Module: OcrFile::OcrEngines::CloudVision

Extended by:
CloudVision
Included in:
CloudVision
Defined in:
lib/ocr-file/ocr_engines/cloud_vision.rb

Constant Summary collapse

DEFAULT_LANGUAGE = 
'en'
TEXT_DETECTION =

Available Types: github.com/googleapis/google-cloud-ruby/blob/master/google-cloud-vision/lib/google/cloud/vision/v1/image_annotator_pb.rb

'TEXT_DETECTION'
DOCUMENT_TEXT_DETECTION =

Used for low-quality images

'DOCUMENT_TEXT_DETECTION'

Instance Method Summary collapse

Instance Method Details

#id ⇒ Object

Used for dense text documents



12
13
14
 
# File 'lib/ocr-file/ocr_engines/cloud_vision.rb', line 12

def id
  'cloud-vision'
end

#ocr_to_pdf(file_path, options: { type_of_ocr: '', image_annotator: nil }) ⇒ Object 



24
25
26
27
 
# File 'lib/ocr-file/ocr_engines/cloud_vision.rb', line 24

def ocr_to_pdf(file_path, options: { type_of_ocr: '', image_annotator: nil })
  text = ocr_to_text(file_path, options: { type_of_ocr: '', image_annotator: nil })
  OcrFile::ImageEngines::PdfEngine.pdf_from_text(text, options)
end

#ocr_to_text(file_path, options: { type_of_ocr: '', image_annotator: nil }) ⇒ Object 



16
17
18
19
20
21
22
 
# File 'lib/ocr-file/ocr_engines/cloud_vision.rb', line 16

def ocr_to_text(file_path, options: { type_of_ocr: '', image_annotator: nil })
  type_of_ocr = options[:type_of_ocr]
  image_annotator = options[:image_annotator]

  response = detect_text(type_of_ocr, file_path, image_annotator)
  extract_text(response)
end