Create a table schema in the database for parsing s3 logs.

s3_access_logs

CREATE DATABASE s3_access_logs_db;

CREATE EXTERNAL TABLE `s3_access_logs_db.mybucket_logs`(
  `bucketowner` STRING,
  `bucket_name` STRING,
  `requestdatetime` STRING,
  `remoteip` STRING,
  `requester` STRING,
  `requestid` STRING,
  `operation` STRING,
  `key` STRING,
  `request_uri` STRING,
  `httpstatus` STRING,
  `errorcode` STRING,
  `bytessent` BIGINT,
  `objectsize` BIGINT,
  `totaltime` STRING,
  `turnaroundtime` STRING,
  `referrer` STRING,
  `useragent` STRING,
  `versionid` STRING,
  `hostid` STRING,
  `sigv` STRING,
  `ciphersuite` STRING,
  `authtype` STRING,
  `endpoint` STRING,
  `tlsversion` STRING)
ROW FORMAT SERDE
  'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
  'input.regex'='([^ ]*) ([^ ]*) \\[(.*?)\\] ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) (\"[^\"]*\"|-) (-|[0-9]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) (\"[^\"]*\"|-) ([^ ]*)(?: ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*))?.*$')
STORED AS INPUTFORMAT
  'org.apache.hadoop.mapred.TextInputFormat'
OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
  's3://awsexamplebucket1-logs/prefix/'