File: WTFString.cpp

package info (click to toggle)
webkit2gtk 2.48.3-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, trixie
  • size: 429,620 kB
  • sloc: cpp: 3,696,936; javascript: 194,444; ansic: 169,997; python: 46,499; asm: 19,276; ruby: 18,528; perl: 16,602; xml: 4,650; yacc: 2,360; sh: 2,098; java: 1,993; lex: 1,327; pascal: 366; makefile: 298
file content (634 lines) | stat: -rw-r--r-- 19,083 bytes parent folder | download | duplicates (6)
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
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
/*
 * (C) 1999 Lars Knoll (knoll@kde.org)
 * Copyright (C) 2004-2023 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 "config.h"
#include <wtf/text/WTFString.h>

#include <wtf/ASCIICType.h>
#include <wtf/DataLog.h>
#include <wtf/HexNumber.h>
#include <wtf/NeverDestroyed.h>
#include <wtf/StdLibExtras.h>
#include <wtf/Vector.h>
#include <wtf/dtoa.h>
#include <wtf/text/CString.h>
#include <wtf/text/IntegerToStringConversion.h>
#include <wtf/text/MakeString.h>
#include <wtf/text/StringBuilder.h>
#include <wtf/text/StringToIntegerConversion.h>
#include <wtf/unicode/CharacterNames.h>
#include <wtf/unicode/UTF8Conversion.h>

namespace WTF {

// Construct a string with UTF-16 data.
String::String(std::span<const UChar> characters)
    : m_impl(characters.data() ? RefPtr { StringImpl::create(characters) } : nullptr)
{
}

// Construct a string with latin1 data.
String::String(std::span<const LChar> characters)
    : m_impl(characters.data() ? RefPtr { StringImpl::create(characters) } : nullptr)
{
}

String::String(std::span<const char> characters)
    : m_impl(characters.data() ? RefPtr { StringImpl::create(byteCast<uint8_t>(characters)) } : nullptr)
{
}

// Construct a string with Latin-1 data, from a null-terminated source.
String::String(const char* nullTerminatedString)
    : m_impl(nullTerminatedString ? RefPtr { StringImpl::createFromCString(nullTerminatedString) } : nullptr)
{
}

int codePointCompare(const String& a, const String& b)
{
    return codePointCompare(a.impl(), b.impl());
}

char32_t String::characterStartingAt(unsigned i) const
{
    if (!m_impl || i >= m_impl->length())
        return 0;
    return m_impl->characterStartingAt(i);
}

String makeStringByJoining(std::span<const String> strings, const String& separator)
{
    StringBuilder builder;
    for (const auto& string : strings) {
        if (builder.isEmpty())
            builder.append(string);
        else
            builder.append(separator, string);
    }
    return builder.toString();
}

String makeStringByRemoving(const String& string, unsigned position, unsigned lengthToRemove)
{
    if (!lengthToRemove)
        return string;
    auto length = string.length();
    if (position >= length)
        return string;
    lengthToRemove = std::min(lengthToRemove, length - position);
    StringView view { string };
    return makeString(view.left(position), view.substring(position + lengthToRemove));
}

String String::substringSharingImpl(unsigned offset, unsigned length) const
{
    // FIXME: We used to check against a limit of Heap::minExtraCost / sizeof(UChar).

    unsigned stringLength = this->length();
    offset = std::min(offset, stringLength);
    length = std::min(length, stringLength - offset);

    if (!offset && length == stringLength)
        return *this;
    return StringImpl::createSubstringSharingImpl(*m_impl, offset, length);
}

String String::convertToASCIILowercase() const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToASCIILowercase() : String { };
}

String String::convertToASCIIUppercase() const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToASCIIUppercase() : String { };
}

String String::convertToLowercaseWithoutLocale() const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToLowercaseWithoutLocale() : String { };
}

String String::convertToLowercaseWithoutLocaleStartingAtFailingIndex8Bit(unsigned failingIndex) const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToLowercaseWithoutLocaleStartingAtFailingIndex8Bit(failingIndex) : String { };
}

String String::convertToUppercaseWithoutLocale() const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToUppercaseWithoutLocale() : String { };
}

String String::convertToLowercaseWithLocale(const AtomString& localeIdentifier) const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToLowercaseWithLocale(localeIdentifier) : String { };
}

String String::convertToUppercaseWithLocale(const AtomString& localeIdentifier) const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->convertToUppercaseWithLocale(localeIdentifier) : String { };
}

String String::trim(CodeUnitMatchFunction predicate) const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->trim(predicate) : String { };
}

String String::simplifyWhiteSpace(CodeUnitMatchFunction isWhiteSpace) const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->simplifyWhiteSpace(isWhiteSpace) : String { };
}

String String::foldCase() const
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->foldCase() : String { };
}

Expected<Vector<UChar>, UTF8ConversionError> String::charactersWithoutNullTermination() const
{
    Vector<UChar> result;
    if (!m_impl)
        return result;

    if (!result.tryReserveInitialCapacity(length() + 1))
        return makeUnexpected(UTF8ConversionError::OutOfMemory);

    if (is8Bit())
        result.append(span8());
    else
        result.append(span16());

    return result;
}

Expected<Vector<UChar>, UTF8ConversionError> String::charactersWithNullTermination() const
{
    auto result = charactersWithoutNullTermination();
    if (result)
        result.value().append(0);
    return result;
}

String String::number(int number)
{
    return numberToStringSigned<String>(number);
}

String String::number(unsigned number)
{
    return numberToStringUnsigned<String>(number);
}

String String::number(long number)
{
    return numberToStringSigned<String>(number);
}

String String::number(unsigned long number)
{
    return numberToStringUnsigned<String>(number);
}

String String::number(long long number)
{
    return numberToStringSigned<String>(number);
}

String String::number(unsigned long long number)
{
    return numberToStringUnsigned<String>(number);
}

String String::numberToStringFixedPrecision(float number, unsigned precision, TrailingZerosPolicy trailingZerosTruncatingPolicy)
{
    NumberToStringBuffer buffer;
    return String { numberToFixedPrecisionString(number, precision, buffer, trailingZerosTruncatingPolicy == TrailingZerosPolicy::Truncate) };
}

String String::numberToStringFixedPrecision(double number, unsigned precision, TrailingZerosPolicy trailingZerosTruncatingPolicy)
{
    NumberToStringBuffer buffer;
    return String { numberToFixedPrecisionString(number, precision, buffer, trailingZerosTruncatingPolicy == TrailingZerosPolicy::Truncate) };
}

String String::number(float number)
{
    NumberToStringBuffer buffer;
    return String { numberToStringAndSize(number, buffer) };
}

String String::number(double number)
{
    NumberToStringBuffer buffer;
    return String { numberToStringAndSize(number, buffer) };
}

String String::numberToStringFixedWidth(double number, unsigned decimalPlaces)
{
    NumberToStringBuffer buffer;
    return String { numberToFixedWidthString(number, decimalPlaces, buffer) };
}

double String::toDouble(bool* ok) const
{
    if (!m_impl) {
        if (ok)
            *ok = false;
        return 0.0;
    }
    return m_impl->toDouble(ok);
}

float String::toFloat(bool* ok) const
{
    if (!m_impl) {
        if (ok)
            *ok = false;
        return 0.0f;
    }
    return m_impl->toFloat(ok);
}

String String::isolatedCopy() const &
{
    // FIXME: Should this function, and the many others like it, be inlined?
    return m_impl ? m_impl->isolatedCopy() : String { };
}

String String::isolatedCopy() &&
{
    if (isSafeToSendToAnotherThread()) {
        // Since we know that our string is a temporary that will be destroyed
        // we can just steal the m_impl from it, thus avoiding a copy.
        return { WTFMove(*this) };
    }

    return m_impl ? m_impl->isolatedCopy() : String { };
}

bool String::isSafeToSendToAnotherThread() const
{
    // AtomStrings are not safe to send between threads, as ~StringImpl()
    // will try to remove them from the wrong AtomStringTable.
    return isEmpty() || (m_impl->hasOneRef() && !m_impl->isAtom());
}

template<bool allowEmptyEntries>
inline Vector<String> String::splitInternal(StringView separator) const
{
    Vector<String> result;

    unsigned startPos = 0;
    size_t endPos;
    while ((endPos = find(separator, startPos)) != notFound) {
        if (allowEmptyEntries || startPos != endPos)
            result.append(substring(startPos, endPos - startPos));
        startPos = endPos + separator.length();
    }
    if (allowEmptyEntries || startPos != length())
        result.append(substring(startPos));

    return result;
}

template<bool allowEmptyEntries>
inline void String::splitInternal(UChar separator, const SplitFunctor& functor) const
{
    StringView view(*this);

    unsigned startPos = 0;
    size_t endPos;
    while ((endPos = find(separator, startPos)) != notFound) {
        if (allowEmptyEntries || startPos != endPos)
            functor(view.substring(startPos, endPos - startPos));
        startPos = endPos + 1;
    }
    if (allowEmptyEntries || startPos != length())
        functor(view.substring(startPos));
}

template<bool allowEmptyEntries>
inline Vector<String> String::splitInternal(UChar separator) const
{
    Vector<String> result;
    splitInternal<allowEmptyEntries>(separator, [&result](StringView item) {
        result.append(item.toString());
    });

    return result;
}

void String::split(UChar separator, const SplitFunctor& functor) const
{
    splitInternal<false>(separator, functor);
}

Vector<String> String::split(UChar separator) const
{
    return splitInternal<false>(separator);
}

Vector<String> String::split(StringView separator) const
{
    return splitInternal<false>(separator);
}

void String::splitAllowingEmptyEntries(UChar separator, const SplitFunctor& functor) const
{
    splitInternal<true>(separator, functor);
}

Vector<String> String::splitAllowingEmptyEntries(UChar separator) const
{
    return splitInternal<true>(separator);
}

Vector<String> String::splitAllowingEmptyEntries(StringView separator) const
{
    return splitInternal<true>(separator);
}

CString String::ascii() const
{
    // Printable ASCII characters 32..127 and the null character are
    // preserved, characters outside of this range are converted to '?'.

    if (isEmpty()) {
        std::span<char> characterBuffer;
        return CString::newUninitialized(0, characterBuffer);
    }

    if (this->is8Bit()) {
        auto characters = this->span8();

        std::span<char> characterBuffer;
        CString result = CString::newUninitialized(characters.size(), characterBuffer);

        size_t characterBufferIndex = 0;
        for (auto character : characters)
            characterBuffer[characterBufferIndex++] = character && (character < 0x20 || character > 0x7f) ? '?' : character;

        return result;        
    }

    auto characters = span16();
    std::span<char> characterBuffer;
    CString result = CString::newUninitialized(characters.size(), characterBuffer);

    size_t characterBufferIndex = 0;
    for (auto character : characters)
        characterBuffer[characterBufferIndex++] = character && (character < 0x20 || character > 0x7f) ? '?' : character;

    return result;
}

CString String::latin1() const
{
    // Basic Latin1 (ISO) encoding - Unicode characters 0..255 are
    // preserved, characters outside of this range are converted to '?'.

    if (isEmpty())
        return ""_span;

    if (is8Bit())
        return CString(this->span8());

    auto characters = this->span16();
    std::span<char> characterBuffer;
    CString result = CString::newUninitialized(characters.size(), characterBuffer);

    size_t characterBufferIndex = 0;
    for (auto character : characters)
        characterBuffer[characterBufferIndex++] = !isLatin1(character) ? '?' : character;

    return result;
}

Expected<CString, UTF8ConversionError> String::tryGetUTF8(ConversionMode mode) const
{
    return m_impl ? m_impl->tryGetUTF8(mode) : CString { ""_span };
}

Expected<CString, UTF8ConversionError> String::tryGetUTF8() const
{
    return tryGetUTF8(LenientConversion);
}

CString String::utf8(ConversionMode mode) const
{
    Expected<CString, UTF8ConversionError> expectedString = tryGetUTF8(mode);
    RELEASE_ASSERT(expectedString);
    return expectedString.value();
}

String String::make8Bit(std::span<const UChar> source)
{
    std::span<LChar> destination;
    String result = String::createUninitialized(source.size(), destination);
    StringImpl::copyCharacters(destination, source);
    return result;
}

void String::convertTo16Bit()
{
    if (isNull() || !is8Bit())
        return;
    std::span<UChar> destination;
    auto convertedString = String::createUninitialized(length(), destination);
    StringImpl::copyCharacters(destination, span8());
    *this = WTFMove(convertedString);
}

template<bool replaceInvalidSequences>
String fromUTF8Impl(std::span<const char8_t> string)
{
    RELEASE_ASSERT(string.size() <= String::MaxLength);

    if (string.empty())
        return emptyString();

    if (charactersAreAllASCII(string))
        return StringImpl::create(byteCast<LChar>(string));

    Vector<UChar, 1024> buffer(string.size());
 
    auto result = replaceInvalidSequences
        ? Unicode::convertReplacingInvalidSequences(string, buffer.mutableSpan())
        : Unicode::convert(string, buffer.mutableSpan());
    if (result.code != Unicode::ConversionResultCode::Success)
        return { };

    RELEASE_ASSERT_WITH_SECURITY_IMPLICATION(result.buffer.size() <= string.size());
    return StringImpl::create(result.buffer);
}

String String::fromUTF8(std::span<const char8_t> string)
{
    if (!string.data())
        return { };
    return fromUTF8Impl<false>(string);
}

String String::fromUTF8ReplacingInvalidSequences(std::span<const char8_t> characters)
{
    if (!characters.data())
        return { };
    return fromUTF8Impl<true>(characters);
}

String String::fromUTF8WithLatin1Fallback(std::span<const char8_t> string)
{
    String utf8 = fromUTF8(string);
    if (!utf8) {
        // Do this assertion before chopping the size_t down to unsigned.
        RELEASE_ASSERT(string.size() <= String::MaxLength);
        return byteCast<LChar>(string);
    }
    return utf8;
}

String String::fromCodePoint(char32_t codePoint)
{
    std::array<UChar, 2> buffer;
    uint8_t length = 0;
    UBool error = false;
    U16_APPEND(buffer, length, 2, codePoint, error);
    return error ? String() : String(std::span { buffer }.first(length));
}

// String Operations

template<typename CharacterType, TrailingJunkPolicy policy>
static inline double toDoubleType(std::span<const CharacterType> data, bool* ok, size_t& parsedLength)
{
    size_t leadingSpacesLength = 0;
    while (leadingSpacesLength < data.size() && isUnicodeCompatibleASCIIWhitespace(data[leadingSpacesLength]))
        ++leadingSpacesLength;

    double number = parseDouble(data.subspan(leadingSpacesLength), parsedLength);
    if (!parsedLength) {
        if (ok)
            *ok = false;
        return 0.0;
    }

    parsedLength += leadingSpacesLength;
    if (ok)
        *ok = policy == TrailingJunkPolicy::Allow || parsedLength == data.size();
    return number;
}

double charactersToDouble(std::span<const LChar> data, bool* ok)
{
    size_t parsedLength;
    return toDoubleType<LChar, TrailingJunkPolicy::Disallow>(data, ok, parsedLength);
}

double charactersToDouble(std::span<const UChar> data, bool* ok)
{
    size_t parsedLength;
    return toDoubleType<UChar, TrailingJunkPolicy::Disallow>(data, ok, parsedLength);
}

float charactersToFloat(std::span<const LChar> data, bool* ok)
{
    // FIXME: This will return ok even when the string fits into a double but not a float.
    size_t parsedLength;
    return static_cast<float>(toDoubleType<LChar, TrailingJunkPolicy::Disallow>(data, ok, parsedLength));
}

float charactersToFloat(std::span<const UChar> data, bool* ok)
{
    // FIXME: This will return ok even when the string fits into a double but not a float.
    size_t parsedLength;
    return static_cast<float>(toDoubleType<UChar, TrailingJunkPolicy::Disallow>(data, ok, parsedLength));
}

float charactersToFloat(std::span<const LChar> data, size_t& parsedLength)
{
    // FIXME: This will return ok even when the string fits into a double but not a float.
    return static_cast<float>(toDoubleType<LChar, TrailingJunkPolicy::Allow>(data, nullptr, parsedLength));
}

float charactersToFloat(std::span<const UChar> data, size_t& parsedLength)
{
    // FIXME: This will return ok even when the string fits into a double but not a float.
    return static_cast<float>(toDoubleType<UChar, TrailingJunkPolicy::Allow>(data, nullptr, parsedLength));
}

const StaticString nullStringData { nullptr };
const StaticString emptyStringData { &StringImpl::s_emptyAtomString };

} // namespace WTF

#ifndef NDEBUG

// For use in the debugger.
String* string(const char*);
Vector<char> asciiDebug(StringImpl* impl);
Vector<char> asciiDebug(String& string);

void String::show() const
{
    dataLogF("%s\n", asciiDebug(impl()).data());
}

String* string(const char* s)
{
    // Intentionally leaks memory!
    return new String(String::fromLatin1(s));
}

Vector<char> asciiDebug(StringImpl* impl)
{
    if (!impl)
        return asciiDebug(String("[null]"_s).impl());

    StringBuilder buffer;
    for (unsigned i = 0; i < impl->length(); ++i) {
        UChar ch = (*impl)[i];
        if (isASCIIPrintable(ch)) {
            if (ch == '\\')
                buffer.append(ch);
            buffer.append(ch);
        } else {
            buffer.append('\\', 'u', hex(ch, 4));
        }
    }
    CString narrowString = buffer.toString().ascii();
    return { narrowString.spanIncludingNullTerminator() };
}

Vector<char> asciiDebug(String& string)
{
    return asciiDebug(string.impl());
}

#endif