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

{
  "name": "prof_batch",
  "process.type": "batch",
  "timestamp": 123456,
  "data.sources": [
    {
      "name": "source",
      "connector": {
        "type": "avro",
        "version": "1.7",
        "dataframe.name": "this_table",
        "config": {
          "file.name": "src/test/resources/users_info_src.avro"
        },
        "pre.proc": [
          {
            "dsl.type": "spark-sql",
            "rule": "select * from this_table where user_id < 10014"
          }
        ]
      }
    }
  ],
  "evaluate.rule": {
    "rules": [
      {
        "dsl.type": "griffin-dsl",
        "dq.type": "profiling",
        "out.dataframe.name": "prof",
        "rule": "user_id, count(*) as cnt from source group by user_id",
        "out": [
          {
            "type": "metric",
            "name": "prof",
            "flatten": "array"
          }
        ]
      },
      {
        "dsl.type": "griffin-dsl",
        "dq.type": "profiling",
        "out.dataframe.name": "grp",
        "rule": "source.post_code, count(*) as cnt from source group by source.post_code order by cnt desc",
        "out": [
          {
            "type": "metric",
            "name": "post_group",
            "flatten": "array"
          }
        ]
      }
    ]
  },
  "sinks": [
    "CONSOLE"
  ]
}