examples/bin/examples/indexing/wikipedia_hadoop_config.json

{
  "dataSchema": {
    "dataSource": "wikipedia",
    "parser": {
      "type": "string",
      "parseSpec": {
        "format": "json",
        "timestampSpec": {
          "column": "timestamp",
          "format": "auto"
        },
        "dimensionsSpec": {
          "dimensions": [
            "page",
            "language",
            "user",
            "unpatrolled",
            "newPage",
            "robot",
            "anonymous",
            "namespace",
            "continent",
            "country",
            "region",
            "city"
          ],
          "dimensionExclusions": [],
          "spatialDimensions": []
        }
      }
    },
    "metricsSpec": [
      {
        "type": "count",
        "name": "count"
      },
      {
        "type": "doubleSum",
        "name": "added",
        "fieldName": "added"
      },
      {
        "type": "doubleSum",
        "name": "deleted",
        "fieldName": "deleted"
      },
      {
        "type": "doubleSum",
        "name": "delta",
        "fieldName": "delta"
      }
    ],
    "granularitySpec": {
      "type": "uniform",
      "segmentGranularity": "DAY",
      "queryGranularity": "NONE",
      "intervals": ["2013-08-31/2013-09-01"]
    }
  },
  "ioConfig": {
    "type": "hadoop",
    "inputSpec": {
      "type": "static",
      "paths": "/myPath/druid-0.7.1/examples/indexing/wikipedia_data.json"
    },
    "metadataUpdateSpec": {
      "type": "db",
      "connectURI": "jdbc:mysql:\/\/localhost:3306\/druid",
      "user": "druid",
      "password": "diurd",
      "segmentTable": "druid_segments"
    },
    "segmentOutputPath": "\/tmp\/segments"
  },
  "tuningConfig": {
    "type": "hadoop",
    "workingPath": "\/tmp\/working_path",
    "partitionsSpec": {
      "targetPartitionSize": 5000000
    }
  }
}