~vpzom/pdcm-linkify

f43392fe279c8a48e7ec933bb5b593677d4beb4f — Colin Reeder 2 years ago
Initial commit
3 files changed, 112 insertions(+), 0 deletions(-)

A .gitignore
A Cargo.toml
A src/lib.rs
A  => .gitignore +2 -0
@@ 1,2 @@
/target
Cargo.lock

A  => Cargo.toml +11 -0
@@ 1,11 @@
[package]
name = "pdcm-linkify"
version = "0.1.0"
authors = ["Marcus Klaas <mail@marcusklaas.nl>", "Colin Reeder <vpzomtrrfrt@gmail.com>"]
edition = "2015"

# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

[dependencies]
pulldown-cmark = "0.8.0"
regex = "1.4.2"

A  => src/lib.rs +99 -0
@@ 1,99 @@
extern crate pulldown_cmark;
extern crate regex;

use pulldown_cmark::{CowStr, Event, LinkType, Tag};
use regex::Regex;

static URL_REGEX: &str = r#"((https?|ftp)://|www.)[^\s/$.?#].[^\s]*[^.^\s]"#;

enum LinkState {
    Open,
    Label,
    Close,
}

enum AutoLinkerState<'a> {
    Clear,
    Link(LinkState, CowStr<'a>, CowStr<'a>),
    TrailingText(CowStr<'a>),
}

pub struct AutoLinker<'a, I> {
    iter: I,
    state: AutoLinkerState<'a>,
    regex: Regex,
}

impl<'a, I> AutoLinker<'a, I> {
    pub fn new(iter: I) -> Self {
        Self {
            iter,
            state: AutoLinkerState::Clear,
            regex: Regex::new(URL_REGEX).unwrap(),
        }
    }
}

impl<'a, I> Iterator for AutoLinker<'a, I>
where
    I: Iterator<Item = Event<'a>>,
{
    type Item = Event<'a>;

    fn next(&mut self) -> Option<Self::Item> {
        let text = match std::mem::replace(&mut self.state, AutoLinkerState::Clear) {
            AutoLinkerState::Clear => match self.iter.next() {
                Some(Event::Text(text)) => text,
                x => return x,
            },
            AutoLinkerState::TrailingText(text) => text,
            AutoLinkerState::Link(link_state, link_text, trailing_text) => match link_state {
                LinkState::Open => {
                    self.state = AutoLinkerState::Link(
                        LinkState::Label,
                        link_text.clone(),
                        trailing_text.clone(),
                    );
                    return Some(Event::Start(Tag::Link(
                        LinkType::Inline,
                        link_text,
                        "".into(),
                    )));
                }
                LinkState::Label => {
                    self.state = AutoLinkerState::Link(
                        LinkState::Close,
                        link_text.clone(),
                        trailing_text.clone(),
                    );
                    return Some(Event::Text(link_text));
                }
                LinkState::Close => {
                    self.state = AutoLinkerState::TrailingText(trailing_text);
                    return Some(Event::End(Tag::Link(
                        LinkType::Inline,
                        link_text,
                        "".into(),
                    )));
                }
            },
        };

        match self.regex.find(&text) {
            Some(reg_match) => {
                let link_text = reg_match.as_str();
                let leading_text = &text.as_ref()[..reg_match.start()];
                let trailing_text = &text.as_ref()[reg_match.end()..];

                self.state = AutoLinkerState::Link(
                    LinkState::Open,
                    link_text.to_owned().into(),
                    trailing_text.to_owned().into(),
                );

                Some(Event::Text(leading_text.to_owned().into()))
            }
            None => Some(Event::Text(text)),
        }
    }
}