My ultimate goal is to recursively scan all of a specified directories contents on day x and on day x+1 scan again. Then compare day x to x+1 for differences in files(new/missing), file size, directory size, directory content count and report the differences.

My solution below seems to be a good start, but my full directory listing creates 1G flat files that cannot be read into a hash (hash creation causes program to die for running out of memory).

"Do you want to create one file per directory, such that this one file contains the concatenation of all data found in all other data files in that directory?"
I want a listing of directory contents in each directory file

Any other suggestions on my methods to end goal are welcomed :) Thank You!

#!/usr/local/bin/perl -w

use Date;
use File::Find;
use Data::Dumper;

my $d = Date->new();
my $today=$d->yyyymmdd;
my $yesterday=$d->yesterday;
my $progname   = `basename $0`; chomp($progname);
my $main = "/home/users/user";
my $out = "/home/users/user/tmp/$progname_$today.dat";
my $comp = "/home/users/user/tmp/$progname_$yesterday.dat";
my $final = "/home/users/user/tmp/$progname_compare.dat";
my $skip = qw/skip1|skip2|skip3/;
my $max_size_diff = "25";
my $max_file_diff = "0";

## Main ##
open (OUT, ">$out");
find ({wanted => \&data_for_path, follow=>1, follow_skip=>2}, call_dir
+($p=1), call_dir($p=2), call_dir($p=3));
close OUT;
process();

## Builds the directory structure by using File::Find to recurse into 
+each subdir##
sub data_for_path {
   $size_d = 0;
   if ($File::Find::name =~ /$skip/){return;}
   if (-d $File::Find::name){
      $directory = $File::Find::name;
      print OUT "$directory\tDirectory\tNULL\tNULL\tNULL\n";
   }
   if (-f $File::Find::name){
      my $file = $File::Find::name;
      my $size_f = -s $file;
      $size_d += -s $file;
      print OUT "$file\tFile\t$size_f\tNULL\t0\n";
   }
   if (-l $File::Find::name){
      my $name = $File::Find::name;
      my $link = readlink $name;
      my $size_l = -s $link;
      print OUT "$name\tLink\t$size_l\t$link\t0\n";
   }
}

## Calls wich directory path to use from the main ##
sub call_dir{
   if ($p == 1){
      $sub_dir = "$main/tmp/";
   }
   elsif ($p == 2){
#      $sub_dir = "$main/data";
   }
   elsif ($p == 3){
      $sub_dir = "$main/exe";
   }
}

## Processes flat files ##
sub process {
   open (TODAY_IN, $out);
   foreach my $line_t (<TODAY_IN>){
      ($path, $type, $size, $link, $nfiles) = split(/\s+/, $line_t);
      $today{$path}{'Type'} = $type;
      $today{$path}{'Size'} = $size;
      $today{$path}{'Link'} = $link;
      $today{$path}{'NFILES'} = $nfiles;
   }
   close TODAY_IN;
   open (YESTERDAY_IN, $comp);
   foreach my $line_y (<YESTERDAY_IN>){
      ($path, $type, $size, $link, $nfiles) = split(/\s+/, $line_y);
      $yesterday{$path}{'Type'} = $type;
      $yesterday{$path}{'Size'} = $size;
      $yesterday{$path}{'Link'} = $link;
      $yesterday{$path}{'NFILES'} = $nfiles;
   }
   close YESTERDAY_IN;
#   print Dumper %today;
#   print Dumper %yesterday;
   diff(%today, %yesterday);
   print Dumper %diffOut;
}

## Diffs todays directory structure to yesterdays structure ##
sub diff {
   open (COMP, ">$final");
   foreach $key (keys %today){
      if (exists $yesterday{$key}){
         $size_t = $today{$key}{'Size'};
         $size_y = $yesterday{$key}{'Size'};
         $nfiles_t = $today{$key}{'NFILES'};
         $nfiles_y = $yesterday{$key}{'NFILES'};
         if ($size_y > 0 && $size_t > 0){
            if ($size_t > $size_y){
               my $diff_t = (1-($size_y/$size_t))*100;
               if ($diff_t >= $max_size_diff){
                  $diffOut{$key}{'SizeYest'} = $size_y;
                  $diffOut{$key}{'SizeToday'}  = $size_t;
                  $diffOut{$key}{'SizeDiff'} = $diff_t;
                  print COMP "$key\tYEST:$diffOut{$key}{'SizeYest'}\tT
+OD:$diffOut{$key}{'SizeToday'}\tDIFF:$diffOut{$key}{'SizeDiff'}\n";
               }
            }
            elsif ($size_y > $size_t){
               my $diff_y = (1-($size_t/$size_y))*100;
               if ($diff_y >= $max_size_diff){
                  $diffOut{$key}{'SizeToday'}  = $size_t;
                  $diffOut{$key}{'SizeYest'} = $size_y;
                  $diffOut{$key}{'SizeDiff'} = $diff_y;
                  print COMP "$key\tYEST:$diffOut{$key}{'SizeYest'}\tT
+OD:$diffOut{$key}{'SizeToday'}\tDIFF:$diffOut{$key}{'SizeDiff'}\n";
               }
            }
            if (-d $key){
               if ($nfiles_y > 0 && $nfiles_t > 0){
                  $diffFiles = $nfiles_t-$nfiles_y;
                  if ($diffFiles > $max_file_diff){
                     $diffOut{$key}{'FileDiff'} = $diffFiles;
                     print COMP "$key\tFDIFF:$diffOut{$key}{'FileDiff'
+}\n";
                  }
               }
            }
         }
      }
      else {
         $diffOut{$key}{'SizeToday'} = $size_t;
         $diffOut{$key}{'SizeYest'} = 0;
         $diffOut{$key}{'SizeDiff'} = "New";
         print COMP "$key\tYEST:$diffOut{$key}{'SizeYest'}\tTOD:$diffO
+ut{$key}{'SizeToday'}\tDIFF:$diffOut{$key}{'SizeDiff'}\n";
      }
   }
   close COMP;
   print "Done!\n";
}

[download]

In reply to Re^2: Manage Directory Structure by boardryder
in thread Manage Directory Structure by boardryder

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.