Merge pull request #8 from PopovIILab/dev

Add pytests!

Author: ilypopv

.github/workflows/ci.yml

@@ -0,0 +1,23 @@
+name: pytest
+on:
+  push:
+    branches: [ dev ]
+  pull_request:
+    branches: [ dev ]
+
+jobs:
+  build-test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.12]
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: |
+          python -m pip install --upgrade pip
+          pip install krakenparser
+          pip install pytest
+      - run: pytest -q

README.md

@@ -1,5 +1,9 @@
 # KrakenParser: Convert Kraken2 Reports to CSV
 
+![License](https://img.shields.io/badge/License-MIT-steelblue)
+[![Downloads](https://static.pepy.tech/badge/krakenparser)](https://pepy.tech/project/krakenparser)
+![CI](https://github.com/PopovIILab/KrakenParser/actions/workflows/ci.yml/badge.svg)
+
 <img src="https://github.com/PopovIILab/KrakenParser/blob/main/imgs/KrakenParser_logo_light.png#gh-light-mode-only" align="left"/>
 <img src="https://github.com/PopovIILab/KrakenParser/blob/main/imgs/KrakenParser_logo_dark.png#gh-dark-mode-only" align="left"/>
 
@@ -218,15 +222,15 @@ data/
    │  ├─ counts_family.csv
    │  ├─ ...
    └─ csv_relabund/    # Relative abundance CSV output
-   │  ├─ counts_species.csv
-   │  ├─ counts_genus.csv
-   │  ├─ counts_family.csv
-   │  ├─ ...
+      ├─ counts_species.csv
+      ├─ counts_genus.csv
+      ├─ counts_family.csv
+      ├─ ...
 ```
 
 ## Conclusion
 KrakenParser provides a **simple and automated** way to convert Kraken2 reports into usable CSV files for downstream analysis. You can run the **full pipeline** with a single command or use **individual scripts** as needed.
 
 For any issues or feature requests, feel free to open an issue on GitHub!
 
-🚀 Happy analyzing!
+🚀 Happy analyzing!

tests/test_full_pipeline.py

@@ -0,0 +1,49 @@
+import zipfile
+import shutil
+import subprocess
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture
+def demo_run(tmp_path):
+    repo_root = Path(__file__).parent.parent.resolve()
+    zip_src = repo_root / "demo_data.zip"
+    if not zip_src.exists():
+        pytest.skip("demo_data.zip not found")
+
+    local_zip = tmp_path / "demo_data.zip"
+    shutil.copy(zip_src, local_zip)
+    with zipfile.ZipFile(local_zip, "r") as z:
+        z.extractall(tmp_path)
+
+    demo_data_dir = tmp_path / "demo_data"
+    run_dir = tmp_path / "demo_run"
+    run_dir.mkdir()
+    (demo_data_dir / "kreports").rename(run_dir / "kreports")
+
+    return {"run_dir": run_dir}
+
+
+def test_full_pipeline_end_to_end(demo_run):
+    run_dir = demo_run["run_dir"]
+    kreports_path = run_dir / "kreports"
+
+    # 1. Run KrakenParser
+    cmd = ["KrakenParser", "--complete", "-i", str(kreports_path)]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    assert result.returncode == 0, f"Pipeline failed:\n{result.stderr}"
+
+    # 2. Assert each rank‐level CSV exists and is non‐empty
+    ranks = ["phylum", "class", "order", "family", "genus", "species"]
+    for rank in ranks:
+        csv_path = run_dir / "counts" / "csv" / f"counts_{rank}.csv"
+        assert csv_path.exists(), f"Missing counts_{rank}.csv"
+        assert csv_path.stat().st_size > 0, f"counts_{rank}.csv is empty"
+
+    # 3. Assert relative‐abundance CSVs exist and are non‐empty
+    rel_dir = run_dir / "counts" / "csv_relabund"
+    assert rel_dir.exists(), "csv_relabund directory is missing"
+    rel_species = rel_dir / "counts_species.csv"
+    assert rel_species.exists(), "Missing counts_species.csv in csv_relabund"
+    assert rel_species.stat().st_size > 0, "counts_species.csv is empty"