DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (3b823d058ef5)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=8 sts=2 et sw=2 tw=80: */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "nsReadableUtils.h"

#include <algorithm>

#include "mozilla/CheckedInt.h"

#include "nscore.h"
#include "nsMemory.h"
#include "nsString.h"
#include "nsTArray.h"
#include "nsUTF8Utils.h"

using mozilla::MakeSpan;

/**
 * A helper function that allocates a buffer of the desired character type big
 * enough to hold a copy of the supplied string (plus a zero terminator).
 *
 * @param aSource an string you will eventually be making a copy of
 * @return a new buffer (of the type specified by the second parameter) which
 * you must free with |free|.
 *
 */
template <class FromStringT, class ToCharT>
inline ToCharT* AllocateStringCopy(const FromStringT& aSource, ToCharT*) {
  // Can't overflow due to the definition of nsTSubstring<T>::kMaxCapacity
  return static_cast<ToCharT*>(
      moz_xmalloc((size_t(aSource.Length()) + 1) * sizeof(ToCharT)));
}

char* ToNewCString(const nsAString& aSource) {
  char* dest = AllocateStringCopy(aSource, (char*)nullptr);
  if (!dest) {
    return nullptr;
  }

  auto len = aSource.Length();
  LossyConvertUtf16toLatin1(aSource, MakeSpan(dest, len));
  dest[len] = 0;
  return dest;
}

char* ToNewUTF8String(const nsAString& aSource, uint32_t* aUTF8Count) {
  auto len = aSource.Length();
  // The uses of this function seem temporary enough that it's not
  // worthwhile to be fancy about the allocation size. Let's just use
  // the worst case.
  // Times 3 plus 1, because ConvertUTF16toUTF8 requires times 3 and
  // then we have the terminator.
  // Using CheckedInt<uint32_t>, because aUTF8Count is uint32_t* for
  // historical reasons.
  mozilla::CheckedInt<uint32_t> destLen(len);
  destLen *= 3;
  destLen += 1;
  if (!destLen.isValid()) {
    return nullptr;
  }
  size_t destLenVal = destLen.value();
  char* dest = static_cast<char*>(moz_xmalloc(destLenVal));

  size_t written = ConvertUtf16toUtf8(aSource, MakeSpan(dest, destLenVal));
  dest[written] = 0;

  if (aUTF8Count) {
    *aUTF8Count = written;
  }

  return dest;
}

char* ToNewCString(const nsACString& aSource) {
  // no conversion needed, just allocate a buffer of the correct length and copy
  // into it

  char* dest = AllocateStringCopy(aSource, (char*)nullptr);
  if (!dest) {
    return nullptr;
  }

  auto len = aSource.Length();
  memcpy(dest, aSource.BeginReading(), len * sizeof(char));
  dest[len] = 0;
  return dest;
}

char16_t* ToNewUnicode(const nsAString& aSource) {
  // no conversion needed, just allocate a buffer of the correct length and copy
  // into it

  char16_t* dest = AllocateStringCopy(aSource, (char16_t*)nullptr);
  if (!dest) {
    return nullptr;
  }

  auto len = aSource.Length();
  memcpy(dest, aSource.BeginReading(), len * sizeof(char16_t));
  dest[len] = 0;
  return dest;
}

char16_t* ToNewUnicode(const nsACString& aSource) {
  char16_t* dest = AllocateStringCopy(aSource, (char16_t*)nullptr);
  if (!dest) {
    return nullptr;
  }

  auto len = aSource.Length();
  ConvertLatin1toUtf16(aSource, MakeSpan(dest, len));
  dest[len] = 0;
  return dest;
}

char16_t* UTF8ToNewUnicode(const nsACString& aSource, uint32_t* aUTF16Count) {
  // Compute length plus one as required by ConvertUTF8toUTF16
  uint32_t lengthPlusOne = aSource.Length() + 1;  // Can't overflow

  mozilla::CheckedInt<size_t> allocLength(lengthPlusOne);
  // Add space for zero-termination
  allocLength += 1;
  // We need UTF-16 units
  allocLength *= sizeof(char16_t);

  if (!allocLength.isValid()) {
    return nullptr;
  }

  char16_t* dest = (char16_t*)moz_xmalloc(allocLength.value());

  size_t written = ConvertUtf8toUtf16(aSource, MakeSpan(dest, lengthPlusOne));
  dest[written] = 0;

  if (aUTF16Count) {
    *aUTF16Count = written;
  }

  return dest;
}

char16_t* CopyUnicodeTo(const nsAString& aSource, uint32_t aSrcOffset,
                        char16_t* aDest, uint32_t aLength) {
  MOZ_ASSERT(aSrcOffset + aLength <= aSource.Length());
  memcpy(aDest, aSource.BeginReading() + aSrcOffset,
         size_t(aLength) * sizeof(char16_t));
  return aDest;
}

void ToUpperCase(nsACString& aCString) {
  char* cp = aCString.BeginWriting();
  char* end = cp + aCString.Length();
  while (cp != end) {
    char ch = *cp;
    if (ch >= 'a' && ch <= 'z') {
      *cp = ch - ('a' - 'A');
    }
    ++cp;
  }
}

void ToUpperCase(const nsACString& aSource, nsACString& aDest) {
  aDest.SetLength(aSource.Length());
  const char* src = aSource.BeginReading();
  const char* end = src + aSource.Length();
  char* dst = aDest.BeginWriting();
  while (src != end) {
    char ch = *src;
    if (ch >= 'a' && ch <= 'z') {
      *dst = ch - ('a' - 'A');
    } else {
      *dst = ch;
    }
    ++src;
    ++dst;
  }
}

void ToLowerCase(nsACString& aCString) {
  char* cp = aCString.BeginWriting();
  char* end = cp + aCString.Length();
  while (cp != end) {
    char ch = *cp;
    if (ch >= 'A' && ch <= 'Z') {
      *cp = ch + ('a' - 'A');
    }
    ++cp;
  }
}

void ToLowerCase(const nsACString& aSource, nsACString& aDest) {
  aDest.SetLength(aSource.Length());
  const char* src = aSource.BeginReading();
  const char* end = src + aSource.Length();
  char* dst = aDest.BeginWriting();
  while (src != end) {
    char ch = *src;
    if (ch >= 'A' && ch <= 'Z') {
      *dst = ch + ('a' - 'A');
    } else {
      *dst = ch;
    }
    ++src;
    ++dst;
  }
}

bool ParseString(const nsACString& aSource, char aDelimiter,
                 nsTArray<nsCString>& aArray) {
  nsACString::const_iterator start, end;
  aSource.BeginReading(start);
  aSource.EndReading(end);

  uint32_t oldLength = aArray.Length();

  for (;;) {
    nsACString::const_iterator delimiter = start;
    FindCharInReadable(aDelimiter, delimiter, end);

    if (delimiter != start) {
      if (!aArray.AppendElement(Substring(start, delimiter))) {
        aArray.RemoveElementsAt(oldLength, aArray.Length() - oldLength);
        return false;
      }
    }

    if (delimiter == end) {
      break;
    }
    start = ++delimiter;
    if (start == end) {
      break;
    }
  }

  return true;
}

template <class StringT, class IteratorT, class Comparator>
bool FindInReadable_Impl(const StringT& aPattern, IteratorT& aSearchStart,
                         IteratorT& aSearchEnd, const Comparator& aCompare) {
  bool found_it = false;

  // only bother searching at all if we're given a non-empty range to search
  if (aSearchStart != aSearchEnd) {
    IteratorT aPatternStart, aPatternEnd;
    aPattern.BeginReading(aPatternStart);
    aPattern.EndReading(aPatternEnd);

    // outer loop keeps searching till we find it or run out of string to search
    while (!found_it) {
      // fast inner loop (that's what it's called, not what it is) looks for a
      // potential match
      while (aSearchStart != aSearchEnd &&
             aCompare(aPatternStart.get(), aSearchStart.get(), 1, 1)) {
        ++aSearchStart;
      }

      // if we broke out of the `fast' loop because we're out of string ...
      // we're done: no match
      if (aSearchStart == aSearchEnd) {
        break;
      }

      // otherwise, we're at a potential match, let's see if we really hit one
      IteratorT testPattern(aPatternStart);
      IteratorT testSearch(aSearchStart);

      // slow inner loop verifies the potential match (found by the `fast' loop)
      // at the current position
      for (;;) {
        // we already compared the first character in the outer loop,
        //  so we'll advance before the next comparison
        ++testPattern;
        ++testSearch;

        // if we verified all the way to the end of the pattern, then we found
        // it!
        if (testPattern == aPatternEnd) {
          found_it = true;
          aSearchEnd = testSearch;  // return the exact found range through the
                                    // parameters
          break;
        }

        // if we got to end of the string we're searching before we hit the end
        // of the
        //  pattern, we'll never find what we're looking for
        if (testSearch == aSearchEnd) {
          aSearchStart = aSearchEnd;
          break;
        }

        // else if we mismatched ... it's time to advance to the next search
        // position
        //  and get back into the `fast' loop
        if (aCompare(testPattern.get(), testSearch.get(), 1, 1)) {
          ++aSearchStart;
          break;
        }
      }
    }
  }

  return found_it;
}

/**
 * This searches the entire string from right to left, and returns the first
 * match found, if any.
 */
template <class StringT, class IteratorT, class Comparator>
bool RFindInReadable_Impl(const StringT& aPattern, IteratorT& aSearchStart,
                          IteratorT& aSearchEnd, const Comparator& aCompare) {
  IteratorT patternStart, patternEnd, searchEnd = aSearchEnd;
  aPattern.BeginReading(patternStart);
  aPattern.EndReading(patternEnd);

  // Point to the last character in the pattern
  --patternEnd;
  // outer loop keeps searching till we run out of string to search
  while (aSearchStart != searchEnd) {
    // Point to the end position of the next possible match
    --searchEnd;

    // Check last character, if a match, explore further from here
    if (aCompare(patternEnd.get(), searchEnd.get(), 1, 1) == 0) {
      // We're at a potential match, let's see if we really hit one
      IteratorT testPattern(patternEnd);
      IteratorT testSearch(searchEnd);

      // inner loop verifies the potential match at the current position
      do {
        // if we verified all the way to the end of the pattern, then we found
        // it!
        if (testPattern == patternStart) {
          aSearchStart = testSearch;  // point to start of match
          aSearchEnd = ++searchEnd;   // point to end of match
          return true;
        }

        // if we got to end of the string we're searching before we hit the end
        // of the
        //  pattern, we'll never find what we're looking for
        if (testSearch == aSearchStart) {
          aSearchStart = aSearchEnd;
          return false;
        }

        // test previous character for a match
        --testPattern;
        --testSearch;
      } while (aCompare(testPattern.get(), testSearch.get(), 1, 1) == 0);
    }
  }

  aSearchStart = aSearchEnd;
  return false;
}

bool FindInReadable(const nsAString& aPattern,
                    nsAString::const_iterator& aSearchStart,
                    nsAString::const_iterator& aSearchEnd,
                    const nsStringComparator& aComparator) {
  return FindInReadable_Impl(aPattern, aSearchStart, aSearchEnd, aComparator);
}

bool FindInReadable(const nsACString& aPattern,
                    nsACString::const_iterator& aSearchStart,
                    nsACString::const_iterator& aSearchEnd,
                    const nsCStringComparator& aComparator) {
  return FindInReadable_Impl(aPattern, aSearchStart, aSearchEnd, aComparator);
}

bool CaseInsensitiveFindInReadable(const nsACString& aPattern,
                                   nsACString::const_iterator& aSearchStart,
                                   nsACString::const_iterator& aSearchEnd) {
  return FindInReadable_Impl(aPattern, aSearchStart, aSearchEnd,
                             nsCaseInsensitiveCStringComparator());
}

bool RFindInReadable(const nsAString& aPattern,
                     nsAString::const_iterator& aSearchStart,
                     nsAString::const_iterator& aSearchEnd,
                     const nsStringComparator& aComparator) {
  return RFindInReadable_Impl(aPattern, aSearchStart, aSearchEnd, aComparator);
}

bool RFindInReadable(const nsACString& aPattern,
                     nsACString::const_iterator& aSearchStart,
                     nsACString::const_iterator& aSearchEnd,
                     const nsCStringComparator& aComparator) {
  return RFindInReadable_Impl(aPattern, aSearchStart, aSearchEnd, aComparator);
}

bool FindCharInReadable(char16_t aChar, nsAString::const_iterator& aSearchStart,
                        const nsAString::const_iterator& aSearchEnd) {
  int32_t fragmentLength = aSearchEnd.get() - aSearchStart.get();

  const char16_t* charFoundAt =
      nsCharTraits<char16_t>::find(aSearchStart.get(), fragmentLength, aChar);
  if (charFoundAt) {
    aSearchStart.advance(charFoundAt - aSearchStart.get());
    return true;
  }

  aSearchStart.advance(fragmentLength);
  return false;
}

bool FindCharInReadable(char aChar, nsACString::const_iterator& aSearchStart,
                        const nsACString::const_iterator& aSearchEnd) {
  int32_t fragmentLength = aSearchEnd.get() - aSearchStart.get();

  const char* charFoundAt =
      nsCharTraits<char>::find(aSearchStart.get(), fragmentLength, aChar);
  if (charFoundAt) {
    aSearchStart.advance(charFoundAt - aSearchStart.get());
    return true;
  }

  aSearchStart.advance(fragmentLength);
  return false;
}

bool StringBeginsWith(const nsAString& aSource, const nsAString& aSubstring) {
  nsAString::size_type src_len = aSource.Length(),
                       sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, 0, sub_len).Equals(aSubstring);
}

bool StringBeginsWith(const nsAString& aSource, const nsAString& aSubstring,
                      const nsStringComparator& aComparator) {
  nsAString::size_type src_len = aSource.Length(),
                       sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, 0, sub_len).Equals(aSubstring, aComparator);
}

bool StringBeginsWith(const nsACString& aSource, const nsACString& aSubstring) {
  nsACString::size_type src_len = aSource.Length(),
                        sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, 0, sub_len).Equals(aSubstring);
}

bool StringBeginsWith(const nsACString& aSource, const nsACString& aSubstring,
                      const nsCStringComparator& aComparator) {
  nsACString::size_type src_len = aSource.Length(),
                        sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, 0, sub_len).Equals(aSubstring, aComparator);
}

bool StringEndsWith(const nsAString& aSource, const nsAString& aSubstring) {
  nsAString::size_type src_len = aSource.Length(),
                       sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, src_len - sub_len, sub_len).Equals(aSubstring);
}

bool StringEndsWith(const nsAString& aSource, const nsAString& aSubstring,
                    const nsStringComparator& aComparator) {
  nsAString::size_type src_len = aSource.Length(),
                       sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, src_len - sub_len, sub_len)
      .Equals(aSubstring, aComparator);
}

bool StringEndsWith(const nsACString& aSource, const nsACString& aSubstring) {
  nsACString::size_type src_len = aSource.Length(),
                        sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, src_len - sub_len, sub_len).Equals(aSubstring);
}

bool StringEndsWith(const nsACString& aSource, const nsACString& aSubstring,
                    const nsCStringComparator& aComparator) {
  nsACString::size_type src_len = aSource.Length(),
                        sub_len = aSubstring.Length();
  if (sub_len > src_len) {
    return false;
  }
  return Substring(aSource, src_len - sub_len, sub_len)
      .Equals(aSubstring, aComparator);
}

static const char16_t empty_buffer[1] = {'\0'};

const nsString& EmptyString() {
  static const nsDependentString sEmpty(empty_buffer);

  return sEmpty;
}

const nsCString& EmptyCString() {
  static const nsDependentCString sEmpty((const char*)empty_buffer);

  return sEmpty;
}

const nsString& VoidString() {
  static const nsString sNull(mozilla::detail::StringDataFlags::VOIDED);

  return sNull;
}

const nsCString& VoidCString() {
  static const nsCString sNull(mozilla::detail::StringDataFlags::VOIDED);

  return sNull;
}

int32_t CompareUTF8toUTF16(const nsACString& aUTF8String,
                           const nsAString& aUTF16String, bool* aErr) {
  const char* u8;
  const char* u8end;
  aUTF8String.BeginReading(u8);
  aUTF8String.EndReading(u8end);

  const char16_t* u16;
  const char16_t* u16end;
  aUTF16String.BeginReading(u16);
  aUTF16String.EndReading(u16end);

  for (;;) {
    if (u8 == u8end) {
      if (u16 == u16end) {
        return 0;
      }
      return -1;
    }
    if (u16 == u16end) {
      return 1;
    }
    // No need for ASCII optimization, since both NextChar()
    // calls get inlined.
    uint32_t scalar8 = UTF8CharEnumerator::NextChar(&u8, u8end, aErr);
    uint32_t scalar16 = UTF16CharEnumerator::NextChar(&u16, u16end, aErr);
    if (scalar16 == scalar8) {
      continue;
    }
    if (scalar8 < scalar16) {
      return -1;
    }
    return 1;
  }
}

void AppendUCS4ToUTF16(const uint32_t aSource, nsAString& aDest) {
  NS_ASSERTION(IS_VALID_CHAR(aSource), "Invalid UCS4 char");
  if (IS_IN_BMP(aSource)) {
    aDest.Append(char16_t(aSource));
  } else {
    aDest.Append(H_SURROGATE(aSource));
    aDest.Append(L_SURROGATE(aSource));
  }
}