Fix non-idempotent block doc comment closer rewrite

src/comment.rs

@@ -1074,16 +1074,26 @@ fn light_rewrite_comment(
             // `*` in `/*`.
             let first_non_whitespace = l.find(|c| !char::is_whitespace(c));
             let left_trimmed = if let Some(fnw) = first_non_whitespace {
-                if l.as_bytes()[fnw] == b'*' && fnw > 0 {
-                    &l[fnw - 1..]
+                if l.as_bytes()[fnw] == b'*' {
+                    Cow::Owned(format!(" {}", &l[fnw..]))
                 } else {
-                    &l[fnw..]
+                    Cow::Borrowed(&l[fnw..])
                 }
             } else {
-                ""
+                Cow::Borrowed("")
             };
+
             // Preserve markdown's double-space line break syntax in doc comment.
-            trim_end_unless_two_whitespaces(left_trimmed, is_doc_comment)
+            match left_trimmed {
+                Cow::Borrowed(left_trimmed) => Cow::Borrowed(trim_end_unless_two_whitespaces(
+                    left_trimmed,
+                    is_doc_comment,
+                )),
+                Cow::Owned(left_trimmed) => {
+                    let trimmed = trim_end_unless_two_whitespaces(&left_trimmed, is_doc_comment);
+                    Cow::Owned(trimmed.to_string())
+                }
+            }
         })
         .join(&format!("\n{}", offset.to_string(config)))
 }

tests/source/6639-non-idempotent-block-doc-comments/inner-block-doc-comment.rs

@@ -0,0 +1,9 @@
+/*!First comment.
+*/
+pub mod outer {
+    /*!Second comment.
+*/
+    pub struct Inner {
+        pub octets: Vec<u8>,
+    }
+}

tests/source/6639-non-idempotent-block-doc-comments/naive-outer-block-comment.rs

@@ -0,0 +1,3 @@
+/**
+*/
+mod foo {}

tests/source/6639-non-idempotent-block-doc-comments/outer-block-doc-comment.rs

@@ -0,0 +1,13 @@
+/**First comment.
+*
+*/
+pub mod outer {
+    /**Second comment.
+foo
+*/
+    pub struct Inner {
+        /**Third comment.
+*/
+        pub octets: Vec<u8>,
+    }
+}

tests/source/6639-non-idempotent-block-doc-comments/rustc-sample-1.rs

@@ -0,0 +1,34 @@
+//! Sample from
+//! <https://github.com/rust-lang/rust/blob/70222712809cd5cc1718ed8995914a1cbacb6b92/compiler/rustc_codegen_llvm/src/common.rs#L69-L93>.
+
+pub(crate) fn placeholder() {}
+
+/*
+* A note on nomenclature of linking: "extern", "foreign", and "upcall".
+*
+* An "extern" is an LLVM symbol we wind up emitting an undefined external
+* reference to. This means "we don't have the thing in this compilation unit,
+* please make sure you link it in at runtime". This could be a reference to
+* C code found in a C library, or rust code found in a rust crate.
+*
+* Most "externs" are implicitly declared (automatically) as a result of a
+* user declaring an extern _module_ dependency; this causes the rust driver
+* to locate an extern crate, scan its compilation metadata, and emit extern
+* declarations for any symbols used by the declaring crate.
+*
+* A "foreign" is an extern that references C (or other non-rust ABI) code.
+* There is no metadata to scan for extern references so in these cases either
+* a header-digester like bindgen, or manual function prototypes, have to
+* serve as declarators. So these are usually given explicitly as prototype
+* declarations, in rust code, with ABI attributes on them noting which ABI to
+* link via.
+*
+* An "upcall" is a foreign call generated by the compiler (not corresponding
+* to any user-written call in the code) into the runtime library, to perform
+* some helper task such as bringing a task to life, allocating memory, etc.
+*
+*/
+
+/// A structure representing an active landing pad for the duration of a basic
+/// block.
+pub(crate) struct Funclet<'ll> {}

tests/source/6639-non-idempotent-block-doc-comments/rustc-sample-2.rs

@@ -0,0 +1,24 @@
+//! Taken from
+//! <https://github.com/rust-lang/rust/blob/70222712809cd5cc1718ed8995914a1cbacb6b92/compiler/rustc_mir_transform/src/inline.rs#L1166-L1186>.
+
+/**
+ * Integrator.
+ *
+ * Integrates blocks from the callee function into the calling function.
+ * Updates block indices, references to locals and other control flow
+ * stuff.
+*/
+struct Integrator<'a, 'tcx> {
+    args: &'a [Local],
+    new_locals: RangeFrom<Local>,
+    new_scopes: RangeFrom<SourceScope>,
+    new_blocks: RangeFrom<BasicBlock>,
+    destination: Local,
+    callsite_scope: SourceScopeData<'tcx>,
+    callsite: &'a CallSite<'tcx>,
+    cleanup_block: UnwindAction,
+    in_cleanup_block: bool,
+    return_block: Option<BasicBlock>,
+    tcx: TyCtxt<'tcx>,
+    always_live_locals: DenseBitSet<Local>,
+}

tests/target/6639-non-idempotent-block-doc-comments/inner-block-doc-comment.rs

@@ -0,0 +1,9 @@
+/*!First comment.
+ */
+pub mod outer {
+    /*!Second comment.
+     */
+    pub struct Inner {
+        pub octets: Vec<u8>,
+    }
+}

tests/target/6639-non-idempotent-block-doc-comments/naive-outer-block-comment.rs

@@ -0,0 +1,3 @@
+/**
+ */
+mod foo {}

tests/target/6639-non-idempotent-block-doc-comments/outer-block-doc-comment.rs

@@ -0,0 +1,13 @@
+/**First comment.
+ *
+ */
+pub mod outer {
+    /**Second comment.
+    foo
+    */
+    pub struct Inner {
+        /**Third comment.
+         */
+        pub octets: Vec<u8>,
+    }
+}

tests/target/6639-non-idempotent-block-doc-comments/rustc-sample-1.rs

@@ -0,0 +1,34 @@
+//! Sample from
+//! <https://github.com/rust-lang/rust/blob/70222712809cd5cc1718ed8995914a1cbacb6b92/compiler/rustc_codegen_llvm/src/common.rs#L69-L93>.
+
+pub(crate) fn placeholder() {}
+
+/*
+ * A note on nomenclature of linking: "extern", "foreign", and "upcall".
+ *
+ * An "extern" is an LLVM symbol we wind up emitting an undefined external
+ * reference to. This means "we don't have the thing in this compilation unit,
+ * please make sure you link it in at runtime". This could be a reference to
+ * C code found in a C library, or rust code found in a rust crate.
+ *
+ * Most "externs" are implicitly declared (automatically) as a result of a
+ * user declaring an extern _module_ dependency; this causes the rust driver
+ * to locate an extern crate, scan its compilation metadata, and emit extern
+ * declarations for any symbols used by the declaring crate.
+ *
+ * A "foreign" is an extern that references C (or other non-rust ABI) code.
+ * There is no metadata to scan for extern references so in these cases either
+ * a header-digester like bindgen, or manual function prototypes, have to
+ * serve as declarators. So these are usually given explicitly as prototype
+ * declarations, in rust code, with ABI attributes on them noting which ABI to
+ * link via.
+ *
+ * An "upcall" is a foreign call generated by the compiler (not corresponding
+ * to any user-written call in the code) into the runtime library, to perform
+ * some helper task such as bringing a task to life, allocating memory, etc.
+ *
+ */
+
+/// A structure representing an active landing pad for the duration of a basic
+/// block.
+pub(crate) struct Funclet<'ll> {}

tests/target/6639-non-idempotent-block-doc-comments/rustc-sample-2.rs

@@ -0,0 +1,24 @@
+//! Taken from
+//! <https://github.com/rust-lang/rust/blob/70222712809cd5cc1718ed8995914a1cbacb6b92/compiler/rustc_mir_transform/src/inline.rs#L1166-L1186>.
+
+/**
+ * Integrator.
+ *
+ * Integrates blocks from the callee function into the calling function.
+ * Updates block indices, references to locals and other control flow
+ * stuff.
+ */
+struct Integrator<'a, 'tcx> {
+    args: &'a [Local],
+    new_locals: RangeFrom<Local>,
+    new_scopes: RangeFrom<SourceScope>,
+    new_blocks: RangeFrom<BasicBlock>,
+    destination: Local,
+    callsite_scope: SourceScopeData<'tcx>,
+    callsite: &'a CallSite<'tcx>,
+    cleanup_block: UnwindAction,
+    in_cleanup_block: bool,
+    return_block: Option<BasicBlock>,
+    tcx: TyCtxt<'tcx>,
+    always_live_locals: DenseBitSet<Local>,
+}