Hive版本为 apache-hive-0.13.1
数据准备:
cookie1,2015-04-10 10:00:02,url2 cookie1,2015-04-10 10:00:00,url1 cookie1,2015-04-10 10:03:04,1url3 cookie1,2015-04-10 10:50:05,url6 cookie1,2015-04-10 11:00:00,url7 cookie1,2015-04-10 10:10:00,url4 cookie1,2015-04-10 10:50:01,url5 cookie2,2015-04-10 10:00:02,url22 cookie2,2015-04-10 10:00:00,url11 cookie2,2015-04-10 10:03:04,1url33 cookie2,2015-04-10 10:50:05,url66 cookie2,2015-04-10 11:00:00,url77 cookie2,2015-04-10 10:10:00,url44 cookie2,2015-04-10 10:50:01,url55 CREATE EXTERNAL TABLE lxw1234 ( cookieid string, createtime string, --页面访问时间 url STRING --被访问页面 ) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' stored as textfile location '/tmp/lxw11/'; hive> select * from lxw1234; OK cookie1 2015-04-10 10:00:02 url2 cookie1 2015-04-10 10:00:00 url1 cookie1 2015-04-10 10:03:04 1url3 cookie1 2015-04-10 10:50:05 url6 cookie1 2015-04-10 11:00:00 url7 cookie1 2015-04-10 10:10:00 url4 cookie1 2015-04-10 10:50:01 url5 cookie2 2015-04-10 10:00:02 url22 cookie2 2015-04-10 10:00:00 url11 cookie2 2015-04-10 10:03:04 1url33 cookie2 2015-04-10 10:50:05 url66 cookie2 2015-04-10 11:00:00 url77 cookie2 2015-04-10 10:10:00 url44 cookie2 2015-04-10 10:50:01 url55 LAG cookie1,2015-0