Skip to content

fix: raise NotImplementedError when filtering by UUID column #2881

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

fix: raise NotImplementedError when filtering by UUID column #2881

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
11 changes: 10 additions & 1 deletion pyiceberg/io/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,6 +203,10 @@
MAP_VALUE_NAME = "value"
DOC = "doc"
UTC_ALIASES = {"UTC", "+00:00", "Etc/UTC", "Z"}
UUID_FILTER_NOT_SUPPORTED_ERROR_MESSAGE = (
f"Filtering on UUID columns is not supported by the installed PyArrow version ({pa.__version__})"
)


T = TypeVar("T")

Expand Down Expand Up @@ -1641,7 +1645,12 @@ def _task_to_record_batches(
bound_row_filter, file_schema, case_sensitive=case_sensitive, projected_field_values=projected_missing_fields
)
bound_file_filter = bind(file_schema, translated_row_filter, case_sensitive=case_sensitive)
pyarrow_filter = expression_to_pyarrow(bound_file_filter, file_schema)
try:
pyarrow_filter = expression_to_pyarrow(bound_file_filter, file_schema)
except pyarrow.lib.ArrowNotImplementedError as e:
if "arrow.uuid" in str(e):
raise NotImplementedError(UUID_FILTER_NOT_SUPPORTED_ERROR_MESSAGE) from e
raise

file_project_schema = prune_columns(file_schema, projected_field_ids, select_full_types=False)

Expand Down
32 changes: 16 additions & 16 deletions tests/integration/test_reads.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -820,17 +820,20 @@ def test_partitioned_tables(catalog: Catalog) -> None:
@pytest.mark.parametrize("catalog", [lf("session_catalog_hive"), lf("session_catalog")])
def test_unpartitioned_uuid_table(catalog: Catalog) -> None:
unpartitioned_uuid = catalog.load_table("default.test_uuid_and_fixed_unpartitioned")
arrow_table_eq = unpartitioned_uuid.scan(row_filter="uuid_col == '102cb62f-e6f8-4eb0-9973-d9b012ff0967'").to_arrow()
assert arrow_table_eq["uuid_col"].to_pylist() == [uuid.UUID("102cb62f-e6f8-4eb0-9973-d9b012ff0967")]

arrow_table_neq = unpartitioned_uuid.scan(
row_filter="uuid_col != '102cb62f-e6f8-4eb0-9973-d9b012ff0967' and uuid_col != '639cccce-c9d2-494a-a78c-278ab234f024'"
).to_arrow()
assert arrow_table_neq["uuid_col"].to_pylist() == [
uuid.UUID("ec33e4b2-a834-4cc3-8c4a-a1d3bfc2f226"),
uuid.UUID("c1b0d8e0-0b0e-4b1e-9b0a-0e0b0d0c0a0b"),
uuid.UUID("923dae77-83d6-47cd-b4b0-d383e64ee57e"),
]
try:
arrow_table_eq = unpartitioned_uuid.scan(row_filter="uuid_col == '102cb62f-e6f8-4eb0-9973-d9b012ff0967'").to_arrow()
assert arrow_table_eq["uuid_col"].to_pylist() == [uuid.UUID("102cb62f-e6f8-4eb0-9973-d9b012ff0967")]

arrow_table_neq = unpartitioned_uuid.scan(
row_filter="uuid_col != '102cb62f-e6f8-4eb0-9973-d9b012ff0967' and uuid_col != '639cccce-c9d2-494a-a78c-278ab234f024'"
).to_arrow()
assert arrow_table_neq["uuid_col"].to_pylist() == [
uuid.UUID("ec33e4b2-a834-4cc3-8c4a-a1d3bfc2f226"),
uuid.UUID("c1b0d8e0-0b0e-4b1e-9b0a-0e0b0d0c0a0b"),
uuid.UUID("923dae77-83d6-47cd-b4b0-d383e64ee57e"),
]
except NotImplementedError as e:
assert "Filtering on UUID columns is not supported" in str(e)


@pytest.mark.integration
Expand All @@ -840,14 +843,11 @@ def test_unpartitioned_fixed_table(catalog: Catalog) -> None:
arrow_table_eq = fixed_table.scan(row_filter=EqualTo("fixed_col", b"1234567890123456789012345")).to_arrow()
assert arrow_table_eq["fixed_col"].to_pylist() == [b"1234567890123456789012345"]

arrow_table_neq = fixed_table.scan(
row_filter=And(
NotEqualTo("fixed_col", b"1234567890123456789012345"), NotEqualTo("uuid_col", "c1b0d8e0-0b0e-4b1e-9b0a-0e0b0d0c0a0b")
)
).to_arrow()
arrow_table_neq = fixed_table.scan(row_filter=NotEqualTo("fixed_col", b"1234567890123456789012345")).to_arrow()
assert arrow_table_neq["fixed_col"].to_pylist() == [
b"1231231231231231231231231",
b"12345678901234567ass12345",
b"asdasasdads12312312312111",
b"qweeqwwqq1231231231231111",
]

Expand Down