实现Hive数据同步更新的shell脚本

#Please set the synchronize interval,unit is hour.

update_interval=24

 

#Please set the RDBMS connection params

rdbms_connstr="jdbc:oracle:thin:@192.168.0.147:1521:ORCLGBK"

rdbms_username="SP"

rdbms_pwd="fulong"

rdbms_table="OMP_SERVICE"

rdbms_columns="ID,SERVICE_NAME,SERVICE_PROCESS,CREATE_TIME,ENABLE_ORG,ENABLE_PLATFORM,IF_DEL"

 

#Please set the hive params

hive_increment_table="SERVICE_TMP"

hive_full_table="service_all"

 

#---------------------------------------------------------

 

#Import icrement data in RDBMS into Hive

enddate=$(date '+%Y/%m/%d %H:%M:%S')

startdate=$(date '+%Y/%m/%d %H:%M:%S' -d '-'+${update_interval}+' hours')

 

$SQOOP_HOME/bin/sqoop import --connect ${rdbms_connstr} --username ${rdbms_username} --password ${rdbms_pwd} --table ${rdbms_table} --columns "${rdbms_columns}" --where "CREATE_TIME > to_date('${startdate}','yyyy-mm-dd hh24:mi:ss') and CREATE_TIME < to_date('${enddate}','yyyy-mm-dd hh24:mi:ss')" --hive-import --hive-overwrite --hive-table ${hive_increment_table}

 

#---------------------------------------------------------

 

#Update the old full data table to latest status

$HIVE_HOME/bin/hive -e "insert overwrite table ${hive_full_table} select * from ${hive_increment_table} union all select a.* from ${hive_full_table} a left outer join ${hive_increment_table} b on a.service_code = b.service_code where b.service_code is null;"

内容版权声明:除非注明,否则皆为本站原创文章。

转载注明出处:https://www.heiqu.com/86315d61ba81dddec2898d8df01d931e.html