Skip to content

Handle empty decimal columns #2306

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
wants to merge 2 commits into
base: main
Choose a base branch
from
+25 −4
Open

Handle empty decimal columns #2306

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d1842a0
Handle empty decimal columns
berg2043 Aug 11, 2025
a7512c6
explicitly check for none
berg2043 Aug 14, 2025
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: 6 additions & 2 deletions pyiceberg/io/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2445,8 +2445,12 @@ def data_file_statistics_from_parquet_metadata(

if isinstance(stats_col.iceberg_type, DecimalType) and statistics.physical_type != "FIXED_LEN_BYTE_ARRAY":
scale = stats_col.iceberg_type.scale
col_aggs[field_id].update_min(unscaled_to_decimal(statistics.min_raw, scale))
col_aggs[field_id].update_max(unscaled_to_decimal(statistics.max_raw, scale))
col_aggs[field_id].update_min(
unscaled_to_decimal(statistics.min_raw, scale)
) if statistics.min_raw else None
col_aggs[field_id].update_max(
unscaled_to_decimal(statistics.max_raw, scale)
) if statistics.max_raw else None
else:
col_aggs[field_id].update_min(statistics.min)
col_aggs[field_id].update_max(statistics.max)
Expand Down
21 changes: 19 additions & 2 deletions tests/io/test_pyarrow_stats.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,6 +450,9 @@ def construct_test_table_primitive_types() -> Tuple[pq.FileMetaData, Union[Table
{"id": 13, "name": "decimal8", "required": False, "type": "decimal(5, 2)"},
{"id": 14, "name": "decimal16", "required": False, "type": "decimal(16, 6)"},
{"id": 15, "name": "decimal32", "required": False, "type": "decimal(19, 6)"},
{"id": 16, "name": "empty_decimal8", "required": False, "type": "decimal(5, 2)"},
{"id": 17, "name": "empty_decimal16", "required": False, "type": "decimal(16, 6)"},
{"id": 18, "name": "empty_decimal32", "required": False, "type": "decimal(19, 6)"},
],
},
],
Expand Down Expand Up @@ -477,6 +480,9 @@ def construct_test_table_primitive_types() -> Tuple[pq.FileMetaData, Union[Table
decimal8 = pa.array([Decimal("123.45"), Decimal("678.91")], pa.decimal128(8, 2))
decimal16 = pa.array([Decimal("12345679.123456"), Decimal("67891234.678912")], pa.decimal128(16, 6))
decimal32 = pa.array([Decimal("1234567890123.123456"), Decimal("9876543210703.654321")], pa.decimal128(19, 6))
empty_decimal8 = pa.array([None, None], pa.decimal128(8, 2))
empty_decimal16 = pa.array([None, None], pa.decimal128(16, 6))
empty_decimal32 = pa.array([None, None], pa.decimal128(19, 6))

table = pa.Table.from_pydict(
{
Expand All @@ -495,6 +501,9 @@ def construct_test_table_primitive_types() -> Tuple[pq.FileMetaData, Union[Table
"decimal8": decimal8,
"decimal16": decimal16,
"decimal32": decimal32,
"empty_decimal8": empty_decimal8,
"empty_decimal16": empty_decimal16,
"empty_decimal32": empty_decimal32,
},
schema=arrow_schema,
)
Expand All @@ -520,8 +529,14 @@ def test_metrics_primitive_types() -> None:
)
datafile = DataFile.from_args(**statistics.to_serialized_dict())

assert len(datafile.value_counts) == 15
assert len(datafile.null_value_counts) == 15
assert len(datafile.value_counts) == 18
assert len(datafile.null_value_counts) == 18
assert datafile.null_value_counts[13] != datafile.value_counts[13]
assert datafile.null_value_counts[14] != datafile.value_counts[14]
assert datafile.null_value_counts[15] != datafile.value_counts[15]
assert datafile.null_value_counts[16] == datafile.value_counts[16]
assert datafile.null_value_counts[17] == datafile.value_counts[17]
assert datafile.null_value_counts[18] == datafile.value_counts[18]
assert len(datafile.nan_value_counts) == 0

tz = timezone(timedelta(seconds=19800))
Expand All @@ -542,6 +557,7 @@ def test_metrics_primitive_types() -> None:
assert datafile.lower_bounds[13][::-1].ljust(4, b"\x00") == STRUCT_INT32.pack(12345)
assert datafile.lower_bounds[14][::-1].ljust(8, b"\x00") == STRUCT_INT64.pack(12345679123456)
assert str(int.from_bytes(datafile.lower_bounds[15], byteorder="big", signed=True)).encode("utf-8") == b"1234567890123123456"
assert not any(key in datafile.lower_bounds.keys() for key in [16, 17, 18])

assert len(datafile.upper_bounds) == 15
assert datafile.upper_bounds[1] == STRUCT_BOOL.pack(True)
Expand All @@ -559,6 +575,7 @@ def test_metrics_primitive_types() -> None:
assert datafile.upper_bounds[13][::-1].ljust(4, b"\x00") == STRUCT_INT32.pack(67891)
assert datafile.upper_bounds[14][::-1].ljust(8, b"\x00") == STRUCT_INT64.pack(67891234678912)
assert str(int.from_bytes(datafile.upper_bounds[15], byteorder="big", signed=True)).encode("utf-8") == b"9876543210703654321"
assert not any(key in datafile.upper_bounds.keys() for key in [16, 17, 18])


def construct_test_table_invalid_upper_bound() -> Tuple[pq.FileMetaData, Union[TableMetadataV1, TableMetadataV2]]:
Expand Down