#!/bin/sh
rm -rf ./tmp; # clean previous run

# this assumes that the checks are scanned upright, bottom towards left margin on pdf, one per page
# this assumes you have scans in ./scans
# in pdf format each may have multiple checks, one per page.

mkdir ./tmp
mkdir ./tmp/scans; # incoming pdf with multiple checks
mkdir ./tmp/pngs; # documents for storage prepped

# copy incoming to staging area
cp ./scans/*pdf ./tmp/scans/;

# rip images and resize , crop etc
find ./tmp/scans/ -iname "*pdf" -exec pdftohtml -q -c -zoom 10 '{}' \;
mv ./tmp/scans/*png ./tmp/pngs/;
rm -rf ./tmp/scans
# format the pngs for storing
mogrify -rotate -90 -chop 0x450 ./tmp/pngs/*png;

# Basically all this does is take the pdfs
# and put images in tmp/pngs that are sized properly and right side up.

# STEP 2
# get images from pngs and turn into micr strip files
# ready for gocr

# copy to micr
rm -rf  ./tmp/micr;
mkdir ./tmp/micr;
cp ./tmp/pngs/*png ./tmp/micr/;

mogrify -chop 0x660 ./tmp/micr/*png;

# convert the isolated micr for gocr
find ./tmp/micr/*png -exec convert '{}' '{}'.pbm \;
rename png.pbm pbm ./tmp/micr/*pbm
rm ./tmp/micr/*png