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.

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/vertica): Fixing missing container properties #7197

Merged
merged 1 commit into from
Jan 31, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
import json
import logging
import typing
from typing import Dict, Iterable, List, Optional, Tuple, cast
from typing import Any, Dict, Iterable, List, Optional, Tuple, cast

import pydantic
from pyathena.common import BaseCursor
Expand Down Expand Up @@ -186,6 +186,7 @@ def get_table_properties(
def gen_database_containers(
self,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
# In Athena the schema is the database and database is not existing
return []
Expand All @@ -194,6 +195,7 @@ def gen_schema_containers(
self,
schema: str,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
database_container_key = gen_database_key(
database,
Expand All @@ -209,6 +211,7 @@ def gen_schema_containers(
domain_registry=self.domain_registry,
domain_config=self.config.domain,
report=self.report,
extra_properties=extra_properties,
)

def get_database_container_key(self, db_name: str, schema: str) -> PlatformKey:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,7 @@ def create(cls, config_dict, ctx):
def gen_database_containers(
self,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
database_container_key = gen_database_key(
database,
Expand All @@ -340,12 +341,14 @@ def gen_database_containers(
domain_registry=self.domain_registry,
domain_config=self.config.domain,
report=self.report,
extra_properties=extra_properties,
)

def gen_schema_containers(
self,
schema: str,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
assert isinstance(self.config, PrestoOnHiveConfig)
where_clause_suffix: str = ""
Expand Down Expand Up @@ -394,6 +397,7 @@ def gen_schema_containers(
domain_registry=self.domain_registry,
domain_config=self.config.domain,
report=self.report,
extra_properties=extra_properties,
)

def get_default_ingestion_job_id(self) -> JobId:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -417,6 +417,7 @@ def get_allowed_schemas(self, inspector: Inspector, db_name: str) -> Iterable[st
def gen_database_containers(
self,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
database_container_key = gen_database_key(
database,
Expand All @@ -432,12 +433,14 @@ def gen_database_containers(
domain_registry=self.domain_registry,
domain_config=self.config.domain,
report=self.report,
extra_properties=extra_properties,
)

def gen_schema_containers(
self,
schema: str,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:

database_container_key = gen_database_key(
Expand All @@ -464,6 +467,7 @@ def gen_schema_containers(
domain_registry=self.domain_registry,
domain_config=self.config.domain,
report=self.report,
extra_properties=extra_properties,
)

def add_table_to_schema_container(
Expand Down Expand Up @@ -517,6 +521,9 @@ def get_workunits_internal(self) -> Iterable[Union[MetadataWorkUnit, SqlWorkUnit
yield from self.gen_schema_containers(
database=db_name,
schema=schema,
extra_properties=self.get_schema_properties(
inspector=inspector, schema=schema, database=db_name
),
)

if sql_config.include_tables:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
import typing
from typing import Iterable, Optional
from typing import Any, Dict, Iterable, Optional

from pydantic.fields import Field
from sqlalchemy import create_engine, inspect
Expand Down Expand Up @@ -116,6 +116,7 @@ def gen_schema_containers(
self,
schema: str,
database: str,
extra_properties: Optional[Dict[str, Any]] = None,
) -> Iterable[MetadataWorkUnit]:
return []

Expand Down
15 changes: 13 additions & 2 deletions metadata-ingestion/src/datahub/ingestion/source/sql/vertica.py
Original file line number Diff line number Diff line change
Expand Up @@ -163,12 +163,23 @@ def get_workunits(self) -> Iterable[Union[MetadataWorkUnit, SqlWorkUnit]]:
profiler = self.get_profiler_instance(inspector)

db_name = self.get_db_name(inspector)
yield from self.gen_database_containers(database=db_name)
yield from self.gen_database_containers(
database=db_name,
extra_properties=self.get_database_properties(
inspector=inspector, database=db_name
),
)

for schema in self.get_allowed_schemas(inspector, db_name):
self.add_information_for_schema(inspector, schema)

yield from self.gen_schema_containers(schema=schema, database=db_name)
yield from self.gen_schema_containers(
schema=schema,
database=db_name,
extra_properties=self.get_schema_properties(
inspector=inspector, schema=schema, database=db_name
),
)

if sql_config.include_tables:
yield from self.loop_tables(inspector, schema, sql_config)
Expand Down