pombreda / clarify Goto Github PK

Clarify

Author: David Dahl
Copyright 2007, David L Dahl
http://www.ddahl.com
Created: 2007-04-20

'Clarify' is the opposite of 'obfuscate'

Licensed under Apache License, Version 2.0
http://www.apache.org/licenses/LICENSE-2.0

Clarify is a python module that wraps up tesseract-ocr, xpdf and netpbm

Clarify helps you OCR 'image-only' PDFs. Your input is a PDF that you normally cannot extract text from. The output is text.

So far this project is a messy hack. It would be nice to add some threading or concurrency to speed things up. I am also looking for some input and help in wrapping tesseract with swig, ctypes or pyrex.


ROADMAP:

clean up existing module
add tests
concurrency and threading?? is tesseract thread safe?

REST interface: 
* send url of PDF or JSON dictionary of PDF urls to Web interface (Django)
* add PDFs to queue, process
* put resulting text into database
* notify user when jobs are complete via RSS or Email 

Would this design be cleaner? 

* ctypes/pyrex/swig wrapping pf Tesseract-ocr, xPDF, and NetPBM bins?