{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/google-cloud-dataproc/refs/heads/main/json-schema/cluster-schema.json",
  "title": "Google Cloud Dataproc Cluster",
  "description": "A Dataproc cluster resource representing a managed Apache Hadoop and Spark cluster on Google Cloud.",
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "The Google Cloud Platform project ID that the cluster belongs to."
    },
    "clusterName": {
      "type": "string",
      "description": "The cluster name, which must be unique within a project.",
      "pattern": "^[a-z][-a-z0-9]{0,53}$"
    },
    "config": {
      "type": "object",
      "description": "The cluster config.",
      "properties": {
        "configBucket": {
          "type": "string",
          "description": "Cloud Storage bucket used for staging dependencies and config files."
        },
        "tempBucket": {
          "type": "string",
          "description": "Cloud Storage bucket used for temporary data."
        },
        "gceClusterConfig": {
          "type": "object",
          "properties": {
            "zoneUri": { "type": "string" },
            "networkUri": { "type": "string" },
            "subnetworkUri": { "type": "string" },
            "internalIpOnly": { "type": "boolean" },
            "serviceAccountScopes": {
              "type": "array",
              "items": { "type": "string" }
            },
            "tags": {
              "type": "array",
              "items": { "type": "string" }
            }
          }
        },
        "masterConfig": {
          "$ref": "#/$defs/InstanceGroupConfig"
        },
        "workerConfig": {
          "$ref": "#/$defs/InstanceGroupConfig"
        },
        "secondaryWorkerConfig": {
          "$ref": "#/$defs/InstanceGroupConfig"
        },
        "softwareConfig": {
          "type": "object",
          "properties": {
            "imageVersion": {
              "type": "string",
              "description": "The version of software inside the cluster (e.g., 2.1-debian11)."
            },
            "properties": {
              "type": "object",
              "additionalProperties": { "type": "string" }
            },
            "optionalComponents": {
              "type": "array",
              "items": {
                "type": "string",
                "examples": ["JUPYTER", "ZEPPELIN", "DOCKER", "FLINK"]
              }
            }
          }
        },
        "initializationActions": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "executableFile": { "type": "string" },
              "executionTimeout": { "type": "string" }
            },
            "required": ["executableFile"]
          }
        }
      }
    },
    "labels": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "The labels to associate with this cluster."
    },
    "status": {
      "type": "object",
      "properties": {
        "state": {
          "type": "string",
          "enum": ["UNKNOWN", "CREATING", "RUNNING", "ERROR", "ERROR_DUE_TO_UPDATE", "DELETING", "UPDATING", "STOPPING", "STOPPED", "STARTING", "REPAIRING"]
        },
        "stateStartTime": {
          "type": "string",
          "format": "date-time"
        },
        "detail": {
          "type": "string"
        }
      }
    },
    "clusterUuid": {
      "type": "string",
      "description": "A cluster UUID generated by the Dataproc service."
    }
  },
  "required": ["projectId", "clusterName", "config"],
  "$defs": {
    "InstanceGroupConfig": {
      "type": "object",
      "properties": {
        "numInstances": {
          "type": "integer",
          "minimum": 0,
          "description": "The number of VM instances in the instance group."
        },
        "machineTypeUri": {
          "type": "string",
          "description": "The Compute Engine machine type (e.g., n1-standard-4)."
        },
        "diskConfig": {
          "type": "object",
          "properties": {
            "bootDiskType": {
              "type": "string",
              "enum": ["pd-standard", "pd-ssd", "pd-balanced"]
            },
            "bootDiskSizeGb": {
              "type": "integer",
              "minimum": 10
            },
            "numLocalSsds": {
              "type": "integer",
              "minimum": 0
            }
          }
        },
        "imageUri": {
          "type": "string"
        },
        "preemptibility": {
          "type": "string",
          "enum": ["PREEMPTIBILITY_UNSPECIFIED", "NON_PREEMPTIBLE", "PREEMPTIBLE", "SPOT"]
        }
      }
    }
  }
}