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.

Implementation

Mercurial (81f420f057e4)

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
/* -*- 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/. */
// IWYU pragma: private, include "nsString.h"

#ifndef nsReadableUtils_h___
#define nsReadableUtils_h___

/**
 * I guess all the routines in this file are all mis-named.
 * According to our conventions, they should be |NS_xxx|.
 */

#include "mozilla/Assertions.h"
#include "nsAString.h"
#include "mozilla/TextUtils.h"

#include "nsTArrayForwardDeclare.h"

// From the nsstring crate
extern "C" {
bool nsstring_fallible_append_utf8_impl(nsAString* aThis, const char* aOther,
                                        size_t aOtherLen, size_t aOldLen);

bool nsstring_fallible_append_latin1_impl(nsAString* aThis, const char* aOther,
                                          size_t aOtherLen, size_t aOldLen,
                                          bool aAllowShrinking);

bool nscstring_fallible_append_utf16_to_utf8_impl(nsACString* aThis,
                                                  const char16_t*,
                                                  size_t aOtherLen,
                                                  size_t aOldLen);

bool nscstring_fallible_append_utf16_to_latin1_lossy_impl(nsACString* aThis,
                                                          const char16_t*,
                                                          size_t aOtherLen,
                                                          size_t aOldLen,
                                                          bool aAllowShrinking);

bool nscstring_fallible_append_utf8_to_latin1_lossy_check(
    nsACString* aThis, const nsACString* aOther, size_t aOldLen);

bool nscstring_fallible_append_latin1_to_utf8_check(nsACString* aThis,
                                                    const nsACString* aOther,
                                                    size_t aOldLen);
}

inline size_t Distance(const nsReadingIterator<char16_t>& aStart,
                       const nsReadingIterator<char16_t>& aEnd) {
  MOZ_ASSERT(aStart.get() <= aEnd.get());
  return static_cast<size_t>(aEnd.get() - aStart.get());
}

inline size_t Distance(const nsReadingIterator<char>& aStart,
                       const nsReadingIterator<char>& aEnd) {
  MOZ_ASSERT(aStart.get() <= aEnd.get());
  return static_cast<size_t>(aEnd.get() - aStart.get());
}

// NOTE: Operations that don't need an operand to be an XPCOM string
// are in mozilla/TextUtils.h and mozilla/Utf8.h.

// UTF-8 to UTF-16
// Invalid UTF-8 byte sequences are replaced with the REPLACEMENT CHARACTER.

inline MOZ_MUST_USE bool CopyUTF8toUTF16(mozilla::Span<const char> aSource,
                                         nsAString& aDest,
                                         const mozilla::fallible_t&) {
  return nsstring_fallible_append_utf8_impl(&aDest, aSource.Elements(),
                                            aSource.Length(), 0);
}

inline void CopyUTF8toUTF16(mozilla::Span<const char> aSource,
                            nsAString& aDest) {
  if (MOZ_UNLIKELY(!CopyUTF8toUTF16(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool AppendUTF8toUTF16(mozilla::Span<const char> aSource,
                                           nsAString& aDest,
                                           const mozilla::fallible_t&) {
  return nsstring_fallible_append_utf8_impl(&aDest, aSource.Elements(),
                                            aSource.Length(), aDest.Length());
}

inline void AppendUTF8toUTF16(mozilla::Span<const char> aSource,
                              nsAString& aDest) {
  if (MOZ_UNLIKELY(!AppendUTF8toUTF16(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

// Latin1 to UTF-16
// Interpret each incoming unsigned byte value as a Unicode scalar value (not
// windows-1252!). The function names say "ASCII" instead of "Latin1" for
// legacy reasons.

inline MOZ_MUST_USE bool CopyASCIItoUTF16(mozilla::Span<const char> aSource,
                                          nsAString& aDest,
                                          const mozilla::fallible_t&) {
  return nsstring_fallible_append_latin1_impl(&aDest, aSource.Elements(),
                                              aSource.Length(), 0, true);
}

inline void CopyASCIItoUTF16(mozilla::Span<const char> aSource,
                             nsAString& aDest) {
  if (MOZ_UNLIKELY(!CopyASCIItoUTF16(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool AppendASCIItoUTF16(mozilla::Span<const char> aSource,
                                            nsAString& aDest,
                                            const mozilla::fallible_t&) {
  return nsstring_fallible_append_latin1_impl(
      &aDest, aSource.Elements(), aSource.Length(), aDest.Length(), false);
}

inline void AppendASCIItoUTF16(mozilla::Span<const char> aSource,
                               nsAString& aDest) {
  if (MOZ_UNLIKELY(!AppendASCIItoUTF16(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

// UTF-16 to UTF-8
// Unpaired surrogates are replaced with the REPLACEMENT CHARACTER.

inline MOZ_MUST_USE bool CopyUTF16toUTF8(mozilla::Span<const char16_t> aSource,
                                         nsACString& aDest,
                                         const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf16_to_utf8_impl(
      &aDest, aSource.Elements(), aSource.Length(), 0);
}

inline void CopyUTF16toUTF8(mozilla::Span<const char16_t> aSource,
                            nsACString& aDest) {
  if (MOZ_UNLIKELY(!CopyUTF16toUTF8(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool AppendUTF16toUTF8(
    mozilla::Span<const char16_t> aSource, nsACString& aDest,
    const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf16_to_utf8_impl(
      &aDest, aSource.Elements(), aSource.Length(), aDest.Length());
}

inline void AppendUTF16toUTF8(mozilla::Span<const char16_t> aSource,
                              nsACString& aDest) {
  if (MOZ_UNLIKELY(!AppendUTF16toUTF8(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

// UTF-16 to Latin1
// If all code points in the input are below U+0100, represents each scalar
// value as an unsigned byte. (This is not windows-1252!) If there are code
// points above U+00FF, memory-safely produces garbage and will likely start
// asserting in future debug builds. The nature of the garbage may differ
// based on CPU architecture and must not be relied upon. The names say
// "ASCII" instead of "Latin1" for legacy reasons.

inline MOZ_MUST_USE bool LossyCopyUTF16toASCII(
    mozilla::Span<const char16_t> aSource, nsACString& aDest,
    const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf16_to_latin1_lossy_impl(
      &aDest, aSource.Elements(), aSource.Length(), 0, true);
}

inline void LossyCopyUTF16toASCII(mozilla::Span<const char16_t> aSource,
                                  nsACString& aDest) {
  if (MOZ_UNLIKELY(!LossyCopyUTF16toASCII(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool LossyAppendUTF16toASCII(
    mozilla::Span<const char16_t> aSource, nsACString& aDest,
    const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf16_to_latin1_lossy_impl(
      &aDest, aSource.Elements(), aSource.Length(), aDest.Length(), false);
}

inline void LossyAppendUTF16toASCII(mozilla::Span<const char16_t> aSource,
                                    nsACString& aDest) {
  if (MOZ_UNLIKELY(
          !LossyAppendUTF16toASCII(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

// Latin1 to UTF-8
// Interpret each incoming unsigned byte value as a Unicode scalar value (not
// windows-1252!).
// If the input is ASCII, the heap-allocated nsStringBuffer is shared if
// possible.

inline MOZ_MUST_USE bool CopyLatin1toUTF8(const nsACString& aSource,
                                          nsACString& aDest,
                                          const mozilla::fallible_t&) {
  return nscstring_fallible_append_latin1_to_utf8_check(&aDest, &aSource, 0);
}

inline void CopyLatin1toUTF8(const nsACString& aSource, nsACString& aDest) {
  if (MOZ_UNLIKELY(!CopyLatin1toUTF8(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool AppendLatin1toUTF8(const nsACString& aSource,
                                            nsACString& aDest,
                                            const mozilla::fallible_t&) {
  return nscstring_fallible_append_latin1_to_utf8_check(&aDest, &aSource,
                                                        aDest.Length());
}

inline void AppendLatin1toUTF8(const nsACString& aSource, nsACString& aDest) {
  if (MOZ_UNLIKELY(!AppendLatin1toUTF8(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

// UTF-8 to Latin1
// If all code points in the input are below U+0100, represents each scalar
// value as an unsigned byte. (This is not windows-1252!) If there are code
// points above U+00FF, memory-safely produces garbage in release builds and
// asserts in debug builds. The nature of the garbage may differ
// based on CPU architecture and must not be relied upon.
// If the input is ASCII, the heap-allocated nsStringBuffer is shared if
// possible.

inline MOZ_MUST_USE bool LossyCopyUTF8toLatin1(const nsACString& aSource,
                                               nsACString& aDest,
                                               const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf8_to_latin1_lossy_check(&aDest, &aSource,
                                                              0);
}

inline void LossyCopyUTF8toLatin1(const nsACString& aSource,
                                  nsACString& aDest) {
  if (MOZ_UNLIKELY(!LossyCopyUTF8toLatin1(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aSource.Length());
  }
}

inline MOZ_MUST_USE bool LossyAppendUTF8toLatin1(const nsACString& aSource,
                                                 nsACString& aDest,
                                                 const mozilla::fallible_t&) {
  return nscstring_fallible_append_utf8_to_latin1_lossy_check(&aDest, &aSource,
                                                              aDest.Length());
}

inline void LossyAppendUTF8toLatin1(const nsACString& aSource,
                                    nsACString& aDest) {
  if (MOZ_UNLIKELY(
          !LossyAppendUTF8toLatin1(aSource, aDest, mozilla::fallible))) {
    aDest.AllocFailed(aDest.Length() + aSource.Length());
  }
}

/**
 * Returns a new |char| buffer containing a zero-terminated copy of |aSource|.
 *
 * Allocates and returns a new |char| buffer which you must free with |free|.
 * Performs a conversion with LossyConvertUTF16toLatin1() writing into the
 * newly-allocated buffer.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource a 16-bit wide string
 * @return a new |char| buffer you must free with |free|.
 */
char* ToNewCString(const nsAString& aSource);

/**
 * Returns a new |char| buffer containing a zero-terminated copy of |aSource|.
 *
 * Allocates and returns a new |char| buffer which you must free with |free|.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource an 8-bit wide string
 * @return a new |char| buffer you must free with |free|.
 */
char* ToNewCString(const nsACString& aSource);

/**
 * Returns a new |char| buffer containing a zero-terminated copy of |aSource|.
 *
 * Allocates and returns a new |char| buffer which you must free with
 * |free|.
 * Performs an encoding conversion from a UTF-16 string to a UTF-8 string with
 * unpaired surrogates replaced with the REPLACEMENT CHARACTER copying
 * |aSource| to your new buffer.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource a UTF-16 string (made of char16_t's)
 * @param aUTF8Count the number of 8-bit units that was returned
 * @return a new |char| buffer you must free with |free|.
 */

char* ToNewUTF8String(const nsAString& aSource, uint32_t* aUTF8Count = nullptr);

/**
 * Returns a new |char16_t| buffer containing a zero-terminated copy of
 * |aSource|.
 *
 * Allocates and returns a new |char16_t| buffer which you must free with
 * |free|.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource a UTF-16 string
 * @return a new |char16_t| buffer you must free with |free|.
 */
char16_t* ToNewUnicode(const nsAString& aSource);

/**
 * Returns a new |char16_t| buffer containing a zero-terminated copy of
 * |aSource|.
 *
 * Allocates and returns a new |char16_t| buffer which you must free with
 * |free|.
 *
 * Performs an encoding conversion by 0-padding 8-bit wide characters up to
 * 16-bits wide (i.e. Latin1 to UTF-16 conversion) while copying |aSource|
 * to your new buffer.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource a Latin1 string
 * @return a new |char16_t| buffer you must free with |free|.
 */
char16_t* ToNewUnicode(const nsACString& aSource);

/**
 * Returns a new |char16_t| buffer containing a zero-terminated copy
 * of |aSource|.
 *
 * Allocates and returns a new |char| buffer which you must free with
 * |free|.  Performs an encoding conversion from UTF-8 to UTF-16
 * while copying |aSource| to your new buffer.  Malformed byte sequences
 * are replaced with the REPLACEMENT CHARACTER.
 *
 * The new buffer is zero-terminated, but that may not help you if |aSource|
 * contains embedded nulls.
 *
 * @param aSource an 8-bit wide string, UTF-8 encoded
 * @param aUTF16Count the number of 16-bit units that was returned
 * @return a new |char16_t| buffer you must free with |free|.
 *         (UTF-16 encoded)
 */
char16_t* UTF8ToNewUnicode(const nsACString& aSource,
                           uint32_t* aUTF16Count = nullptr);

/**
 * Copies |aLength| 16-bit code units from the start of |aSource| to the
 * |char16_t| buffer |aDest|.
 *
 * After this operation |aDest| is not null terminated.
 *
 * @param aSource a UTF-16 string
 * @param aSrcOffset start offset in the source string
 * @param aDest a |char16_t| buffer
 * @param aLength the number of 16-bit code units to copy
 * @return pointer to destination buffer - identical to |aDest|
 */
char16_t* CopyUnicodeTo(const nsAString& aSource, uint32_t aSrcOffset,
                        char16_t* aDest, uint32_t aLength);

/**
 * Replaces unpaired surrogates with U+FFFD in the argument.
 *
 * Copies a shared string buffer or an otherwise read-only
 * buffer only if there are unpaired surrogates.
 */
inline MOZ_MUST_USE bool EnsureUTF16Validity(nsAString& aString) {
  uint32_t upTo = mozilla::Utf16ValidUpTo(aString);
  uint32_t len = aString.Length();
  if (upTo == len) {
    return true;
  }
  char16_t* ptr = aString.BeginWriting(mozilla::fallible);
  if (!ptr) {
    return false;
  }
  auto span = mozilla::MakeSpan(ptr, len);
  span[upTo] = 0xFFFD;
  mozilla::EnsureUtf16ValiditySpan(span.From(upTo + 1));
  return true;
}

bool ParseString(const nsACString& aAstring, char aDelimiter,
                 nsTArray<nsCString>& aArray);

/**
 * Converts case in place in the argument string.
 */
void ToUpperCase(nsACString&);

void ToLowerCase(nsACString&);

void ToUpperCase(nsACString&);

void ToLowerCase(nsACString&);

/**
 * Converts case from string aSource to aDest.
 */
void ToUpperCase(const nsACString& aSource, nsACString& aDest);

void ToLowerCase(const nsACString& aSource, nsACString& aDest);

/**
 * Finds the leftmost occurrence of |aPattern|, if any in the range
 * |aSearchStart|..|aSearchEnd|.
 *
 * Returns |true| if a match was found, and adjusts |aSearchStart| and
 * |aSearchEnd| to point to the match.  If no match was found, returns |false|
 * and makes |aSearchStart == aSearchEnd|.
 *
 * Currently, this is equivalent to the O(m*n) implementation previously on
 * |ns[C]String|.
 *
 * If we need something faster, then we can implement that later.
 */

bool FindInReadable(const nsAString& aPattern, nsAString::const_iterator&,
                    nsAString::const_iterator&,
                    const nsStringComparator& = nsDefaultStringComparator());
bool FindInReadable(const nsACString& aPattern, nsACString::const_iterator&,
                    nsACString::const_iterator&,
                    const nsCStringComparator& = nsDefaultCStringComparator());

/* sometimes we don't care about where the string was, just that we
 * found it or not */
inline bool FindInReadable(
    const nsAString& aPattern, const nsAString& aSource,
    const nsStringComparator& aCompare = nsDefaultStringComparator()) {
  nsAString::const_iterator start, end;
  aSource.BeginReading(start);
  aSource.EndReading(end);
  return FindInReadable(aPattern, start, end, aCompare);
}

inline bool FindInReadable(
    const nsACString& aPattern, const nsACString& aSource,
    const nsCStringComparator& aCompare = nsDefaultCStringComparator()) {
  nsACString::const_iterator start, end;
  aSource.BeginReading(start);
  aSource.EndReading(end);
  return FindInReadable(aPattern, start, end, aCompare);
}

bool CaseInsensitiveFindInReadable(const nsACString& aPattern,
                                   nsACString::const_iterator&,
                                   nsACString::const_iterator&);

/**
 * Finds the rightmost occurrence of |aPattern|
 * Returns |true| if a match was found, and adjusts |aSearchStart| and
 * |aSearchEnd| to point to the match.  If no match was found, returns |false|
 * and makes |aSearchStart == aSearchEnd|.
 */
bool RFindInReadable(const nsAString& aPattern, nsAString::const_iterator&,
                     nsAString::const_iterator&,
                     const nsStringComparator& = nsDefaultStringComparator());
bool RFindInReadable(const nsACString& aPattern, nsACString::const_iterator&,
                     nsACString::const_iterator&,
                     const nsCStringComparator& = nsDefaultCStringComparator());

/**
 * Finds the leftmost occurrence of |aChar|, if any in the range
 * |aSearchStart|..|aSearchEnd|.
 *
 * Returns |true| if a match was found, and adjusts |aSearchStart| to
 * point to the match.  If no match was found, returns |false| and
 * makes |aSearchStart == aSearchEnd|.
 */
bool FindCharInReadable(char16_t aChar, nsAString::const_iterator& aSearchStart,
                        const nsAString::const_iterator& aSearchEnd);
bool FindCharInReadable(char aChar, nsACString::const_iterator& aSearchStart,
                        const nsACString::const_iterator& aSearchEnd);

bool StringBeginsWith(const nsAString& aSource, const nsAString& aSubstring);
bool StringBeginsWith(const nsAString& aSource, const nsAString& aSubstring,
                      const nsStringComparator& aComparator);
bool StringBeginsWith(const nsACString& aSource, const nsACString& aSubstring);
bool StringBeginsWith(const nsACString& aSource, const nsACString& aSubstring,
                      const nsCStringComparator& aComparator);
bool StringEndsWith(const nsAString& aSource, const nsAString& aSubstring);
bool StringEndsWith(const nsAString& aSource, const nsAString& aSubstring,
                    const nsStringComparator& aComparator);
bool StringEndsWith(const nsACString& aSource, const nsACString& aSubstring);
bool StringEndsWith(const nsACString& aSource, const nsACString& aSubstring,
                    const nsCStringComparator& aComparator);

const nsString& EmptyString();
const nsCString& EmptyCString();

const nsString& VoidString();
const nsCString& VoidCString();

/**
 * Compare a UTF-8 string to an UTF-16 string.
 *
 * Returns 0 if the strings are equal, -1 if aUTF8String is less
 * than aUTF16Count, and 1 in the reverse case. Errors are replaced
 * with U+FFFD and then the U+FFFD is compared as if it had occurred
 * in the input. If aErr is not nullptr, *aErr is set to true if
 * either string had malformed sequences.
 */
int32_t CompareUTF8toUTF16(const nsACString& aUTF8String,
                           const nsAString& aUTF16String, bool* aErr = nullptr);

void AppendUCS4ToUTF16(const uint32_t aSource, nsAString& aDest);

#endif  // !defined(nsReadableUtils_h___)