brack-tokenizer 0.1.0

The tokenizer for the Brack programming language
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

use crate::{
    tokenizer::Tokenizer,
    tokens::{Location, LocationData, Token},
};

use unicode_segmentation::UnicodeSegmentation;

pub fn separate(s: &str) -> (String, String) {
    let graphemes = s.graphemes(true);
    match graphemes.count() {
        0 => ('\0'.to_string(), String::new()),
        1 => (s.graphemes(true).nth(0).unwrap().to_string(), String::new()),
        _ => {
            let mut graphemes = s.graphemes(true);
            let head = graphemes.next().unwrap().to_string();
            let tail = graphemes.collect::<String>();
            (head, tail)
        }
    }
}

pub fn take_text_token_from_pool(t: &Tokenizer, strip: bool) -> Option<(Tokenizer, Token)> {
    let pool = t.pool.clone().unwrap_or_default();

    if &pool == "" {
        return None;
    }

    if strip {
        let mut space_count = 0;
        for c in pool.chars() {
            if c == ' ' {
                space_count += 1;
            } else {
                break;
            }
        }
        let t2 = Tokenizer {
            column: Some(t.column.unwrap_or_default()),
            token_start_column: Some(t.token_start_column.unwrap_or_default() + space_count),
            ..Default::default()
        };
        return Some((
            t.merge(&t2),
            Token::Text(
                pool.trim().to_string(),
                Location {
                    start: LocationData {
                        line: t.token_start_line.unwrap_or_default(),
                        character: t.token_start_column.unwrap_or_default() + space_count,
                    },
                    end: LocationData {
                        line: t.line.unwrap_or_default(),
                        character: t.column.unwrap_or_default(),
                    },
                },
            ),
        ));
    }

    let t2 = Tokenizer {
        token_start_column: Some(t.column.unwrap_or_default()),
        ..Default::default()
    };
    return Some((
        t.merge(&t2),
        Token::Text(
            pool.to_string(),
            Location {
                start: LocationData {
                    line: t.token_start_line.unwrap_or_default(),
                    character: t.token_start_column.unwrap_or_default(),
                },
                end: LocationData {
                    line: t.line.unwrap_or_default(),
                    character: t.column.unwrap_or_default(),
                },
            },
        ),
    ));
}

pub fn update_tokens(t: &Tokenizer, strip: bool) -> Vec<Token> {
    let mut tokens = t.tokens.clone().unwrap_or_default();
    let pool = t.pool.clone().unwrap_or_default();

    if &pool == "" {
        return tokens;
    }

    if strip {
        let mut space_count = 0;
        for c in pool.chars() {
            if c == ' ' {
                space_count += 1;
            } else {
                break;
            }
        }
        tokens.push(Token::Text(
            pool.trim().to_string(),
            Location {
                start: LocationData {
                    line: t.token_start_line.unwrap_or_default() + space_count,
                    character: t.token_start_column.unwrap_or_default(),
                },
                end: LocationData {
                    line: t.line.unwrap_or_default(),
                    character: t.column.unwrap_or_default(),
                },
            },
        ));
        return tokens;
    }

    tokens.push(Token::Text(
        pool.to_string(),
        Location {
            start: LocationData {
                line: t.token_start_line.unwrap_or_default(),
                character: t.token_start_column.unwrap_or_default(),
            },
            end: LocationData {
                line: t.line.unwrap_or_default(),
                character: t.column.unwrap_or_default(),
            },
        },
    ));
    tokens
}