From 599a8c6e2bf7da70b20ef3046f5ce099dfd637f8 Mon Sep 17 00:00:00 2001 From: David Tolpin Date: Thu, 19 Nov 2015 13:57:23 -0800 Subject: [SPARK-11812][PYSPARK] invFunc=None works properly with python's reduceByKeyAndWindow invFunc is optional and can be None. Instead of invFunc (the parameter) invReduceFunc (a local function) was checked for trueness (that is, not None, in this context). A local function is never None, thus the case of invFunc=None (a common one when inverse reduction is not defined) was treated incorrectly, resulting in loss of data. In addition, the docstring used wrong parameter names, also fixed. Author: David Tolpin Closes #9775 from dtolpin/master. --- python/pyspark/streaming/dstream.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'python/pyspark/streaming/dstream.py') diff --git a/python/pyspark/streaming/dstream.py b/python/pyspark/streaming/dstream.py index 698336cfce..acec850f02 100644 --- a/python/pyspark/streaming/dstream.py +++ b/python/pyspark/streaming/dstream.py @@ -524,8 +524,8 @@ class DStream(object): `invFunc` can be None, then it will reduce all the RDDs in window, could be slower than having `invFunc`. - @param reduceFunc: associative reduce function - @param invReduceFunc: inverse function of `reduceFunc` + @param func: associative reduce function + @param invFunc: inverse function of `reduceFunc` @param windowDuration: width of the window; must be a multiple of this DStream's batching interval @param slideDuration: sliding interval of the window (i.e., the interval after which @@ -556,7 +556,7 @@ class DStream(object): if kv[1] is not None else kv[0]) jreduceFunc = TransformFunction(self._sc, reduceFunc, reduced._jrdd_deserializer) - if invReduceFunc: + if invFunc: jinvReduceFunc = TransformFunction(self._sc, invReduceFunc, reduced._jrdd_deserializer) else: jinvReduceFunc = None -- cgit v1.2.3