2020-03-02 13:23:11 +00:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2018-2020, Andreas Kling <kling@serenityos.org>
|
|
|
|
* Copyright (c) 2020, Fei Wu <f.eiwu@yahoo.com>
|
|
|
|
*
|
2021-04-22 08:24:48 +00:00
|
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
2020-03-02 13:23:11 +00:00
|
|
|
*/
|
|
|
|
|
2020-02-26 07:25:24 +00:00
|
|
|
#pragma once
|
|
|
|
|
2021-11-07 13:50:41 +00:00
|
|
|
#include <AK/Concepts.h>
|
2022-10-22 13:38:21 +00:00
|
|
|
#include <AK/EnumBits.h>
|
2020-02-26 07:25:24 +00:00
|
|
|
#include <AK/Forward.h>
|
|
|
|
|
|
|
|
namespace AK {
|
|
|
|
|
2021-11-07 13:50:41 +00:00
|
|
|
namespace Detail {
|
|
|
|
template<Concepts::AnyString T, Concepts::AnyString U>
|
|
|
|
inline constexpr bool IsHashCompatible<T, U> = true;
|
|
|
|
}
|
|
|
|
|
2020-02-26 07:25:24 +00:00
|
|
|
enum class CaseSensitivity {
|
|
|
|
CaseInsensitive,
|
|
|
|
CaseSensitive,
|
|
|
|
};
|
|
|
|
|
2022-07-05 20:33:15 +00:00
|
|
|
enum class ReplaceMode {
|
|
|
|
All,
|
|
|
|
FirstOnly,
|
|
|
|
};
|
|
|
|
|
2020-09-20 13:35:04 +00:00
|
|
|
enum class TrimMode {
|
|
|
|
Left,
|
|
|
|
Right,
|
|
|
|
Both
|
|
|
|
};
|
|
|
|
|
2021-06-18 16:21:27 +00:00
|
|
|
enum class TrimWhitespace {
|
|
|
|
Yes,
|
|
|
|
No,
|
|
|
|
};
|
|
|
|
|
2022-10-22 13:38:21 +00:00
|
|
|
enum class SplitBehavior : unsigned {
|
2022-10-22 14:31:59 +00:00
|
|
|
// Neither keep empty substrings nor keep the trailing separator.
|
|
|
|
// This is the default behavior if unspecified.
|
2022-10-22 13:38:21 +00:00
|
|
|
Nothing = 0,
|
2022-10-22 14:31:59 +00:00
|
|
|
|
2022-10-22 13:38:21 +00:00
|
|
|
// If two separators follow each other without any characters
|
2022-10-22 14:31:59 +00:00
|
|
|
// in between, keep a "" in the resulting vector. (or only the
|
|
|
|
// separator if KeepTrailingSeparator is used)
|
2022-10-22 13:38:21 +00:00
|
|
|
KeepEmpty = 1,
|
2022-10-22 14:31:59 +00:00
|
|
|
|
|
|
|
// Do not strip off the separator at the end of the string.
|
|
|
|
KeepTrailingSeparator = 2,
|
2022-10-22 13:38:21 +00:00
|
|
|
};
|
|
|
|
AK_ENUM_BITWISE_OPERATORS(SplitBehavior);
|
|
|
|
|
2020-10-25 05:34:39 +00:00
|
|
|
struct MaskSpan {
|
|
|
|
size_t start;
|
|
|
|
size_t length;
|
|
|
|
|
2022-04-01 17:58:27 +00:00
|
|
|
bool operator==(MaskSpan const& other) const
|
2020-10-25 05:34:39 +00:00
|
|
|
{
|
|
|
|
return start == other.start && length == other.length;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2020-02-26 07:25:24 +00:00
|
|
|
namespace StringUtils {
|
|
|
|
|
2021-11-10 23:55:02 +00:00
|
|
|
bool matches(StringView str, StringView mask, CaseSensitivity = CaseSensitivity::CaseInsensitive, Vector<MaskSpan>* match_spans = nullptr);
|
2020-12-10 13:17:30 +00:00
|
|
|
template<typename T = int>
|
2021-11-10 23:55:02 +00:00
|
|
|
Optional<T> convert_to_int(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
2020-12-10 13:17:30 +00:00
|
|
|
template<typename T = unsigned>
|
2021-11-10 23:55:02 +00:00
|
|
|
Optional<T> convert_to_uint(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
2020-12-10 13:17:30 +00:00
|
|
|
template<typename T = unsigned>
|
2021-11-10 23:55:02 +00:00
|
|
|
Optional<T> convert_to_uint_from_hex(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
2021-12-20 20:06:54 +00:00
|
|
|
template<typename T = unsigned>
|
|
|
|
Optional<T> convert_to_uint_from_octal(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
2022-10-10 22:48:45 +00:00
|
|
|
#ifndef KERNEL
|
|
|
|
template<typename T>
|
|
|
|
Optional<T> convert_to_floating_point(StringView, TrimWhitespace = TrimWhitespace::Yes);
|
|
|
|
#endif
|
2023-03-10 07:48:54 +00:00
|
|
|
bool equals_ignoring_ascii_case(StringView, StringView);
|
2021-11-10 23:55:02 +00:00
|
|
|
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);
|
2022-12-15 21:20:14 +00:00
|
|
|
Optional<size_t> find_last(StringView haystack, StringView needle);
|
2022-09-30 19:19:53 +00:00
|
|
|
Optional<size_t> find_last_not(StringView haystack, char needle);
|
2021-11-10 23:55:02 +00:00
|
|
|
Vector<size_t> find_all(StringView haystack, StringView needle);
|
2021-07-01 16:12:21 +00:00
|
|
|
enum class SearchDirection {
|
|
|
|
Forward,
|
|
|
|
Backward
|
|
|
|
};
|
2021-11-10 23:55:02 +00:00
|
|
|
Optional<size_t> find_any_of(StringView haystack, StringView needles, SearchDirection);
|
2021-07-01 12:58:37 +00:00
|
|
|
|
2022-12-04 18:02:33 +00:00
|
|
|
DeprecatedString to_snakecase(StringView);
|
|
|
|
DeprecatedString to_titlecase(StringView);
|
|
|
|
DeprecatedString invert_case(StringView);
|
2021-02-20 21:39:22 +00:00
|
|
|
|
2022-12-04 18:02:33 +00:00
|
|
|
DeprecatedString replace(StringView, StringView needle, StringView replacement, ReplaceMode);
|
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> replace(String const&, StringView needle, StringView replacement, ReplaceMode);
|
|
|
|
|
2021-11-10 23:55:02 +00:00
|
|
|
size_t count(StringView, StringView needle);
|
2021-09-10 22:02:24 +00:00
|
|
|
|
2020-02-26 07:25:24 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2022-11-26 11:18:30 +00:00
|
|
|
#if USING_AK_GLOBALLY
|
2020-02-26 07:25:24 +00:00
|
|
|
using AK::CaseSensitivity;
|
2022-07-05 20:33:15 +00:00
|
|
|
using AK::ReplaceMode;
|
2022-10-22 13:38:21 +00:00
|
|
|
using AK::SplitBehavior;
|
2020-09-20 13:35:04 +00:00
|
|
|
using AK::TrimMode;
|
2021-06-18 16:21:27 +00:00
|
|
|
using AK::TrimWhitespace;
|
2022-11-26 11:18:30 +00:00
|
|
|
#endif
|