Merge remote-tracking branch 'origin/master' into use-high-bit-of-mas…

…k-for-select

.github/workflows/ci.yml

@@ -418,7 +418,6 @@ jobs:
               RUST_CONFIGURE_ARGS: "--build=x86_64-pc-windows-msvc --host=aarch64-pc-windows-msvc --enable-full-tools --enable-profiler"
               SCRIPT: python x.py dist bootstrap --include-default-paths
               DIST_REQUIRE_ALL_TOOLS: 1
-              WINDOWS_SDK_20348_HACK: 1
             os: windows-2019-8core-32gb
           - name: dist-i686-mingw
             env:

.gitmodules

@@ -1,34 +1,45 @@
 [submodule "src/doc/nomicon"]
 	path = src/doc/nomicon
 	url = https://github.com/rust-lang/nomicon.git
+	shallow = true
 [submodule "src/tools/cargo"]
 	path = src/tools/cargo
 	url = https://github.com/rust-lang/cargo.git
+	shallow = true
 [submodule "src/doc/reference"]
 	path = src/doc/reference
 	url = https://github.com/rust-lang/reference.git
+	shallow = true
 [submodule "src/doc/book"]
 	path = src/doc/book
 	url = https://github.com/rust-lang/book.git
+	shallow = true
 [submodule "src/doc/rust-by-example"]
 	path = src/doc/rust-by-example
 	url = https://github.com/rust-lang/rust-by-example.git
+	shallow = true
 [submodule "library/stdarch"]
 	path = library/stdarch
 	url = https://github.com/rust-lang/stdarch.git
+	shallow = true
 [submodule "src/doc/rustc-dev-guide"]
 	path = src/doc/rustc-dev-guide
 	url = https://github.com/rust-lang/rustc-dev-guide.git
+	shallow = true
 [submodule "src/doc/edition-guide"]
 	path = src/doc/edition-guide
 	url = https://github.com/rust-lang/edition-guide.git
+	shallow = true
 [submodule "src/llvm-project"]
 	path = src/llvm-project
 	url = https://github.com/rust-lang/llvm-project.git
 	branch = rustc/16.0-2023-06-05
+	shallow = true
 [submodule "src/doc/embedded-book"]
 	path = src/doc/embedded-book
 	url = https://github.com/rust-embedded/book.git
+	shallow = true
 [submodule "library/backtrace"]
 	path = library/backtrace
 	url = https://github.com/rust-lang/backtrace-rs.git
+	shallow = true

Cargo.lock

@@ -2495,6 +2495,7 @@ dependencies = [
  "serde_json",
  "sysinfo",
  "tar",
+ "tempfile",
  "xz",
  "zip",
 ]
@@ -3785,7 +3786,7 @@ name = "rustc_lexer"
 version = "0.1.0"
 dependencies = [
  "expect-test",
- "unic-emoji-char",
+ "unicode-properties",
  "unicode-xid",
 ]
 
@@ -5445,38 +5446,6 @@ dependencies = [
  "tempfile",
 ]
 
-[[package]]
-name = "unic-char-property"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a8c57a407d9b6fa02b4795eb81c5b6652060a15a7903ea981f3d723e6c0be221"
-dependencies = [
- "unic-char-range",
-]
-
-[[package]]
-name = "unic-char-range"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0398022d5f700414f6b899e10b8348231abf9173fa93144cbc1a43b9793c1fbc"
-
-[[package]]
-name = "unic-common"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "80d7ff825a6a654ee85a63e80f92f054f904f21e7d12da4e22f9834a4aaa35bc"
-
-[[package]]
-name = "unic-emoji-char"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b07221e68897210270a38bde4babb655869637af0f69407f96053a34f76494d"
-dependencies = [
- "unic-char-property",
- "unic-char-range",
- "unic-ucd-version",
-]
-
 [[package]]
 name = "unic-langid"
 version = "0.9.1"
@@ -5520,15 +5489,6 @@ dependencies = [
  "unic-langid-impl",
 ]
 
-[[package]]
-name = "unic-ucd-version"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96bd2f2237fe450fcd0a1d2f5f4e91711124f7857ba2e964247776ebeeb7b0c4"
-dependencies = [
- "unic-common",
-]
-
 [[package]]
 name = "unicase"
 version = "2.6.0"
@@ -5566,6 +5526,12 @@ dependencies = [
  "tinyvec",
 ]
 
+[[package]]
+name = "unicode-properties"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7f91c8b21fbbaa18853c3d0801c78f4fc94cdb976699bb03e832e75f7fd22f0"
+
 [[package]]
 name = "unicode-script"
 version = "0.5.5"

compiler/rustc/build.rs

@@ -18,7 +18,7 @@ fn set_windows_exe_options() {
     let mut manifest = env::current_dir().unwrap();
     manifest.push(WINDOWS_MANIFEST_FILE);
 
-    println!("cargo:rerun-if-changed={}", WINDOWS_MANIFEST_FILE);
+    println!("cargo:rerun-if-changed={WINDOWS_MANIFEST_FILE}");
     // Embed the Windows application manifest file.
     println!("cargo:rustc-link-arg-bin=rustc-main=/MANIFEST:EMBED");
     println!("cargo:rustc-link-arg-bin=rustc-main=/MANIFESTINPUT:{}", manifest.to_str().unwrap());

compiler/rustc_abi/src/layout.rs

@@ -260,8 +260,7 @@ pub trait LayoutCalculator {
                 }
                 _ => assert!(
                     start == Bound::Unbounded && end == Bound::Unbounded,
-                    "nonscalar layout for layout_scalar_valid_range type: {:#?}",
-                    st,
+                    "nonscalar layout for layout_scalar_valid_range type: {st:#?}",
                 ),
             }
 
@@ -463,7 +462,7 @@ pub trait LayoutCalculator {
             min = 0;
             max = 0;
         }
-        assert!(min <= max, "discriminant range is {}...{}", min, max);
+        assert!(min <= max, "discriminant range is {min}...{max}");
         let (min_ity, signed) = discr_range_of_repr(min, max); //Integer::repr_discr(tcx, ty, &repr, min, max);
 
         let mut align = dl.aggregate_align;
@@ -537,8 +536,7 @@ pub trait LayoutCalculator {
             // space necessary to represent would have to be discarded (or layout is wrong
             // on thinking it needs 16 bits)
             panic!(
-                "layout decided on a larger discriminant type ({:?}) than typeck ({:?})",
-                min_ity, typeck_ity
+                "layout decided on a larger discriminant type ({min_ity:?}) than typeck ({typeck_ity:?})"
             );
             // However, it is fine to make discr type however large (as an optimisation)
             // after this point – we’ll just truncate the value we load in codegen.

compiler/rustc_abi/src/lib.rs

@@ -332,7 +332,7 @@ impl TargetDataLayout {
             16 => 1 << 15,
             32 => 1 << 31,
             64 => 1 << 47,
-            bits => panic!("obj_size_bound: unknown pointer bit size {}", bits),
+            bits => panic!("obj_size_bound: unknown pointer bit size {bits}"),
         }
     }
 
@@ -342,7 +342,7 @@ impl TargetDataLayout {
             16 => I16,
             32 => I32,
             64 => I64,
-            bits => panic!("ptr_sized_integer: unknown pointer bit size {}", bits),
+            bits => panic!("ptr_sized_integer: unknown pointer bit size {bits}"),
         }
     }
 
@@ -399,7 +399,7 @@ impl FromStr for Endian {
         match s {
             "little" => Ok(Self::Little),
             "big" => Ok(Self::Big),
-            _ => Err(format!(r#"unknown endian: "{}""#, s)),
+            _ => Err(format!(r#"unknown endian: "{s}""#)),
         }
     }
 }
@@ -456,7 +456,7 @@ impl Size {
     pub fn bits(self) -> u64 {
         #[cold]
         fn overflow(bytes: u64) -> ! {
-            panic!("Size::bits: {} bytes in bits doesn't fit in u64", bytes)
+            panic!("Size::bits: {bytes} bytes in bits doesn't fit in u64")
         }
 
         self.bytes().checked_mul(8).unwrap_or_else(|| overflow(self.bytes()))
@@ -1179,17 +1179,12 @@ impl FieldsShape {
                 unreachable!("FieldsShape::offset: `Primitive`s have no fields")
             }
             FieldsShape::Union(count) => {
-                assert!(
-                    i < count.get(),
-                    "tried to access field {} of union with {} fields",
-                    i,
-                    count
-                );
+                assert!(i < count.get(), "tried to access field {i} of union with {count} fields");
                 Size::ZERO
             }
             FieldsShape::Array { stride, count } => {
                 let i = u64::try_from(i).unwrap();
-                assert!(i < count, "tried to access field {} of array with {} fields", i, count);
+                assert!(i < count, "tried to access field {i} of array with {count} fields");
                 stride * i
             }
             FieldsShape::Arbitrary { ref offsets, .. } => offsets[FieldIdx::from_usize(i)],
@@ -1294,7 +1289,7 @@ impl Abi {
                 Primitive::Int(_, signed) => signed,
                 _ => false,
             },
-            _ => panic!("`is_signed` on non-scalar ABI {:?}", self),
+            _ => panic!("`is_signed` on non-scalar ABI {self:?}"),
         }
     }
 

compiler/rustc_ast/src/tokenstream.rs

@@ -13,7 +13,7 @@
 //! and a borrowed `TokenStream` is sufficient to build an owned `TokenStream` without taking
 //! ownership of the original.
 
-use crate::ast::StmtKind;
+use crate::ast::{AttrStyle, StmtKind};
 use crate::ast_traits::{HasAttrs, HasSpan, HasTokens};
 use crate::token::{self, Delimiter, Nonterminal, Token, TokenKind};
 use crate::AttrVec;
@@ -22,11 +22,11 @@ use rustc_data_structures::stable_hasher::{HashStable, StableHasher};
 use rustc_data_structures::sync::{self, Lrc};
 use rustc_macros::HashStable_Generic;
 use rustc_serialize::{Decodable, Decoder, Encodable, Encoder};
-use rustc_span::{Span, DUMMY_SP};
+use rustc_span::{sym, Span, Symbol, DUMMY_SP};
 use smallvec::{smallvec, SmallVec};
 
 use std::borrow::Cow;
-use std::{fmt, iter, mem};
+use std::{cmp, fmt, iter, mem};
 
 /// When the main Rust parser encounters a syntax-extension invocation, it
 /// parses the arguments to the invocation as a token tree. This is a very
@@ -566,6 +566,92 @@ impl TokenStream {
     pub fn chunks(&self, chunk_size: usize) -> core::slice::Chunks<'_, TokenTree> {
         self.0.chunks(chunk_size)
     }
+
+    /// Desugar doc comments like `/// foo` in the stream into `#[doc =
+    /// r"foo"]`. Modifies the `TokenStream` via `Lrc::make_mut`, but as little
+    /// as possible.
+    pub fn desugar_doc_comments(&mut self) {
+        if let Some(desugared_stream) = desugar_inner(self.clone()) {
+            *self = desugared_stream;
+        }
+
+        // The return value is `None` if nothing in `stream` changed.
+        fn desugar_inner(mut stream: TokenStream) -> Option<TokenStream> {
+            let mut i = 0;
+            let mut modified = false;
+            while let Some(tt) = stream.0.get(i) {
+                match tt {
+                    &TokenTree::Token(
+                        Token { kind: token::DocComment(_, attr_style, data), span },
+                        _spacing,
+                    ) => {
+                        let desugared = desugared_tts(attr_style, data, span);
+                        let desugared_len = desugared.len();
+                        Lrc::make_mut(&mut stream.0).splice(i..i + 1, desugared);
+                        modified = true;
+                        i += desugared_len;
+                    }
+
+                    &TokenTree::Token(..) => i += 1,
+
+                    &TokenTree::Delimited(sp, delim, ref delim_stream) => {
+                        if let Some(desugared_delim_stream) = desugar_inner(delim_stream.clone()) {
+                            let new_tt = TokenTree::Delimited(sp, delim, desugared_delim_stream);
+                            Lrc::make_mut(&mut stream.0)[i] = new_tt;
+                            modified = true;
+                        }
+                        i += 1;
+                    }
+                }
+            }
+            if modified { Some(stream) } else { None }
+        }
+
+        fn desugared_tts(attr_style: AttrStyle, data: Symbol, span: Span) -> Vec<TokenTree> {
+            // Searches for the occurrences of `"#*` and returns the minimum number of `#`s
+            // required to wrap the text. E.g.
+            // - `abc d` is wrapped as `r"abc d"` (num_of_hashes = 0)
+            // - `abc "d"` is wrapped as `r#"abc "d""#` (num_of_hashes = 1)
+            // - `abc "##d##"` is wrapped as `r###"abc ##"d"##"###` (num_of_hashes = 3)
+            let mut num_of_hashes = 0;
+            let mut count = 0;
+            for ch in data.as_str().chars() {
+                count = match ch {
+                    '"' => 1,
+                    '#' if count > 0 => count + 1,
+                    _ => 0,
+                };
+                num_of_hashes = cmp::max(num_of_hashes, count);
+            }
+
+            // `/// foo` becomes `doc = r"foo"`.
+            let delim_span = DelimSpan::from_single(span);
+            let body = TokenTree::Delimited(
+                delim_span,
+                Delimiter::Bracket,
+                [
+                    TokenTree::token_alone(token::Ident(sym::doc, false), span),
+                    TokenTree::token_alone(token::Eq, span),
+                    TokenTree::token_alone(
+                        TokenKind::lit(token::StrRaw(num_of_hashes), data, None),
+                        span,
+                    ),
+                ]
+                .into_iter()
+                .collect::<TokenStream>(),
+            );
+
+            if attr_style == AttrStyle::Inner {
+                vec![
+                    TokenTree::token_alone(token::Pound, span),
+                    TokenTree::token_alone(token::Not, span),
+                    body,
+                ]
+            } else {
+                vec![TokenTree::token_alone(token::Pound, span), body]
+            }
+        }
+    }
 }
 
 /// By-reference iterator over a [`TokenStream`], that produces `&TokenTree`
@@ -628,15 +714,6 @@ impl TokenTreeCursor {
     pub fn look_ahead(&self, n: usize) -> Option<&TokenTree> {
         self.stream.0.get(self.index + n)
     }
-
-    // Replace the previously obtained token tree with `tts`, and rewind to
-    // just before them.
-    pub fn replace_prev_and_rewind(&mut self, tts: Vec<TokenTree>) {
-        assert!(self.index > 0);
-        self.index -= 1;
-        let stream = Lrc::make_mut(&mut self.stream.0);
-        stream.splice(self.index..self.index + 1, tts);
-    }
 }
 
 #[derive(Debug, Copy, Clone, PartialEq, Encodable, Decodable, HashStable_Generic)]