druid/examples/quickstart/tutorial/wikipedia-index-hadoop.json

{
  "type" : "index_hadoop",
  "spec" : {
    "dataSchema" : {
      "dataSource" : "wikipedia",
      "parser" : {
        "type" : "hadoopyString",
        "parseSpec" : {
          "format" : "json",
          "dimensionsSpec" : {
            "dimensions" : [
              "channel",
              "cityName",
              "comment",
              "countryIsoCode",
              "countryName",
              "isAnonymous",
              "isMinor",
              "isNew",
              "isRobot",
              "isUnpatrolled",
              "metroCode",
              "namespace",
              "page",
              "regionIsoCode",
              "regionName",
              "user",
              { "name": "added", "type": "long" },
              { "name": "deleted", "type": "long" },
              { "name": "delta", "type": "long" }
            ]
          },
          "timestampSpec" : {
            "format" : "auto",
            "column" : "time"
          }
        }
      },
      "metricsSpec" : [],
      "granularitySpec" : {
        "type" : "uniform",
        "segmentGranularity" : "day",
        "queryGranularity" : "none",
        "intervals" : ["2015-09-12/2015-09-13"],
        "rollup" : false
      }
    },
    "ioConfig" : {
      "type" : "hadoop",
      "inputSpec" : {
        "type" : "static",
        "paths" : "/quickstart/wikiticker-2015-09-12-sampled.json.gz"
      }
    },
    "tuningConfig" : {
      "type" : "hadoop",
      "partitionsSpec" : {
        "type" : "hashed",
        "targetPartitionSize" : 5000000
      },
      "forceExtendableShardSpecs" : true,
      "jobProperties" : {
        "fs.default.name" : "hdfs://druid-hadoop-demo:9000",
        "fs.defaultFS" : "hdfs://druid-hadoop-demo:9000",
        "dfs.datanode.address" : "druid-hadoop-demo",
        "dfs.client.use.datanode.hostname" : "true",
        "dfs.datanode.use.datanode.hostname" : "true",
        "yarn.resourcemanager.hostname" : "druid-hadoop-demo",
        "yarn.nodemanager.vmem-check-enabled" : "false",
        "mapreduce.map.java.opts" : "-Duser.timezone=UTC -Dfile.encoding=UTF-8",
        "mapreduce.job.user.classpath.first" : "true",
        "mapreduce.reduce.java.opts" : "-Duser.timezone=UTC -Dfile.encoding=UTF-8",
        "mapreduce.map.memory.mb" : 1024,
        "mapreduce.reduce.memory.mb" : 1024
      }
    }
  },
  "hadoopDependencyCoordinates": ["org.apache.hadoop:hadoop-client:2.8.5"]
}