--原始数据
192.168.57.4 - - [29/Feb/2019:18:14:35 +0800] "GET /bg-upper.png HTTP/1.1" 304 -
--创建表
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'
--导入的数据会通过正则表达式匹配
WITH SERDEPROPERTIES("input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) \\[(.*)\\] \"(.*)\" (-|[0-9]*) (-|[0-9]*)")
STORED AS TEXTFILE;
--加载数据
load data local inpath '/root/data/log' into table logtbl;
--查询表
select * from logtbl;
--数据显示如下(不包含[]和")
192.168.57.4 - - 29/Feb/2019:18:14:35 +0800 GET /bg-upper.png HTTP/1.1 304 -
4.Hive Serde
最新推荐文章于 2023-11-17 11:28:40 发布