Hadoop 压缩文件命令
hadoop jar /usr/bin/hadoop/software/hadoop/share/hadoop/tools/lib/hadoop-streaming-2.7.2.4.jar \
-Dmapred.reduce.tasks=5 \
-Dmapred.output.compress=true \
-Dmapred.compress.map.output=true \
-Dmapred.output.compression.codec=org.apache.hadoop.io.compress.BZip2Codec \
-input /home/wechat_log_2020_02_18.har \
-output /home/wechat_log_2020_02_18.har.bz2 \
-mapper /bin/cat \
-reducer /bin/cat \
-inputformat org.apache.hadoop.mapred.TextInputFormat \
-outputformat org.apache.hadoop.mapred.TextOutputFormat