Dockerize DataLibrary pipelin

.github/workflows/python-package.yml

@@ -1,40 +1,31 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
-
+---
 name: Python package
-
 on:
-  push:
-    branches: [ "master" ]
   pull_request:
-    branches: [ "master" ]
+    branches:
+      - master
+
+permissions:
+  contents: write
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
     strategy:
-      fail-fast: false
       matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
-
+        python-version:
+          - "3.11"
+          - "3.12"
+          - "3.13"
+          - "3.14"
     steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with pytest
-      run: |
-        pytest
+      - uses: actions/checkout@v6
+      - name: Install uv and set Python version
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: uv sync --dev
+      - name: Lint with Ruff
+        run: |
+          uv run ruff check . --fix

Dockerfile

@@ -0,0 +1,34 @@
+# syntax=docker/dockerfile:1
+FROM python:3.11-slim
+
+# Install uv from official image
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
+# System dependencies + SQL Server ODBC driver
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl gnupg2 ca-certificates unixodbc-dev  build-essential   && \
+    curl -fsSL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor -o /usr/share/keyrings/microsoft-prod.gpg && \
+    echo "deb [signed-by=/usr/share/keyrings/microsoft-prod.gpg] https://packages.microsoft.com/debian/12/prod bookworm main" > /etc/apt/sources.list.d/mssql-release.list && \
+    apt-get update && \
+    ACCEPT_EULA=Y apt-get install -y --no-install-recommends msodbcsql18 && \
+    DRIVER_PATH="$(ls /opt/microsoft/msodbcsql18/lib64/libmsodbcsql-18*.so* | head -n 1)" && \
+    printf "[SQL Server]\nDescription=Microsoft ODBC Driver 18 for SQL Server (alias)\nDriver=%s\nUsageCount=1\n" "$DRIVER_PATH" >> /etc/odbcinst.ini && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+ENV UV_PYTHON=python3.11
+ENV UV_SYSTEM_PYTHON=1
+
+# Install dependencies first for better layer caching
+COPY pyproject.toml ./
+COPY uv.lock ./
+RUN uv sync --frozen
+
+# Copy project files
+COPY . .
+
+# Runtime default environment for main.py arg
+ENV APP_ENV=hpc_dev
+
+CMD ["sh", "-c", "uv run python main.py --db"]

Makefile

@@ -0,0 +1,101 @@
+#* Variables
+SHELL := /usr/bin/env bash
+PYTHON := python
+PYTHONPATH := `pwd`/src
+
+#* INSTALL
+
+#* Install dependencies and package
+.PHONY: install
+install:
+	uv sync --all-extras --dev --frozen
+
+#* LINTING
+
+#* Check formatting
+.PHONY: check-codestyle
+check-codestyle:
+	uv run isort --diff --check-only --settings-path pyproject.toml ./
+	uv run black --diff --check --config pyproject.toml ./
+	uv run ruff check .
+
+#* Fix formatting
+.PHONY: codestyle
+codestyle:
+	uv run isort --settings-path pyproject.toml ./
+	uv run black --fast --config pyproject.toml ./
+	uv run ruff check . --fix
+
+# .PHONY: test
+# test:
+# 	uv run pytest tests/unit --cov=data_bridges_knots --cov-report=html
+# 	uv run coverage-badge -o assets/images/coverage.svg -f
+
+#* Typing
+.PHONY: mypy
+mypy:
+	uv run mypy --config-file pyproject.toml ./
+
+# .PHONY: check-safety
+# check-safety:
+# 	uv run bandit -r src
+
+#* All in one
+.PHONY: lint
+lint: test check-codestyle mypy
+
+#* DOCS
+
+# #* Documentation
+# # Test 
+# .PHONY: docs-test
+# docs-test:
+# 	uv run python -m doctest data_bridges_knots/client.py
+
+#* DOCKER
+
+# Example: make docker-build VERSION=latest
+# Example: make docker-build IMAGE=some_name VERSION=0.1.0
+.PHONY: docker-build
+docker-build:
+	@echo Building docker $(IMAGE):$(VERSION) ...
+	docker build \
+		-t $(IMAGE):$(VERSION) . \
+		-f ./docker/Dockerfile --no-cache
+
+# Example: make docker-remove VERSION=latest
+# Example: make docker-remove IMAGE=some_name VERSION=0.1.0
+.PHONY: docker-remove
+docker-remove:
+	@echo Removing docker $(IMAGE):$(VERSION) ...
+	docker rmi -f $(IMAGE):$(VERSION)
+
+
+#* CLEANING
+
+.PHONY: pycache-remove
+pycache-remove:
+	find . | grep -E "(__pycache__|\.pyc|\.pyo$$)" | xargs rm -rf
+
+.PHONY: dsstore-remove
+dsstore-remove:
+	find . | grep -E ".DS_Store" | xargs rm -rf
+
+.PHONY: mypycache-remove
+mypycache-remove:
+	find . | grep -E ".mypy_cache" | xargs rm -rf
+
+.PHONY: ipynbcheckpoints-remove
+ipynbcheckpoints-remove:
+	find . | grep -E ".ipynb_checkpoints" | xargs rm -rf
+
+.PHONY: pytestcache-remove
+pytestcache-remove:
+	find . | grep -E ".pytest_cache" | xargs rm -rf
+
+.PHONY: build-remove
+build-remove:
+	rm -rf build/
+
+.PHONY: cleanup
+cleanup: pycache-remove dsstore-remove mypycache-remove ipynbcheckpoints-remove pytestcache-remove

README.md

@@ -21,7 +21,7 @@ This is a Python CLI tool to query the [WFP Data Library API](https://datalib.va
 - Packages listed in `requirements.txt`
 
 ## Documentation
-For more details on the Data Library API endpoints, see the [API documentation](http://docs.ckan.org/en/2.9/api/).
+For more details on the Data Library API endpoints, see the [API documentation](http://docs.ckan.org/en/2.11/api/).
 
 ## Contributing
 Contributions to add more API querying/exporting functionality are welcome!

datalibrary/__init__.py

@@ -1,3 +1,9 @@
-from .extract import DataLibrary, get_survey_data, get_user_data, get_member_data, get_data
+from .extract import (
+    DataLibrary,
+    get_data,
+    get_member_data,
+    get_survey_data,
+    get_user_data,
+)
 
-__all__ = ["DataLibrary"]
+__all__ = ["DataLibrary"]