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

Ignore tables without table_type parameters while loading all iceberg table from Glue and Hive catalog #1332

Merged
merged 2 commits into from
Nov 19, 2024
Merged

Ignore tables without table_type parameters while loading all iceberg table from Glue and Hive catalog #1332

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8d40312
Ignore tables without table_type parameters while loading all iceberg…
Nov 18, 2024
fb449ef
Use TABLE_TYPE
Nov 19, 2024
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
2 changes: 1 addition & 1 deletion pyiceberg/catalog/glue.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -773,4 +773,4 @@ def drop_view(self, identifier: Union[str, Identifier]) -> None:

@staticmethod
def __is_iceberg_table(table: TableTypeDef) -> bool:
return table.get("Parameters", {}).get("table_type", "").lower() == ICEBERG
return table.get("Parameters", {}).get(TABLE_TYPE, "").lower() == ICEBERG
2 changes: 1 addition & 1 deletion pyiceberg/catalog/hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -651,7 +651,7 @@ def list_tables(self, namespace: Union[str, Identifier]) -> List[Identifier]:
for table in open_client.get_table_objects_by_name(
dbname=database_name, tbl_names=open_client.get_all_tables(db_name=database_name)
)
if table.parameters[TABLE_TYPE].lower() == ICEBERG
if table.parameters.get(TABLE_TYPE, "").lower() == ICEBERG
]

def list_namespaces(self, namespace: Union[str, Identifier] = ()) -> List[Identifier]:
Expand Down
10 changes: 10 additions & 0 deletions tests/catalog/test_glue.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,6 +449,7 @@ def test_list_tables(
test_catalog.create_namespace(namespace=database_name)

non_iceberg_table_name = "non_iceberg_table"
non_table_type_table_name = "non_table_type_table"
glue_client = boto3.client("glue", endpoint_url=moto_endpoint_url)
glue_client.create_table(
DatabaseName=database_name,
Expand All @@ -458,12 +459,21 @@ def test_list_tables(
"Parameters": {"table_type": "noniceberg"},
},
)
glue_client.create_table(
DatabaseName=database_name,
TableInput={
"Name": non_table_type_table_name,
"TableType": "OTHER_TABLE_TYPE",
"Parameters": {},
},
)

for table_name in table_list:
test_catalog.create_table((database_name, table_name), table_schema_nested)
loaded_table_list = test_catalog.list_tables(database_name)

assert (database_name, non_iceberg_table_name) not in loaded_table_list
assert (database_name, non_table_type_table_name) not in loaded_table_list
for table_name in table_list:
assert (database_name, table_name) in loaded_table_list

Expand Down
10 changes: 7 additions & 3 deletions tests/catalog/test_hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -919,16 +919,20 @@ def test_list_tables(hive_table: HiveTable) -> None:
tbl3.tableName = "table3"
tbl3.dbName = "database"
tbl3.parameters["table_type"] = "non_iceberg"
tbl4 = deepcopy(hive_table)
tbl4.tableName = "table4"
tbl4.dbName = "database"
tbl4.parameters.pop("table_type")

catalog._client = MagicMock()
catalog._client.__enter__().get_all_tables.return_value = ["table1", "table2", "table3"]
catalog._client.__enter__().get_table_objects_by_name.return_value = [tbl1, tbl2, tbl3]
catalog._client.__enter__().get_all_tables.return_value = ["table1", "table2", "table3", "table4"]
catalog._client.__enter__().get_table_objects_by_name.return_value = [tbl1, tbl2, tbl3, tbl4]

got_tables = catalog.list_tables("database")
assert got_tables == [("database", "table1"), ("database", "table2")]
catalog._client.__enter__().get_all_tables.assert_called_with(db_name="database")
catalog._client.__enter__().get_table_objects_by_name.assert_called_with(
dbname="database", tbl_names=["table1", "table2", "table3"]
dbname="database", tbl_names=["table1", "table2", "table3", "table4"]
)


Expand Down