Merge pull request #2 from alliance-genome/KANBAN-504_seq-retrieval

KANBAN-504 seq retrieval core functionality

.github/workflows/PR-validation.yml

@@ -0,0 +1,66 @@
+name: PR validation
+on:
+  pull_request:
+    types: [synchronize, opened, reopened, edited]
+    branches:
+      - main
+jobs:
+  pipeline-seq-retrieval-container-image-build:
+    name: pipeline/seq_retrieval container-image build
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./pipeline/seq_retrieval/
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          sparse-checkout: |
+            pipeline/seq_retrieval/
+      - name: Build container image
+        run: |
+          make container-image
+  pipeline-seq-retrieval-python-typing-check:
+    name: pipeline/seq_retrieval python typing check
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./pipeline/seq_retrieval/
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          sparse-checkout: |
+            pipeline/seq_retrieval/
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Check python typing
+        run: |
+          make check-python-typing
+  pipeline-seq-retrieval-python-style-check:
+    name: pipeline/seq_retrieval python style check
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./pipeline/seq_retrieval/
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          sparse-checkout: |
+            pipeline/seq_retrieval/
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Check python style
+        run: |
+          make check-python-style
+  #TODO: add unit testing
+  #TODO: add integration testing

.gitignore

@@ -1,12 +1,13 @@
-# Byte-compiled / optimized / DLL files
+# Python files
+## Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
 *$py.class
 
-# C extensions
+## C extensions
 *.so
 
-# Distribution / packaging
+## Distribution / packaging
 .Python
 build/
 develop-eggs/
@@ -26,17 +27,17 @@ share/python-wheels/
 *.egg
 MANIFEST
 
-# PyInstaller
+## 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
+## package installer logs
 pip-log.txt
 pip-delete-this-directory.txt
 
-# Unit test / coverage reports
+## Unit test / coverage reports
 htmlcov/
 .tox/
 .nox/
@@ -51,75 +52,75 @@ coverage.xml
 .pytest_cache/
 cover/
 
-# Translations
+## Translations
 *.mo
 *.pot
 
-# Django stuff:
+## Django stuff:
 *.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
 
-# Flask stuff:
+## Flask stuff:
 instance/
 .webassets-cache
 
-# Scrapy stuff:
+## Scrapy stuff:
 .scrapy
 
-# Sphinx documentation
+## Sphinx documentation
 docs/_build/
 
-# PyBuilder
+## PyBuilder
 .pybuilder/
 target/
 
-# Jupyter Notebook
+## Jupyter Notebook
 .ipynb_checkpoints
 
-# IPython
+## IPython
 profile_default/
 ipython_config.py
 
-# pyenv
+## pyenv
 #   For a library or package, you might want to ignore these files since the code is
 #   intended to run in multiple environments; otherwise, check them in:
 # .python-version
 
-# pipenv
+## pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 #   install all needed dependencies.
 #Pipfile.lock
 
-# poetry
+## poetry
 #   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
 #poetry.lock
 
-# pdm
+## pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
 #pdm.lock
 #   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
 #   in version control.
 #   https://pdm.fming.dev/#use-with-ide
 .pdm.toml
 
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+## PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 __pypackages__/
 
-# Celery stuff
+## Celery stuff
 celerybeat-schedule
 celerybeat.pid
 
-# SageMath parsed files
+## SageMath parsed files
 *.sage.py
 
-# Environments
+## Environments
 .env
 .venv
 env/
@@ -128,33 +129,36 @@ ENV/
 env.bak/
 venv.bak/
 
-# Spyder project settings
+## Spyder project settings
 .spyderproject
 .spyproject
 
-# Rope project settings
+## Rope project settings
 .ropeproject
 
-# mkdocs documentation
+## mkdocs documentation
 /site
 
-# mypy
+## mypy
 .mypy_cache/
 .dmypy.json
 dmypy.json
 
-# Pyre type checker
+## Pyre type checker
 .pyre/
 
-# pytype static type analyzer
+## pytype static type analyzer
 .pytype/
 
-# Cython debug symbols
+## Cython debug symbols
 cython_debug/
 
-# PyCharm
+## PyCharm
 #  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# VS Code
+.vscode/

pipeline/seq_retrieval/.flake8

@@ -0,0 +1,6 @@
+[flake8]
+ignore = E203, E266, E501, F401, W503, E501
+max-complexity = 18
+select = B,C,E,F,W,T4
+exclude = venv
+per-file-ignores = __init__.py:F401

pipeline/seq_retrieval/Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12-alpine
+
+WORKDIR /usr/src/app
+
+RUN apk add --no-cache build-base zlib-dev bzip2-dev xz-dev
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY src/ ./
+
+ENTRYPOINT [ "python", "main.py"]
+CMD [ "--help" ]

pipeline/seq_retrieval/Makefile

@@ -0,0 +1,34 @@
+.PHONY: check-venv-active check-python-typing
+
+container-image:
+	docker build -t agr_pavi/seq_retrieval .
+python-dependencies:
+	pip install -r requirements.txt
+
+python-dependencies-update:
+	pip install -U -r requirements.txt
+
+python-test-dependencies:
+	pip install -r tests/requirements.txt
+
+check-python-typing: python-dependencies python-test-dependencies
+	mypy --install-types --non-interactive src/main.py
+
+check-python-style: python-dependencies python-test-dependencies
+	flake8 ./
+
+check-venv-active:
+ifeq ($(VIRTUAL_ENV),)
+	@echo 'No active python virtual environment found.'\
+		  'Please active the virtual environment first by running `source venv/bin/activate`,'\
+		  'or read README.md for instructions on how to set up a new one.'
+	@exit 1
+else
+	@:
+endif
+
+python-dependencies-dev: check-venv-active python-dependencies
+
+python-dependencies-dev-update: check-venv-active python-dependencies-update
+
+check-python-typing-dev: check-venv-active check-python-typing