string_util_unittest.cc 41.9 KB
Newer Older
gejun's avatar
gejun committed
1 2 3 4
// Copyright 2013 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

5
#include "butil/strings/string_util.h"
gejun's avatar
gejun committed
6 7 8 9 10 11

#include <math.h>
#include <stdarg.h>

#include <algorithm>

12 13 14
#include "butil/basictypes.h"
#include "butil/strings/string16.h"
#include "butil/strings/utf_string_conversions.h"
gejun's avatar
gejun committed
15 16
#include <gtest/gtest.h>

17
namespace butil {
gejun's avatar
gejun committed
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725

static const struct trim_case {
  const wchar_t* input;
  const TrimPositions positions;
  const wchar_t* output;
  const TrimPositions return_value;
} trim_cases[] = {
  {L" Google Video ", TRIM_LEADING, L"Google Video ", TRIM_LEADING},
  {L" Google Video ", TRIM_TRAILING, L" Google Video", TRIM_TRAILING},
  {L" Google Video ", TRIM_ALL, L"Google Video", TRIM_ALL},
  {L"Google Video", TRIM_ALL, L"Google Video", TRIM_NONE},
  {L"", TRIM_ALL, L"", TRIM_NONE},
  {L"  ", TRIM_LEADING, L"", TRIM_LEADING},
  {L"  ", TRIM_TRAILING, L"", TRIM_TRAILING},
  {L"  ", TRIM_ALL, L"", TRIM_ALL},
  {L"\t\rTest String\n", TRIM_ALL, L"Test String", TRIM_ALL},
  {L"\x2002Test String\x00A0\x3000", TRIM_ALL, L"Test String", TRIM_ALL},
};

static const struct trim_case_ascii {
  const char* input;
  const TrimPositions positions;
  const char* output;
  const TrimPositions return_value;
} trim_cases_ascii[] = {
  {" Google Video ", TRIM_LEADING, "Google Video ", TRIM_LEADING},
  {" Google Video ", TRIM_TRAILING, " Google Video", TRIM_TRAILING},
  {" Google Video ", TRIM_ALL, "Google Video", TRIM_ALL},
  {"Google Video", TRIM_ALL, "Google Video", TRIM_NONE},
  {"", TRIM_ALL, "", TRIM_NONE},
  {"  ", TRIM_LEADING, "", TRIM_LEADING},
  {"  ", TRIM_TRAILING, "", TRIM_TRAILING},
  {"  ", TRIM_ALL, "", TRIM_ALL},
  {"\t\rTest String\n", TRIM_ALL, "Test String", TRIM_ALL},
};

namespace {

// Helper used to test TruncateUTF8ToByteSize.
bool Truncated(const std::string& input, const size_t byte_size,
               std::string* output) {
    size_t prev = input.length();
    TruncateUTF8ToByteSize(input, byte_size, output);
    return prev != output->length();
}

}  // namespace

TEST(StringUtilTest, TruncateUTF8ToByteSize) {
  std::string output;

  // Empty strings and invalid byte_size arguments
  EXPECT_FALSE(Truncated(std::string(), 0, &output));
  EXPECT_EQ(output, "");
  EXPECT_TRUE(Truncated("\xe1\x80\xbf", 0, &output));
  EXPECT_EQ(output, "");
  EXPECT_FALSE(Truncated("\xe1\x80\xbf", (size_t)-1, &output));
  EXPECT_FALSE(Truncated("\xe1\x80\xbf", 4, &output));

  // Testing the truncation of valid UTF8 correctly
  EXPECT_TRUE(Truncated("abc", 2, &output));
  EXPECT_EQ(output, "ab");
  EXPECT_TRUE(Truncated("\xc2\x81\xc2\x81", 2, &output));
  EXPECT_EQ(output.compare("\xc2\x81"), 0);
  EXPECT_TRUE(Truncated("\xc2\x81\xc2\x81", 3, &output));
  EXPECT_EQ(output.compare("\xc2\x81"), 0);
  EXPECT_FALSE(Truncated("\xc2\x81\xc2\x81", 4, &output));
  EXPECT_EQ(output.compare("\xc2\x81\xc2\x81"), 0);

  {
    const char array[] = "\x00\x00\xc2\x81\xc2\x81";
    const std::string array_string(array, arraysize(array));
    EXPECT_TRUE(Truncated(array_string, 4, &output));
    EXPECT_EQ(output.compare(std::string("\x00\x00\xc2\x81", 4)), 0);
  }

  {
    const char array[] = "\x00\xc2\x81\xc2\x81";
    const std::string array_string(array, arraysize(array));
    EXPECT_TRUE(Truncated(array_string, 4, &output));
    EXPECT_EQ(output.compare(std::string("\x00\xc2\x81", 3)), 0);
  }

  // Testing invalid UTF8
  EXPECT_TRUE(Truncated("\xed\xa0\x80\xed\xbf\xbf", 6, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xed\xa0\x8f", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xed\xbf\xbf", 3, &output));
  EXPECT_EQ(output.compare(""), 0);

  // Testing invalid UTF8 mixed with valid UTF8
  EXPECT_FALSE(Truncated("\xe1\x80\xbf", 3, &output));
  EXPECT_EQ(output.compare("\xe1\x80\xbf"), 0);
  EXPECT_FALSE(Truncated("\xf1\x80\xa0\xbf", 4, &output));
  EXPECT_EQ(output.compare("\xf1\x80\xa0\xbf"), 0);
  EXPECT_FALSE(Truncated("a\xc2\x81\xe1\x80\xbf\xf1\x80\xa0\xbf",
              10, &output));
  EXPECT_EQ(output.compare("a\xc2\x81\xe1\x80\xbf\xf1\x80\xa0\xbf"), 0);
  EXPECT_TRUE(Truncated("a\xc2\x81\xe1\x80\xbf\xf1""a""\x80\xa0",
              10, &output));
  EXPECT_EQ(output.compare("a\xc2\x81\xe1\x80\xbf\xf1""a"), 0);
  EXPECT_FALSE(Truncated("\xef\xbb\xbf" "abc", 6, &output));
  EXPECT_EQ(output.compare("\xef\xbb\xbf" "abc"), 0);

  // Overlong sequences
  EXPECT_TRUE(Truncated("\xc0\x80", 2, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xc1\x80\xc1\x81", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xe0\x80\x80", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xe0\x82\x80", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xe0\x9f\xbf", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf0\x80\x80\x8D", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf0\x80\x82\x91", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf0\x80\xa0\x80", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf0\x8f\xbb\xbf", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf8\x80\x80\x80\xbf", 5, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xfc\x80\x80\x80\xa0\xa5", 6, &output));
  EXPECT_EQ(output.compare(""), 0);

  // Beyond U+10FFFF (the upper limit of Unicode codespace)
  EXPECT_TRUE(Truncated("\xf4\x90\x80\x80", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf8\xa0\xbf\x80\xbf", 5, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xfc\x9c\xbf\x80\xbf\x80", 6, &output));
  EXPECT_EQ(output.compare(""), 0);

  // BOMs in UTF-16(BE|LE) and UTF-32(BE|LE)
  EXPECT_TRUE(Truncated("\xfe\xff", 2, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xff\xfe", 2, &output));
  EXPECT_EQ(output.compare(""), 0);

  {
    const char array[] = "\x00\x00\xfe\xff";
    const std::string array_string(array, arraysize(array));
    EXPECT_TRUE(Truncated(array_string, 4, &output));
    EXPECT_EQ(output.compare(std::string("\x00\x00", 2)), 0);
  }

  // Variants on the previous test
  {
    const char array[] = "\xff\xfe\x00\x00";
    const std::string array_string(array, 4);
    EXPECT_FALSE(Truncated(array_string, 4, &output));
    EXPECT_EQ(output.compare(std::string("\xff\xfe\x00\x00", 4)), 0);
  }
  {
    const char array[] = "\xff\x00\x00\xfe";
    const std::string array_string(array, arraysize(array));
    EXPECT_TRUE(Truncated(array_string, 4, &output));
    EXPECT_EQ(output.compare(std::string("\xff\x00\x00", 3)), 0);
  }

  // Non-characters : U+xxFFF[EF] where xx is 0x00 through 0x10 and <FDD0,FDEF>
  EXPECT_TRUE(Truncated("\xef\xbf\xbe", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf0\x8f\xbf\xbe", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xf3\xbf\xbf\xbf", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xef\xb7\x90", 3, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_TRUE(Truncated("\xef\xb7\xaf", 3, &output));
  EXPECT_EQ(output.compare(""), 0);

  // Strings in legacy encodings that are valid in UTF-8, but
  // are invalid as UTF-8 in real data.
  EXPECT_TRUE(Truncated("caf\xe9", 4, &output));
  EXPECT_EQ(output.compare("caf"), 0);
  EXPECT_TRUE(Truncated("\xb0\xa1\xb0\xa2", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
  EXPECT_FALSE(Truncated("\xa7\x41\xa6\x6e", 4, &output));
  EXPECT_EQ(output.compare("\xa7\x41\xa6\x6e"), 0);
  EXPECT_TRUE(Truncated("\xa7\x41\xa6\x6e\xd9\xee\xe4\xee", 7,
              &output));
  EXPECT_EQ(output.compare("\xa7\x41\xa6\x6e"), 0);

  // Testing using the same string as input and output.
  EXPECT_FALSE(Truncated(output, 4, &output));
  EXPECT_EQ(output.compare("\xa7\x41\xa6\x6e"), 0);
  EXPECT_TRUE(Truncated(output, 3, &output));
  EXPECT_EQ(output.compare("\xa7\x41"), 0);

  // "abc" with U+201[CD] in windows-125[0-8]
  EXPECT_TRUE(Truncated("\x93" "abc\x94", 5, &output));
  EXPECT_EQ(output.compare("\x93" "abc"), 0);

  // U+0639 U+064E U+0644 U+064E in ISO-8859-6
  EXPECT_TRUE(Truncated("\xd9\xee\xe4\xee", 4, &output));
  EXPECT_EQ(output.compare(""), 0);

  // U+03B3 U+03B5 U+03B9 U+03AC in ISO-8859-7
  EXPECT_TRUE(Truncated("\xe3\xe5\xe9\xdC", 4, &output));
  EXPECT_EQ(output.compare(""), 0);
}

TEST(StringUtilTest, TrimWhitespace) {
  string16 output;  // Allow contents to carry over to next testcase
  for (size_t i = 0; i < arraysize(trim_cases); ++i) {
    const trim_case& value = trim_cases[i];
    EXPECT_EQ(value.return_value,
              TrimWhitespace(WideToUTF16(value.input), value.positions,
                             &output));
    EXPECT_EQ(WideToUTF16(value.output), output);
  }

  // Test that TrimWhitespace() can take the same string for input and output
  output = ASCIIToUTF16("  This is a test \r\n");
  EXPECT_EQ(TRIM_ALL, TrimWhitespace(output, TRIM_ALL, &output));
  EXPECT_EQ(ASCIIToUTF16("This is a test"), output);

  // Once more, but with a string of whitespace
  output = ASCIIToUTF16("  \r\n");
  EXPECT_EQ(TRIM_ALL, TrimWhitespace(output, TRIM_ALL, &output));
  EXPECT_EQ(string16(), output);

  std::string output_ascii;
  for (size_t i = 0; i < arraysize(trim_cases_ascii); ++i) {
    const trim_case_ascii& value = trim_cases_ascii[i];
    EXPECT_EQ(value.return_value,
              TrimWhitespace(value.input, value.positions, &output_ascii));
    EXPECT_EQ(value.output, output_ascii);
  }
}

static const struct collapse_case {
  const wchar_t* input;
  const bool trim;
  const wchar_t* output;
} collapse_cases[] = {
  {L" Google Video ", false, L"Google Video"},
  {L"Google Video", false, L"Google Video"},
  {L"", false, L""},
  {L"  ", false, L""},
  {L"\t\rTest String\n", false, L"Test String"},
  {L"\x2002Test String\x00A0\x3000", false, L"Test String"},
  {L"    Test     \n  \t String    ", false, L"Test String"},
  {L"\x2002Test\x1680 \x2028 \tString\x00A0\x3000", false, L"Test String"},
  {L"   Test String", false, L"Test String"},
  {L"Test String    ", false, L"Test String"},
  {L"Test String", false, L"Test String"},
  {L"", true, L""},
  {L"\n", true, L""},
  {L"  \r  ", true, L""},
  {L"\nFoo", true, L"Foo"},
  {L"\r  Foo  ", true, L"Foo"},
  {L" Foo bar ", true, L"Foo bar"},
  {L"  \tFoo  bar  \n", true, L"Foo bar"},
  {L" a \r b\n c \r\n d \t\re \t f \n ", true, L"abcde f"},
};

TEST(StringUtilTest, CollapseWhitespace) {
  for (size_t i = 0; i < arraysize(collapse_cases); ++i) {
    const collapse_case& value = collapse_cases[i];
    EXPECT_EQ(WideToUTF16(value.output),
              CollapseWhitespace(WideToUTF16(value.input), value.trim));
  }
}

static const struct collapse_case_ascii {
  const char* input;
  const bool trim;
  const char* output;
} collapse_cases_ascii[] = {
  {" Google Video ", false, "Google Video"},
  {"Google Video", false, "Google Video"},
  {"", false, ""},
  {"  ", false, ""},
  {"\t\rTest String\n", false, "Test String"},
  {"    Test     \n  \t String    ", false, "Test String"},
  {"   Test String", false, "Test String"},
  {"Test String    ", false, "Test String"},
  {"Test String", false, "Test String"},
  {"", true, ""},
  {"\n", true, ""},
  {"  \r  ", true, ""},
  {"\nFoo", true, "Foo"},
  {"\r  Foo  ", true, "Foo"},
  {" Foo bar ", true, "Foo bar"},
  {"  \tFoo  bar  \n", true, "Foo bar"},
  {" a \r b\n c \r\n d \t\re \t f \n ", true, "abcde f"},
};

TEST(StringUtilTest, CollapseWhitespaceASCII) {
  for (size_t i = 0; i < arraysize(collapse_cases_ascii); ++i) {
    const collapse_case_ascii& value = collapse_cases_ascii[i];
    EXPECT_EQ(value.output, CollapseWhitespaceASCII(value.input, value.trim));
  }
}

TEST(StringUtilTest, IsStringUTF8) {
  EXPECT_TRUE(IsStringUTF8("abc"));
  EXPECT_TRUE(IsStringUTF8("\xc2\x81"));
  EXPECT_TRUE(IsStringUTF8("\xe1\x80\xbf"));
  EXPECT_TRUE(IsStringUTF8("\xf1\x80\xa0\xbf"));
  EXPECT_TRUE(IsStringUTF8("a\xc2\x81\xe1\x80\xbf\xf1\x80\xa0\xbf"));
  EXPECT_TRUE(IsStringUTF8("\xef\xbb\xbf" "abc"));  // UTF-8 BOM

  // surrogate code points
  EXPECT_FALSE(IsStringUTF8("\xed\xa0\x80\xed\xbf\xbf"));
  EXPECT_FALSE(IsStringUTF8("\xed\xa0\x8f"));
  EXPECT_FALSE(IsStringUTF8("\xed\xbf\xbf"));

  // overlong sequences
  EXPECT_FALSE(IsStringUTF8("\xc0\x80"));  // U+0000
  EXPECT_FALSE(IsStringUTF8("\xc1\x80\xc1\x81"));  // "AB"
  EXPECT_FALSE(IsStringUTF8("\xe0\x80\x80"));  // U+0000
  EXPECT_FALSE(IsStringUTF8("\xe0\x82\x80"));  // U+0080
  EXPECT_FALSE(IsStringUTF8("\xe0\x9f\xbf"));  // U+07ff
  EXPECT_FALSE(IsStringUTF8("\xf0\x80\x80\x8D"));  // U+000D
  EXPECT_FALSE(IsStringUTF8("\xf0\x80\x82\x91"));  // U+0091
  EXPECT_FALSE(IsStringUTF8("\xf0\x80\xa0\x80"));  // U+0800
  EXPECT_FALSE(IsStringUTF8("\xf0\x8f\xbb\xbf"));  // U+FEFF (BOM)
  EXPECT_FALSE(IsStringUTF8("\xf8\x80\x80\x80\xbf"));  // U+003F
  EXPECT_FALSE(IsStringUTF8("\xfc\x80\x80\x80\xa0\xa5"));  // U+00A5

  // Beyond U+10FFFF (the upper limit of Unicode codespace)
  EXPECT_FALSE(IsStringUTF8("\xf4\x90\x80\x80"));  // U+110000
  EXPECT_FALSE(IsStringUTF8("\xf8\xa0\xbf\x80\xbf"));  // 5 bytes
  EXPECT_FALSE(IsStringUTF8("\xfc\x9c\xbf\x80\xbf\x80"));  // 6 bytes

  // BOMs in UTF-16(BE|LE) and UTF-32(BE|LE)
  EXPECT_FALSE(IsStringUTF8("\xfe\xff"));
  EXPECT_FALSE(IsStringUTF8("\xff\xfe"));
  EXPECT_FALSE(IsStringUTF8(std::string("\x00\x00\xfe\xff", 4)));
  EXPECT_FALSE(IsStringUTF8("\xff\xfe\x00\x00"));

  // Non-characters : U+xxFFF[EF] where xx is 0x00 through 0x10 and <FDD0,FDEF>
  EXPECT_FALSE(IsStringUTF8("\xef\xbf\xbe"));  // U+FFFE)
  EXPECT_FALSE(IsStringUTF8("\xf0\x8f\xbf\xbe"));  // U+1FFFE
  EXPECT_FALSE(IsStringUTF8("\xf3\xbf\xbf\xbf"));  // U+10FFFF
  EXPECT_FALSE(IsStringUTF8("\xef\xb7\x90"));  // U+FDD0
  EXPECT_FALSE(IsStringUTF8("\xef\xb7\xaf"));  // U+FDEF
  // Strings in legacy encodings. We can certainly make up strings
  // in a legacy encoding that are valid in UTF-8, but in real data,
  // most of them are invalid as UTF-8.
  EXPECT_FALSE(IsStringUTF8("caf\xe9"));  // cafe with U+00E9 in ISO-8859-1
  EXPECT_FALSE(IsStringUTF8("\xb0\xa1\xb0\xa2"));  // U+AC00, U+AC001 in EUC-KR
  EXPECT_FALSE(IsStringUTF8("\xa7\x41\xa6\x6e"));  // U+4F60 U+597D in Big5
  // "abc" with U+201[CD] in windows-125[0-8]
  EXPECT_FALSE(IsStringUTF8("\x93" "abc\x94"));
  // U+0639 U+064E U+0644 U+064E in ISO-8859-6
  EXPECT_FALSE(IsStringUTF8("\xd9\xee\xe4\xee"));
  // U+03B3 U+03B5 U+03B9 U+03AC in ISO-8859-7
  EXPECT_FALSE(IsStringUTF8("\xe3\xe5\xe9\xdC"));

  // Check that we support Embedded Nulls. The first uses the canonical UTF-8
  // representation, and the second uses a 2-byte sequence. The second version
  // is invalid UTF-8 since UTF-8 states that the shortest encoding for a
  // given codepoint must be used.
  static const char kEmbeddedNull[] = "embedded\0null";
  EXPECT_TRUE(IsStringUTF8(
      std::string(kEmbeddedNull, sizeof(kEmbeddedNull))));
  EXPECT_FALSE(IsStringUTF8("embedded\xc0\x80U+0000"));
}

TEST(StringUtilTest, ConvertASCII) {
  static const char* char_cases[] = {
    "Google Video",
    "Hello, world\n",
    "0123ABCDwxyz \a\b\t\r\n!+,.~"
  };

  static const wchar_t* const wchar_cases[] = {
    L"Google Video",
    L"Hello, world\n",
    L"0123ABCDwxyz \a\b\t\r\n!+,.~"
  };

  for (size_t i = 0; i < arraysize(char_cases); ++i) {
    EXPECT_TRUE(IsStringASCII(char_cases[i]));
    string16 utf16 = ASCIIToUTF16(char_cases[i]);
    EXPECT_EQ(WideToUTF16(wchar_cases[i]), utf16);

    std::string ascii = UTF16ToASCII(WideToUTF16(wchar_cases[i]));
    EXPECT_EQ(char_cases[i], ascii);
  }

  EXPECT_FALSE(IsStringASCII("Google \x80Video"));

  // Convert empty strings.
  string16 empty16;
  std::string empty;
  EXPECT_EQ(empty, UTF16ToASCII(empty16));
  EXPECT_EQ(empty16, ASCIIToUTF16(empty));

  // Convert strings with an embedded NUL character.
  const char chars_with_nul[] = "test\0string";
  const int length_with_nul = arraysize(chars_with_nul) - 1;
  std::string string_with_nul(chars_with_nul, length_with_nul);
  std::wstring wide_with_nul = ASCIIToWide(string_with_nul);
  EXPECT_EQ(static_cast<std::wstring::size_type>(length_with_nul),
            wide_with_nul.length());
  std::string narrow_with_nul = UTF16ToASCII(WideToUTF16(wide_with_nul));
  EXPECT_EQ(static_cast<std::string::size_type>(length_with_nul),
            narrow_with_nul.length());
  EXPECT_EQ(0, string_with_nul.compare(narrow_with_nul));
}

TEST(StringUtilTest, ToUpperASCII) {
  EXPECT_EQ('C', ToUpperASCII('C'));
  EXPECT_EQ('C', ToUpperASCII('c'));
  EXPECT_EQ('2', ToUpperASCII('2'));

  EXPECT_EQ(L'C', ToUpperASCII(L'C'));
  EXPECT_EQ(L'C', ToUpperASCII(L'c'));
  EXPECT_EQ(L'2', ToUpperASCII(L'2'));

  std::string in_place_a("Cc2");
  StringToUpperASCII(&in_place_a);
  EXPECT_EQ("CC2", in_place_a);

  std::wstring in_place_w(L"Cc2");
  StringToUpperASCII(&in_place_w);
  EXPECT_EQ(L"CC2", in_place_w);

  std::string original_a("Cc2");
  std::string upper_a = StringToUpperASCII(original_a);
  EXPECT_EQ("CC2", upper_a);

  std::wstring original_w(L"Cc2");
  std::wstring upper_w = StringToUpperASCII(original_w);
  EXPECT_EQ(L"CC2", upper_w);
}

TEST(StringUtilTest, LowerCaseEqualsASCII) {
  static const struct {
    const char*    src_a;
    const char*    dst;
  } lowercase_cases[] = {
    { "FoO", "foo" },
    { "foo", "foo" },
    { "FOO", "foo" },
  };

  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(lowercase_cases); ++i) {
    EXPECT_TRUE(LowerCaseEqualsASCII(ASCIIToUTF16(lowercase_cases[i].src_a),
                                     lowercase_cases[i].dst));
    EXPECT_TRUE(LowerCaseEqualsASCII(lowercase_cases[i].src_a,
                                     lowercase_cases[i].dst));
  }
}

TEST(StringUtilTest, FormatBytesUnlocalized) {
  static const struct {
    int64_t bytes;
    const char* expected;
  } cases[] = {
    // Expected behavior: we show one post-decimal digit when we have
    // under two pre-decimal digits, except in cases where it makes no
    // sense (zero or bytes).
    // Since we switch units once we cross the 1000 mark, this keeps
    // the display of file sizes or bytes consistently around three
    // digits.
    {0, "0 B"},
    {512, "512 B"},
    {1024*1024, "1.0 MB"},
    {1024*1024*1024, "1.0 GB"},
    {10LL*1024*1024*1024, "10.0 GB"},
    {99LL*1024*1024*1024, "99.0 GB"},
    {105LL*1024*1024*1024, "105 GB"},
    {105LL*1024*1024*1024 + 500LL*1024*1024, "105 GB"},
    {~(1LL<<63), "8192 PB"},

    {99*1024 + 103, "99.1 kB"},
    {1024*1024 + 103, "1.0 MB"},
    {1024*1024 + 205 * 1024, "1.2 MB"},
    {1024*1024*1024 + (927 * 1024*1024), "1.9 GB"},
    {10LL*1024*1024*1024, "10.0 GB"},
    {100LL*1024*1024*1024, "100 GB"},
  };

  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(cases); ++i) {
    EXPECT_EQ(ASCIIToUTF16(cases[i].expected),
              FormatBytesUnlocalized(cases[i].bytes));
  }
}
TEST(StringUtilTest, ReplaceSubstringsAfterOffset) {
  static const struct {
    const char* str;
    string16::size_type start_offset;
    const char* find_this;
    const char* replace_with;
    const char* expected;
  } cases[] = {
    {"aaa", 0, "a", "b", "bbb"},
    {"abb", 0, "ab", "a", "ab"},
    {"Removing some substrings inging", 0, "ing", "", "Remov some substrs "},
    {"Not found", 0, "x", "0", "Not found"},
    {"Not found again", 5, "x", "0", "Not found again"},
    {" Making it much longer ", 0, " ", "Four score and seven years ago",
     "Four score and seven years agoMakingFour score and seven years agoit"
     "Four score and seven years agomuchFour score and seven years agolonger"
     "Four score and seven years ago"},
    {"Invalid offset", 9999, "t", "foobar", "Invalid offset"},
    {"Replace me only me once", 9, "me ", "", "Replace me only once"},
    {"abababab", 2, "ab", "c", "abccc"},
  };

  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(cases); i++) {
    string16 str = ASCIIToUTF16(cases[i].str);
    ReplaceSubstringsAfterOffset(&str, cases[i].start_offset,
                                 ASCIIToUTF16(cases[i].find_this),
                                 ASCIIToUTF16(cases[i].replace_with));
    EXPECT_EQ(ASCIIToUTF16(cases[i].expected), str);
  }
}

TEST(StringUtilTest, ReplaceFirstSubstringAfterOffset) {
  static const struct {
    const char* str;
    string16::size_type start_offset;
    const char* find_this;
    const char* replace_with;
    const char* expected;
  } cases[] = {
    {"aaa", 0, "a", "b", "baa"},
    {"abb", 0, "ab", "a", "ab"},
    {"Removing some substrings inging", 0, "ing", "",
      "Remov some substrings inging"},
    {"Not found", 0, "x", "0", "Not found"},
    {"Not found again", 5, "x", "0", "Not found again"},
    {" Making it much longer ", 0, " ", "Four score and seven years ago",
     "Four score and seven years agoMaking it much longer "},
    {"Invalid offset", 9999, "t", "foobar", "Invalid offset"},
    {"Replace me only me once", 4, "me ", "", "Replace only me once"},
    {"abababab", 2, "ab", "c", "abcabab"},
  };

  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(cases); i++) {
    string16 str = ASCIIToUTF16(cases[i].str);
    ReplaceFirstSubstringAfterOffset(&str, cases[i].start_offset,
                                     ASCIIToUTF16(cases[i].find_this),
                                     ASCIIToUTF16(cases[i].replace_with));
    EXPECT_EQ(ASCIIToUTF16(cases[i].expected), str);
  }
}

TEST(StringUtilTest, HexDigitToInt) {
  EXPECT_EQ(0, HexDigitToInt('0'));
  EXPECT_EQ(1, HexDigitToInt('1'));
  EXPECT_EQ(2, HexDigitToInt('2'));
  EXPECT_EQ(3, HexDigitToInt('3'));
  EXPECT_EQ(4, HexDigitToInt('4'));
  EXPECT_EQ(5, HexDigitToInt('5'));
  EXPECT_EQ(6, HexDigitToInt('6'));
  EXPECT_EQ(7, HexDigitToInt('7'));
  EXPECT_EQ(8, HexDigitToInt('8'));
  EXPECT_EQ(9, HexDigitToInt('9'));
  EXPECT_EQ(10, HexDigitToInt('A'));
  EXPECT_EQ(11, HexDigitToInt('B'));
  EXPECT_EQ(12, HexDigitToInt('C'));
  EXPECT_EQ(13, HexDigitToInt('D'));
  EXPECT_EQ(14, HexDigitToInt('E'));
  EXPECT_EQ(15, HexDigitToInt('F'));

  // Verify the lower case as well.
  EXPECT_EQ(10, HexDigitToInt('a'));
  EXPECT_EQ(11, HexDigitToInt('b'));
  EXPECT_EQ(12, HexDigitToInt('c'));
  EXPECT_EQ(13, HexDigitToInt('d'));
  EXPECT_EQ(14, HexDigitToInt('e'));
  EXPECT_EQ(15, HexDigitToInt('f'));
}

// This checks where we can use the assignment operator for a va_list. We need
// a way to do this since Visual C doesn't support va_copy, but assignment on
// va_list is not guaranteed to be a copy. See StringAppendVT which uses this
// capability.
static void VariableArgsFunc(const char* format, ...) {
  va_list org;
  va_start(org, format);

  va_list dup;
  GG_VA_COPY(dup, org);
  int i1 = va_arg(org, int);
  int j1 = va_arg(org, int);
  char* s1 = va_arg(org, char*);
  double d1 = va_arg(org, double);
  va_end(org);

  int i2 = va_arg(dup, int);
  int j2 = va_arg(dup, int);
  char* s2 = va_arg(dup, char*);
  double d2 = va_arg(dup, double);

  EXPECT_EQ(i1, i2);
  EXPECT_EQ(j1, j2);
  EXPECT_STREQ(s1, s2);
  EXPECT_EQ(d1, d2);

  va_end(dup);
}

TEST(StringUtilTest, VAList) {
  VariableArgsFunc("%d %d %s %lf", 45, 92, "This is interesting", 9.21);
}

// Test for Tokenize
template <typename STR>
void TokenizeTest() {
  std::vector<STR> r;
  size_t size;

  size = Tokenize(STR("This is a string"), STR(" "), &r);
  EXPECT_EQ(4U, size);
  ASSERT_EQ(4U, r.size());
  EXPECT_EQ(r[0], STR("This"));
  EXPECT_EQ(r[1], STR("is"));
  EXPECT_EQ(r[2], STR("a"));
  EXPECT_EQ(r[3], STR("string"));
  r.clear();

  size = Tokenize(STR("one,two,three"), STR(","), &r);
  EXPECT_EQ(3U, size);
  ASSERT_EQ(3U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR("two"));
  EXPECT_EQ(r[2], STR("three"));
  r.clear();

  size = Tokenize(STR("one,two:three;four"), STR(",:"), &r);
  EXPECT_EQ(3U, size);
  ASSERT_EQ(3U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR("two"));
  EXPECT_EQ(r[2], STR("three;four"));
  r.clear();

  size = Tokenize(STR("one,two:three;four"), STR(";,:"), &r);
  EXPECT_EQ(4U, size);
  ASSERT_EQ(4U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR("two"));
  EXPECT_EQ(r[2], STR("three"));
  EXPECT_EQ(r[3], STR("four"));
  r.clear();

  size = Tokenize(STR("one, two, three"), STR(","), &r);
  EXPECT_EQ(3U, size);
  ASSERT_EQ(3U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR(" two"));
  EXPECT_EQ(r[2], STR(" three"));
  r.clear();

  size = Tokenize(STR("one, two, three, "), STR(","), &r);
  EXPECT_EQ(4U, size);
  ASSERT_EQ(4U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR(" two"));
  EXPECT_EQ(r[2], STR(" three"));
  EXPECT_EQ(r[3], STR(" "));
  r.clear();

  size = Tokenize(STR("one, two, three,"), STR(","), &r);
  EXPECT_EQ(3U, size);
  ASSERT_EQ(3U, r.size());
  EXPECT_EQ(r[0], STR("one"));
  EXPECT_EQ(r[1], STR(" two"));
  EXPECT_EQ(r[2], STR(" three"));
  r.clear();

  size = Tokenize(STR(), STR(","), &r);
  EXPECT_EQ(0U, size);
  ASSERT_EQ(0U, r.size());
  r.clear();

  size = Tokenize(STR(","), STR(","), &r);
  EXPECT_EQ(0U, size);
  ASSERT_EQ(0U, r.size());
  r.clear();

  size = Tokenize(STR(",;:."), STR(".:;,"), &r);
  EXPECT_EQ(0U, size);
  ASSERT_EQ(0U, r.size());
  r.clear();

  size = Tokenize(STR("\t\ta\t"), STR("\t"), &r);
  EXPECT_EQ(1U, size);
  ASSERT_EQ(1U, r.size());
  EXPECT_EQ(r[0], STR("a"));
  r.clear();

  size = Tokenize(STR("\ta\t\nb\tcc"), STR("\n"), &r);
  EXPECT_EQ(2U, size);
  ASSERT_EQ(2U, r.size());
  EXPECT_EQ(r[0], STR("\ta\t"));
  EXPECT_EQ(r[1], STR("b\tcc"));
  r.clear();
}

TEST(StringUtilTest, TokenizeStdString) {
  TokenizeTest<std::string>();
}

TEST(StringUtilTest, TokenizeStringPiece) {
726
  TokenizeTest<butil::StringPiece>();
gejun's avatar
gejun committed
727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995
}

// Test for JoinString
TEST(StringUtilTest, JoinString) {
  std::vector<std::string> in;
  EXPECT_EQ("", JoinString(in, ','));

  in.push_back("a");
  EXPECT_EQ("a", JoinString(in, ','));

  in.push_back("b");
  in.push_back("c");
  EXPECT_EQ("a,b,c", JoinString(in, ','));

  in.push_back(std::string());
  EXPECT_EQ("a,b,c,", JoinString(in, ','));
  in.push_back(" ");
  EXPECT_EQ("a|b|c|| ", JoinString(in, '|'));
}

// Test for JoinString overloaded with std::string separator
TEST(StringUtilTest, JoinStringWithString) {
  std::string separator(", ");
  std::vector<std::string> parts;
  EXPECT_EQ(std::string(), JoinString(parts, separator));

  parts.push_back("a");
  EXPECT_EQ("a", JoinString(parts, separator));

  parts.push_back("b");
  parts.push_back("c");
  EXPECT_EQ("a, b, c", JoinString(parts, separator));

  parts.push_back(std::string());
  EXPECT_EQ("a, b, c, ", JoinString(parts, separator));
  parts.push_back(" ");
  EXPECT_EQ("a|b|c|| ", JoinString(parts, "|"));
}

// Test for JoinString overloaded with string16 separator
TEST(StringUtilTest, JoinStringWithString16) {
  string16 separator = ASCIIToUTF16(", ");
  std::vector<string16> parts;
  EXPECT_EQ(string16(), JoinString(parts, separator));

  parts.push_back(ASCIIToUTF16("a"));
  EXPECT_EQ(ASCIIToUTF16("a"), JoinString(parts, separator));

  parts.push_back(ASCIIToUTF16("b"));
  parts.push_back(ASCIIToUTF16("c"));
  EXPECT_EQ(ASCIIToUTF16("a, b, c"), JoinString(parts, separator));

  parts.push_back(ASCIIToUTF16(""));
  EXPECT_EQ(ASCIIToUTF16("a, b, c, "), JoinString(parts, separator));
  parts.push_back(ASCIIToUTF16(" "));
  EXPECT_EQ(ASCIIToUTF16("a|b|c|| "), JoinString(parts, ASCIIToUTF16("|")));
}

TEST(StringUtilTest, StartsWith) {
  EXPECT_TRUE(StartsWithASCII("javascript:url", "javascript", true));
  EXPECT_FALSE(StartsWithASCII("JavaScript:url", "javascript", true));
  EXPECT_TRUE(StartsWithASCII("javascript:url", "javascript", false));
  EXPECT_TRUE(StartsWithASCII("JavaScript:url", "javascript", false));
  EXPECT_FALSE(StartsWithASCII("java", "javascript", true));
  EXPECT_FALSE(StartsWithASCII("java", "javascript", false));
  EXPECT_FALSE(StartsWithASCII(std::string(), "javascript", false));
  EXPECT_FALSE(StartsWithASCII(std::string(), "javascript", true));
  EXPECT_TRUE(StartsWithASCII("java", std::string(), false));
  EXPECT_TRUE(StartsWithASCII("java", std::string(), true));

  EXPECT_TRUE(StartsWith(ASCIIToUTF16("javascript:url"),
                         ASCIIToUTF16("javascript"), true));
  EXPECT_FALSE(StartsWith(ASCIIToUTF16("JavaScript:url"),
                          ASCIIToUTF16("javascript"), true));
  EXPECT_TRUE(StartsWith(ASCIIToUTF16("javascript:url"),
                         ASCIIToUTF16("javascript"), false));
  EXPECT_TRUE(StartsWith(ASCIIToUTF16("JavaScript:url"),
                         ASCIIToUTF16("javascript"), false));
  EXPECT_FALSE(StartsWith(ASCIIToUTF16("java"),
                          ASCIIToUTF16("javascript"), true));
  EXPECT_FALSE(StartsWith(ASCIIToUTF16("java"),
                          ASCIIToUTF16("javascript"), false));
  EXPECT_FALSE(StartsWith(string16(), ASCIIToUTF16("javascript"), false));
  EXPECT_FALSE(StartsWith(string16(), ASCIIToUTF16("javascript"), true));
  EXPECT_TRUE(StartsWith(ASCIIToUTF16("java"), string16(), false));
  EXPECT_TRUE(StartsWith(ASCIIToUTF16("java"), string16(), true));
}

TEST(StringUtilTest, EndsWith) {
  EXPECT_TRUE(EndsWith(ASCIIToUTF16("Foo.plugin"),
                       ASCIIToUTF16(".plugin"), true));
  EXPECT_FALSE(EndsWith(ASCIIToUTF16("Foo.Plugin"),
                        ASCIIToUTF16(".plugin"), true));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16("Foo.plugin"),
                       ASCIIToUTF16(".plugin"), false));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16("Foo.Plugin"),
                       ASCIIToUTF16(".plugin"), false));
  EXPECT_FALSE(EndsWith(ASCIIToUTF16(".plug"), ASCIIToUTF16(".plugin"), true));
  EXPECT_FALSE(EndsWith(ASCIIToUTF16(".plug"), ASCIIToUTF16(".plugin"), false));
  EXPECT_FALSE(EndsWith(ASCIIToUTF16("Foo.plugin Bar"),
                        ASCIIToUTF16(".plugin"), true));
  EXPECT_FALSE(EndsWith(ASCIIToUTF16("Foo.plugin Bar"),
                        ASCIIToUTF16(".plugin"), false));
  EXPECT_FALSE(EndsWith(string16(), ASCIIToUTF16(".plugin"), false));
  EXPECT_FALSE(EndsWith(string16(), ASCIIToUTF16(".plugin"), true));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16("Foo.plugin"), string16(), false));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16("Foo.plugin"), string16(), true));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16(".plugin"),
                       ASCIIToUTF16(".plugin"), false));
  EXPECT_TRUE(EndsWith(ASCIIToUTF16(".plugin"), ASCIIToUTF16(".plugin"), true));
  EXPECT_TRUE(EndsWith(string16(), string16(), false));
  EXPECT_TRUE(EndsWith(string16(), string16(), true));
}

TEST(StringUtilTest, GetStringFWithOffsets) {
  std::vector<string16> subst;
  subst.push_back(ASCIIToUTF16("1"));
  subst.push_back(ASCIIToUTF16("2"));
  std::vector<size_t> offsets;

  ReplaceStringPlaceholders(ASCIIToUTF16("Hello, $1. Your number is $2."),
                            subst,
                            &offsets);
  EXPECT_EQ(2U, offsets.size());
  EXPECT_EQ(7U, offsets[0]);
  EXPECT_EQ(25U, offsets[1]);
  offsets.clear();

  ReplaceStringPlaceholders(ASCIIToUTF16("Hello, $2. Your number is $1."),
                            subst,
                            &offsets);
  EXPECT_EQ(2U, offsets.size());
  EXPECT_EQ(25U, offsets[0]);
  EXPECT_EQ(7U, offsets[1]);
  offsets.clear();
}

TEST(StringUtilTest, ReplaceStringPlaceholdersTooFew) {
  // Test whether replacestringplaceholders works as expected when there
  // are fewer inputs than outputs.
  std::vector<string16> subst;
  subst.push_back(ASCIIToUTF16("9a"));
  subst.push_back(ASCIIToUTF16("8b"));
  subst.push_back(ASCIIToUTF16("7c"));

  string16 formatted =
      ReplaceStringPlaceholders(
          ASCIIToUTF16("$1a,$2b,$3c,$4d,$5e,$6f,$1g,$2h,$3i"), subst, NULL);

  EXPECT_EQ(formatted, ASCIIToUTF16("9aa,8bb,7cc,d,e,f,9ag,8bh,7ci"));
}

TEST(StringUtilTest, ReplaceStringPlaceholders) {
  std::vector<string16> subst;
  subst.push_back(ASCIIToUTF16("9a"));
  subst.push_back(ASCIIToUTF16("8b"));
  subst.push_back(ASCIIToUTF16("7c"));
  subst.push_back(ASCIIToUTF16("6d"));
  subst.push_back(ASCIIToUTF16("5e"));
  subst.push_back(ASCIIToUTF16("4f"));
  subst.push_back(ASCIIToUTF16("3g"));
  subst.push_back(ASCIIToUTF16("2h"));
  subst.push_back(ASCIIToUTF16("1i"));

  string16 formatted =
      ReplaceStringPlaceholders(
          ASCIIToUTF16("$1a,$2b,$3c,$4d,$5e,$6f,$7g,$8h,$9i"), subst, NULL);

  EXPECT_EQ(formatted, ASCIIToUTF16("9aa,8bb,7cc,6dd,5ee,4ff,3gg,2hh,1ii"));
}

TEST(StringUtilTest, ReplaceStringPlaceholdersMoreThan9Replacements) {
  std::vector<string16> subst;
  subst.push_back(ASCIIToUTF16("9a"));
  subst.push_back(ASCIIToUTF16("8b"));
  subst.push_back(ASCIIToUTF16("7c"));
  subst.push_back(ASCIIToUTF16("6d"));
  subst.push_back(ASCIIToUTF16("5e"));
  subst.push_back(ASCIIToUTF16("4f"));
  subst.push_back(ASCIIToUTF16("3g"));
  subst.push_back(ASCIIToUTF16("2h"));
  subst.push_back(ASCIIToUTF16("1i"));
  subst.push_back(ASCIIToUTF16("0j"));
  subst.push_back(ASCIIToUTF16("-1k"));
  subst.push_back(ASCIIToUTF16("-2l"));
  subst.push_back(ASCIIToUTF16("-3m"));
  subst.push_back(ASCIIToUTF16("-4n"));

  string16 formatted =
      ReplaceStringPlaceholders(
          ASCIIToUTF16("$1a,$2b,$3c,$4d,$5e,$6f,$7g,$8h,$9i,"
                       "$10j,$11k,$12l,$13m,$14n,$1"), subst, NULL);

  EXPECT_EQ(formatted, ASCIIToUTF16("9aa,8bb,7cc,6dd,5ee,4ff,3gg,2hh,"
                                    "1ii,0jj,-1kk,-2ll,-3mm,-4nn,9a"));
}

TEST(StringUtilTest, StdStringReplaceStringPlaceholders) {
  std::vector<std::string> subst;
  subst.push_back("9a");
  subst.push_back("8b");
  subst.push_back("7c");
  subst.push_back("6d");
  subst.push_back("5e");
  subst.push_back("4f");
  subst.push_back("3g");
  subst.push_back("2h");
  subst.push_back("1i");

  std::string formatted =
      ReplaceStringPlaceholders(
          "$1a,$2b,$3c,$4d,$5e,$6f,$7g,$8h,$9i", subst, NULL);

  EXPECT_EQ(formatted, "9aa,8bb,7cc,6dd,5ee,4ff,3gg,2hh,1ii");
}

TEST(StringUtilTest, ReplaceStringPlaceholdersConsecutiveDollarSigns) {
  std::vector<std::string> subst;
  subst.push_back("a");
  subst.push_back("b");
  subst.push_back("c");
  EXPECT_EQ(ReplaceStringPlaceholders("$$1 $$$2 $$$$3", subst, NULL),
            "$1 $$2 $$$3");
}

TEST(StringUtilTest, MatchPatternTest) {
  EXPECT_TRUE(MatchPattern("www.google.com", "*.com"));
  EXPECT_TRUE(MatchPattern("www.google.com", "*"));
  EXPECT_FALSE(MatchPattern("www.google.com", "www*.g*.org"));
  EXPECT_TRUE(MatchPattern("Hello", "H?l?o"));
  EXPECT_FALSE(MatchPattern("www.google.com", "http://*)"));
  EXPECT_FALSE(MatchPattern("www.msn.com", "*.COM"));
  EXPECT_TRUE(MatchPattern("Hello*1234", "He??o\\*1*"));
  EXPECT_FALSE(MatchPattern("", "*.*"));
  EXPECT_TRUE(MatchPattern("", "*"));
  EXPECT_TRUE(MatchPattern("", "?"));
  EXPECT_TRUE(MatchPattern("", ""));
  EXPECT_FALSE(MatchPattern("Hello", ""));
  EXPECT_TRUE(MatchPattern("Hello*", "Hello*"));
  // Stop after a certain recursion depth.
  EXPECT_FALSE(MatchPattern("123456789012345678", "?????????????????*"));

  // Test UTF8 matching.
  EXPECT_TRUE(MatchPattern("heart: \xe2\x99\xa0", "*\xe2\x99\xa0"));
  EXPECT_TRUE(MatchPattern("heart: \xe2\x99\xa0.", "heart: ?."));
  EXPECT_TRUE(MatchPattern("hearts: \xe2\x99\xa0\xe2\x99\xa0", "*"));
  // Invalid sequences should be handled as a single invalid character.
  EXPECT_TRUE(MatchPattern("invalid: \xef\xbf\xbe", "invalid: ?"));
  // If the pattern has invalid characters, it shouldn't match anything.
  EXPECT_FALSE(MatchPattern("\xf4\x90\x80\x80", "\xf4\x90\x80\x80"));

  // Test UTF16 character matching.
  EXPECT_TRUE(MatchPattern(UTF8ToUTF16("www.google.com"),
                           UTF8ToUTF16("*.com")));
  EXPECT_TRUE(MatchPattern(UTF8ToUTF16("Hello*1234"),
                           UTF8ToUTF16("He??o\\*1*")));

  // This test verifies that consecutive wild cards are collapsed into 1
  // wildcard (when this doesn't occur, MatchPattern reaches it's maximum
  // recursion depth).
  EXPECT_TRUE(MatchPattern(UTF8ToUTF16("Hello"),
                           UTF8ToUTF16("He********************************o")));
}

TEST(StringUtilTest, LcpyTest) {
  // Test the normal case where we fit in our buffer.
  {
    char dst[10];
    wchar_t wdst[10];
996
    EXPECT_EQ(7U, butil::strlcpy(dst, "abcdefg", arraysize(dst)));
gejun's avatar
gejun committed
997
    EXPECT_EQ(0, memcmp(dst, "abcdefg", 8));
998
    EXPECT_EQ(7U, butil::wcslcpy(wdst, L"abcdefg", arraysize(wdst)));
gejun's avatar
gejun committed
999 1000 1001 1002 1003 1004 1005 1006
    EXPECT_EQ(0, memcmp(wdst, L"abcdefg", sizeof(wchar_t) * 8));
  }

  // Test dst_size == 0, nothing should be written to |dst| and we should
  // have the equivalent of strlen(src).
  {
    char dst[2] = {1, 2};
    wchar_t wdst[2] = {1, 2};
1007
    EXPECT_EQ(7U, butil::strlcpy(dst, "abcdefg", 0));
gejun's avatar
gejun committed
1008 1009
    EXPECT_EQ(1, dst[0]);
    EXPECT_EQ(2, dst[1]);
1010
    EXPECT_EQ(7U, butil::wcslcpy(wdst, L"abcdefg", 0));
gejun's avatar
gejun committed
1011 1012 1013 1014 1015 1016 1017 1018
    EXPECT_EQ(static_cast<wchar_t>(1), wdst[0]);
    EXPECT_EQ(static_cast<wchar_t>(2), wdst[1]);
  }

  // Test the case were we _just_ competely fit including the null.
  {
    char dst[8];
    wchar_t wdst[8];
1019
    EXPECT_EQ(7U, butil::strlcpy(dst, "abcdefg", arraysize(dst)));
gejun's avatar
gejun committed
1020
    EXPECT_EQ(0, memcmp(dst, "abcdefg", 8));
1021
    EXPECT_EQ(7U, butil::wcslcpy(wdst, L"abcdefg", arraysize(wdst)));
gejun's avatar
gejun committed
1022 1023 1024 1025 1026 1027 1028
    EXPECT_EQ(0, memcmp(wdst, L"abcdefg", sizeof(wchar_t) * 8));
  }

  // Test the case were we we are one smaller, so we can't fit the null.
  {
    char dst[7];
    wchar_t wdst[7];
1029
    EXPECT_EQ(7U, butil::strlcpy(dst, "abcdefg", arraysize(dst)));
gejun's avatar
gejun committed
1030
    EXPECT_EQ(0, memcmp(dst, "abcdef", 7));
1031
    EXPECT_EQ(7U, butil::wcslcpy(wdst, L"abcdefg", arraysize(wdst)));
gejun's avatar
gejun committed
1032 1033 1034 1035 1036 1037 1038
    EXPECT_EQ(0, memcmp(wdst, L"abcdef", sizeof(wchar_t) * 7));
  }

  // Test the case were we are just too small.
  {
    char dst[3];
    wchar_t wdst[3];
1039
    EXPECT_EQ(7U, butil::strlcpy(dst, "abcdefg", arraysize(dst)));
gejun's avatar
gejun committed
1040
    EXPECT_EQ(0, memcmp(dst, "ab", 3));
1041
    EXPECT_EQ(7U, butil::wcslcpy(wdst, L"abcdefg", arraysize(wdst)));
gejun's avatar
gejun committed
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
    EXPECT_EQ(0, memcmp(wdst, L"ab", sizeof(wchar_t) * 3));
  }
}

TEST(StringUtilTest, WprintfFormatPortabilityTest) {
  static const struct {
    const wchar_t* input;
    bool portable;
  } cases[] = {
    { L"%ls", true },
    { L"%s", false },
    { L"%S", false },
    { L"%lS", false },
    { L"Hello, %s", false },
    { L"%lc", true },
    { L"%c", false },
    { L"%C", false },
    { L"%lC", false },
    { L"%ls %s", false },
    { L"%s %ls", false },
    { L"%s %ls %s", false },
    { L"%f", true },
    { L"%f %F", false },
    { L"%d %D", false },
    { L"%o %O", false },
    { L"%u %U", false },
    { L"%f %d %o %u", true },
    { L"%-8d (%02.1f%)", true },
    { L"% 10s", false },
    { L"% 10ls", true }
  };
  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(cases); ++i)
1074
    EXPECT_EQ(cases[i].portable, butil::IsWprintfFormatPortable(cases[i].input));
gejun's avatar
gejun committed
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
}

TEST(StringUtilTest, RemoveChars) {
  const char* kRemoveChars = "-/+*";
  std::string input = "A-+bc/d!*";
  EXPECT_TRUE(RemoveChars(input, kRemoveChars, &input));
  EXPECT_EQ("Abcd!", input);

  // No characters match kRemoveChars.
  EXPECT_FALSE(RemoveChars(input, kRemoveChars, &input));
  EXPECT_EQ("Abcd!", input);

  // Empty string.
  input.clear();
  EXPECT_FALSE(RemoveChars(input, kRemoveChars, &input));
  EXPECT_EQ(std::string(), input);
}

TEST(StringUtilTest, ReplaceChars) {
  struct TestData {
    const char* input;
    const char* replace_chars;
    const char* replace_with;
    const char* output;
    bool result;
  } cases[] = {
    { "", "", "", "", false },
    { "test", "", "", "test", false },
    { "test", "", "!", "test", false },
    { "test", "z", "!", "test", false },
    { "test", "e", "!", "t!st", true },
    { "test", "e", "!?", "t!?st", true },
    { "test", "ez", "!", "t!st", true },
    { "test", "zed", "!?", "t!?st", true },
    { "test", "t", "!?", "!?es!?", true },
    { "test", "et", "!>", "!>!>s!>", true },
    { "test", "zest", "!", "!!!!", true },
    { "test", "szt", "!", "!e!!", true },
    { "test", "t", "test", "testestest", true },
  };

  for (size_t i = 0; i < ARRAYSIZE_UNSAFE(cases); ++i) {
    std::string output;
    bool result = ReplaceChars(cases[i].input,
                               cases[i].replace_chars,
                               cases[i].replace_with,
                               &output);
    EXPECT_EQ(cases[i].result, result);
    EXPECT_EQ(cases[i].output, output);
  }
}

TEST(StringUtilTest, ContainsOnlyChars) {
  // Providing an empty list of characters should return false but for the empty
  // string.
  EXPECT_TRUE(ContainsOnlyChars(std::string(), std::string()));
  EXPECT_FALSE(ContainsOnlyChars("Hello", std::string()));

  EXPECT_TRUE(ContainsOnlyChars(std::string(), "1234"));
  EXPECT_TRUE(ContainsOnlyChars("1", "1234"));
  EXPECT_TRUE(ContainsOnlyChars("1", "4321"));
  EXPECT_TRUE(ContainsOnlyChars("123", "4321"));
  EXPECT_FALSE(ContainsOnlyChars("123a", "4321"));

  EXPECT_TRUE(ContainsOnlyChars(std::string(), kWhitespaceASCII));
  EXPECT_TRUE(ContainsOnlyChars(" ", kWhitespaceASCII));
  EXPECT_TRUE(ContainsOnlyChars("\t", kWhitespaceASCII));
  EXPECT_TRUE(ContainsOnlyChars("\t \r \n  ", kWhitespaceASCII));
  EXPECT_FALSE(ContainsOnlyChars("a", kWhitespaceASCII));
  EXPECT_FALSE(ContainsOnlyChars("\thello\r \n  ", kWhitespaceASCII));

  EXPECT_TRUE(ContainsOnlyChars(string16(), kWhitespaceUTF16));
  EXPECT_TRUE(ContainsOnlyChars(ASCIIToUTF16(" "), kWhitespaceUTF16));
  EXPECT_TRUE(ContainsOnlyChars(ASCIIToUTF16("\t"), kWhitespaceUTF16));
  EXPECT_TRUE(ContainsOnlyChars(ASCIIToUTF16("\t \r \n  "), kWhitespaceUTF16));
  EXPECT_FALSE(ContainsOnlyChars(ASCIIToUTF16("a"), kWhitespaceUTF16));
  EXPECT_FALSE(ContainsOnlyChars(ASCIIToUTF16("\thello\r \n  "),
                                  kWhitespaceUTF16));
}

class WriteIntoTest : public testing::Test {
 protected:
  static void WritesCorrectly(size_t num_chars) {
    std::string buffer;
    char kOriginal[] = "supercali";
    strncpy(WriteInto(&buffer, num_chars + 1), kOriginal, num_chars);
    // Using std::string(buffer.c_str()) instead of |buffer| truncates the
    // string at the first \0.
    EXPECT_EQ(std::string(kOriginal,
                          std::min(num_chars, arraysize(kOriginal) - 1)),
              std::string(buffer.c_str()));
    EXPECT_EQ(num_chars, buffer.size());
  }
};

TEST_F(WriteIntoTest, WriteInto) {
  // Validate that WriteInto reserves enough space and
  // sizes a string correctly.
  WritesCorrectly(1);
  WritesCorrectly(2);
  WritesCorrectly(5000);

  // Validate that WriteInto doesn't modify other strings
  // when using a Copy-on-Write implementation.
  const char kLive[] = "live";
  const char kDead[] = "dead";
  const std::string live = kLive;
  std::string dead = live;
  strncpy(WriteInto(&dead, 5), kDead, 4);
  EXPECT_EQ(kDead, dead);
  EXPECT_EQ(4u, dead.size());
  EXPECT_EQ(kLive, live);
  EXPECT_EQ(4u, live.size());
}

1190
}  // namespace butil