Merge pull request #2105 from nnethercote/add-ripgrep

Add `ripgrep-14.1.1` benchmark

Author: Kobzol

collector/compile-benchmarks/README.md

@@ -46,6 +46,8 @@ They mostly consist of real-world crates.
 - **regex-1.5.5**: A regular expression parser. Used by many Rust programs.
 - **ripgrep-13.0.0**: A line-oriented search tool. A widely-used utility, and a
   binary crate.
+- **ripgrep-14.1.1**: A line-oriented search tool. A widely-used utility, and a
+  binary crate.
 - **serde-1.0.136**: A serialization/deserialization crate. Used by many other
   Rust programs.
 - **serde-1.0.219**: A serialization/deserialization crate. Used by many other

collector/compile-benchmarks/REUSE.toml

@@ -210,6 +210,11 @@ path = "ripgrep-13.0.0-tiny/**"
 SPDX-FileCopyrightText = "ripgrep contributors"
 SPDX-License-Identifier = "MIT OR Unlicense"
 
+[[annotations]]
+path = "ripgrep-14.1.1/**"
+SPDX-FileCopyrightText = "ripgrep contributors"
+SPDX-License-Identifier = "MIT OR Unlicense"
+
 [[annotations]]
 path = "serde-1.0.136/**"
 SPDX-FileCopyrightText = "serde contributors"

collector/compile-benchmarks/ripgrep-14.1.1/.cargo/config.toml

@@ -0,0 +1,21 @@
+# On Windows MSVC, statically link the C runtime so that the resulting EXE does
+# not depend on the vcruntime DLL.
+#
+# See: https://github.com/BurntSushi/ripgrep/pull/1613
+[target.x86_64-pc-windows-msvc]
+rustflags = ["-C", "target-feature=+crt-static"]
+[target.i686-pc-windows-msvc]
+rustflags = ["-C", "target-feature=+crt-static"]
+
+# Do the same for MUSL targets. At the time of writing (2023-10-23), this is
+# the default. But the plan is for the default to change to dynamic linking.
+# The whole point of MUSL with respect to ripgrep is to create a fully
+# statically linked executable.
+#
+# See: https://github.com/rust-lang/compiler-team/issues/422
+# See: https://github.com/rust-lang/compiler-team/issues/422#issuecomment-812135847
+[target.x86_64-unknown-linux-musl]
+rustflags = [
+  "-C", "target-feature=+crt-static",
+  "-C", "link-self-contained=yes",
+]

collector/compile-benchmarks/ripgrep-14.1.1/.cargo_vcs_info.json

@@ -0,0 +1,6 @@
+{
+  "git": {
+    "sha1": "4649aa9700619f94cf9c66876e9549d83420e16c"
+  },
+  "path_in_vcs": ""
+}

collector/compile-benchmarks/ripgrep-14.1.1/.gitignore

@@ -0,0 +1,22 @@
+.*.swp
+tags
+target
+/grep/Cargo.lock
+/globset/Cargo.lock
+/ignore/Cargo.lock
+/termcolor/Cargo.lock
+/wincolor/Cargo.lock
+/deployment
+/.idea
+
+# Snapcraft files
+stage
+prime
+parts
+*.snap
+*.pyc
+ripgrep*_source.tar.bz2
+
+# Cargo timings
+cargo-timing-*.html
+cargo-timing.html

collector/compile-benchmarks/ripgrep-14.1.1/.ignore

@@ -0,0 +1 @@
+!/.github/

collector/compile-benchmarks/ripgrep-14.1.1/0-println.patch

@@ -0,0 +1,12 @@
+diff --git a/crates/core/search.rs b/crates/core/search.rs
+index 67273425..4794ab49 100644
+--- a/crates/core/search.rs
++++ b/crates/core/search.rs
+@@ -340,6 +340,7 @@ impl<W: WriteColor> SearchWorker<W> {
+     fn search_path(&mut self, path: &Path) -> io::Result<SearchResult> {
+         use self::PatternMatcher::*;
+ 
++        println!("testing");
+         let (searcher, printer) = (&mut self.searcher, &mut self.printer);
+         match self.matcher {
+             RustRegex(ref m) => search_path(m, searcher, printer, path),