category: Utilities
provider: Open Source
sectionorder:
- Connect
- Collect
commonfields:
  id: Image OCR
  version: -1
configuration:
- display: A CSV of language codes of the language to use for OCR (leave empty to use defaults).
  name: langs
  type: 0
  section: Connect
  advanced: true
  required: false
- additionalinfo: If true, will not raise an error if the image is corrupt and could not be processed.
  display: Skip on corrupted images
  name: skip_corrupted
  section: Connect
  advanced: true
  required: false
  type: 8
description: Extracts text from images.
display: Image OCR
name: Image OCR
defaultEnabled: true
fromversion: 5.0.0
script:
  commands:
  - description: Lists supported languages for which the integration can extract text.
    name: image-ocr-list-languages
  - arguments:
    - description: A comma-separated list of Entry IDs of image files to process.
      name: entryid
      required: true
      isArray: true
    - description: A CSV of language codes of the language to use for OCR. Overrides the default configured language list.
      isArray: true
      name: langs
    - description: Turn on verbose flag to display tesseract and other used libraries versions.
      required: false
      defaultValue: false
      name: verbose
    name: image-ocr-extract-text
    description: Extract text from images.
    outputs:
    - contextPath: File.Text
      description: Extracted text from the passed image file.
      type: String
  dockerimage: demisto/tesseract:1.0.0.11009641
  runonce: false
  script: '-'
  type: python
  subtype: python3
tests:
- No tests (auto formatted)