def construct_flow_workunit(
self, connector: ConnectorManifest
) -> Iterable[MetadataWorkUnit]:
connector_name = connector.name
connector_type = connector.type
connector_class = connector.config.get("connector.class")
# connector_url = connector.url # NOTE: this will expose connector credential when used
flow_urn = builder.make_data_flow_urn(
"kafka-connect", connector_name, self.config.env
)
flow_property_bag: Optional[Dict[str, str]] = None
mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataFlowSnapshotClass(
urn=flow_urn,
aspects=[
models.DataFlowInfoClass(
name=connector_name,
description=f"{connector_type.capitalize()} connector using `{connector_class}` plugin.",
customProperties=flow_property_bag,
# externalUrl=connector_url, # NOTE: this will expose connector credential when used
),
# ownership,
# tags,
],
)
)
for c in [connector_name]:
wu = MetadataWorkUnit(id=c, mce=mce)
self.report.report_workunit(wu)
yield wu
def test_type_error() -> None:
dataflow = models.DataFlowSnapshotClass(
urn=mce_builder.make_data_flow_urn(orchestrator="argo",
flow_id="42",
cluster="DEV"),
aspects=[
models.DataFlowInfoClass(
name="hello_datahub",
description="Hello Datahub",
externalUrl="http://example.com",
# This is a type error - custom properties should be a Dict[str, str].
customProperties={"x": 1}, # type: ignore
)
],
)
with pytest.raises(avrojson.AvroTypeException):
dataflow.to_obj()
def send_lineage_to_datahub(
config: DatahubBasicLineageConfig,
operator: "BaseOperator",
inlets: List[_Entity],
outlets: List[_Entity],
context: Dict,
) -> None:
# This is necessary to avoid issues with circular imports.
from airflow.serialization.serialized_objects import (
SerializedBaseOperator,
SerializedDAG,
)
dag: "DAG" = context["dag"]
task: "BaseOperator" = context["task"]
# resolve URNs for upstream nodes in subdags upstream of the current task.
upstream_subdag_task_urns: List[str] = []
for upstream_task_id in task.upstream_task_ids:
upstream_task = dag.task_dict[upstream_task_id]
# if upstream task is not a subdag, then skip it
if upstream_task.subdag is None:
continue
# else, link the leaf tasks of the upstream subdag as upstream tasks
upstream_subdag = upstream_task.subdag
upstream_subdag_flow_urn = builder.make_data_flow_urn(
"airflow", upstream_subdag.dag_id, config.cluster)
for upstream_subdag_task_id in upstream_subdag.task_dict:
upstream_subdag_task = upstream_subdag.task_dict[
upstream_subdag_task_id]
upstream_subdag_task_urn = builder.make_data_job_urn_with_flow(
upstream_subdag_flow_urn, upstream_subdag_task_id)
# if subdag task is a leaf task, then link it as an upstream task
if len(upstream_subdag_task._downstream_task_ids) == 0:
upstream_subdag_task_urns.append(upstream_subdag_task_urn)
# resolve URNs for upstream nodes that trigger the subdag containing the current task.
# (if it is in a subdag at all)
upstream_subdag_triggers: List[str] = []
# subdags are always named with 'parent.child' style or Airflow won't run them
# add connection from subdag trigger(s) if subdag task has no upstreams
if (dag.is_subdag and dag.parent_dag is not None
and len(task._upstream_task_ids) == 0):
# filter through the parent dag's tasks and find the subdag trigger(s)
subdags = [
x for x in dag.parent_dag.task_dict.values()
if x.subdag is not None
]
matched_subdags = [
x for x in subdags
if getattr(getattr(x, "subdag"), "dag_id") == dag.dag_id
]
# id of the task containing the subdag
subdag_task_id = matched_subdags[0].task_id
parent_dag_urn = builder.make_data_flow_urn("airflow",
dag.parent_dag.dag_id,
config.cluster)
# iterate through the parent dag's tasks and find the ones that trigger the subdag
for upstream_task_id in dag.parent_dag.task_dict:
upstream_task = dag.parent_dag.task_dict[upstream_task_id]
upstream_task_urn = builder.make_data_job_urn_with_flow(
parent_dag_urn, upstream_task_id)
# if the task triggers the subdag, link it to this node in the subdag
if subdag_task_id in upstream_task._downstream_task_ids:
upstream_subdag_triggers.append(upstream_task_urn)
# TODO: capture context
# context dag_run
# task_instance: "TaskInstance" = context["task_instance"]
# TODO: capture raw sql from db operators
flow_urn = builder.make_data_flow_urn("airflow", dag.dag_id,
config.cluster)
job_urn = builder.make_data_job_urn_with_flow(flow_urn, task.task_id)
base_url = conf.get("webserver", "base_url")
flow_url = f"{base_url}/tree?dag_id={dag.dag_id}"
job_url = f"{base_url}/taskinstance/list/?flt1_dag_id_equals={dag.dag_id}&_flt_3_task_id={task.task_id}"
# operator.log.info(f"{flow_url=}")
# operator.log.info(f"{job_url=}")
# operator.log.info(f"{dag.get_serialized_fields()=}")
# operator.log.info(f"{task.get_serialized_fields()=}")
# operator.log.info(f"{SerializedDAG.serialize_dag(dag)=}")
flow_property_bag: Dict[str, str] = {
key: repr(value)
for (key, value) in SerializedDAG.serialize_dag(dag).items()
}
for key in dag.get_serialized_fields():
if key not in flow_property_bag:
flow_property_bag[key] = repr(getattr(dag, key))
job_property_bag: Dict[str, str] = {
key: repr(value)
for (key,
value) in SerializedBaseOperator.serialize_operator(task).items()
}
for key in task.get_serialized_fields():
if key not in job_property_bag:
job_property_bag[key] = repr(getattr(task, key))
# operator.log.info(f"{flow_property_bag=}")
# operator.log.info(f"{job_property_bag=}")
allowed_task_keys = [
"_downstream_task_ids",
"_inlets",
"_outlets",
"_task_type",
"_task_module",
"depends_on_past",
"email",
"label",
"execution_timeout",
"end_date",
"start_date",
"sla",
"sql",
"task_id",
"trigger_rule",
"wait_for_downstream",
]
job_property_bag = {
k: v
for (k, v) in job_property_bag.items() if k in allowed_task_keys
}
allowed_flow_keys = [
"_access_control",
"_concurrency",
"_default_view",
"catchup",
"fileloc",
"is_paused_upon_creation",
"start_date",
"tags",
"timezone",
]
flow_property_bag = {
k: v
for (k, v) in flow_property_bag.items() if k in allowed_flow_keys
}
if config.capture_ownership_info:
ownership = models.OwnershipClass(
owners=[
models.OwnerClass(
owner=builder.make_user_urn(dag.owner),
type=models.OwnershipTypeClass.DEVELOPER,
source=models.OwnershipSourceClass(
type=models.OwnershipSourceTypeClass.SERVICE,
url=dag.filepath,
),
)
],
lastModified=models.AuditStampClass(
time=0, actor=builder.make_user_urn("airflow")),
)
# operator.log.info(f"{ownership=}")
ownership_aspect = [ownership]
else:
ownership_aspect = []
if config.capture_tags_info:
tags = models.GlobalTagsClass(tags=[
models.TagAssociationClass(tag=builder.make_tag_urn(tag))
for tag in (dag.tags or [])
])
# operator.log.info(f"{tags=}")
tags_aspect = [tags]
else:
tags_aspect = []
flow_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataFlowSnapshotClass(
urn=flow_urn,
aspects=[
models.DataFlowInfoClass(
name=dag.dag_id,
description=f"{dag.description}\n\n{dag.doc_md or ''}",
customProperties=flow_property_bag,
externalUrl=flow_url,
),
*ownership_aspect,
*tags_aspect,
],
))
# exclude subdag operator tasks since these are not emitted, resulting in empty metadata
upstream_tasks = ([
builder.make_data_job_urn_with_flow(flow_urn, task_id)
for task_id in task.upstream_task_ids
if dag.task_dict[task_id].subdag is None
] + upstream_subdag_task_urns + upstream_subdag_triggers)
job_doc = ((operator.doc or operator.doc_md or operator.doc_json
or operator.doc_yaml or operator.doc_rst)
if not AIRFLOW_1 else None)
job_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataJobSnapshotClass(
urn=job_urn,
aspects=[
models.DataJobInfoClass(
name=task.task_id,
type=models.AzkabanJobTypeClass.COMMAND,
description=job_doc,
customProperties=job_property_bag,
externalUrl=job_url,
),
models.DataJobInputOutputClass(
inputDatasets=_entities_to_urn_list(inlets or []),
outputDatasets=_entities_to_urn_list(outlets or []),
inputDatajobs=upstream_tasks,
),
*ownership_aspect,
*tags_aspect,
],
))
force_entity_materialization = [
models.MetadataChangeEventClass(
proposedSnapshot=models.DatasetSnapshotClass(
urn=iolet,
aspects=[
models.StatusClass(removed=False),
],
))
for iolet in _entities_to_urn_list((inlets or []) + (outlets or []))
]
hook = config.make_emitter_hook()
mces = [
flow_mce,
job_mce,
*force_entity_materialization,
]
operator.log.info("DataHub lineage backend - emitting metadata:\n" +
"\n".join(json.dumps(mce.to_obj()) for mce in mces))
hook.emit_mces(mces)
def send_lineage_to_datahub(
config: DatahubBasicLineageConfig,
operator: "BaseOperator",
inlets: List[_Entity],
outlets: List[_Entity],
context: Dict,
) -> None:
# This is necessary to avoid issues with circular imports.
from airflow.serialization.serialized_objects import (
SerializedBaseOperator,
SerializedDAG,
)
dag: "DAG" = context["dag"]
task: "BaseOperator" = context["task"]
# TODO: capture context
# context dag_run
# task_instance: "TaskInstance" = context["task_instance"]
# TODO: capture raw sql from db operators
flow_urn = builder.make_data_flow_urn("airflow", dag.dag_id,
config.cluster)
job_urn = builder.make_data_job_urn_with_flow(flow_urn, task.task_id)
base_url = conf.get("webserver", "base_url")
flow_url = f"{base_url}/tree?dag_id={dag.dag_id}"
job_url = f"{base_url}/taskinstance/list/?flt1_dag_id_equals={dag.dag_id}&_flt_3_task_id={task.task_id}"
# operator.log.info(f"{flow_url=}")
# operator.log.info(f"{job_url=}")
# operator.log.info(f"{dag.get_serialized_fields()=}")
# operator.log.info(f"{task.get_serialized_fields()=}")
# operator.log.info(f"{SerializedDAG.serialize_dag(dag)=}")
flow_property_bag: Dict[str, str] = {
key: repr(value)
for (key, value) in SerializedDAG.serialize_dag(dag).items()
}
for key in dag.get_serialized_fields():
if key not in flow_property_bag:
flow_property_bag[key] = repr(getattr(dag, key))
job_property_bag: Dict[str, str] = {
key: repr(value)
for (key,
value) in SerializedBaseOperator.serialize_operator(task).items()
}
for key in task.get_serialized_fields():
if key not in job_property_bag:
job_property_bag[key] = repr(getattr(task, key))
# operator.log.info(f"{flow_property_bag=}")
# operator.log.info(f"{job_property_bag=}")
allowed_task_keys = [
"_downstream_task_ids",
"_inlets",
"_outlets",
"_task_type",
"_task_module",
"depends_on_past",
"email",
"label",
"execution_timeout",
"end_date",
"start_date",
"sla",
"sql",
"task_id",
"trigger_rule",
"wait_for_downstream",
]
job_property_bag = {
k: v
for (k, v) in job_property_bag.items() if k in allowed_task_keys
}
allowed_flow_keys = [
"_access_control",
"_concurrency",
"_default_view",
"catchup",
"fileloc",
"is_paused_upon_creation",
"start_date",
"tags",
"timezone",
]
flow_property_bag = {
k: v
for (k, v) in flow_property_bag.items() if k in allowed_flow_keys
}
if config.capture_ownership_info:
timestamp = int(
dateutil.parser.parse(context["ts"]).timestamp() * 1000)
ownership = models.OwnershipClass(
owners=[
models.OwnerClass(
owner=builder.make_user_urn(dag.owner),
type=models.OwnershipTypeClass.DEVELOPER,
source=models.OwnershipSourceClass(
type=models.OwnershipSourceTypeClass.SERVICE,
url=dag.filepath,
),
)
],
lastModified=models.AuditStampClass(
time=timestamp, actor=builder.make_user_urn("airflow")),
)
# operator.log.info(f"{ownership=}")
ownership_aspect = [ownership]
else:
ownership_aspect = []
if config.capture_tags_info:
tags = models.GlobalTagsClass(tags=[
models.TagAssociationClass(tag=builder.make_tag_urn(tag))
for tag in (dag.tags or [])
])
# operator.log.info(f"{tags=}")
tags_aspect = [tags]
else:
tags_aspect = []
flow_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataFlowSnapshotClass(
urn=flow_urn,
aspects=[
models.DataFlowInfoClass(
name=dag.dag_id,
description=f"{dag.description}\n\n{dag.doc_md or ''}",
customProperties=flow_property_bag,
externalUrl=flow_url,
),
*ownership_aspect,
*tags_aspect,
],
))
job_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataJobSnapshotClass(
urn=job_urn,
aspects=[
models.DataJobInfoClass(
name=task.task_id,
type=models.AzkabanJobTypeClass.COMMAND,
description=None,
customProperties=job_property_bag,
externalUrl=job_url,
),
models.DataJobInputOutputClass(
inputDatasets=_entities_to_urn_list(inlets or []),
outputDatasets=_entities_to_urn_list(outlets or []),
inputDatajobs=[
builder.make_data_job_urn_with_flow(flow_urn, task_id)
for task_id in task.upstream_task_ids
],
),
*ownership_aspect,
*tags_aspect,
],
))
force_entity_materialization = [
models.MetadataChangeEventClass(
proposedSnapshot=models.DatasetSnapshotClass(
urn=iolet,
aspects=[
models.StatusClass(removed=False),
],
))
for iolet in _entities_to_urn_list((inlets or []) + (outlets or []))
]
hook = config.make_emitter_hook()
mces = [
flow_mce,
job_mce,
*force_entity_materialization,
]
operator.log.info("DataHub lineage backend - emitting metadata:\n" +
"\n".join(json.dumps(mce.to_obj()) for mce in mces))
hook.emit_mces(mces)
def send_lineage(
operator: "BaseOperator",
inlets: Optional[List] = None,
outlets: Optional[List] = None,
context: Dict = None,
) -> None:
# This is necessary to avoid issues with circular imports.
from airflow.lineage import prepare_lineage
from airflow.serialization.serialized_objects import (
SerializedBaseOperator,
SerializedDAG,
)
from datahub.integrations.airflow.hooks import AIRFLOW_1
# Detect Airflow 1.10.x inlet/outlet configurations in Airflow 2.x, and
# convert to the newer version. This code path will only be triggered
# when 2.x receives a 1.10.x inlet/outlet config.
needs_repeat_preparation = False
if (not AIRFLOW_1 and isinstance(operator._inlets, list)
and len(operator._inlets) == 1
and isinstance(operator._inlets[0], dict)):
from airflow.lineage import AUTO
operator._inlets = [
# See https://airflow.apache.org/docs/apache-airflow/1.10.15/lineage.html.
*operator._inlets[0].get(
"datasets", []), # assumes these are attr-annotated
*operator._inlets[0].get("task_ids", []),
*([AUTO] if operator._inlets[0].get("auto", False) else []),
]
needs_repeat_preparation = True
if (not AIRFLOW_1 and isinstance(operator._outlets, list)
and len(operator._outlets) == 1
and isinstance(operator._outlets[0], dict)):
operator._outlets = [*operator._outlets[0].get("datasets", [])]
needs_repeat_preparation = True
if needs_repeat_preparation:
# Rerun the lineage preparation routine, now that the old format has been translated to the new one.
prepare_lineage(lambda self, ctx: None)(operator, context)
context = context or {} # ensure not None to satisfy mypy
dag: "DAG" = context["dag"]
task = context["task"]
# TODO: capture context
# context dag_run
# task_instance: "TaskInstance" = context["task_instance"]
# TODO: capture raw sql from db operators
flow_urn = builder.make_data_flow_urn("airflow", dag.dag_id)
job_urn = builder.make_data_job_urn_with_flow(flow_urn, task.task_id)
base_url = conf.get("webserver", "base_url")
flow_url = f"{base_url}/tree?dag_id={dag.dag_id}"
job_url = f"{base_url}/taskinstance/list/?flt1_dag_id_equals={dag.dag_id}&_flt_3_task_id={task.task_id}"
# operator.log.info(f"{flow_url=}")
# operator.log.info(f"{job_url=}")
# operator.log.info(f"{dag.get_serialized_fields()=}")
# operator.log.info(f"{task.get_serialized_fields()=}")
# operator.log.info(f"{SerializedDAG.serialize_dag(dag)=}")
flow_property_bag: Dict[str, str] = {
key: repr(value)
for (key, value) in SerializedDAG.serialize_dag(dag).items()
}
for key in dag.get_serialized_fields():
if key not in flow_property_bag:
flow_property_bag[key] = repr(getattr(dag, key))
job_property_bag: Dict[str, str] = {
key: repr(value)
for (key, value
) in SerializedBaseOperator.serialize_operator(task).items()
}
for key in task.get_serialized_fields():
if key not in job_property_bag:
job_property_bag[key] = repr(getattr(task, key))
# operator.log.info(f"{flow_property_bag=}")
# operator.log.info(f"{job_property_bag=}")
timestamp = int(
dateutil.parser.parse(context["ts"]).timestamp() * 1000)
ownership = models.OwnershipClass(
owners=[
models.OwnerClass(
owner=builder.make_user_urn(dag.owner),
type=models.OwnershipTypeClass.DEVELOPER,
source=models.OwnershipSourceClass(
type=models.OwnershipSourceTypeClass.SERVICE,
url=dag.filepath,
),
)
],
lastModified=models.AuditStampClass(
time=timestamp, actor=builder.make_user_urn("airflow")),
)
# operator.log.info(f"{ownership=}")
tags = models.GlobalTagsClass(tags=[
models.TagAssociationClass(tag=f"airflow_{tag}")
for tag in (dag.tags or [])
])
# operator.log.info(f"{tags=}")
flow_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataFlowSnapshotClass(
urn=flow_urn,
aspects=[
models.DataFlowInfoClass(
name=dag.dag_id,
description=f"{dag.description}\n\n{dag.doc_md or ''}",
customProperties=flow_property_bag,
externalUrl=flow_url,
),
ownership,
tags,
],
))
job_mce = models.MetadataChangeEventClass(
proposedSnapshot=models.DataJobSnapshotClass(
urn=job_urn,
aspects=[
models.DataJobInfoClass(
name=task.task_id,
type=models.AzkabanJobTypeClass.COMMAND,
description=None,
customProperties=job_property_bag,
externalUrl=job_url,
),
models.DataJobInputOutputClass(
inputDatasets=_entities_to_urn_list(inlets or []),
outputDatasets=_entities_to_urn_list(outlets or []),
),
ownership,
tags,
],
))
lineage_mces = [
builder.make_lineage_mce(_entities_to_urn_list(inlets or []),
outlet)
for outlet in _entities_to_urn_list(outlets or [])
]
force_upstream_materialization = [
models.MetadataChangeEventClass(
proposedSnapshot=models.DatasetSnapshotClass(
urn=inlet,
aspects=[
models.StatusClass(removed=False),
],
)) for inlet in _entities_to_urn_list(inlets or [])
]
hook = make_emitter_hook()
mces = [
flow_mce,
job_mce,
*lineage_mces,
*force_upstream_materialization,
]
operator.log.info("DataHub lineage backend - emitting metadata:\n" +
"\n".join(json.dumps(mce.to_obj()) for mce in mces))
hook.emit_mces(mces)