syntax = "proto3";
package sarus_data_spec;

message Dataset {
  // The dataset definition
  string uuid = 1; // e.g. RFC 4122 id used to refer to the dataset (content linked?)
  string name = 2;
  string doc = 3;
  Spec spec = 4;
  map<string, string> properties = 5; // Other properties

  // Definitions
  message Spec {// How to obtain the dataset
    oneof spec {
      Transformed transformed = 1;
      File file = 2;
      Files files = 3;
      Archive archive = 4;
      Sql sql = 5;
      Huggingface huggingface = 6;
    }
  }

  message Transformed {
    string transform = 1; // Transform id
    repeated string arguments = 2; // Dataset or other object ids
    map<string, string> named_arguments = 3;
  }

  message File {
    string format = 1;
    string uri = 2; // File URI
  }

  message Files {
    string format = 1;
    string uri_pattern = 2; // Pattern of files
  }

  message Archive {
    string format = 1;
    string archive_format = 2;
    string uri = 3; // Archive URI
  }

  message Sql {
    string uri = 1; // As in https://docs.sqlalchemy.org/en/14/core/engines.html
    repeated Table tables = 2;// the sql schemas from which the data can be downloaded
    message Table {
      string schema=1;
      string table=2;
    }
  }

  message Huggingface {
    string name = 1;
    string split = 2;
  }
}