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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
|
/*
* Copyright (c) 2019-2020, Sergey Bugaev <bugaevc@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/Assertions.h>
#include <AK/Format.h>
#include <AK/Utf8View.h>
namespace AK {
Utf8View::Utf8View(const String& string)
: m_string(string)
{
}
Utf8View::Utf8View(const StringView& string)
: m_string(string)
{
}
Utf8View::Utf8View(const char* string)
: m_string(string)
{
}
const unsigned char* Utf8View::begin_ptr() const
{
return (const unsigned char*)m_string.characters_without_null_termination();
}
const unsigned char* Utf8View::end_ptr() const
{
return begin_ptr() + m_string.length();
}
Utf8CodepointIterator Utf8View::begin() const
{
return { begin_ptr(), m_string.length() };
}
Utf8CodepointIterator Utf8View::end() const
{
return { end_ptr(), 0 };
}
size_t Utf8View::byte_offset_of(const Utf8CodepointIterator& it) const
{
VERIFY(it.m_ptr >= begin_ptr());
VERIFY(it.m_ptr <= end_ptr());
return it.m_ptr - begin_ptr();
}
Utf8View Utf8View::substring_view(int byte_offset, int byte_length) const
{
StringView string = m_string.substring_view(byte_offset, byte_length);
return Utf8View { string };
}
static inline bool decode_first_byte(
unsigned char byte,
size_t& out_code_point_length_in_bytes,
u32& out_value)
{
if ((byte & 128) == 0) {
out_value = byte;
out_code_point_length_in_bytes = 1;
return true;
}
if ((byte & 64) == 0) {
return false;
}
if ((byte & 32) == 0) {
out_value = byte & 31;
out_code_point_length_in_bytes = 2;
return true;
}
if ((byte & 16) == 0) {
out_value = byte & 15;
out_code_point_length_in_bytes = 3;
return true;
}
if ((byte & 8) == 0) {
out_value = byte & 7;
out_code_point_length_in_bytes = 4;
return true;
}
return false;
}
bool Utf8View::validate(size_t& valid_bytes) const
{
valid_bytes = 0;
for (auto ptr = begin_ptr(); ptr < end_ptr(); ptr++) {
size_t code_point_length_in_bytes;
u32 value;
bool first_byte_makes_sense = decode_first_byte(*ptr, code_point_length_in_bytes, value);
if (!first_byte_makes_sense)
return false;
for (size_t i = 1; i < code_point_length_in_bytes; i++) {
ptr++;
if (ptr >= end_ptr())
return false;
if (*ptr >> 6 != 2)
return false;
}
valid_bytes += code_point_length_in_bytes;
}
return true;
}
size_t Utf8View::calculate_length() const
{
size_t length = 0;
for ([[maybe_unused]] auto code_point : *this) {
++length;
}
return length;
}
bool Utf8View::starts_with(const Utf8View& start) const
{
if (start.is_empty())
return true;
if (is_empty())
return false;
if (start.length() > length())
return false;
if (begin_ptr() == start.begin_ptr())
return true;
for (auto k = begin(), l = start.begin(); l != start.end(); ++k, ++l) {
if (*k != *l)
return false;
}
return true;
}
Utf8CodepointIterator::Utf8CodepointIterator(const unsigned char* ptr, size_t length)
: m_ptr(ptr)
, m_length(length)
{
}
bool Utf8CodepointIterator::operator==(const Utf8CodepointIterator& other) const
{
return m_ptr == other.m_ptr && m_length == other.m_length;
}
bool Utf8CodepointIterator::operator!=(const Utf8CodepointIterator& other) const
{
return !(*this == other);
}
Utf8CodepointIterator& Utf8CodepointIterator::operator++()
{
VERIFY(m_length > 0);
size_t code_point_length_in_bytes = 0;
u32 value;
bool first_byte_makes_sense = decode_first_byte(*m_ptr, code_point_length_in_bytes, value);
VERIFY(first_byte_makes_sense);
VERIFY(code_point_length_in_bytes <= m_length);
m_ptr += code_point_length_in_bytes;
m_length -= code_point_length_in_bytes;
return *this;
}
size_t Utf8CodepointIterator::code_point_length_in_bytes() const
{
VERIFY(m_length > 0);
size_t code_point_length_in_bytes = 0;
u32 value;
bool first_byte_makes_sense = decode_first_byte(*m_ptr, code_point_length_in_bytes, value);
VERIFY(first_byte_makes_sense);
return code_point_length_in_bytes;
}
u32 Utf8CodepointIterator::operator*() const
{
VERIFY(m_length > 0);
u32 code_point_value_so_far = 0;
size_t code_point_length_in_bytes = 0;
bool first_byte_makes_sense = decode_first_byte(m_ptr[0], code_point_length_in_bytes, code_point_value_so_far);
if (!first_byte_makes_sense)
dbgln("First byte doesn't make sense, bytes: {}", StringView { (const char*)m_ptr, m_length });
VERIFY(first_byte_makes_sense);
if (code_point_length_in_bytes > m_length)
dbgln("Not enough bytes (need {}, have {}), first byte is: {:#02x}, '{}'", code_point_length_in_bytes, m_length, m_ptr[0], (const char*)m_ptr);
VERIFY(code_point_length_in_bytes <= m_length);
for (size_t offset = 1; offset < code_point_length_in_bytes; offset++) {
VERIFY(m_ptr[offset] >> 6 == 2);
code_point_value_so_far <<= 6;
code_point_value_so_far |= m_ptr[offset] & 63;
}
return code_point_value_so_far;
}
}
|
