Github user holdenk commented on a diff in the pull request: https://github.com/apache/spark/pull/17077#discussion_r111214507 --- Diff: python/pyspark/sql/tests.py --- @@ -2167,6 +2167,56 @@ def test_BinaryType_serialization(self): df = self.spark.createDataFrame(data, schema=schema) df.collect() + def test_bucketed_write(self): + data = [ + (1, "foo", 3.0), (2, "foo", 5.0), + (3, "bar", -1.0), (4, "bar", 6.0), + ] + df = self.spark.createDataFrame(data, ["x", "y", "z"]) + + def count_bucketed_cols(names, table="pyspark_bucket"): + """Given a sequence of column names and a table name + query the catalog and return number o columns which are + used for bucketing + """ + cols = self.spark.catalog.listColumns(table) + num = len([c for c in cols if c.name in names and c.isBucket]) + return num + + # Test write with one bucketing column + df.write.bucketBy(3, "x").mode("overwrite").saveAsTable("pyspark_bucket") + self.assertEqual(count_bucketed_cols(["x"]), 1) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + # Test write two bucketing columns + df.write.bucketBy(3, "x", "y").mode("overwrite").saveAsTable("pyspark_bucket") + self.assertEqual(count_bucketed_cols(["x", "y"]), 2) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + # Test write with bucket and sort + df.write.bucketBy(2, "x").sortBy("z").mode("overwrite").saveAsTable("pyspark_bucket") + self.assertEqual(count_bucketed_cols(["x"]), 1) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + # Test write with a list of columns + df.write.bucketBy(3, ["x", "y"]).mode("overwrite").saveAsTable("pyspark_bucket") + self.assertEqual(count_bucketed_cols(["x", "y"]), 2) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + # Test write with bucket and sort with a list of columns + (df.write.bucketBy(2, "x") + .sortBy(["y", "z"]) + .mode("overwrite").saveAsTable("pyspark_bucket")) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + # Test write with bucket and sort with multiple columns + (df.write.bucketBy(2, "x") + .sortBy("y", "z") + .mode("overwrite").saveAsTable("pyspark_bucket")) + self.assertSetEqual(set(data), set(self.spark.table("pyspark_bucket").collect())) + + self.spark.sql("DROP TABLE IF EXISTS pyspark_bucket") --- End diff -- If we're going to drop the table here we should probably put it in a final block.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org