Github user zero323 commented on a diff in the pull request:
https://github.com/apache/spark/pull/17077#discussion_r110693499
--- Diff: python/pyspark/sql/tests.py ---
@@ -2167,6 +2167,61 @@ 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"])
+
+ # Test write with one bucketing column
+ df.write.bucketBy(3,
"x").mode("overwrite").saveAsTable("pyspark_bucket")
+ self.assertEqual(
+ len([c for c in
self.spark.catalog.listColumns("pyspark_bucket")
+ if c.name == "x" and c.isBucket]),
+ 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(
+ len([c for c in
self.spark.catalog.listColumns("pyspark_bucket")
+ if c.name in ("x", "y") and c.isBucket]),
--- End diff --
If you think it is better I'll trust your judgment.
---
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]
