tortilla 0.1.0

Somewhat syntax-aware text wrapping for source code and plain text documents
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

use unicode_segmentation::{GraphemeIndices, UnicodeSegmentation};

use super::{Newline, Token};

enum State {
    Clean,
    Word(usize),
}

pub(super) struct Lex<'t> {
    input: &'t str,
    inner: GraphemeIndices<'t>,
    state: State,
    pending: Option<Token<'static>>,
}

impl<'t> Lex<'t> {
    pub fn new(input: &'t str) -> Self {
        Self {
            input,
            state: State::Clean,
            inner: input.grapheme_indices(true),
            pending: None,
        }
    }
}

fn word_break(grapheme: &str) -> Option<Token<'static>> {
    Some(match grapheme {
        " " => Token::Space,
        "\t" => Token::Tab,
        "\n" => Token::Newline(Newline::LF),
        "\r\n" => Token::Newline(Newline::CRLF),
        _ => return None,
    })
}

impl<'t> Iterator for Lex<'t> {
    type Item = Token<'t>;

    fn next(&mut self) -> Option<Self::Item> {
        if let Some(token) = self.pending.take() {
            return Some(token);
        }

        for (byte_idx, grapheme) in self.inner.by_ref() {
            match self.state {
                State::Clean => {
                    if let Some(token) = word_break(grapheme) {
                        return Some(token);
                    } else {
                        self.state = State::Word(byte_idx);
                    }
                }

                State::Word(start_idx) => {
                    if let Some(token) = word_break(grapheme) {
                        self.state = State::Clean;
                        self.pending = Some(token);
                        return Some(Token::Word(&self.input[start_idx..byte_idx]));
                    }
                }
            }
        }

        if let State::Word(start_idx) = self.state {
            self.state = State::Clean;
            return Some(Token::Word(&self.input[start_idx..]));
        }

        None
    }
}

#[cfg(test)]
mod tests {
    use crate::tokens;

    fn lex(input: &str) -> Vec<crate::Token<'_>> {
        super::Lex::new(input).collect()
    }

    #[test]
    fn empty() {
        assert_eq!(lex(""), tokens![]);
    }

    #[test]
    fn single_space() {
        assert_eq!(lex(" "), tokens![s]);
    }

    #[test]
    fn single_tab() {
        assert_eq!(lex("\t"), tokens![t]);
    }

    #[test]
    fn mixed_whitespace() {
        assert_eq!(lex("\t  \t "), tokens![t, s, s, t, s]);
    }

    #[test]
    fn single_lf() {
        assert_eq!(lex("\n"), tokens![lf]);
    }

    #[test]
    fn single_crlf() {
        assert_eq!(lex("\r\n"), tokens![crlf]);
    }

    #[test]
    fn mixed_newlines() {
        assert_eq!(lex("\r\n\n\n\r\n"), tokens![crlf, lf, lf, crlf],);
    }

    #[test]
    fn one_letter_word() {
        assert_eq!(lex("a"), tokens!["a"]);
    }

    #[test]
    fn multi_letter_word() {
        assert_eq!(lex("foobar"), tokens!["foobar"]);
    }

    #[test]
    fn full_sentence() {
        assert_eq!(
            lex("Buffalo buffalo Buffalo buffalo buffalo buffalo Buffalo buffalo."),
            tokens![
                "Buffalo", s, "buffalo", s, "Buffalo", s, "buffalo", s, "buffalo", s, "buffalo", s,
                "Buffalo", s, "buffalo."
            ]
        );
    }

    #[test]
    fn mixed_paragraphs() {
        assert_eq!(
            lex("\t\tfoo  bar \nbaz\r\n"),
            tokens![t, t, "foo", s, s, "bar", s, lf, "baz", crlf]
        );
    }
}