Skip to content

Instantly share code, notes, and snippets.

@praveev
Created March 7, 2016 04:13
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save praveev/269d9f6bf1ce16b6f50c to your computer and use it in GitHub Desktop.
Save praveev/269d9f6bf1ce16b6f50c to your computer and use it in GitHub Desktop.
{
"spec" : {
"dataSchema" : {
"dataSource" : "website",
"parser" : {
"type" : "string",
"parseSpec" : {
"format" : "csv",
"timestampSpec" : {
"column" : "timestamp",
"format" : "yyyyMMddHH",
"missingValue" : null
},
"dimensionsSpec" : {
"dimensions" : [ "country", "host" ],
"dimensionExclusions" : [ ],
"spatialDimensions" : [ ]
},
"listDelimiter" : null,
"columns" : [ "timestamp", "host", "country", "visited_num" ]
},
"encoding" : "UTF-8"
},
"metricsSpec" : [ {
"type" : "longSum",
"name" : "visited_num",
"fieldName" : "visited_num"
} ],
"granularitySpec" : {
"type" : "uniform",
"segmentGranularity" : "DAY",
"queryGranularity" : {
"type" : "none"
},
"intervals" : [ "2014-10-21T17:00:00.000-07:00/2014-10-22T17:00:00.000-07:00" ]
}
},
"ioConfig" : {
"type" : "hadoop",
"inputSpec" : {
"paths" : "/tmp/test_webdata_data.json",
"type" : "static"
},
"metadataUpdateSpec" : null,
"segmentOutputPath" : "/private/var/folders/j_/xbgxm4bn5q79537hd1f8g_m00000gn/T/1457317345893-0"
},
"tuningConfig" : {
"type" : "hadoop",
"workingPath" : "/private/var/folders/j_/xbgxm4bn5q79537hd1f8g_m00000gn/T/1457317345893-0",
"version" : "2016-03-06T18:22:28.608-08:00",
"partitionsSpec" : {
"type" : "multiDimension",
"partitionDimensions" : [ "host", "country", "project" ],
"targetPartitionSize" : 3,
"maxPartitionSize" : 4,
"assumeGrouped" : true,
"numShards" : -1
},
"shardSpecs" : { },
"indexSpec" : {
"bitmap" : {
"type" : "concise"
},
"dimensionCompression" : null,
"metricCompression" : null
},
"leaveIntermediate" : false,
"cleanupOnFailure" : false,
"overwriteFiles" : false,
"ignoreInvalidRows" : false,
"jobProperties" : { },
"combineText" : false,
"persistInHeap" : false,
"ingestOffheap" : false,
"bufferSize" : 134217728,
"aggregationBufferRatio" : 0.5,
"useCombiner" : false,
"rowFlushBoundary" : 80000
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment