#!/usr/bin/perl

use strict;
use warnings; 
use DBI;
use File::Find::Rule;
use PDF::API2;
use File::Basename;
#use Data::Dumper;
#use Data::Dump 'pp';

my $t0 = time();

my ($got_count, $got_timed, $got_total_pages) = get_pdfs();

print "\n\n Result:  $got_count files found in $got_timed seconds - Total number of pages: $got_total_pages\n\n\n";

exit;

sub get_pdfs {

  my $dbh = DBI->connect ("dbi:CSV:", undef, undef, {
      f_ext   => ".txt/r",
      #f_dir   => "",
      f_enc   => "utf-8",
      RaiseError => 1 }
  ) or die "Cannot connect: $DBI::errstr";
         
  $dbh->{csv_tables}{prod_pdf_files} = {
 
    f_file => "data.txt", # list of file names to search
    col_names => [qw( file_name location acc_nbr )],

  };

  my $sth = $dbh->prepare ("
      SELECT DISTINCT file_name, location
      FROM prod_pdf_files 
      --WHERE file_name LIKE ?
   ");
   
  #$sth->execute('%.pdf');
  $sth->execute();
  my $pdfs = $sth->fetchall_arrayref();
  #pp @$pdfs;
  
  my $count = 0;
  my $totalpages = 0;
  
  my $other_path = '/alldocs';
  
  foreach my $files ( @{$pdfs} ) {

    next unless ($files->[0] =~ m/\.pdf$/i);
    
    my $filename_loc = $other_path.$files->[1].$files->[0];
    my $pages = pdf_pagecount( $filename_loc );
    $totalpages += $pages;
    $count++;
    
  }

  my $dur = time()-$t0;
  
  return $count, $dur, $totalpages;

} # End get_pdfs Sub

sub pdf_pagecount {
    
  my $doc = shift;
  my $pages;

  eval { my $pdf = PDF::API2->open($doc);
    $pages = $pdf->pages;
  };
  
  if ($@){
    warn "$doc | Error captured : $@\n";
  } else {
    return $pages;
  };


}