def _create_subType_wu(
self, node: DBTNode,
node_datahub_urn: str) -> Optional[MetadataWorkUnit]:
if not node.node_type:
return None
subtypes: Optional[List[str]]
if node.node_type == "model":
if node.materialization:
subtypes = [node.materialization, "view"]
else:
subtypes = ["model", "view"]
else:
subtypes = [node.node_type]
subtype_mcp = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=node_datahub_urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=subtypes),
)
subtype_wu = MetadataWorkUnit(
id=
f"{self.platform}-{subtype_mcp.entityUrn}-{subtype_mcp.aspectName}",
mcp=subtype_mcp,
)
return subtype_wu
def _build_dataset_mcps(
self,
looker_view: LookerView) -> List[MetadataChangeProposalWrapper]:
events = []
subTypeEvent = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=looker_view.id.get_urn(self.source_config),
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["view"]),
)
events.append(subTypeEvent)
if looker_view.view_details is not None:
viewEvent = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=looker_view.id.get_urn(self.source_config),
aspectName="viewProperties",
aspect=looker_view.view_details,
)
events.append(viewEvent)
return events
def _to_metadata_events( # noqa: C901
self, config: LookerCommonConfig, reporter: SourceReport,
base_url: str) -> Optional[List[Union[MetadataChangeEvent,
MetadataChangeProposalWrapper]]]:
# We only generate MCE-s for explores that contain from clauses and do NOT contain joins
# All other explores (passthrough explores and joins) end in correct resolution of lineage, and don't need additional nodes in the graph.
dataset_snapshot = DatasetSnapshot(
urn=self.get_explore_urn(config),
aspects=[], # we append to this list later on
)
browse_paths = BrowsePathsClass(
paths=[self.get_explore_browse_path(config)])
dataset_snapshot.aspects.append(browse_paths)
dataset_snapshot.aspects.append(StatusClass(removed=False))
custom_properties = {}
if self.label is not None:
custom_properties["looker.explore.label"] = str(self.label)
if self.source_file is not None:
custom_properties["looker.explore.file"] = str(self.source_file)
dataset_props = DatasetPropertiesClass(
description=self.description,
customProperties=custom_properties,
)
dataset_props.externalUrl = self._get_url(base_url)
dataset_snapshot.aspects.append(dataset_props)
if self.upstream_views is not None:
assert self.project_name is not None
upstreams = [
UpstreamClass(
dataset=LookerViewId(
project_name=self.project_name,
model_name=self.model_name,
view_name=view_name,
).get_urn(config),
type=DatasetLineageTypeClass.VIEW,
) for view_name in sorted(self.upstream_views)
]
upstream_lineage = UpstreamLineage(upstreams=upstreams)
dataset_snapshot.aspects.append(upstream_lineage)
if self.fields is not None:
schema_metadata = LookerUtil._get_schema(
platform_name=config.platform_name,
schema_name=self.name,
view_fields=self.fields,
reporter=reporter,
)
if schema_metadata is not None:
dataset_snapshot.aspects.append(schema_metadata)
mce = MetadataChangeEvent(proposedSnapshot=dataset_snapshot)
mcp = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_snapshot.urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["explore"]),
)
return [mce, mcp]
def gen_containers(
container_key: KeyType,
name: str,
sub_types: List[str],
parent_container_key: Optional[PlatformKey] = None,
domain_urn: Optional[str] = None,
description: Optional[str] = None,
owner_urn: Optional[str] = None,
external_url: Optional[str] = None,
tags: Optional[List[str]] = None,
) -> Iterable[MetadataWorkUnit]:
container_urn = make_container_urn(guid=container_key.guid(), )
mcp = MetadataChangeProposalWrapper(
entityType="container",
changeType=ChangeTypeClass.UPSERT,
entityUrn=f"{container_urn}",
# entityKeyAspect=ContainerKeyClass(guid=schema_container_key.guid()),
aspectName="containerProperties",
aspect=ContainerProperties(
name=name,
description=description,
customProperties=container_key.dict(exclude_none=True,
by_alias=True),
externalUrl=external_url,
),
)
wu = MetadataWorkUnit(id=f"container-info-{name}-{container_urn}", mcp=mcp)
yield wu
mcp = MetadataChangeProposalWrapper(
entityType="container",
changeType=ChangeTypeClass.UPSERT,
entityUrn=f"{container_urn}",
# entityKeyAspect=ContainerKeyClass(guid=schema_container_key.guid()),
aspectName="dataPlatformInstance",
aspect=DataPlatformInstance(
platform=f"{make_data_platform_urn(container_key.platform)}", ),
)
wu = MetadataWorkUnit(
id=f"container-platforminstance-{name}-{container_urn}", mcp=mcp)
yield wu
# Set subtype
subtype_mcp = MetadataChangeProposalWrapper(
entityType="container",
changeType=ChangeTypeClass.UPSERT,
entityUrn=f"{container_urn}",
# entityKeyAspect=ContainerKeyClass(guid=schema_container_key.guid()),
aspectName="subTypes",
aspect=SubTypesClass(typeNames=sub_types),
)
wu = MetadataWorkUnit(id=f"container-subtypes-{name}-{container_urn}",
mcp=subtype_mcp)
yield wu
if domain_urn:
yield from add_domain_to_entity_wu(
entity_type="container",
entity_urn=container_urn,
domain_urn=domain_urn,
)
if owner_urn:
yield from add_owner_to_entity_wu(
entity_type="container",
entity_urn=container_urn,
owner_urn=owner_urn,
)
if tags:
yield from add_tags_to_entity_wu(
entity_type="container",
entity_urn=container_urn,
tags=tags,
)
if parent_container_key:
parent_container_urn = make_container_urn(
guid=parent_container_key.guid(), )
# Set database container
parent_container_mcp = MetadataChangeProposalWrapper(
entityType="container",
changeType=ChangeTypeClass.UPSERT,
entityUrn=f"{container_urn}",
# entityKeyAspect=ContainerKeyClass(guid=schema_container_key.guid()),
aspectName="container",
aspect=ContainerClass(container=parent_container_urn),
# aspect=ContainerKeyClass(guid=database_container_key.guid())
)
wu = MetadataWorkUnit(
id=
f"container-parent-container-{name}-{container_urn}-{parent_container_urn}",
mcp=parent_container_mcp,
)
yield wu
def _extract_record(self, topic: str,
partitioned: bool) -> Iterable[MetadataWorkUnit]:
logger.info(f"topic = {topic}")
# 1. Create and emit the default dataset for the topic. Extract type, tenant, namespace
# and topic name from full Pulsar topic name i.e. persistent://tenant/namespace/topic
pulsar_topic = PulsarTopic(topic)
platform_urn = make_data_platform_urn(self.platform)
dataset_urn = make_dataset_urn_with_platform_instance(
platform=self.platform,
name=pulsar_topic.fullname,
platform_instance=self.config.platform_instance,
env=self.config.env,
)
status_wu = MetadataWorkUnit(
id=f"{dataset_urn}-status",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="status",
aspect=StatusClass(removed=False),
),
)
self.report.report_workunit(status_wu)
yield status_wu
# 2. Emit schemaMetadata aspect
schema, schema_metadata = self._get_schema_metadata(
pulsar_topic, platform_urn)
if schema_metadata is not None:
schema_metadata_wu = MetadataWorkUnit(
id=f"{dataset_urn}-schemaMetadata",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="schemaMetadata",
aspect=schema_metadata,
),
)
self.report.report_workunit(schema_metadata_wu)
yield schema_metadata_wu
# TODO Add topic properties (Pulsar 2.10.0 feature)
# 3. Construct and emit dataset properties aspect
if schema is not None:
schema_properties = {
"schema_version": str(schema.schema_version),
"schema_type": schema.schema_type,
"partitioned": str(partitioned).lower(),
}
# Add some static properties to the schema properties
schema.properties.update(schema_properties)
dataset_properties_wu = MetadataWorkUnit(
id=f"{dataset_urn}-datasetProperties",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="datasetProperties",
aspect=DatasetPropertiesClass(
description=schema.schema_description,
customProperties=schema.properties,
),
),
)
self.report.report_workunit(dataset_properties_wu)
yield dataset_properties_wu
# 4. Emit browsePaths aspect
pulsar_path = (
f"{pulsar_topic.tenant}/{pulsar_topic.namespace}/{pulsar_topic.topic}"
)
browse_path_suffix = (f"{self.config.platform_instance}/{pulsar_path}"
if self.config.platform_instance else
pulsar_path)
browse_path_wu = MetadataWorkUnit(
id=f"{dataset_urn}-browsePaths",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="browsePaths",
aspect=BrowsePathsClass([
f"/{self.config.env.lower()}/{self.platform}/{browse_path_suffix}"
]),
),
)
self.report.report_workunit(browse_path_wu)
yield browse_path_wu
# 5. Emit dataPlatformInstance aspect.
if self.config.platform_instance:
platform_instance_wu = MetadataWorkUnit(
id=f"{dataset_urn}-dataPlatformInstance",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="dataPlatformInstance",
aspect=DataPlatformInstanceClass(
platform=platform_urn,
instance=make_dataplatform_instance_urn(
self.platform, self.config.platform_instance),
),
),
)
self.report.report_workunit(platform_instance_wu)
yield platform_instance_wu
# 6. Emit subtype aspect marking this as a "topic"
subtype_wu = MetadataWorkUnit(
id=f"{dataset_urn}-subTypes",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["topic"]),
),
)
self.report.report_workunit(subtype_wu)
yield subtype_wu
# 7. Emit domains aspect
domain_urn: Optional[str] = None
for domain, pattern in self.config.domain.items():
if pattern.allowed(pulsar_topic.fullname):
domain_urn = make_domain_urn(domain)
if domain_urn:
wus = add_domain_to_entity_wu(
entity_type="dataset",
entity_urn=dataset_urn,
domain_urn=domain_urn,
)
for wu in wus:
self.report.report_workunit(wu)
yield wu
def _extract_mcps(self,
index: str) -> Iterable[MetadataChangeProposalWrapper]:
logger.debug(f"index = {index}")
raw_index = self.client.indices.get(index=index)
raw_index_metadata = raw_index[index]
# 0. Dedup data_streams.
data_stream = raw_index_metadata.get("data_stream")
if data_stream:
index = data_stream
self.data_stream_partition_count[index] += 1
if self.data_stream_partition_count[index] > 1:
# This is a duplicate, skip processing it further.
return
# 1. Construct and emit the schemaMetadata aspect
# 1.1 Generate the schema fields from ES mappings.
index_mappings = raw_index_metadata["mappings"]
index_mappings_json_str: str = json.dumps(index_mappings)
md5_hash = md5(index_mappings_json_str.encode()).hexdigest()
schema_fields = list(
ElasticToSchemaFieldConverter.get_schema_fields(index_mappings))
# 1.2 Generate the SchemaMetadata aspect
schema_metadata = SchemaMetadata(
schemaName=index,
platform=make_data_platform_urn(self.platform),
version=0,
hash=md5_hash,
platformSchema=OtherSchemaClass(rawSchema=index_mappings_json_str),
fields=schema_fields,
)
# 1.3 Emit the mcp
dataset_urn: str = make_dataset_urn(self.platform, index,
self.source_config.env)
yield MetadataChangeProposalWrapper(
entityType="dataset",
entityUrn=dataset_urn,
aspectName="schemaMetadata",
aspect=schema_metadata,
changeType=ChangeTypeClass.UPSERT,
)
# 2. Construct and emit the status aspect.
yield MetadataChangeProposalWrapper(
entityType="dataset",
entityUrn=dataset_urn,
aspectName="status",
aspect=StatusClass(removed=False),
changeType=ChangeTypeClass.UPSERT,
)
# 3. Construct and emit subtype
yield MetadataChangeProposalWrapper(
entityType="dataset",
entityUrn=dataset_urn,
aspectName="subTypes",
aspect=SubTypesClass(
typeNames=["Index" if not data_stream else "DataStream"]),
changeType=ChangeTypeClass.UPSERT,
)
# 4. Construct and emit properties if needed
index_aliases = raw_index_metadata.get("aliases", {}).keys()
if index_aliases:
yield MetadataChangeProposalWrapper(
entityType="dataset",
entityUrn=dataset_urn,
aspectName="datasetProperties",
aspect=DatasetPropertiesClass(
customProperties={"aliases": ",".join(index_aliases)}),
changeType=ChangeTypeClass.UPSERT,
)
def emit_custom_sql_datasources(self) -> Iterable[MetadataWorkUnit]:
count_on_query = len(self.custom_sql_ids_being_used)
custom_sql_filter = "idWithin: {}".format(
json.dumps(self.custom_sql_ids_being_used))
custom_sql_connection, total_count, has_next_page = self.get_connection_object(
custom_sql_graphql_query, "customSQLTablesConnection",
custom_sql_filter)
current_count = 0
while has_next_page:
count = (count_on_query if current_count +
count_on_query < total_count else total_count -
current_count)
(
custom_sql_connection,
total_count,
has_next_page,
) = self.get_connection_object(
custom_sql_graphql_query,
"customSQLTablesConnection",
custom_sql_filter,
count,
current_count,
)
current_count += count
unique_custom_sql = get_unique_custom_sql(
custom_sql_connection.get("nodes", []))
for csql in unique_custom_sql:
csql_id: str = csql.get("id", "")
csql_urn = builder.make_dataset_urn(self.platform, csql_id,
self.config.env)
dataset_snapshot = DatasetSnapshot(
urn=csql_urn,
aspects=[],
)
# lineage from datasource -> custom sql source #
yield from self._create_lineage_from_csql_datasource(
csql_urn, csql.get("datasources", []))
# lineage from custom sql -> datasets/tables #
columns = csql.get("columns", [])
yield from self._create_lineage_to_upstream_tables(
csql_urn, columns)
# Schema Metadata
schema_metadata = self.get_schema_metadata_for_custom_sql(
columns)
if schema_metadata is not None:
dataset_snapshot.aspects.append(schema_metadata)
# Browse path
browse_paths = BrowsePathsClass(paths=[
f"/{self.config.env.lower()}/{self.platform}/Custom SQL/{csql.get('name', '')}/{csql_id}"
])
dataset_snapshot.aspects.append(browse_paths)
dataset_properties = DatasetPropertiesClass(
name=csql.get("name"), description=csql.get("description"))
dataset_snapshot.aspects.append(dataset_properties)
view_properties = ViewPropertiesClass(
materialized=False,
viewLanguage="SQL",
viewLogic=clean_query(csql.get("query", "")),
)
dataset_snapshot.aspects.append(view_properties)
yield self.get_metadata_change_event(dataset_snapshot)
yield self.get_metadata_change_proposal(
dataset_snapshot.urn,
aspect_name="subTypes",
aspect=SubTypesClass(typeNames=["View", "Custom SQL"]),
)
def emit_datasource(self,
datasource: dict,
workbook: dict = None) -> Iterable[MetadataWorkUnit]:
datasource_info = workbook
if workbook is None:
datasource_info = datasource
project = (datasource_info.get("projectName", "").replace(
"/", REPLACE_SLASH_CHAR) if datasource_info else "")
datasource_id = datasource.get("id", "")
datasource_name = f"{datasource.get('name')}.{datasource_id}"
datasource_urn = builder.make_dataset_urn(self.platform, datasource_id,
self.config.env)
if datasource_id not in self.datasource_ids_being_used:
self.datasource_ids_being_used.append(datasource_id)
dataset_snapshot = DatasetSnapshot(
urn=datasource_urn,
aspects=[],
)
# Browse path
browse_paths = BrowsePathsClass(paths=[
f"/{self.config.env.lower()}/{self.platform}/{project}/{datasource.get('name', '')}/{datasource_name}"
])
dataset_snapshot.aspects.append(browse_paths)
# Ownership
owner = (self._get_ownership(
datasource_info.get("owner", {}).get("username", ""))
if datasource_info else None)
if owner is not None:
dataset_snapshot.aspects.append(owner)
# Dataset properties
dataset_props = DatasetPropertiesClass(
name=datasource.get("name"),
description=datasource.get("description"),
customProperties={
"hasExtracts":
str(datasource.get("hasExtracts", "")),
"extractLastRefreshTime":
datasource.get("extractLastRefreshTime", "") or "",
"extractLastIncrementalUpdateTime":
datasource.get("extractLastIncrementalUpdateTime", "") or "",
"extractLastUpdateTime":
datasource.get("extractLastUpdateTime", "") or "",
"type":
datasource.get("__typename", ""),
},
)
dataset_snapshot.aspects.append(dataset_props)
# Upstream Tables
if datasource.get("upstreamTables") is not None:
# datasource -> db table relations
upstream_tables = self._create_upstream_table_lineage(
datasource, project)
if upstream_tables:
upstream_lineage = UpstreamLineage(upstreams=upstream_tables)
yield self.get_metadata_change_proposal(
datasource_urn,
aspect_name="upstreamLineage",
aspect=upstream_lineage,
)
# Datasource Fields
schema_metadata = self._get_schema_metadata_for_embedded_datasource(
datasource.get("fields", []))
if schema_metadata is not None:
dataset_snapshot.aspects.append(schema_metadata)
yield self.get_metadata_change_event(dataset_snapshot)
yield self.get_metadata_change_proposal(
dataset_snapshot.urn,
aspect_name="subTypes",
aspect=SubTypesClass(typeNames=["Data Source"]),
)
if datasource.get("__typename") == "EmbeddedDatasource":
yield from add_entity_to_container(self.gen_workbook_key(workbook),
"dataset", dataset_snapshot.urn)
def emit_custom_sql_datasources(self) -> Iterable[MetadataWorkUnit]:
count_on_query = len(self.custom_sql_ids_being_used)
custom_sql_filter = "idWithin: {}".format(
json.dumps(self.custom_sql_ids_being_used)
)
custom_sql_connection, total_count, has_next_page = self.get_connection_object(
custom_sql_graphql_query, "customSQLTablesConnection", custom_sql_filter
)
current_count = 0
while has_next_page:
count = (
count_on_query
if current_count + count_on_query < total_count
else total_count - current_count
)
(
custom_sql_connection,
total_count,
has_next_page,
) = self.get_connection_object(
custom_sql_graphql_query,
"customSQLTablesConnection",
custom_sql_filter,
count,
current_count,
)
current_count += count
unique_custom_sql = get_unique_custom_sql(
custom_sql_connection.get("nodes", [])
)
for csql in unique_custom_sql:
csql_id: str = csql["id"]
csql_urn = builder.make_dataset_urn(
self.platform, csql_id, self.config.env
)
dataset_snapshot = DatasetSnapshot(
urn=csql_urn,
aspects=[],
)
datasource_name = None
project = None
if len(csql["datasources"]) > 0:
yield from self._create_lineage_from_csql_datasource(
csql_urn, csql["datasources"]
)
# CustomSQLTable id owned by exactly one tableau data source
logger.debug(
f"Number of datasources referencing CustomSQLTable: {len(csql['datasources'])}"
)
datasource = csql["datasources"][0]
datasource_name = datasource.get("name")
if datasource.get(
"__typename"
) == "EmbeddedDatasource" and datasource.get("workbook"):
datasource_name = (
f"{datasource.get('workbook').get('name')}/{datasource_name}"
if datasource_name
and datasource.get("workbook").get("name")
else None
)
yield from add_entity_to_container(
self.gen_workbook_key(datasource["workbook"]),
"dataset",
dataset_snapshot.urn,
)
project = self._get_project(datasource)
# lineage from custom sql -> datasets/tables #
columns = csql.get("columns", [])
yield from self._create_lineage_to_upstream_tables(csql_urn, columns)
# Schema Metadata
schema_metadata = self.get_schema_metadata_for_custom_sql(columns)
if schema_metadata is not None:
dataset_snapshot.aspects.append(schema_metadata)
# Browse path
csql_name = csql.get("name") if csql.get("name") else csql_id
if project and datasource_name:
browse_paths = BrowsePathsClass(
paths=[
f"/{self.config.env.lower()}/{self.platform}/{project}/{datasource['name']}/{csql_name}"
]
)
dataset_snapshot.aspects.append(browse_paths)
else:
logger.debug(f"Browse path not set for Custom SQL table {csql_id}")
dataset_properties = DatasetPropertiesClass(
name=csql.get("name"), description=csql.get("description")
)
dataset_snapshot.aspects.append(dataset_properties)
view_properties = ViewPropertiesClass(
materialized=False,
viewLanguage="SQL",
viewLogic=clean_query(csql.get("query", "")),
)
dataset_snapshot.aspects.append(view_properties)
yield self.get_metadata_change_event(dataset_snapshot)
yield self.get_metadata_change_proposal(
dataset_snapshot.urn,
aspect_name="subTypes",
aspect=SubTypesClass(typeNames=["View", "Custom SQL"]),
)
def _extract_record(
self, topic: str) -> Iterable[MetadataWorkUnit]: # noqa: C901
logger.debug(f"topic = {topic}")
# 1. Create the default dataset snapshot for the topic.
dataset_name = topic
platform_urn = make_data_platform_urn(self.platform)
dataset_urn = make_dataset_urn_with_platform_instance(
platform=self.platform,
name=dataset_name,
platform_instance=self.source_config.platform_instance,
env=self.source_config.env,
)
dataset_snapshot = DatasetSnapshot(
urn=dataset_urn,
aspects=[Status(removed=False)], # we append to this list later on
)
# 2. Attach schemaMetadata aspect (pass control to SchemaRegistry)
schema_metadata = self.schema_registry_client.get_schema_metadata(
topic, platform_urn)
if schema_metadata is not None:
dataset_snapshot.aspects.append(schema_metadata)
# 3. Attach browsePaths aspect
browse_path_suffix = (f"{self.source_config.platform_instance}/{topic}"
if self.source_config.platform_instance else
topic)
browse_path = BrowsePathsClass([
f"/{self.source_config.env.lower()}/{self.platform}/{browse_path_suffix}"
])
dataset_snapshot.aspects.append(browse_path)
# 4. Attach dataPlatformInstance aspect.
if self.source_config.platform_instance:
dataset_snapshot.aspects.append(
DataPlatformInstanceClass(
platform=platform_urn,
instance=make_dataplatform_instance_urn(
self.platform, self.source_config.platform_instance),
))
# 5. Emit the datasetSnapshot MCE
mce = MetadataChangeEvent(proposedSnapshot=dataset_snapshot)
wu = MetadataWorkUnit(id=f"kafka-{topic}", mce=mce)
self.report.report_workunit(wu)
yield wu
# 5. Add the subtype aspect marking this as a "topic"
subtype_wu = MetadataWorkUnit(
id=f"{topic}-subtype",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["topic"]),
),
)
self.report.report_workunit(subtype_wu)
yield subtype_wu
domain_urn: Optional[str] = None
# 6. Emit domains aspect MCPW
for domain, pattern in self.source_config.domain.items():
if pattern.allowed(dataset_name):
domain_urn = make_domain_urn(domain)
if domain_urn:
wus = add_domain_to_entity_wu(
entity_type="dataset",
entity_urn=dataset_urn,
domain_urn=domain_urn,
)
for wu in wus:
self.report.report_workunit(wu)
yield wu
def _process_table(
self,
dataset_name: str,
inspector: Inspector,
schema: str,
table: str,
sql_config: SQLAlchemyConfig,
) -> Iterable[Union[SqlWorkUnit, MetadataWorkUnit]]:
columns = self._get_columns(dataset_name, inspector, schema, table)
dataset_urn = make_dataset_urn_with_platform_instance(
self.platform,
dataset_name,
self.config.platform_instance,
self.config.env,
)
dataset_snapshot = DatasetSnapshot(
urn=dataset_urn,
aspects=[StatusClass(removed=False)],
)
if self.is_stateful_ingestion_configured():
cur_checkpoint = self.get_current_checkpoint(
self.get_default_ingestion_job_id())
if cur_checkpoint is not None:
checkpoint_state = cast(BaseSQLAlchemyCheckpointState,
cur_checkpoint.state)
checkpoint_state.add_table_urn(dataset_urn)
description, properties, location_urn = self.get_table_properties(
inspector, schema, table)
dataset_properties = DatasetPropertiesClass(
name=table,
description=description,
customProperties=properties,
)
dataset_snapshot.aspects.append(dataset_properties)
if location_urn:
external_upstream_table = UpstreamClass(
dataset=location_urn,
type=DatasetLineageTypeClass.COPY,
)
lineage_mcpw = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_snapshot.urn,
aspectName="upstreamLineage",
aspect=UpstreamLineage(upstreams=[external_upstream_table]),
)
lineage_wu = MetadataWorkUnit(
id=
f"{self.platform}-{lineage_mcpw.entityUrn}-{lineage_mcpw.aspectName}",
mcp=lineage_mcpw,
)
yield lineage_wu
pk_constraints: dict = inspector.get_pk_constraint(table, schema)
foreign_keys = self._get_foreign_keys(dataset_urn, inspector, schema,
table)
schema_fields = self.get_schema_fields(dataset_name, columns,
pk_constraints)
schema_metadata = get_schema_metadata(
self.report,
dataset_name,
self.platform,
columns,
pk_constraints,
foreign_keys,
schema_fields,
)
dataset_snapshot.aspects.append(schema_metadata)
db_name = self.get_db_name(inspector)
yield from self.add_table_to_schema_container(dataset_urn, db_name,
schema)
mce = MetadataChangeEvent(proposedSnapshot=dataset_snapshot)
wu = SqlWorkUnit(id=dataset_name, mce=mce)
self.report.report_workunit(wu)
yield wu
dpi_aspect = self.get_dataplatform_instance_aspect(
dataset_urn=dataset_urn)
if dpi_aspect:
yield dpi_aspect
subtypes_aspect = MetadataWorkUnit(
id=f"{dataset_name}-subtypes",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["table"]),
),
)
yield subtypes_aspect
yield from self._get_domain_wu(
dataset_name=dataset_name,
entity_urn=dataset_urn,
entity_type="dataset",
sql_config=sql_config,
)
def _process_view(
self,
dataset_name: str,
inspector: Inspector,
schema: str,
view: str,
sql_config: SQLAlchemyConfig,
) -> Iterable[Union[SqlWorkUnit, MetadataWorkUnit]]:
try:
columns = inspector.get_columns(view, schema)
except KeyError:
# For certain types of views, we are unable to fetch the list of columns.
self.report.report_warning(dataset_name,
"unable to get schema for this view")
schema_metadata = None
else:
schema_fields = self.get_schema_fields(dataset_name, columns)
schema_metadata = get_schema_metadata(
self.report,
dataset_name,
self.platform,
columns,
canonical_schema=schema_fields,
)
try:
# SQLALchemy stubs are incomplete and missing this method.
# PR: https://github.com/dropbox/sqlalchemy-stubs/pull/223.
view_info: dict = inspector.get_table_comment(
view, schema) # type: ignore
except NotImplementedError:
description: Optional[str] = None
properties: Dict[str, str] = {}
else:
description = view_info["text"]
# The "properties" field is a non-standard addition to SQLAlchemy's interface.
properties = view_info.get("properties", {})
try:
view_definition = inspector.get_view_definition(view, schema)
if view_definition is None:
view_definition = ""
else:
# Some dialects return a TextClause instead of a raw string,
# so we need to convert them to a string.
view_definition = str(view_definition)
except NotImplementedError:
view_definition = ""
properties["view_definition"] = view_definition
properties["is_view"] = "True"
dataset_urn = make_dataset_urn_with_platform_instance(
self.platform,
dataset_name,
self.config.platform_instance,
self.config.env,
)
dataset_snapshot = DatasetSnapshot(
urn=dataset_urn,
aspects=[StatusClass(removed=False)],
)
db_name = self.get_db_name(inspector)
yield from self.add_table_to_schema_container(dataset_urn, db_name,
schema)
if self.is_stateful_ingestion_configured():
cur_checkpoint = self.get_current_checkpoint(
self.get_default_ingestion_job_id())
if cur_checkpoint is not None:
checkpoint_state = cast(BaseSQLAlchemyCheckpointState,
cur_checkpoint.state)
checkpoint_state.add_view_urn(dataset_urn)
dataset_properties = DatasetPropertiesClass(
name=view,
description=description,
customProperties=properties,
)
dataset_snapshot.aspects.append(dataset_properties)
if schema_metadata:
dataset_snapshot.aspects.append(schema_metadata)
mce = MetadataChangeEvent(proposedSnapshot=dataset_snapshot)
wu = SqlWorkUnit(id=dataset_name, mce=mce)
self.report.report_workunit(wu)
yield wu
dpi_aspect = self.get_dataplatform_instance_aspect(
dataset_urn=dataset_urn)
if dpi_aspect:
yield dpi_aspect
subtypes_aspect = MetadataWorkUnit(
id=f"{view}-subtypes",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["view"]),
),
)
yield subtypes_aspect
if "view_definition" in properties:
view_definition_string = properties["view_definition"]
view_properties_aspect = ViewPropertiesClass(
materialized=False,
viewLanguage="SQL",
viewLogic=view_definition_string)
yield MetadataWorkUnit(
id=f"{view}-viewProperties",
mcp=MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=dataset_urn,
aspectName="viewProperties",
aspect=view_properties_aspect,
),
)
yield from self._get_domain_wu(
dataset_name=dataset_name,
entity_urn=dataset_urn,
entity_type="dataset",
sql_config=sql_config,
)
def generate_stitched_record(relnships_graph: RelationshipGraph) -> List[Any]:
def strip_types(field_path: str) -> str:
final_path = field_path
final_path = re.sub(r"(\[type=[a-zA-Z]+\]\.)", "", final_path)
final_path = re.sub(r"^\[version=2.0\]\.", "", final_path)
return final_path
datasets: List[DatasetSnapshotClass] = []
for entity_name, entity_def in entity_registry.items():
entity_display_name = entity_def.display_name
entity_fields = []
for aspect_name in entity_def.aspects:
if aspect_name not in aspect_registry:
print(
f"Did not find aspect name: {aspect_name} in aspect_registry"
)
continue
# all aspects should have a schema
aspect_schema = aspect_registry[aspect_name].schema
assert aspect_schema
entity_fields.append({
"type": aspect_schema.to_json(),
"name": aspect_name,
})
if entity_fields:
names = avro.schema.Names()
field_objects = []
for f in entity_fields:
field = avro.schema.Field(
type=f["type"],
name=f["name"],
has_default=False,
)
field_objects.append(field)
with unittest.mock.patch("avro.schema.Names.add_name", add_name):
entity_avro_schema = avro.schema.RecordSchema(
name=entity_name,
namespace="datahub.metadata.model",
names=names,
fields=[],
)
entity_avro_schema.set_prop("fields", field_objects)
rawSchema = json.dumps(entity_avro_schema.to_json())
# always add the URN which is the primary key
urn_field = SchemaField(
fieldPath="urn",
type=SchemaFieldDataTypeClass(type=StringTypeClass()),
nativeDataType="string",
nullable=False,
isPartOfKey=True,
description=
f"The primary identifier for the {entity_name} entity. See the {entity_def.keyAspect} field to understand the structure of this urn.",
)
schema_fields: List[SchemaField] = [
urn_field
] + avro_schema_to_mce_fields(rawSchema)
foreign_keys: List[ForeignKeyConstraintClass] = []
source_dataset_urn = make_dataset_urn(
platform=make_data_platform_urn("datahub"),
name=f"{entity_display_name}",
)
for f_field in schema_fields:
if f_field.jsonProps:
json_dict = json.loads(f_field.jsonProps)
if "Aspect" in json_dict:
aspect_info = json_dict["Aspect"]
f_field.globalTags = f_field.globalTags or GlobalTagsClass(
tags=[])
f_field.globalTags.tags.append(
TagAssociationClass(tag="urn:li:tag:Aspect"))
# if this is the key aspect, also add primary-key
if entity_def.keyAspect == aspect_info.get("name"):
f_field.isPartOfKey = True
if "timeseries" == aspect_info.get("type", ""):
# f_field.globalTags = f_field.globalTags or GlobalTagsClass(
# tags=[]
# )
f_field.globalTags.tags.append(
TagAssociationClass(tag="urn:li:tag:Temporal"))
import pdb
# breakpoint()
if "Searchable" in json_dict:
f_field.globalTags = f_field.globalTags or GlobalTagsClass(
tags=[])
f_field.globalTags.tags.append(
TagAssociationClass(tag="urn:li:tag:Searchable"))
if "Relationship" in json_dict:
relationship_info = json_dict["Relationship"]
# detect if we have relationship specified at leaf level or thru path specs
if "entityTypes" not in relationship_info:
# path spec
assert (
len(relationship_info.keys()) == 1
), "We should never have more than one path spec assigned to a relationship annotation"
final_info = None
for k, v in relationship_info.items():
final_info = v
relationship_info = final_info
assert "entityTypes" in relationship_info
entity_types: List[str] = relationship_info.get(
"entityTypes", [])
relnship_name = relationship_info.get("name", None)
for entity_type in entity_types:
destination_entity_name = capitalize_first(
entity_type)
foreign_dataset_urn = make_dataset_urn(
platform=make_data_platform_urn("datahub"),
name=destination_entity_name,
)
fkey = ForeignKeyConstraintClass(
name=relnship_name,
foreignDataset=foreign_dataset_urn,
foreignFields=[
f"urn:li:schemaField:({foreign_dataset_urn}, urn)"
],
sourceFields=[
f"urn:li:schemaField:({source_dataset_urn},{f_field.fieldPath})"
],
)
foreign_keys.append(fkey)
relnships_graph.add_edge(
entity_display_name,
destination_entity_name,
fkey.name,
f" via `{strip_types(f_field.fieldPath)}`",
edge_id=
f"{entity_display_name}:{fkey.name}:{destination_entity_name}:{strip_types(f_field.fieldPath)}",
)
schemaMetadata = SchemaMetadataClass(
schemaName=f"{entity_name}",
platform=make_data_platform_urn("datahub"),
platformSchema=OtherSchemaClass(rawSchema=rawSchema),
fields=schema_fields,
version=0,
hash="",
foreignKeys=foreign_keys if foreign_keys else None,
)
dataset = DatasetSnapshotClass(
urn=make_dataset_urn(
platform=make_data_platform_urn("datahub"),
name=f"{entity_display_name}",
),
aspects=[
schemaMetadata,
GlobalTagsClass(
tags=[TagAssociationClass(tag="urn:li:tag:Entity")]),
BrowsePathsClass(
[f"/prod/datahub/entities/{entity_display_name}"]),
],
)
datasets.append(dataset)
events: List[Union[MetadataChangeEventClass,
MetadataChangeProposalWrapper]] = []
for d in datasets:
entity_name = d.urn.split(":")[-1].split(",")[1]
d.aspects.append(
DatasetPropertiesClass(
description=make_entity_docs(entity_name, relnships_graph)))
mce = MetadataChangeEventClass(proposedSnapshot=d, )
events.append(mce)
mcp = MetadataChangeProposalWrapper(
entityType="dataset",
changeType=ChangeTypeClass.UPSERT,
entityUrn=d.urn,
aspectName="subTypes",
aspect=SubTypesClass(typeNames=["entity"]),
)
events.append(mcp)
return events
