ruby-parser 0.0.0-dev1

A parser for the Ruby language
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

use crate::*;
use nom::branch::alt;
use nom::character::complete::{char, none_of, one_of};
use nom::combinator::map;
use nom::multi::many0;

/// `'` *single_quoted_string_character** `'`
pub(crate) fn single_quoted_string(i: Input) -> StringResult {
    let (i, _) = char('\'')(i)?;
    let (i, contents) = many0(single_quoted_string_character)(i)?;
    let (i, _) = char('\'')(i)?;
    let mut string = String::new();
    for s in contents {
        string.push_str(&s);
    }
    Ok((i, string))
}

/// *single_quoted_string_non_escaped_character* | *single_quoted_escape_sequence*
pub(crate) fn single_quoted_string_character(i: Input) -> StringResult {
    alt((
        map(single_quoted_string_non_escaped_character, |char| {
            char.to_string()
        }),
        single_quoted_escape_sequence,
    ))(i)
}

/// *single_escape_character_sequence* | *single_quoted_string_non_escaped_character_sequence*
pub(crate) fn single_quoted_escape_sequence(i: Input) -> StringResult {
    alt((
        single_escape_character_sequence,
        single_quoted_string_non_escaped_character_sequence,
    ))(i)
}

/// `\` *single_quoted_string_meta_character*
pub(crate) fn single_escape_character_sequence(i: Input) -> StringResult {
    let (i, _) = char('\\')(i)?;
    let (i, char) = single_quoted_string_meta_character(i)?;
    Ok((i, char.to_string()))
}

/// `\` *single_quoted_string_non_escaped_character*
pub(crate) fn single_quoted_string_non_escaped_character_sequence(i: Input) -> StringResult {
    let (i, char1) = char('\\')(i)?;
    let (i, char2) = single_quoted_string_non_escaped_character(i)?;
    Ok((i, string_from_2_chars(char1, char2)))
}

/// `'` | `\`
pub(crate) fn single_quoted_string_meta_character(i: Input) -> CharResult {
    one_of("'\\")(i)
}

/// *source_character* **but not** *single_quoted_string_meta_character*
pub(crate) fn single_quoted_string_non_escaped_character(i: Input) -> CharResult {
    none_of("'\\")(i)
}

/// Constructs a string from two characters
fn string_from_2_chars(c1: char, c2: char) -> String {
    let mut string = String::with_capacity(c1.len_utf8() + c2.len_utf8());
    string.push(c1);
    string.push(c2);
    string
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_single_quoted_string_non_escaped_character_sequence() {
        use_parser!(
            single_quoted_string_non_escaped_character_sequence
        );
        // Parse errors
        assert_err!("");
        assert_err!("\\");
        assert_err!("\\\\");
        assert_err!("\\'");
        assert_err!("foo");
        // Success cases
        assert_ok!("\\1", "\\1".to_owned());
        assert_ok!("\\a", "\\a".to_owned());
        assert_ok!("\\東", "\\東".to_owned()); // U+6771: 'CJK Unified Ideograph-6771' "East"
    }

    #[test]
    fn test_single_escape_character_sequence() {
        use_parser!(single_escape_character_sequence);
        // Parse errors
        assert_err!("");
        assert_err!("\\");
        assert_err!("\\1");
        assert_err!("\\a");
        assert_err!("foo");
        // Success cases
        assert_ok!("\\'", "'".to_owned());
        assert_ok!("\\\\", "\\".to_owned());
    }

    #[test]
    fn test_single_quoted_string() {
        use_parser!(single_quoted_string);
        fn t(i: &str) -> String {
            i.to_owned()
        }
        // Parse errors
        assert_err!("");
        assert_err!("\\''");
        assert_err!("'\\\\''");
        assert_err!("foo");
        assert_err!("'");
        assert_err!("'''");
        assert_err!("'foo");
        // Success cases
        assert_ok!("''");
        assert_ok!("'\\''");
        assert_ok!("'This is a normal string.'", t("This is a normal string."));
        assert_ok!(
            "'Here\\'s \\a \"handful\" of chars: \\\\ \n \0 東 é é.'",
            t("Here's \\a \"handful\" of chars: \\ \n \0 東 é é.")
        );
        // Semantics
        assert_ok!("'\\a\\'\\\\'", t("\\a'\\"));
        // Positioning
        assert_eq!(
            single_quoted_string("'One\nTwo\nThree'".into()),
            Ok((Input::new_with_pos("", 15, 3, 7), t("One\nTwo\nThree")))
        );
        assert_eq!(
            single_quoted_string("''".into()),
            Ok((Input::new_with_pos("", 2, 1, 3), t("")))
        );
        assert_eq!(
            single_quoted_string("'\n'".into()),
            Ok((Input::new_with_pos("", 3, 2, 2), t("\n")))
        );
    }
}