| OLD | NEW |
|---|
| (Empty) | |
| 1 #!/usr/bin/env dart |
| 2 // Copyright (c) 2012, the Dart project authors. Please see the AUTHORS file |
| 3 // for details. All rights reserved. Use of this source code is governed by a |
| 4 // BSD-style license that can be found in the LICENSE file. |
| 5 |
| 6 #library("utf8_tests"); |
| 7 #import("dunit.dart"); |
| 8 #import("../../string_encoding/unicode.dart"); |
| 9 #import("../../string_encoding/unicode_core.dart"); |
| 10 #source("../../string_encoding/utf8_impl.dart"); |
| 11 |
| 12 void main() { |
| 13 TestSuite suite = new TestSuite(); |
| 14 suite.registerTestClass(new Utf8Tests()); |
| 15 suite.run(); |
| 16 } |
| 17 |
| 18 class Utf8Tests extends TestClass { |
| 19 static final String testEnglishPhrase = |
| 20 "The quick brown fox jumps over the lazy dog."; |
| 21 |
| 22 static final List<int> testEnglishUtf8 = const<int> [ |
| 23 0x54, 0x68, 0x65, 0x20, 0x71, 0x75, 0x69, 0x63, |
| 24 0x6b, 0x20, 0x62, 0x72, 0x6f, 0x77, 0x6e, 0x20, |
| 25 0x66, 0x6f, 0x78, 0x20, 0x6a, 0x75, 0x6d, 0x70, |
| 26 0x73, 0x20, 0x6f, 0x76, 0x65, 0x72, 0x20, 0x74, |
| 27 0x68, 0x65, 0x20, 0x6c, 0x61, 0x7a, 0x79, 0x20, |
| 28 0x64, 0x6f, 0x67, 0x2e]; |
| 29 |
| 30 static final String testDanishPhrase = "Quizdeltagerne spiste jordbær med " + |
| 31 "fløde mens cirkusklovnen Wolther spillede på xylofon."; |
| 32 |
| 33 static final List<int> testDanishUtf8 = const<int>[ |
| 34 0x51, 0x75, 0x69, 0x7a, 0x64, 0x65, 0x6c, 0x74, |
| 35 0x61, 0x67, 0x65, 0x72, 0x6e, 0x65, 0x20, 0x73, |
| 36 0x70, 0x69, 0x73, 0x74, 0x65, 0x20, 0x6a, 0x6f, |
| 37 0x72, 0x64, 0x62, 0xc3, 0xa6, 0x72, 0x20, 0x6d, |
| 38 0x65, 0x64, 0x20, 0x66, 0x6c, 0xc3, 0xb8, 0x64, |
| 39 0x65, 0x20, 0x6d, 0x65, 0x6e, 0x73, 0x20, 0x63, |
| 40 0x69, 0x72, 0x6b, 0x75, 0x73, 0x6b, 0x6c, 0x6f, |
| 41 0x76, 0x6e, 0x65, 0x6e, 0x20, 0x57, 0x6f, 0x6c, |
| 42 0x74, 0x68, 0x65, 0x72, 0x20, 0x73, 0x70, 0x69, |
| 43 0x6c, 0x6c, 0x65, 0x64, 0x65, 0x20, 0x70, 0xc3, |
| 44 0xa5, 0x20, 0x78, 0x79, 0x6c, 0x6f, 0x66, 0x6f, |
| 45 0x6e, 0x2e]; |
| 46 |
| 47 // unusual formatting due to strange editor interaction w/ text direction. |
| 48 static final String |
| 49 testHebrewPhrase = "דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה"; |
| 50 |
| 51 static final List<int> testHebrewUtf8 = const<int>[ |
| 52 0xd7, 0x93, 0xd7, 0x92, 0x20, 0xd7, 0xa1, 0xd7, |
| 53 0xa7, 0xd7, 0xa8, 0xd7, 0x9f, 0x20, 0xd7, 0xa9, |
| 54 0xd7, 0x98, 0x20, 0xd7, 0x91, 0xd7, 0x99, 0xd7, |
| 55 0x9d, 0x20, 0xd7, 0x9e, 0xd7, 0x90, 0xd7, 0x95, |
| 56 0xd7, 0x9b, 0xd7, 0x96, 0xd7, 0x91, 0x20, 0xd7, |
| 57 0x95, 0xd7, 0x9c, 0xd7, 0xa4, 0xd7, 0xaa, 0xd7, |
| 58 0xa2, 0x20, 0xd7, 0x9e, 0xd7, 0xa6, 0xd7, 0x90, |
| 59 0x20, 0xd7, 0x9c, 0xd7, 0x95, 0x20, 0xd7, 0x97, |
| 60 0xd7, 0x91, 0xd7, 0xa8, 0xd7, 0x94, 0x20, 0xd7, |
| 61 0x90, 0xd7, 0x99, 0xd7, 0x9a, 0x20, 0xd7, 0x94, |
| 62 0xd7, 0xa7, 0xd7, 0x9c, 0xd7, 0x99, 0xd7, 0x98, |
| 63 0xd7, 0x94]; |
| 64 |
| 65 static final String testRussianPhrase = "Съешь же ещё этих мягких " + |
| 66 "французских булок да выпей чаю"; |
| 67 |
| 68 static final List<int> testRussianUtf8 = const<int>[ |
| 69 0xd0, 0xa1, 0xd1, 0x8a, 0xd0, 0xb5, 0xd1, 0x88, |
| 70 0xd1, 0x8c, 0x20, 0xd0, 0xb6, 0xd0, 0xb5, 0x20, |
| 71 0xd0, 0xb5, 0xd1, 0x89, 0xd1, 0x91, 0x20, 0xd1, |
| 72 0x8d, 0xd1, 0x82, 0xd0, 0xb8, 0xd1, 0x85, 0x20, |
| 73 0xd0, 0xbc, 0xd1, 0x8f, 0xd0, 0xb3, 0xd0, 0xba, |
| 74 0xd0, 0xb8, 0xd1, 0x85, 0x20, 0xd1, 0x84, 0xd1, |
| 75 0x80, 0xd0, 0xb0, 0xd0, 0xbd, 0xd1, 0x86, 0xd1, |
| 76 0x83, 0xd0, 0xb7, 0xd1, 0x81, 0xd0, 0xba, 0xd0, |
| 77 0xb8, 0xd1, 0x85, 0x20, 0xd0, 0xb1, 0xd1, 0x83, |
| 78 0xd0, 0xbb, 0xd0, 0xbe, 0xd0, 0xba, 0x20, 0xd0, |
| 79 0xb4, 0xd0, 0xb0, 0x20, 0xd0, 0xb2, 0xd1, 0x8b, |
| 80 0xd0, 0xbf, 0xd0, 0xb5, 0xd0, 0xb9, 0x20, 0xd1, |
| 81 0x87, 0xd0, 0xb0, 0xd1, 0x8e]; |
| 82 |
| 83 static final String testGreekPhrase = "Γαζέες καὶ μυρτιὲς δὲν θὰ βρῶ πιὰ " + |
| 84 "στὸ χρυσαφὶ ξέφωτο"; |
| 85 |
| 86 static final List<int> testGreekUtf8 = const<int>[ |
| 87 0xce, 0x93, 0xce, 0xb1, 0xce, 0xb6, 0xce, 0xad, |
| 88 0xce, 0xb5, 0xcf, 0x82, 0x20, 0xce, 0xba, 0xce, |
| 89 0xb1, 0xe1, 0xbd, 0xb6, 0x20, 0xce, 0xbc, 0xcf, |
| 90 0x85, 0xcf, 0x81, 0xcf, 0x84, 0xce, 0xb9, 0xe1, |
| 91 0xbd, 0xb2, 0xcf, 0x82, 0x20, 0xce, 0xb4, 0xe1, |
| 92 0xbd, 0xb2, 0xce, 0xbd, 0x20, 0xce, 0xb8, 0xe1, |
| 93 0xbd, 0xb0, 0x20, 0xce, 0xb2, 0xcf, 0x81, 0xe1, |
| 94 0xbf, 0xb6, 0x20, 0xcf, 0x80, 0xce, 0xb9, 0xe1, |
| 95 0xbd, 0xb0, 0x20, 0xcf, 0x83, 0xcf, 0x84, 0xe1, |
| 96 0xbd, 0xb8, 0x20, 0xcf, 0x87, 0xcf, 0x81, 0xcf, |
| 97 0x85, 0xcf, 0x83, 0xce, 0xb1, 0xcf, 0x86, 0xe1, |
| 98 0xbd, 0xb6, 0x20, 0xce, 0xbe, 0xce, 0xad, 0xcf, |
| 99 0x86, 0xcf, 0x89, 0xcf, 0x84, 0xce, 0xbf]; |
| 100 |
| 101 static final String testKatakanaPhrase = """ |
| 102 イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム |
| 103 ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン"""; |
| 104 |
| 105 static final List<int> testKatakanaUtf8 = const<int>[ |
| 106 0xe3, 0x82, 0xa4, 0xe3, 0x83, 0xad, 0xe3, 0x83, |
| 107 0x8f, 0xe3, 0x83, 0x8b, 0xe3, 0x83, 0x9b, 0xe3, |
| 108 0x83, 0x98, 0xe3, 0x83, 0x88, 0x20, 0xe3, 0x83, |
| 109 0x81, 0xe3, 0x83, 0xaa, 0xe3, 0x83, 0x8c, 0xe3, |
| 110 0x83, 0xab, 0xe3, 0x83, 0xb2, 0x20, 0xe3, 0x83, |
| 111 0xaf, 0xe3, 0x82, 0xab, 0xe3, 0x83, 0xa8, 0xe3, |
| 112 0x82, 0xbf, 0xe3, 0x83, 0xac, 0xe3, 0x82, 0xbd, |
| 113 0x20, 0xe3, 0x83, 0x84, 0xe3, 0x83, 0x8d, 0xe3, |
| 114 0x83, 0x8a, 0xe3, 0x83, 0xa9, 0xe3, 0x83, 0xa0, |
| 115 0x0a, 0xe3, 0x82, 0xa6, 0xe3, 0x83, 0xb0, 0xe3, |
| 116 0x83, 0x8e, 0xe3, 0x82, 0xaa, 0xe3, 0x82, 0xaf, |
| 117 0xe3, 0x83, 0xa4, 0xe3, 0x83, 0x9e, 0x20, 0xe3, |
| 118 0x82, 0xb1, 0xe3, 0x83, 0x95, 0xe3, 0x82, 0xb3, |
| 119 0xe3, 0x82, 0xa8, 0xe3, 0x83, 0x86, 0x20, 0xe3, |
| 120 0x82, 0xa2, 0xe3, 0x82, 0xb5, 0xe3, 0x82, 0xad, |
| 121 0xe3, 0x83, 0xa6, 0xe3, 0x83, 0xa1, 0xe3, 0x83, |
| 122 0x9f, 0xe3, 0x82, 0xb7, 0x20, 0xe3, 0x83, 0xb1, |
| 123 0xe3, 0x83, 0x92, 0xe3, 0x83, 0xa2, 0xe3, 0x82, |
| 124 0xbb, 0xe3, 0x82, 0xb9, 0xe3, 0x83, 0xb3]; |
| 125 |
| 126 void registerTests(TestSuite suite) { |
| 127 register("testUtf8bytesToCodepoints", testUtf8bytesToCodepoints, suite); |
| 128 register("testUtf8BytesToString", testUtf8BytesToString, suite); |
| 129 register("testEncodeToUtf8", testEncodeToUtf8, suite); |
| 130 } |
| 131 |
| 132 void testEncodeToUtf8() { |
| 133 Expect.listEquals(testEnglishUtf8, encodeAsUtf8(testEnglishPhrase), |
| 134 "english to utf8"); |
| 135 |
| 136 Expect.listEquals(testDanishUtf8, encodeAsUtf8(testDanishPhrase), |
| 137 "encode danish to utf8"); |
| 138 |
| 139 Expect.listEquals(testHebrewUtf8, encodeAsUtf8(testHebrewPhrase), |
| 140 "Hebrew to utf8"); |
| 141 |
| 142 Expect.listEquals(testRussianUtf8, encodeAsUtf8(testRussianPhrase), |
| 143 "Russian to utf8"); |
| 144 |
| 145 Expect.listEquals(testGreekUtf8, encodeAsUtf8(testGreekPhrase), |
| 146 "Greek to utf8"); |
| 147 |
| 148 Expect.listEquals(testKatakanaUtf8, encodeAsUtf8(testKatakanaPhrase), |
| 149 "Katakana to utf8"); |
| 150 } |
| 151 |
| 152 void testUtf8bytesToCodepoints() { |
| 153 Expect.listEquals([954, 972, 963, 956, 949], |
| 154 _utf8ToCodepoints([0xce, 0xba, 0xcf, 0x8c, 0xcf, |
| 155 0x83, 0xce, 0xbc, 0xce, 0xb5]), "κόσμε"); |
| 156 |
| 157 // boundary conditions: First possible sequence of a certain length |
| 158 Expect.listEquals([0x0], _utf8ToCodepoints([0x0]), "0"); |
| 159 Expect.listEquals([0x80], _utf8ToCodepoints([0xc2, 0x80]), "80"); |
| 160 Expect.listEquals([0x800], |
| 161 _utf8ToCodepoints([0xe0, 0xa0, 0x80]), "800"); |
| 162 Expect.listEquals([0x10000], |
| 163 _utf8ToCodepoints([0xf0, 0x90, 0x80, 0x80]), "10000"); |
| 164 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 165 _utf8ToCodepoints([0xf8, 0x88, 0x80, 0x80, 0x80]), "200000"); |
| 166 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 167 _utf8ToCodepoints([0xfc, 0x84, 0x80, 0x80, 0x80, 0x80]), |
| 168 "4000000"); |
| 169 |
| 170 // boundary conditions: Last possible sequence of a certain length |
| 171 Expect.listEquals([0x7f], _utf8ToCodepoints([0x7f]), "7f"); |
| 172 Expect.listEquals([0x7ff], _utf8ToCodepoints([0xdf, 0xbf]), "7ff"); |
| 173 Expect.listEquals([0xffff], |
| 174 _utf8ToCodepoints([0xef, 0xbf, 0xbf]), "ffff"); |
| 175 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 176 _utf8ToCodepoints([0xf7, 0xbf, 0xbf, 0xbf]), "1fffff"); |
| 177 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 178 _utf8ToCodepoints([0xfb, 0xbf, 0xbf, 0xbf, 0xbf]), "3ffffff"); |
| 179 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 180 _utf8ToCodepoints([0xfd, 0xbf, 0xbf, 0xbf, 0xbf, 0xbf]), |
| 181 "4000000"); |
| 182 |
| 183 // other boundary conditions |
| 184 Expect.listEquals([0xd7ff], |
| 185 _utf8ToCodepoints([0xed, 0x9f, 0xbf]), "d7ff"); |
| 186 Expect.listEquals([0xe000], |
| 187 _utf8ToCodepoints([0xee, 0x80, 0x80]), "e000"); |
| 188 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 189 _utf8ToCodepoints([0xef, 0xbf, 0xbd]), "fffd"); |
| 190 Expect.listEquals([0x10ffff], |
| 191 _utf8ToCodepoints([0xf4, 0x8f, 0xbf, 0xbf]), "10ffff"); |
| 192 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 193 _utf8ToCodepoints([0xf4, 0x90, 0x80, 0x80]), "110000"); |
| 194 |
| 195 // unexpected continuation bytes |
| 196 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 197 _utf8ToCodepoints([0x80]), "80 => replacement character"); |
| 198 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 199 _utf8ToCodepoints([0xbf]), "bf => replacement character"); |
| 200 |
| 201 List<int> allContinuationBytes = <int>[]; |
| 202 List<int> matchingReplacementChars = <int>[]; |
| 203 for (int i = 0x80; i < 0xc0; i++) { |
| 204 allContinuationBytes.add(i); |
| 205 matchingReplacementChars.add(UNICODE_REPLACEMENT_CHARACTER_CODEPOINT); |
| 206 } |
| 207 Expect.listEquals(matchingReplacementChars, |
| 208 _utf8ToCodepoints(allContinuationBytes), |
| 209 "80 - bf => replacement character x 64"); |
| 210 |
| 211 List<int> allFirstTwoByteSeq = <int>[]; |
| 212 matchingReplacementChars = <int>[]; |
| 213 for (int i = 0xc0; i < 0xe0; i++) { |
| 214 allFirstTwoByteSeq.addAll([i, 0x20]); |
| 215 matchingReplacementChars.addAll( |
| 216 [UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]); |
| 217 } |
| 218 Expect.listEquals(matchingReplacementChars, |
| 219 _utf8ToCodepoints(allFirstTwoByteSeq), |
| 220 "c0 - df + space => replacement character + space x 32"); |
| 221 |
| 222 List<int> allFirstThreeByteSeq = <int>[]; |
| 223 matchingReplacementChars = <int>[]; |
| 224 for (int i = 0xe0; i < 0xf0; i++) { |
| 225 allFirstThreeByteSeq.addAll([i, 0x20]); |
| 226 matchingReplacementChars.addAll( |
| 227 [UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]); |
| 228 } |
| 229 Expect.listEquals(matchingReplacementChars, |
| 230 _utf8ToCodepoints(allFirstThreeByteSeq), |
| 231 "e0 - ef + space => replacement character x 16"); |
| 232 |
| 233 List<int> allFirstFourByteSeq = <int>[]; |
| 234 matchingReplacementChars = <int>[]; |
| 235 for (int i = 0xf0; i < 0xf8; i++) { |
| 236 allFirstFourByteSeq.addAll([i, 0x20]); |
| 237 matchingReplacementChars.addAll( |
| 238 [UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]); |
| 239 } |
| 240 Expect.listEquals(matchingReplacementChars, |
| 241 _utf8ToCodepoints(allFirstFourByteSeq), |
| 242 "f0 - f7 + space => replacement character x 8"); |
| 243 |
| 244 List<int> allFirstFiveByteSeq = <int>[]; |
| 245 matchingReplacementChars = <int>[]; |
| 246 for (int i = 0xf8; i < 0xfc; i++) { |
| 247 allFirstFiveByteSeq.addAll([i, 0x20]); |
| 248 matchingReplacementChars.addAll( |
| 249 [UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]); |
| 250 } |
| 251 Expect.listEquals(matchingReplacementChars, |
| 252 _utf8ToCodepoints(allFirstFiveByteSeq), |
| 253 "f8 - fb + space => replacement character x 4"); |
| 254 |
| 255 List<int> allFirstSixByteSeq = <int>[]; |
| 256 matchingReplacementChars = <int>[]; |
| 257 for (int i = 0xfc; i < 0xfe; i++) { |
| 258 allFirstSixByteSeq.addAll([i, 0x20]); |
| 259 matchingReplacementChars.addAll( |
| 260 [UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]); |
| 261 } |
| 262 Expect.listEquals(matchingReplacementChars, |
| 263 _utf8ToCodepoints(allFirstSixByteSeq), |
| 264 "fc - fd + space => replacement character x 2"); |
| 265 |
| 266 // Sequences with last continuation byte missing |
| 267 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 268 _utf8ToCodepoints([0xc2]), |
| 269 "2-byte sequence with last byte missing"); |
| 270 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 271 _utf8ToCodepoints([0xe0, 0x80]), |
| 272 "3-byte sequence with last byte missing"); |
| 273 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 274 _utf8ToCodepoints([0xf0, 0x80, 0x80]), |
| 275 "4-byte sequence with last byte missing"); |
| 276 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 277 _utf8ToCodepoints([0xf8, 0x88, 0x80, 0x80]), |
| 278 "5-byte sequence with last byte missing"); |
| 279 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 280 _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80]), |
| 281 "6-byte sequence with last byte missing"); |
| 282 |
| 283 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 284 _utf8ToCodepoints([0xdf]), |
| 285 "2-byte sequence with last byte missing (hi)"); |
| 286 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 287 _utf8ToCodepoints([0xef, 0xbf]), |
| 288 "3-byte sequence with last byte missing (hi)"); |
| 289 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 290 _utf8ToCodepoints([0xf7, 0xbf, 0xbf]), |
| 291 "4-byte sequence with last byte missing (hi)"); |
| 292 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 293 _utf8ToCodepoints([0xfb, 0xbf, 0xbf, 0xbf]), |
| 294 "5-byte sequence with last byte missing (hi)"); |
| 295 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 296 _utf8ToCodepoints([0xfd, 0xbf, 0xbf, 0xbf, 0xbf]), |
| 297 "6-byte sequence with last byte missing (hi)"); |
| 298 |
| 299 // Concatenation of incomplete sequences |
| 300 Expect.listEquals( |
| 301 [ UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 302 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 303 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 304 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 305 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 306 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 307 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 308 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 309 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 310 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT ], |
| 311 _utf8ToCodepoints( |
| 312 [ 0xc2, |
| 313 0xe0, 0x80, |
| 314 0xf0, 0x80, 0x80, |
| 315 0xf8, 0x88, 0x80, 0x80, |
| 316 0xfc, 0x80, 0x80, 0x80, 0x80, |
| 317 0xdf, |
| 318 0xef, 0xbf, |
| 319 0xf7, 0xbf, 0xbf, |
| 320 0xfb, 0xbf, 0xbf, 0xbf, |
| 321 0xfd, 0xbf, 0xbf, 0xbf, 0xbf ]), |
| 322 "Concatenation of incomplete sequences"); |
| 323 |
| 324 // Impossible bytes |
| 325 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 326 _utf8ToCodepoints([0xfe]), "fe"); |
| 327 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 328 _utf8ToCodepoints([0xff]), "ff"); |
| 329 Expect.listEquals([ |
| 330 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 331 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 332 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 333 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 334 _utf8ToCodepoints([0xfe, 0xfe, 0xff, 0xff]), "fe fe ff ff"); |
| 335 |
| 336 // Overlong sequences |
| 337 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 338 _utf8ToCodepoints([0xc0, 0xaf]), "c0 af"); |
| 339 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 340 _utf8ToCodepoints([0xe0, 0x80, 0xaf]), "e0 80 af"); |
| 341 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 342 _utf8ToCodepoints([0xf0, 0x80, 0x80, 0xaf]), "f0 80 80 af"); |
| 343 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 344 _utf8ToCodepoints([0xf8, 0x80, 0x80, 0x80, 0xaf]), "f8 80 80 80 af"); |
| 345 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 346 _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80, 0xaf]), |
| 347 "fc 80 80 80 80 af"); |
| 348 |
| 349 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 350 _utf8ToCodepoints([0xc1, 0xbf]), "c1 bf"); |
| 351 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 352 _utf8ToCodepoints([0xe0, 0x9f, 0xbf]), "e0 9f bf"); |
| 353 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 354 _utf8ToCodepoints([0xf0, 0x8f, 0xbf, 0xbf]), "f0 8f bf bf"); |
| 355 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 356 _utf8ToCodepoints([0xf8, 0x87, 0xbf, 0xbf, 0xbf]), "f8 87 bf bf bf"); |
| 357 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 358 _utf8ToCodepoints([0xfc, 0x83, 0xbf, 0xbf, 0xbf, 0xbf]), |
| 359 "fc 83 bf bf bf bf"); |
| 360 |
| 361 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 362 _utf8ToCodepoints([0xc0, 0x80]), "c0 80"); |
| 363 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 364 _utf8ToCodepoints([0xe0, 0x80, 0x80]), "e0 80 80"); |
| 365 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 366 _utf8ToCodepoints([0xf0, 0x80, 0x80, 0x80]), "f0 80 80 80"); |
| 367 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 368 _utf8ToCodepoints([0xf8, 0x80, 0x80, 0x80, 0x80]), "f8 80 80 80 80"); |
| 369 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 370 _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80, 0x80]), |
| 371 "fc 80 80 80 80 80"); |
| 372 |
| 373 // Illegal code positions |
| 374 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 375 _utf8ToCodepoints([0xed, 0xa0, 0x80]), "U+D800"); |
| 376 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 377 _utf8ToCodepoints([0xed, 0xad, 0xbf]), "U+DB7F"); |
| 378 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 379 _utf8ToCodepoints([0xed, 0xae, 0x80]), "U+DB80"); |
| 380 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 381 _utf8ToCodepoints([0xed, 0xaf, 0xbf]), "U+DBFF"); |
| 382 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 383 _utf8ToCodepoints([0xed, 0xb0, 0x80]), "U+DC00"); |
| 384 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 385 _utf8ToCodepoints([0xed, 0xbe, 0x80]), "U+DF80"); |
| 386 Expect.listEquals([UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 387 _utf8ToCodepoints([0xed, 0xbf, 0xbf]), "U+DFFF"); |
| 388 |
| 389 // Paired UTF-16 surrogates |
| 390 Expect.listEquals([ |
| 391 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 392 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 393 _utf8ToCodepoints([0xed, 0xa0, 0x80, 0xed, 0xb0, 0x80]), |
| 394 "U+D800 U+DC00"); |
| 395 Expect.listEquals([ |
| 396 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 397 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 398 _utf8ToCodepoints([0xed, 0xa0, 0x80, 0xed, 0xbf, 0xbf]), |
| 399 "U+D800 U+DFFF"); |
| 400 Expect.listEquals([ |
| 401 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 402 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 403 _utf8ToCodepoints([0xed, 0xad, 0xbf, 0xed, 0xb0, 0x80]), |
| 404 "U+DB7F U+DC00"); |
| 405 Expect.listEquals([ |
| 406 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 407 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 408 _utf8ToCodepoints([0xed, 0xad, 0xbf, 0xed, 0xbf, 0xbf]), |
| 409 "U+DB7F U+DFFF"); |
| 410 Expect.listEquals([ |
| 411 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 412 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 413 _utf8ToCodepoints([0xed, 0xae, 0x80, 0xed, 0xb0, 0x80]), |
| 414 "U+DB80 U+DC00"); |
| 415 Expect.listEquals([ |
| 416 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 417 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 418 _utf8ToCodepoints([0xed, 0xae, 0x80, 0xed, 0xbf, 0xbf]), |
| 419 "U+DB80 U+DFFF"); |
| 420 Expect.listEquals([ |
| 421 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 422 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 423 _utf8ToCodepoints([0xed, 0xaf, 0xbf, 0xed, 0xb0, 0x80]), |
| 424 "U+DBFF U+DC00"); |
| 425 Expect.listEquals([ |
| 426 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT, |
| 427 UNICODE_REPLACEMENT_CHARACTER_CODEPOINT], |
| 428 _utf8ToCodepoints([0xed, 0xaf, 0xbf, 0xed, 0xbf, 0xbf]), |
| 429 "U+DBFF U+DFFF"); |
| 430 |
| 431 // Other illegal code positions (???) |
| 432 Expect.listEquals([0xfffe], _utf8ToCodepoints([0xef, 0xbf, 0xbe]), |
| 433 "U+FFFE"); |
| 434 Expect.listEquals([0xffff], _utf8ToCodepoints([0xef, 0xbf, 0xbf]), |
| 435 "U+FFFF"); |
| 436 } |
| 437 |
| 438 void testUtf8BytesToString() { |
| 439 Expect.stringEquals(testEnglishPhrase, |
| 440 decodeFromUtf8(testEnglishUtf8), "English"); |
| 441 |
| 442 Expect.stringEquals(testDanishPhrase, |
| 443 decodeFromUtf8(testDanishUtf8), "Danish"); |
| 444 |
| 445 Expect.stringEquals(testHebrewPhrase, |
| 446 decodeFromUtf8(testHebrewUtf8), "Hebrew"); |
| 447 |
| 448 Expect.stringEquals(testRussianPhrase, |
| 449 decodeFromUtf8(testRussianUtf8), "Russian"); |
| 450 |
| 451 Expect.stringEquals(testGreekPhrase, |
| 452 decodeFromUtf8(testGreekUtf8), "Greek"); |
| 453 |
| 454 Expect.stringEquals(testKatakanaPhrase, |
| 455 decodeFromUtf8(testKatakanaUtf8), "Katakana"); |
| 456 } |
| 457 } |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 9233041:
String encoding utility methods and tests for Unicode, UTF-8, -16 and -32. (Closed)
Base URL: https://dart.googlecode.com/svn/branches/bleeding_edge/dart