diff options
author | Patrick Simianer <p@simianer.de> | 2014-06-14 16:46:27 +0200 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2014-06-14 16:46:27 +0200 |
commit | 26c490f404731d053a6205719b6246502c07b449 (patch) | |
tree | 3aa721098f1251dfbf2249ecd2736434c13b1d48 /hadoop/streaming/partitioner_test1.sh |
init
Diffstat (limited to 'hadoop/streaming/partitioner_test1.sh')
-rwxr-xr-x | hadoop/streaming/partitioner_test1.sh | 27 |
1 files changed, 27 insertions, 0 deletions
diff --git a/hadoop/streaming/partitioner_test1.sh b/hadoop/streaming/partitioner_test1.sh new file mode 100755 index 0000000..6e6344c --- /dev/null +++ b/hadoop/streaming/partitioner_test1.sh @@ -0,0 +1,27 @@ +#!/bin/sh + + +hadoop dfs -put partitioner_test.input partitioner_test.input + +HADOOP_HOME=/usr/lib/hadoop +HADOOP_VERSION=0.20.2-cdh3u1 +JAR=contrib/streaming/hadoop-streaming-$HADOOP_VERSION.jar +HSTREAMING="$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/$JAR" + +OUT=partitioner1_out + +$HSTREAMING \ + -input partitioner_test.input \ + -output $OUT \ + -mapper /bin/cat \ + -jobconf mapred.reduce.tasks=2 \ + -partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner \ + -jobconf stream.map.output.field.separator="\t" \ + -jobconf map.output.key.field.separator=. \ + -jobconf stream.num.map.output.key.fields=2 \ + -jobconf mapred.text.key.partitioner.options=-k1 + +hadoop dfs -get $OUT . +hadoop dfs -rmr $OUT +hadoop dfs -rm partitioner_test.input + |