#!/usr/bin/env python3
# Copyright 2018 by Don Armstrong <don@donarmstrong.com>
# Licensed under the terms of the GPL version 3 or any later version at your option.


import argparse
import subprocess
import re

parser = argparse.ArgumentParser(description="Make a PDF from TIFF files with OCR")

parser.add_argument('--output','-f',default='output.pdf')
parser.add_argument('tiff',nargs='+')
args = parser.parse_args()
# combine the tiff files into a multi-image tiff
subprocess.run(['e2mtiff','--output','temp.tiff']+args.tiff,check=True)
# tesseract appends pdf when we write to an output for some reason
output_name = re.sub(r"\.pdf$","",args.output)
subprocess.run(['tesseract','temp.tiff',output_name,'pdf'],check=True)