How to access VisionKit?

cvp

@JonB I was busy to post this

def documentCameraViewController_didFinishWithScan_(_self, _cmd, _controller, _scan):
	VNDocumentViewController = ObjCInstance(_controller)
	scan = ObjCInstance(_scan)	# VNDocumentCameraScan
	#print(scan)
	VNDocumentViewController.dismissViewControllerAnimated_completion_(True, None)

JonB

@cvp re: getting the name wrong, in Swift, they omit the "nouns", i think. So the docs show the selectors without nouns. In objc_util it lets you do this too, if you use kwargs.

Re: dismissing... So did that work? If not, maybe need to on_main_thread it?

cvp

scan returns an UIImage

	print(scan.imageOfPageAtIndex_(0))

cvp

@JonB said:

documentCameraViewController_didFinishWithScan_

One more time, thanks for your help.

I really become too old for this stuff. Shame on me, I'm so sad to have not seen that myself.
Sorry to all people who tried to help us.😢😪

cvp

@emkay_online quick an dirty to see the UIImage

	import ctypes
	from PIL import Image
	UIImage = scan.imageOfPageAtIndex_(0)	
	# Save UIImage to jpg file
	func = c.UIImageJPEGRepresentation
	func.argtypes = [ctypes.c_void_p, ctypes.c_float]
	func.restype = ctypes.c_void_p
	x = ObjCInstance(func(UIImage.ptr, 1.0))
	x.writeToFile_atomically_('test.jpg', True)
	# Display jpg file
	image = Image.open("test.jpg")
	image.show()

cvp

@emkay_online operational

from objc_util import *
import ui
load_framework('VisionKit')

def documentCameraViewController_didFinishWithScan_(_self, _cmd, _controller, _scan):
	VNDocumentViewController = ObjCInstance(_controller)
	scan = ObjCInstance(_scan)	# VNDocumentCameraSca
	
	UIImage = scan.imageOfPageAtIndex_(0)	
	ObjCInstance(VNDocumentViewController.ui_view['iv']).setImage_(UIImage)

	VNDocumentViewController.dismissViewControllerAnimated_completion_(True, None)
	
def documentCameraViewController_didFailWithError_(_self, _cmd, _controller, _error):
	print('documentCameraViewController_didFailWithError_')
	
def documentCameraViewControllerDidCancel_(_self, _cmd, _controller):
	print('documentCameraViewControllerDidCancel_')

methods = [documentCameraViewController_didFinishWithScan_, documentCameraViewController_didFailWithError_, documentCameraViewControllerDidCancel_]
protocols = ['VNDocumentCameraViewControllerDelegate']
try:
		MyVNDocumentCameraViewControllerDelegate = ObjCClass('MyVNDocumentCameraViewControllerDelegate')
except:
	MyVNDocumentCameraViewControllerDelegate = create_objc_class('MyVNDocumentCameraViewControllerDelegate', methods=methods, protocols=protocols)

@on_main_thread	
def main():
	VNDocumentCameraViewController = ObjCClass('VNDocumentCameraViewController').alloc().init()
	delegate = MyVNDocumentCameraViewControllerDelegate.alloc().init()
	VNDocumentCameraViewController.delegate = delegate	

	uiview = ui.View()
	iv = ui.ImageView(name='iv')
	iv.frame = uiview.bounds
	iv.flex = 'wh'
	uiview.add_subview(iv)
	uiview.present('fullscreen')
	VNDocumentCameraViewController.ui_view = uiview	# to pass to delegate
	
	objc_uiview = ObjCInstance(uiview)
	SUIViewController = ObjCClass('SUIViewController')
	vc = SUIViewController.viewControllerForView_(objc_uiview)	
	vc.presentViewController_animated_completion_(VNDocumentCameraViewController, True, None)
	
main()

mikael

@cvp, good stuff. It gives the straightened-out picture, right? Can I get a multi-page PDF, or is the framework for single pictures only?

cvp

@mikael no,no, the framework is for multiple scans but my little script not.
I think that if you don't dismiss the camera view controller, you could continue to scan multiple images, but I did not test it.

JonB

i think the document object guves you UIImages only, but you could create a pdf using some UIKit functions:

https://developer.apple.com/documentation/uikit/images_and_pdf?language=objc

(you need to acces the functions using c.UIGraphicsBeginPDFContextToFile etc and set argtypes and restype)

I think the basic flow is, you have to create a pdf context to a file, begn a pdf page, draw your content (UiImage's drawAtPoint ), begn a new page, etc, then finally end the context.

cvp

Do you know that PIL save has an option to save as pdf?

pil_image.save('File.pdf',"PDF",resolution=100.0)

stephen

@cvp this would of been wonderfull information about 3 months go lol

JonB

@cvp can PIL do multipage PDF? I guess you still would need to do the ui2pil type business.

mikael

@JonB said:

@cvp can PIL do multipage PDF? I guess you still would need to do the ui2pil type business.

Which I guess would make it slow in a way that this type of use case does not reslly tolerate.

Playing with the idea of a truly personalized doc scanner that would put the scan whete it needs to go. Also, combining this with the text recognition stuff would be good (as soon as they get international characters right).

JonB

But the built in objc methods for writing to PDF (see link above) ought to be reasonably fast. I haven't tried.

cvp

@JonB said:

can PIL do multipage PDF? I guess you still would need to do the ui2pil type business.

I don't think it does multi pages, but easy to do it yourself via PdfFileMerger.
Yes for ui2pil

cvp

@JonB said:

But the built in objc methods for writing to PDF (see link above) ought to be reasonably fast. I haven't tried

I have already done the inverse (PDF -> image) via Objectivec context.. quick 🙄

emkay_online

@cvp Thank you so much for this code. It works a treat and really gives me a solid foundation to build on.

Also thank you for giving me a good grounding in the objc_util module - it's certainly a complex one, especially for someone with no iOS coding experience.

Thank you.

cvp

@emkay_online you should dismiss the viewcontroller in the didcancel delegate, not in the didfinish like I did for testing only. This if you want to process multiple scans

cvp

@JonB said:

But the built in objc methods for writing to PDF (see link above) ought to be reasonably fast. I haven't tried.

Please applaus. ok, I exaggerate 😂, but was not so easy (for me)

from objc_util import *
import ui

UIGraphicsGetCurrentContext = c.UIGraphicsGetCurrentContext
UIGraphicsGetCurrentContext.restype = c_void_p
UIGraphicsGetCurrentContext.argtypes = []

UIGraphicsBeginPDFContextToData = c.UIGraphicsBeginPDFContextToData
UIGraphicsBeginPDFContextToData.restype = None
UIGraphicsBeginPDFContextToData.argtypes = [c_void_p, CGRect, c_void_p]

UIGraphicsBeginPDFPage = c.UIGraphicsBeginPDFPage
UIGraphicsBeginPDFPage.restype = None
UIGraphicsBeginPDFPage.argtypes = []

UIGraphicsEndPDFContext = c.UIGraphicsEndPDFContext
UIGraphicsEndPDFContext.restype = None
UIGraphicsEndPDFContext.argtypes = []

pdfdata = NSMutableData.alloc()#.init()
ui_image = ui.Image.named('test:Lenna')
uiimage = ObjCInstance(ui_image)
w,h = ui_image.size
frame = CGRect(CGPoint(0, 0), CGSize(w, h))	
UIGraphicsBeginPDFContextToData(pdfdata, frame, None)
UIGraphicsBeginPDFPage()
pdfContext = UIGraphicsGetCurrentContext()
uiimage.drawInRect_(frame)
UIGraphicsEndPDFContext()
# just to be sure that pdfdata is ok
with open('a.pdf',mode='wb') as fil:
	b = nsdata_to_bytes(pdfdata)
	fil.write(b)

JonB

👏👏👏

If you are going straight to file, you might consider using

https://developer.apple.com/documentation/uikit/1623927-uigraphicsbeginpdfcontexttofile?language=objc

instead of creating the context as nsdata. Might save a few lines.

Also, you can use drawAtPoint instead of drawInRect, so that you don't need to specify w,h.

I think if you omit the frame when you create the context, it also create an 8.5x11.