feat: allow link ignore with mlc-ignore

src/link_extractors/html_link_extractor.rs

@@ -11,23 +11,33 @@ enum ParserState {
     Anchor,
     EqualSign,
     Link,
+    Ignore,
 }
 
-impl LinkExtractor for HtmlLinkExtractor {
-    fn find_links(&self, text: &str) -> Vec<MarkupLink> {
+impl HtmlLinkExtractor {
+    pub fn find_links_with_ignore_info(&self, text: &str) -> (Vec<MarkupLink>, bool) {
         let mut result: Vec<MarkupLink> = Vec::new();
         let mut state: ParserState = ParserState::Text;
         let mut link_column = 0;
         let mut link_line = 0;
         for (line, line_str) in text.lines().enumerate() {
             let line_chars: Vec<char> = line_str.chars().collect();
             let mut column: usize = 0;
+            if matches!(state, ParserState::Ignore) {
+                info!("Ignore line {}", line);
+                state = ParserState::Text;
+                continue;
+            }
             while line_chars.get(column).is_some() {
                 match state {
+                    ParserState::Ignore => {}
                     ParserState::Comment => {
-                        if line_chars.get(column) == Some(&'-')
-                            && line_chars.get(column + 1) == Some(&'-')
-                            && line_chars.get(column + 2) == Some(&'>')
+                        if line_str.contains("mlc-ignore") {
+                            info!("Ignore next link from line {}", line);
+                            state = ParserState::Ignore;
+                            break;
+                        } else if line_chars.len() >= column + 3
+                            && line_chars[column..column + 3] == ['-', '-', '>']
                         {
                             column += 2;
                             state = ParserState::Text;
@@ -104,7 +114,13 @@ impl LinkExtractor for HtmlLinkExtractor {
                 column += 1;
             }
         }
-        result
+        return (result, matches!(state, ParserState::Ignore));
+    }
+}
+
+impl LinkExtractor for HtmlLinkExtractor {
+    fn find_links(&self, text: &str) -> Vec<MarkupLink> {
+        return self.find_links_with_ignore_info(text).0;
     }
 }
 
@@ -155,6 +171,15 @@ mod tests {
         assert_eq!(vec![expected], result);
     }
 
+    #[test]
+    fn ignore_next_line() {
+        let le = HtmlLinkExtractor();
+        let result =
+            le.find_links("blah <!-- mlc-ignore -->\n<a href=\"some%20file.html\">foo</a>.");
+        assert!(result.is_empty());
+    }
+
+    #[test_case("<!-- mlc-ignore -->\n<a href=\"https://foo.com\">Bar</a>\n<a href=\"https://www.w3schools.com\">Visit W3Schools.com!</a>", 3, 1)]
     #[test_case("<a href=\"https://www.w3schools.com\">Visit W3Schools.com!</a>", 1, 1)]
     #[test_case(
         "<a\nhref\n=\n  \"https://www.w3schools.com\">\nVisit W3Schools.com!\n</a>",
@@ -167,7 +192,7 @@ mod tests {
         1
     )]
     #[test_case(
-        "<!--comment--><a href=\"https://www.w3schools.com\">Visit W3Schools.com!</a>",
+        "<!--comment--><a href=\"https://www.w3schools.com\">Visit W3Schools.com!</a><!--inf comment",
         1,
         15
     )]

src/link_extractors/markdown_link_extractor.rs

@@ -43,9 +43,14 @@ impl LinkExtractor for MarkdownLinkExtractor {
         };
 
         let mut result: Vec<MarkupLink> = Vec::new();
+        let mut ignore_next: bool = false;
         for (evt, range) in parser.into_offset_iter() {
             match evt {
                 Event::End(tag) => {
+                    if ignore_next {
+                        ignore_next = false;
+                        continue;
+                    }
                     match tag {
                         Tag::Link(_link_type, destination, _title)
                         | Tag::Image(_link_type, destination, _title) => {
@@ -62,7 +67,12 @@ impl LinkExtractor for MarkdownLinkExtractor {
                 }
                 Event::Html(html) => {
                     let line_col = line_column_from_idx(range.start);
-                    let mut html_result = html_extractor.find_links(html.as_ref());
+                    let (mut html_result, ignore) =
+                        html_extractor.find_links_with_ignore_info(html.as_ref());
+                    if ignore {
+                        ignore_next = true;
+                        continue;
+                    }
                     html_result = html_result
                         .iter()
                         .map(|md_link| {
@@ -259,6 +269,18 @@ mod tests {
         assert_eq!(vec![expected], result);
     }
 
+    #[test]
+    fn link_ignored() {
+        let le = MarkdownLinkExtractor();
+        let link_str = "http://example.net/";
+        let input = format!(
+            "<!-- mlc-ignore -->\n[This link]({}) is ignore no title attribute.",
+            link_str
+        );
+        let result = le.find_links(&input);
+        assert!(result.is_empty());
+    }
+
     #[test]
     fn link_with_title() {
         let le = MarkdownLinkExtractor();