Merge pull request #21143 from rust-lang/rustc-pull

minor: sync from downstream

Author: lnicola

.github/workflows/ci.yml

@@ -22,7 +22,7 @@ jobs:
       BASE_SHA: ${{ github.event.pull_request.base.sha }}
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           # linkcheck needs the base commit.
           fetch-depth: 0
@@ -83,8 +83,18 @@ jobs:
           git commit -m "Deploy ${GITHUB_SHA} to gh-pages"
           git push --quiet -f "https://x-token:${{ secrets.GITHUB_TOKEN }}@github.com/${GITHUB_REPOSITORY}" HEAD:gh-pages
 
+      - name: Cache sembr build
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            ci/sembr/target/
+          key: sembr-${{ hashFiles('ci/sembr/Cargo.lock') }}
+
       - name: Check if files comply with semantic line breaks
         continue-on-error: true
         run: |
           # using split_inclusive that uses regex feature that uses an unstable feature
-          RUSTC_BOOTSTRAP=1 cargo run --manifest-path ci/sembr/Cargo.toml src
+          RUSTC_BOOTSTRAP=1 cargo run --release --manifest-path ci/sembr/Cargo.toml src

.github/workflows/date-check.yml

@@ -15,7 +15,7 @@ jobs:
 
     steps:
       - name: Checkout repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Ensure Rust is up-to-date
         run: |

ci/sembr/Cargo.lock

@@ -22,13 +22,15 @@ struct Cli {
     show_diff: bool,
 }
 
-static REGEX_IGNORE: LazyLock<Regex> =
-    LazyLock::new(|| Regex::new(r"^\s*(\d\.|\-|\*)\s+").unwrap());
-static REGEX_IGNORE_END: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"(\.|\?|;|!)$").unwrap());
+static REGEX_IGNORE_END: LazyLock<Regex> =
+    LazyLock::new(|| Regex::new(r"(\.|\?|;|!|,|\-)$").unwrap());
 static REGEX_IGNORE_LINK_TARGETS: LazyLock<Regex> =
     LazyLock::new(|| Regex::new(r"^\[.+\]: ").unwrap());
 static REGEX_SPLIT: LazyLock<Regex> =
-    LazyLock::new(|| Regex::new(r"([^\.]\.|[^r]\?|;|!)\s+").unwrap());
+    LazyLock::new(|| Regex::new(r"([^\.\d\-\*]\.|[^r]\?|;|!)\s").unwrap());
+// list elements, numbered (1.) or not  (- and *)
+static REGEX_LIST_ENTRY: LazyLock<Regex> =
+    LazyLock::new(|| Regex::new(r"^\s*(\d\.|\-|\*)\s+").unwrap());
 
 fn main() -> Result<()> {
     let cli = Cli::parse();
@@ -99,7 +101,6 @@ fn ignore(line: &str, in_code_block: bool) -> bool {
         || line.trim_start().starts_with('>')
         || line.starts_with('#')
         || line.trim().is_empty()
-        || REGEX_IGNORE.is_match(line)
         || REGEX_IGNORE_LINK_TARGETS.is_match(line)
 }
 
@@ -120,11 +121,19 @@ fn comply(content: &str) -> String {
             continue;
         }
         if REGEX_SPLIT.is_match(&line) {
-            let indent = line.find(|ch: char| !ch.is_whitespace()).unwrap();
-            let new_lines: Vec<_> = line
-                .split_inclusive(&*REGEX_SPLIT)
-                .map(|portion| format!("{:indent$}{}", "", portion.trim()))
+            let indent = if let Some(regex_match) = REGEX_LIST_ENTRY.find(&line) {
+                regex_match.len()
+            } else {
+                line.find(|ch: char| !ch.is_whitespace()).unwrap()
+            };
+            let mut newly_split_lines = line.split_inclusive(&*REGEX_SPLIT);
+            let first = newly_split_lines.next().unwrap().trim_end().to_owned();
+            let mut remaining: Vec<_> = newly_split_lines
+                .map(|portion| format!("{:indent$}{}", "", portion.trim_end()))
                 .collect();
+            let mut new_lines = Vec::new();
+            new_lines.push(first);
+            new_lines.append(&mut remaining);
             new_content.splice(new_n..=new_n, new_lines.clone());
             new_n += new_lines.len() - 1;
         }
@@ -168,7 +177,10 @@ fn lengthen_lines(content: &str, limit: usize) -> String {
         let Some(next_line) = content.get(n + 1) else {
             continue;
         };
-        if ignore(next_line, in_code_block) || REGEX_IGNORE_END.is_match(line) {
+        if ignore(next_line, in_code_block)
+            || REGEX_LIST_ENTRY.is_match(next_line)
+            || REGEX_IGNORE_END.is_match(line)
+        {
             continue;
         }
         if line.len() + next_line.len() < limit {
@@ -182,42 +194,47 @@ fn lengthen_lines(content: &str, limit: usize) -> String {
 
 #[test]
 fn test_sembr() {
-    let original = "\
+    let original = "
 # some. heading
-must! be; split?  and.   normalizes space
-1. ignore numbered
+must! be; split?
+1. ignore a dot after number. but no further
 ignore | tables
 ignore e.g. and
 ignore i.e. and
 ignore E.g. too
-- ignore. list
-* ignore. list
+- list. entry
+ * list. entry
 ```
 some code. block
 ```
 sentence with *italics* should not be ignored. truly.
 git log main.. compiler
+ foo.   bar.  baz
 ";
-    let expected = "\
+    let expected = "
 # some. heading
 must!
 be;
 split?
-and.
-normalizes space
-1. ignore numbered
+1. ignore a dot after number.
+   but no further
 ignore | tables
 ignore e.g. and
 ignore i.e. and
 ignore E.g. too
-- ignore. list
-* ignore. list
+- list.
+  entry
+ * list.
+   entry
 ```
 some code. block
 ```
 sentence with *italics* should not be ignored.
 truly.
 git log main.. compiler
+ foo.
+   bar.
+  baz
 ";
     assert_eq!(expected, comply(original));
 }
@@ -230,12 +247,28 @@ short sentences
 <div class='warning'>
 a bit of text inside
 </div>
+preserve next line
+1. one
+
+preserve next line
+- two
+
+preserve next line
+* three
 ";
     let expected = "\
 do not split short sentences
 <div class='warning'>
 a bit of text inside
 </div>
+preserve next line
+1. one
+
+preserve next line
+- two
+
+preserve next line
+* three
 ";
     assert_eq!(expected, lengthen_lines(original, 50));
 }
@@ -263,13 +296,13 @@ fn test_prettify_ignore_link_targets() {
 
 #[test]
 fn test_sembr_then_prettify() {
-    let original = "\
+    let original = "
 hi there. do
 not split
 short sentences.
 hi again.
 ";
-    let expected = "\
+    let expected = "
 hi there.
 do
 not split
@@ -278,15 +311,15 @@ hi again.
 ";
     let processed = comply(original);
     assert_eq!(expected, processed);
-    let expected = "\
+    let expected = "
 hi there.
 do not split
 short sentences.
 hi again.
 ";
     let processed = lengthen_lines(&processed, 50);
     assert_eq!(expected, processed);
-    let expected = "\
+    let expected = "
 hi there.
 do not split short sentences.
 hi again.
@@ -297,12 +330,12 @@ hi again.
 
 #[test]
 fn test_sembr_question_mark() {
-    let original = "\
+    let original = "
 o? whatever
 r? @reviewer
  r? @reviewer
 ";
-    let expected = "\
+    let expected = "
 o?
 whatever
 r? @reviewer

ci/sembr/src/main.rs

@@ -1 +1 @@
-8401398e1f14a24670ee1a3203713dc2f0f8b3a8
+cc328c12382f05d8ddf6ffc8139deb7985270ad8

rust-version

@@ -68,7 +68,7 @@ This instructs `git` to perform a "shallow clone", cloning the repository but tr
 the last `N` commits.
 
 Passing `--depth 1` tells `git` to clone the repository but truncate the history to the latest
-commit that is on the `master` branch, which is usually fine for browsing the source code or
+commit that is on the `main` branch, which is usually fine for browsing the source code or
 building the compiler.
 
 ```bash
@@ -172,7 +172,7 @@ You can install it with `cargo install --path src/tools/x`.
 
 To clarify that this is another global installed binary util, which is
 similar to the one declared in section [What is `x.py`](#what-is-xpy), but
-it works as an independent process to execute the `x.py` rather than calling the 
+it works as an independent process to execute the `x.py` rather than calling the
 shell to run the platform related scripts.
 
 ## Create a `bootstrap.toml`

src/building/how-to-build-and-run.md

@@ -296,7 +296,7 @@ lets you use `cargo fmt`.
 [the section on vscode]: suggested.md#configuring-rust-analyzer-for-rustc
 [the section on rustup]: how-to-build-and-run.md?highlight=rustup#creating-a-rustup-toolchain
 
-## Faster Builds with CI-rustc  
+## Faster Builds with CI-rustc
 
 If you are not working on the compiler, you often don't need to build the compiler tree.
 For example, you can skip building the compiler and only build the `library` tree or the
@@ -389,7 +389,7 @@ times, and having to update each clone individually.
 Fortunately, Git has a better solution called [worktrees]. This lets you create
 multiple "working trees", which all share the same Git database. Moreover,
 because all of the worktrees share the same object database, if you update a
-branch (e.g. master) in any of them, you can use the new commits from any of the
+branch (e.g. `main`) in any of them, you can use the new commits from any of the
 worktrees. One caveat, though, is that submodules do not get shared. They will
 still be cloned multiple times.
 
@@ -403,10 +403,10 @@ command:
 git worktree add ../rust2
 ```
 
-Creating a new worktree for a new branch based on `master` looks like:
+Creating a new worktree for a new branch based on `main` looks like:
 
 ```bash
-git worktree add -b my-feature ../rust2 master
+git worktree add -b my-feature ../rust2 main
 ```
 
 You can then use that rust2 folder as a separate workspace for modifying and