Apache PDFBox Documents API

openapi: 3.0.3
info:
  title: Apache PDFBox Documents API
  description: Apache PDFBox is an open-source Java library for working with PDF documents. This API represents the REST service interface for PDF creation, manipulation, text extraction, and digital signatures.
  version: 3.0.0
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  contact:
    url: https://pdfbox.apache.org/
servers:
- url: https://{host}/pdfbox
  description: Apache PDFBox REST service
  variables:
    host:
      default: localhost:8080
tags:
- name: Documents
paths:
  /documents:
    post:
      operationId: createDocument
      summary: Apache PDFBox Create Document
      description: Create a new empty PDF document.
      tags:
      - Documents
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateDocumentRequest'
      responses:
        '200':
          description: Document created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentInfo'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /documents/{documentId}/text:
    get:
      operationId: extractText
      summary: Apache PDFBox Extract Text
      description: Extract plain text from a PDF document.
      tags:
      - Documents
      parameters:
      - $ref: '#/components/parameters/documentId'
      - name: startPage
        in: query
        schema:
          type: integer
        description: Start page number (1-based)
      - name: endPage
        in: query
        schema:
          type: integer
        description: End page number (inclusive)
      responses:
        '200':
          description: Extracted text
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TextExtractionResult'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /documents/{documentId}/metadata:
    get:
      operationId: getMetadata
      summary: Apache PDFBox Get Metadata
      description: Get PDF document metadata including title, author, creation date.
      tags:
      - Documents
      parameters:
      - $ref: '#/components/parameters/documentId'
      responses:
        '200':
          description: Document metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentMetadata'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    CreateDocumentRequest:
      type: object
      properties:
        title:
          type: string
          example: My Document
        author:
          type: string
          example: John Smith
        pageSize:
          type: string
          example: A4
          enum:
          - A4
          - LETTER
          - LEGAL
          - A3
          - A5
    DocumentInfo:
      type: object
      properties:
        documentId:
          type: string
          example: doc-abc123
        title:
          type: string
          example: My Document
        pageCount:
          type: integer
          example: 10
        fileSize:
          type: integer
          example: 204800
        version:
          type: string
          example: '1.4'
    TextExtractionResult:
      type: object
      properties:
        documentId:
          type: string
          example: doc-abc123
        text:
          type: string
          example: This is extracted text from the PDF document.
        pageCount:
          type: integer
          example: 5
        wordCount:
          type: integer
          example: 1234
    DocumentMetadata:
      type: object
      properties:
        title:
          type: string
          example: Annual Report 2026
        author:
          type: string
          example: Jane Doe
        subject:
          type: string
          example: Financial Summary
        creator:
          type: string
          example: Apache PDFBox
        producer:
          type: string
          example: Apache PDFBox
        creationDate:
          type: string
          format: date-time
          example: '2026-04-19T10:00:00Z'
        modificationDate:
          type: string
          format: date-time
          example: '2026-04-19T11:00:00Z'
  parameters:
    documentId:
      name: documentId
      in: path
      required: true
      schema:
        type: string
      description: Document identifier
      example: doc-abc123
x-generated-from: documentation