Skip to content

Support string_view and binary_view #1748

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

Merged
kevinjqliu merged 1 commit into from
Mar 3, 2025
Merged

Support string_view and binary_view #1748

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions pyiceberg/io/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1189,7 +1189,7 @@ def primitive(self, primitive: pa.DataType) -> PrimitiveType:
elif isinstance(primitive, pa.Decimal128Type):
primitive = cast(pa.Decimal128Type, primitive)
return DecimalType(primitive.precision, primitive.scale)
elif pa.types.is_string(primitive) or pa.types.is_large_string(primitive):
elif pa.types.is_string(primitive) or pa.types.is_large_string(primitive) or pa.types.is_string_view(primitive):
return StringType()
elif pa.types.is_date32(primitive):
return DateType()
Expand All @@ -1215,7 +1215,7 @@ def primitive(self, primitive: pa.DataType) -> PrimitiveType:
elif primitive.tz is None:
return TimestampType()

elif pa.types.is_binary(primitive) or pa.types.is_large_binary(primitive):
elif pa.types.is_binary(primitive) or pa.types.is_large_binary(primitive) or pa.types.is_binary_view(primitive):
return BinaryType()
elif pa.types.is_fixed_size_binary(primitive):
primitive = cast(pa.FixedSizeBinaryType, primitive)
Expand Down
12 changes: 6 additions & 6 deletions tests/io/test_pyarrow_visitor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,18 +225,18 @@ def test_pyarrow_timestamp_tz_invalid_tz() -> None:
visit_pyarrow(pyarrow_type, _ConvertToIceberg())


def test_pyarrow_string_to_iceberg() -> None:
pyarrow_type = pa.large_string()
@pytest.mark.parametrize("pyarrow_type", [pa.string(), pa.large_string(), pa.string_view()])
def test_pyarrow_string_to_iceberg(pyarrow_type: pa.DataType) -> None:
converted_iceberg_type = visit_pyarrow(pyarrow_type, _ConvertToIceberg())
assert converted_iceberg_type == StringType()
assert visit(converted_iceberg_type, _ConvertToArrowSchema()) == pyarrow_type
assert visit(converted_iceberg_type, _ConvertToArrowSchema()) == pa.large_string()


def test_pyarrow_variable_binary_to_iceberg() -> None:
pyarrow_type = pa.large_binary()
@pytest.mark.parametrize("pyarrow_type", [pa.binary(), pa.large_binary(), pa.binary_view()])
def test_pyarrow_variable_binary_to_iceberg(pyarrow_type: pa.DataType) -> None:
converted_iceberg_type = visit_pyarrow(pyarrow_type, _ConvertToIceberg())
assert converted_iceberg_type == BinaryType()
assert visit(converted_iceberg_type, _ConvertToArrowSchema()) == pyarrow_type
assert visit(converted_iceberg_type, _ConvertToArrowSchema()) == pa.large_binary()


def test_pyarrow_struct_to_iceberg() -> None:
Expand Down