feat: refactored adding support for RETL and Profiles

.github/workflows/test.yaml

@@ -19,6 +19,13 @@ jobs:
     - name: Install dependencies
       run: |
         pip3 install -r requirements.txt
-    - name: Test with unittest
+    - name: Test with pytest
       run: |
+        pip3 install pytest-cov
         make test
+    - name: Upload Coverage to Codecov
+      uses: codecov/codecov-action@v4
+      with:
+          fail_ci_if_error: true
+          files: ./coverage.xml
+          token: ${{ secrets.CODECOV_TOKEN }}

.gitignore

@@ -1,6 +1,7 @@
 *.egg-info
 **/__pycache__
 .vscode
+.venv/
 
 
 # Distribution / packaging
@@ -36,4 +37,4 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-cover/
+cover/

Makefile

@@ -1,3 +1,3 @@
 .PHONY: test
 test:
-	python3 -m unittest discover -s rudder_airflow_provider/test 
+	pytest --cov=rudder_airflow_provider rudder_airflow_provider/test --cov-report=xml

examples/profiles_sample_dag.py

@@ -0,0 +1,34 @@
+from datetime import datetime, timedelta
+
+from airflow import DAG
+
+from rudder_airflow_provider.operators.rudderstack import RudderstackProfilesOperator
+
+default_args = {
+    "owner": "airflow",
+    "depends_on_past": False,
+    "email": ["[email protected]"],
+    "email_on_failure": False,
+    "email_on_retry": False,
+    "retries": 1,
+    "retry_delay": timedelta(minutes=5),
+}
+
+with DAG(
+    "rudderstack-profiles-sample",
+    default_args=default_args,
+    description="A simple tutorial DAG",
+    schedule_interval=timedelta(days=1),
+    start_date=datetime(2021, 1, 1),
+    catchup=False,
+    tags=["rs-profiles"],
+) as dag:
+    # profile_id is template field
+    rs_operator = RudderstackProfilesOperator(
+        profile_id="{{ var.value.profile_id }}",
+        task_id="<replace task id>",
+        connection_id="<rudderstack api connection id>",
+    )
+
+if __name__ == "__main__":
+    dag.test()

examples/retl_sample.dag.py → examples/retl_sample_dag.py

@@ -5,30 +5,31 @@
 from rudder_airflow_provider.operators.rudderstack import RudderstackRETLOperator
 
 default_args = {
-    'owner': 'airflow',
-    'depends_on_past': False,
-    'email': ['[email protected]'],
-    'email_on_failure': False,
-    'email_on_retry': False,
-    'retries': 1,
-    'retry_delay': timedelta(minutes=5)
+    "owner": "airflow",
+    "depends_on_past": False,
+    "email": ["[email protected]"],
+    "email_on_failure": False,
+    "email_on_retry": False,
+    "retries": 1,
+    "retry_delay": timedelta(minutes=5),
 }
 
-with DAG('rudderstack-sample',
+with DAG(
+    "rudderstack-sample",
     default_args=default_args,
-    description='A simple tutorial DAG',
+    description="A simple tutorial DAG",
     schedule_interval=timedelta(days=1),
     start_date=datetime(2021, 1, 1),
     catchup=False,
-    tags=['rs']) as dag:
+    tags=["rs"],
+) as dag:
     # retl_connection_id, sync_type are template fields
     rs_operator = RudderstackRETLOperator(
         retl_connection_id="{{ var.value.retl_connection_id }}",
-        task_id='<replace task id>',
-        connection_id='<rudderstack api connection id>',
+        task_id="<replace task id>",
+        connection_id="<rudderstack api connection id>",
         sync_type="{{ var.value.sync_type }}",
-        wait_for_completion=True
     )
 
 if __name__ == "__main__":
-    dag.test()
+    dag.test()

pyproject.toml

@@ -4,3 +4,35 @@ requires = [
     "wheel"
 ]
 build-backend = "setuptools.build_meta"
+
+[build-system]
+requires = [
+    "setuptools >= 61.0",
+    "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "rudderstack-airflow-provider"
+version = "2.0.0"
+readme = "README.md"
+license = {file = "LICENSE"}
+description = "Apache airflow provider for managing Reverse ETL syncs and Profiles runs in RudderStack."
+keywords = [ "airflow", "orchestration", "rudderstack"]
+classifiers = [
+    "Framework :: Apache Airflow",
+    "Framework :: Apache Airflow :: Provider",
+]
+dependencies = [
+    "apache-airflow",
+    "pytest",
+    "requests",
+    "responses",
+    "setuptools"
+]
+requires-python = ">= 3.6"
+
+[tool.setuptools.packages.find]
+exclude = *test*
+
+[project.entry-points.apache_airflow_provider]
+provider_info = "sample_provider.__init__:get_provider_info"

requirements.txt

@@ -1,3 +1,4 @@
-apache-airflow == 2.8.0
-requests == 2.28.2
+apache-airflow == 2.10.0
+requests == 2.32.3
 setuptools == 65.5.1 # not directly required, pinned by Snyk to avoid a vulnerability
+pytest==7.3.1

rudder_airflow_provider/__init__.py

@@ -1,6 +1,6 @@
 def get_provider_info():
     return {
-        'package-name': 'rudderstack-airflow-provider',
-        'name': 'rudderstack-airflow-provider',
-        'description': 'Apache airflow provider for Rudderstack'
+        "package-name": "rudderstack-airflow-provider",
+        "name": "rudderstack-airflow-provider",
+        "description": "Apache airflow provider for Rudderstack",
     }