Don't override explicit link definitions.

If the author has an explicit link definition, don't allow std_links
to override it.

Author: ehuss

mdbook-spec/src/std_links.rs

@@ -1,6 +1,7 @@
 use mdbook::book::Chapter;
 use once_cell::sync::Lazy;
 use regex::{Captures, Regex};
+use std::collections::HashSet;
 use std::fmt::Write as _;
 use std::fs;
 use std::io::{self, Write as _};
@@ -32,6 +33,15 @@ static STD_LINK_RE: Lazy<Regex> = Lazy::new(|| {
 static STD_LINK_EXTRACT_RE: Lazy<Regex> =
     Lazy::new(|| Regex::new(r#"<li><a [^>]*href="(https://doc.rust-lang.org/[^"]+)""#).unwrap());
 
+/// The Regex for a markdown link definition.
+static LINK_DEF_RE: Lazy<Regex> = Lazy::new(|| {
+    // This is a pretty lousy regex for a link definition. It doesn't
+    // handle things like blockquotes, code blocks, etc. Using a
+    // markdown parser isn't really feasible here, it would be nice to
+    // improve this.
+    Regex::new(r#"(?m)^(?<label>\[[^]]+\]): *(?<dest>.*)"#).unwrap()
+});
+
 /// Converts links to the standard library to the online documentation in a
 /// fashion similar to rustdoc intra-doc links.
 pub fn std_links(chapter: &Chapter) -> String {
@@ -87,7 +97,7 @@ pub fn std_links(chapter: &Chapter) -> String {
     output
 }
 
-/// Collects all markdown links.
+/// Collects all markdown links, excluding those that already have link definitions.
 ///
 /// Returns a `Vec` of `(link, Option<dest>)` where markdown text like
 /// ``[`std::fmt`]`` would return that as a link. The dest is optional, for
@@ -112,6 +122,21 @@ fn collect_markdown_links(chapter: &Chapter) -> Vec<(&str, Option<&str>)> {
     }
     links.sort();
     links.dedup();
+    // Remove any links that already have a link definition. We don't want
+    // to override what the author explicitly specified.
+    let existing_labels: HashSet<_> = LINK_DEF_RE
+        .captures_iter(&chapter.content)
+        .map(|cap| cap.get(1).unwrap().as_str())
+        .collect();
+    links.retain(|(link, dest)| {
+        let mut tmp = None;
+        let label: &str = dest.map_or(link, |d| {
+            tmp = Some(format!("[`{d}`]"));
+            tmp.as_deref().unwrap()
+        });
+        !existing_labels.contains(label)
+    });
+
     links
 }