Apache Nutch Reader API

openapi: 3.1.2
info:
  title: Apache Nutch REST Admin Reader API
  description: REST API for managing Apache Nutch crawl jobs, configurations, seed lists, database queries, and data readers.
  version: 1.0.0
  license:
    name: Apache 2.0
    identifier: Apache-2.0
  contact:
    name: Apache Nutch
    url: https://nutch.apache.org
servers:
- url: '{protocol}://localhost:{port}'
  description: Nutch REST server
  variables:
    protocol:
      default: http
      enum:
      - http
      - https
      description: The protocol used to access the Nutch server.
    port:
      default: '8081'
      description: The port the Nutch server listens on. Configurable via the --port command-line argument.
security:
- basicAuth: []
tags:
- name: Reader
  description: Read sequence files and webgraph data
paths:
  /reader/sequence/read:
    post:
      tags:
      - Reader
      summary: Apache Nutch Read a Sequence File
      description: Reads key-value pairs from a Hadoop sequence file. Supports reading all rows, a limited number of rows, a row range, or counting the total number of rows.
      operationId: seqRead
      parameters:
      - $ref: '#/components/parameters/nrows'
      - $ref: '#/components/parameters/start'
      - $ref: '#/components/parameters/end'
      - $ref: '#/components/parameters/count'
      requestBody:
        required: true
        description: Reader configuration specifying the file path.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ReaderConfig'
      responses:
        '200':
          description: Sequence file data. Returns application/json when reading rows, or text/plain when count=true.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
            text/plain:
              schema:
                type: integer
                format: int32
                minimum: 0
                maximum: 2147483647
                description: Number of rows in the sequence file.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /reader/link:
    get:
      tags:
      - Reader
      summary: Apache Nutch Get Link Reader Schema
      description: Returns the schema describing the fields in link reader responses.
      operationId: getLinkSchema
      responses:
        '200':
          description: Link reader response schema.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LinkSchema'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /reader/link/read:
    post:
      tags:
      - Reader
      summary: Apache Nutch Read Link Objects
      description: Reads link data (LinkDatum) from the Nutch webgraph. Supports reading all rows, a limited number of rows, a row range, or counting the total number of rows.
      operationId: linkRead
      parameters:
      - $ref: '#/components/parameters/nrows'
      - $ref: '#/components/parameters/start'
      - $ref: '#/components/parameters/end'
      - $ref: '#/components/parameters/count'
      requestBody:
        required: true
        description: Reader configuration specifying the file path.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ReaderConfig'
      responses:
        '200':
          description: Link data. Returns application/json when reading rows, or text/plain when count=true.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
            text/plain:
              schema:
                type: integer
                format: int32
                minimum: 0
                maximum: 2147483647
                description: Number of link entries.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /reader/node:
    get:
      tags:
      - Reader
      summary: Apache Nutch Get Node Reader Schema
      description: Returns the schema describing the fields in node reader responses.
      operationId: getNodeSchema
      responses:
        '200':
          description: Node reader response schema.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NodeSchema'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /reader/node/read:
    post:
      tags:
      - Reader
      summary: Apache Nutch Read Node Objects
      description: Reads Node objects from the Nutch webgraph. Supports reading all rows, a limited number of rows, a row range, or counting the total number of rows.
      operationId: nodeRead
      parameters:
      - $ref: '#/components/parameters/nrows'
      - $ref: '#/components/parameters/start'
      - $ref: '#/components/parameters/end'
      - $ref: '#/components/parameters/count'
      requestBody:
        required: true
        description: Reader configuration specifying the file path.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ReaderConfig'
      responses:
        '200':
          description: Node data. Returns application/json when reading rows, or text/plain when count=true.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
            text/plain:
              schema:
                type: integer
                format: int32
                minimum: 0
                maximum: 2147483647
                description: Number of node entries.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  responses:
    Unauthorized:
      description: Unauthorized. Basic authentication credentials are missing or invalid.
      content:
        application/json:
          schema:
            type: object
            properties:
              message:
                type: string
            example:
              message: Authentication required.
    BadRequest:
      description: Bad request. The request body is missing, malformed, or contains invalid parameters.
      content:
        text/plain:
          schema:
            type: string
          example: Nutch configuration cannot be empty!
    InternalServerError:
      description: An unexpected server error occurred.
      content:
        text/plain:
          schema:
            type: string
          example: Internal server error.
  parameters:
    start:
      name: start
      in: query
      required: false
      description: Starting line number for a range read.
      schema:
        type: integer
        format: int32
        minimum: -1
        maximum: 2147483647
        default: -1
    nrows:
      name: nrows
      in: query
      required: false
      description: Number of rows to read. If not specified (or -1), all rows are returned.
      schema:
        type: integer
        format: int32
        minimum: -1
        maximum: 2147483647
        default: -1
    count:
      name: count
      in: query
      required: false
      description: If true, returns the number of lines instead of the data itself. When set, the response content type is text/plain.
      schema:
        type: boolean
        default: false
    end:
      name: end
      in: query
      required: false
      description: Ending line number for a range read.
      schema:
        type: integer
        format: int32
        minimum: 0
        maximum: 2147483647
  schemas:
    LinkSchema:
      type: object
      description: Schema describing the fields in a link reader response.
      properties:
        key_url:
          type: string
          example: string
        timestamp:
          type: string
          example: int
        score:
          type: string
          example: float
        anchor:
          type: string
          example: string
        linktype:
          type: string
          example: string
        url:
          type: string
          example: string
    NodeSchema:
      type: object
      description: Schema describing the fields in a node reader response.
      properties:
        key_url:
          type: string
          example: string
        num_inlinks:
          type: string
          example: int
        num_outlinks:
          type: string
          example: int
        inlink_score:
          type: string
          example: float
        outlink_score:
          type: string
          example: float
        metadata:
          type: string
          example: string
    ReaderConfig:
      type: object
      description: Configuration specifying a file path for reader operations.
      required:
      - path
      properties:
        path:
          type: string
          description: The path to the sequence file, link data, or node data to read.
      example:
        path: crawl-01/crawldb/current/part-00000/data
  securitySchemes:
    basicAuth:
      type: http
      scheme: basic
      description: HTTP Basic Authentication.