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(ingestion): improve robustness of glue ingestion source #2626

Merged
merged 1 commit into from
Jun 1, 2021
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
fix(ingestion): improve robustness of glue ingestion source
fixes: #2625
  • Loading branch information
thomas.larsson committed May 31, 2021
commit 798dc1296c86f791ca0d69aac4d80db2cf57198c
50 changes: 22 additions & 28 deletions metadata-ingestion/src/datahub/ingestion/source/glue.py
Original file line number Diff line number Diff line change
Expand Up @@ -140,38 +140,32 @@ def create(cls, config_dict, ctx):

def get_workunits(self) -> Iterable[MetadataWorkUnit]:
def get_all_tables() -> List[dict]:
def get_tables_from_database(
database_name: str, tables: List
) -> List[dict]:
kwargs = {"DatabaseName": database_name}
while True:
data = self.glue_client.get_tables(**kwargs)
tables += data["TableList"]
if "NextToken" in data:
kwargs["NextToken"] = data["NextToken"]
else:
break
return tables

def get_tables_from_all_databases() -> List[dict]:
tables = []
kwargs: Dict = {}
while True:
data = self.glue_client.search_tables(**kwargs)
tables += data["TableList"]
if "NextToken" in data:
kwargs["NextToken"] = data["NextToken"]
else:
break
return tables
def get_tables_from_database(database_name: str) -> List[dict]:
new_tables = []
paginator = self.glue_client.get_paginator("get_tables")
for page in paginator.paginate(DatabaseName=database_name):
new_tables += page["TableList"]

return new_tables

def get_database_names() -> List[str]:
database_names = []
paginator = self.glue_client.get_paginator("get_databases")
for page in paginator.paginate():
for db in page["DatabaseList"]:
if self.source_config.database_pattern.allowed(db["Name"]):
database_names.append(db["Name"])

return database_names

if self.source_config.database_pattern.is_fully_specified_allow_list():
all_tables: List[dict] = []
database_names = self.source_config.database_pattern.get_allowed_list()
for database in database_names:
all_tables += get_tables_from_database(database, all_tables)
else:
all_tables = get_tables_from_all_databases()
database_names = get_database_names()

all_tables: List[dict] = []
for database in database_names:
all_tables += get_tables_from_database(database)
return all_tables

tables = get_all_tables()
Expand Down
20 changes: 18 additions & 2 deletions metadata-ingestion/tests/unit/test_glue_source.py
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,20 @@ def test_turn_boto_glue_data_to_metadata_event(self):
stringy_timestamp = datetime.strptime(FROZEN_TIME, "%Y-%m-%d %H:%M:%S")
timestamp = int(datetime.timestamp(stringy_timestamp) * 1000)

response = {
get_databases_response = {
"DatabaseList": [
{
"Name": "datalake_grilled",
"Description": "irrelevant",
"LocationUri": "irrelevant",
"Parameters": {},
"CreateTime": datetime(2015, 1, 1),
"CreateTableDefaultPermissions": [],
"CatalogId": "irrelevant",
},
],
}
get_tables_response = {
"TableList": [
{
"Name": "Barbeque",
Expand All @@ -110,7 +123,10 @@ def test_turn_boto_glue_data_to_metadata_event(self):
}

with Stubber(self.glue_source.glue_client) as stubber:
stubber.add_response("search_tables", response, {})
stubber.add_response("get_databases", get_databases_response, {})
stubber.add_response(
"get_tables", get_tables_response, {"DatabaseName": "datalake_grilled"}
)
actual_work_unit = list(self.glue_source.get_workunits())[0]

expected_metadata_work_unit = create_metadata_work_unit(timestamp)
Expand Down