milenkovicm commented on code in PR #2748:
URL:
https://github.com/apache/datafusion-ballista/pull/2748#discussion_r4482697466
##########
python/python/tests/test_context.py:
##########
@@ -302,6 +302,37 @@ def test_sql_explain_analyze(ctx):
assert "output_rows" in plan
+NOT_IN_QUERY = "SELECT a FROM t WHERE a NOT IN (SELECT b FROM s)"
+
+
+def register_not_in_tables(ctx, tmp_path):
+ pq.write_table(pa.table({"a": [1, 2, 3, 4, None]}), tmp_path / "t.parquet")
+ pq.write_table(pa.table({"b": [2, 4]}), tmp_path / "s.parquet")
+ ctx.register_parquet("t", str(tmp_path / "t.parquet"))
+ ctx.register_parquet("s", str(tmp_path / "s.parquet"))
+ ctx.sql("SET datafusion.optimizer.prefer_hash_join = true").collect()
+
+
+def test_not_in_subquery(ctx, tmp_path):
+ register_not_in_tables(ctx, tmp_path)
+ result = to_table(ctx.sql(NOT_IN_QUERY))
+ assert sorted(result.column("a").to_pylist()) == [1, 3]
+
+
[email protected](
Review Comment:
created a big task tracking all known issues
https://github.com/apache/datafusion-ballista/issues/2781
--
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]
