· 6 years ago · Jun 20, 2019, 06:48 PM
1CREATE EXTERNAL TABLE IF NOT EXISTS s3_logs(
2 BucketOwner STRING,
3 Bucket STRING,
4 RequestDateTime STRING,
5 RemoteIP STRING,
6 Requester STRING,
7 RequestID STRING,
8 Operation STRING,
9 Key STRING,
10 RequestURI_operation STRING,
11 RequestURI_key STRING,
12 RequestURI_httpProtoversion STRING,
13 HTTPstatus STRING,
14 ErrorCode STRING,
15 BytesSent BIGINT,
16 ObjectSize BIGINT,
17 TotalTime STRING,
18 TurnAroundTime STRING,
19 Referrer STRING,
20 UserAgent STRING,
21 VersionId STRING,
22 HostId STRING,
23 SigV STRING,
24 CipherSuite STRING,
25 AuthType STRING,
26 EndPoint STRING,
27 TLSVersion STRING
28)
29ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
30WITH SERDEPROPERTIES (
31 'serialization.format' = '1', 'input.regex' = '([^ ]*) ([^ ]*) \\[(.*?)\\] ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) \\\"([^ ]*) ([^ ]*) (- |[^ ]*)\\\" (-|[0-9]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) (\"[^\"]*\") ([^ ]*)(?: ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*))?.*$' ) LOCATION 's3://teckburg-analytics-bucket/logging'