[SPARK-9812] [STREAMING] Fix Python 3 compatibility issue in PySpark Streaming and some docs

This PR includes the following fixes:
1. Use `range` instead of `xrange` in `queue_stream.py` to support Python 3.
2. Fix the issue that `utf8_decoder` will return `bytes` rather than `str` when receiving an empty `bytes` in Python 3.
3. Fix the commands in docs so that the user can copy them directly to the command line. The previous commands was broken in the middle of a path, so when copying to the command line, the path would be split to two parts by the extra spaces, which forces the user to fix it manually.

Author: zsxwing <zsxwing@gmail.com>

Closes #8315 from zsxwing/SPARK-9812.

3 files changed, 9 insertions, 3 deletions

diff --git a/python/pyspark/streaming/flume.py b/python/pyspark/streaming/flume.py
index cbb573f226..c0cdc50d8d 100644
--- a/python/pyspark/streaming/flume.py
+++ b/python/pyspark/streaming/flume.py
@@ -31,7 +31,9 @@ __all__ = ['FlumeUtils', 'utf8_decoder']
 
 def utf8_decoder(s):
     """ Decode the unicode as UTF-8 """
-    return s and s.decode('utf-8')
+    if s is None:
+        return None
+    return s.decode('utf-8')
 
 
 class FlumeUtils(object):
diff --git a/python/pyspark/streaming/kafka.py b/python/pyspark/streaming/kafka.py
index dc5b7fd878..8a814c64c0 100644
--- a/python/pyspark/streaming/kafka.py
+++ b/python/pyspark/streaming/kafka.py
@@ -29,7 +29,9 @@ __all__ = ['Broker', 'KafkaUtils', 'OffsetRange', 'TopicAndPartition', 'utf8_dec
 
 def utf8_decoder(s):
     """ Decode the unicode as UTF-8 """
-    return s and s.decode('utf-8')
+    if s is None:
+        return None
+    return s.decode('utf-8')
 
 
 class KafkaUtils(object):
diff --git a/python/pyspark/streaming/kinesis.py b/python/pyspark/streaming/kinesis.py
index bcfe2703fe..34be5880e1 100644
--- a/python/pyspark/streaming/kinesis.py
+++ b/python/pyspark/streaming/kinesis.py
@@ -26,7 +26,9 @@ __all__ = ['KinesisUtils', 'InitialPositionInStream', 'utf8_decoder']
 
 def utf8_decoder(s):
     """ Decode the unicode as UTF-8 """
-    return s and s.decode('utf-8')
+    if s is None:
+        return None
+    return s.decode('utf-8')
 
 
 class KinesisUtils(object):