Add unicode-normalization-0.1.24

collector/compile-benchmarks/README.md

@@ -59,6 +59,9 @@ They mostly consist of real-world crates.
 - **unicode-normalization-0.1.19**: Unicode character composition and decomposition
   utilities. Uses huge `match` statements that stress the compiler in unusual
   ways.
+- **unicode-normalization-0.1.24**: Unicode character composition and decomposition
+  utilities. Uses huge `match` statements that stress the compiler in unusual
+  ways.
 
 ## Secondary
 

collector/compile-benchmarks/REUSE.toml

@@ -289,6 +289,11 @@ path = "unicode-normalization-0.1.19/**"
 SPDX-FileCopyrightText = "unicode-normalization contributors"
 SPDX-License-Identifier = "MIT OR Apache-2.0"
 
+[[annotations]]
+path = "unicode-normalization-0.1.24/**"
+SPDX-FileCopyrightText = "unicode-normalization contributors"
+SPDX-License-Identifier = "MIT OR Apache-2.0"
+
 [[annotations]]
 path = "unify-linearly/**"
 SPDX-FileCopyrightText = "The Rust Project Developers (see https://thanks.rust-lang.org)"

collector/compile-benchmarks/unicode-normalization-0.1.24/.cargo_vcs_info.json

@@ -0,0 +1,6 @@
+{
+  "git": {
+    "sha1": "c9921309f09ebd05108920fda92efbf5f8124a7d"
+  },
+  "path_in_vcs": ""
+}

collector/compile-benchmarks/unicode-normalization-0.1.24/.github/workflows/rust.yml

@@ -0,0 +1,87 @@
+name: Rust
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+env:
+  CARGO_INCREMENTAL: 0
+  CARGO_TERM_COLOR: always
+  RUST_BACKTRACE: 1
+  RUSTFLAGS: -D warnings
+  RUSTDOCFLAGS: -D warnings --cfg docsrs
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        rust:
+          - stable
+          - beta
+          - nightly
+    steps:
+    - uses: actions/checkout@v2
+    - name: Install toolchain
+      uses: actions-rs/toolchain@v1
+      with:
+          toolchain: ${{ matrix.rust }}
+          override: true
+          components: rustfmt, clippy
+    - name: Build
+      run: cargo build --verbose
+    - name: Run tests with all features
+      run: cargo test --all-features --verbose
+    - name: Run tests without features
+      run: cargo test --no-default-features --verbose
+    - name: Package
+      run: cargo package
+    - name: Test package
+      run: cd $(find target/package/ -maxdepth 1 -mindepth 1 -type d) && cargo test
+    - name: Test package without features
+      run: cd $(find target/package/ -maxdepth 1 -mindepth 1 -type d) && cargo test --no-default-features
+    - name: Build docs
+      if: matrix.rust == 'nightly'
+      run: cargo doc --all-features --verbose
+    - name: Check formatting
+      if: matrix.rust == 'stable'
+      run: cargo fmt --all --check
+    - name: Check clippy
+      if: matrix.rust == 'stable'
+      run: cargo clippy --all-features --lib --tests --examples --verbose
+    - name: Check benchmarks with clippy
+      if: matrix.rust == 'nightly'
+      run: cargo clippy --all-features --benches --verbose
+    - name: Check fuzz tests with clippy
+      if: matrix.rust == 'stable'
+      working-directory: fuzz
+      run: cargo clippy --all-features --all-targets --verbose
+    - name: Check fuzz tests formatting
+      if: matrix.rust == 'stable'
+      working-directory: fuzz
+      run: cargo fmt --all --check
+  msrv:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Install msrv toolchain
+      uses: dtolnay/[email protected]
+    - name: Use tinyvec 1.6.0
+      run: cargo update -p tinyvec --precise 1.6.0
+    - name: Build
+      run: cargo build --verbose --all-features
+  regen:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v5
+      with:
+        python-version: '3.12'
+    - name: Regen
+      run: cd scripts && python3 unicode.py
+    - name: Diff tables
+      run: diff src/tables.rs scripts/tables.rs
+    - name: Diff tests
+      run: diff tests/data/normalization_tests.rs scripts/normalization_tests.rs

collector/compile-benchmarks/unicode-normalization-0.1.24/.gitignore

@@ -0,0 +1,5 @@
+target
+#Cargo.lock
+scripts/tmp
+*.pyc
+*.txt

collector/compile-benchmarks/unicode-normalization-0.1.24/.travis.yml

@@ -0,0 +1,17 @@
+language: rust
+rust:
+  - 1.36.0
+  - stable
+  - nightly
+sudo: false
+script:
+  - cargo build --verbose
+  - cargo test --verbose
+  - cargo test --verbose --no-default-features
+  - cargo package
+  - cd target/package/unicode-normalization-*
+  - cargo test --verbose
+  - cargo test --verbose --no-default-features
+notifications:
+  email:
+    on_success: never

collector/compile-benchmarks/unicode-normalization-0.1.24/0-println.patch

@@ -0,0 +1,12 @@
+diff --git a/src/lookups.rs b/src/lookups.rs
+index ea7a96c4..c1938cd1 100644
+--- a/src/lookups.rs
++++ b/src/lookups.rs
+@@ -43,6 +43,7 @@ pub(crate) fn composition_table(c1: char, c2: char) -> Option<char> {
+ }
+
+ pub(crate) fn canonical_fully_decomposed(c: char) -> Option<&'static [char]> {
++    println!("testing");
+     mph_lookup(
+         c.into(),
+         CANONICAL_DECOMPOSED_SALT,

collector/compile-benchmarks/unicode-normalization-0.1.24/COPYRIGHT

@@ -0,0 +1,7 @@
+Licensed under the Apache License, Version 2.0
+<LICENSE-APACHE or
+http://www.apache.org/licenses/LICENSE-2.0> or the MIT
+license <LICENSE-MIT or http://opensource.org/licenses/MIT>,
+at your option. All files in the project carrying such
+notice may not be copied, modified, or distributed except
+according to those terms.

collector/compile-benchmarks/unicode-normalization-0.1.24/Cargo.toml

@@ -0,0 +1,68 @@
+# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
+#
+# When uploading crates to the registry Cargo will automatically
+# "normalize" Cargo.toml files for maximal compatibility
+# with all versions of Cargo and also rewrite `path` dependencies
+# to registry (e.g., crates.io) dependencies.
+#
+# If you are reading this file be aware that the original Cargo.toml
+# will likely look very different (and much more reasonable).
+# See Cargo.toml.orig for the original contents.
+
+[package]
+edition = "2018"
+rust-version = "1.36"
+name = "unicode-normalization"
+version = "0.1.24"
+authors = [
+    "kwantam <[email protected]>",
+    "Manish Goregaokar <[email protected]>",
+]
+build = false
+exclude = [
+    "target/*",
+    "Cargo.lock",
+    "scripts/tmp",
+    "*.txt",
+    "tests/*",
+]
+autobins = false
+autoexamples = false
+autotests = false
+autobenches = false
+description = """
+This crate provides functions for normalization of
+Unicode strings, including Canonical and Compatible
+Decomposition and Recomposition, as described in
+Unicode Standard Annex #15.
+"""
+homepage = "https://github.com/unicode-rs/unicode-normalization"
+documentation = "https://docs.rs/unicode-normalization/"
+readme = "README.md"
+keywords = [
+    "text",
+    "unicode",
+    "normalization",
+    "decomposition",
+    "recomposition",
+]
+license = "MIT/Apache-2.0"
+repository = "https://github.com/unicode-rs/unicode-normalization"
+
+[lib]
+name = "unicode_normalization"
+path = "src/lib.rs"
+
+[[bench]]
+name = "bench"
+path = "benches/bench.rs"
+
+[dependencies.tinyvec]
+version = "1"
+features = ["alloc"]
+
+[features]
+default = ["std"]
+std = []
+
+[workspace]