tortank 0.30.7

Turtle/N3 parser
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203

use std::borrow::Cow;

use nom::branch::alt;
use nom::bytes::streaming::{is_not, take_while_m_n};
use nom::character::complete::anychar;
use nom::character::streaming::{char, multispace1};
use nom::combinator::{map, map_opt, map_res, value, verify};
use nom::error::{FromExternalError, ParseError};
use nom::multi::fold_many0;
use nom::sequence::{delimited, preceded};
use nom::{IResult, Parser};

// copied from https://github.com/rust-bakery/nom/blob/7.1.3/examples/string.rs
// parser combinators are constructed from the bottom up:
// first we write parsers for the smallest elements (escaped characters),
// then combine them into larger parsers.

// Parse a unicode sequence, of the form u{XXXX}, where XXXX is 1 to 6
// hexadecimal numerals. We will combine this later with parse_escaped_char
// to parse sequences like \u{00AC}.
fn parse_unicode<'a, E>(input: &'a str) -> IResult<&'a str, char, E>
where
    E: ParseError<&'a str> + FromExternalError<&'a str, std::num::ParseIntError>,
{
    // `take_while_m_n` parses between `m` and `n` bytes (inclusive) that match
    // a predicate. `parse_hex` here parses between 1 and 6 hexadecimal numerals.
    let parse_hex = take_while_m_n(1, 6, |c: char| c.is_ascii_hexdigit());

    // `preceded` takes a prefix parser, and if it succeeds, returns the result
    // of the body parser. In this case, it parses u{XXXX}.
    let parse_delimited_hex = preceded(
        char('u'),
        // `delimited` is like `preceded`, but it parses both a prefix and a suffix.
        // It returns the result of the middle parser. In this case, it parses
        // {XXXX}, where XXXX is 1 to 6 hex numerals, and returns XXXX
        delimited(char('{'), parse_hex, char('}')),
    );

    // `map_res` takes the result of a parser and applies a function that returns
    // a Result. In this case we take the hex bytes from parse_hex and attempt to
    // convert them to a u32.
    let parse_u32 = map_res(parse_delimited_hex, move |hex| u32::from_str_radix(hex, 16));

    // map_opt is like map_res, but it takes an Option instead of a Result. If
    // the function returns None, map_opt returns an error. In this case, because
    // not all u32 values are valid unicode code points, we have to fallibly
    // convert to char with from_u32.
    map_opt(parse_u32, std::char::from_u32).parse(input)
}

/// Parse an escaped character: \n, \t, \r, \u{00AC}, etc.
fn parse_escaped_char<'a, E>(input: &'a str) -> IResult<&'a str, char, E>
where
    E: ParseError<&'a str> + FromExternalError<&'a str, std::num::ParseIntError>,
{
    preceded(
        char('\\'),
        // `alt` tries each parser in sequence, returning the result of
        // the first successful match
        alt((
            parse_unicode,
            // The `value` parser returns a fixed value (the first argument) if its
            // parser (the second argument) succeeds. In these cases, it looks for
            // the marker characters (n, r, t, etc) and returns the matching
            // character (\n, \r, \t, etc).
            value('\n', char('n')),
            value('\r', char('r')),
            value('\t', char('t')),
            value('\u{08}', char('b')),
            value('\u{0C}', char('f')),
            value('\\', char('\\')),
            value('/', char('/')),
            value('"', char('"')),
        )),
    )
    .parse(input)
}

/// Parse a backslash, followed by any amount of whitespace. This is used later
/// to discard any escaped whitespace.
fn parse_escaped_whitespace<'a, E: ParseError<&'a str>>(
    input: &'a str,
) -> IResult<&'a str, &'a str, E> {
    preceded(char('\\'), multispace1).parse(input)
}
fn parse_escaped_anychar<'a, E: ParseError<&'a str>>(input: &'a str) -> IResult<&'a str, char, E> {
    preceded(char('\\'), anychar).parse(input)
}

/// Parse a non-empty block of text that doesn't include \ or "
fn parse_literal<'a, E: ParseError<&'a str>>(input: &'a str) -> IResult<&'a str, &'a str, E> {
    // `is_not` parses a string of 0 or more characters that aren't one of the
    // given characters.
    let not_quote_slash = is_not("\"\\");

    // `verify` runs a parser, then runs a verification function on the output of
    // the parser. The verification function accepts out output only if it
    // returns true. In this case, we want to ensure that the output of is_not
    // is non-empty.
    verify(not_quote_slash, |s: &str| !s.is_empty()).parse(input)
}

/// A string fragment contains a fragment of a string being parsed: either
/// a non-empty Literal (a series of non-escaped characters), a single
/// parsed escaped character, or a block of escaped whitespace.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
enum StringFragment<'a> {
    Literal(&'a str),
    EscapedChar(char),
    EscapedWS,
    EscapedAnychar(char),
}

/// Combine parse_literal, parse_escaped_whitespace, and parse_escaped_char
/// into a StringFragment.
fn parse_fragment<'a, E>(input: &'a str) -> IResult<&'a str, StringFragment<'a>, E>
where
    E: ParseError<&'a str> + FromExternalError<&'a str, std::num::ParseIntError>,
{
    alt((
        // The `map` combinator runs a parser, then applies a function to the output
        // of that parser.
        map(parse_literal, StringFragment::Literal),
        map(parse_escaped_char, StringFragment::EscapedChar),
        value(StringFragment::EscapedWS, parse_escaped_whitespace),
        map(parse_escaped_anychar, StringFragment::EscapedAnychar),
    ))
    .parse(input)
}

/// Parse a string. Use a loop of parse_fragment and push all of the fragments
/// into an output string.
pub(crate) fn parse_escaped_string<'a, E>(input: &'a str) -> IResult<&'a str, Cow<'a, str>, E>
where
    E: ParseError<&'a str> + FromExternalError<&'a str, std::num::ParseIntError>,
{
    // fold_many0 is the equivalent of iterator::fold. It runs a parser in a loop,
    // and for each output value, calls a folding function on each output value.
    let build_string = || {
        fold_many0(
            // Our parser function– parses a single string fragment
            parse_fragment,
            // Our init value, an empty string
            String::new,
            // Our folding function. For each fragment, append the fragment to the
            // string.
            |mut string, fragment| {
                match fragment {
                    StringFragment::Literal(s) => string.push_str(s),
                    StringFragment::EscapedChar(c) => string.push(c),
                    StringFragment::EscapedWS => {}
                    StringFragment::EscapedAnychar(c) => {
                        string.push('\\');
                        string.push(c)
                    }
                }
                string
            },
        )
    };

    // Finally, parse the string. Note that, if `build_string` could accept a raw
    // " character, the closing delimiter " would never match. When using
    // `delimited` with a looping parser (like fold_many0), be sure that the
    // loop won't accidentally match your closing delimiter!

    map(build_string(), Cow::Owned).parse(input)
}

#[cfg(test)]
mod test {
    use std::borrow::Cow;

    use nom::{Parser, bytes::complete::tag, sequence::delimited};

    use crate::prelude::ParserResult;

    use super::parse_escaped_string;

    #[test]
    fn parse_escaped_string_with_tab() {
        let input = "\"\n".to_string()
            + "This is a long comment\n"
            + "that spans multiple lines.\n\n"
            + "It contains spaces, special characters like %, &, and @, and \n"
            + "even new lines. This format ensures the string is \n"
            + "properly encapsulated without breaking syntax rules.\n"
            + "\t\t\n"
            + "You can add as much text as needed here.\"";
        let expected = "\n".to_string()
            + "This is a long comment\n"
            + "that spans multiple lines.\n\n"
            + "It contains spaces, special characters like %, &, and @, and \n"
            + "even new lines. This format ensures the string is \n"
            + "properly encapsulated without breaking syntax rules.\n\t\t\n"
            + "You can add as much text as needed here.";

        let v: ParserResult<Cow<'_, str>> =
            delimited(tag("\""), parse_escaped_string, tag("\"")).parse(&input);
        let (_, res) = v.unwrap();
        assert_eq!(res, expected);
    }
}