misc-conf 0.1.2

Nom parser for nginx/apache configuration
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

use nom::character::{complete::space0, streaming::anychar};
#[allow(unused_imports)]
use nom::{
    branch::alt,
    bytes::complete::{escaped, tag, take_till, take_until, take_while, take_while_m_n},
    character::{
        complete::{alphanumeric1, char as cchar, multispace0, multispace1, none_of, one_of},
        is_alphabetic, is_newline, is_space,
        streaming::space1,
    },
    combinator::{fail, map, map_res, opt, value},
    number::complete::be_u8,
    sequence::{delimited, tuple},
    IResult,
};

use crate::lexer::Literal;

#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub enum Token<'a> {
    OpenTag,
    EndTag,
    CloseTag,
    NewLine,
    Eof,
    Literal(Literal<'a>),
}

impl<'a> Token<'a> {
    pub fn ident(&self) -> Option<&'a str> {
        // TODO: check ident rule
        self.raw_string()
    }

    pub fn raw_string(&self) -> Option<&'a str> {
        self.literal().map(|l| l.raw)
    }

    pub fn literal(&self) -> Option<Literal<'a>> {
        match self {
            Self::Literal(l) => Some(*l),
            _ => None,
        }
    }
}

fn opentag(input: &[u8]) -> IResult<&[u8], Token> {
    value(Token::OpenTag, tag(b"<"))(input)
}

fn endtag(input: &[u8]) -> IResult<&[u8], Token> {
    value(Token::EndTag, tag(b">"))(input)
}

fn newline(input: &[u8]) -> IResult<&[u8], Token> {
    value(Token::NewLine, tuple((opt(tag(b"\r")), tag(b"\n"))))(input)
}

fn closetag(input: &[u8]) -> IResult<&[u8], Token> {
    value(Token::CloseTag, tag(b"</"))(input)
}

fn comment(input: &[u8]) -> IResult<&[u8], &[u8]> {
    map(
        tuple((
            tag("#"),
            take_till(is_newline),
            opt(tag(b"\r")),
            opt(tag(b"\n")),
        )),
        |x| x.1,
    )(input)
}

fn literal(input: &[u8]) -> IResult<&[u8], Token> {
    let (_, mut first) = be_u8(input)?;

    let (input, raw) = match first {
        b'"' => map_res(
            // for empty string
            map(
                delimited(
                    cchar(first as _),
                    opt(escaped(none_of(r#"\""#), '\\', anychar)),
                    cchar(first as _),
                ),
                Option::unwrap_or_default,
            ),
            std::str::from_utf8,
        )(input),
        b'\'' => map_res(
            // for empty string
            map(
                delimited(
                    cchar(first as _),
                    opt(escaped(none_of(r#"\'"#), '\\', anychar)),
                    cchar(first as _),
                ),
                Option::unwrap_or_default,
            ),
            std::str::from_utf8,
        )(input),
        _ => {
            first = 0;
            map_res(
                escaped(none_of(" \t\r\n<>'\"\\"), '\\', anychar),
                std::str::from_utf8,
            )(input)
        }
    }?;
    Ok((input, Token::Literal(Literal { raw, quote: first })))
}

pub fn tokenizer(input: &[u8]) -> IResult<&[u8], Token> {
    inner_tokenizer::<false>(input)
}

fn space_and_comment<const NL: bool>(input: &[u8]) -> IResult<&[u8], Option<&[u8]>> {
    let space = if NL { space0 } else { multispace0 };
    map(tuple((space, opt(comment))), |x| x.1)(input)
}

pub fn inner_tokenizer<const NL: bool>(mut input: &[u8]) -> IResult<&[u8], Token> {
    loop {
        let (rest, cmt) = space_and_comment::<NL>(input)?;
        input = rest;
        if cmt.is_some() {
            // println!("[cmt] {:?}", std::str::from_utf8(cmt.unwrap()));
        } else {
            break;
        }
    }
    if input.len() == 0 {
        return Ok((input, Token::Eof));
    }
    alt((closetag, opentag, endtag, newline, literal))(input)
}