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

/*
 * tokenizer.rs
 *
 * ftml - Library to parse Wikidot text
 * Copyright (C) 2019-2021 Wikijump Team
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero 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 Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
 */

use crate::parsing::{ExtractedToken, Token};
use crate::text::FullText;

#[derive(Debug, Clone)]
pub struct Tokenization<'t> {
    tokens: Vec<ExtractedToken<'t>>,
    full_text: FullText<'t>,
}

impl<'t> Tokenization<'t> {
    #[inline]
    pub fn tokens<'r>(&'r self) -> &'r [ExtractedToken<'t>] {
        &self.tokens
    }

    #[inline]
    pub(crate) fn full_text(&self) -> FullText<'t> {
        self.full_text
    }
}

impl<'t> From<Tokenization<'t>> for Vec<ExtractedToken<'t>> {
    #[inline]
    fn from(tokenization: Tokenization<'t>) -> Vec<ExtractedToken<'t>> {
        tokenization.tokens
    }
}

/// Take an input string and produce a list of tokens for consumption by the parser.
pub fn tokenize<'t>(log: &slog::Logger, text: &'t str) -> Tokenization<'t> {
    let log = &log.new(slog_o!(
        "filename" => slog_filename!(),
        "lineno" => slog_lineno!(),
        "function" => "tokenize",
        "text" => str!(text),
    ));

    info!(log, "Running lexer on text");

    let tokens = Token::extract_all(log, text);
    let full_text = FullText::new(text);

    Tokenization { tokens, full_text }
}