kdeps-tools-ocr_image

version: 1.1.0
description: 'Extract text from an image via tesseract OCR. Runs entirely locally -- no API key required. Supports png, jpg/jpeg, tiff, bmp, gif. Requires: file (absolute path to the image). Optional: language (tesseract -l value, e.g. ''eng'' or ''eng+fra''; default ''eng''). Does not support PDF -- use load_document with type pdf for text-layer PDFs.'
parameters:
  file:
    type: string
    description: Absolute path to the image to extract text from
    required: true
  language:
    type: string
    description: 'tesseract -l value, e.g. ''eng'' or ''eng+fra''. Default: eng'
    default: eng
exec:
  command: tesseract
  install: tesseract-ocr
  paths: [file]               # checked against the workspace boundary
  args:
    - "{{.args.file}}"
    - stdout                  # tesseract writes the text to stdout
    - "-l"
    - "{{.args.language}}"