hadoop hive 手记

hadoop hive  手记

 

1,创建表及分区,针对于squid_log 

create table squid_tmp(visittime string, clientip string, visitdom string, visiturl string, visitstat string) partitioned by (pt_ip string) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' STORED AS TEXTFILE;

 

create table squid_tmpp(visittime string, clientip string, visitdom string, visiturl string, visitstat string) partitioned by (pt_ip string, pt_dt int) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' STORED AS TEXTFILE;

 

create table squid_log (visittime string, clientip string, visitdom string, visiturl string, visitstat string) partitioned by (pt_ip string, pt_dt int) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' STORED AS TEXTFILE;

 

2, 导入文本到hive 中

load data local inpath '/data1/squid_log/117.34.80.249/tmp.log' overwrite into table squid.squid_tmp partition(pt_ip = '117.34.80.249')

 

3, 从 squid_tmp 导入到squid_log中

insert into table squid_log partition(pt_ip, pt_dt) select visittime, clientip, visitdom, visiturl, visitstat, substr(visittime,1,8) as pt_dt, pt_ip from squid_tmp;

 

4, hive 删除分区

alter table squid_log drop partition(pt_ip = '117.34.80.249', pt_dt=20130224);

 

5, hive 查看分区信息

show partitions squid_log;

 

本文转自 swq499809608 51CTO博客，原文链接:http://blog.51cto.com/swq499809608/1142460