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(ingestion): correct trino datatype handling #5541

Merged
merged 3 commits into from
Aug 4, 2022
Merged

fix(ingestion): correct trino datatype handling #5541

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
102475c
fix(ingestion): correct trino datatype handling
ms32035 Aug 2, 2022
b2de790
Update unit-tests + add row type for TRINO.
rslanka Aug 3, 2022
ef46c28
Cleanup trino type extraction logic + enhance the unit tests to cover…
rslanka Aug 3, 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
8 changes: 5 additions & 3 deletions metadata-ingestion/src/datahub/ingestion/source/sql/sql_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,9 +228,10 @@ def resolve_postgres_modified_type(type_string: str) -> Any:


def resolve_trino_modified_type(type_string: str) -> Any:
# for cases like timestamp(3)
if re.match(r"[a-zA-Z]+\([0-9]+\)", type_string):
modified_type_base = re.match(r"([a-zA-Z]+)\([0-9]+\)", type_string).group(1) # type: ignore
# for cases like timestamp(3), decimal(10,0), row(...)
match = re.match(r"([a-zA-Z]+)\(.+\)", type_string)
if match:
modified_type_base: str = match.group(1)
return TRINO_SQL_TYPES_MAP[modified_type_base]
else:
return TRINO_SQL_TYPES_MAP[type_string]
Expand Down Expand Up @@ -337,4 +338,5 @@ def resolve_trino_modified_type(type_string: str) -> Any:
"date": DateType,
"time": TimeType,
"timestamp": TimeType,
"row": RecordType,
}
19 changes: 18 additions & 1 deletion metadata-ingestion/tests/integration/dbt/test_dbt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,8 +480,25 @@ def test_dbt_tests(pytestconfig, tmp_path, mock_time, **kwargs):
@pytest.mark.parametrize(
"data_type, expected_data_type",
[
("timestamp(3)", "timestamp"),
("boolean", "boolean"),
("tinyint", "tinyint"),
("smallint", "smallint"),
("int", "int"),
("integer", "integer"),
("bigint", "bigint"),
("real", "real"),
("double", "double"),
("decimal(10,0)", "decimal"),
("varchar(20)", "varchar"),
("char", "char"),
("varbinary", "varbinary"),
("json", "json"),
("date", "date"),
("time", "time"),
("time(12)", "time"),
("timestamp", "timestamp"),
("timestamp(3)", "timestamp"),
("row(x bigint, y double)", "row"),
],
)
def test_resolve_trino_modified_type(data_type, expected_data_type):
Expand Down