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
|
/*
* (C) 1999 Lars Knoll (knoll@kde.org)
* Copyright (C) 2004, 2005, 2006, 2007, 2008, 2010, 2012 Apple Inc. All rights
* reserved.
* Copyright (C) 2007-2009 Torch Mobile, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public License
* along with this library; see the file COPYING.LIB. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*/
#include "third_party/blink/renderer/platform/wtf/text/wtf_string.h"
#include <locale.h>
#include <stdarg.h>
#include <algorithm>
#include <limits>
#include <string_view>
#include "base/compiler_specific.h"
#include "base/functional/callback.h"
#include "base/logging.h"
#include "base/numerics/safe_conversions.h"
#include "base/strings/span_printf.h"
#include "build/build_config.h"
#include "third_party/blink/renderer/platform/wtf/dtoa.h"
#include "third_party/blink/renderer/platform/wtf/math_extras.h"
#include "third_party/blink/renderer/platform/wtf/size_assertions.h"
#include "third_party/blink/renderer/platform/wtf/text/ascii_ctype.h"
#include "third_party/blink/renderer/platform/wtf/text/case_map.h"
#include "third_party/blink/renderer/platform/wtf/text/character_names.h"
#include "third_party/blink/renderer/platform/wtf/text/character_visitor.h"
#include "third_party/blink/renderer/platform/wtf/text/code_point_iterator.h"
#include "third_party/blink/renderer/platform/wtf/text/copy_lchars_from_uchar_source.h"
#include "third_party/blink/renderer/platform/wtf/text/string_builder.h"
#include "third_party/blink/renderer/platform/wtf/text/string_utf8_adaptor.h"
#include "third_party/blink/renderer/platform/wtf/text/unicode.h"
#include "third_party/blink/renderer/platform/wtf/text/utf8.h"
#include "third_party/blink/renderer/platform/wtf/vector.h"
#include "third_party/perfetto/include/perfetto/tracing/traced_value.h"
namespace WTF {
ASSERT_SIZE(String, void*);
// Construct a string with UTF-16 data.
String::String(base::span<const UChar> utf16_data)
: impl_(utf16_data.data() ? StringImpl::Create(utf16_data) : nullptr) {}
// Construct a string with UTF-16 data, from a null-terminated source.
String::String(const UChar* str) {
if (!str) {
return;
}
impl_ = StringImpl::Create(std::u16string_view(str));
}
// Construct a string with latin1 data.
String::String(base::span<const LChar> latin1_data)
: impl_(latin1_data.data() ? StringImpl::Create(latin1_data) : nullptr) {}
int CodeUnitCompare(const String& a, const String& b) {
return CodeUnitCompare(a.Impl(), b.Impl());
}
int CodeUnitCompareIgnoringASCIICase(const String& a, const char* b) {
return CodeUnitCompareIgnoringASCIICase(a.Impl(),
reinterpret_cast<const LChar*>(b));
}
wtf_size_t String::Find(base::RepeatingCallback<bool(UChar)> match_callback,
wtf_size_t index) const {
return impl_ ? impl_->Find(match_callback, index) : kNotFound;
}
UChar32 String::CharacterStartingAt(unsigned i) const {
if (!impl_ || i >= impl_->length())
return 0;
return impl_->CharacterStartingAt(i);
}
CodePointIterator String::begin() const {
return CodePointIterator(*this);
}
CodePointIterator String::end() const {
return CodePointIterator::End(*this);
}
void String::Ensure16Bit() {
if (IsNull())
return;
if (!Is8Bit())
return;
if (!empty()) {
impl_ = Make16BitFrom8BitSource(impl_->Span8()).ReleaseImpl();
} else {
impl_ = StringImpl::empty16_bit_;
}
}
void String::Truncate(unsigned length) {
if (impl_)
impl_ = impl_->Truncate(length);
}
void String::Remove(unsigned start, unsigned length_to_remove) {
if (impl_)
impl_ = impl_->Remove(start, length_to_remove);
}
String String::Substring(unsigned pos, unsigned len) const {
if (!impl_)
return String();
return impl_->Substring(pos, len);
}
String String::DeprecatedLower() const {
if (!impl_)
return String();
return CaseMap::FastToLowerInvariant(impl_.get());
}
String String::LowerASCII() const {
if (!impl_)
return String();
return impl_->LowerASCII();
}
String String::UpperASCII() const {
if (!impl_)
return String();
return impl_->UpperASCII();
}
unsigned String::LengthWithStrippedWhiteSpace() const {
if (!impl_) {
return 0;
}
return impl_->LengthWithStrippedWhiteSpace();
}
String String::StripWhiteSpace() const {
if (!impl_)
return String();
return impl_->StripWhiteSpace();
}
String String::StripWhiteSpace(IsWhiteSpaceFunctionPtr is_white_space) const {
if (!impl_)
return String();
return impl_->StripWhiteSpace(is_white_space);
}
String String::SimplifyWhiteSpace(StripBehavior strip_behavior) const {
if (!impl_)
return String();
return impl_->SimplifyWhiteSpace(strip_behavior);
}
String String::SimplifyWhiteSpace(IsWhiteSpaceFunctionPtr is_white_space,
StripBehavior strip_behavior) const {
if (!impl_)
return String();
return impl_->SimplifyWhiteSpace(is_white_space, strip_behavior);
}
String String::RemoveCharacters(CharacterMatchFunctionPtr find_match) const {
if (!impl_)
return String();
return impl_->RemoveCharacters(find_match);
}
String String::FoldCase() const {
if (!impl_)
return String();
return impl_->FoldCase();
}
String String::Format(const char* format, ...) {
// vsnprintf is locale sensitive when converting floats to strings
// and we need it to always use a decimal point. Double check that
// the locale is compatible, and also that it is the default "C"
// locale so that we aren't just lucky. Android's locales work
// differently so can't check the same way there.
DCHECK_EQ(UNSAFE_TODO(strcmp(localeconv()->decimal_point, ".")), 0);
#if !BUILDFLAG(IS_ANDROID)
DCHECK_EQ(UNSAFE_TODO(strcmp(setlocale(LC_NUMERIC, NULL), "C")), 0);
#endif // !BUILDFLAG(IS_ANDROID)
va_list args;
// TODO(esprehn): base uses 1024, maybe we should use a bigger size too.
static const unsigned kDefaultSize = 256;
Vector<char, kDefaultSize> buffer(kDefaultSize);
va_start(args, format);
int length = base::VSpanPrintf(buffer, format, args);
va_end(args);
// TODO(esprehn): Negative result can only happen if there's an encoding
// error, what's the locale set to inside blink? Can this happen?
if (length < 0) {
return String();
}
if (static_cast<unsigned>(length) >= buffer.size()) {
// Buffer is too small to hold the full result. Resize larger and try
// again. `length` doesn't include the NUL terminator so add space for
// it when growing.
if (length == std::numeric_limits<int>::max()) {
// But length can't grow if it is already at max size (and signed
// overflow below would be UB).
return String();
}
buffer.Grow(length + 1);
// We need to call va_end() and then va_start() each time we use args, as
// the contents of args is undefined after the call to vsnprintf according
// to http://man.cx/snprintf(3)
//
// Not calling va_end/va_start here happens to work on lots of systems, but
// fails e.g. on 64bit Linux.
va_start(args, format);
length = base::VSpanPrintf(buffer, format, args);
va_end(args);
// TODO(tsepez): can we get an error the second time around if
// we didn't get an error the first time? Can this happen?
if (length < 0) {
return String();
}
}
// Note that first() will CHECK() if length is OOB.
return String(base::span(buffer).first(base::checked_cast<size_t>(length)));
}
String String::EncodeForDebugging() const {
return StringView(*this).EncodeForDebugging();
}
String String::Number(float number) {
return Number(static_cast<double>(number));
}
String String::Number(double number, unsigned precision) {
NumberToStringBuffer buffer;
return String(NumberToFixedPrecisionString(number, precision, buffer));
}
String String::NumberToStringECMAScript(double number) {
NumberToStringBuffer buffer;
return String(NumberToString(number, buffer));
}
String String::NumberToStringFixedWidth(double number,
unsigned decimal_places) {
NumberToStringBuffer buffer;
return String(NumberToFixedWidthString(number, decimal_places, buffer));
}
int String::ToIntStrict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToInt(NumberParsingOptions::Strict(), ok);
}
unsigned String::ToUIntStrict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToUInt(NumberParsingOptions::Strict(), ok);
}
unsigned String::HexToUIntStrict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->HexToUIntStrict(ok);
}
uint64_t String::HexToUInt64Strict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->HexToUInt64Strict(ok);
}
int64_t String::ToInt64Strict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToInt64(NumberParsingOptions::Strict(), ok);
}
uint64_t String::ToUInt64Strict(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToUInt64(NumberParsingOptions::Strict(), ok);
}
int String::ToInt(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToInt(NumberParsingOptions::Loose(), ok);
}
unsigned String::ToUInt(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0;
}
return impl_->ToUInt(NumberParsingOptions::Loose(), ok);
}
double String::ToDouble(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0.0;
}
return impl_->ToDouble(ok);
}
float String::ToFloat(bool* ok) const {
if (!impl_) {
if (ok)
*ok = false;
return 0.0f;
}
return impl_->ToFloat(ok);
}
void String::Split(const StringView& separator,
bool allow_empty_entries,
Vector<String>& result) const {
result.clear();
unsigned start_pos = 0;
wtf_size_t end_pos;
while ((end_pos = Find(separator, start_pos)) != kNotFound) {
if (allow_empty_entries || start_pos != end_pos)
result.push_back(Substring(start_pos, end_pos - start_pos));
start_pos = end_pos + separator.length();
}
if (allow_empty_entries || start_pos != length())
result.push_back(Substring(start_pos));
}
void String::Split(UChar separator,
bool allow_empty_entries,
Vector<String>& result) const {
result.clear();
unsigned start_pos = 0;
wtf_size_t end_pos;
while ((end_pos = find(separator, start_pos)) != kNotFound) {
if (allow_empty_entries || start_pos != end_pos)
result.push_back(Substring(start_pos, end_pos - start_pos));
start_pos = end_pos + 1;
}
if (allow_empty_entries || start_pos != length())
result.push_back(Substring(start_pos));
}
std::string String::Ascii() const {
// Printable ASCII characters 32..127 and the null character are
// preserved, characters outside of this range are converted to '?'.
unsigned length = this->length();
if (!length)
return std::string();
std::string ascii(length, '\0');
VisitCharacters(*this, [&ascii](auto chars) {
for (size_t i = 0; i < chars.size(); ++i) {
const auto ch = chars[i];
ascii[i] = ch && (ch < 0x20 || ch > 0x7f) ? '?' : static_cast<char>(ch);
}
});
return ascii;
}
std::string String::Latin1() const {
// Basic Latin1 (ISO) encoding - Unicode characters 0..255 are
// preserved, characters outside of this range are converted to '?'.
unsigned length = this->length();
if (!length)
return std::string();
if (Is8Bit()) {
return std::string(base::as_string_view(Span8()));
}
std::string latin1(length, '\0');
base::span<const UChar> characters = Span16();
for (size_t i = 0; i < characters.size(); ++i) {
const UChar ch = characters[i];
latin1[i] = ch > 0xff ? '?' : static_cast<char>(ch);
}
return latin1;
}
String String::Make8BitFrom16BitSource(base::span<const UChar> source) {
if (source.empty()) {
return g_empty_string;
}
const wtf_size_t length = base::checked_cast<wtf_size_t>(source.size());
base::span<LChar> destination;
String result = String::CreateUninitialized(length, destination);
CopyLCharsFromUCharSource(destination.data(), source.data(), length);
return result;
}
String String::Make16BitFrom8BitSource(base::span<const LChar> source) {
if (source.empty()) {
return g_empty_string16_bit;
}
base::span<UChar> destination;
String result = String::CreateUninitialized(source.size(), destination);
StringImpl::CopyChars(destination, source);
return result;
}
String String::FromUTF8(base::span<const uint8_t> bytes) {
const uint8_t* string_start = bytes.data();
wtf_size_t length = base::checked_cast<wtf_size_t>(bytes.size());
if (!string_start)
return String();
if (!length)
return g_empty_string;
ASCIIStringAttributes attributes = CharacterAttributes(bytes);
if (attributes.contains_only_ascii)
return StringImpl::Create(bytes, attributes);
Vector<UChar, 1024> buffer(length);
unicode::ConversionResult result =
unicode::ConvertUTF8ToUTF16(bytes, base::span(buffer));
if (result.status != unicode::kConversionOK) {
return String();
}
return StringImpl::Create(result.converted);
}
String String::FromUTF8(const char* s) {
if (!s) {
return String();
}
return FromUTF8(std::string_view(s));
}
String String::FromUTF8WithLatin1Fallback(base::span<const uint8_t> bytes) {
String utf8 = FromUTF8(bytes);
if (!utf8)
return String(bytes);
return utf8;
}
std::ostream& operator<<(std::ostream& out, const String& string) {
return out << string.EncodeForDebugging().Utf8();
}
#ifndef NDEBUG
void String::Show() const {
DLOG(INFO) << *this;
}
#endif
void String::WriteIntoTrace(perfetto::TracedValue context) const {
if (!length()) {
std::move(context).WriteString("", 0);
return;
}
// Avoid the default String to StringView conversion since it calls
// AddRef() on the StringImpl and this method is sometimes called in
// places where that triggers DCHECKs.
StringUTF8Adaptor adaptor(Is8Bit() ? StringView(Span8())
: StringView(Span16()));
std::move(context).WriteString(adaptor.data(), adaptor.size());
}
} // namespace WTF
|