+ To start + + let's run away. + +
+Word
+ back we go + doesn't exist +This is a paragraph with some inline https://example.com and a normal example
This is a paragraph with some inline https://example.com and a normal example
Some random text
https://foo.com and http://bar.com/some/path
Something else
example link inside pre
- bold
+bold
"#; + #[test] + fn test_extract_fragments() { + let expected = HashSet::from([ + "content".to_string(), + "inline-code".to_string(), + "emphasis".to_string(), + ]); + let actual = extract_html_fragments(HTML_INPUT); + assert_eq!(actual, expected); + } + #[test] fn test_skip_verbatim() { let expected = vec![RawUri { diff --git a/lychee-lib/src/extract/html/mod.rs b/lychee-lib/src/extract/html/mod.rs index ceafb66f48..ef02c06fc4 100644 --- a/lychee-lib/src/extract/html/mod.rs +++ b/lychee-lib/src/extract/html/mod.rs @@ -1,3 +1,4 @@ +//! Extract links and fragments from html documents pub(crate) mod html5ever; pub(crate) mod html5gum; mod srcset; diff --git a/lychee-lib/src/extract/markdown.rs b/lychee-lib/src/extract/markdown.rs index 06e53d4654..4cb1fc3338 100644 --- a/lychee-lib/src/extract/markdown.rs +++ b/lychee-lib/src/extract/markdown.rs @@ -1,11 +1,11 @@ -//! Extract things from markdown documents +//! Extract links and fragments from markdown documents use std::collections::{HashMap, HashSet}; use pulldown_cmark::{Event, Options, Parser, Tag}; use crate::{extract::plaintext::extract_plaintext, types::uri::raw::RawUri}; -use super::html::html5gum::extract_html; +use super::html::html5gum::{extract_html, extract_html_fragments}; /// Extract unparsed URL strings from a Markdown string. pub(crate) fn extract_markdown(input: &str, include_verbatim: bool) -> Vec