Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support impersonation service account parameter for Dataflow runner #23961

Merged
merged 2 commits into from
May 31, 2022
Merged

Support impersonation service account parameter for Dataflow runner #23961

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6f3aa92
Support impersonation service account parameter for Dataflow runner
May 27, 2022
df4eec6
Extension of the tests for apache beam related to DataflowRunner
May 27, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions airflow/providers/apache/beam/operators/beam.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@ class BeamDataflowMixin(metaclass=ABCMeta):
dataflow_config: DataflowConfiguration
gcp_conn_id: str
delegate_to: Optional[str]
dataflow_support_impersonation: bool = True

def _set_dataflow(
self,
Expand Down Expand Up @@ -91,6 +92,13 @@ def __get_dataflow_pipeline_options(
pipeline_options[job_name_key] = job_name
if self.dataflow_config.service_account:
pipeline_options["serviceAccount"] = self.dataflow_config.service_account
if self.dataflow_support_impersonation and self.dataflow_config.impersonation_chain:
lwyszomi marked this conversation as resolved.
Show resolved Hide resolved
if isinstance(self.dataflow_config.impersonation_chain, list):
pipeline_options["impersonateServiceAccount"] = ",".join(
self.dataflow_config.impersonation_chain
)
else:
pipeline_options["impersonateServiceAccount"] = self.dataflow_config.impersonation_chain
uranusjr marked this conversation as resolved.
Show resolved Hide resolved
pipeline_options["project"] = self.dataflow_config.project_id
pipeline_options["region"] = self.dataflow_config.location
pipeline_options.setdefault("labels", {}).update(
Expand Down Expand Up @@ -549,6 +557,13 @@ def __init__(
**kwargs,
)

if self.dataflow_config.impersonation_chain:
self.log.info(
"Impersonation chain parameter is not supported for Apache Beam GO SDK and will be skipped "
"in the execution"
)
self.dataflow_support_impersonation = False

self.go_file = go_file
self.should_init_go_module = False
self.pipeline_options.setdefault("labels", {}).update(
Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,7 +205,7 @@ def write_version(filename: str = os.path.join(*[my_dir, "airflow", "git_version
'xmltodict<0.13.0',
]
apache_beam = [
'apache-beam>=2.33.0',
'apache-beam>=2.39.0',
]
arangodb = ['python-arango>=7.3.2']
asana = ['asana>=0.10']
Expand Down
9 changes: 6 additions & 3 deletions tests/providers/apache/beam/operators/test_beam.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@
'output': 'gs://test/output',
'labels': {'foo': 'bar', 'airflow-version': TEST_VERSION},
}
TEST_IMPERSONATION_ACCOUNT = "test@impersonation.com"


class TestBeamRunPythonPipelineOperator(unittest.TestCase):
Expand Down Expand Up @@ -104,7 +105,7 @@ def test_exec_dataflow_runner(self, gcs_hook, dataflow_hook_mock, beam_hook_mock
"""Test DataflowHook is created and the right args are passed to
start_python_dataflow.
"""
dataflow_config = DataflowConfiguration()
dataflow_config = DataflowConfiguration(impersonation_chain=TEST_IMPERSONATION_ACCOUNT)
self.operator.runner = "DataflowRunner"
self.operator.dataflow_config = dataflow_config
gcs_provide_file = gcs_hook.return_value.provide_file
Expand All @@ -126,6 +127,7 @@ def test_exec_dataflow_runner(self, gcs_hook, dataflow_hook_mock, beam_hook_mock
'output': 'gs://test/output',
'labels': {'foo': 'bar', 'airflow-version': TEST_VERSION},
'region': 'us-central1',
'impersonate_service_account': TEST_IMPERSONATION_ACCOUNT,
}
gcs_provide_file.assert_called_once_with(object_url=PY_FILE)
persist_link_mock.assert_called_once_with(
Expand Down Expand Up @@ -222,7 +224,7 @@ def test_exec_dataflow_runner(self, gcs_hook, dataflow_hook_mock, beam_hook_mock
"""Test DataflowHook is created and the right args are passed to
start_java_dataflow.
"""
dataflow_config = DataflowConfiguration()
dataflow_config = DataflowConfiguration(impersonation_chain="test@impersonation.com")
self.operator.runner = "DataflowRunner"
self.operator.dataflow_config = dataflow_config
gcs_provide_file = gcs_hook.return_value.provide_file
Expand All @@ -247,6 +249,7 @@ def test_exec_dataflow_runner(self, gcs_hook, dataflow_hook_mock, beam_hook_mock
'region': 'us-central1',
'labels': {'foo': 'bar', 'airflow-version': TEST_VERSION},
'output': 'gs://test/output',
'impersonateServiceAccount': TEST_IMPERSONATION_ACCOUNT,
}
persist_link_mock.assert_called_once_with(
self.operator,
Expand Down Expand Up @@ -373,7 +376,7 @@ def test_exec_dataflow_runner(self, gcs_hook, dataflow_hook_mock, beam_hook_mock
"""Test DataflowHook is created and the right args are passed to
start_go_dataflow.
"""
dataflow_config = DataflowConfiguration()
dataflow_config = DataflowConfiguration(impersonation_chain="test@impersonation.com")
self.operator.runner = "DataflowRunner"
self.operator.dataflow_config = dataflow_config
gcs_provide_file = gcs_hook.return_value.provide_file
Expand Down