makegdocs

#!/usr/bin/perl

# docs.google.com can convert/OCR pdf files under 11MB to word, so split a folder with images into pdfs with the max size of 11MB
# next upload to google drive and open with google docs each


# from outside a dir with jpg or png files
# makepdf dir_with_jpg_files
# will run all jpg or png files

use strict;
use warnings;
use Cwd;
my $cwd = cwd;

#use Sysadm::Install qw(qquote);

# Max files size that gdocs will convert: 11MB
use constant MAX_SIZE => (1024*1024*11);

my $dir = shift || ".";
chdir $dir;
my @img =  map { qq[$dir/$_] } sort <*jpg>, <*jpeg>, <*png>, <*gif>, <*tiff>, <*tif>, <*JPG>, <*JPEG>, <*PNG>, <*GIF>, <*TIFF>, <*TIF>, <*/*jpg>, <*/*jpeg>, <*/*png>, <*/*gif>, <*/*tiff>, <*/*tif>, <*/*JPG>, <*/*JPEG>, <*/*PNG>, <*/*GIF>, <*/*TIFF>, <*/*TIF>;;
chdir $cwd;

#die join "  ",   $dir, @img;

my $output = "output.pdf";
$output = "$dir" if $dir ne ".";

my @pdfs = ();
my $c = 0;
my $total = 0;
my @list = ();
my $full = 0;
while (@img) {
    my $sz = -s $img[0];
    #print "size $sz\n";
    if (($total + $sz) < MAX_SIZE) {
        push @list, map { qq["$_"] } shift @img;
        $total += $sz;
        #print "filling $total $sz\n";
    }
    else {
        $full = 1;
    }

    if ($full or not @img) {
        $c++;
        #print "ok,  $total, @list\n";
        #die MAX_SIZE, $total, @list;
        my $f = sprintf "$output-%02d.pdf", $c;
        my $cmd = qq[convert -define pdf:use-trimbox=true @list "$f"];
        print "$cmd\n";
        system $cmd;
        $total = 0;
        @list = ();
        $full = 0;
    }
}