druid/extensions-contrib/parquet-extensions/example/date_test_data_job_string.json

{
  "type": "index_hadoop",
  "spec": {
    "ioConfig": {
      "type": "hadoop",
      "inputSpec": {
        "type": "static",
        "inputFormat": "io.druid.data.input.parquet.DruidParquetInputFormat",
        "paths": "example/test_date_data.snappy.parquet"
      },
      "metadataUpdateSpec": {
        "type": "postgresql",
        "connectURI": "jdbc:postgresql://localhost/druid",
        "user" : "druid",
        "password" : "asdf",
        "segmentTable": "druid_segments"
      },
      "segmentOutputPath": "/tmp/segments"
    },
    "dataSchema": {
      "dataSource": "date_dataset_string",
      "parser": {
        "type": "parquet",
        "parseSpec": {
          "format": "timeAndDims",
          "timestampSpec": {
            "column": "date_as_string",
            "format": "Y-M-d"
          },
          "dimensionsSpec": {
            "dimensions": [
              "idx"
            ]
          }
        }
      },
      "metricsSpec": [{
        "type": "count",
        "name": "count"
      }],
      "granularitySpec": {
        "type": "uniform",
        "segmentGranularity": "DAY",
        "queryGranularity": "NONE",
        "intervals": ["2017-06-17/2017-09-24"]
      }
    },
    "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
    }
  }
}