | |
| 22 ["толсто́й", "xn--lsa83dealbred", false, true, true], | |
| 23 | |
| 24 // Mixed script Cyrillic/Latin | |
| 25 ["толсто́й-in-Russian", | |
| 26 "xn---in-russian-1jg071b0a8bb4cpd", false, false, false], | |
| 27 | |
| 28 // Mixed script Latin/Cyrillic | |
| 29 ["war-and-миръ", "xn--war-and--b9g3b7b3h", false, false, false], | |
| 30 | |
| 31 // Cherokee (Restricted script) | |
| 32 ["ᏣᎳᎩ", "xn--f9dt7l", false, false, false], | |
| 33 | |
| 34 // Yi (Aspirational script) | |
| 35 ["ꆈꌠꁱꂷ", "xn--4o7a6e1x64c", false, true, true], | |
| 36 | |
| 37 // Greek alone | |
| 38 ["πλάτων", "xn--hxa3ahjw4a", false, true, true], | |
| 39 | |
| 40 // Mixed script Greek/Latin | |
| 41 ["πλάτωνicrelationship", | |
| 42 "xn--icrelationship-96j4t9a3cwe2e", false, false, false], | |
| 43 | |
| 44 // Mixed script Latin/Greek | |
| 45 ["spaceὈδύσσεια", "xn--space-h9dui0b0ga2j1562b", false, false, false], | |
| 46 | |
| 47 // Devanagari alone | |
| 48 ["मराठी", "xn--d2b1ag0dl", false, true, true], | |
| 49 | |
| 50 // Devanagari with Armenian | |
| 51 ["मराठीՀայաստան", | |
| 52 "xn--y9aaa1d0ai1cq964f8dwa2o1a", false, false, false], | |
| 53 | |
| 54 // Devanagari with common | |
| 55 ["मराठी123", "xn--123-mhh3em2hra", false, true, true], | |
| 56 | |
| 57 // Common with Devanagari | |
| 58 ["123मराठी", "xn--123-phh3em2hra", false, true, true], | |
| 59 | |
| 60 // Latin with Han | |
| 61 ["chairman毛", | |
| 62 "xn--chairman-k65r", false, true, true], | |
| 63 | |
| 64 // Han with Latin | |
| 65 ["山葵sauce", "xn--sauce-6j9ii40v", false, true, true], | |
| 66 | |
| 67 // Latin with Han, Hiragana and Katakana | |
| 68 ["van語ではドイ", "xn--van-ub4bpb6w0in486d", false, true, true], | |
| 69 | |
| 70 // Latin with Han, Katakana and Hiragana | |
| 71 ["van語ドイでは", "xn--van-ub4bpb4w0ip486d", false, true, true], | |
| 72 | |
| 73 // Latin with Hiragana, Han and Katakana | |
| 74 ["vanでは語ドイ", "xn--van-ub4bpb6w0ip486d", false, true, true], | |
| 75 | |
| 76 // Latin with Hiragana, Katakana and Han | |
| 77 ["vanではドイ語", "xn--van-ub4bpb6w0ir486d", false, true, true], | |
| 78 | |
| 79 // Latin with Katakana, Han and Hiragana | |
| 80 ["vanドイ語では", "xn--van-ub4bpb4w0ir486d", false, true, true], | |
| 81 | |
| 82 // Latin with Katakana, Hiragana and Han | |
| 83 ["vanドイでは語", "xn--van-ub4bpb4w0it486d", false, true, true], | |
| 84 | |
| 85 // Han with Latin, Hiragana and Katakana | |
| 86 ["語vanではドイ", "xn--van-ub4bpb6w0ik486d", false, true, true], | |
| 87 | |
| 88 // Han with Latin, Katakana and Hiragana | |
| 89 ["語vanドイでは", "xn--van-ub4bpb4w0im486d", false, true, true], | |
| 90 | |
| 91 // Han with Hiragana, Latin and Katakana | |
| 92 ["語ではvanドイ", "xn--van-rb4bpb9w0ik486d", false, true, true], | |
| 93 | |
| 94 // Han with Hiragana, Katakana and Latin | |
| 95 ["語ではドイvan", "xn--van-rb4bpb6w0in486d", false, true, true], | |
| 96 | |
| 97 // Han with Katakana, Latin and Hiragana | |
| 98 ["語ドイvanでは", "xn--van-ub4bpb1w0ip486d", false, true, true], | |
| 99 | |
| 100 // Han with Katakana, Hiragana and Latin | |
| 101 ["語ドイではvan", "xn--van-rb4bpb4w0ip486d", false, true, true], | |
| 102 | |
| 103 // Hiragana with Latin, Han and Katakana | |
| 104 ["イツvan語ではド", "xn--van-ub4bpb1wvhsbx330n", false, true, true], | |
| 105 | |
| 106 // Hiragana with Latin, Katakana and Han | |
| 107 ["ではvanドイ語", "xn--van-rb4bpb9w0ir486d", false, true, true], | |
| 108 | |
| 109 // Hiragana with Han, Latin and Katakana | |
| 110 ["では語vanドイ", "xn--van-rb4bpb9w0im486d", false, true, true], | |
| 111 | |
| 112 // Hiragana with Han, Katakana and Latin | |
| 113 ["では語ドイvan", "xn--van-rb4bpb6w0ip486d", false, true, true], | |
| 114 | |
| 115 // Hiragana with Katakana, Latin and Han | |
| 116 ["ではドイvan語", "xn--van-rb4bpb6w0iu486d", false, true, true], | |
| 117 | |
| 118 // Hiragana with Katakana, Han and Latin | |
| 119 ["ではドイ語van", "xn--van-rb4bpb6w0ir486d", false, true, true], | |
| 120 | |
| 121 // Katakana with Latin, Han and Hiragana | |
| 122 ["ドイvan語では", "xn--van-ub4bpb1w0iu486d", false, true, true], | |
| 123 | |
| 124 // Katakana with Latin, Hiragana and Han | |
| 125 ["ドイvanでは語", "xn--van-ub4bpb1w0iw486d", false, true, true], | |
| 126 | |
| 127 // Katakana with Han, Latin and Hiragana | |
| 128 ["ドイ語vanでは", "xn--van-ub4bpb1w0ir486d", false, true, true], | |
| 129 | |
| 130 // Katakana with Han, Hiragana and Latin | |
| 131 ["ドイ語ではvan", "xn--van-rb4bpb4w0ir486d", false, true, true], | |
| 132 | |
| 133 // Katakana with Hiragana, Latin and Han | |
| 134 ["ドイではvan語", "xn--van-rb4bpb4w0iw486d", false, true, true], | |
| 135 | |
| 136 // Katakana with Hiragana, Han and Latin | |
| 137 ["ドイでは語van", "xn--van-rb4bpb4w0it486d", false, true, true], | |
| 138 | |
| 139 // Han with common | |
| 140 ["中国123", "xn--123-u68dy61b", false, true, true], | |
| 141 | |
| 142 // common with Han | |
| 143 ["123中国", "xn--123-x68dy61b", false, true, true], | |
| 144 | |
| 145 // Characters that normalize to permitted characters | |
| 146 // (also tests Plane 1 supplementary characters) | |
| 147 ["super𝟖", "super8", true, true, true], | |
| 148 | |
| 149 // Han from Plane 2 | |
| 150 ["𠀀𠀁𠀂", "xn--j50icd", false, true, true], | |
| 151 | |
| 152 // Han from Plane 2 with js (UTF-16) escapes | |
| 153 ["\uD840\uDC00\uD840\uDC01\uD840\uDC02", | |
| 154 "xn--j50icd", false, true, true], | |
| 155 | |
| 156 // Same with a lone high surrogate at the end | |
| 157 ["\uD840\uDC00\uD840\uDC01\uD840", "", false, false, false], | |
| 158 | |
| 159 // Latin text and Bengali digits | |
| 160 ["super৪", "xn--super-k2l", false, false, true], | |
| 161 | |
| 162 // Bengali digits and Latin text | |
| 163 ["৫ab", "xn--ab-x5f", false, false, true], | |
| 164 | |
| 165 // Bengali text and Latin digits | |
| 166 ["অঙ্কুর8", "xn--8-70d2cp0j6dtd", false, true, true], | |
| 167 | |
| 168 // Latin digits and Bengali text | |
| 169 ["5াব", "xn--5-h3d7c", false, true, true], | |
| 170 | |
| 171 // Mixed numbering systems | |
| 172 ["٢٠۰٠", "xn--8hbae38c", false, false, false], | |
| 173 | |
| 174 // Traditional Chinese | |
| 175 ["萬城", "xn--uis754h", false, true, true], | |
| 176 | |
| 177 // Simplified Chinese | |
| 178 ["万城", "xn--chq31v", false, true, true], | |
| 179 | |
| 180 // Simplified-only and Traditional-only Chinese in the same label | |
| 181 ["万萬城", "xn--chq31vsl1b", false, true, true], | |
| 182 | |
| 183 // Traditional-only and Simplified-only Chinese in the same label | |
| 184 ["萬万城", "xn--chq31vrl1b", false, true, true], | |
| 185 | |
| 186 // Han and Latin and Bopomofo | |
| 187 ["注音符号bopomofoㄅㄆㄇㄈ", | |
| 188 "xn--bopomofo-hj5gkalm1637i876cuw0brk5f", | |
| 189 false, true, true], | |
| 190 | |
| 191 // Han, bopomofo, Latin | |
| 192 ["注音符号ㄅㄆㄇㄈbopomofo", | |
| 193 "xn--bopomofo-8i5gkalm9637i876cuw0brk5f", | |
| 194 false, true, true], | |
| 195 | |
| 196 // Latin, Han, Bopomofo | |
| 197 ["bopomofo注音符号ㄅㄆㄇㄈ", | |
| 198 "xn--bopomofo-hj5gkalm9637i876cuw0brk5f", | |
| 199 false, true, true], | |
| 200 | |
| 201 // Latin, Bopomofo, Han | |
| 202 ["bopomofoㄅㄆㄇㄈ注音符号", | |
| 203 "xn--bopomofo-hj5gkalm3737i876cuw0brk5f", | |
| 204 false, true, true], | |
| 205 | |
| 206 // Bopomofo, Han, Latin | |
| 207 ["ㄅㄆㄇㄈ注音符号bopomofo", | |
| 208 "xn--bopomofo-8i5gkalm3737i876cuw0brk5f", | |
| 209 false, true, true], | |
| 210 | |
| 211 // Bopomofo, Latin, Han | |
| 212 ["ㄅㄆㄇㄈbopomofo注音符号", | |
| 213 "xn--bopomofo-8i5gkalm1837i876cuw0brk5f", | |
| 214 false, true, true], | |
| 215 | |
| 216 // Han, bopomofo and katakana | |
| 217 ["注音符号ㄅㄆㄇㄈボポモフォ", | |
| 218 "xn--jckteuaez1shij0450gylvccz9asi4e", | |
| 219 false, false, false], | |
| 220 | |
| 221 // Han, katakana, bopomofo | |
| 222 ["注音符号ボポモフォㄅㄆㄇㄈ", | |
| 223 "xn--jckteuaez6shij5350gylvccz9asi4e", | |
| 224 false, false, false], | |
| 225 | |
| 226 // bopomofo, han, katakana | |
| 227 ["ㄅㄆㄇㄈ注音符号ボポモフォ", | |
| 228 "xn--jckteuaez1shij4450gylvccz9asi4e", | |
| 229 false, false, false], | |
| 230 | |
| 231 // bopomofo, katakana, han | |
| 232 ["ㄅㄆㄇㄈボポモフォ注音符号", | |
| 233 "xn--jckteuaez1shij9450gylvccz9asi4e", | |
| 234 false, false, false], | |
| 235 | |
| 236 // katakana, Han, bopomofo | |
| 237 ["ボポモフォ注音符号ㄅㄆㄇㄈ", | |
| 238 "xn--jckteuaez6shij0450gylvccz9asi4e", | |
| 239 false, false, false], | |
| 240 | |
| 241 // katakana, bopomofo, Han | |
| 242 ["ボポモフォㄅㄆㄇㄈ注音符号", | |
| 243 "xn--jckteuaez6shij4450gylvccz9asi4e", | |
| 244 false, false, false], | |
| 245 | |
| 246 // Han, Hangul and Latin | |
| 247 ["韓한글hangul", | |
| 248 "xn--hangul-2m5ti09k79ze", false, true, true], | |
| 249 | |
| 250 // Han, Latin and Hangul | |
| 251 ["韓hangul한글", | |
| 252 "xn--hangul-2m5to09k79ze", false, true, true], | |
| 253 | |
| 254 // Hangul, Han and Latin | |
| 255 ["한글韓hangul", | |
| 256 "xn--hangul-2m5th09k79ze", false, true, true], | |
| 257 | |
| 258 // Hangul, Latin and Han | |
| 259 ["한글hangul韓", | |
| 260 "xn--hangul-8m5t898k79ze", false, true, true], | |
| 261 | |
| 262 // Latin, Han and Hangul | |
| 263 ["hangul韓한글", | |
| 264 "xn--hangul-8m5ti09k79ze", false, true, true], | |
| 265 | |
| 266 // Latin, Hangul and Han | |
| 267 ["hangul한글韓", | |
| 268 "xn--hangul-8m5th09k79ze", false, true, true], | |
| 269 | |
| 270 // Hangul and katakana | |
| 271 ["한글ハングル", | |
| 272 "xn--qck1c2d4a9266lkmzb", false, false, false], | |
| 273 | |
| 274 // Katakana and Hangul | |
| 275 ["ハングル한글", | |
| 276 "xn--qck1c2d4a2366lkmzb", false, false, false], | |
| 277 | |
| 278 // Thai (also tests that node with over 63 UTF-8 octets doesn't fail) | |
| 279 ["เครื่องทําน้ําทําน้ําแข็ง", | |
| 280 "xn--22cdjb2fanb9fyepcbbb9dwh4a3igze4fdcd", | |
| 281 false, true, true] | |
| 282 ]; | |
| 283 | |
| 284 | |
| 285 const profiles = ["ASCII", "high", "moderate"]; | |
| 286 | |
| 287 function run_test() { | |
| 288 var pbi = Cc["@mozilla.org/preferences-service;1"].getService(Ci.nsIPrefBranch); | |
| 289 var oldProfile = pbi.getCharPref("network.IDN.restriction_profile", "moderate"); | |
| 290 var oldWhiteListCom; | |
| 291 try { | |
| 292 oldWhitelistCom = pbi.getBoolPref("network.IDN.whitelist.com"); | |
| 293 } catch(e) { | |
| 294 oldWhitelistCom = false; | |
| 295 } | |
| 296 var idnService = Cc["@mozilla.org/network/idn-service;1"].getService(Ci.nsIIDNService); | |
| 297 | |
| 298 for (var i = 0; i < profiles.length; ++i) { | |
| 299 pbi.setCharPref("network.IDN.restriction_profile", profiles[i]); | |
| 300 pbi.setBoolPref("network.IDN.whitelist.com", false); | |
| 301 | |
| 302 dump("testing " + profiles[i] + " profile"); | |
| 303 | |
| 304 for (var j = 0; j < testcases.length; ++j) { | |
| 305 var test = testcases[j]; | |
| 306 var URL = test[0] + ".com"; | |
| 307 var punycodeURL = test[1] + ".com"; | |
| 308 var expectedUnicode = test[2 + i]; | |
| 309 var isASCII = {}; | |
| 310 | |
| 311 var result; | |
| 312 try { | |
| 313 result = idnService.convertToDisplayIDN(URL, isASCII); | |
| 314 } catch(e) { | |
| 315 result = ".com"; | |
| 316 } | |
| 317 if (punycodeURL.substr(0, 4) == "xn--") { | |
| 318 // test convertToDisplayIDN with a Unicode URL and with a | |
| 319 // Punycode URL if we have one | |
| 320 do_check_eq(escape(result), | |
| 321 expectedUnicode ? escape(URL) : escape(punycodeURL)); | |
| 322 | |
| 323 result = idnService.convertToDisplayIDN(punycodeURL, isASCII); | |
| 324 do_check_eq(escape(result), | |
| 325 expectedUnicode ? escape(URL) : escape(punycodeURL)); | |
| 326 } else { | |
| 327 // The "punycode" URL isn't punycode. This happens in testcases | |
| 328 // where the Unicode URL has become normalized to an ASCII URL, | |
| 329 // so, even though expectedUnicode is true, the expected result | |
| 330 // is equal to punycodeURL | |
| 331 do_check_eq(escape(result), escape(punycodeURL)); | |
| 332 } | |
| 333 } | |
| 334 } | |
| 335 pbi.setBoolPref("network.IDN.whitelist.com", oldWhitelistCom); | |
| 336 pbi.setCharPref("network.IDN.restriction_profile", oldProfile); | |
| 337 } |
