1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
|
/*
* Copyright (c) 2018-2022, Andreas Kling <kling@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#pragma once
#include <AK/Concepts.h>
#include <AK/Format.h>
#include <AK/Forward.h>
#include <AK/Optional.h>
#include <AK/RefCounted.h>
#include <AK/Span.h>
#include <AK/StringView.h>
#include <AK/Traits.h>
#include <AK/Types.h>
namespace AK {
namespace Detail {
class StringData;
}
// String is a strongly owned sequence of Unicode code points encoded as UTF-8.
// The data may or may not be heap-allocated, and may or may not be reference counted.
// There is no guarantee that the underlying bytes are null-terminated.
class String {
public:
// NOTE: For short strings, we avoid heap allocations by storing them in the data pointer slot.
static constexpr size_t MAX_SHORT_STRING_BYTE_COUNT = sizeof(Detail::StringData*) - 1;
String(String const&);
String(String&&);
String& operator=(String&&);
String& operator=(String const&);
~String();
// Creates an empty (zero-length) String.
String();
// Creates a new String from a sequence of UTF-8 encoded code points.
static ErrorOr<String> from_utf8(StringView);
// Creates a new String by transforming this String to lower- or uppercase. Using these methods
// require linking LibUnicode into your application.
ErrorOr<String> to_lowercase(Optional<StringView> const& locale = {}) const;
ErrorOr<String> to_uppercase(Optional<StringView> const& locale = {}) const;
// Creates a substring with a deep copy of the specified data window.
ErrorOr<String> substring_from_byte_offset(size_t start, size_t byte_count) const;
// Creates a substring that strongly references the origin superstring instead of making a deep copy of the data.
ErrorOr<String> substring_from_byte_offset_with_shared_superstring(size_t start, size_t byte_count) const;
// Returns an iterable view over the Unicode code points.
[[nodiscard]] Utf8View code_points() const;
// Returns the underlying UTF-8 encoded bytes.
// NOTE: There is no guarantee about null-termination.
[[nodiscard]] ReadonlyBytes bytes() const;
// Returns true if the String is zero-length.
[[nodiscard]] bool is_empty() const;
// Returns a StringView covering the full length of the string. Note that iterating this will go byte-at-a-time, not code-point-at-a-time.
[[nodiscard]] StringView bytes_as_string_view() const;
ErrorOr<String> replace(StringView needle, StringView replacement, ReplaceMode replace_mode) const;
[[nodiscard]] bool operator==(String const&) const;
[[nodiscard]] bool operator!=(String const& other) const { return !(*this == other); }
[[nodiscard]] bool operator==(FlyString const&) const;
[[nodiscard]] bool operator!=(FlyString const& other) const { return !(*this == other); }
[[nodiscard]] bool operator==(StringView) const;
[[nodiscard]] bool operator!=(StringView other) const { return !(*this == other); }
[[nodiscard]] bool operator==(char const* cstring) const;
[[nodiscard]] bool operator!=(char const* cstring) const { return !(*this == cstring); }
// NOTE: UTF-8 is defined in a way that lexicographic ordering of code points is equivalent to lexicographic ordering of bytes.
[[nodiscard]] int operator<=>(String const& other) const { return this->bytes_as_string_view().compare(other.bytes_as_string_view()); }
[[nodiscard]] u32 hash() const;
template<Arithmetic T>
static ErrorOr<String> number(T value)
{
return formatted("{}", value);
}
static ErrorOr<String> vformatted(StringView fmtstr, TypeErasedFormatParams&);
template<typename... Parameters>
static ErrorOr<String> formatted(CheckedFormatString<Parameters...>&& fmtstr, Parameters const&... parameters)
{
VariadicFormatParams<AllowDebugOnlyFormatters::No, Parameters...> variadic_format_parameters { parameters... };
return vformatted(fmtstr.view(), variadic_format_parameters);
}
// NOTE: This is primarily interesting to unit tests.
[[nodiscard]] bool is_short_string() const;
[[nodiscard]] static String fly_string_data_to_string(Badge<FlyString>, uintptr_t const&);
[[nodiscard]] static StringView fly_string_data_to_string_view(Badge<FlyString>, uintptr_t const&);
[[nodiscard]] uintptr_t to_fly_string_data(Badge<FlyString>) const;
static void ref_fly_string_data(Badge<FlyString>, uintptr_t);
static void unref_fly_string_data(Badge<FlyString>, uintptr_t);
void did_create_fly_string(Badge<FlyString>) const;
// FIXME: Remove these once all code has been ported to String
[[nodiscard]] DeprecatedString to_deprecated_string() const;
static ErrorOr<String> from_deprecated_string(DeprecatedString const&);
private:
// NOTE: If the least significant bit of the pointer is set, this is a short string.
static constexpr uintptr_t SHORT_STRING_FLAG = 1;
static constexpr bool has_short_string_bit(uintptr_t data)
{
return (data & SHORT_STRING_FLAG) != 0;
}
struct ShortString {
ReadonlyBytes bytes() const;
size_t byte_count() const;
// NOTE: This is the byte count shifted left 1 step and or'ed with a 1 (the SHORT_STRING_FLAG)
u8 byte_count_and_short_string_flag { 0 };
u8 storage[MAX_SHORT_STRING_BYTE_COUNT] = { 0 };
};
explicit String(NonnullRefPtr<Detail::StringData>);
explicit String(ShortString);
union {
ShortString m_short_string;
Detail::StringData* m_data { nullptr };
};
};
template<>
struct Traits<String> : public GenericTraits<String> {
static unsigned hash(String const&);
};
template<>
struct Formatter<String> : Formatter<StringView> {
ErrorOr<void> format(FormatBuilder&, String const&);
};
}
|
