Merge branch 'main' into gtest-build-time

Author: oech3

.github/workflows/GnuTests.yml

@@ -80,7 +80,8 @@ jobs:
       run: |
         ## Install dependencies
         sudo apt-get update
-        sudo apt-get install -y autopoint gperf gdb python3-pyinotify valgrind libexpect-perl libacl1-dev libattr1-dev libcap-dev libselinux1-dev attr quilt
+        ## Check that build-gnu.sh works on the non SELinux system by installing libselinux only on lima
+        sudo apt-get install -y autopoint gperf gdb python3-pyinotify valgrind libexpect-perl libacl1-dev libattr1-dev libcap-dev attr quilt
     - name: Add various locales
       shell: bash
       run: |
@@ -109,7 +110,7 @@ jobs:
       run: |
         ## Build binaries
         cd 'uutils'
-        bash util/build-gnu.sh --release-build
+        env PROFILE=release-small bash util/build-gnu.sh
 
     ### Run tests as user
     - name: Run GNU tests
@@ -244,7 +245,7 @@ jobs:
     ### Build
     - name: Build binaries
       run: |
-        lima bash -c "cd ~/work/uutils/ && SELINUX_ENABLED=1 bash util/build-gnu.sh --release-build"
+        lima bash -c "cd ~/work/uutils/ && SELINUX_ENABLED=1 PROFILE=release-small bash util/build-gnu.sh"
 
     ### Run tests as user
     - name: Generate SELinux tests list

.github/workflows/benchmarks.yml

@@ -37,6 +37,7 @@ jobs:
           - { package: uu_numfmt }
           - { package: uu_rm }
           - { package: uu_seq }
+          - { package: uu_shuf }
           - { package: uu_sort }
           - { package: uu_split }
           - { package: uu_tsort }

Cargo.lock

@@ -349,7 +349,6 @@ notify = { version = "=8.2.0", features = ["macos_kqueue"] }
 num-bigint = "0.4.4"
 num-prime = "0.4.4"
 num-traits = "0.2.19"
-number_prefix = "0.4"
 onig = { version = "~6.5.1", default-features = false }
 parse_datetime = "0.13.0"
 phf = "0.13.1"
@@ -373,6 +372,7 @@ textwrap = { version = "0.16.1", features = ["terminal_size"] }
 thiserror = "2.0.3"
 time = { version = "0.3.36" }
 unicode-width = "0.2.0"
+unit-prefix = "0.5"
 utmp-classic = "0.1.6"
 uutils_term_grid = "0.7"
 walkdir = "2.5"

Cargo.toml

@@ -230,7 +230,9 @@ To run uutils against the GNU test suite locally, run the following commands:
 ```shell
 bash util/build-gnu.sh
 # Build uutils with release optimizations
-bash util/build-gnu.sh --release-build
+env PROFILE=release bash util/build-gnu.sh
+# Build uutils with SELinux
+env SELINUX_ENABLED=1 bash util/build-gnu.sh
 bash util/run-gnu-test.sh
 # To run a single test:
 bash util/run-gnu-test.sh tests/touch/not-owner.sh # for example

DEVELOPMENT.md

@@ -1375,10 +1375,19 @@ pub fn copy(sources: &[PathBuf], target: &Path, options: &Options) -> CopyResult
             {
                 // There is already a file and it isn't a symlink (managed in a different place)
                 if copied_destinations.contains(&dest) && options.backup != BackupMode::Numbered {
-                    // If the target file was already created in this cp call, do not overwrite
-                    return Err(CpError::Error(
-                        translate!("cp-error-will-not-overwrite-just-created", "dest" => dest.quote(), "source" => source.quote()),
-                    ));
+                    // If the target was already created in this cp call, check if it's a directory.
+                    // Directories should be merged (GNU cp behavior), but files should not be overwritten.
+                    let dest_is_dir = fs::metadata(&dest).is_ok_and(|m| m.is_dir());
+                    let source_is_dir = fs::metadata(source).is_ok_and(|m| m.is_dir());
+
+                    // Only prevent overwriting if both source and dest are files (not directories)
+                    // Directories should be merged, which is handled by copy_directory
+                    if !dest_is_dir || !source_is_dir {
+                        // If the target file was already created in this cp call, do not overwrite
+                        return Err(CpError::Error(
+                            translate!("cp-error-will-not-overwrite-just-created", "dest" => dest.quote(), "source" => source.quote()),
+                        ));
+                    }
                 }
             }
 

fuzz/Cargo.lock

@@ -27,3 +27,12 @@ fluent = { workspace = true }
 [[bin]]
 name = "shuf"
 path = "src/main.rs"
+
+[[bench]]
+name = "shuf_bench"
+harness = false
+
+[dev-dependencies]
+divan = { workspace = true }
+tempfile = { workspace = true }
+uucore = { workspace = true, features = ["benchmark"] }

src/uu/cp/src/cp.rs

@@ -0,0 +1,53 @@
+// This file is part of the uutils coreutils package.
+//
+// For the full copyright and license information, please view the LICENSE
+// file that was distributed with this source code.
+
+use divan::{Bencher, black_box};
+use uu_shuf::uumain;
+use uucore::benchmark::{run_util_function, setup_test_file, text_data};
+
+/// Benchmark shuffling lines from a file
+/// Tests the default mode with a large number of lines
+#[divan::bench(args = [100_000])]
+fn shuf_lines(bencher: Bencher, num_lines: usize) {
+    let data = text_data::generate_by_lines(num_lines, 80);
+    let file_path = setup_test_file(&data);
+    let file_path_str = file_path.to_str().unwrap();
+
+    bencher.bench(|| {
+        black_box(run_util_function(uumain, &[file_path_str]));
+    });
+}
+
+/// Benchmark shuffling a numeric range with -i
+/// Tests the input-range mode which uses a different algorithm
+#[divan::bench(args = [1_000_000])]
+fn shuf_input_range(bencher: Bencher, range_size: usize) {
+    let range_arg = format!("1-{range_size}");
+
+    bencher.bench(|| {
+        black_box(run_util_function(uumain, &["-i", &range_arg]));
+    });
+}
+
+/// Benchmark shuffling with repeat (sampling with replacement)
+/// Tests the -r flag combined with -n to output a specific count
+#[divan::bench(args = [50_000])]
+fn shuf_repeat_sampling(bencher: Bencher, num_lines: usize) {
+    let data = text_data::generate_by_lines(10_000, 80);
+    let file_path = setup_test_file(&data);
+    let file_path_str = file_path.to_str().unwrap();
+    let count = format!("{num_lines}");
+
+    bencher.bench(|| {
+        black_box(run_util_function(
+            uumain,
+            &["-r", "-n", &count, file_path_str],
+        ));
+    });
+}
+
+fn main() {
+    divan::main();
+}

src/uu/shuf/Cargo.toml

@@ -26,7 +26,7 @@ bstr = { workspace = true }
 chrono = { workspace = true, optional = true }
 clap = { workspace = true }
 uucore_procs = { workspace = true }
-number_prefix = { workspace = true }
+unit-prefix = { workspace = true }
 phf = { workspace = true }
 dns-lookup = { workspace = true, optional = true }
 dunce = { version = "1.0.4", optional = true }