measure/src/test/resources/_profiling-batch-sparksql.json

{
  "name": "prof_batch",
  "process.type": "batch",
  "timestamp": 123456,
  "data.sources": [
    {
      "name": "source",
      "connector": {
        "type": "avro",
        "version": "1.7",
        "config": {
          "file.name": "src/test/resources/users_info_src.avro"
        }
      }
    }
  ],
  "evaluate.rule": {
    "rules": [
      {
        "dsl.type": "spark-sql",
        "out.dataframe.name": "prof",
        "rule": "select count(*) as `cnt`, count(distinct `post_code`) as `dis-cnt`, max(user_id) as `max` from source",
        "out": [
          {
            "type": "metric",
            "name": "prof"
          }
        ]
      },
      {
        "dsl.type": "spark-sql",
        "out.dataframe.name": "grp",
        "rule": "select post_code as `pc`, count(*) as `cnt` from source group by post_code",
        "out": [
          {
            "type": "metric",
            "name": "post_group",
            "flatten": "array"
          }
        ]
      }
    ]
  },
  "sinks": [
    "CONSOLE",
    "ELASTICSEARCH"
  ]
}