ndrluis commented on code in PR #2881:
URL: https://github.com/apache/iceberg-python/pull/2881#discussion_r2662701292
##########
tests/integration/test_writes/test_writes.py:
##########
@@ -2530,3 +2530,63 @@ def test_v3_write_and_read_row_lineage(spark:
SparkSession, session_catalog: Cat
assert tbl.metadata.next_row_id == initial_next_row_id + len(test_data), (
"Expected next_row_id to be incremented by the number of added rows"
)
+
+
[email protected]
+def test_write_uuid_in_pyiceberg_and_scan(session_catalog: Catalog, spark:
SparkSession) -> None:
+ """Test UUID compatibility between PyIceberg and Spark.
+
+ UUIDs must be written as binary(16) for Spark compatibility since Java
Arrow
+ metadata differs from Python Arrow metadata for UUID types.
+ """
+ identifier = "default.test_write_uuid_in_pyiceberg_and_scan"
+
+ catalog = load_catalog("default", type="in-memory")
+ catalog.create_namespace("ns")
+
+ schema = Schema(NestedField(field_id=1, name="uuid_col",
field_type=UUIDType(), required=False))
+
+ test_data_with_null = {
+ "uuid_col": [
+ uuid.UUID("00000000-0000-0000-0000-000000000000").bytes,
+ None,
+ uuid.UUID("11111111-1111-1111-1111-111111111111").bytes,
+ ]
+ }
+
+ try:
+ session_catalog.drop_table(identifier=identifier)
+ except NoSuchTableError:
+ pass
+
+ table = _create_table(session_catalog, identifier, {"format-version":
"2"}, schema=schema)
+
+ arrow_table = pa.table(test_data_with_null, schema=schema.as_arrow())
+
+ # Write with pyarrow
+ table.append(arrow_table)
+
+ # Write with pyspark
+ spark.sql(
+ f"""
+ INSERT INTO {identifier} VALUES
("22222222-2222-2222-2222-222222222222")
+ """
+ )
+ df = spark.table(identifier)
+
+ table.refresh()
+
+ assert df.count() == 4
+ assert len(table.scan().to_arrow()) == 4
+
+ result = df.where("uuid_col = '00000000-0000-0000-0000-000000000000'")
+ assert result.count() == 1
Review Comment:
The stacktrace has changed because of the fix that I made in the Java
implementation. This PR (https://github.com/apache/iceberg/pull/14027) has more
details about the problem and in the issue
https://github.com/apache/iceberg-python/issues/2372 I explain the problem from
the pyiceberg side and why we are changing back to binary(16).
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
