chore(lib): add style and script ignore

.github/workflows/rust.yml

@@ -0,0 +1,29 @@
+name: Rust
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/cache@v3
+        id: cache
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
+      - name: Build
+        run: cargo build --verbose --release
+      - name: Run tests
+        run: cargo test

.github/workflows/stale.yml

@@ -0,0 +1,21 @@
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+    - cron: "30 1 * * *"
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@v3
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          stale-issue-message: "This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days."
+          stale-pr-message: "This PR is stale because it has been open 45 days with no activity. Remove stale label or comment or this will be closed in 10 days."
+          close-issue-message: "This issue was closed because it has been stalled for 5 days with no activity."
+          close-pr-message: "This PR was closed because it has been stalled for 10 days with no activity."
+          days-before-issue-stale: 30
+          days-before-pr-stale: 45
+          days-before-issue-close: 5
+          days-before-pr-close: 10

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "fast_html2md"
-version = "0.0.11"
+version = "0.0.12"
 edition = "2021"
 description = "A fast html2md crate for rust"
 categories = ["development-tools", "parsing", "parser-implementations"]

src/anchors.rs

@@ -12,8 +12,6 @@ pub struct AnchorHandler {
 impl TagHandler for AnchorHandler {
     fn handle(&mut self, tag: &Handle, printer: &mut StructuredPrinter) {
         self.start_pos = printer.data.len();
-
-        // try to extract a hyperlink
         self.url = match tag.data {
             NodeData::Element { ref attrs, .. } => {
                 let attrs = attrs.borrow();
@@ -22,7 +20,7 @@ impl TagHandler for AnchorHandler {
                     .find(|attr| attr.name.local.as_bytes() == b"href");
 
                 match href {
-                    Some(link) => link.value.trim().into(),
+                    Some(link) => link.value.trim_ascii().into(),
                     None => String::new(),
                 }
             }
@@ -31,8 +29,35 @@ impl TagHandler for AnchorHandler {
     }
 
     fn after_handle(&mut self, printer: &mut StructuredPrinter) {
-        // add braces around already present text, put an url afterwards
-        printer.insert_str(self.start_pos, "[");
-        printer.append_str(&format!("]({})", self.url))
+        match printer.data.get(self.start_pos..) {
+            Some(d) => {
+                let starts_new_line = d.starts_with("\n");
+                let ends_new_line = d.ends_with("\n");
+
+                if starts_new_line || ends_new_line {
+                    // handle start
+                    if starts_new_line {
+                        printer.insert_str(self.start_pos + 1, "[");
+                    } else {
+                        printer.insert_str(self.start_pos, "[");
+                    }
+
+                    // handle end
+                    if ends_new_line {
+                        let next_position = printer.data.len();
+                        printer.insert_str(next_position - 1, &format!("]({})", self.url));
+                    } else {
+                        printer.append_str(&format!("]({})", self.url));
+                    }
+                } else {
+                    printer.insert_str(self.start_pos, "[");
+                    printer.append_str(&format!("]({})", self.url));
+                }
+            }
+            _ => {
+                printer.insert_str(self.start_pos, "[");
+                printer.append_str(&format!("]({})", self.url));
+            }
+        }
     }
 }

src/lib.rs

@@ -77,6 +77,7 @@ pub fn parse_html_custom(
         Ok(dom) => {
             let mut result = StructuredPrinter::default();
             walk(&dom.document, &mut result, custom, commonmark);
+            // we want to eventually remove the clean step.
             clean_markdown(&result.data)
         }
         _ => Default::default(),
@@ -128,30 +129,31 @@ fn walk(
         NodeData::Document | NodeData::Doctype { .. } | NodeData::ProcessingInstruction { .. } => {}
         NodeData::Text { ref contents } => {
             let mut text = contents.borrow().to_string();
-            let inside_pre = result.parent_chain.iter().any(|tag| tag == "pre");
+
+            let inside_pre = result.parent_chain.iter().any(|t| t == "pre");
             if inside_pre {
                 // this is preformatted text, insert as-is
                 result.append_str(&text);
+
             } else if !(text.trim().len() == 0
                 && (result.data.chars().last() == Some('\n')
                     || result.data.chars().last() == Some(' ')))
             {
                 // in case it's not just a whitespace after the newline or another whitespace
 
                 // regular text, collapse whitespace and newlines in text
-                let inside_code = result.parent_chain.iter().any(|tag| tag == "code");
+                let inside_code = result.parent_chain.iter().any(|t| t == "code");
                 if !inside_code {
                     text = escape_markdown(result, &text);
                 }
                 let minified_text = EXCESSIVE_WHITESPACE_PATTERN.replace_all(&text, " ");
-                let minified_text = minified_text.trim_matches(|ch: char| ch == '\n' || ch == '\r');
-                result.append_str(&minified_text);
+                result.append_str(&minified_text.trim_ascii());
             }
         }
         NodeData::Comment { .. } => {} // ignore comments
         NodeData::Element { ref name, .. } => {
-            tag_name = name.local.to_string();
             let inside_pre = result.parent_chain.iter().any(|tag| tag == "pre");
+            tag_name = name.local.to_string();
 
             if inside_pre {
                 // don't add any html tags inside the pre section
@@ -200,22 +202,24 @@ fn walk(
         }
     }
 
+    let ignore_tags = tag_name == "style" || tag_name == "script";
+
     // handle this tag, while it's not in parent chain
     // and doesn't have child siblings
     handler.handle(&input, result);
 
     // save this tag name as parent for child nodes
-    result.parent_chain.push(tag_name.to_string()); // e.g. it was ["body"] and now it's ["body", "p"]
+    result.parent_chain.push(tag_name.clone()); // e.g. it was ["body"] and now it's ["body", "p"]
     let current_depth = result.parent_chain.len(); // e.g. it was 1 and now it's 2
 
     // create space for siblings of next level
     result.siblings.insert(current_depth, vec![]);
 
     for child in input.children.borrow().iter() {
-        if handler.skip_descendants() {
+        if handler.skip_descendants() || ignore_tags {
             continue;
         }
-
+  
         walk(&child, result, custom, commonmark);
 
         match child.data {