Skip to content

Core: Preserve empty partition bounds in inspect.manifests #3708

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

Open
fallintoplace wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Core: Preserve empty partition bounds in inspect.manifests #3708

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/table/inspect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -560,7 +560,7 @@ def _partition_summaries_to_rows(
partition_field_type, from_bytes(partition_field_type, field_summary.lower_bound)
)
)
if field_summary.lower_bound
if field_summary.lower_bound is not None
else None
)
upper_bound = (
Expand All @@ -569,7 +569,7 @@ def _partition_summaries_to_rows(
partition_field_type, from_bytes(partition_field_type, field_summary.upper_bound)
)
)
if field_summary.upper_bound
if field_summary.upper_bound is not None
else None
)
rows.append(
Expand Down
13 changes: 13 additions & 0 deletions tests/table/test_inspect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,11 @@

from pyiceberg.conversions import to_bytes
from pyiceberg.manifest import DataFile, DataFileContent
from pyiceberg.partitioning import PartitionField, PartitionSpec
from pyiceberg.schema import Schema
from pyiceberg.table.inspect import InspectTable, _readable_bound
from pyiceberg.table.snapshots import Snapshot
from pyiceberg.transforms import IdentityTransform
from pyiceberg.typedef import Record
from pyiceberg.types import NestedField, StringType
from tests.catalog.test_base import InMemoryCatalog
Expand Down Expand Up @@ -93,3 +95,14 @@ def test_partitions_last_updated_uses_latest_snapshot_regardless_of_order(newest
(partition_row,) = partitions_map.values()
assert partition_row["last_updated_at"] == newer.timestamp_ms
assert partition_row["last_updated_snapshot_id"] == newer.snapshot_id


def test_inspect_manifests_preserves_empty_string_bounds(catalog: InMemoryCatalog) -> None:
schema = Schema(NestedField(1, "s", StringType()))
spec = PartitionSpec(PartitionField(1, 1000, IdentityTransform(), "s"))
tbl = catalog.create_table("default.empty_string_partition", schema, partition_spec=spec)
tbl.append(pa.table({"s": [""]}, schema=pa.schema([pa.field("s", pa.large_string())])))

partition_summary = tbl.inspect.manifests().to_pydict()["partition_summaries"][0][0]
assert partition_summary["lower_bound"] == ""
assert partition_summary["upper_bound"] == ""