aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python/streaming/direct_kafka_wordcount.py
diff options
context:
space:
mode:
authorzsxwing <zsxwing@gmail.com>2015-08-19 18:36:01 -0700
committerTathagata Das <tathagata.das1565@gmail.com>2015-08-19 18:36:01 -0700
commit1f29d502e7ecd6faa185d70dc714f9ea3922fb6d (patch)
tree3eabe5f24204341f8d13be9bd3ae3d637b40b87b /examples/src/main/python/streaming/direct_kafka_wordcount.py
parent2f2686a73f5a2a53ca5b1023e0d7e0e6c9be5896 (diff)
downloadspark-1f29d502e7ecd6faa185d70dc714f9ea3922fb6d.tar.gz
spark-1f29d502e7ecd6faa185d70dc714f9ea3922fb6d.tar.bz2
spark-1f29d502e7ecd6faa185d70dc714f9ea3922fb6d.zip
[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.
Diffstat (limited to 'examples/src/main/python/streaming/direct_kafka_wordcount.py')
-rw-r--r--examples/src/main/python/streaming/direct_kafka_wordcount.py6
1 files changed, 3 insertions, 3 deletions
diff --git a/examples/src/main/python/streaming/direct_kafka_wordcount.py b/examples/src/main/python/streaming/direct_kafka_wordcount.py
index 6ef188a220..ea20678b9a 100644
--- a/examples/src/main/python/streaming/direct_kafka_wordcount.py
+++ b/examples/src/main/python/streaming/direct_kafka_wordcount.py
@@ -23,8 +23,8 @@
http://kafka.apache.org/documentation.html#quickstart
and then run the example
- `$ bin/spark-submit --jars external/kafka-assembly/target/scala-*/\
- spark-streaming-kafka-assembly-*.jar \
+ `$ bin/spark-submit --jars \
+ external/kafka-assembly/target/scala-*/spark-streaming-kafka-assembly-*.jar \
examples/src/main/python/streaming/direct_kafka_wordcount.py \
localhost:9092 test`
"""
@@ -37,7 +37,7 @@ from pyspark.streaming.kafka import KafkaUtils
if __name__ == "__main__":
if len(sys.argv) != 3:
- print >> sys.stderr, "Usage: direct_kafka_wordcount.py <broker_list> <topic>"
+ print("Usage: direct_kafka_wordcount.py <broker_list> <topic>", file=sys.stderr)
exit(-1)
sc = SparkContext(appName="PythonStreamingDirectKafkaWordCount")