From 1f1819b20f887b487557c31e54b8bcd95b582dc6 Mon Sep 17 00:00:00 2001 From: Josh Rosen Date: Mon, 18 Aug 2014 20:42:19 -0700 Subject: [SPARK-3114] [PySpark] Fix Python UDFs in Spark SQL. This fixes SPARK-3114, an issue where we inadvertently broke Python UDFs in Spark SQL. This PR modifiers the test runner script to always run the PySpark SQL tests, irrespective of whether SparkSQL itself has been modified. It also includes Davies' fix for the bug. Closes #2026. Author: Josh Rosen Author: Davies Liu Closes #2027 from JoshRosen/pyspark-sql-fix and squashes the following commits: 9af2708 [Davies Liu] bugfix: disable compression of command 0d8d3a4 [Josh Rosen] Always run Python Spark SQL tests. --- python/pyspark/worker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'python/pyspark/worker.py') diff --git a/python/pyspark/worker.py b/python/pyspark/worker.py index 77a9c4a0e0..6805063e06 100644 --- a/python/pyspark/worker.py +++ b/python/pyspark/worker.py @@ -72,7 +72,7 @@ def main(infile, outfile): value = ser._read_with_length(infile) _broadcastRegistry[bid] = Broadcast(bid, value) - command = ser._read_with_length(infile) + command = pickleSer._read_with_length(infile) (func, deserializer, serializer) = command init_time = time.time() iterator = deserializer.load_stream(infile) -- cgit v1.2.3