CREATE EXTERNAL TABLE nik.regex_access_log (
ip STRING,
dte STRING,
request_type STRING,
uri STRING,
protocol STRING,
status STRING,
bytes_sent STRING,
referer STRING,
useragent STRING
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
'input.regex'='^(\\S+) \\S+ \\S+ \\[([^\\[]+)\\] "(\\w+) (\\S+) (\\S+)" (\\d+) (\\d+) "([^"]+)" "([^"]+)".*'
)
STORED AS TEXTFILE
LOCATION 's3://nikita-ds-playground/raw/access-log/2018-12-28/';