mirror of
https://github.com/RGBCube/serenity
synced 2025-10-31 20:42:43 +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.
120 lines
3.4 KiB
C++
120 lines
3.4 KiB
C++
/*
|
|
* Copyright (c) 2018-2020, Andreas Kling <kling@serenityos.org>
|
|
* Copyright (c) 2020, Fei Wu <f.eiwu@yahoo.com>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/Concepts.h>
|
|
#include <AK/EnumBits.h>
|
|
#include <AK/Forward.h>
|
|
|
|
namespace AK {
|
|
|
|
namespace Detail {
|
|
template<Concepts::AnyString T, Concepts::AnyString U>
|
|
inline constexpr bool IsHashCompatible<T, U> = true;
|
|
}
|
|
|
|
enum class CaseSensitivity {
|
|
CaseInsensitive,
|
|
CaseSensitive,
|
|
};
|
|
|
|
enum class ReplaceMode {
|
|
All,
|
|
FirstOnly,
|
|
};
|
|
|
|
enum class TrimMode {
|
|
Left,
|
|
Right,
|
|
Both
|
|
};
|
|
|
|
enum class TrimWhitespace {
|
|
Yes,
|
|
No,
|
|
};
|
|
|
|
enum class SplitBehavior : unsigned {
|
|
// Neither keep empty substrings nor keep the trailing separator.
|
|
// This is the default behavior if unspecified.
|
|
Nothing = 0,
|
|
|
|
// If two separators follow each other without any characters
|
|
// in between, keep a "" in the resulting vector. (or only the
|
|
// separator if KeepTrailingSeparator is used)
|
|
KeepEmpty = 1,
|
|
|
|
// Do not strip off the separator at the end of the string.
|
|
KeepTrailingSeparator = 2,
|
|
};
|
|
AK_ENUM_BITWISE_OPERATORS(SplitBehavior);
|
|
|
|
struct MaskSpan {
|
|
size_t start;
|
|
size_t length;
|
|
|
|
bool operator==(MaskSpan const& other) const
|
|
{
|
|
return start == other.start && length == other.length;
|
|
}
|
|
};
|
|
|
|
namespace StringUtils {
|
|
|
|
bool matches(StringView str, StringView mask, CaseSensitivity = CaseSensitivity::CaseInsensitive, Vector<MaskSpan>* match_spans = nullptr);
|
|
template<typename T = int>
|
|
Optional<T> convert_to_int(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
template<typename T = unsigned>
|
|
Optional<T> convert_to_uint(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
template<typename T = unsigned>
|
|
Optional<T> convert_to_uint_from_hex(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
template<typename T = unsigned>
|
|
Optional<T> convert_to_uint_from_octal(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
#ifndef KERNEL
|
|
template<typename T>
|
|
Optional<T> convert_to_floating_point(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
#endif
|
|
bool equals_ignoring_case(StringView, StringView);
|
|
bool ends_with(StringView a, StringView b, CaseSensitivity);
|
|
bool starts_with(StringView, StringView, CaseSensitivity);
|
|
bool contains(StringView, StringView, CaseSensitivity);
|
|
bool is_whitespace(StringView);
|
|
StringView trim(StringView string, StringView characters, TrimMode mode);
|
|
StringView trim_whitespace(StringView string, TrimMode mode);
|
|
|
|
Optional<size_t> find(StringView haystack, char needle, size_t start = 0);
|
|
Optional<size_t> find(StringView haystack, StringView needle, size_t start = 0);
|
|
Optional<size_t> find_last(StringView haystack, char needle);
|
|
Optional<size_t> find_last_not(StringView haystack, char needle);
|
|
Vector<size_t> find_all(StringView haystack, StringView needle);
|
|
enum class SearchDirection {
|
|
Forward,
|
|
Backward
|
|
};
|
|
Optional<size_t> find_any_of(StringView haystack, StringView needles, SearchDirection);
|
|
|
|
DeprecatedString to_snakecase(StringView);
|
|
DeprecatedString to_titlecase(StringView);
|
|
DeprecatedString invert_case(StringView);
|
|
|
|
DeprecatedString replace(StringView, StringView needle, StringView replacement, ReplaceMode);
|
|
ErrorOr<String> replace(String const&, StringView needle, StringView replacement, ReplaceMode);
|
|
|
|
size_t count(StringView, StringView needle);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#if USING_AK_GLOBALLY
|
|
using AK::CaseSensitivity;
|
|
using AK::ReplaceMode;
|
|
using AK::SplitBehavior;
|
|
using AK::TrimMode;
|
|
using AK::TrimWhitespace;
|
|
#endif
|