rdblue commented on code in PR #6437:
URL: https://github.com/apache/iceberg/pull/6437#discussion_r1051661637
##########
python/tests/io/test_pyarrow.py:
##########
@@ -572,3 +581,388 @@ def test_always_true_to_pyarrow(bound_reference:
BoundReference[str]) -> None:
def test_always_false_to_pyarrow(bound_reference: BoundReference[str]) -> None:
assert repr(expression_to_pyarrow(AlwaysFalse())) ==
"<pyarrow.compute.Expression false>"
+
+
[email protected]
+def schema_int() -> Schema:
+ return Schema(NestedField(1, "id", IntegerType()), schema_id=1)
+
+
[email protected]
+def schema_str() -> Schema:
+ return Schema(NestedField(2, "data", IntegerType()), schema_id=1)
+
+
[email protected]
+def schema_long() -> Schema:
+ return Schema(NestedField(3, "id", LongType()), schema_id=1)
+
+
[email protected]
+def table_int(schema_int: Schema, tmpdir: str) -> str:
+ pyarrow_schema = pa.schema(schema_to_pyarrow(schema_int),
metadata={"iceberg.schema": schema_int.json()})
+
+ target_file = f"file:{tmpdir}/a.parquet"
+
+ with pq.ParquetWriter(target_file, pyarrow_schema) as writer:
+ writer.write_table(pa.Table.from_arrays([pa.array([0, 1, 2])],
schema=pyarrow_schema))
+
+ return target_file
+
+
[email protected]
+def table_str(schema_str: Schema, tmpdir: str) -> str:
+ pyarrow_schema = pa.schema(schema_to_pyarrow(schema_str),
metadata={"iceberg.schema": schema_str.json()})
+
+ target_file = f"file:{tmpdir}/b.parquet"
+
+ with pq.ParquetWriter(target_file, pyarrow_schema) as writer:
+ writer.write_table(pa.Table.from_arrays([pa.array([0, 1, 2])],
schema=pyarrow_schema))
+
+ return target_file
+
+
[email protected]
+def table_long(schema_long: Schema, tmpdir: str) -> str:
+ pyarrow_schema = pa.schema(schema_to_pyarrow(schema_long),
metadata={"iceberg.schema": schema_long.json()})
+
+ target_file = f"file:{tmpdir}/c.parquet"
+
+ with pq.ParquetWriter(target_file, pyarrow_schema) as writer:
+ writer.write_table(pa.Table.from_arrays([pa.array([0, 1, 2])],
schema=pyarrow_schema))
+
+ return target_file
+
+
+def test_projection_add_column(schema_int: Schema, table_int: str) -> None:
+ schema = Schema(
Review Comment:
These appear to be the only tests with nested types. I think we want to test
that nested structs can also be projected.
--
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]
