用于做序列化和反序列化。
1.创建文件hiveSerDe.txt
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-upper.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-nav.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /asf-logo.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-button.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-middle.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET / HTTP/1.1" 200 11217
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET / HTTP/1.1" 200 11217
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.css HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /asf-logo.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-middle.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-button.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-nav.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-upper.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET / HTTP/1.1" 200 11217
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.css HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET / HTTP/1.1" 200 11217
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.css HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /tomcat.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-button.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:36 +0800] "GET /bg-upper.png HTTP/1.1" 304 -
2.语法
CREATE TABLE logtbl (
host STRING,
identity STRING,
t_user STRING,
time STRING,
request STRING,
referer STRING,
agent STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) \\[(.*)\\] \"(.*)\" (-|[0-9]*) (-|[0-9]*)"
)
STORED AS TEXTFILE;
3.加载数据
hive> load data local inpath '/test01/hiveSerDe.txt' overwrite into table logtbl;
4.查看hdf文件的内容
hive> dfs -cat /user/hive_remote/warehouse/logtbl/hiveSerDe.txt;
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-upper.png HTTP/1.1" 304 -
192.168.57.4 - - [29/Feb/2016:18:14:35 +0800] "GET /bg-nav.png HTTP/1.1" 304 -