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/secondary_sort.sh |
init
Diffstat (limited to 'hadoop/streaming/secondary_sort.sh')
-rwxr-xr-x | hadoop/streaming/secondary_sort.sh | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/hadoop/streaming/secondary_sort.sh b/hadoop/streaming/secondary_sort.sh new file mode 100755 index 0000000..7fa0c6d --- /dev/null +++ b/hadoop/streaming/secondary_sort.sh @@ -0,0 +1,30 @@ +#!/bin/sh + + +hadoop dfs -put secondary_sort.input secondary_sort.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=comp_out + +$HSTREAMING \ + -input secondary_sort.input \ + -output $OUT \ + -partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner \ + -jobconf map.output.key.field.separator="-*-" \ + -jobconf mapred.text.key.partitioner.options="-k1,1n" \ + -mapper /bin/cat \ + -reducer org.apache.hadoop.mapred.lib.IdentityReducer \ + -jobconf mapred.output.key.comparator.class=org.apache.hadoop.mapred.lib.KeyFieldBasedComparator \ + -jobconf stream.num.map.output.key.fields=2 \ + -jobconf stream.map.output.field.separator="\t" \ + -jobconf mapred.text.key.comparator.options="-k1,1n -k2,2nr" \ + -jobconf mapred.reduce.tasks=3 + +hadoop dfs -get $OUT . +hadoop dfs -rmr $OUT +hadoop dfs -rm secondary_sort.input + |