Skip to content
Open
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
6 changes: 4 additions & 2 deletions pyiceberg/partitioning.py
Original file line number Diff line number Diff line change
Expand Up @@ -546,8 +546,10 @@ def _(type: IcebergType, value: int | date | None) -> int | None:


@_to_partition_representation.register(TimeType)
def _(type: IcebergType, value: time | None) -> int | None:
return time_to_micros(value) if value is not None else None
def _(type: IcebergType, value: int | time | None) -> int | None:
if value is None or isinstance(value, int):
return value
return time_to_micros(value)


@_to_partition_representation.register(UUIDType)
Expand Down
38 changes: 36 additions & 2 deletions tests/io/test_pyarrow.py
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
import uuid
import warnings
from collections.abc import Iterator
from datetime import date, datetime, timezone
from datetime import date, datetime, time, timezone
from pathlib import Path
from typing import Any
from unittest.mock import MagicMock, patch
Expand Down Expand Up @@ -93,7 +93,7 @@
from pyiceberg.table import FileScanTask, TableProperties, WriteTask
from pyiceberg.table.metadata import TableMetadataV2
from pyiceberg.table.name_mapping import create_mapping_from_schema
from pyiceberg.transforms import HourTransform, IdentityTransform
from pyiceberg.transforms import BucketTransform, HourTransform, IdentityTransform
from pyiceberg.typedef import UTF8, Properties, Record, TableVersion
from pyiceberg.types import (
BinaryType,
Expand Down Expand Up @@ -2784,6 +2784,40 @@ def test_partition_for_demo() -> None:
)


@pytest.mark.parametrize("format_version", [1, 2])
def test_append_time_bucket_partition(tmp_path: Path, format_version: int) -> None:
schema = Schema(NestedField(1, "event_time", TimeType(), required=False))
spec = PartitionSpec(PartitionField(1, 1000, BucketTransform(16), "event_time_bucket"))
data = pa.table(
{"event_time": [time(0), time(12, 34, 56, 123456), time(23, 59, 59, 999999), None, time(0)]},
schema=schema.as_arrow(),
)

with InMemoryCatalog("test", warehouse=tmp_path.as_uri()) as catalog:
catalog.create_namespace("default")
table = catalog.create_table(
"default.events", schema=schema, partition_spec=spec, properties={"format-version": str(format_version)}
)
table.append(data)

rows = table.scan().to_arrow()["event_time"].to_pylist()
assert rows.count(None) == 1
assert sorted(value for value in rows if value is not None) == sorted(
value for value in data["event_time"].to_pylist() if value is not None
)

files = table.inspect.data_files().to_pylist()
assert {file["partition"]["event_time_bucket"]: file["record_count"] for file in files} == {
12: 2,
11: 1,
8: 1,
None: 1,
}
for file in files:
bucket = file["partition"]["event_time_bucket"]
assert f"/event_time_bucket={bucket if bucket is not None else 'null'}/" in file["file_path"]


def test_partition_for_nested_field() -> None:
schema = Schema(
NestedField(id=1, name="foo", field_type=StringType(), required=True),
Expand Down
18 changes: 17 additions & 1 deletion tests/test_transforms.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
# under the License.
# pylint: disable=eval-used,protected-access,redefined-outer-name
from collections.abc import Callable
from datetime import date, datetime
from datetime import date, datetime, time
from decimal import Decimal
from typing import Annotated, Any
from uuid import UUID
Expand Down Expand Up @@ -1643,6 +1643,22 @@ def test_to_partition_representation_timestamps(source_type: PrimitiveType, valu
assert _to_partition_representation(source_type, value) == expected


@pytest.mark.parametrize(
"value, expected",
[
pytest.param(None, None, id="none"),
pytest.param(time(0), 0, id="midnight"),
pytest.param(time(12, 34, 56, 123456), 45_296_123_456, id="microseconds"),
pytest.param(time(23, 59, 59, 999999), 86_399_999_999, id="end_of_day"),
pytest.param(0, 0, id="zero_int_passthrough"),
pytest.param(12, 12, id="bucket_int_passthrough"),
pytest.param(86_399_999_999, 86_399_999_999, id="time_int_passthrough"),
],
)
def test_to_partition_representation_time(value: int | time | None, expected: int | None) -> None:
assert _to_partition_representation(TimeType(), value) == expected


def test_to_partition_representation_unrecognized_type_raises() -> None:
with pytest.raises(ValueError, match="Type not recognized"):
_to_partition_representation(TimestampType(), "not-a-datetime-or-int")
Expand Down
Loading