Created
April 26, 2016 15:31
-
-
Save l15k4/abcb148dda1d0f8174d4b216388504a2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
val exclusions = List( // removed cid c-geo:c3 | |
"timestamp","d_memberID","gwid","diid","c-geo:st","c-geo:ac","c-geo:c2","c-geo:cn","c-geo:ct","c-geo:dc","c-geo:la","c-geo:lo","c-geo:pc","c-geo:rc","c-geo:sp", | |
"ua","ua-cp","ua-os","accept","accept-charset","accept-encoding","accept-language","connection","from","x-wap-profile","x-att-deviceid","via","x-forwarded-for","x-uidh","forwarded","referrer","c-ip","ce","count","ctr","logic","max","miid","msg","npid","cs-uri-stem" | |
) | |
val segmentGrn = Granularity.DAY | |
private def hadoopTask(interval: String) = | |
IndexTask( | |
IndexTask.hadoopType, | |
IngestionSpec( | |
DataSchema( | |
"gwiq", | |
Parser.hadoopyString( | |
ParseSpec.json( | |
TimestampSpec("timestamp"), DimensionsSpec(List.empty, exclusions, List.empty) | |
) | |
), | |
List(Aggregation.count("count"), Aggregation.hll("gwid", "gwid"), Aggregation.hll("d_memberID", "d_memberID")), | |
GranularitySpec.uniform(List(interval), Some(segmentGrn.toString), Some(Granularity.DAY.toString)) | |
), | |
IoConfig.hadoop(InputSpec.granularity(Granularity.DAY.toString, s"s3n://${sys.env("AWS_ACCESS_KEY_ID")}:${sys.env("AWS_SECRET_ACCESS_KEY")}@gwiq-views-p/gwiq/base-json-gz", ".*", Some("yyyy/MM/dd"))), | |
Some(TuningConfig(TuningConfig.hadoopType)) | |
) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment