Initial commit

.github/workflows/release.yml

@@ -0,0 +1,115 @@
+name: Release
+
+on:
+  release:
+    types: [created]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [x86_64, x86, aarch64]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          args: --release --out dist --find-interpreter
+          sccache: "true"
+          manylinux: auto
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: dist
+
+  windows:
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        target: [x64, x86]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          architecture: ${{ matrix.target }}
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          args: --release --out dist --find-interpreter
+          sccache: "true"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: dist
+
+  macos:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: macos-latest
+            target: x86_64
+          - runner: macos-14
+            target: aarch64
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: "true"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: dist
+
+  sdist:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Build sdist
+        uses: PyO3/maturin-action@v1
+        with:
+          command: sdist
+          args: --out dist
+      - name: Upload sdist
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: dist
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    needs: [linux, windows, macos, sdist]
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+      - name: Delete artifacts after upload
+        uses: geekyeggo/delete-artifact@v5
+        with:
+          name: wheels

.github/workflows/test.yml

@@ -0,0 +1,39 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+  workflow_dispatch:
+
+# Make sure CI fails on all warnings, including Clippy lints
+env:
+  RUSTFLAGS: "-Dwarnings"
+
+jobs:
+  clippy_check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Run Clippy
+        run: cargo clippy --all-targets --all-features
+
+  pytest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Install package and dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[test]
+      - name: Run tests
+        run: |
+          pytest

.gitignore

@@ -1,3 +1,9 @@
+# IDE
+.vscode/
+
+# Python
+__pycache__/
+
 # Generated by Cargo
 # will have compiled files and executables
 debug/

Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "ms2rescore-rs"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[lib]
+name = "ms2rescore_rs"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = "0.20.0"
+mzdata = "0.13.0"
+timsrust = "0.2.3"

pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["maturin>=1.5,<2.0"]
+build-backend = "maturin"
+
+[project]
+name = "ms2rescore-rs"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Rust",
+    "Programming Language :: Python :: Implementation :: CPython",
+    "Programming Language :: Python :: Implementation :: PyPy",
+]
+dynamic = ["version"]
+
+[project.optional-dependencies]
+test = ["pytest"]
+
+[tool.maturin]
+features = ["pyo3/extension-module"]

src/file_types.rs

@@ -0,0 +1,41 @@
+pub enum SpectrumFileType {
+    MascotGenericFormat,
+    MzML,
+    BrukerRaw,
+    // ThermoRaw,
+    Unknown,
+}
+
+pub fn match_file_type(spectrum_path: &str) -> SpectrumFileType {
+    let extension = spectrum_path.split('.').last().unwrap_or("").to_lowercase();
+    match extension.as_str() {
+        "mgf" => SpectrumFileType::MascotGenericFormat,
+        "mzml" => SpectrumFileType::MzML,
+        "d" | "ms2" => SpectrumFileType::BrukerRaw,
+        // "raw" => SpectrumFileType::ThermoRaw,
+        _ => match (
+            folder_contains_extension(spectrum_path, "bin"),
+            folder_contains_extension(spectrum_path, "parquet"),
+        ) {
+            (true, true) => SpectrumFileType::BrukerRaw,
+            _ => SpectrumFileType::Unknown,
+        },
+    }
+}
+
+fn folder_contains_extension(input: impl AsRef<std::path::Path>, extension: &str) -> bool {
+    let folder_path: std::path::PathBuf = input.as_ref().to_path_buf();
+    if !folder_path.is_dir() {
+        return false;
+    }
+    if let Ok(entries) = std::fs::read_dir(folder_path) {
+        for entry in entries.flatten() {
+            if let Some(ext) = entry.path().extension() {
+                if ext == extension {
+                    return true;
+                }
+            }
+        }
+    }
+    false
+}

src/lib.rs

@@ -0,0 +1,41 @@
+mod file_types;
+mod parse_mzdata;
+mod parse_timsrust;
+mod precursor;
+
+use std::collections::HashMap;
+
+use pyo3::exceptions::PyOSError;
+use pyo3::prelude::*;
+
+use file_types::{match_file_type, SpectrumFileType};
+use precursor::Precursor;
+
+/// Get mapping of spectrum identifiers to precursor information.
+#[pyfunction]
+pub fn get_precursor_info(spectrum_path: String) -> PyResult<HashMap<String, Precursor>> {
+    let file_type = match_file_type(&spectrum_path);
+
+    let precursors = match file_type {
+        SpectrumFileType::MascotGenericFormat | SpectrumFileType::MzML => {
+            parse_mzdata::parse_precursor_info(&spectrum_path, file_type)
+        }
+        SpectrumFileType::BrukerRaw => parse_timsrust::parse_precursor_info(&spectrum_path),
+        // SpectrumFileType::ThermoRaw => parse_with_mzdata_thermo(&spectrum_path, file_type),
+        SpectrumFileType::Unknown => return Err(PyOSError::new_err("Unsupported file type")),
+    };
+
+    match precursors {
+        Ok(precursors) => Ok(precursors),
+        Err(e) => Err(PyOSError::new_err(e.to_string())),
+    }
+}
+
+
+/// A Python module implemented in Rust.
+#[pymodule]
+fn ms2rescore_rs(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_class::<Precursor>()?;
+    m.add_function(wrap_pyfunction!(get_precursor_info, m)?)?;
+    Ok(())
+}