Auto merge of rust-lang#127127 - notriddle:notriddle/pulldown-cmark-0…

….11, r=GuillaumeGomez

rustdoc: update to pulldown-cmark 0.11

r? rustdoc

This pull request updates rustdoc to the latest version of pulldown-cmark. Along with adding new markdown extensions (which this PR doesn't enable), the new pulldown-cmark version also fixes a large number of bugs. Because all text files successfully parse as markdown, these bugfixes change the output, which can break people's existing docs.

A crater run, rust-lang#121659, has already been run for this change.

The first commit upgrades and fixes rustdoc. The second commit adds a lint for the footnote and block quote parser changes, which break the largest numbers of docs in the Crater run. The strikethrough change was mitigated in pulldown-cmark itself.

Unblocks rust-lang/rust-clippy#12876

Cargo.lock

@@ -3141,7 +3141,19 @@ dependencies = [
  "bitflags 2.5.0",
  "getopts",
  "memchr",
- "pulldown-cmark-escape",
+ "pulldown-cmark-escape 0.10.1",
+ "unicase",
+]
+
+[[package]]
+name = "pulldown-cmark"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8746739f11d39ce5ad5c2520a9b75285310dbfe78c541ccf832d38615765aec0"
+dependencies = [
+ "bitflags 2.5.0",
+ "memchr",
+ "pulldown-cmark-escape 0.11.0",
  "unicase",
 ]
 
@@ -3151,6 +3163,12 @@ version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bd348ff538bc9caeda7ee8cad2d1d48236a1f443c1fa3913c6a02fe0043b1dd3"
 
+[[package]]
+name = "pulldown-cmark-escape"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
+
 [[package]]
 name = "pulldown-cmark-to-cmark"
 version = "13.0.0"
@@ -4604,7 +4622,7 @@ name = "rustc_resolve"
 version = "0.0.0"
 dependencies = [
  "bitflags 2.5.0",
- "pulldown-cmark 0.9.6",
+ "pulldown-cmark 0.11.0",
  "rustc_arena",
  "rustc_ast",
  "rustc_ast_pretty",
@@ -4883,6 +4901,7 @@ dependencies = [
  "indexmap",
  "itertools",
  "minifier",
+ "pulldown-cmark 0.9.6",
  "regex",
  "rustdoc-json-types",
  "serde",

compiler/rustc_data_structures/src/sync.rs

@@ -35,11 +35,11 @@
 //! |                         |                     |                                 |
 //! | `ParallelIterator`      | `Iterator`          | `rayon::iter::ParallelIterator` |
 //!
-//! [^1] `MTLock` is similar to `Lock`, but the serial version avoids the cost
+//! [^1]: `MTLock` is similar to `Lock`, but the serial version avoids the cost
 //! of a `RefCell`. This is appropriate when interior mutability is not
 //! required.
 //!
-//! [^2] `MTRef`, `MTLockRef` are type aliases.
+//! [^2]: `MTRef`, `MTLockRef` are type aliases.
 
 pub use crate::marker::*;
 use std::collections::HashMap;

compiler/rustc_resolve/Cargo.toml

@@ -6,7 +6,7 @@ edition = "2021"
 [dependencies]
 # tidy-alphabetical-start
 bitflags = "2.4.1"
-pulldown-cmark = { version = "0.9.6", default-features = false }
+pulldown-cmark = { version = "0.11", features = ["html"], default-features = false }
 rustc_arena = { path = "../rustc_arena" }
 rustc_ast = { path = "../rustc_ast" }
 rustc_ast_pretty = { path = "../rustc_ast_pretty" }

compiler/rustc_resolve/src/rustdoc.rs

@@ -1,4 +1,6 @@
-use pulldown_cmark::{BrokenLink, CowStr, Event, LinkType, Options, Parser, Tag};
+use pulldown_cmark::{
+    BrokenLink, BrokenLinkCallback, CowStr, Event, LinkType, Options, Parser, Tag,
+};
 use rustc_ast as ast;
 use rustc_ast::util::comments::beautify_doc_string;
 use rustc_data_structures::fx::FxHashMap;
@@ -427,7 +429,9 @@ fn parse_links<'md>(doc: &'md str) -> Vec<Box<str>> {
 
     while let Some(event) = event_iter.next() {
         match event {
-            Event::Start(Tag::Link(link_type, dest, _)) if may_be_doc_link(link_type) => {
+            Event::Start(Tag::Link { link_type, dest_url, title: _, id: _ })
+                if may_be_doc_link(link_type) =>
+            {
                 if matches!(
                     link_type,
                     LinkType::Inline
@@ -441,7 +445,7 @@ fn parse_links<'md>(doc: &'md str) -> Vec<Box<str>> {
                     }
                 }
 
-                links.push(preprocess_link(&dest));
+                links.push(preprocess_link(&dest_url));
             }
             _ => {}
         }
@@ -451,8 +455,8 @@ fn parse_links<'md>(doc: &'md str) -> Vec<Box<str>> {
 }
 
 /// Collects additional data of link.
-fn collect_link_data<'input, 'callback>(
-    event_iter: &mut Parser<'input, 'callback>,
+fn collect_link_data<'input, F: BrokenLinkCallback<'input>>(
+    event_iter: &mut Parser<'input, F>,
 ) -> Option<Box<str>> {
     let mut display_text: Option<String> = None;
     let mut append_text = |text: CowStr<'_>| {

src/librustdoc/Cargo.toml

@@ -13,6 +13,7 @@ base64 = "0.21.7"
 itertools = "0.12"
 indexmap = "2"
 minifier = "0.3.0"
+pulldown-cmark-old = { version = "0.9.6", package = "pulldown-cmark", default-features = false }
 regex = "1"
 rustdoc-json-types = { path = "../rustdoc-json-types" }
 serde_json = "1.0"