Py port of gtfsort + CI , new tree, and additional updates

.github/workflows/check.yml

@@ -25,59 +25,59 @@ jobs:
           toolchain: ${{ matrix.rust }}
 
       - name: Cargo Check with Minimum Feature Flags
-        run: cargo check --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM"
+        run: cargo check --manifest-path ./gtfsort/Cargo.toml --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM"
 
       - name: Cargo Check with Full Feature Flags
-        run: cargo check --features "$GTFSORT_TEST_FEATURES_FULL"
+        run: cargo check --manifest-path ./gtfsort/Cargo.toml --features "$GTFSORT_TEST_FEATURES_FULL"
 
       - name: Cargo Clippy with Minimum Feature Flags
-        run: cargo clippy --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM" -- -D warnings
+        run: cargo clippy --manifest-path ./gtfsort/Cargo.toml --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM" -- -D warnings
 
       - name: Cargo Clippy with Full Feature Flags
-        run: cargo clippy --features "$GTFSORT_TEST_FEATURES_FULL" -- -D warnings
+        run: cargo clippy --manifest-path ./gtfsort/Cargo.toml --features "$GTFSORT_TEST_FEATURES_FULL" -- -D warnings
 
       - name: Cargo Test with Minimum Feature Flags
         # saves time on more expensive machines
         if: ${{ startsWith(matrix.os, 'ubuntu') }}
-        run: RUST_BACKTRACE=full cargo test --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM" -- --nocapture
+        run: RUST_BACKTRACE=full cargo test --manifest-path ./gtfsort/Cargo.toml --no-default-features --features "$GTFSORT_TEST_FEATURES_MINIMUM" -- --nocapture
 
       - name: Cargo Build Release
-        run: cargo build --release --features "$GTFSORT_TEST_FEATURES_FULL"
+        run: cargo build --manifest-path ./gtfsort/Cargo.toml --release --features "$GTFSORT_TEST_FEATURES_FULL"
 
       - name: Cargo Test with Full Feature Flags
-        run: RUST_BACKTRACE=full cargo test --features "$GTFSORT_TEST_FEATURES_FULL" -- --nocapture
+        run: RUST_BACKTRACE=full cargo test --manifest-path ./gtfsort/Cargo.toml --features "$GTFSORT_TEST_FEATURES_FULL" -- --nocapture
 
       - name: Check C headers are up-to-date
         if: ${{ startsWith(matrix.os, 'ubuntu') }}
-        run: git diff --exit-code include/gtfsort.h include/gtfsort.hxx
+        run: git diff --exit-code ./gtfsort/include/gtfsort.h ./gtfsort/include/gtfsort.hxx
 
       - name: Cargo Clean
         if: ${{ matrix.rust == 'stable' }}
-        run: cargo clean
+        run: cargo clean --manifest-path ./gtfsort/Cargo.toml 
 
       - name: Build Release
         if: ${{ matrix.rust == 'stable' }}
-        run: cargo build --release --features "$GTFSORT_TEST_FEATURES_RELEASE"
+        run: cargo build --manifest-path ./gtfsort/Cargo.toml --release --features "$GTFSORT_TEST_FEATURES_RELEASE"
 
       - name: Upload Build Artifacts
         if: ${{ startsWith(matrix.os, 'macos') != true && matrix.rust == 'stable' }}  
         uses: actions/upload-artifact@v4
         with:
           name: build-artifacts-${{ matrix.os }}
           path: |
-            target/release/gtfsort
-            target/release/libgtfsort.so
+            ./gtfsort/target/release/gtfsort
+            ./gtfsort/target/release/libgtfsort.so
 
       - name: Upload Build Artifacts (macOS)
         if: ${{ startsWith(matrix.os, 'macos') && matrix.rust == 'stable' }}
         uses: actions/upload-artifact@v4
         with:
           name: build-artifacts-${{ matrix.os }}
           path: |
-            target/release/gtfsort
-            target/release/libgtfsort.dylib
-            include/gtfsort.h
-            include/gtfsort.hxx
+            ./gtfsort/target/release/gtfsort
+            ./gtfsort/target/release/libgtfsort.dylib
+            ./gtfsort/include/gtfsort.h
+            ./gtfsort/include/gtfsort.hxx
 
   check-windows:
       runs-on: windows-latest
@@ -106,45 +106,82 @@ jobs:
             target: x86_64-pc-windows-gnu
 
         - name: Cargo Check with Minimum Feature Flags
-          run: cargo check --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM
+          run: cargo check --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM
 
         - name: Cargo Check with Full Feature Flags
-          run: cargo check --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL
+          run: cargo check --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL
 
         - name: Cargo Clippy with Minimum Feature Flags
-          run: cargo clippy --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM -- -D warnings
+          run: cargo clippy --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM -- -D warnings
 
         - name: Cargo Clippy with Full Feature Flags
-          run: cargo clippy --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL -- -D warnings
+          run: cargo clippy --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL -- -D warnings
 
         - name: Cargo Test with Minimum Feature Flags
-          run: $env:RUST_BACKTRACE="full"; cargo test --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM -- --nocapture
+          run: $env:RUST_BACKTRACE="full"; cargo test --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --no-default-features --features $env:GTFSORT_TEST_FEATURES_MINIMUM -- --nocapture
 
         - name: Cargo Build Release
-          run: cargo build --target x86_64-pc-windows-gnu --release --features $env:GTFSORT_TEST_FEATURES_FULL
+          run: cargo build --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --release --features $env:GTFSORT_TEST_FEATURES_FULL
 
         - name: Cargo Test with Full Feature Flags
-          run: $env:RUST_BACKTRACE="full"; cargo test --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL -- --nocapture
+          run: $env:RUST_BACKTRACE="full"; cargo test --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --features $env:GTFSORT_TEST_FEATURES_FULL -- --nocapture
 
         - name: Cargo Clean
           if: ${{ matrix.rust == 'stable' }}
-          run: cargo clean
+          run: cargo clean --manifest-path ./gtfsort/Cargo.toml 
 
         - name: Build Release
           if: ${{ matrix.rust == 'stable' }}
-          run: cargo build --target x86_64-pc-windows-gnu --release --features $env:GTFSORT_TEST_FEATURES_RELEASE
+          run: cargo build --manifest-path ./gtfsort/Cargo.toml --target x86_64-pc-windows-gnu --release --features $env:GTFSORT_TEST_FEATURES_RELEASE
 
         - name: Upload Build Artifacts
           if: ${{ matrix.rust == 'stable' }}
           uses: actions/upload-artifact@v4
           with:
             name: build-artifacts-windows
             path: |
-              target/x86_64-pc-windows-gnu/release/gtfsort.exe
-              target/x86_64-pc-windows-gnu/release/gtfsort.dll
-              include/gtfsort.h
-              include/gtfsort.hxx
+              ./gtfsort/target/x86_64-pc-windows-gnu/release/gtfsort.exe
+              ./gtfsort/target/x86_64-pc-windows-gnu/release/gtfsort.dll
+              ./gtfsort/include/gtfsort.h
+              ./gtfsort/include/gtfsort.hxx
 
+  py_port:
+    needs: [check-unix]
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9']
+        target: [x86_64, aarch64]
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Set up Rust
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+
+      - name: Install pipx
+        run: python -m pip install --user pipx && python -m pipx ensurepath
+
+      - name: Install dependencies
+        run: pipx install hatch maturin
+
+      - name: Create Hatch environment
+        shell: bash
+        run: cd py-gtfsort && hatch env create
+
+      - name: Activate Hatch env, build and run py test
+        shell: bash
+        run: |
+          cd py-gtfsort
+          source $(hatch env find)/bin/activate
+          maturin develop --release --manifest-path Cargo.toml --features test
+          hatch run test --verbose
+
   benchmark:
     needs: [check-unix, check-windows]
     if: ${{ needs.check-unix.result == 'success' && contains(github.event.head_commit.message, '[ci benchmark]') }}
@@ -173,20 +210,20 @@ jobs:
         run: git fetch upstream
 
       - name: Build Benchmark
-        run: cargo build --release --bin gtfsort-benchmark --features "mmap benchmark"
+        run: cargo build --manifest-path ./gtfsort/Cargo.toml --release --bin gtfsort-benchmark --features "mmap benchmark"
 
       - name: Run Benchmark
         env:
           GITHUB_REPO_OWNER: ${{ github.event.repository.owner.login }}
           GITHUB_REPO_NAME: ${{ github.event.repository.name }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: target/release/gtfsort-benchmark -r upstream/master -- --show-output
+        run: ./gtfsort/target/release/gtfsort-benchmark -r upstream/master -- --show-output
 
       - name: Upload Benchmark Results
         uses: actions/upload-artifact@v4
         with:
             name: benchmark-results-${{ matrix.os }}
             path: |
-              tests/benchmark_*.csv
-              tests/benchmark_*.md
-              tests/benchmark-output.txt
+              ./gtfsort/tests/benchmark_*.csv
+              ./gtfsort/tests/benchmark_*.md
+              ./gtfsort/tests/benchmark-output.txt

CITATION.cff

@@ -2,20 +2,27 @@
 # Visit https://bit.ly/cffinit to generate yours today!
 
 cff-version: 1.2.0
-title: gtfsort
+title: "gtfsort: A tool for sorting GTF files"
 message: >-
   If you use this software, please cite it using the
   metadata from this file.
 type: software
 authors:
   - given-names: Alejandro
     family-names: Gonzales-Irribarren
-    email: [email protected]
+    email: [email protected]
     affiliation: >-
-      Laboratorio Internacional de Investigación sobre el
-      Genoma Humano, Universidad Nacional Autónoma de
-      México, Santiago de Querétaro, 76230, México
+      LOEWE Centre for Translational Biodiversity Genomics, 
+      Senckenberganlage 25, 60325 Frankfurt, Germany
     orcid: 'https://orcid.org/0000-0001-7010-8146'
+  - given-names: Anne
+    family-names: Fu
+    email: [email protected]
+    affiliation: >-
+      School of Natural Sciences and Mathematics, The University of
+      Texas at Dallas, Richardson, TX 75080, USA
+    orcid: 'https://orcid.org/0000-0002-9025-6071'
+
 identifiers:
   - type: url
     value: 'https://github.com/alejandrogzi/gtfsort'
@@ -34,6 +41,8 @@ abstract: >-
 keywords:
   - sort-algorithm
   - gtf
+  - gff3
   - gene-annotation
 license: MIT
-version: 0.2.1
+version: 0.2.3
+doi: 10.1101/2023.10.21.563454

README.md

@@ -20,7 +20,7 @@ While current tools (most of them GFF3-focused) have been recommended for sortin
 > 
 > If you use gtfsort in your work, please cite:
 > 
-> Gonzales-Irribarren A. gtfsort: a tool to efficiently sort GTF files. bioRxiv 2023.10.21.563454; doi: https://doi.org/10.1101/2023.10.21.563454
+> Gonzales-Irribarren A and Fu. A. gtfsort: a tool to efficiently sort GTF files. bioRxiv 2023.10.21.563454; doi: https://doi.org/10.1101/2023.10.21.563454
 
 ## Usage
 ``` rust
@@ -36,7 +36,7 @@ Options:
     --version: print version
 ```
 
-> What's new on v.0.2.2
+> What's new on v.0.2.3
 >
 > - **gtfsort now supports GFF sorting!**
 > - Now gtfsort is bit more faster (~0.2s); 1.9GB (*Cyprinus carpio carpio*) in 6.7s

.gitignore → gtfsort/.gitignore

@@ -1,3 +1,3 @@
-/target
+target/
 tests/
 

Cargo.toml → gtfsort/Cargo.toml

@@ -1,14 +1,14 @@
 [package]
 name = "gtfsort"
-version = "0.2.2"
-authors = ["alejandrogzi <[email protected]>"]
+version = "0.2.3"
+authors = ["alejandrogzi <[email protected]>", "eternal-flame-AD <[email protected]>"]
 edition = "2021"
 license = "MIT"
-description = "An optimized chr/pos/feature GTF2.5-3 sorter using a lexicographic-based index ordering algorithm written in Rust."
+description = "An optimized chr/pos/feature GTF/GFF sorter using a lexicographic-based index ordering algorithm written in Rust."
 homepage = "https://github.com/alejandrogzi/gtfsort"
 repository = "https://github.com/alejandrogzi/gtfsort"
 readme = "README.md"
-keywords = ["sort", "gtf", "cli", "gtfsort"]
+keywords = ["sort", "gtf", "gff", "gtfsort"]
 categories = ["command-line-utilities", "science"]
 default-run = "gtfsort"
 

src/lib.rs → gtfsort/src/lib.rs

@@ -6,15 +6,17 @@ pub mod ord;
 pub use ord::CowNaturalSort;
 
 pub mod utils;
-use thiserror::Error;
 pub use utils::*;
 
 pub mod interop;
 
 #[cfg(feature = "testing")]
 pub mod test_utils;
+#[cfg(feature = "testing")]
+pub use test_utils::*;
 
 use std::{io, path::PathBuf};
+use thiserror::Error;
 
 #[cfg(feature = "mmap")]
 use mmap::Madvice;

src/main.rs → gtfsort/src/main.rs

@@ -2,7 +2,7 @@
 //! A fast and efficient GTF sorter tool.
 //!
 //! ## Overview
-//! `gtfsort` is a rapid chr/pos/feature GTF2.5-3 sorter using a lexicographic-based
+//! `gtfsort` is a rapid chr/pos/feature GTF/GFF sorter using a lexicographic-based
 //! index ordering algorithm written in Rust. This tool is intended to be used as a
 //! standalone command-line tool. The primary goal of this tool is to sort GTF files
 //! by chromosome, position and feature in a fast and memory-efficient way.
@@ -31,8 +31,8 @@ use gtfsort::*;
 #[derive(Parser, Debug)]
 #[clap(
     name = "gtfsort",
-    version = "0.2.2",
-    author = "Alejandro Gonzales-Irribarren <[email protected]>",
+    version = "0.2.3",
+    author = "alejandrogzi <[email protected]>, eternal-flame-AD <[email protected]>",
     about = "An optimized chr/pos/feature GTF2.5-3 sorter using a lexicographic-based index ordering algorithm written in Rust."
 )]
 struct Args {

src/test_utils.rs → gtfsort/src/test_utils.rs

@@ -47,7 +47,17 @@ impl Deref for TempFile {
 impl Drop for TempFile {
     fn drop(&mut self) {
         if self.cleanup {
-            std::fs::remove_file(&self.path).unwrap();
+            // std::fs::remove_file(&self.path).unwrap();
+            if self.path.exists() {
+                if let Err(e) = std::fs::remove_file(&self.path) {
+                    eprintln!(
+                        "Warning: Failed to remove temporary file {:?}: {:?}",
+                        self.path, e
+                    );
+                }
+            } else {
+                eprintln!("Warning: Temporary file {:?} does not exist.", self.path);
+            }
         }
     }
 }
@@ -176,7 +186,7 @@ pub fn crc32_hex<R: Read>(mut r: R) -> String {
 }
 
 pub struct TestFile {
-    name: String,
+    pub name: String,
     expect_output_cksum: Vec<&'static str>,
 }
 

src/utils.rs → gtfsort/src/utils.rs

@@ -275,7 +275,7 @@ pub fn write_obj_mmaped<'a, P: AsRef<Path> + Debug>(
 pub fn parallel_parse<const SEP: u8>(s: &str) -> Result<ChromRecord<'_>, &'static str> {
     let x = s
         .par_lines()
-        .filter(|line| !line.starts_with("#"))
+        .filter(|line| !line.starts_with('#'))
         .filter_map(|line| Record::parse::<SEP>(line).ok())
         .fold(HashMap::new, |mut acc: ChromRecord, record| {
             acc.entry(record.chrom).or_default().push(record);