Merge branch 'rust-lang:master' into patch-1

.github/workflows/ci.yml

@@ -54,10 +54,14 @@ jobs:
           os: ubuntu-latest
           rust: stable
           target: i686-unknown-linux-gnu
-        - build: stable-mips
+        - build: stable-powerpc64
           os: ubuntu-latest
           rust: stable
-          target: mips64-unknown-linux-gnuabi64
+          target: powerpc64-unknown-linux-gnu
+        - build: stable-s390x
+          os: ubuntu-latest
+          rust: stable
+          target: s390x-unknown-linux-gnu
         - build: beta
           os: ubuntu-latest
           rust: beta
@@ -77,7 +81,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: ${{ matrix.rust }}
     - name: Install and configure Cross
@@ -92,12 +96,6 @@ jobs:
         cd "$dir"
         curl -LO "https://github.com/cross-rs/cross/releases/download/$CROSS_VERSION/cross-x86_64-unknown-linux-musl.tar.gz"
         tar xf cross-x86_64-unknown-linux-musl.tar.gz
-
-        # We used to install 'cross' from master, but it kept failing. So now
-        # we build from a known-good version until 'cross' becomes more stable
-        # or we find an alternative. Notably, between v0.2.1 and current
-        # master (2022-06-14), the number of Cross's dependencies has doubled.
-        # cargo install --bins --git https://github.com/rust-embedded/cross --tag v0.2.1
         echo "CARGO=cross" >> $GITHUB_ENV
         echo "TARGET=--target ${{ matrix.target }}" >> $GITHUB_ENV
     - name: Show command used for Cargo
@@ -141,9 +139,28 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
-        toolchain: 1.60.0
+        toolchain: 1.65.0
+    # The memchr 2.6 release purportedly bumped its MSRV to Rust 1.60, but it
+    # turned out that on aarch64, it was using something that wasn't stabilized
+    # until Rust 1.61[1]. (This was an oversight on my part. I had previously
+    # thought everything I needed was on Rust 1.60.) To resolve that, I just
+    # bumped memchr's MSRV to 1.61. Since it was so soon after the memchr 2.6
+    # release, I treated this as a bugfix.
+    #
+    # But the regex crate's MSRV is at Rust 1.60, and it now depends on at
+    # least memchr 2.6 (to make use of its `alloc` feature). So we can't set
+    # a lower minimal version. And I can't just bump the MSRV in a patch
+    # release as a bug fix because regex 1.9 was released quite some time ago.
+    # I could just release regex 1.10 and bump the MSRV there, but eh, I don't
+    # want to put out another minor version release just for this.
+    #
+    # So... pin memchr to 2.6.2, which at least works on x86-64 on Rust 1.60.
+    #
+    # [1]: https://github.com/BurntSushi/memchr/issues/136
+    - name: Pin memchr to 2.6.2
+      run: cargo update -p memchr --precise 2.6.2
     - name: Basic build
       run: cargo build --verbose
     - name: Build docs
@@ -162,7 +179,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: stable
     - name: Run full test suite
@@ -175,7 +192,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: stable
     - name: Run full test suite
@@ -188,7 +205,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: stable
     - name: Run full test suite
@@ -201,7 +218,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: stable
     - name: Run full test suite
@@ -216,7 +233,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         # We use nightly here so that we can use miri I guess?
         # It caught me by surprise that miri seems to only be
@@ -233,7 +250,7 @@ jobs:
     - name: Checkout repository
       uses: actions/checkout@v3
     - name: Install Rust
-      uses: dtolnay/rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
         toolchain: stable
         components: rustfmt

CHANGELOG.md

@@ -1,3 +1,198 @@
+1.10.2 (2023-10-16)
+===================
+This is a new patch release that fixes a search regression where incorrect
+matches could be reported.
+
+Bug fixes:
+
+* [BUG #1110](https://github.com/rust-lang/regex/issues/1110):
+Revert broadening of reverse suffix literal optimization introduced in 1.10.1.
+
+
+1.10.1 (2023-10-14)
+===================
+This is a new patch release with a minor increase in the number of valid
+patterns and a broadening of some literal optimizations.
+
+New features:
+
+* [FEATURE 04f5d7be](https://github.com/rust-lang/regex/commit/04f5d7be4efc542864cc400f5d43fbea4eb9bab6):
+Loosen ASCII-compatible rules such that regexes like `(?-u:☃)` are now allowed.
+
+Performance improvements:
+
+* [PERF 8a8d599f](https://github.com/rust-lang/regex/commit/8a8d599f9d2f2d78e9ad84e4084788c2d563afa5):
+Broader the reverse suffix optimization to apply in more cases.
+
+
+1.10.0 (2023-10-09)
+===================
+This is a new minor release of `regex` that adds support for start and end
+word boundary assertions. That is, `\<` and `\>`. The minimum supported Rust
+version has also been raised to 1.65, which was released about one year ago.
+
+The new word boundary assertions are:
+
+* `\<` or `\b{start}`: a Unicode start-of-word boundary (`\W|\A` on the left,
+`\w` on the right).
+* `\>` or `\b{end}`: a Unicode end-of-word boundary (`\w` on the left, `\W|\z`
+on the right)).
+* `\b{start-half}`: half of a Unicode start-of-word boundary (`\W|\A` on the
+left).
+* `\b{end-half}`: half of a Unicode end-of-word boundary (`\W|\z` on the
+right).
+
+The `\<` and `\>` are GNU extensions to POSIX regexes. They have been added
+to the `regex` crate because they enjoy somewhat broad support in other regex
+engines as well (for example, vim). The `\b{start}` and `\b{end}` assertions
+are aliases for `\<` and `\>`, respectively.
+
+The `\b{start-half}` and `\b{end-half}` assertions are not found in any
+other regex engine (although regex engines with general look-around support
+can certainly express them). They were added principally to support the
+implementation of word matching in grep programs, where one generally wants to
+be a bit more flexible in what is considered a word boundary.
+
+New features:
+
+* [FEATURE #469](https://github.com/rust-lang/regex/issues/469):
+Add support for `\<` and `\>` word boundary assertions.
+* [FEATURE(regex-automata) #1031](https://github.com/rust-lang/regex/pull/1031):
+DFAs now have a `start_state` method that doesn't use an `Input`.
+
+Performance improvements:
+
+* [PERF #1051](https://github.com/rust-lang/regex/pull/1051):
+Unicode character class operations have been optimized in `regex-syntax`.
+* [PERF #1090](https://github.com/rust-lang/regex/issues/1090):
+Make patterns containing lots of literal characters use less memory.
+
+Bug fixes:
+
+* [BUG #1046](https://github.com/rust-lang/regex/issues/1046):
+Fix a bug that could result in incorrect match spans when using a Unicode word
+boundary and searching non-ASCII strings.
+* [BUG(regex-syntax) #1047](https://github.com/rust-lang/regex/issues/1047):
+Fix panics that can occur in `Ast->Hir` translation (not reachable from `regex`
+crate).
+* [BUG(regex-syntax) #1088](https://github.com/rust-lang/regex/issues/1088):
+Remove guarantees in the API that connect the `u` flag with a specific HIR
+representation.
+
+`regex-automata` breaking change release:
+
+This release includes a `regex-automata 0.4.0` breaking change release, which
+was necessary in order to support the new word boundary assertions. For
+example, the `Look` enum has new variants and the `LookSet` type now uses `u32`
+instead of `u16` to represent a bitset of look-around assertions. These are
+overall very minor changes, and most users of `regex-automata` should be able
+to move to `0.4` from `0.3` without any changes at all.
+
+`regex-syntax` breaking change release:
+
+This release also includes a `regex-syntax 0.8.0` breaking change release,
+which, like `regex-automata`, was necessary in order to support the new word
+boundary assertions. This release also includes some changes to the `Ast`
+type to reduce heap usage in some cases. If you are using the `Ast` type
+directly, your code may require some minor modifications. Otherwise, users of
+`regex-syntax 0.7` should be able to migrate to `0.8` without any code changes.
+
+`regex-lite` release:
+
+The `regex-lite 0.1.1` release contains support for the new word boundary
+assertions. There are no breaking changes.
+
+
+1.9.6 (2023-09-30)
+==================
+This is a patch release that fixes a panic that can occur when the default
+regex size limit is increased to a large number.
+
+* [BUG aa4e4c71](https://github.com/rust-lang/regex/commit/aa4e4c7120b0090ce0624e3c42a2ed06dd8b918a):
+Fix a bug where computing the maximum haystack length for the bounded
+backtracker could result underflow and thus provoke a panic later in a search
+due to a broken invariant.
+
+
+1.9.5 (2023-09-02)
+==================
+This is a patch release that hopefully mostly fixes a performance bug that
+occurs when sharing a regex across multiple threads.
+
+Issue [#934](https://github.com/rust-lang/regex/issues/934)
+explains this in more detail. It is [also noted in the crate
+documentation](https://docs.rs/regex/latest/regex/#sharing-a-regex-across-threads-can-result-in-contention).
+The bug can appear when sharing a regex across multiple threads simultaneously,
+as might be the case when using a regex from a `OnceLock`, `lazy_static` or
+similar primitive. Usually high contention only results when using many threads
+to execute searches on small haystacks.
+
+One can avoid the contention problem entirely through one of two methods.
+The first is to use lower level APIs from `regex-automata` that require passing
+state explicitly, such as [`meta::Regex::search_with`](https://docs.rs/regex-automata/latest/regex_automata/meta/struct.Regex.html#method.search_with).
+The second is to clone a regex and send it to other threads explicitly. This
+will not use any additional memory usage compared to sharing the regex. The
+only downside of this approach is that it may be less convenient, for example,
+it won't work with things like `OnceLock` or `lazy_static` or `once_cell`.
+
+With that said, as of this release, the contention performance problems have
+been greatly reduced. This was achieved by changing the free-list so that it
+was sharded across threads, and that ensuring each sharded mutex occupies a
+single cache line to mitigate false sharing. So while contention may still
+impact performance in some cases, it should be a lot better now.
+
+Because of the changes to how the free-list works, please report any issues you
+find with this release. That not only includes search time regressions but also
+significant regressions in memory usage. Reporting improvements is also welcome
+as well! If possible, provide a reproduction.
+
+Bug fixes:
+
+* [BUG #934](https://github.com/rust-lang/regex/issues/934):
+Fix a performance bug where high contention on a single regex led to massive
+slow downs.
+
+
+1.9.4 (2023-08-26)
+==================
+This is a patch release that fixes a bug where `RegexSet::is_match(..)` could
+incorrectly return false (even when `RegexSet::matches(..).matched_any()`
+returns true).
+
+Bug fixes:
+
+* [BUG #1070](https://github.com/rust-lang/regex/issues/1070):
+Fix a bug where a prefilter was incorrectly configured for a `RegexSet`.
+
+
+1.9.3 (2023-08-05)
+==================
+This is a patch release that fixes a bug where some searches could result in
+incorrect match offsets being reported. It is difficult to characterize the
+types of regexes susceptible to this bug. They generally involve patterns
+that contain no prefix or suffix literals, but have an inner literal along with
+a regex prefix that can conditionally match.
+
+Bug fixes:
+
+* [BUG #1060](https://github.com/rust-lang/regex/issues/1060):
+Fix a bug with the reverse inner literal optimization reporting incorrect match
+offsets.
+
+
+1.9.2 (2023-08-05)
+==================
+This is a patch release that fixes another memory usage regression. This
+particular regression occurred only when using a `RegexSet`. In some cases,
+much more heap memory (by one or two orders of magnitude) was allocated than in
+versions prior to 1.9.0.
+
+Bug fixes:
+
+* [BUG #1059](https://github.com/rust-lang/regex/issues/1059):
+Fix a memory usage regression when using a `RegexSet`.
+
+
 1.9.1 (2023-07-07)
 ==================
 This is a patch release which fixes a memory usage regression. In the regex

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "regex"
-version = "1.9.1"  #:version
+version = "1.10.2"  #:version
 authors = ["The Rust Project Developers", "Andrew Gallant <[email protected]>"]
 license = "MIT OR Apache-2.0"
 readme = "README.md"
@@ -15,7 +15,7 @@ categories = ["text-processing"]
 autotests = false
 exclude = ["/scripts/*", "/.github/*"]
 edition = "2021"
-rust-version = "1.60.0"
+rust-version = "1.65"
 
 [workspace]
 members = [
@@ -52,6 +52,7 @@ std = [
 # to actually emit the log messages somewhere.
 logging = [
   "aho-corasick?/logging",
+  "memchr?/logging",
   "regex-automata/logging",
 ]
 # The 'use_std' feature is DEPRECATED. It will be removed in regex 2. Until
@@ -167,20 +168,20 @@ optional = true
 
 # For skipping along search text quickly when a leading byte is known.
 [dependencies.memchr]
-version = "2.5.0"
+version = "2.6.0"
 optional = true
 
 # For the actual regex engines.
 [dependencies.regex-automata]
 path = "regex-automata"
-version = "0.3.1"
+version = "0.4.3"
 default-features = false
 features = ["alloc", "syntax", "meta", "nfa-pikevm"]
 
 # For parsing regular expressions.
 [dependencies.regex-syntax]
 path = "regex-syntax"
-version = "0.7.3"
+version = "0.8.2"
 default-features = false
 
 [dev-dependencies]