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

feat(ingest): add ability to preserve dbt table identifier casing #7854

Closed
wants to merge 4 commits into from
Closed

feat(ingest): add ability to preserve dbt table identifier casing #7854

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9b2f44c
feat(ingest): add ability to preserve dbt table identifier casing
viplazylmht Apr 19, 2023
efe2d6e
Merge branch 'datahub-project:master' into dbt-preverse-dataset-urns
viplazylmht Apr 27, 2023
789fe53
Merge branch 'master' into dbt-preverse-dataset-urns
shirshanka May 23, 2023
81460e0
Merge branch 'master' into dbt-preverse-dataset-urns
hsheth2 May 24, 2023
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
14 changes: 13 additions & 1 deletion metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,10 @@ class DBTCommonConfig(
stateful_ingestion: Optional[StatefulStaleMetadataRemovalConfig] = pydantic.Field(
default=None, description="DBT Stateful Ingestion Config."
)
convert_dataset_urns_to_lowercase: bool = Field(
default=True,
description="When enabled, converts dataset URNs to lowercase to ensure cross-platform compatibility. ",
)
convert_column_urns_to_lowercase: bool = Field(
default=False,
description="When enabled, converts column URNs to lowercase to ensure cross-platform compatibility. "
Expand Down Expand Up @@ -403,10 +407,11 @@ def get_urn(
target_platform: str,
env: str,
data_platform_instance: Optional[str],
convert_dataset_urns_to_lowercase: Optional[bool],
) -> str:
db_fqn = self.get_db_fqn()
if target_platform != DBT_PLATFORM:
db_fqn = db_fqn.lower()
db_fqn = db_fqn.lower() if convert_dataset_urns_to_lowercase else db_fqn
return mce_builder.make_dataset_urn_with_platform_instance(
platform=target_platform,
name=db_fqn,
Expand Down Expand Up @@ -446,6 +451,7 @@ def get_upstreams(
target_platform_instance: Optional[str],
environment: str,
platform_instance: Optional[str],
convert_dataset_urns_to_lowercase: Optional[bool],
) -> List[str]:
upstream_urns = []

Expand Down Expand Up @@ -474,6 +480,7 @@ def get_upstreams(
platform_value,
environment,
platform_instance_value,
convert_dataset_urns_to_lowercase,
)
)
return upstream_urns
Expand Down Expand Up @@ -737,6 +744,7 @@ def create_test_entity_mcps(
target_platform_instance=self.config.target_platform_instance,
environment=self.config.env,
platform_instance=None,
convert_dataset_urns_to_lowercase=self.config.convert_dataset_urns_to_lowercase,
)

for upstream_urn in sorted(upstream_urns):
Expand Down Expand Up @@ -978,6 +986,7 @@ def create_platform_mces(
mce_platform,
self.config.env,
mce_platform_instance,
self.config.convert_dataset_urns_to_lowercase,
)
if not self.config.entities_enabled.can_emit_node_type(node.node_type):
logger.debug(
Expand Down Expand Up @@ -1035,6 +1044,7 @@ def create_platform_mces(
DBT_PLATFORM,
self.config.env,
self.config.platform_instance,
self.config.convert_dataset_urns_to_lowercase,
)
upstreams_lineage_class = get_upstream_lineage([upstream_dbt_urn])
if self.config.incremental_lineage:
Expand Down Expand Up @@ -1372,6 +1382,7 @@ def _create_lineage_aspect_for_dbt_node(
self.config.target_platform_instance,
self.config.env,
self.config.platform_instance,
self.config.convert_dataset_urns_to_lowercase,
)

# if a node is of type source in dbt, its upstream lineage should have the corresponding table/view
Expand All @@ -1382,6 +1393,7 @@ def _create_lineage_aspect_for_dbt_node(
self.config.target_platform,
self.config.env,
self.config.target_platform_instance,
self.config.convert_dataset_urns_to_lowercase,
)
)
if upstream_urns:
Expand Down