nom-lua 0.0.2

Lua 5.3 parser written in nom
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

// Copyright 2017 The nom-lua project developers
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

use ast::ASTNode;
use nom::{hex_digit, digit};
use std::{str, char};

named!(pub parse_string<ASTNode>,
       map!(alt!(/*parse_string_literal |*/ parse_string_short_literal), |s| ASTNode::String(s)));


//named!(parse_string_literal<String>, map_res!(raw_string, |s, _| s));

//pub fn raw_string(input: &str) -> IResult<&str, (String, usize)> {
//    let mut chars = input.char_indices();
//    let mut n = 0;
//    while let Some((byte_offset, ch)) = chars.next() {
//        match ch {
//            '"' => {
//                n = byte_offset;
//                break;
//            }
//            '#' => {}
//            _ => return IResult::Error,
//        }
//    }
//    let mut s = String::new();
//    for (byte_offset, ch) in chars {
//        match ch {
//            '"' if input[byte_offset + 1..].starts_with(&input[..n]) => {
//                let rest = &input[byte_offset + 1 + n..];
//                return IResult::Done(rest, (s, n));
//            }
//            '\r' => {}
//            _ => s.push(ch),
//        }
//    }
//    IResult::Error
//}

// TODO: A short literal string cannot contain unescaped line breaks nor escapes not forming a valid escape sequence.
// TODO: " ' inside strings are valid
named!(parse_string_short_literal<String>,
       delimited!(
        alt!(tag!("\"") | tag!("'")),
        fold_many0!(alt!(
            map!(linebreak, |_| '\n') |
            parse_byte |
            parse_unicode |
            one_of!("\x07\x08\x09\x0A\x0B\x0C\x0D")
            // Find a way to discard the output from this: preceded!(tag!(r#"\z"#), alt!(sp |
            // linebreak))
        ), String::new(), |mut acc: String, item| {
            acc.push(item);
            acc
        }),
        alt!(tag!("\"") | tag!("'"))));

named!(parse_byte<char>, alt!(parse_byte_x | parse_byte_d));

named!(parse_byte_x<char>, map!(map_res!(map_res!(
                preceded!(tag!("\\x"), hex_digit),
                str::from_utf8),
            |s| u8::from_str_radix(s, 16)), |i: u8| i as char));

named!(linebreak, alt!(tag!("\\\r\n") | tag!("\\\n\r") | tag!("\\\n")));


// TODO: if a decimal escape sequence is to be followed by a digit, it must be expressed using exactly three digits
// Notice, the fold_many_m_n is not actually enforcing bounds here, because digit recognizes
// more than one character, but I think this implementation might be usefull for the future
named!(parse_byte_d<char>, map!(map_res!(
            preceded!(tag!("\\"), fold_many_m_n!(1, 3, digit, String::new(), |mut acc: String, item: &[u8]| {
                for c in item {
                    acc.push(*c as char);
                }
                acc
            })),
            |s: String| s.parse::<u8>()), |i: u8| i as char));

named!(parse_unicode<char>,
       map_opt!(
           map_res!(
               map_res!(
                   delimited!(tag!("\\u{"), recognize!(hex_digit), tag!("}")),
                   str::from_utf8),
                   |h| u32::from_str_radix(h, 16)),
                   char::from_u32));

#[cfg(test)]
mod tests {
    ast_panic_test!(parse_unicode_1, parse_unicode, r#"\u{}"#);
    ast_test!(parse_unicode_2, parse_unicode, r#"\u{A}"#, char::from_u32(0xA).unwrap());
    ast_test!(parse_unicode_3, parse_unicode, r#"\u{a2}"#, char::from_u32(0xa2).unwrap());
    ast_test!(parse_unicode_4, parse_unicode, r#"\u{AFf9}"#, char::from_u32(0xAFf9).unwrap());
    ast_test!(parse_unicode_5, parse_unicode, r#"\u{0000000000000FFFF}"#, char::from_u32(0xFFFF).unwrap());
    ast_test!(parse_unicode_6, parse_unicode, r#"\u{10FFFF}"#, char::from_u32(0x10FFFF).unwrap());
    ast_panic_test!(parse_unicode_7, parse_unicode, r#"\u{110000}"#);


    ast_test!(parse_byte_d_1, parse_byte_d, r#"\0"#, '\0');
    ast_test!(parse_byte_d_2, parse_byte_d, r#"\00"#, '\0');
    ast_test!(parse_byte_d_3, parse_byte_d, r#"\000"#, '\0');
    // TODO: This should parse to the rust string r#"\u{0}0"# make this test reflect that
    ast_test!(parse_byte_d_4, parse_byte_d, r#"\0000"#, '\0');
    ast_test!(parse_byte_d_5, parse_byte_d, r#"\230"#, '\u{E6}');
    ast_panic_test!(parse_byte_d_6, parse_byte_d, r#"\256"#);


    ast_test!(parse_byte_x_1, parse_byte_x, r#"\x00"#, '\0');
    // TODO: This should parse to the rust string "\u{0a}0" make this test reflect that
    //ast_test!(parse_byte_x_2, parse_byte_x, r#"\x0a0"#, '\x0a');
    ast_test!(parse_byte_x_3, parse_byte_x, r#"\x23"#, '\u{23}');
    ast_test!(parse_byte_x_4, parse_byte_x, r#"\x000023"#, '\u{23}');
    ast_test!(parse_byte_x_5, parse_byte_x, r#"\xFf"#, '\u{FF}');

    ast_test!(parse_string_short_literal_1, parse_string_short_literal, r#""""#, "");
    ast_test!(parse_string_short_literal_2, parse_string_short_literal, r#"''"#, "");
    ast_test!(parse_string_short_literal_3, parse_string_short_literal, r#"'\u{1F62A}'"#, "😪");
    ast_test!(parse_string_short_literal_4, parse_string_short_literal, r#"'\097'"#, "a");
    ast_test!(parse_string_short_literal_5, parse_string_short_literal, format!("'{}'", "\x07\x08\x09\x0A\x0B\x0C\x0D"), "\x07\x08\x09\x0A\x0B\x0C\x0D");
    ast_test!(parse_string_short_literal_6, parse_string_short_literal, "'\\\n\r'", "\n");
    ast_test!(parse_string_short_literal_7, parse_string_short_literal, "'\\\r\n'", "\n");
    ast_test!(parse_string_short_literal_8, parse_string_short_literal, "'\\\n'", "\n");
}