Github user zero323 commented on a diff in the pull request:
https://github.com/apache/spark/pull/17077#discussion_r111221795
--- 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 --
@holdenk Do you suggest adding `tearDown`? I thought about it but right now
tests are so inflated (sadly not much support for
[SPARK-19224](https://issues.apache.org/jira/browse/SPARK-19224)) it will be
completely detached from the context.
From the other hand adding artificial `try ... finally` seems wrong.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
