| 1 | /* |
| 2 | * Copyright (C) 2004-2017 Apple Inc. All rights reserved. |
| 3 | * |
| 4 | * This library is free software; you can redistribute it and/or |
| 5 | * modify it under the terms of the GNU Library General Public |
| 6 | * License as published by the Free Software Foundation; either |
| 7 | * version 2 of the License, or (at your option) any later version. |
| 8 | * |
| 9 | * This library is distributed in the hope that it will be useful, |
| 10 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 11 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 12 | * Library General Public License for more details. |
| 13 | * |
| 14 | * You should have received a copy of the GNU Library General Public License |
| 15 | * along with this library; see the file COPYING.LIB. If not, write to |
| 16 | * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, |
| 17 | * Boston, MA 02110-1301, USA. |
| 18 | * |
| 19 | */ |
| 20 | |
| 21 | #pragma once |
| 22 | |
| 23 | #include <utility> |
| 24 | #include <wtf/NeverDestroyed.h> |
| 25 | #include <wtf/text/AtomicStringImpl.h> |
| 26 | #include <wtf/text/IntegerToStringConversion.h> |
| 27 | #include <wtf/text/WTFString.h> |
| 28 | |
| 29 | #if OS(WINDOWS) |
| 30 | #include <wtf/text/win/WCharStringExtras.h> |
| 31 | #endif |
| 32 | |
| 33 | // Define 'NO_IMPLICIT_ATOMICSTRING' before including this header, |
| 34 | // to disallow (expensive) implicit String-->AtomicString conversions. |
| 35 | #ifdef NO_IMPLICIT_ATOMICSTRING |
| 36 | #define ATOMICSTRING_CONVERSION explicit |
| 37 | #else |
| 38 | #define ATOMICSTRING_CONVERSION |
| 39 | #endif |
| 40 | |
| 41 | namespace WTF { |
| 42 | |
| 43 | struct AtomicStringHash; |
| 44 | |
| 45 | class AtomicString { |
| 46 | public: |
| 47 | WTF_EXPORT_PRIVATE static void init(); |
| 48 | |
| 49 | AtomicString(); |
| 50 | AtomicString(const LChar*); |
| 51 | AtomicString(const char*); |
| 52 | AtomicString(const LChar*, unsigned length); |
| 53 | AtomicString(const UChar*, unsigned length); |
| 54 | AtomicString(const UChar*); |
| 55 | |
| 56 | template<size_t inlineCapacity> |
| 57 | explicit AtomicString(const Vector<UChar, inlineCapacity>& characters) |
| 58 | : m_string(AtomicStringImpl::add(characters.data(), characters.size())) |
| 59 | { |
| 60 | } |
| 61 | |
| 62 | AtomicString(AtomicStringImpl*); |
| 63 | AtomicString(RefPtr<AtomicStringImpl>&&); |
| 64 | AtomicString(const StaticStringImpl*); |
| 65 | ATOMICSTRING_CONVERSION AtomicString(StringImpl*); |
| 66 | ATOMICSTRING_CONVERSION AtomicString(const String&); |
| 67 | AtomicString(StringImpl* baseString, unsigned start, unsigned length); |
| 68 | |
| 69 | // FIXME: AtomicString doesn’t always have AtomicStringImpl, so one of those two names needs to change.. |
| 70 | AtomicString(UniquedStringImpl* uid); |
| 71 | |
| 72 | enum ConstructFromLiteralTag { ConstructFromLiteral }; |
| 73 | AtomicString(const char* characters, unsigned length, ConstructFromLiteralTag) |
| 74 | : m_string(AtomicStringImpl::addLiteral(characters, length)) |
| 75 | { |
| 76 | } |
| 77 | |
| 78 | template<unsigned characterCount> ALWAYS_INLINE AtomicString(const char (&characters)[characterCount], ConstructFromLiteralTag) |
| 79 | : m_string(AtomicStringImpl::addLiteral(characters, characterCount - 1)) |
| 80 | { |
| 81 | COMPILE_ASSERT(characterCount > 1, AtomicStringFromLiteralNotEmpty); |
| 82 | COMPILE_ASSERT((characterCount - 1 <= ((unsigned(~0) - sizeof(StringImpl)) / sizeof(LChar))), AtomicStringFromLiteralCannotOverflow); |
| 83 | } |
| 84 | |
| 85 | // We have to declare the copy constructor and copy assignment operator as well, otherwise |
| 86 | // they'll be implicitly deleted by adding the move constructor and move assignment operator. |
| 87 | AtomicString(const AtomicString& other) : m_string(other.m_string) { } |
| 88 | AtomicString(AtomicString&& other) : m_string(WTFMove(other.m_string)) { } |
| 89 | AtomicString& operator=(const AtomicString& other) { m_string = other.m_string; return *this; } |
| 90 | AtomicString& operator=(AtomicString&& other) { m_string = WTFMove(other.m_string); return *this; } |
| 91 | |
| 92 | // Hash table deleted values, which are only constructed and never copied or destroyed. |
| 93 | AtomicString(WTF::HashTableDeletedValueType) : m_string(WTF::HashTableDeletedValue) { } |
| 94 | bool isHashTableDeletedValue() const { return m_string.isHashTableDeletedValue(); } |
| 95 | |
| 96 | unsigned existingHash() const { return isNull() ? 0 : impl()->existingHash(); } |
| 97 | |
| 98 | operator const String&() const { return m_string; } |
| 99 | const String& string() const { return m_string; }; |
| 100 | |
| 101 | AtomicStringImpl* impl() const { return static_cast<AtomicStringImpl *>(m_string.impl()); } |
| 102 | |
| 103 | bool is8Bit() const { return m_string.is8Bit(); } |
| 104 | const LChar* characters8() const { return m_string.characters8(); } |
| 105 | const UChar* characters16() const { return m_string.characters16(); } |
| 106 | unsigned length() const { return m_string.length(); } |
| 107 | |
| 108 | UChar operator[](unsigned int i) const { return m_string[i]; } |
| 109 | |
| 110 | WTF_EXPORT_PRIVATE static AtomicString number(int); |
| 111 | WTF_EXPORT_PRIVATE static AtomicString number(unsigned); |
| 112 | WTF_EXPORT_PRIVATE static AtomicString number(unsigned long); |
| 113 | WTF_EXPORT_PRIVATE static AtomicString number(unsigned long long); |
| 114 | WTF_EXPORT_PRIVATE static AtomicString number(float); |
| 115 | WTF_EXPORT_PRIVATE static AtomicString number(double); |
| 116 | // If we need more overloads of the number function, we can add all the others that String has, but these seem to do for now. |
| 117 | |
| 118 | bool contains(UChar character) const { return m_string.contains(character); } |
| 119 | bool contains(const LChar* string) const { return m_string.contains(string); } |
| 120 | bool contains(const String& string) const { return m_string.contains(string); } |
| 121 | bool containsIgnoringASCIICase(const String& string) const { return m_string.containsIgnoringASCIICase(string); } |
| 122 | |
| 123 | size_t find(UChar character, unsigned start = 0) const { return m_string.find(character, start); } |
| 124 | size_t find(const LChar* string, unsigned start = 0) const { return m_string.find(string, start); } |
| 125 | size_t find(const String& string, unsigned start = 0) const { return m_string.find(string, start); } |
| 126 | size_t findIgnoringASCIICase(const String& string) const { return m_string.findIgnoringASCIICase(string); } |
| 127 | size_t findIgnoringASCIICase(const String& string, unsigned startOffset) const { return m_string.findIgnoringASCIICase(string, startOffset); } |
| 128 | size_t find(CodeUnitMatchFunction matchFunction, unsigned start = 0) const { return m_string.find(matchFunction, start); } |
| 129 | |
| 130 | bool startsWith(const String& string) const { return m_string.startsWith(string); } |
| 131 | bool startsWithIgnoringASCIICase(const String& string) const { return m_string.startsWithIgnoringASCIICase(string); } |
| 132 | bool startsWith(UChar character) const { return m_string.startsWith(character); } |
| 133 | template<unsigned matchLength> bool startsWith(const char (&prefix)[matchLength]) const { return m_string.startsWith<matchLength>(prefix); } |
| 134 | |
| 135 | bool endsWith(const String& string) const { return m_string.endsWith(string); } |
| 136 | bool endsWithIgnoringASCIICase(const String& string) const { return m_string.endsWithIgnoringASCIICase(string); } |
| 137 | bool endsWith(UChar character) const { return m_string.endsWith(character); } |
| 138 | template<unsigned matchLength> bool endsWith(const char (&prefix)[matchLength]) const { return m_string.endsWith<matchLength>(prefix); } |
| 139 | |
| 140 | WTF_EXPORT_PRIVATE AtomicString convertToASCIILowercase() const; |
| 141 | WTF_EXPORT_PRIVATE AtomicString convertToASCIIUppercase() const; |
| 142 | |
| 143 | int toInt(bool* ok = 0) const { return m_string.toInt(ok); } |
| 144 | double toDouble(bool* ok = 0) const { return m_string.toDouble(ok); } |
| 145 | float toFloat(bool* ok = 0) const { return m_string.toFloat(ok); } |
| 146 | bool percentage(int& p) const { return m_string.percentage(p); } |
| 147 | |
| 148 | bool isNull() const { return m_string.isNull(); } |
| 149 | bool isEmpty() const { return m_string.isEmpty(); } |
| 150 | |
| 151 | #if USE(CF) |
| 152 | AtomicString(CFStringRef); |
| 153 | #endif |
| 154 | |
| 155 | #ifdef __OBJC__ |
| 156 | AtomicString(NSString*); |
| 157 | operator NSString*() const { return m_string; } |
| 158 | #endif |
| 159 | |
| 160 | #if OS(WINDOWS) && U_ICU_VERSION_MAJOR_NUM >= 59 |
| 161 | AtomicString(const wchar_t* characters, unsigned length) |
| 162 | : AtomicString(ucharFrom(characters), length) { } |
| 163 | |
| 164 | AtomicString(const wchar_t* characters) |
| 165 | : AtomicString(ucharFrom(characters)) { } |
| 166 | #endif |
| 167 | |
| 168 | // AtomicString::fromUTF8 will return a null string if the input data contains invalid UTF-8 sequences. |
| 169 | static AtomicString fromUTF8(const char*, size_t); |
| 170 | static AtomicString fromUTF8(const char*); |
| 171 | |
| 172 | #ifndef NDEBUG |
| 173 | void show() const; |
| 174 | #endif |
| 175 | |
| 176 | private: |
| 177 | // The explicit constructors with AtomicString::ConstructFromLiteral must be used for literals. |
| 178 | AtomicString(ASCIILiteral); |
| 179 | |
| 180 | enum class CaseConvertType { Upper, Lower }; |
| 181 | template<CaseConvertType> AtomicString convertASCIICase() const; |
| 182 | |
| 183 | WTF_EXPORT_PRIVATE static AtomicString fromUTF8Internal(const char*, const char*); |
| 184 | |
| 185 | String m_string; |
| 186 | }; |
| 187 | |
| 188 | static_assert(sizeof(AtomicString) == sizeof(String), "AtomicString and String must be same size!" ); |
| 189 | |
| 190 | inline bool operator==(const AtomicString& a, const AtomicString& b) { return a.impl() == b.impl(); } |
| 191 | bool operator==(const AtomicString&, const LChar*); |
| 192 | inline bool operator==(const AtomicString& a, const char* b) { return WTF::equal(a.impl(), reinterpret_cast<const LChar*>(b)); } |
| 193 | inline bool operator==(const AtomicString& a, const Vector<UChar>& b) { return a.impl() && equal(a.impl(), b.data(), b.size()); } |
| 194 | inline bool operator==(const AtomicString& a, const String& b) { return equal(a.impl(), b.impl()); } |
| 195 | inline bool operator==(const LChar* a, const AtomicString& b) { return b == a; } |
| 196 | inline bool operator==(const String& a, const AtomicString& b) { return equal(a.impl(), b.impl()); } |
| 197 | inline bool operator==(const Vector<UChar>& a, const AtomicString& b) { return b == a; } |
| 198 | |
| 199 | inline bool operator!=(const AtomicString& a, const AtomicString& b) { return a.impl() != b.impl(); } |
| 200 | inline bool operator!=(const AtomicString& a, const LChar* b) { return !(a == b); } |
| 201 | inline bool operator!=(const AtomicString& a, const char* b) { return !(a == b); } |
| 202 | inline bool operator!=(const AtomicString& a, const String& b) { return !equal(a.impl(), b.impl()); } |
| 203 | inline bool operator!=(const AtomicString& a, const Vector<UChar>& b) { return !(a == b); } |
| 204 | inline bool operator!=(const LChar* a, const AtomicString& b) { return !(b == a); } |
| 205 | inline bool operator!=(const String& a, const AtomicString& b) { return !equal(a.impl(), b.impl()); } |
| 206 | inline bool operator!=(const Vector<UChar>& a, const AtomicString& b) { return !(a == b); } |
| 207 | |
| 208 | bool equalIgnoringASCIICase(const AtomicString&, const AtomicString&); |
| 209 | bool equalIgnoringASCIICase(const AtomicString&, const String&); |
| 210 | bool equalIgnoringASCIICase(const String&, const AtomicString&); |
| 211 | bool equalIgnoringASCIICase(const AtomicString&, const char*); |
| 212 | |
| 213 | template<unsigned length> bool equalLettersIgnoringASCIICase(const AtomicString&, const char (&lowercaseLetters)[length]); |
| 214 | |
| 215 | inline AtomicString::AtomicString() |
| 216 | { |
| 217 | } |
| 218 | |
| 219 | inline AtomicString::AtomicString(const LChar* string) |
| 220 | : m_string(AtomicStringImpl::add(string)) |
| 221 | { |
| 222 | } |
| 223 | |
| 224 | inline AtomicString::AtomicString(const char* string) |
| 225 | : m_string(AtomicStringImpl::add(string)) |
| 226 | { |
| 227 | } |
| 228 | |
| 229 | inline AtomicString::AtomicString(const LChar* string, unsigned length) |
| 230 | : m_string(AtomicStringImpl::add(string, length)) |
| 231 | { |
| 232 | } |
| 233 | |
| 234 | inline AtomicString::AtomicString(const UChar* string, unsigned length) |
| 235 | : m_string(AtomicStringImpl::add(string, length)) |
| 236 | { |
| 237 | } |
| 238 | |
| 239 | inline AtomicString::AtomicString(const UChar* string) |
| 240 | : m_string(AtomicStringImpl::add(string)) |
| 241 | { |
| 242 | } |
| 243 | |
| 244 | inline AtomicString::AtomicString(AtomicStringImpl* string) |
| 245 | : m_string(string) |
| 246 | { |
| 247 | } |
| 248 | |
| 249 | inline AtomicString::AtomicString(RefPtr<AtomicStringImpl>&& string) |
| 250 | : m_string(WTFMove(string)) |
| 251 | { |
| 252 | } |
| 253 | |
| 254 | inline AtomicString::AtomicString(StringImpl* string) |
| 255 | : m_string(AtomicStringImpl::add(string)) |
| 256 | { |
| 257 | } |
| 258 | |
| 259 | inline AtomicString::AtomicString(const StaticStringImpl* string) |
| 260 | : m_string(AtomicStringImpl::add(string)) |
| 261 | { |
| 262 | } |
| 263 | |
| 264 | inline AtomicString::AtomicString(const String& string) |
| 265 | : m_string(AtomicStringImpl::add(string.impl())) |
| 266 | { |
| 267 | } |
| 268 | |
| 269 | inline AtomicString::AtomicString(StringImpl* baseString, unsigned start, unsigned length) |
| 270 | : m_string(AtomicStringImpl::add(baseString, start, length)) |
| 271 | { |
| 272 | } |
| 273 | |
| 274 | inline AtomicString::AtomicString(UniquedStringImpl* uid) |
| 275 | : m_string(uid) |
| 276 | { |
| 277 | } |
| 278 | |
| 279 | #if USE(CF) |
| 280 | |
| 281 | inline AtomicString::AtomicString(CFStringRef string) |
| 282 | : m_string(AtomicStringImpl::add(string)) |
| 283 | { |
| 284 | } |
| 285 | |
| 286 | #endif |
| 287 | |
| 288 | #ifdef __OBJC__ |
| 289 | |
| 290 | inline AtomicString::AtomicString(NSString* string) |
| 291 | : m_string(AtomicStringImpl::add((__bridge CFStringRef)string)) |
| 292 | { |
| 293 | } |
| 294 | |
| 295 | #endif |
| 296 | |
| 297 | // Define external global variables for the commonly used atomic strings. |
| 298 | // These are only usable from the main thread. |
| 299 | extern WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> nullAtomData; |
| 300 | extern WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> emptyAtomData; |
| 301 | extern WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> starAtomData; |
| 302 | extern WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> xmlAtomData; |
| 303 | extern WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> xmlnsAtomData; |
| 304 | |
| 305 | inline const AtomicString& nullAtom() { return nullAtomData.get(); } |
| 306 | inline const AtomicString& emptyAtom() { return emptyAtomData.get(); } |
| 307 | inline const AtomicString& starAtom() { return starAtomData.get(); } |
| 308 | inline const AtomicString& xmlAtom() { return xmlAtomData.get(); } |
| 309 | inline const AtomicString& xmlnsAtom() { return xmlnsAtomData.get(); } |
| 310 | |
| 311 | inline AtomicString AtomicString::fromUTF8(const char* characters, size_t length) |
| 312 | { |
| 313 | if (!characters) |
| 314 | return nullAtom(); |
| 315 | if (!length) |
| 316 | return emptyAtom(); |
| 317 | return fromUTF8Internal(characters, characters + length); |
| 318 | } |
| 319 | |
| 320 | inline AtomicString AtomicString::fromUTF8(const char* characters) |
| 321 | { |
| 322 | if (!characters) |
| 323 | return nullAtom(); |
| 324 | if (!*characters) |
| 325 | return emptyAtom(); |
| 326 | return fromUTF8Internal(characters, nullptr); |
| 327 | } |
| 328 | |
| 329 | // AtomicStringHash is the default hash for AtomicString |
| 330 | template<typename T> struct DefaultHash; |
| 331 | template<> struct DefaultHash<AtomicString> { |
| 332 | typedef AtomicStringHash Hash; |
| 333 | }; |
| 334 | |
| 335 | template<unsigned length> inline bool equalLettersIgnoringASCIICase(const AtomicString& string, const char (&lowercaseLetters)[length]) |
| 336 | { |
| 337 | return equalLettersIgnoringASCIICase(string.string(), lowercaseLetters); |
| 338 | } |
| 339 | |
| 340 | inline bool equalIgnoringASCIICase(const AtomicString& a, const AtomicString& b) |
| 341 | { |
| 342 | return equalIgnoringASCIICase(a.string(), b.string()); |
| 343 | } |
| 344 | |
| 345 | inline bool equalIgnoringASCIICase(const AtomicString& a, const String& b) |
| 346 | { |
| 347 | return equalIgnoringASCIICase(a.string(), b); |
| 348 | } |
| 349 | |
| 350 | inline bool equalIgnoringASCIICase(const String& a, const AtomicString& b) |
| 351 | { |
| 352 | return equalIgnoringASCIICase(a, b.string()); |
| 353 | } |
| 354 | |
| 355 | inline bool equalIgnoringASCIICase(const AtomicString& a, const char* b) |
| 356 | { |
| 357 | return equalIgnoringASCIICase(a.string(), b); |
| 358 | } |
| 359 | |
| 360 | template<> struct IntegerToStringConversionTrait<AtomicString> { |
| 361 | using ReturnType = AtomicString; |
| 362 | using AdditionalArgumentType = void; |
| 363 | static AtomicString flush(LChar* characters, unsigned length, void*) { return { characters, length }; } |
| 364 | }; |
| 365 | |
| 366 | } // namespace WTF |
| 367 | |
| 368 | #ifndef ATOMICSTRING_HIDE_GLOBALS |
| 369 | using WTF::AtomicString; |
| 370 | using WTF::nullAtom; |
| 371 | using WTF::emptyAtom; |
| 372 | using WTF::starAtom; |
| 373 | using WTF::xmlAtom; |
| 374 | using WTF::xmlnsAtom; |
| 375 | #endif |
| 376 | |
| 377 | #include <wtf/text/StringConcatenate.h> |
| 378 | |