From 762ba0bf1c0025b8a0209e027814d6abc42ebbc3 Mon Sep 17 00:00:00 2001 From: Kan Zhang Date: Sat, 10 May 2014 14:01:08 -0700 Subject: [PATCH] [SPARK-1690] Tolerating empty elements when saving Python RDD to text files Tolerate empty strings in PythonRDD Author: Kan Zhang Closes #644 from kanzhang/SPARK-1690 and squashes the following commits: c62ad33 [Kan Zhang] Adding Python doctest 473ec4b [Kan Zhang] [SPARK-1690] Tolerating empty elements when saving Python RDD to text files --- .../scala/org/apache/spark/api/python/PythonRDD.scala | 5 +++-- python/pyspark/rdd.py | 8 ++++++++ 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala index 388b838d78bba..2971c277aa863 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala @@ -94,6 +94,7 @@ private[spark] class PythonRDD[T: ClassTag]( val obj = new Array[Byte](length) stream.readFully(obj) obj + case 0 => Array.empty[Byte] case SpecialLengths.TIMING_DATA => // Timing data from worker val bootTime = stream.readLong() @@ -123,7 +124,7 @@ private[spark] class PythonRDD[T: ClassTag]( stream.readFully(update) accumulator += Collections.singletonList(update) } - Array.empty[Byte] + null } } catch { @@ -143,7 +144,7 @@ private[spark] class PythonRDD[T: ClassTag]( var _nextObj = read() - def hasNext = _nextObj.length != 0 + def hasNext = _nextObj != null } new InterruptibleIterator(context, stdoutIterator) } diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 3a1c56af5b221..4f74824ba4cf2 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -891,6 +891,14 @@ def saveAsTextFile(self, path): >>> from glob import glob >>> ''.join(sorted(input(glob(tempFile.name + "/part-0000*")))) '0\\n1\\n2\\n3\\n4\\n5\\n6\\n7\\n8\\n9\\n' + + Empty lines are tolerated when saving to text files. + + >>> tempFile2 = NamedTemporaryFile(delete=True) + >>> tempFile2.close() + >>> sc.parallelize(['', 'foo', '', 'bar', '']).saveAsTextFile(tempFile2.name) + >>> ''.join(sorted(input(glob(tempFile2.name + "/part-0000*")))) + '\\n\\n\\nbar\\nfoo\\n' """ def func(split, iterator): for x in iterator: