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
213
214
215
|
/*
* Copyright (c) 2020, Emanuel Sprung <emanuel.sprung@gmail.com>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include "RegexLexer.h"
#include <AK/Assertions.h>
#include <AK/Debug.h>
#include <AK/Format.h>
#include <stdio.h>
namespace regex {
const char* Token::name(const TokenType type)
{
switch (type) {
#define __ENUMERATE_REGEX_TOKEN(x) \
case TokenType::x: \
return #x;
ENUMERATE_REGEX_TOKENS
#undef __ENUMERATE_REGEX_TOKEN
default:
VERIFY_NOT_REACHED();
return "<Unknown>";
}
}
const char* Token::name() const
{
return name(m_type);
}
Lexer::Lexer(const StringView source)
: m_source(source)
{
}
ALWAYS_INLINE int Lexer::peek(size_t offset) const
{
if ((m_position + offset) >= m_source.length())
return EOF;
return (unsigned char)m_source[m_position + offset];
}
void Lexer::back(size_t offset)
{
if (offset == m_position + 1)
offset = m_position; // 'position == 0' occurs twice.
VERIFY(offset <= m_position);
if (!offset)
return;
m_position -= offset;
m_previous_position = (m_position > 0) ? m_position - 1 : 0;
m_current_char = m_source[m_position];
}
ALWAYS_INLINE void Lexer::consume()
{
m_previous_position = m_position;
if (m_position >= m_source.length()) {
m_position = m_source.length() + 1;
m_current_char = EOF;
return;
}
m_current_char = m_source[m_position++];
}
void Lexer::reset()
{
m_position = 0;
m_current_token = { TokenType::Eof, 0, StringView(nullptr) };
m_current_char = 0;
m_previous_position = 0;
}
bool Lexer::try_skip(char c)
{
if (peek() != c)
return false;
consume();
return true;
}
char Lexer::skip()
{
auto c = peek();
consume();
VERIFY(c != EOF);
return c;
}
Token Lexer::next()
{
size_t token_start_position;
auto begin_token = [&] {
token_start_position = m_position;
};
auto commit_token = [&](auto type) -> Token& {
VERIFY(token_start_position + m_previous_position - token_start_position + 1 <= m_source.length());
auto substring = m_source.substring_view(token_start_position, m_previous_position - token_start_position + 1);
m_current_token = Token(type, token_start_position, substring);
return m_current_token;
};
auto emit_token = [&](auto type) -> Token& {
m_current_token = Token(type, m_position, m_source.substring_view(m_position, 1));
consume();
return m_current_token;
};
auto match_escape_sequence = [&]() -> size_t {
switch (peek(1)) {
case '^':
case '.':
case '[':
case ']':
case '$':
case '(':
case ')':
case '|':
case '*':
case '+':
case '?':
case '{':
case '\\':
return 2;
default:
dbgln_if(REGEX_DEBUG, "[LEXER] Found invalid escape sequence: \\{:c} (the parser will have to deal with this!)", peek(1));
return 0;
}
};
while (m_position <= m_source.length()) {
auto ch = peek();
if (ch == '(')
return emit_token(TokenType::LeftParen);
if (ch == ')')
return emit_token(TokenType::RightParen);
if (ch == '{')
return emit_token(TokenType::LeftCurly);
if (ch == '}')
return emit_token(TokenType::RightCurly);
if (ch == '[')
return emit_token(TokenType::LeftBracket);
if (ch == ']')
return emit_token(TokenType::RightBracket);
if (ch == '.')
return emit_token(TokenType::Period);
if (ch == '*')
return emit_token(TokenType::Asterisk);
if (ch == '+')
return emit_token(TokenType::Plus);
if (ch == '$')
return emit_token(TokenType::Dollar);
if (ch == '^')
return emit_token(TokenType::Circumflex);
if (ch == '|')
return emit_token(TokenType::Pipe);
if (ch == '?')
return emit_token(TokenType::Questionmark);
if (ch == ',')
return emit_token(TokenType::Comma);
if (ch == '/')
return emit_token(TokenType::Slash);
if (ch == '=')
return emit_token(TokenType::EqualSign);
if (ch == ':')
return emit_token(TokenType::Colon);
if (ch == '-')
return emit_token(TokenType::HyphenMinus);
if (ch == '\\') {
size_t escape = match_escape_sequence();
if (escape > 0) {
begin_token();
for (size_t i = 0; i < escape; ++i)
consume();
return commit_token(TokenType::EscapeSequence);
}
}
if (ch == EOF)
break;
return emit_token(TokenType::Char);
}
return Token(TokenType::Eof, m_position, nullptr);
}
}
|
