ScanSnapのPDFファイルがOCR済みかどうかチェックする

gistfile1.txt

#!/usr/bin/env perl

use strict;
use feature ":5.10";
use CAM::PDF;
use Encode;
use Encode::UTF8Mac;
use IO::All;

$|=1;
binmode STDOUT, ":utf8";

my $dir = io("/Users/bokutin/Pictures/ScanSnap/");
my @pdf = grep { $_->filename =~ m/\.pdf$/i } $dir->all_files;

for my $file (@pdf) {
    my $fn = $file->pathname;
    my $pdf = CAM::PDF->new($fn);

    my $has_text = 0;
    for my $page_num ( 1 .. 10 ) {
        if ( $pdf->getPageText($page_num) ) {
            $has_text = 1;
            last;
        }
    }

    say sprintf("%s, %s", decode('utf-8-mac', $file->filename), $has_text ? "YES" : "NO");
}