feast-dev · adchia · Jul 11, 2022 · Jul 8, 2022 · Jul 8, 2022
diff --git a/.github/workflows/pr_local_integration_tests.yml b/.github/workflows/pr_local_integration_tests.yml
@@ -0,0 +1,63 @@
+name: pr-local-integration-tests
+# This runs local tests with containerized stubs of online stores. This is the main dev workflow
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - synchronize
+      - labeled
+
+jobs:
+  integration-test-python-local:
+    # all jobs MUST have this if check for 'ok-to-test' or 'approved' for security purposes.
+    if:
+      (github.event.action == 'labeled' && (github.event.label.name == 'approved' || github.event.label.name == 'lgtm' || github.event.label.name == 'ok-to-test')) ||
+      (github.event.action != 'labeled' && (contains(github.event.pull_request.labels.*.name, 'ok-to-test') || contains(github.event.pull_request.labels.*.name, 'approved') || contains(github.event.pull_request.labels.*.name, 'lgtm')))
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [ "3.8" ]
+        os: [ ubuntu-latest ]
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          # pull_request_target runs the workflow in the context of the base repo
+          # as such actions/checkout needs to be explicit configured to retrieve
+          # code from the PR.
+          ref: refs/pull/${{ github.event.pull_request.number }}/merge
+          submodules: recursive
+      - name: Setup Python
+        uses: actions/setup-python@v2
+        id: setup-python
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+      - name: Upgrade pip version
+        run: |
+          pip install --upgrade "pip>=21.3.1,<22.1"
+      - name: Get pip cache dir
+        id: pip-cache
+        run: |
+          echo "::set-output name=dir::$(pip cache dir)"
+      - name: pip cache
+        uses: actions/cache@v2
+        with:
+          path: |
+            ${{ steps.pip-cache.outputs.dir }}
+            /opt/hostedtoolcache/Python
+            /Users/runner/hostedtoolcache/Python
+          key: ${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-pip-${{ hashFiles(format('**/py{0}-ci-requirements.txt', env.PYTHON)) }}
+          restore-keys: |
+            ${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-pip-
+      - name: Install pip-tools
+        run: pip install pip-tools
+      - name: Install dependencies
+        run: make install-python-ci-dependencies
+      - name: Test local integration tests
+        if: ${{ always() }}  # this will guarantee that step won't be canceled and resources won't leak
+        run: make test-python-integration-local
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -133,17 +133,19 @@ make test-python
 
 ### Integration Tests
 There are two sets of tests you can run:
-1. Local integration tests (for faster development)
+1. Local integration tests (for faster development, tests file offline store & key online stores)
 2. Full integration tests (requires cloud environment setups)
 
 #### Local integration tests
-To get local integration tests running, you'll need to have Redis setup:
+For this approach of running tests, you'll need to have docker set up locally: [Get Docker](https://docs.docker.com/get-docker/)
 
-Redis
-1. Install Redis: [Quickstart](https://redis.io/topics/quickstart)
-2. Run `redis-server`
+It leverages a file based offline store to test against emulated versions of Datastore, DynamoDB, and Redis, using ephemeral containers. 
 
-Now run `make test-python-universal-local`
+These tests create new temporary tables / datasets locally only, and they are cleaned up. when the containers are torn down.
+
+```sh
+make test-python-integration-local
+```
 
 #### Full integration tests
 To test across clouds, on top of setting up Redis, you also need GCP / AWS / Snowflake setup.
@@ -166,7 +168,15 @@ To test across clouds, on top of setting up Redis, you also need GCP / AWS / Sno
 2. Modify `RedshiftDataSourceCreator` to use your credentials
 
 **Snowflake**
-- See https://signup.snowflake.com/
+1. See https://signup.snowflake.com/ to setup a trial. 
+2. Then to run successfully, you'll need some environment variables setup:
+```sh
+export SNOWFLAKE_CI_DEPLOYMENT='[snowflake_deployment]'                            
+export SNOWFLAKE_CI_USER='[your user]'
+export SNOWFLAKE_CI_PASSWORD='[your pw]'
+export SNOWFLAKE_CI_ROLE='[your CI role e.g. SYSADMIN]'
+export SNOWFLAKE_CI_WAREHOUSE='[your warehouse]'
+```
 
 Then run `make test-python-integration`. Note that for Snowflake / GCP / AWS, this will create new temporary tables / datasets.
 

diff --git a/Makefile b/Makefile
@@ -68,8 +68,26 @@ test-python:
 test-python-integration:
 	FEAST_USAGE=False IS_TEST=True python -m pytest -n 8 --integration sdk/python/tests
 
+test-python-integration-local:
+	@(docker info > /dev/null 2>&1 && \
+		FEAST_USAGE=False \
+		IS_TEST=True \
+		FEAST_IS_LOCAL_TEST=True \
+		FEAST_LOCAL_ONLINE_CONTAINER=True \
+		python -m pytest -n 8 --integration \
+			-k "not test_apply_entity_integration and \
+				not test_apply_feature_view_integration and \
+				not test_apply_data_source_integration" \
+		sdk/python/tests \
+	) || echo "This script uses Docker, and it isn't running - please start the Docker Daemon and try again!";
+
 test-python-integration-container:
-	FEAST_USAGE=False IS_TEST=True FEAST_LOCAL_ONLINE_CONTAINER=True python -m pytest -n 8 --integration sdk/python/tests
+	@(docker info > /dev/null 2>&1 && \
+		FEAST_USAGE=False \
+		IS_TEST=True \
+		FEAST_LOCAL_ONLINE_CONTAINER=True \
+		python -m pytest -n 8 --integration sdk/python/tests \
+	) || echo "This script uses Docker, and it isn't running - please start the Docker Daemon and try again!";
 
 test-python-universal-contrib:
 	PYTHONPATH='.' \
@@ -104,14 +122,11 @@ test-python-universal-postgres:
 				not test_universal_types" \
 			sdk/python/tests
 
-test-python-universal-local:
-	FEAST_USAGE=False IS_TEST=True FEAST_IS_LOCAL_TEST=True python -m pytest -n 8 --integration sdk/python/tests
-
 test-python-universal:
 	FEAST_USAGE=False IS_TEST=True python -m pytest -n 8 --integration sdk/python/tests
 
 test-python-go-server: compile-go-lib
-	FEAST_USAGE=False IS_TEST=True FEAST_GO_FEATURE_RETRIEVAL=True pytest --integration --goserver sdk/python/tests
+	FEAST_USAGE=False IS_TEST=True pytest --integration --goserver sdk/python/tests
 
 format-python:
 	# Sort

@@ -110,7 +110,10 @@ def pytest_collection_modifyitems(config, items: List[Item]):
             items.append(t)
 
     goserver_tests = [t for t in items if "goserver" in t.keywords]
-    if should_run_goserver:
+    if not should_run_goserver:
+        for t in goserver_tests:
+            items.remove(t)
+    else:
         items.clear()
         for t in goserver_tests:
             items.append(t)

@@ -91,6 +91,7 @@
     "sqlite": ({"type": "sqlite"}, None),
 }
 
+# Only configure Cloud DWH if running full integration tests
 if os.getenv("FEAST_IS_LOCAL_TEST", "False") != "True":
     AVAILABLE_OFFLINE_STORES.extend(
         [
@@ -141,6 +142,7 @@
         }
 
 
+# Replace online stores with emulated online stores if we're running local integration tests
 if os.getenv("FEAST_LOCAL_ONLINE_CONTAINER", "False").lower() == "true":
     replacements: Dict[
         str, Tuple[Union[str, Dict[str, str]], Optional[Type[OnlineStoreCreator]]]

@@ -27,7 +27,7 @@ def create_online_store(self) -> Dict[str, str]:
         self.container.start()
         log_string_to_wait_for = r"\[datastore\] Dev App Server is now running"
         wait_for_logs(
-            container=self.container, predicate=log_string_to_wait_for, timeout=5
+            container=self.container, predicate=log_string_to_wait_for, timeout=10
         )
         exposed_port = self.container.get_exposed_port("8081")
         os.environ[datastore.client.DATASTORE_EMULATOR_HOST] = f"0.0.0.0:{exposed_port}"

@@ -21,7 +21,7 @@ def create_online_store(self) -> Dict[str, str]:
             "Initializing DynamoDB Local with the following configuration:"
         )
         wait_for_logs(
-            container=self.container, predicate=log_string_to_wait_for, timeout=5
+            container=self.container, predicate=log_string_to_wait_for, timeout=10
         )
         exposed_port = self.container.get_exposed_port("8000")
         return {

@@ -19,7 +19,7 @@ def create_online_store(self) -> Dict[str, str]:
             "Initializing Hbase Local with the following configuration:"
         )
         wait_for_logs(
-            container=self.container, predicate=log_string_to_wait_for, timeout=5
+            container=self.container, predicate=log_string_to_wait_for, timeout=10
         )
         exposed_port = self.container.get_exposed_port("9090")
         return {"type": "hbase", "host": "127.0.0.1", "port": exposed_port}

@@ -17,7 +17,7 @@ def create_online_store(self) -> Dict[str, str]:
         self.container.start()
         log_string_to_wait_for = "Ready to accept connections"
         wait_for_logs(
-            container=self.container, predicate=log_string_to_wait_for, timeout=5
+            container=self.container, predicate=log_string_to_wait_for, timeout=10
         )
         exposed_port = self.container.get_exposed_port("6379")
         return {"type": "redis", "connection_string": f"localhost:{exposed_port},db=0"}

@@ -571,7 +571,18 @@ def test_apply_feature_view_integration(test_registry):
 @pytest.mark.parametrize(
     "test_registry", [lazy_fixture("gcs_registry"), lazy_fixture("s3_registry")],
 )
+def test_apply_data_source_integration(test_registry: Registry):
+    run_test_data_source_apply(test_registry)
+
+
+@pytest.mark.parametrize(
+    "test_registry", [lazy_fixture("local_registry")],
+)
 def test_apply_data_source(test_registry: Registry):
+    run_test_data_source_apply(test_registry)
+
+
+def run_test_data_source_apply(test_registry: Registry):
     # Create Feature Views
     batch_source = FileSource(
         name="test_source",