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 aa361d14 Test, write subset of schema (#704)
aa361d14 is described below
commit aa361d1485f4a914bc0bbc2e574becaec9a773ac
Author: Kevin Liu <[email protected]>
AuthorDate: Thu May 9 09:29:26 2024 -0700
Test, write subset of schema (#704)
---
tests/integration/test_writes/test_writes.py | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/tests/integration/test_writes/test_writes.py
b/tests/integration/test_writes/test_writes.py
index a4a93396..74b6857d 100644
--- a/tests/integration/test_writes/test_writes.py
+++ b/tests/integration/test_writes/test_writes.py
@@ -857,3 +857,15 @@ def test_sanitize_character_partitioned(catalog: Catalog)
-> None:
)
assert len(tbl.scan().to_arrow()) == 22
+
+
[email protected]("format_version", [1, 2])
+def table_write_subset_of_schema(session_catalog: Catalog,
arrow_table_with_null: pa.Table, format_version: int) -> None:
+ identifier = "default.table_append_subset_of_schema"
+ tbl = _create_table(session_catalog, identifier, {"format-version":
format_version}, [arrow_table_with_null])
+ arrow_table_without_some_columns =
arrow_table_with_null.combine_chunks().drop(arrow_table_with_null.column_names[0])
+ assert len(arrow_table_without_some_columns.columns) <
len(arrow_table_with_null.columns)
+ tbl.overwrite(arrow_table_without_some_columns)
+ tbl.append(arrow_table_without_some_columns)
+ # overwrite and then append should produce twice the data
+ assert len(tbl.scan().to_arrow()) == len(arrow_table_without_some_columns)
* 2
