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

//! This module implements parsers to extract hyperlinks and image elements
//! from HTML text input. The parsers in this module search for HTML only,
//! no other markup languages are recognized.
#![allow(dead_code)]

use crate::parser::image::html_img_link;
use nom::bytes::complete::take_till;
use nom::character::complete::anychar;
use parse_hyperlinks::parser::html::html_text2dest_link;
use parse_hyperlinks::parser::Link;

/// Consumes the input until the parser finds an HTML formatted _inline image_ (`Link::Image`).
///
/// The parser consumes the finding and returns
/// `Ok((remaining_input, (skipped_input, Link)))` or some error.
///
///
/// # HTML
///
/// ```
/// use parse_hyperlinks::parser::Link;
/// use parse_hyperlinks_html::parser::parse::take_img_link;
/// use std::borrow::Cow;
///
/// let i = r#"abc<img src="destination1" alt="text1">abc
/// abc<img src="destination2" alt="text2">abc
/// "#;
///
/// let (i, r) = take_img_link(i).unwrap();
/// assert_eq!(r.0, "abc");
/// assert_eq!(r.1, Link::Image(Cow::from("text1"), Cow::from("destination1")));
/// let (i, r) = take_img_link(i).unwrap();
/// assert_eq!(r.0, "abc\nabc");
/// assert_eq!(r.1, Link::Image(Cow::from("text2"), Cow::from("destination2")));
/// ```
pub fn take_img_link(i: &str) -> nom::IResult<&str, (&str, Link)> {
    let mut j = i;
    let mut skip_count = 0;

    let res = loop {
        // Start searching for inline images.

        // Regular `Link::Image` can start everywhere.
        if let Ok((k, r)) = html_img_link(j) {
            break (k, r);
        };

        // This makes sure that we advance.
        let (k, _) = anychar(j)?;
        skip_count += j.len() - k.len();
        j = k;

        // This might not consume bytes and never fails.
        let (k, _) = take_till(|c| c == '<')(j)?;

        skip_count += j.len() - k.len();
        j = k;
    };

    // We found a link. Return it.
    let (l, link) = res;

    let skipped_input = &i[0..skip_count];

    Ok((l, (skipped_input, link)))
}

/// Consumes the input until the parser finds an HTML formatted hyperlink _text2dest_
/// (`Link::Text2Dest`).
///
/// The parser consumes the finding and returns
/// `Ok((remaining_input, (skipped_input, Link)))` or some error.
///
///
/// # HTML
///
/// ```
/// use parse_hyperlinks::parser::Link;
/// use parse_hyperlinks_html::parser::parse::take_link;
/// use std::borrow::Cow;
///
/// let i = "abc<a href=\"dest1\" title=\"title1\">text1</a>abc\
///          abc<a href=\"dest2\" title=\"title2\">text2</a>abc";
///
/// let (i, r) = take_link(i).unwrap();
/// assert_eq!(r.0, "abc");
/// assert_eq!(r.1, Link::Text2Dest(Cow::from("text1"), Cow::from("dest1"), Cow::from("title1")));
/// let (i, r) = take_link(i).unwrap();
/// assert_eq!(r.0, "abcabc");
/// assert_eq!(r.1, Link::Text2Dest(Cow::from("text2"), Cow::from("dest2"), Cow::from("title2")));
/// ```
pub fn take_link(i: &str) -> nom::IResult<&str, (&str, Link)> {
    let mut j = i;
    let mut skip_count = 0;

    let res = loop {
        // Start searching for inline hyperlinks.

        // Regular `Link::Text2Dest` can start everywhere.

        if let Ok((k, r)) = html_text2dest_link(j) {
            break (k, r);
        };

        // This makes sure that we advance.
        let (k, _) = anychar(j)?;
        skip_count += j.len() - k.len();
        j = k;

        // This might not consume bytes and never fails.
        let (k, _) = take_till(|c| c == '<')(j)?;

        skip_count += j.len() - k.len();
        j = k;
    };

    // We found a link. Return it.
    let (l, link) = res;

    let skipped_input = &i[0..skip_count];

    Ok((l, (skipped_input, link)))
}