druid/extensions-contrib/parquet-extensions/example/wikipedia_hadoop_parquet_ta...

59 lines
1.3 KiB
JSON
Executable File

{
"type" : "index_hadoop",
"spec" : {
"ioConfig": {
"type": "hadoop",
"inputSpec": {
"type": "static",
"inputFormat": "io.druid.data.input.parquet.DruidParquetInputFormat",
"paths": "wikipedia_list.parquet"
}
},
"dataSchema": {
"dataSource": "wikipedia",
"parser": {
"type": "parquet",
"parseSpec": {
"format": "timeAndDims",
"timestampSpec": {
"column": "timestamp",
"format": "auto"
},
"dimensionsSpec": {
"dimensions": [
"page",
"language",
"user"
],
"dimensionExclusions": [],
"spatialDimensions": []
}
}
},
"metricsSpec": [
{
"type": "count",
"name": "count"
},
{
"type": "doubleSum",
"name": "added",
"fieldName": "added"
}
],
"granularitySpec": {
"type": "uniform",
"segmentGranularity": "DAY",
"queryGranularity": "NONE",
"intervals": ["2013-08-31/2013-09-01"]
}
},
"tuningConfig": {
"type": "hadoop",
"partitionsSpec": {
"targetPartitionSize": 5000000
}
}
}
}