Rollup merge of #105848 - lukas-code:backticks, r=GuillaumeGomez,jyn514,notriddle

rustdoc: Add a new lint for broken inline code

This patch adds `rustdoc::unescaped_backticks`, a new rustdoc lint that will detect broken inline code nodes.

The lint woks by finding stray backticks and with some heuristics tries to guess where the second backtick might be missing.

Here is how it looks:
```rust
#![warn(rustdoc::unescaped_backticks)]

/// `add(a, b) is the same as `add(b, a)`.
pub fn add(a: i32, b: i32) -> i32 { a + b }
```
```text
warning: unescaped backtick
 --> src/lib.rs:3:41
  |
3 | /// `add(a, b) is the same as `add(b, a)`.
  |                                         ^
  |
help: a previous inline code might be longer than expected
  |
3 | /// `add(a, b)` is the same as `add(b, a)`.
  |               +
help: if you meant to use a literal backtick, escape it
  |
3 | /// `add(a, b) is the same as `add(b, a)\`.
  |                                         +
```

If we can't get proper spans, for example if the doc comment comes from a macro expansion, we print the suggestion in help messages instead. Here's a [real-world example](https://docs.rs/tracing-subscriber/0.3.17/tracing_subscriber/layer/trait.Filter.html#method.max_level_hint):

```text
warning: unescaped backtick
    --> /tracing-subscriber-0.3.17/src/layer/mod.rs:1400:9
     |
1400 | /         /// Returns an optional hint of the highest [verbosity level][level] that
1401 | |         /// this `Filter` will enable.
1402 | |         ///
1403 | |         /// If this method returns a [`LevelFilter`], it will be used as a hint to
...    |
1427 | |         /// [`Interest`]: tracing_core::subscriber::Interest
1428 | |         /// [rebuild]: tracing_core::callsite::rebuild_interest_cache
     | |_____________________________________________________________________^
     |
     = help: a previous inline code might be longer than expected
              change: Therefore, if the `Filter will change the value returned by this
             to this: Therefore, if the `Filter` will change the value returned by this
     = help: if you meant to use a literal backtick, escape it
              change: [`rebuild_interest_cache`][rebuild] is called after the value of the max
             to this: [`rebuild_interest_cache\`][rebuild] is called after the value of the max
```

You can find more examples [here](https://gist.github.com/lukas-code/7678ddf5c608aee97b3a669de80d3465).

A limitation of the current implementation is, that it cannot suggest removing misplaced backticks, for example [here](https://docs.rs/tikv-jemalloc-sys/0.5.3+5.3.0-patched/tikv_jemalloc_sys/fn.mallctl.html).

The lint is allowed by default ~~and nightly-only~~ for now, ~~but without a feature gate. This is similar to how `rustdoc::invalid_html_tags` and `rustdoc::bare_urls` were handled.~~

Author: matthiaskrgr

src/doc/rustdoc/src/lints.md

@@ -374,3 +374,41 @@ warning: this URL is not a hyperlink
 
 warning: 2 warnings emitted
 ```
+
+## `unescaped_backticks`
+
+This lint is **allowed by default**. It detects backticks (\`) that are not escaped.
+This usually means broken inline code. For example:
+
+```rust
+#![warn(rustdoc::unescaped_backticks)]
+
+/// `add(a, b) is the same as `add(b, a)`.
+pub fn add(a: i32, b: i32) -> i32 { a + b }
+```
+
+Which will give:
+
+```text
+warning: unescaped backtick
+ --> src/lib.rs:3:41
+  |
+3 | /// `add(a, b) is the same as `add(b, a)`.
+  |                                         ^
+  |
+note: the lint level is defined here
+ --> src/lib.rs:1:9
+  |
+1 | #![warn(rustdoc::unescaped_backticks)]
+  |         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+help: a previous inline code might be longer than expected
+  |
+3 | /// `add(a, b)` is the same as `add(b, a)`.
+  |               +
+help: if you meant to use a literal backtick, escape it
+  |
+3 | /// `add(a, b) is the same as `add(b, a)\`.
+  |                                         +
+
+warning: 1 warning emitted
+```

src/librustdoc/lib.rs

@@ -7,14 +7,15 @@
 #![feature(assert_matches)]
 #![feature(box_patterns)]
 #![feature(drain_filter)]
+#![feature(impl_trait_in_assoc_type)]
+#![feature(iter_intersperse)]
+#![feature(lazy_cell)]
 #![feature(let_chains)]
-#![feature(test)]
 #![feature(never_type)]
-#![feature(lazy_cell)]
-#![feature(type_ascription)]
-#![feature(iter_intersperse)]
+#![feature(round_char_boundary)]
+#![feature(test)]
 #![feature(type_alias_impl_trait)]
-#![feature(impl_trait_in_assoc_type)]
+#![feature(type_ascription)]
 #![recursion_limit = "256"]
 #![warn(rustc::internal)]
 #![allow(clippy::collapsible_if, clippy::collapsible_else_if)]

src/librustdoc/lint.rs

@@ -174,6 +174,17 @@ declare_rustdoc_lint! {
    "codeblock could not be parsed as valid Rust or is empty"
 }
 
+declare_rustdoc_lint! {
+   /// The `unescaped_backticks` lint detects unescaped backticks (\`), which usually
+   /// mean broken inline code. This is a `rustdoc` only lint, see the documentation
+   /// in the [rustdoc book].
+   ///
+   /// [rustdoc book]: ../../../rustdoc/lints.html#unescaped_backticks
+   UNESCAPED_BACKTICKS,
+   Allow,
+   "detects unescaped backticks in doc comments"
+}
+
 pub(crate) static RUSTDOC_LINTS: Lazy<Vec<&'static Lint>> = Lazy::new(|| {
     vec![
         BROKEN_INTRA_DOC_LINKS,
@@ -185,6 +196,7 @@ pub(crate) static RUSTDOC_LINTS: Lazy<Vec<&'static Lint>> = Lazy::new(|| {
         INVALID_HTML_TAGS,
         BARE_URLS,
         MISSING_CRATE_LEVEL_DOCS,
+        UNESCAPED_BACKTICKS,
     ]
 });
 

src/librustdoc/passes/lint.rs

@@ -4,6 +4,7 @@
 mod bare_urls;
 mod check_code_block_syntax;
 mod html_tags;
+mod unescaped_backticks;
 
 use super::Pass;
 use crate::clean::*;
@@ -27,6 +28,7 @@ impl<'a, 'tcx> DocVisitor for Linter<'a, 'tcx> {
         bare_urls::visit_item(self.cx, item);
         check_code_block_syntax::visit_item(self.cx, item);
         html_tags::visit_item(self.cx, item);
+        unescaped_backticks::visit_item(self.cx, item);
 
         self.visit_item_recur(item)
     }