[SPARK-8378] [STREAMING] Add the Python API for Flume

Author: zsxwing <zsxwing@gmail.com>

Closes #6830 from zsxwing/flume-python and squashes the following commits:

78dfdac [zsxwing] Fix the compile error in the test code
f1bf3c0 [zsxwing] Address TD's comments
0449723 [zsxwing] Add sbt goal streaming-flume-assembly/assembly
e93736b [zsxwing] Fix the test case for determine_modules_to_test
9d5821e [zsxwing] Fix pyspark_core dependencies
f9ee681 [zsxwing] Merge branch 'master' into flume-python
7a55837 [zsxwing] Add streaming_flume_assembly to run-tests.py
b96b0de [zsxwing] Merge branch 'master' into flume-python
ce85e83 [zsxwing] Fix incompatible issues for Python 3
01cbb3d [zsxwing] Add import sys
152364c [zsxwing] Fix the issue that StringIO doesn't work in Python 3
14ba0ff [zsxwing] Add flume-assembly for sbt building
b8d5551 [zsxwing] Merge branch 'master' into flume-python
4762c34 [zsxwing] Fix the doc
0336579 [zsxwing] Refactor Flume unit tests and also add tests for Python API
9f33873 [zsxwing] Add the Python API for Flume

1 files changed, 55 insertions, 0 deletions

diff --git a/examples/src/main/python/streaming/flume_wordcount.py b/examples/src/main/python/streaming/flume_wordcount.py
new file mode 100644
index 0000000000..091b64d8c4
--- /dev/null
+++ b/examples/src/main/python/streaming/flume_wordcount.py
@@ -0,0 +1,55 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""
+ Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
+ Usage: flume_wordcount.py <hostname> <port>
+
+ To run this on your local machine, you need to setup Flume first, see
+ https://flume.apache.org/documentation.html
+
+ and then run the example
+    `$ bin/spark-submit --jars external/flume-assembly/target/scala-*/\
+      spark-streaming-flume-assembly-*.jar examples/src/main/python/streaming/flume_wordcount.py \
+      localhost 12345
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext
+from pyspark.streaming import StreamingContext
+from pyspark.streaming.flume import FlumeUtils
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: flume_wordcount.py <hostname> <port>", file=sys.stderr)
+        exit(-1)
+
+    sc = SparkContext(appName="PythonStreamingFlumeWordCount")
+    ssc = StreamingContext(sc, 1)
+
+    hostname, port = sys.argv[1:]
+    kvs = FlumeUtils.createStream(ssc, hostname, int(port))
+    lines = kvs.map(lambda x: x[1])
+    counts = lines.flatMap(lambda line: line.split(" ")) \
+        .map(lambda word: (word, 1)) \
+        .reduceByKey(lambda a, b: a+b)
+    counts.pprint()
+
+    ssc.start()
+    ssc.awaitTermination()