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
|
/*
* Ricochet - A minimalist CLI web browser for fast, distraction-free navigation.
* Copyright (C) 2026 Richard Qin
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*/
#include "ricochet/parser/html_lexer.hh"
#include <cstdint>
#include <string_view>
namespace ricochet::parser {
namespace {
enum class LexerState : std::uint8_t
{
Data, // Reading plain text
TagOpen, // Just encountered '<'
TagName, // Reading the name of an opening tag (e.g., "div")
ClosingTagName, // Reading the name of a closing tag (e.g., "/div")
SwallowAttributes // Ignore attributes mode (ignore until encountering '>')
};
void emit_text( std::string& buffer, std::vector<HtmlToken>& tokens )
{
if ( buffer.empty() ) {
return;
}
bool all_whitespace = true;
for ( const char c : buffer ) {
if ( !std::isspace( static_cast<unsigned char>( c ) ) ) {
all_whitespace = false;
break;
}
}
if ( !all_whitespace ) {
tokens.emplace_back( TextToken { buffer } );
}
buffer.clear();
}
} // namespace
std::vector<HtmlToken> HtmlLexer::tokenize( // NOLINT(readability-convert-member-functions-to-static)
std::string_view html ) const
{
std::vector<HtmlToken> tokens;
LexerState state = LexerState::Data;
std::string buffer {};
for ( const char c : html ) {
switch ( state ) {
case LexerState::Data:
if ( c == '<' ) {
emit_text( buffer, tokens );
state = LexerState::TagOpen;
} else {
buffer += c;
}
break;
case LexerState::TagOpen:
if ( c == '/' ) {
state = LexerState::ClosingTagName;
} else if ( std::isalpha( static_cast<unsigned char>( c ) ) ) {
buffer.push_back( c );
state = LexerState::TagName;
} else {
buffer.push_back( '<' );
buffer.push_back( c );
state = LexerState::Data;
}
break;
case LexerState::TagName:
if ( c == '>' ) {
tokens.emplace_back( TagOpenToken { buffer } );
buffer.clear();
state = LexerState::Data;
} else {
buffer += c;
}
break;
case LexerState::ClosingTagName:
if ( c == '>' ) {
tokens.emplace_back( TagCloseToken { buffer } );
buffer.clear();
state = LexerState::Data;
} else {
buffer += static_cast<char>( std::tolower( static_cast<unsigned char>( c ) ) );
}
break;
case LexerState::SwallowAttributes:
if ( c == '>' ) {
state = LexerState::Data;
}
break;
}
}
emit_text( buffer, tokens );
return tokens;
}
} // namespace ricochet::parser
|
