Apache Nutch · Schema

JobInfo

Information about a crawl job.

Web CrawlerIndexingSearchApacheJavaHadoopOpen Source

Properties

Name	Type	Description
id	string	The unique job identifier.
type	string	The type of Nutch crawl job.
confId	string	The configuration ID used for this job.
args	object	Arguments passed to the job.
result	object	Result data returned after job completion.
state	string	The current state of a job.
msg	string	A human-readable status or error message.
crawlId	string	The crawl identifier associated with this job.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/apache-nutch/refs/heads/main/json-schema/apache-nutch-job-info-schema.json",
  "title": "JobInfo",
  "description": "Information about a crawl job.",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The unique job identifier."
    },
    "type": {
      "type": "string",
      "description": "The type of Nutch crawl job.",
      "enum": [
        "INJECT",
        "GENERATE",
        "FETCH",
        "PARSE",
        "UPDATEDB",
        "INDEX",
        "READDB",
        "CLASS",
        "INVERTLINKS",
        "DEDUP"
      ]
    },
    "confId": {
      "type": "string",
      "description": "The configuration ID used for this job."
    },
    "args": {
      "type": "object",
      "additionalProperties": true,
      "description": "Arguments passed to the job."
    },
    "result": {
      "type": "object",
      "additionalProperties": true,
      "description": "Result data returned after job completion."
    },
    "state": {
      "type": "string",
      "description": "The current state of a job.",
      "enum": [
        "IDLE",
        "RUNNING",
        "FINISHED",
        "FAILED",
        "KILLED",
        "STOPPING",
        "KILLING",
        "ANY"
      ]
    },
    "msg": {
      "type": "string",
      "description": "A human-readable status or error message."
    },
    "crawlId": {
      "type": "string",
      "description": "The crawl identifier associated with this job."
    }
  },
  "required": [
    "type",
    "state"
  ]
}