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

fix(ingest): presto-on-hive - Adding db name to the presto on hive urn #6024

Merged
merged 6 commits into from
Oct 19, 2022
Merged

fix(ingest): presto-on-hive - Adding db name to the presto on hive urn #6024

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
4b2ef38
Adding db name to the presto on hive urn
treff7es Sep 22, 2022
c654725
Merge branch 'master' into add_database_to_hive_urn
treff7es Oct 18, 2022
7d5dc3e
Making configurable to add database name to urns
treff7es Oct 18, 2022
1f25262
Fixing test
treff7es Oct 18, 2022
15694ef
Merge branch 'master' into add_database_to_hive_urn
treff7es Oct 18, 2022
cc6932b
changing config name to something more meaningful
shirshanka Oct 19, 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
33 changes: 30 additions & 3 deletions metadata-ingestion/src/datahub/ingestion/source/sql/presto_on_hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,6 +121,11 @@ class PrestoOnHiveConfig(BasicSQLAlchemyConfig):
description="Dataset Subtype name to be 'Table' or 'View' Valid options: ['True', 'False']",
)

include_catalog_name_in_ids: bool = Field(
default=False,
description="Add the Presto catalog name (e.g. hive) to the generated dataset urns. `urn:li:dataset:(urn:li:dataPlatform:hive,hive.user.logging_events,PROD)` versus `urn:li:dataset:(urn:li:dataPlatform:hive,user.logging_events,PROD)`",
)

def get_sql_alchemy_url(self, uri_opts: Optional[Dict[str, Any]] = None) -> str:
if not ((self.host_port and self.scheme) or self.sqlalchemy_uri):
raise ValueError("host_port and schema or connect_uri required.")
Expand Down Expand Up @@ -407,9 +412,17 @@ def loop_tables(
iter_res = self._alchemy_client.execute_query(statement)

for key, group in groupby(iter_res, self._get_table_key):
db_name = self.get_db_name(inspector)
schema_name = (
f"{db_name}.{key.schema}"
if self.config.include_catalog_name_in_ids
else key.schema
)

dataset_name = self.get_identifier(
schema=key.schema, entity=key.table, inspector=inspector
schema=schema_name, entity=key.table, inspector=inspector
)

self.report.report_entity_scanned(dataset_name, ent_type="table")

if not sql_config.table_pattern.allowed(dataset_name):
Expand Down Expand Up @@ -521,8 +534,14 @@ def get_hive_view_columns(self, inspector: Inspector) -> Iterable[ViewDataset]:

iter_res = self._alchemy_client.execute_query(statement)
for key, group in groupby(iter_res, self._get_table_key):
db_name = self.get_db_name(inspector)
schema_name = (
f"{db_name}.{key.schema}"
if self.config.include_catalog_name_in_ids
else key.schema
)
dataset_name = self.get_identifier(
schema=key.schema, entity=key.table, inspector=inspector
schema=schema_name, entity=key.table, inspector=inspector
)
columns = list(group)

Expand Down Expand Up @@ -553,8 +572,16 @@ def get_presto_view_columns(self, inspector: Inspector) -> Iterable[ViewDataset]

iter_res = self._alchemy_client.execute_query(statement)
for row in iter_res:
db_name = self.get_db_name(inspector)
schema_name = (
f"{db_name}.{row['schema']}"
if self.config.include_catalog_name_in_ids
else row["schema"]
)
dataset_name = self.get_identifier(
schema=row["schema"], entity=row["name"], inspector=inspector
schema=schema_name,
entity=row["name"],
inspector=inspector,
)

columns, view_definition = self._get_presto_view_column_metadata(
Expand Down
Loading