duplexscan

#!/bin/sh

# This script takes a scanned PDF of double-sided pages that have been
# scanned by an ADF (manually doing duplex scanning by first scanning
# all front sides and then all back sides) and produces a PDF with the
# pages in the right order.
#
# The back sides are expected to be in reverse order (because you
# reverse the entire stack to scan the back sides, not each sheet
# individually).
#
# This script needs the pdftk to be installed.
#
# Permission is hereby granted, free of charge, to anyone obtaining a copy
# of this document and accompanying files, to do whatever they want with
# them without any restriction, including, but not limited to, copying,
# modification and redistribution.
#
# NO WARRANTY OF ANY KIND IS PROVIDED.

INPUT="$1"
OUTPUT="$2"

if [ -z "$INPUT" -o -z "$OUTPUT" -o "$1" = "-h" -o "$1" = "--help" ]; then
    echo "usage: $0 INPUT.pdf OUTPUT.pdf"
    echo "INPUT.pdf should have an even number of pages, first all odd (front) pages, followed by all even (back) pages."
    echo "OUTPUT.pdf will have the pages in the right order."
    exit 1
fi

if ! [ -e "$INPUT" ]; then
    echo "Input file not found: $INPUT"
    exit 1
fi

if [ -e "$OUTPUT" ]; then
    echo "Output already exists: $OUTPUT"
    exit 1
fi


PAGES=$(pdftk "$INPUT" dump_data 2>/dev/null | grep NumberOfPages | awk '{print $2}' | tr -dc '[0-9]')

if [ -z "$PAGES" ]; then
    echo "Failed to detect number of pages"
    exit 1
fi

pdftk "$INPUT" shuffle 1-$(($PAGES / 2)) end-$(($PAGES / 2 + 1)) output "$OUTPUT" verbose