henrike@webrtc.org | f7795df | 2014-05-13 18:00:26 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2004 The WebRTC Project Authors. All rights reserved. |
| 3 | * |
| 4 | * Use of this source code is governed by a BSD-style license |
| 5 | * that can be found in the LICENSE file in the root of the source |
| 6 | * tree. An additional intellectual property rights grant can be found |
| 7 | * in the file PATENTS. All contributing project authors may |
| 8 | * be found in the AUTHORS file in the root of the source tree. |
| 9 | */ |
| 10 | |
| 11 | #include "webrtc/base/common.h" |
| 12 | #include "webrtc/base/gunit.h" |
| 13 | #include "webrtc/base/stringencode.h" |
| 14 | #include "webrtc/base/stringutils.h" |
| 15 | |
| 16 | namespace rtc { |
| 17 | |
| 18 | TEST(Utf8EncodeTest, EncodeDecode) { |
| 19 | const struct Utf8Test { |
| 20 | const char* encoded; |
| 21 | size_t encsize, enclen; |
| 22 | unsigned long decoded; |
| 23 | } kTests[] = { |
| 24 | { "a ", 5, 1, 'a' }, |
| 25 | { "\x7F ", 5, 1, 0x7F }, |
| 26 | { "\xC2\x80 ", 5, 2, 0x80 }, |
| 27 | { "\xDF\xBF ", 5, 2, 0x7FF }, |
| 28 | { "\xE0\xA0\x80 ", 5, 3, 0x800 }, |
| 29 | { "\xEF\xBF\xBF ", 5, 3, 0xFFFF }, |
| 30 | { "\xF0\x90\x80\x80 ", 5, 4, 0x10000 }, |
| 31 | { "\xF0\x90\x80\x80 ", 3, 0, 0x10000 }, |
| 32 | { "\xF0\xF0\x80\x80 ", 5, 0, 0 }, |
| 33 | { "\xF0\x90\x80 ", 5, 0, 0 }, |
| 34 | { "\x90\x80\x80 ", 5, 0, 0 }, |
| 35 | { NULL, 0, 0 }, |
| 36 | }; |
| 37 | for (size_t i = 0; kTests[i].encoded; ++i) { |
| 38 | unsigned long val = 0; |
| 39 | ASSERT_EQ(kTests[i].enclen, utf8_decode(kTests[i].encoded, |
| 40 | kTests[i].encsize, |
| 41 | &val)); |
| 42 | unsigned long result = (kTests[i].enclen == 0) ? 0 : kTests[i].decoded; |
| 43 | ASSERT_EQ(result, val); |
| 44 | |
| 45 | if (kTests[i].decoded == 0) { |
| 46 | // Not an interesting encoding test case |
| 47 | continue; |
| 48 | } |
| 49 | |
| 50 | char buffer[5]; |
| 51 | memset(buffer, 0x01, ARRAY_SIZE(buffer)); |
| 52 | ASSERT_EQ(kTests[i].enclen, utf8_encode(buffer, |
| 53 | kTests[i].encsize, |
| 54 | kTests[i].decoded)); |
| 55 | ASSERT_TRUE(memcmp(buffer, kTests[i].encoded, kTests[i].enclen) == 0); |
| 56 | // Make sure remainder of buffer is unchanged |
| 57 | ASSERT_TRUE(memory_check(buffer + kTests[i].enclen, |
| 58 | 0x1, |
| 59 | ARRAY_SIZE(buffer) - kTests[i].enclen)); |
| 60 | } |
| 61 | } |
| 62 | |
| 63 | class HexEncodeTest : public testing::Test { |
| 64 | public: |
| 65 | HexEncodeTest() : enc_res_(0), dec_res_(0) { |
| 66 | for (size_t i = 0; i < sizeof(data_); ++i) { |
| 67 | data_[i] = (i + 128) & 0xff; |
| 68 | } |
| 69 | memset(decoded_, 0x7f, sizeof(decoded_)); |
| 70 | } |
| 71 | |
| 72 | char data_[10]; |
| 73 | char encoded_[31]; |
| 74 | char decoded_[11]; |
| 75 | size_t enc_res_; |
| 76 | size_t dec_res_; |
| 77 | }; |
| 78 | |
| 79 | // Test that we can convert to/from hex with no delimiter. |
| 80 | TEST_F(HexEncodeTest, TestWithNoDelimiter) { |
| 81 | enc_res_ = hex_encode(encoded_, sizeof(encoded_), data_, sizeof(data_)); |
| 82 | ASSERT_EQ(sizeof(data_) * 2, enc_res_); |
| 83 | ASSERT_STREQ("80818283848586878889", encoded_); |
| 84 | dec_res_ = hex_decode(decoded_, sizeof(decoded_), encoded_, enc_res_); |
| 85 | ASSERT_EQ(sizeof(data_), dec_res_); |
| 86 | ASSERT_EQ(0, memcmp(data_, decoded_, dec_res_)); |
| 87 | } |
| 88 | |
| 89 | // Test that we can convert to/from hex with a colon delimiter. |
| 90 | TEST_F(HexEncodeTest, TestWithDelimiter) { |
| 91 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(encoded_), |
| 92 | data_, sizeof(data_), ':'); |
| 93 | ASSERT_EQ(sizeof(data_) * 3 - 1, enc_res_); |
| 94 | ASSERT_STREQ("80:81:82:83:84:85:86:87:88:89", encoded_); |
| 95 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), |
| 96 | encoded_, enc_res_, ':'); |
| 97 | ASSERT_EQ(sizeof(data_), dec_res_); |
| 98 | ASSERT_EQ(0, memcmp(data_, decoded_, dec_res_)); |
| 99 | } |
| 100 | |
| 101 | // Test that encoding with one delimiter and decoding with another fails. |
| 102 | TEST_F(HexEncodeTest, TestWithWrongDelimiter) { |
| 103 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(encoded_), |
| 104 | data_, sizeof(data_), ':'); |
| 105 | ASSERT_EQ(sizeof(data_) * 3 - 1, enc_res_); |
| 106 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), |
| 107 | encoded_, enc_res_, '/'); |
| 108 | ASSERT_EQ(0U, dec_res_); |
| 109 | } |
| 110 | |
| 111 | // Test that encoding without a delimiter and decoding with one fails. |
| 112 | TEST_F(HexEncodeTest, TestExpectedDelimiter) { |
| 113 | enc_res_ = hex_encode(encoded_, sizeof(encoded_), data_, sizeof(data_)); |
| 114 | ASSERT_EQ(sizeof(data_) * 2, enc_res_); |
| 115 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), |
| 116 | encoded_, enc_res_, ':'); |
| 117 | ASSERT_EQ(0U, dec_res_); |
| 118 | } |
| 119 | |
| 120 | // Test that encoding with a delimiter and decoding without one fails. |
| 121 | TEST_F(HexEncodeTest, TestExpectedNoDelimiter) { |
| 122 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(encoded_), |
| 123 | data_, sizeof(data_), ':'); |
| 124 | ASSERT_EQ(sizeof(data_) * 3 - 1, enc_res_); |
| 125 | dec_res_ = hex_decode(decoded_, sizeof(decoded_), encoded_, enc_res_); |
| 126 | ASSERT_EQ(0U, dec_res_); |
| 127 | } |
| 128 | |
| 129 | // Test that we handle a zero-length buffer with no delimiter. |
| 130 | TEST_F(HexEncodeTest, TestZeroLengthNoDelimiter) { |
| 131 | enc_res_ = hex_encode(encoded_, sizeof(encoded_), "", 0); |
| 132 | ASSERT_EQ(0U, enc_res_); |
| 133 | dec_res_ = hex_decode(decoded_, sizeof(decoded_), encoded_, enc_res_); |
| 134 | ASSERT_EQ(0U, dec_res_); |
| 135 | } |
| 136 | |
| 137 | // Test that we handle a zero-length buffer with a delimiter. |
| 138 | TEST_F(HexEncodeTest, TestZeroLengthWithDelimiter) { |
| 139 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(encoded_), "", 0, ':'); |
| 140 | ASSERT_EQ(0U, enc_res_); |
| 141 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), |
| 142 | encoded_, enc_res_, ':'); |
| 143 | ASSERT_EQ(0U, dec_res_); |
| 144 | } |
| 145 | |
| 146 | // Test the std::string variants that take no delimiter. |
| 147 | TEST_F(HexEncodeTest, TestHelpersNoDelimiter) { |
| 148 | std::string result = hex_encode(data_, sizeof(data_)); |
| 149 | ASSERT_EQ("80818283848586878889", result); |
| 150 | dec_res_ = hex_decode(decoded_, sizeof(decoded_), result); |
| 151 | ASSERT_EQ(sizeof(data_), dec_res_); |
| 152 | ASSERT_EQ(0, memcmp(data_, decoded_, dec_res_)); |
| 153 | } |
| 154 | |
| 155 | // Test the std::string variants that use a delimiter. |
| 156 | TEST_F(HexEncodeTest, TestHelpersWithDelimiter) { |
| 157 | std::string result = hex_encode_with_delimiter(data_, sizeof(data_), ':'); |
| 158 | ASSERT_EQ("80:81:82:83:84:85:86:87:88:89", result); |
| 159 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), result, ':'); |
| 160 | ASSERT_EQ(sizeof(data_), dec_res_); |
| 161 | ASSERT_EQ(0, memcmp(data_, decoded_, dec_res_)); |
| 162 | } |
| 163 | |
| 164 | // Test that encoding into a too-small output buffer (without delimiter) fails. |
| 165 | TEST_F(HexEncodeTest, TestEncodeTooShort) { |
| 166 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(data_) * 2, |
| 167 | data_, sizeof(data_), 0); |
| 168 | ASSERT_EQ(0U, enc_res_); |
| 169 | } |
| 170 | |
| 171 | // Test that encoding into a too-small output buffer (with delimiter) fails. |
| 172 | TEST_F(HexEncodeTest, TestEncodeWithDelimiterTooShort) { |
| 173 | enc_res_ = hex_encode_with_delimiter(encoded_, sizeof(data_) * 3 - 1, |
| 174 | data_, sizeof(data_), ':'); |
| 175 | ASSERT_EQ(0U, enc_res_); |
| 176 | } |
| 177 | |
| 178 | // Test that decoding into a too-small output buffer fails. |
| 179 | TEST_F(HexEncodeTest, TestDecodeTooShort) { |
| 180 | dec_res_ = hex_decode_with_delimiter(decoded_, 4, "0123456789", 10, 0); |
| 181 | ASSERT_EQ(0U, dec_res_); |
| 182 | ASSERT_EQ(0x7f, decoded_[4]); |
| 183 | } |
| 184 | |
| 185 | // Test that decoding non-hex data fails. |
| 186 | TEST_F(HexEncodeTest, TestDecodeBogusData) { |
| 187 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), "xyz", 3, 0); |
| 188 | ASSERT_EQ(0U, dec_res_); |
| 189 | } |
| 190 | |
| 191 | // Test that decoding an odd number of hex characters fails. |
| 192 | TEST_F(HexEncodeTest, TestDecodeOddHexDigits) { |
| 193 | dec_res_ = hex_decode_with_delimiter(decoded_, sizeof(decoded_), "012", 3, 0); |
| 194 | ASSERT_EQ(0U, dec_res_); |
| 195 | } |
| 196 | |
| 197 | // Test that decoding a string with too many delimiters fails. |
| 198 | TEST_F(HexEncodeTest, TestDecodeWithDelimiterTooManyDelimiters) { |
| 199 | dec_res_ = hex_decode_with_delimiter(decoded_, 4, "01::23::45::67", 14, ':'); |
| 200 | ASSERT_EQ(0U, dec_res_); |
| 201 | } |
| 202 | |
| 203 | // Test that decoding a string with a leading delimiter fails. |
| 204 | TEST_F(HexEncodeTest, TestDecodeWithDelimiterLeadingDelimiter) { |
| 205 | dec_res_ = hex_decode_with_delimiter(decoded_, 4, ":01:23:45:67", 12, ':'); |
| 206 | ASSERT_EQ(0U, dec_res_); |
| 207 | } |
| 208 | |
| 209 | // Test that decoding a string with a trailing delimiter fails. |
| 210 | TEST_F(HexEncodeTest, TestDecodeWithDelimiterTrailingDelimiter) { |
| 211 | dec_res_ = hex_decode_with_delimiter(decoded_, 4, "01:23:45:67:", 12, ':'); |
| 212 | ASSERT_EQ(0U, dec_res_); |
| 213 | } |
| 214 | |
| 215 | // Tests counting substrings. |
| 216 | TEST(TokenizeTest, CountSubstrings) { |
| 217 | std::vector<std::string> fields; |
| 218 | |
| 219 | EXPECT_EQ(5ul, tokenize("one two three four five", ' ', &fields)); |
| 220 | fields.clear(); |
| 221 | EXPECT_EQ(1ul, tokenize("one", ' ', &fields)); |
| 222 | |
| 223 | // Extra spaces should be ignored. |
| 224 | fields.clear(); |
| 225 | EXPECT_EQ(5ul, tokenize(" one two three four five ", ' ', &fields)); |
| 226 | fields.clear(); |
| 227 | EXPECT_EQ(1ul, tokenize(" one ", ' ', &fields)); |
| 228 | fields.clear(); |
| 229 | EXPECT_EQ(0ul, tokenize(" ", ' ', &fields)); |
| 230 | } |
| 231 | |
| 232 | // Tests comparing substrings. |
| 233 | TEST(TokenizeTest, CompareSubstrings) { |
| 234 | std::vector<std::string> fields; |
| 235 | |
| 236 | tokenize("find middle one", ' ', &fields); |
| 237 | ASSERT_EQ(3ul, fields.size()); |
| 238 | ASSERT_STREQ("middle", fields.at(1).c_str()); |
| 239 | fields.clear(); |
| 240 | |
| 241 | // Extra spaces should be ignored. |
| 242 | tokenize(" find middle one ", ' ', &fields); |
| 243 | ASSERT_EQ(3ul, fields.size()); |
| 244 | ASSERT_STREQ("middle", fields.at(1).c_str()); |
| 245 | fields.clear(); |
| 246 | tokenize(" ", ' ', &fields); |
| 247 | ASSERT_EQ(0ul, fields.size()); |
| 248 | } |
| 249 | |
| 250 | TEST(TokenizeTest, TokenizeAppend) { |
| 251 | ASSERT_EQ(0ul, tokenize_append("A B C", ' ', NULL)); |
| 252 | |
| 253 | std::vector<std::string> fields; |
| 254 | |
| 255 | tokenize_append("A B C", ' ', &fields); |
| 256 | ASSERT_EQ(3ul, fields.size()); |
| 257 | ASSERT_STREQ("B", fields.at(1).c_str()); |
| 258 | |
| 259 | tokenize_append("D E", ' ', &fields); |
| 260 | ASSERT_EQ(5ul, fields.size()); |
| 261 | ASSERT_STREQ("B", fields.at(1).c_str()); |
| 262 | ASSERT_STREQ("E", fields.at(4).c_str()); |
| 263 | } |
| 264 | |
| 265 | TEST(TokenizeTest, TokenizeWithMarks) { |
| 266 | ASSERT_EQ(0ul, tokenize("D \"A B", ' ', '(', ')', NULL)); |
| 267 | |
| 268 | std::vector<std::string> fields; |
| 269 | tokenize("A B C", ' ', '"', '"', &fields); |
| 270 | ASSERT_EQ(3ul, fields.size()); |
| 271 | ASSERT_STREQ("C", fields.at(2).c_str()); |
| 272 | |
| 273 | tokenize("\"A B\" C", ' ', '"', '"', &fields); |
| 274 | ASSERT_EQ(2ul, fields.size()); |
| 275 | ASSERT_STREQ("A B", fields.at(0).c_str()); |
| 276 | |
| 277 | tokenize("D \"A B\" C", ' ', '"', '"', &fields); |
| 278 | ASSERT_EQ(3ul, fields.size()); |
| 279 | ASSERT_STREQ("D", fields.at(0).c_str()); |
| 280 | ASSERT_STREQ("A B", fields.at(1).c_str()); |
| 281 | |
| 282 | tokenize("D \"A B\" C \"E F\"", ' ', '"', '"', &fields); |
| 283 | ASSERT_EQ(4ul, fields.size()); |
| 284 | ASSERT_STREQ("D", fields.at(0).c_str()); |
| 285 | ASSERT_STREQ("A B", fields.at(1).c_str()); |
| 286 | ASSERT_STREQ("E F", fields.at(3).c_str()); |
| 287 | |
| 288 | // No matching marks. |
| 289 | tokenize("D \"A B", ' ', '"', '"', &fields); |
| 290 | ASSERT_EQ(3ul, fields.size()); |
| 291 | ASSERT_STREQ("D", fields.at(0).c_str()); |
| 292 | ASSERT_STREQ("\"A", fields.at(1).c_str()); |
| 293 | |
| 294 | tokenize("D (A B) C (E F) G", ' ', '(', ')', &fields); |
| 295 | ASSERT_EQ(5ul, fields.size()); |
| 296 | ASSERT_STREQ("D", fields.at(0).c_str()); |
| 297 | ASSERT_STREQ("A B", fields.at(1).c_str()); |
| 298 | ASSERT_STREQ("E F", fields.at(3).c_str()); |
| 299 | } |
| 300 | |
| 301 | // Tests counting substrings. |
| 302 | TEST(SplitTest, CountSubstrings) { |
| 303 | std::vector<std::string> fields; |
| 304 | |
| 305 | EXPECT_EQ(5ul, split("one,two,three,four,five", ',', &fields)); |
| 306 | fields.clear(); |
| 307 | EXPECT_EQ(1ul, split("one", ',', &fields)); |
| 308 | |
| 309 | // Empty fields between commas count. |
| 310 | fields.clear(); |
| 311 | EXPECT_EQ(5ul, split("one,,three,four,five", ',', &fields)); |
| 312 | fields.clear(); |
| 313 | EXPECT_EQ(3ul, split(",three,", ',', &fields)); |
| 314 | fields.clear(); |
| 315 | EXPECT_EQ(1ul, split("", ',', &fields)); |
| 316 | } |
| 317 | |
| 318 | // Tests comparing substrings. |
| 319 | TEST(SplitTest, CompareSubstrings) { |
| 320 | std::vector<std::string> fields; |
| 321 | |
| 322 | split("find,middle,one", ',', &fields); |
| 323 | ASSERT_EQ(3ul, fields.size()); |
| 324 | ASSERT_STREQ("middle", fields.at(1).c_str()); |
| 325 | fields.clear(); |
| 326 | |
| 327 | // Empty fields between commas count. |
| 328 | split("find,,middle,one", ',', &fields); |
| 329 | ASSERT_EQ(4ul, fields.size()); |
| 330 | ASSERT_STREQ("middle", fields.at(2).c_str()); |
| 331 | fields.clear(); |
| 332 | split("", ',', &fields); |
| 333 | ASSERT_EQ(1ul, fields.size()); |
| 334 | ASSERT_STREQ("", fields.at(0).c_str()); |
| 335 | } |
| 336 | |
| 337 | TEST(BoolTest, DecodeValid) { |
| 338 | bool value; |
| 339 | EXPECT_TRUE(FromString("true", &value)); |
| 340 | EXPECT_TRUE(value); |
| 341 | EXPECT_TRUE(FromString("true,", &value)); |
| 342 | EXPECT_TRUE(value); |
| 343 | EXPECT_TRUE(FromString("true , true", &value)); |
| 344 | EXPECT_TRUE(value); |
| 345 | EXPECT_TRUE(FromString("true ,\n false", &value)); |
| 346 | EXPECT_TRUE(value); |
| 347 | EXPECT_TRUE(FromString(" true \n", &value)); |
| 348 | EXPECT_TRUE(value); |
| 349 | |
| 350 | EXPECT_TRUE(FromString("false", &value)); |
| 351 | EXPECT_FALSE(value); |
| 352 | EXPECT_TRUE(FromString(" false ", &value)); |
| 353 | EXPECT_FALSE(value); |
| 354 | EXPECT_TRUE(FromString(" false, ", &value)); |
| 355 | EXPECT_FALSE(value); |
| 356 | |
| 357 | EXPECT_TRUE(FromString<bool>("true\n")); |
| 358 | EXPECT_FALSE(FromString<bool>("false\n")); |
| 359 | } |
| 360 | |
| 361 | TEST(BoolTest, DecodeInvalid) { |
| 362 | bool value; |
| 363 | EXPECT_FALSE(FromString("True", &value)); |
| 364 | EXPECT_FALSE(FromString("TRUE", &value)); |
| 365 | EXPECT_FALSE(FromString("False", &value)); |
| 366 | EXPECT_FALSE(FromString("FALSE", &value)); |
| 367 | EXPECT_FALSE(FromString("0", &value)); |
| 368 | EXPECT_FALSE(FromString("1", &value)); |
| 369 | EXPECT_FALSE(FromString("0,", &value)); |
| 370 | EXPECT_FALSE(FromString("1,", &value)); |
| 371 | EXPECT_FALSE(FromString("1,0", &value)); |
| 372 | EXPECT_FALSE(FromString("1.", &value)); |
| 373 | EXPECT_FALSE(FromString("1.0", &value)); |
| 374 | EXPECT_FALSE(FromString("", &value)); |
| 375 | EXPECT_FALSE(FromString<bool>("false\nfalse")); |
| 376 | } |
| 377 | |
| 378 | TEST(BoolTest, RoundTrip) { |
| 379 | bool value; |
| 380 | EXPECT_TRUE(FromString(ToString(true), &value)); |
| 381 | EXPECT_TRUE(value); |
| 382 | EXPECT_TRUE(FromString(ToString(false), &value)); |
| 383 | EXPECT_FALSE(value); |
| 384 | } |
| 385 | } // namespace rtc |