From 75b9fe4c5ff6f206c6fc9100563d625b39f142ba Mon Sep 17 00:00:00 2001 From: zsxwing Date: Wed, 1 Jul 2015 11:59:24 -0700 Subject: [SPARK-8378] [STREAMING] Add the Python API for Flume Author: zsxwing 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 --- dev/sparktestsupport/modules.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'dev/sparktestsupport') diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py index efe3a897e9..993583e2f4 100644 --- a/dev/sparktestsupport/modules.py +++ b/dev/sparktestsupport/modules.py @@ -203,7 +203,7 @@ streaming_flume_sink = Module( streaming_flume = Module( - name="streaming_flume", + name="streaming-flume", dependencies=[streaming], source_file_regexes=[ "external/flume", @@ -214,6 +214,15 @@ streaming_flume = Module( ) +streaming_flume_assembly = Module( + name="streaming-flume-assembly", + dependencies=[streaming_flume, streaming_flume_sink], + source_file_regexes=[ + "external/flume-assembly", + ] +) + + mllib = Module( name="mllib", dependencies=[streaming, sql], @@ -241,7 +250,7 @@ examples = Module( pyspark_core = Module( name="pyspark-core", - dependencies=[mllib, streaming, streaming_kafka], + dependencies=[], source_file_regexes=[ "python/(?!pyspark/(ml|mllib|sql|streaming))" ], @@ -281,7 +290,7 @@ pyspark_sql = Module( pyspark_streaming = Module( name="pyspark-streaming", - dependencies=[pyspark_core, streaming, streaming_kafka], + dependencies=[pyspark_core, streaming, streaming_kafka, streaming_flume_assembly], source_file_regexes=[ "python/pyspark/streaming" ], -- cgit v1.2.3