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

//! Library and application for parsing hyperlinks and link reference
//! definitions in Markdown, reStructuredText, Asciidoc and HTML format. The
//! library implements the
//! [CommonMark Specification 0.29](https://spec.commonmark.org/0.29/),
//! [reStructuredText Markup Specification](https://docutils.sourceforge.io/docs/ref/rst/restructuredtext.html)
//! (revision 8571, date 2020-10-28),
//! [Asciidoctor User Manual, chapter 26](https://asciidoctor.org/docs/user-manual/#url) (date 2020-12-03)
//! and the
//! [HTML 5.2: section 4.5.](https://www.w3.org/TR/html52/textlevel-semantics.html#the-a-element)
//! specification.
#![allow(dead_code)]

pub mod iterator;
pub mod parser;
pub mod renderer;

use nom::error::Error;
use nom::error::ErrorKind;
use nom::error::ParseError;
use nom::Err;
use nom::IResult;

/// A parser similar to `nom::bytes::complete::take_until()`, but that does not
/// stop at balanced opening and closing tags. It is designed to work inside the
/// `nom::sequence::delimited()` parser.
///
/// # Basic usage
/// ```
/// use nom::bytes::complete::tag;
/// use nom::sequence::delimited;
/// use parse_hyperlinks::take_until_unbalanced;
///
/// let mut parser = delimited(tag("<"), take_until_unbalanced('<', '>'), tag(">"));
/// assert_eq!(parser("<<inside>inside>abc"), Ok(("abc", "<inside>inside")));
/// ```
/// It skips nested brackets until it finds an extra unbalanced closing bracket. Escaped brackets
/// like `\<` and `\>` are not considered as brackets and are not counted. This function is
/// very similar to `nom::bytes::complete::take_until(">")`, except it also takes nested brackets.
pub fn take_until_unbalanced(
    opening_bracket: char,
    closing_bracket: char,
) -> impl Fn(&str) -> IResult<&str, &str> {
    move |i: &str| {
        let mut index = 0;
        let mut bracket_counter = 0;
        while let Some(n) = &i[index..].find(&[opening_bracket, closing_bracket, '\\'][..]) {
            index += n;
            let mut it = i[index..].chars();
            match it.next().unwrap_or_default() {
                c if c == '\\' => {
                    // Skip the escape char `\`.
                    index += '\\'.len_utf8();
                    // Skip also the following char.
                    let c = it.next().unwrap_or_default();
                    index += c.len_utf8();
                }
                c if c == opening_bracket => {
                    bracket_counter += 1;
                    index += opening_bracket.len_utf8();
                }
                c if c == closing_bracket => {
                    // Closing bracket.
                    bracket_counter -= 1;
                    index += closing_bracket.len_utf8();
                }
                // Can not happen.
                _ => unreachable!(),
            };
            // We found the unmatched closing bracket.
            if bracket_counter == -1 {
                // We do not consume it.
                index -= closing_bracket.len_utf8();
                return Ok((&i[index..], &i[0..index]));
            };
        }

        if bracket_counter == 0 {
            Ok(("", i))
        } else {
            Err(Err::Error(Error::from_error_kind(i, ErrorKind::TakeUntil)))
        }
    }
}

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

    #[test]
    fn test_take_until_unmatched() {
        assert_eq!(take_until_unbalanced('(', ')')("abc"), Ok(("", "abc")));
        assert_eq!(
            take_until_unbalanced('(', ')')("url)abc"),
            Ok((")abc", "url"))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')("u()rl)abc"),
            Ok((")abc", "u()rl"))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')("u(())rl)abc"),
            Ok((")abc", "u(())rl"))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')("u(())r()l)abc"),
            Ok((")abc", "u(())r()l"))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')("u(())r()labc"),
            Ok(("", "u(())r()labc"))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')(r#"u\((\))r()labc"#),
            Ok(("", r#"u\((\))r()labc"#))
        );
        assert_eq!(
            take_until_unbalanced('(', ')')("u(())r(labc"),
            Err(nom::Err::Error(nom::error::Error::new(
                "u(())r(labc",
                ErrorKind::TakeUntil
            )))
        );
        assert_eq!(
            take_until_unbalanced('€', 'ü')("€uü€€üürlüabc"),
            Ok(("üabc", "€uü€€üürl"))
        );
    }
}