blob: d9ce23ac760e2b5c2b93f55dca25d06405c73e47 (
plain)
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
|
/*
* 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/>.
*/
#pragma once
#include <string>
#include <string_view>
#include <variant>
#include <vector>
namespace ricochet::parser {
struct TextToken
{
std::string content {};
};
struct TagOpenToken
{
std::string name {};
};
struct TagCloseToken
{
std::string name {};
};
using HtmlToken = std::variant<TextToken, TagOpenToken, TagCloseToken>;
class HtmlLexer
{
public:
HtmlLexer() = default;
~HtmlLexer() = default;
HtmlLexer( const HtmlLexer& ) = delete;
HtmlLexer& operator=( const HtmlLexer& ) = delete;
HtmlLexer( HtmlLexer&& ) = delete;
HtmlLexer& operator=( HtmlLexer&& ) = delete;
/**
* @brief Perform lexical analysis to convert HTML source code into a structured sequence of tokens
*/
std::vector<HtmlToken> tokenize( std::string_view html ) const;
private:
};
} // namespace ricochet::parser
|
