Migrate project from Poetry to uv (#32)

* chore: migrate project from Poetry to uv

* ci: switch workflows to uv

Author: allisonwang-db

.github/workflows/ci.yml

@@ -17,37 +17,24 @@ jobs:
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
-      
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-        
-    - name: Install Poetry
-      uses: snok/install-poetry@v1.3.4
-      with:
-        version: latest
-        virtualenvs-create: true
-        virtualenvs-in-project: true
-        
-    - name: Load cached venv
-      id: cached-poetry-dependencies
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v1
+
+    - name: Ensure Python ${{ matrix.python-version }}
+      run: uv python install ${{ matrix.python-version }}
+
+    - name: Cache virtual environment
+      id: cache-uv-venv
       uses: actions/cache@v4
       with:
         path: .venv
-        key: venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
-        
-    - name: Install dependencies
-      if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-      run: poetry install --no-interaction --no-root --extras "all"
-      
-    - name: Install project
-      run: poetry install --no-interaction --extras "all"
-      
-    - name: Run tests
-      run: poetry run pytest tests/ -v
-      
+        key: uv-venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('uv.lock') }}
+
+    - name: Sync dependencies
+      run: uv sync --all-extras --python ${{ matrix.python-version }}
+
     - name: Run tests with coverage
       run: |
-        poetry run pytest tests/ --cov=pyspark_datasources --cov-report=xml --cov-report=term-missing
+        uv run pytest tests/ --cov=pyspark_datasources --cov-report=xml --cov-report=term-missing
   

.github/workflows/docs.yml

@@ -29,38 +29,25 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-        
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-          
-      - name: Install Poetry
-        run: |
-          curl -sSL https://install.python-poetry.org | python - -y
-          echo "$HOME/.local/bin" >> $GITHUB_PATH
-        
-      - name: Configure Poetry
-        run: |
-          poetry config virtualenvs.create true
-          poetry config virtualenvs.in-project true
-          
-      - name: Load cached venv
-        id: cached-poetry-dependencies
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v1
+
+      - name: Ensure Python 3.11
+        run: uv python install 3.11
+
+      - name: Cache virtual environment
+        id: cache-uv-venv
         uses: actions/cache@v4
         with:
           path: .venv
-          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
-          
-      - name: Install dependencies
-        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction --no-root
-        
-      - name: Install project
-        run: poetry install --no-interaction
-        
+          key: uv-venv-${{ runner.os }}-3.11-${{ hashFiles('uv.lock') }}
+
+      - name: Sync dependencies
+        run: uv sync --python 3.11 --group dev
+
       - name: Build MkDocs
-        run: poetry run mkdocs build
+        run: uv run mkdocs build
 
       - name: Setup Pages
         uses: actions/configure-pages@v5

contributing/DEVELOPMENT.md

@@ -4,7 +4,7 @@
 
 ### Prerequisites
 - Python 3.9-3.12
-- Poetry for dependency management
+- [uv](https://docs.astral.sh/uv/) for dependency management
 - Apache Spark 4.0+ (or Databricks Runtime 15.4 LTS+)
 
 ### Installation
@@ -14,14 +14,14 @@
 git clone https://github.com/allisonwang-db/pyspark-data-sources.git
 cd pyspark-data-sources
 
-# Install dependencies
-poetry install
+# Install dependencies (creates .venv/ automatically)
+uv sync
 
 # Install with all optional dependencies
-poetry install --extras all
+uv sync --extra all
 
-# Activate virtual environment
-poetry shell
+# Activate virtual environment (optional)
+source .venv/bin/activate
 ```
 
 ### macOS Setup
@@ -84,27 +84,27 @@ This project uses [Ruff](https://github.com/astral-sh/ruff) for code formatting
 
 ```bash
 # Format code
-poetry run ruff format .
+uv run ruff format .
 
 # Run linter
-poetry run ruff check .
+uv run ruff check .
 
 # Run linter with auto-fix
-poetry run ruff check . --fix
+uv run ruff check . --fix
 
 # Check specific file
-poetry run ruff check pyspark_datasources/fake.py
+uv run ruff check pyspark_datasources/fake.py
 ```
 
 ### Pre-commit Hooks (Optional)
 
 ```bash
 # Install pre-commit hooks
-poetry add --group dev pre-commit
-pre-commit install
+uv add --dev pre-commit
+uv run pre-commit install
 
 # Run manually
-pre-commit run --all-files
+uv run pre-commit run --all-files
 ```
 
 ## Documentation
@@ -245,24 +245,24 @@ Add your data source to the table in README.md with examples.
 
 ```bash
 # Add required dependency
-poetry add requests
+uv add requests
 
 # Add optional dependency
-poetry add --optional faker
+uv add --optional faker faker
 
 # Add dev dependency
-poetry add --group dev pytest-cov
+uv add --dev pytest-cov
 
 # Update dependencies
-poetry update
+uv sync --upgrade
 ```
 
 ### Managing Extras
 
 Edit `pyproject.toml` to add optional dependency groups:
 
 ```toml
-[tool.poetry.extras]
+[project.optional-dependencies]
 mynewsource = ["special-library"]
 all = ["faker", "datasets", "special-library", ...]
 ```
@@ -363,17 +363,18 @@ import os
 os.environ["OBJC_DISABLE_INITIALIZE_FORK_SAFETY"] = "YES"
 ```
 
-### Poetry Issues
+### uv Troubleshooting
 
 ```bash
 # Clear cache
-poetry cache clear pypi --all
+uv cache clean
 
-# Update lock file
-poetry lock --no-update
+# Check that the lockfile matches pyproject
+uv lock --check
 
-# Reinstall
-poetry install --remove-untracked
+# Recreate the virtual environment
+rm -rf .venv
+uv sync
 ```
 
 ### Spark Session Issues