mango 0.4.0

The Mango programming language (UNDER CONSTRUCTION)
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 ::lazy_static::lazy_static;
use ::regex::Regex;

use crate::lexing::lexer::Lexer;
use crate::lexing::reader::reader::{Reader, ReaderResult};
use crate::token::{ParenthesisCloseToken, ParenthesisOpenToken, Tokens};
use crate::token::collect::{parenthesis_close, parenthesis_open, comma, ellipsis, period, newline, unlexable};

lazy_static! {
    static ref SEPARATOR_RE: Regex = Regex::new("^(\\.\\.\\.|…|\\.|,|\r\n|\n|\r)").unwrap();
}

/// Lex any number of parentheses, braces and brackets, and add the tokens to the Lexer.
pub fn lex_separators(reader: &mut impl Reader, lexer: &mut impl Lexer) {

    let mut found_newline = false;
    while let ReaderResult::Match(sym) = reader.strip_match(&*SEPARATOR_RE) {
        let token = match sym.as_str() {
            r"..." | r"…" => ellipsis(),
            r"." => period(),
            r"," => comma(),
            "\r\n" | "\n" | "\r" => {
                // Indentation should be parsed after a newline, so stop.
                found_newline = true;
                lexer.set_at_indentable(true);
                newline()
            },
            _ => unreachable!(),
        };
        lexer.add(token);
        if found_newline { break }
    }
}

#[cfg(test)]
mod grouping {
    use crate::io::source::SourceFile;
    use crate::lexing::lexer::{CodeLexer, Lexer};
    use crate::lexing::reader::source_reader::SourceReader;
    use crate::lexing::tests::create_lexer;
    use crate::token::{EndBlockToken, StartBlockToken, Tokens};
    use crate::token::collect::{comma, ellipsis, period, newline, unlexable};

    use super::lex_separators;
    use crate::token::collect::token_list::TokenList;

    fn check(input: &str, expected: &[Tokens]) {
        let expected: TokenList = expected.into();
        let (source, mut reader, mut lexer) = create_lexer(input);
        lex_separators(&mut reader, &mut lexer);
        assert_eq!(lexer.tokens(), &expected);
    }

    #[test]
    fn empty() {
        check("", &vec![]);
        check("    \t", &vec![]);
    }

    #[test]
    fn mismatch() {
        check("(", &vec![]);
        check("0", &vec![]);
        check("a", &vec![]);
    }

    #[test]
    fn single_ellipsis() {
        check(r"...", &vec![ellipsis()]);
        check(r"…", &vec![ellipsis()]);
    }

    #[test]
    fn multiple_ellipsis() {
        check(r"...…", &vec![ellipsis(), ellipsis()]);
        check(r"…...", &vec![ellipsis(), ellipsis()]);
        check(r"……", &vec![ellipsis(), ellipsis()]);
        check(r"......", &vec![ellipsis(), ellipsis()]);
    }

    #[test]
    fn single_period() {
        check(r".", &vec![period()]);
    }

    #[test]
    fn multiple_period() {
        check(r"..", &vec![period(), period()]);
        check(r".. .", &vec![period(), period(), period()]);
    }

    #[test]
    fn single_comma() {
        check(r",", &vec![comma()]);
    }

    #[test]
    fn multiple_comma() {
        // Probably a syntax error later on, but that's the parser's problem.
        check(r",,", &vec![comma(), comma()]);
    }

    #[test]
    fn single_newline() {
        check("\r\n", &vec![newline()]);
        check("\n", &vec![newline()]);
        check("\r", &vec![newline()]);
    }

    #[test]
    fn multiple_newline() {
        // Only one newline should be matched
        check("\n\n", &vec![newline()]);
        check("\r\r", &vec![newline()]);
        check("\r\n \r\n", &vec![newline()]);
    }

    #[test]
    fn after_mismatch() {
        check(r"1 …", &vec![]);
        check(r"1 .", &vec![]);
        check(r"1 ,", &vec![]);
        check("1 \r", &vec![]);
    }

    #[test]
    fn combined_1() {
        check(",....\r\n", &vec![
            comma(),
            ellipsis(),
            period(),
            newline(),
        ]);
    }

    #[test]
    fn combined_2() {
        check("...….,\n,", &vec![
            ellipsis(),
            ellipsis(),
            period(),
            comma(),
            newline(),
        ]);
    }

    #[test]
    fn and_words() {
        check(r"...abc", &vec![ellipsis()]);
        check(r".abc", &vec![period()]);
        check(r",abc", &vec![comma()]);
        check("\nabc", &vec![newline()]);
    }
}