Merge pull request #5 from bigbio/dev

tests improved

Author: ypriverol

.github/workflows/pyspectrafuse-containers.yml

@@ -88,6 +88,18 @@ jobs:
         # Note: Only building for linux/amd64
         platforms: linux/amd64
 
+    - name: Test container functionality
+      run: |
+        echo "Testing container import and CLI..."
+        docker run --rm ghcr.io/bigbio/pyspectrafuse:${{ steps.version.outputs.VERSION }} --help || docker run --rm ghcr.io/bigbio/pyspectrafuse:latest --help
+        echo "Testing Python imports..."
+        docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:${{ steps.version.outputs.VERSION }} -c "from pyspectrafuse.pyspectrafuse import main; print('CLI import successful')" || docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:latest -c "from pyspectrafuse.pyspectrafuse import main; print('CLI import successful')"
+        echo "Testing consensus strategy imports..."
+        docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:${{ steps.version.outputs.VERSION }} -c "from pyspectrafuse.consensus_strategy.best_spetrum_strategy import BestSpectrumStrategy; print('BestSpectrumStrategy import successful')" || docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:latest -c "from pyspectrafuse.consensus_strategy.best_spetrum_strategy import BestSpectrumStrategy; print('BestSpectrumStrategy import successful')"
+        echo "Testing spectrum_utils import (numba caching test)..."
+        docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:${{ steps.version.outputs.VERSION }} -c "import spectrum_utils.spectrum as sus; print('spectrum_utils import successful')" || docker run --rm --entrypoint python ghcr.io/bigbio/pyspectrafuse:latest -c "import spectrum_utils.spectrum as sus; print('spectrum_utils import successful')"
+        echo "All container tests passed!"
+
     - name: Free up disk space after build
       run: |
         docker image rm ghcr.io/bigbio/pyspectrafuse:latest || true

.github/workflows/tests.yml

@@ -49,3 +49,4 @@ jobs:
         name: codecov-umbrella
         fail_ci_if_error: false
 
+

.gitignore

@@ -163,3 +163,14 @@ cython_debug/
 #Ignore cursor AI rules
 .cursor/
 .codacy/
+
+# Test data files (downloaded from FTP)
+**/PXD*.parquet
+**/PXD*.sdrf.tsv
+**/pyspectrafuse_ftp_test_*/
+**/mgf_output/
+**/msp_output/
+**/*.mgf
+**/*.msp
+**/test_data/
+**/integration_test_data/

Dockerfile

@@ -6,10 +6,14 @@ LABEL description="pyspectrafuse - Command-line utilities for spectrum clusterin
 # Set working directory
 WORKDIR /app
 
+# Set numba cache directory to a writable location
+ENV NUMBA_CACHE_DIR=/tmp/numba_cache
+
 # Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* \
+    && mkdir -p /tmp/numba_cache
 
 # Copy requirements first for better caching
 COPY requirements.txt .
@@ -26,7 +30,7 @@ COPY pyspectrafuse/ ./pyspectrafuse/
 RUN pip install --no-cache-dir -e .
 
 # Set the entrypoint
-ENTRYPOINT ["pyspectrafuse_cli"]
+ENTRYPOINT ["pyspectrafuse"]
 
 # Default command
 CMD ["--help"]

README.md

@@ -1,5 +1,11 @@
 # pyspectrafuse
 
+[![Tests](https://github.com/bigbio/pyspectrafuse/actions/workflows/tests.yml/badge.svg)](https://github.com/bigbio/pyspectrafuse/actions/workflows/tests.yml)
+[![Containers](https://github.com/bigbio/pyspectrafuse/actions/workflows/pyspectrafuse-containers.yml/badge.svg)](https://github.com/bigbio/pyspectrafuse/actions/workflows/pyspectrafuse-containers.yml)
+[![codecov](https://codecov.io/gh/bigbio/pyspectrafuse/branch/master/graph/badge.svg)](https://codecov.io/gh/bigbio/pyspectrafuse)
+[![Python](https://img.shields.io/badge/python-3.8%2B-blue.svg)](https://www.python.org/downloads/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
 Python library with utility scripts for spectrafuse pipeline - a tool for processing and converting mass spectrometry data formats, generating consensus spectra, and handling cluster-based analysis workflows.
 
 ## Features
@@ -64,7 +70,7 @@ The package provides a command-line interface with two main commands:
 Convert parquet files to MGF format:
 
 ```bash
-pyspectrafuse_cli convert-mgf \
+pyspectrafuse convert-mgf \
     --parquet_dir /path/to/parquet/files \
     --batch_size 100000 \
     --spectra_capacity 1000000 \
@@ -82,7 +88,7 @@ pyspectrafuse_cli convert-mgf \
 Generate MSP format files from clustered spectra:
 
 ```bash
-pyspectrafuse_cli msp \
+pyspectrafuse msp \
     --parquet_dir /path/to/project \
     --method_type average \
     --cluster_tsv_file /path/to/cluster.tsv \

pyproject.toml

@@ -33,7 +33,7 @@ Homepage = "https://github.com/bigbio/pyspectrafuse"
 Repository = "https://github.com/bigbio/pyspectrafuse"
 
 [project.scripts]
-pyspectrafuse_cli = "pyspectrafuse.pyspectrafuse_cli:main"
+pyspectrafuse = "pyspectrafuse.pyspectrafuse:main"
 
 [tool.setuptools]
 include-package-data = true

pyspectrafuse/commands/quantmsio2mgf.py

@@ -9,7 +9,6 @@
 import os
 
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
-REVISION = "0.1.1"
 
 logger = logging.getLogger(__name__)
 

pyspectrafuse/commands/spectrum2msp.py

@@ -13,7 +13,6 @@
 import uuid
 
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
-REVISION = "0.1.1"
 
 logger = logging.getLogger(__name__)
 

pyspectrafuse/pyspectrafuse_cli.py pyspectrafuse/pyspectrafuse.pypyspectrafuse/pyspectrafuse_cli.py renamed to pyspectrafuse/pyspectrafuse.py

@@ -4,7 +4,6 @@
 from pyspectrafuse import __version__
 
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
-REVISION = "0.1.1"
 
 
 # Cli returns command line requests

requirements.txt

@@ -11,3 +11,4 @@ pytest>=7.0.0
 pytest-cov>=4.0.0
 pytest-mock>=3.10.0
 
+