Apache Pig Jobs API

openapi: 3.0.3
info:
  title: Apache Pig Jobs API
  description: Apache Pig is a platform for analyzing large data sets using Pig Latin, a high-level scripting language that compiles to MapReduce/Tez jobs. This API represents the Pig REST service for job submission and management.
  version: 0.17.0
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  contact:
    url: https://pig.apache.org/
servers:
- url: https://{host}/pig
  variables:
    host:
      default: localhost:8080
tags:
- name: Jobs
paths:
  /jobs:
    get:
      operationId: listJobs
      summary: Apache Pig List Jobs
      description: List all Pig jobs with their status and execution details.
      tags:
      - Jobs
      parameters:
      - name: status
        in: query
        schema:
          type: string
          enum:
          - submitted
          - running
          - succeeded
          - failed
          - killed
        description: Filter by job status
      - name: limit
        in: query
        schema:
          type: integer
          default: 20
        description: Maximum number of jobs to return
      responses:
        '200':
          description: List of jobs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobList'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    post:
      operationId: submitJob
      summary: Apache Pig Submit Job
      description: Submit a Pig Latin script for execution.
      tags:
      - Jobs
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/JobRequest'
      responses:
        '201':
          description: Job submitted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /jobs/{jobId}:
    get:
      operationId: getJob
      summary: Apache Pig Get Job
      description: Get details and status of a specific Pig job.
      tags:
      - Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Job details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    delete:
      operationId: killJob
      summary: Apache Pig Kill Job
      description: Kill a running Pig job.
      tags:
      - Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Job killed
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /jobs/{jobId}/logs:
    get:
      operationId: getJobLogs
      summary: Apache Pig Get Job Logs
      description: Get execution logs for a Pig job.
      tags:
      - Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Job logs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobLogs'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    JobRequest:
      type: object
      required:
      - script
      properties:
        script:
          type: string
          description: Pig Latin script content
          example: 'A = LOAD ''data.csv'' USING PigStorage('','');

            B = FILTER A BY $0 > 100;

            STORE B INTO ''output'';'
        name:
          type: string
          description: Job name
          example: sales-analysis
        executionEngine:
          type: string
          enum:
          - mapreduce
          - tez
          - local
          default: tez
        parameters:
          type: object
          additionalProperties:
            type: string
          description: Script parameters as key-value pairs
    JobList:
      type: object
      properties:
        jobs:
          type: array
          items:
            $ref: '#/components/schemas/Job'
        total:
          type: integer
          example: 5
    Job:
      type: object
      properties:
        jobId:
          type: string
          example: job_20260419_001
        name:
          type: string
          example: sales-analysis
        status:
          type: string
          enum:
          - submitted
          - running
          - succeeded
          - failed
          - killed
          example: running
        submittedAt:
          type: string
          format: date-time
          example: '2026-04-19T10:00:00Z'
        startedAt:
          type: string
          format: date-time
          example: '2026-04-19T10:01:00Z'
        completedAt:
          type: string
          format: date-time
        executionEngine:
          type: string
          enum:
          - mapreduce
          - tez
          - local
          example: tez
        progress:
          type: number
          description: Progress percentage 0-100
          example: 45.5
    JobLogs:
      type: object
      properties:
        jobId:
          type: string
          example: job_20260419_001
        logs:
          type: array
          items:
            type: string
          example:
          - 2026-04-19 10:00:00 INFO Pig script started
  parameters:
    jobId:
      name: jobId
      in: path
      required: true
      schema:
        type: string
      description: Job identifier
      example: job_20260419_001
x-generated-from: documentation