This is an automated email from the ASF dual-hosted git repository.
honahx pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new 7e3e508c Minor fixes, #523 followup (#563)
7e3e508c is described below
commit 7e3e508c96e76a41f65db54cf4e943a99f67ab1e
Author: Kevin Liu <[email protected]>
AuthorDate: Sat Mar 30 19:24:35 2024 -0700
Minor fixes, #523 followup (#563)
---
pyiceberg/table/__init__.py | 5 +++--
tests/catalog/test_sql.py | 5 +----
tests/integration/test_reads.py | 1 -
tests/integration/test_writes.py | 1 -
4 files changed, 4 insertions(+), 8 deletions(-)
diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
index 18fac993..b20ea226 100644
--- a/pyiceberg/table/__init__.py
+++ b/pyiceberg/table/__init__.py
@@ -1131,8 +1131,9 @@ class Table:
_check_schema_compatible(self.schema(), other_schema=df.schema)
# cast if the two schemas are compatible but not equal
- if self.schema().as_arrow() != df.schema:
- df = df.cast(self.schema().as_arrow())
+ table_arrow_schema = self.schema().as_arrow()
+ if table_arrow_schema != df.schema:
+ df = df.cast(table_arrow_schema)
with self.transaction() as txn:
with
txn.update_snapshot(snapshot_properties=snapshot_properties).fast_append() as
update_snapshot:
diff --git a/tests/catalog/test_sql.py b/tests/catalog/test_sql.py
index b20f617e..99b85506 100644
--- a/tests/catalog/test_sql.py
+++ b/tests/catalog/test_sql.py
@@ -197,7 +197,7 @@ def test_create_table_with_pyarrow_schema(
'catalog',
[
lazy_fixture('catalog_memory'),
- # lazy_fixture('catalog_sqlite'),
+ lazy_fixture('catalog_sqlite'),
],
)
def test_write_pyarrow_schema(catalog: SqlCatalog, random_identifier:
Identifier) -> None:
@@ -220,9 +220,6 @@ def test_write_pyarrow_schema(catalog: SqlCatalog,
random_identifier: Identifier
database_name, _table_name = random_identifier
catalog.create_namespace(database_name)
table = catalog.create_table(random_identifier, pyarrow_table.schema)
- print(pyarrow_table.schema)
- print(table.schema().as_struct())
- print()
table.overwrite(pyarrow_table)
diff --git a/tests/integration/test_reads.py b/tests/integration/test_reads.py
index fdc13ae7..c670bc48 100644
--- a/tests/integration/test_reads.py
+++ b/tests/integration/test_reads.py
@@ -274,7 +274,6 @@ def test_ray_nan_rewritten(catalog: Catalog) -> None:
def test_ray_not_nan_count(catalog: Catalog) -> None:
table_test_null_nan_rewritten =
catalog.load_table("default.test_null_nan_rewritten")
ray_dataset =
table_test_null_nan_rewritten.scan(row_filter=NotNaN("col_numeric"),
selected_fields=("idx",)).to_ray()
- print(ray_dataset.take())
assert ray_dataset.count() == 2
diff --git a/tests/integration/test_writes.py b/tests/integration/test_writes.py
index 5d6be0a7..0186e662 100644
--- a/tests/integration/test_writes.py
+++ b/tests/integration/test_writes.py
@@ -480,7 +480,6 @@ def test_write_parquet_other_properties(
properties: Dict[str, Any],
expected_kwargs: Dict[str, Any],
) -> None:
- print(type(mocker))
identifier = "default.test_write_parquet_other_properties"
# The properties we test cannot be checked on the resulting Parquet file,
so we spy on the ParquetWriter call instead
