ladybird/AK/StringBuilder.cpp

239 lines
5.5 KiB
C++
Raw Normal View History

/*
* Copyright (c) 2018-2021, Andreas Kling <kling@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/ByteBuffer.h>
#include <AK/Checked.h>
#include <AK/PrintfImplementation.h>
AK: Introduce the new String, replacement for DeprecatedString 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.
2022-12-01 12:27:43 +00:00
#include <AK/String.h>
#include <AK/StringBuilder.h>
#include <AK/StringView.h>
#include <AK/UnicodeUtils.h>
#include <AK/Utf32View.h>
#ifndef KERNEL
# include <AK/DeprecatedString.h>
2023-02-14 14:37:39 +00:00
# include <AK/FlyString.h>
# include <AK/Utf16View.h>
#endif
namespace AK {
inline ErrorOr<void> StringBuilder::will_append(size_t size)
{
Checked<size_t> needed_capacity = m_buffer.size();
needed_capacity += size;
VERIFY(!needed_capacity.has_overflow());
// Prefer to completely use the existing capacity first
if (needed_capacity <= m_buffer.capacity())
return {};
Checked<size_t> expanded_capacity = needed_capacity;
expanded_capacity *= 2;
VERIFY(!expanded_capacity.has_overflow());
TRY(m_buffer.try_ensure_capacity(expanded_capacity.value()));
return {};
}
ErrorOr<StringBuilder> StringBuilder::create(size_t initial_capacity)
{
StringBuilder builder;
TRY(builder.m_buffer.try_ensure_capacity(initial_capacity));
return builder;
}
StringBuilder::StringBuilder(size_t initial_capacity)
{
m_buffer.ensure_capacity(initial_capacity);
}
ErrorOr<void> StringBuilder::try_append(StringView string)
{
if (string.is_empty())
return {};
TRY(will_append(string.length()));
TRY(m_buffer.try_append(string.characters_without_null_termination(), string.length()));
return {};
}
ErrorOr<void> StringBuilder::try_append(char ch)
{
TRY(will_append(1));
TRY(m_buffer.try_append(ch));
return {};
}
ErrorOr<void> StringBuilder::try_append_repeated(char ch, size_t n)
{
TRY(will_append(n));
for (size_t i = 0; i < n; ++i)
TRY(try_append(ch));
return {};
}
void StringBuilder::append(StringView string)
{
MUST(try_append(string));
}
ErrorOr<void> StringBuilder::try_append(char const* characters, size_t length)
{
return try_append(StringView { characters, length });
}
void StringBuilder::append(char const* characters, size_t length)
{
MUST(try_append(characters, length));
}
void StringBuilder::append(char ch)
{
MUST(try_append(ch));
}
void StringBuilder::appendvf(char const* fmt, va_list ap)
{
printf_internal([this](char*&, char ch) {
append(ch);
},
nullptr, fmt, ap);
}
void StringBuilder::append_repeated(char ch, size_t n)
{
MUST(try_append_repeated(ch, n));
}
2020-03-08 12:44:38 +00:00
ByteBuffer StringBuilder::to_byte_buffer() const
{
// FIXME: Handle OOM failure.
return ByteBuffer::copy(data(), length()).release_value_but_fixme_should_propagate_errors();
}
ErrorOr<ByteBuffer> StringBuilder::try_to_byte_buffer() const
{
return TRY(ByteBuffer::copy(data(), length()));
}
#ifndef KERNEL
DeprecatedString StringBuilder::to_deprecated_string() const
{
if (is_empty())
return DeprecatedString::empty();
return DeprecatedString((char const*)data(), length());
}
AK: Introduce the new String, replacement for DeprecatedString 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.
2022-12-01 12:27:43 +00:00
ErrorOr<String> StringBuilder::to_string() const
{
return String::from_utf8(string_view());
}
2023-02-14 14:37:39 +00:00
ErrorOr<FlyString> StringBuilder::to_fly_string() const
{
return FlyString::from_utf8(string_view());
}
#endif
StringView StringBuilder::string_view() const
{
return StringView { data(), m_buffer.size() };
}
void StringBuilder::clear()
{
m_buffer.clear();
}
ErrorOr<void> StringBuilder::try_append_code_point(u32 code_point)
{
auto nwritten = TRY(AK::UnicodeUtils::try_code_point_to_utf8(code_point, [this](char c) { return try_append(c); }));
if (nwritten < 0) {
TRY(try_append(0xef));
TRY(try_append(0xbf));
TRY(try_append(0xbd));
}
return {};
}
void StringBuilder::append_code_point(u32 code_point)
{
MUST(try_append_code_point(code_point));
}
#ifndef KERNEL
ErrorOr<void> StringBuilder::try_append(Utf16View const& utf16_view)
{
for (size_t i = 0; i < utf16_view.length_in_code_units();) {
auto code_point = utf16_view.code_point_at(i);
TRY(try_append_code_point(code_point));
i += (code_point > 0xffff ? 2 : 1);
}
return {};
}
void StringBuilder::append(Utf16View const& utf16_view)
{
MUST(try_append(utf16_view));
}
#endif
ErrorOr<void> StringBuilder::try_append(Utf32View const& utf32_view)
{
for (size_t i = 0; i < utf32_view.length(); ++i) {
auto code_point = utf32_view.code_points()[i];
TRY(try_append_code_point(code_point));
}
return {};
}
void StringBuilder::append(Utf32View const& utf32_view)
{
MUST(try_append(utf32_view));
}
void StringBuilder::append_as_lowercase(char ch)
{
if (ch >= 'A' && ch <= 'Z')
append(ch + 0x20);
else
append(ch);
}
void StringBuilder::append_escaped_for_json(StringView string)
{
MUST(try_append_escaped_for_json(string));
}
ErrorOr<void> StringBuilder::try_append_escaped_for_json(StringView string)
{
for (auto ch : string) {
switch (ch) {
case '\b':
TRY(try_append("\\b"sv));
break;
case '\n':
TRY(try_append("\\n"sv));
break;
case '\t':
TRY(try_append("\\t"sv));
break;
case '\"':
TRY(try_append("\\\""sv));
break;
case '\\':
TRY(try_append("\\\\"sv));
break;
default:
if (ch >= 0 && ch <= 0x1f)
TRY(try_appendff("\\u{:04x}", ch));
else
TRY(try_append(ch));
}
}
return {};
}
}