Merge pull request #13 from EBI-Metagenomics/feature/code-review-mber…

…acochea

Project restructure, addition of tests, general bug fixes

.env.example

@@ -0,0 +1,2 @@
+ENA_WEBIN=""
+ENA_WEBIN_PASSWORD=""

.github/workflows/test.yml

@@ -0,0 +1,24 @@
+name: Testing
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.8, 3.9, "3.10"]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Dependencies
+        run: |
+          pip install .[test]
+      - name: 🧪 - Testing
+        run: |
+          pytest -v

.gitignore

@@ -1 +1,84 @@
+#IntelliJ project structure files
+*.iml
+*.xml
+.idea/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.genome_uploader.config.env
+
+# Rope project settings
+.ropeproject
+
+# VSCode
+.vscode/
+
+# Ruff
+.ruff_cache/
+
+#personal
 cluster_uploader_wrapper.py

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+      - id: black
+  - repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        name: isort (python)
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.0.286
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --show-fixes]

LICENSE.md

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2017-2022 EMBL-EBI
+   Copyright 2017-2024 EMBL-EBI
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

README.md

@@ -47,7 +47,7 @@ The script needs `python`, `pandas`, `requests`, and `ena-webin-cli` to run. We
 ```bash
 # Create environment and install requirements
 conda env create -f requirements.yml
-conda activate genomeUploader
+conda activate genome_uploader
 ```
 
 You can generate pre-upload files with:

examples/input_example.tsv

@@ -1,3 +1,3 @@
-genome_name	genome_path	accessions	assembly_software	binning_software	binning_parameters	stats_generation_software	completeness	contamination	genome_coverage	metagenome	co-assembly	broad_environment	local_environment	environmental_medium	rRNA_presence	taxonomy_lineage
+genome_name	genome_path	accessions	assembly_software	binning_software	binning_parameters	stats_generation_software	completeness	contamination	genome_coverage	metagenome	co-assembly	broad_environment	local_environment	environmental_medium	rRNA_presence	NCBI_lineage
 coassembly2728_3.fa	./coassembly2728_3.fa.gz	SRR1622827,SRR1622828	MetaSPAdes_v3.15.3	metaWRAP_v1.3	default	EukCC_v2.1.0	98.2	0.2	26.24	skin metagenome	True	human	skin	finger	False	1;131567;2759;33154;4751;451864;5204;452284;1538075;162474;742845;55193;76775
 ERR4647712_megahit_bin.fa	./ERR4647712_megahit_bin.fa.gz	ERR4647712	megahit_v1.2.9	MGnify-genomes-generation-pipeline_v1.0.0	default	CheckM2_v1.0.1	90.81	0.59	14.2	chicken gut metagenome	False	chicken	gut	mucosa	True	d__Bacteria;p__Firmicutes;c__Bacilli;o__Lactobacillales;f__Lactobacillaceae;g__Lactobacillus;s__Lactobacillus crispatus

genomeuploader/__init__.py

@@ -0,0 +1 @@
+__version__ = "2.0.0"