mirror of
https://github.com/SerenityOS/serenity
synced 2024-07-21 10:05:32 +00:00
a3e82eaad3
DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
213 lines
4.1 KiB
C++
213 lines
4.1 KiB
C++
/*
|
|
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/Types.h>
|
|
|
|
namespace AK {
|
|
|
|
namespace Detail {
|
|
template<size_t inline_capacity>
|
|
class ByteBuffer;
|
|
}
|
|
|
|
class Bitmap;
|
|
using ByteBuffer = AK::Detail::ByteBuffer<32>;
|
|
class Error;
|
|
class GenericLexer;
|
|
class IPv4Address;
|
|
class JsonArray;
|
|
class JsonObject;
|
|
class JsonValue;
|
|
class StackInfo;
|
|
class DeprecatedString;
|
|
class StringBuilder;
|
|
class StringImpl;
|
|
class StringView;
|
|
class Time;
|
|
class URL;
|
|
class FlyString;
|
|
class String;
|
|
class Utf16View;
|
|
class Utf32View;
|
|
class Utf8CodePointIterator;
|
|
class Utf8View;
|
|
class InputStream;
|
|
class InputMemoryStream;
|
|
class DuplexMemoryStream;
|
|
class OutputStream;
|
|
class InputBitStream;
|
|
class OutputBitStream;
|
|
class OutputMemoryStream;
|
|
|
|
template<size_t Capacity>
|
|
class CircularDuplexStream;
|
|
|
|
template<typename T>
|
|
class Span;
|
|
|
|
template<typename T, size_t Size>
|
|
struct Array;
|
|
|
|
template<typename Container, typename ValueType>
|
|
class SimpleIterator;
|
|
|
|
using ReadonlyBytes = Span<u8 const>;
|
|
using Bytes = Span<u8>;
|
|
|
|
template<typename T, AK::MemoryOrder DefaultMemoryOrder>
|
|
class Atomic;
|
|
|
|
template<typename T>
|
|
class SinglyLinkedList;
|
|
|
|
template<typename T>
|
|
class DoublyLinkedList;
|
|
|
|
template<typename T, size_t capacity>
|
|
class CircularQueue;
|
|
|
|
template<typename T>
|
|
struct Traits;
|
|
|
|
template<typename T, typename TraitsForT = Traits<T>, bool IsOrdered = false>
|
|
class HashTable;
|
|
|
|
template<typename T, typename TraitsForT = Traits<T>>
|
|
using OrderedHashTable = HashTable<T, TraitsForT, true>;
|
|
|
|
template<typename K, typename V, typename KeyTraits = Traits<K>, bool IsOrdered = false>
|
|
class HashMap;
|
|
|
|
template<typename K, typename V, typename KeyTraits = Traits<K>>
|
|
using OrderedHashMap = HashMap<K, V, KeyTraits, true>;
|
|
|
|
template<typename T>
|
|
class Badge;
|
|
|
|
template<typename T>
|
|
class FixedArray;
|
|
|
|
template<size_t precision, typename Underlying = i32>
|
|
class FixedPoint;
|
|
|
|
template<typename>
|
|
class Function;
|
|
|
|
template<typename Out, typename... In>
|
|
class Function<Out(In...)>;
|
|
|
|
template<typename T>
|
|
class NonnullRefPtr;
|
|
|
|
template<typename T>
|
|
class NonnullOwnPtr;
|
|
|
|
template<typename T, size_t inline_capacity = 0>
|
|
class NonnullOwnPtrVector;
|
|
|
|
template<typename T, size_t inline_capacity = 0>
|
|
class NonnullRefPtrVector;
|
|
|
|
template<typename T>
|
|
class Optional;
|
|
|
|
#ifdef KERNEL
|
|
template<typename T>
|
|
class NonnullLockRefPtr;
|
|
|
|
template<typename T, size_t inline_capacity = 0>
|
|
class NonnullLockRefPtrVector;
|
|
|
|
template<typename T>
|
|
struct LockRefPtrTraits;
|
|
|
|
template<typename T, typename PtrTraits = LockRefPtrTraits<T>>
|
|
class LockRefPtr;
|
|
#endif
|
|
|
|
template<typename T>
|
|
class RefPtr;
|
|
|
|
template<typename T>
|
|
class OwnPtr;
|
|
|
|
template<typename T>
|
|
class WeakPtr;
|
|
|
|
template<typename T, size_t inline_capacity = 0>
|
|
requires(!IsRvalueReference<T>) class Vector;
|
|
|
|
template<typename T, typename ErrorType = Error>
|
|
class [[nodiscard]] ErrorOr;
|
|
|
|
}
|
|
|
|
#if USING_AK_GLOBALLY
|
|
using AK::Array;
|
|
using AK::Atomic;
|
|
using AK::Badge;
|
|
using AK::Bitmap;
|
|
using AK::ByteBuffer;
|
|
using AK::Bytes;
|
|
using AK::CircularDuplexStream;
|
|
using AK::CircularQueue;
|
|
using AK::DeprecatedString;
|
|
using AK::DoublyLinkedList;
|
|
using AK::DuplexMemoryStream;
|
|
using AK::Error;
|
|
using AK::ErrorOr;
|
|
using AK::FixedArray;
|
|
using AK::FixedPoint;
|
|
using AK::FlyString;
|
|
using AK::Function;
|
|
using AK::GenericLexer;
|
|
using AK::HashMap;
|
|
using AK::HashTable;
|
|
using AK::InputBitStream;
|
|
using AK::InputMemoryStream;
|
|
using AK::InputStream;
|
|
using AK::IPv4Address;
|
|
using AK::JsonArray;
|
|
using AK::JsonObject;
|
|
using AK::JsonValue;
|
|
using AK::NonnullOwnPtr;
|
|
using AK::NonnullOwnPtrVector;
|
|
using AK::NonnullRefPtr;
|
|
using AK::NonnullRefPtrVector;
|
|
using AK::Optional;
|
|
using AK::OutputBitStream;
|
|
using AK::OutputMemoryStream;
|
|
using AK::OutputStream;
|
|
using AK::OwnPtr;
|
|
using AK::ReadonlyBytes;
|
|
using AK::RefPtr;
|
|
using AK::SinglyLinkedList;
|
|
using AK::Span;
|
|
using AK::StackInfo;
|
|
using AK::String;
|
|
using AK::StringBuilder;
|
|
using AK::StringImpl;
|
|
using AK::StringView;
|
|
using AK::Time;
|
|
using AK::Traits;
|
|
using AK::URL;
|
|
using AK::Utf16View;
|
|
using AK::Utf32View;
|
|
using AK::Utf8CodePointIterator;
|
|
using AK::Utf8View;
|
|
using AK::Vector;
|
|
|
|
# ifdef KERNEL
|
|
using AK::LockRefPtr;
|
|
using AK::LockRefPtrTraits;
|
|
using AK::NonnullLockRefPtr;
|
|
using AK::NonnullLockRefPtrVector;
|
|
# endif
|
|
|
|
#endif
|