mirror of
https://github.com/SerenityOS/serenity
synced 2024-07-22 02:26:11 +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.
104 lines
3 KiB
C++
104 lines
3 KiB
C++
/*
|
|
* Copyright (c) 2018-2021, Andreas Kling <kling@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/ByteBuffer.h>
|
|
#include <AK/Format.h>
|
|
#include <AK/Forward.h>
|
|
#include <AK/StringView.h>
|
|
#include <stdarg.h>
|
|
|
|
namespace AK {
|
|
|
|
class StringBuilder {
|
|
public:
|
|
using OutputType = DeprecatedString;
|
|
|
|
explicit StringBuilder(size_t initial_capacity = inline_capacity);
|
|
~StringBuilder() = default;
|
|
|
|
ErrorOr<void> try_append(StringView);
|
|
#ifndef KERNEL
|
|
ErrorOr<void> try_append(Utf16View const&);
|
|
#endif
|
|
ErrorOr<void> try_append(Utf32View const&);
|
|
ErrorOr<void> try_append_code_point(u32);
|
|
ErrorOr<void> try_append(char);
|
|
template<typename... Parameters>
|
|
ErrorOr<void> try_appendff(CheckedFormatString<Parameters...>&& fmtstr, Parameters const&... parameters)
|
|
{
|
|
VariadicFormatParams variadic_format_params { parameters... };
|
|
return vformat(*this, fmtstr.view(), variadic_format_params);
|
|
}
|
|
ErrorOr<void> try_append(char const*, size_t);
|
|
ErrorOr<void> try_append_repeated(char, size_t);
|
|
ErrorOr<void> try_append_escaped_for_json(StringView);
|
|
|
|
void append(StringView);
|
|
#ifndef KERNEL
|
|
void append(Utf16View const&);
|
|
#endif
|
|
void append(Utf32View const&);
|
|
void append(char);
|
|
void append_code_point(u32);
|
|
void append(char const*, size_t);
|
|
void appendvf(char const*, va_list);
|
|
void append_repeated(char, size_t);
|
|
|
|
void append_as_lowercase(char);
|
|
void append_escaped_for_json(StringView);
|
|
|
|
template<typename... Parameters>
|
|
void appendff(CheckedFormatString<Parameters...>&& fmtstr, Parameters const&... parameters)
|
|
{
|
|
VariadicFormatParams variadic_format_params { parameters... };
|
|
MUST(vformat(*this, fmtstr.view(), variadic_format_params));
|
|
}
|
|
|
|
#ifndef KERNEL
|
|
[[nodiscard]] DeprecatedString build() const;
|
|
[[nodiscard]] DeprecatedString to_deprecated_string() const;
|
|
ErrorOr<String> to_string() const;
|
|
#endif
|
|
|
|
[[nodiscard]] ByteBuffer to_byte_buffer() const;
|
|
|
|
[[nodiscard]] StringView string_view() const;
|
|
void clear();
|
|
|
|
[[nodiscard]] size_t length() const { return m_buffer.size(); }
|
|
[[nodiscard]] bool is_empty() const { return m_buffer.is_empty(); }
|
|
void trim(size_t count) { m_buffer.resize(m_buffer.size() - count); }
|
|
|
|
template<class SeparatorType, class CollectionType>
|
|
void join(SeparatorType const& separator, CollectionType const& collection, StringView fmtstr = "{}"sv)
|
|
{
|
|
bool first = true;
|
|
for (auto& item : collection) {
|
|
if (first)
|
|
first = false;
|
|
else
|
|
append(separator);
|
|
appendff(fmtstr, item);
|
|
}
|
|
}
|
|
|
|
private:
|
|
ErrorOr<void> will_append(size_t);
|
|
u8* data() { return m_buffer.data(); }
|
|
u8 const* data() const { return m_buffer.data(); }
|
|
|
|
static constexpr size_t inline_capacity = 256;
|
|
AK::Detail::ByteBuffer<inline_capacity> m_buffer;
|
|
};
|
|
|
|
}
|
|
|
|
#if USING_AK_GLOBALLY
|
|
using AK::StringBuilder;
|
|
#endif
|