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
|
/*
* Copyright (c) 2020, Benoit Lormeau <blormeau@outlook.com>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/Assertions.h>
#include <AK/CharacterTypes.h>
#include <AK/GenericLexer.h>
#include <AK/String.h>
#include <AK/StringBuilder.h>
#include <AK/Utf16View.h>
namespace AK {
// Consume a number of characters
StringView GenericLexer::consume(size_t count)
{
if (count == 0)
return {};
size_t start = m_index;
size_t length = min(count, m_input.length() - m_index);
m_index += length;
return m_input.substring_view(start, length);
}
// Consume the rest of the input
StringView GenericLexer::consume_all()
{
if (is_eof())
return {};
auto rest = m_input.substring_view(m_index, m_input.length() - m_index);
m_index = m_input.length();
return rest;
}
// Consume until a new line is found
StringView GenericLexer::consume_line()
{
size_t start = m_index;
while (!is_eof() && peek() != '\r' && peek() != '\n')
m_index++;
size_t length = m_index - start;
consume_specific('\r');
consume_specific('\n');
if (length == 0)
return {};
return m_input.substring_view(start, length);
}
// Consume and return characters until `stop` is peek'd
// The `stop` character is ignored, as it is user-defined
StringView GenericLexer::consume_until(char stop)
{
size_t start = m_index;
while (!is_eof() && peek() != stop)
m_index++;
size_t length = m_index - start;
ignore();
if (length == 0)
return {};
return m_input.substring_view(start, length);
}
// Consume and return characters until the string `stop` is found
// The `stop` string is ignored, as it is user-defined
StringView GenericLexer::consume_until(const char* stop)
{
size_t start = m_index;
while (!is_eof() && !next_is(stop))
m_index++;
size_t length = m_index - start;
ignore(__builtin_strlen(stop));
if (length == 0)
return {};
return m_input.substring_view(start, length);
}
/*
* Consume a string surrounded by single or double quotes. The returned
* StringView does not include the quotes. An escape character can be provided
* to capture the enclosing quotes. Please note that the escape character will
* still be in the resulting StringView
*/
StringView GenericLexer::consume_quoted_string(char escape_char)
{
if (!next_is(is_quote))
return {};
char quote_char = consume();
size_t start = m_index;
while (!is_eof()) {
if (next_is(escape_char))
m_index++;
else if (next_is(quote_char))
break;
m_index++;
}
size_t length = m_index - start;
if (peek() != quote_char) {
// Restore the index in case the string is unterminated
m_index = start - 1;
return {};
}
// Ignore closing quote
ignore();
return m_input.substring_view(start, length);
}
String GenericLexer::consume_and_unescape_string(char escape_char)
{
auto view = consume_quoted_string(escape_char);
if (view.is_null())
return {};
StringBuilder builder;
for (size_t i = 0; i < view.length(); ++i)
builder.append(consume_escaped_character(escape_char));
return builder.to_string();
}
auto GenericLexer::consume_escaped_code_point(bool combine_surrogate_pairs) -> Result<u32, UnicodeEscapeError>
{
if (!consume_specific("\\u"sv))
return UnicodeEscapeError::MalformedUnicodeEscape;
if (next_is('{'))
return decode_code_point();
return decode_single_or_paired_surrogate(combine_surrogate_pairs);
}
auto GenericLexer::decode_code_point() -> Result<u32, UnicodeEscapeError>
{
bool starts_with_open_bracket = consume_specific('{');
VERIFY(starts_with_open_bracket);
u32 code_point = 0;
while (true) {
if (!next_is(is_ascii_hex_digit))
return UnicodeEscapeError::MalformedUnicodeEscape;
auto new_code_point = (code_point << 4u) | parse_ascii_hex_digit(consume());
if (new_code_point < code_point)
return UnicodeEscapeError::UnicodeEscapeOverflow;
code_point = new_code_point;
if (consume_specific('}'))
break;
}
if (is_unicode(code_point))
return code_point;
return UnicodeEscapeError::UnicodeEscapeOverflow;
}
auto GenericLexer::decode_single_or_paired_surrogate(bool combine_surrogate_pairs) -> Result<u32, UnicodeEscapeError>
{
constexpr size_t surrogate_length = 4;
auto decode_one_surrogate = [&]() -> Optional<u16> {
u16 surrogate = 0;
for (size_t i = 0; i < surrogate_length; ++i) {
if (!next_is(is_ascii_hex_digit))
return {};
surrogate = (surrogate << 4u) | parse_ascii_hex_digit(consume());
}
return surrogate;
};
auto high_surrogate = decode_one_surrogate();
if (!high_surrogate.has_value())
return UnicodeEscapeError::MalformedUnicodeEscape;
if (!Utf16View::is_high_surrogate(*high_surrogate))
return *high_surrogate;
if (!combine_surrogate_pairs || !consume_specific("\\u"sv))
return *high_surrogate;
auto low_surrogate = decode_one_surrogate();
if (!low_surrogate.has_value())
return UnicodeEscapeError::MalformedUnicodeEscape;
if (Utf16View::is_low_surrogate(*low_surrogate))
return Utf16View::decode_surrogate_pair(*high_surrogate, *low_surrogate);
retreat(6);
return *high_surrogate;
}
}
|
