oak-markdown 0.0.11

High-performance incremental Markdown parser for the oak ecosystem with flexible configuration, optimized for documentation and content creation.
Documentation 
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

use crate::lexer::{MarkdownLexer, State, token_type::MarkdownTokenType};
use oak_core::Source;

impl<'config> MarkdownLexer<'config> {
    /// Handles list markers.
    pub fn lex_list_marker<S: Source + ?Sized>(&self, state: &mut State<S>) -> bool {
        let start_pos = state.get_position();

        let mut check_pos = start_pos;
        while check_pos > 0 {
            check_pos -= 1;
            if let Some(ch) = state.source().get_char_at(check_pos) {
                if ch == '\n' || ch == '\r' {
                    break;
                }
                else if ch != ' ' && ch != '\t' {
                    return false;
                }
            }
        }

        if let Some(ch) = state.peek() {
            match ch {
                '-' | '*' | '+' => {
                    state.advance(1);
                    if let Some(next_ch) = state.peek() {
                        if next_ch == ' ' || next_ch == '\t' {
                            state.add_token(MarkdownTokenType::ListMarker, start_pos, state.get_position());
                            return true;
                        }
                    }
                    state.set_position(start_pos);
                    false
                }
                '0'..='9' => {
                    while let Some(digit) = state.peek() {
                        if digit.is_ascii_digit() { state.advance(1) } else { break }
                    }

                    if let Some('.') = state.peek() {
                        state.advance(1);
                        if let Some(next_ch) = state.peek() {
                            if next_ch == ' ' || next_ch == '\t' {
                                state.add_token(MarkdownTokenType::ListMarker, start_pos, state.get_position());
                                return true;
                            }
                        }
                    }

                    state.set_position(start_pos);
                    false
                }
                _ => false,
            }
        }
        else {
            false
        }
    }

    /// Handles task markers.
    pub fn lex_task_marker<S: Source + ?Sized>(&self, state: &mut State<S>) -> bool {
        let start_pos = state.get_position();

        if let Some('[') = state.peek() {
            state.advance(1);
            if let Some(ch) = state.peek() {
                if ch == ' ' || ch == 'x' || ch == 'X' {
                    state.advance(1);
                    if let Some(']') = state.peek() {
                        state.advance(1);
                        state.add_token(MarkdownTokenType::TaskMarker, start_pos, state.get_position());
                        return true;
                    }
                }
            }
            state.set_position(start_pos);
        }
        false
    }

    /// Lexes definition list descriptions.
    pub fn lex_definition_description<S: Source + ?Sized>(&self, state: &mut State<S>) -> bool {
        let start_pos = state.get_position();

        let mut check_pos = start_pos;
        while check_pos > 0 {
            check_pos -= 1;
            if let Some(ch) = state.source().get_char_at(check_pos) {
                if ch == '\n' || ch == '\r' {
                    break;
                }
                else if ch != ' ' && ch != '\t' {
                    return false;
                }
            }
        }

        if let Some(':') = state.peek() {
            state.advance(1);
            if let Some(next_ch) = state.peek() {
                if next_ch == ' ' || next_ch == '\t' {
                    state.add_token(MarkdownTokenType::DefinitionDescription, start_pos, state.get_position());
                    return true;
                }
            }
            state.set_position(start_pos);
            false
        }
        else {
            false
        }
    }

    /// Lexes abbreviation definitions.
    pub fn lex_abbreviation<S: Source + ?Sized>(&self, state: &mut State<S>) -> bool {
        let start_pos = state.get_position();

        let mut check_pos = start_pos;
        while check_pos > 0 {
            check_pos -= 1;
            if let Some(ch) = state.source().get_char_at(check_pos) {
                if ch == '\n' || ch == '\r' {
                    break;
                }
                else if ch != ' ' && ch != '\t' {
                    return false;
                }
            }
        }

        if let Some('*') = state.peek() {
            state.advance(1);
            if let Some('[') = state.peek() {
                state.advance(1);

                while let Some(ch) = state.peek() {
                    if ch == ']' {
                        state.advance(1);
                        if let Some(':') = state.peek() {
                            state.advance(1);
                            state.add_token(MarkdownTokenType::Abbreviation, start_pos, state.get_position());
                            return true;
                        }
                        break;
                    }
                    state.advance(ch.len_utf8());
                }
            }
            state.set_position(start_pos);
        }
        false
    }
}