sql 适用于CloudTrail日志的AWS Athena表

Posted 2021-05-13

CREATE EXTERNAL TABLE IF NOT EXISTS cloudtrail_logs (
eventversion STRING,
useridentity STRUCT<
               type:STRING,
               principalid:STRING,
               arn:STRING,
               accountid:STRING,
               invokedby:STRING,
               accesskeyid:STRING,
               userName:STRING,
sessioncontext:STRUCT<
attributes:STRUCT<
               mfaauthenticated:STRING,
               creationdate:STRING>,
sessionissuer:STRUCT<  
               type:STRING,
               principalId:STRING,
               arn:STRING, 
               accountId:STRING,
               userName:STRING>>>,
eventtime STRING,
eventsource STRING,
eventname STRING,
awsregion STRING,
sourceipaddress STRING,
useragent STRING,
errorcode STRING,
errormessage STRING,
requestparameters STRING,
responseelements STRING,
additionaleventdata STRING,
requestid STRING,
eventid STRING,
resources ARRAY<STRUCT<
               ARN:STRING,
               accountId:STRING,
               type:STRING>>,
eventtype STRING,
apiversion STRING,
readonly STRING,
recipientaccountid STRING,
serviceeventdetails STRING,
sharedeventid STRING,
vpcendpointid STRING
)
PARTITIONED BY (year int, month int, day int)
ROW FORMAT SERDE 'com.amazon.emr.hive.serde.CloudTrailSerde'
STORED AS INPUTFORMAT 'com.amazon.emr.cloudtrail.CloudTrailInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION 's3://{BUCKET}/AWSLogs/{ACCOUNTID}/CloudTrail/{REGION}/';

/* Create partitions */
ALTER TABLE cloudtrail_logs add partition (year=2017, month=1, day=1) LOCATION "s3://{BUCKET}/AWSLogs/{ACCOUNTID}/CloudTrail/{REGION}/2017/01/01/";