Migrate from hatch to uv

.github/workflows/ci.yaml

@@ -13,50 +13,26 @@ jobs:
       matrix:
         python-version: ["3.11", "3.12"]
 
-    # All steps will run for each Python version inside this container
-    container:
-      image: python:${{ matrix.python-version }}-slim
-
     steps:
-      # Check out the code onto the runner host,
-      # but it's automatically available inside the container.
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
-      - name: Cache pip dependencies
-        uses: actions/cache@v4
+      - name: Install uv and set the Python version
+        uses: astral-sh/setup-uv@v6
         with:
-          path: ~/.cache/pip
-          key: pip-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/pyproject.toml') }}
-          restore-keys: |
-            pip-${{ runner.os }}-${{ matrix.python-version }}-
+          python-version: ${{ matrix.python-version }}
 
-      - name: Install Hatch
-        run: pip install --no-cache-dir hatch
+      - name: Install dependencies
+        run: uv sync --locked
 
-      - name: Cache Hatch environments
-        uses: actions/cache@v4
-        with:
-          path: ~/.local/share/hatch
-          key: hatch-env-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/pyproject.toml') }}
-          restore-keys: |
-            hatch-env-${{ runner.os }}-${{ matrix.python-version }}-
+      - name: Check formatting with Ruff
+        run: uv run ruff format --check
+
+      # TODO(dwnoble): Fix formatting issues in datacommons-schema and uncomment these
+      #- name: Lint with Ruff
+      #  run: uv run ruff check
 
       - name: Run tests
         run: |
           # Enable parallel test execution
-          hatch test --parallel
-        env:
-          # Add environment variables to speed up test execution
-          PYTHONHASHSEED: 0
-          PYTHONUNBUFFERED: 1
-
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-results-${{ matrix.python-version }}
-          path: |
-            .coverage
-            htmlcov/
-          if-no-files-found: error
+          uv run pytest

.pre-commit-config.yaml

@@ -1,17 +1,16 @@
 repos:
   - repo: local
     hooks:
-      # Formats code with ruff via `hatch fmt`
-      - id: ruff-format-hatch-settings
-        name: hatch-ruff
-        language: system
-        entry: hatch fmt
-        types: [python]
-        verbose: true
-      # Runs tests before git pushing
       - id: run-tests
-        name: Run Tests
-        entry: hatch test
+        name: Run tests
+        entry: uv run pytest
         language: system
         pass_filenames: false
         stages: [pre-push]
+      - id: ruff-format
+        name: ruff-format
+        entry: uv run ruff format
+        language: system
+        types: [python]
+        args: []
+        stages: [pre-push]

README.md

@@ -17,18 +17,10 @@ This guide covers setting up a local Data Commons, defining schemas in JSON-LD,
 Before you begin, ensure you have the following installed:
 
 - [Python](https://www.python.org/downloads/) 3.11 or higher
-- [Hatch](https://hatch.pypa.io/latest/) (Python project manager)
+- [uv](https://docs.astral.sh/uv/getting-started/installation/) (Python project manager)
 - A Google Cloud Platform (GCP) project with Cloud Spanner enabled
 - A Cloud Spanner instance and database (using Google Standard SQL) for storing the knowledge graph
 
-### Installing Hatch
-
-You can install Hatch using pip:
-
-```bash
-pip install hatch
-```
-
 ## Setting Up Data Commons
 
 This section will guide you through setting up Data Commons locally and defining your first custom schema and data.
@@ -49,33 +41,22 @@ The repository contains three main components:
 - `datacommons-db`: The database layer for storing and querying data
 - `datacommons-schema`: Schema management and validation tools
 
-#### Create a Hatch environment
+#### Create a virtual environment with uv
 
 ```bash
-hatch env create
+uv sync
 ```
 
 #### Run Tests
 
 Run the test suite to verify your setup:
 
 ```bash
-hatch test
+uv run pytest
 ```
 
 Tests are also run automatically before pushing changes.
 
-#### Enter the Hatch Shell
-
-Activate the project's environment to run local commands. All subsequent commands should be run inside this shell.
-
-```bash
-hatch shell
-```
-
-To exit the shell, type `exit` or press `ctrl+d`
-
-
 #### Configure GCP Spanner Environment Variables
 
 Before starting the server, you need to set up your GCP Spanner environment variables. These are required for the application to connect to your Spanner database. The application will initialize a new database from scratch using these settings:
@@ -90,10 +71,10 @@ Replace the values with your actual GCP project and Spanner instance details. Yo
 
 #### Start Data Commons:
 
-Activate our hatch environment and run the `datacommons-api` command to start a local development server.
+Run the `datacommons-api` command using `uv` to start a local development server.
 
 ```bash
-datacommons-api
+uv run datacommons-api
 ```
 
 This will start the Data Commons API server on port 5000, ready to receive your schema and data.

packages/datacommons-api/src/datacommons/api/app.py → packages/datacommons-api/datacommons_api/app.py

@@ -14,7 +14,7 @@
 
 from fastapi import FastAPI
 
-from datacommons.api.endpoints.routers import node_router
+from datacommons_api.endpoints.routers import node_router
 
 # FastAPI initialization
 app = FastAPI(

packages/datacommons-api/src/datacommons/api/app_cli.py → packages/datacommons-api/datacommons_api/app_cli.py

@@ -15,10 +15,11 @@
 import click
 import uvicorn
 
-from datacommons.api.app import app
-from datacommons.api.core.config import get_config
-from datacommons.api.core.logging import get_logger, setup_logging
-from datacommons.db.session import initialize_db
+from datacommons_api.app import app
+from datacommons_api.core.config import get_config
+from datacommons_api.core.logging import get_logger, setup_logging
+from datacommons_db.session import initialize_db
+
 
 setup_logging()
 logger = get_logger(__name__)
@@ -35,7 +36,11 @@ def main(host: str, port: int, *, reload: bool = False):
 
     # Initialize the database
     logger.info("Initializing database...")
-    initialize_db(config.GCP_PROJECT_ID, config.GCP_SPANNER_INSTANCE_ID, config.GCP_SPANNER_DATABASE_NAME)
+    initialize_db(
+        config.GCP_PROJECT_ID,
+        config.GCP_SPANNER_INSTANCE_ID,
+        config.GCP_SPANNER_DATABASE_NAME,
+    )
     logger.info("Starting API server...")
     uvicorn.run(
         app,

packages/datacommons-api/src/datacommons/api/core/config.py → packages/datacommons-api/datacommons_api/core/config.py

@@ -15,12 +15,16 @@
 import os
 import sys
 
-from datacommons.api.core.logging import get_logger
+from datacommons_api.core.logging import get_logger
 
 logger = get_logger(__name__)
 
 # Required environment variables
-REQUIRED_ENV_VARS = ["GCP_PROJECT_ID", "GCP_SPANNER_INSTANCE_ID", "GCP_SPANNER_DATABASE_NAME"]
+REQUIRED_ENV_VARS = [
+    "GCP_PROJECT_ID",
+    "GCP_SPANNER_INSTANCE_ID",
+    "GCP_SPANNER_DATABASE_NAME",
+]
 
 
 class Config:
@@ -45,7 +49,11 @@ class ProductionConfig(Config):
 
 
 # Configuration dictionary
-config = {"development": DevelopmentConfig, "production": ProductionConfig, "default": DevelopmentConfig}
+config = {
+    "development": DevelopmentConfig,
+    "production": ProductionConfig,
+    "default": DevelopmentConfig,
+}
 
 
 def validate_config_or_exit(config: Config) -> None:

packages/datacommons-api/src/datacommons/api/core/logging.py → packages/datacommons-api/datacommons_api/core/logging.py

@@ -23,12 +23,12 @@
 Usage:
 
 ```python
-from datacommons.api.core.logging import get_logger
+from datacommons_api.core.logging import get_logger
 
 logger = get_logger(__name__)
 
 logger.info("Hello, world!")
-# Output: "INFO [datacommons.api.core.logging] [2021-01-01 12:00:00+0000] Hello, world!"
+# Output: "INFO [datacommons_api.core.logging] [2021-01-01 12:00:00+0000] Hello, world!"
 ```
 
 """

packages/datacommons-api/src/datacommons/api/endpoints/dependencies.py → packages/datacommons-api/datacommons_api/endpoints/dependencies.py

@@ -15,9 +15,9 @@
 
 from collections.abc import Generator
 
-from datacommons.api.core.config import get_config
-from datacommons.api.services.graph_service import GraphService
-from datacommons.db.session import get_session
+from datacommons_api.core.config import get_config
+from datacommons_api.services.graph_service import GraphService
+from datacommons_db.session import get_session
 
 
 def with_graph_service() -> Generator[GraphService, None, None]:
@@ -28,7 +28,11 @@ def with_graph_service() -> Generator[GraphService, None, None]:
       GraphService: A GraphService instance
     """
     config = get_config()
-    db = get_session(config.GCP_PROJECT_ID, config.GCP_SPANNER_INSTANCE_ID, config.GCP_SPANNER_DATABASE_NAME)
+    db = get_session(
+        config.GCP_PROJECT_ID,
+        config.GCP_SPANNER_INSTANCE_ID,
+        config.GCP_SPANNER_DATABASE_NAME,
+    )
     graph_service = GraphService(db)
     try:
         yield graph_service

packages/datacommons-api/src/datacommons/api/endpoints/routers/node_router.py → packages/datacommons-api/datacommons_api/endpoints/routers/node_router.py

@@ -16,12 +16,12 @@
 
 from fastapi import APIRouter, Depends, Query
 
-from datacommons.api.core.constants import DEFAULT_NODE_FETCH_LIMIT
-from datacommons.api.core.logging import get_logger
-from datacommons.api.endpoints.dependencies import with_graph_service
-from datacommons.api.endpoints.responses import UpdateResponse
-from datacommons.api.services.graph_service import GraphService
-from datacommons.schema.models.jsonld import JSONLDDocument
+from datacommons_api.core.constants import DEFAULT_NODE_FETCH_LIMIT
+from datacommons_api.core.logging import get_logger
+from datacommons_api.endpoints.dependencies import with_graph_service
+from datacommons_api.endpoints.responses import UpdateResponse
+from datacommons_api.services.graph_service import GraphService
+from datacommons_schema.models.jsonld import JSONLDDocument
 
 logger = get_logger(__name__)
 
@@ -32,7 +32,9 @@
 @router.get("/nodes/", response_model=JSONLDDocument, response_model_exclude_none=True)
 def get_nodes(
     limit: int = DEFAULT_NODE_FETCH_LIMIT,
-    type_filter: Annotated[list[str] | None, Query(alias="type", description="Zero or more types")] = None,
+    type_filter: Annotated[
+        list[str] | None, Query(alias="type", description="Zero or more types")
+    ] = None,
     graph_service: Annotated[GraphService, Depends(with_graph_service)] = None,
 ) -> JSONLDDocument:
     """
@@ -44,12 +46,15 @@ def get_nodes(
 
 @router.post("/nodes/", response_model=UpdateResponse, response_model_exclude_none=True)
 def insert_nodes(
-    jsonld: JSONLDDocument, graph_service: Annotated[GraphService, Depends(with_graph_service)] = None
+    jsonld: JSONLDDocument,
+    graph_service: Annotated[GraphService, Depends(with_graph_service)] = None,
 ) -> UpdateResponse:
     """Insert a JSON-LD document into the database"""
     try:
         graph_service.insert_graph_nodes(jsonld)
-        return UpdateResponse(success=True, message="Inserted %d nodes successfully" % len(jsonld.graph))
+        return UpdateResponse(
+            success=True, message="Inserted %d nodes successfully" % len(jsonld.graph)
+        )
     except Exception as e:
         logger.exception("Error inserting nodes")
         return UpdateResponse(success=False, message=str(e))