druid/extensions-contrib/orc-extensions/example/hadoop_orc_job.json

{
  "type": "index_hadoop",
  "spec": {
    "ioConfig": {
      "type": "hadoop",
      "inputSpec": {
        "type": "static",
        "inputFormat": "org.apache.hadoop.hive.ql.io.orc.OrcNewInputFormat",
        "paths": "wikipedia.gz.orc"
      },
      "metadataUpdateSpec": {
        "type": "postgresql",
        "connectURI": "jdbc:postgresql://localhost/druid",
        "user" : "druid",
        "password" : "asdf",
        "segmentTable": "druid_segments"
      },
      "segmentOutputPath": "/tmp/segments"
    },
    "dataSchema": {
      "dataSource": "wikipedia",
      "parser": {
        "type": "orc",
        "parseSpec": {
          "format": "timeAndDims",
          "timestampSpec": {
            "column": "timestamp",
            "format": "auto"
          },
          "dimensionsSpec": {
            "dimensions": [
              "timestamp",
              "col1",
              "col2"
            ],
            "dimensionExclusions": [],
            "spatialDimensions": []
          }
        },
        "typeString": "struct<timestamp:string,col1:string,col2:array<string>,val1:float>"
      },
      "metricsSpec": [],
      "granularitySpec": {
        "type": "uniform",
        "segmentGranularity": "DAY",
        "queryGranularity": "NONE",
        "intervals": ["2015-01-01/2017-01-01"]
      }
    },
    "tuningConfig": {
      "type": "hadoop",
      "workingPath": "tmp/working_path",
      "partitionsSpec": {
        "targetPartitionSize": 5000000
      },
      "jobProperties" : {
        "mapreduce.map.java.opts": "-server -Duser.timezone=UTC -Dfile.encoding=UTF-8 -XX:+PrintGCDetails -XX:+PrintGCTimeStamps",
        "mapreduce.reduce.java.opts": "-server -Duser.timezone=UTC -Dfile.encoding=UTF-8 -XX:+PrintGCDetails -XX:+PrintGCTimeStamps",
        "mapred.child.java.opts": "-server -XX:+PrintGCDetails -XX:+PrintGCTimeStamps"
      },
      "leaveIntermediate": true
    }
  }
}