From 9eeea250cd6cf1e3e28f6a2b4c6f568c346f97ce Mon Sep 17 00:00:00 2001
From: Matthias <matthias-endler@gmx.net>
Date: Tue, 29 Nov 2022 00:38:43 +0100
Subject: [PATCH] Exclude <script> tags by default (#848)

This is a naive approach to exclude script tags from
getting checked. The reason is that the tag leads to
a lot of false-positives (e.g. `//unpkg.com/docsify-edit-on-github@1`
within a script block gets detected as an e-mail address).

A more thorough approach would be the use of a tree-builder in
html5gum and html5ever, but this could have a negative performance
impact.

I also did not want to add a new flag (e.g. `--include-scripts`) for this
setting because the current set of flags around exclusion/inclusion is
already quite long.

Fixes #821.
---
 lychee-lib/src/collector.rs         |  1 -
 lychee-lib/src/extract/html5ever.rs | 17 +++++++++++++++++
 lychee-lib/src/extract/html5gum.rs  | 17 +++++++++++++++++
 lychee-lib/src/extract/mod.rs       |  5 ++++-
 4 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/lychee-lib/src/collector.rs b/lychee-lib/src/collector.rs
index 8daa0d3..d9ff9ae 100644
--- a/lychee-lib/src/collector.rs
+++ b/lychee-lib/src/collector.rs
@@ -319,7 +319,6 @@ mod tests {
             website("https://example.com/css/style_relative_url.css"),
             website("https://example.com/head/home"),
             website("https://example.com/images/icon.png"),
-            website("https://example.com/js/script.js"),
         ]);
 
         assert_eq!(links, expected_links);
diff --git a/lychee-lib/src/extract/html5ever.rs b/lychee-lib/src/extract/html5ever.rs
index 7674618..c7d2a23 100644
--- a/lychee-lib/src/extract/html5ever.rs
+++ b/lychee-lib/src/extract/html5ever.rs
@@ -228,4 +228,21 @@ mod tests {
         let uris = extract_html(input, false);
         assert_eq!(uris, expected);
     }
+
+    #[test]
+    fn test_exclude_script_tags() {
+        let input = r#"
+        <script>
+        var foo = "https://example.com";
+        </script>
+        <a href="https://example.org">i'm fine</a> 
+        "#;
+        let expected = vec![RawUri {
+            text: "https://example.org".to_string(),
+            element: Some("a".to_string()),
+            attribute: Some("href".to_string()),
+        }];
+        let uris = extract_html(input, false);
+        assert_eq!(uris, expected);
+    }
 }
diff --git a/lychee-lib/src/extract/html5gum.rs b/lychee-lib/src/extract/html5gum.rs
index e641375..624f289 100644
--- a/lychee-lib/src/extract/html5gum.rs
+++ b/lychee-lib/src/extract/html5gum.rs
@@ -316,4 +316,21 @@ mod tests {
         let uris = extract_html(input, false);
         assert_eq!(uris, expected);
     }
+
+    #[test]
+    fn test_exclude_script_tags() {
+        let input = r#"
+        <script>
+        var foo = "https://example.com";
+        </script>
+        <a href="https://example.org">i'm fine</a> 
+        "#;
+        let expected = vec![RawUri {
+            text: "https://example.org".to_string(),
+            element: Some("a".to_string()),
+            attribute: Some("href".to_string()),
+        }];
+        let uris = extract_html(input, false);
+        assert_eq!(uris, expected);
+    }
 }
diff --git a/lychee-lib/src/extract/mod.rs b/lychee-lib/src/extract/mod.rs
index 1c41666..20f9fe6 100644
--- a/lychee-lib/src/extract/mod.rs
+++ b/lychee-lib/src/extract/mod.rs
@@ -11,10 +11,13 @@ use plaintext::extract_plaintext;
 /// Check if the given element is in the list of preformatted ("verbatim") tags.
 ///
 /// These will be excluded from link checking by default.
+// Including the <script> tag is debatable, but the alternative is to
+// have a separate list of tags which need a separate config setting and that
+// seems worse.
 pub(crate) fn is_verbatim_elem(name: &str) -> bool {
     matches!(
         name,
-        "pre" | "code" | "textarea" | "samp" | "xmp" | "plaintext" | "listing"
+        "code" | "listing" | "plaintext" | "samp" | "script" | "textarea" | "xmp" | "pre"
     )
 }