#!/usr/bin/perl
use Time::Local;
use DBI;

# acumenCount

# checks through the directories in /srv/www/htdocs/content and does a count
# of collections, item level and page level files

# jody DeRidder  updated 4/2/10
## Copyright (c) 2010, The University of Alabama Libraries. 
## Contributed by Jody DeRidder, 6/10/10.
## All rights reserved.

## Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:

##    * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
##    * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in 
##       the documentation and/or other materials provided with the distribution.
##    * Neither the name of The University of Alabama Libraries nor the names of its contributors may be used to endorse or promote products 
##       derived from this software without specific prior written permission.

##THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, 
##THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR 
##CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
##PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
##LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
##EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

$hostname = "localhost";
$port = "3306";
$user = "user";
$password = "password";
$database = "InfoTrack";
$dbh = DBI->connect("DBI:mysql:$database:$hostname:$port",
      $user, $password) or die "can't connect to database: ",$DBI::errstr,"\n";

$h->{PrintError} = 1;
$h->{RaiseError} = 1;

$base = "/srv/www/htdocs/content/";

&timestamp; 
$out = "./output/AcumenCollCount_".$timestamp.".txt";
open (OUT, ">".$out) or die "can't open $out\n";
print OUT  "Coll ID\tColl Title\tItem Count\tFile Count\tHas EAD (1=yes)\n";

opendir(BASE, $base) or die "can't look through $base\n";
while ($file = readdir(BASE)){
   if ($file =~ /^\./){ next;}
   elsif ($file =~ /^[a-z]{1}\d{4}$/){
     push (@topdirs, $base.$file);
     }
   }
close(BASE);

# collection level
foreach $dir (@topdirs){
  opendir(IN, $dir) or die "can't look through $dir\n";

  while ($file = readdir(IN)){
    if ($file =~ /^\./ || $file =~ /Documentation/ || $file =~ /Metadata/){ next;}
    push (@colldirs, $dir."/".$file);
    }
  close(IN);
  }

foreach $colld (@colldirs){
   ($short = $colld) =~ s,$base,,;   # take off base
   $short =~ s,\/,\_,g;  #replace / with _
   $short =~ s,__+,_,g; # clean up doubles  -- now $short should match collnum
   push (@collnums, $short);
   }

$numcolls = scalar (@collnums);
print "we have $numcolls collections represented in Acumen.\n";
 
#$out2 = "> ./collListAcumen";
#open (OUT2, $out2) or die "can't open $out2\n";

@sorted = sort (@collnums);

foreach $coll (@sorted){
 #  print OUT2 "$coll\n";
   undef @mydirs;
   $mycount = 0;
   undef $title;
 
   ($mydir = $coll) =~ s,\_,\/,g;  # reconstruct directory from name
   $mydir = $base."/".$mydir."/";

   $id = $dbh->quote($coll);
   $d = $dbh->quote("D");
   $a = $dbh->quote("A");
   $sth = $dbh->prepare("select title from allColls where id_2009 = $id and analogOrDigital = $d")
     or die "can't prepare select for $coll: ",$dbh->errstr(),"\n";
   $sth->execute()
       or die "Can't select for $coll : ", $sth->errstr(),"\n";

   $title = $sth->fetchrow_array();
   $sth->finish();

   if (!$title){
     $sth = $dbh->prepare("select title from allColls where id_2009 = $id and analogOrDigital = $a")
     or die "can't prepare select for $coll: ",$dbh->errstr(),"\n";
     $sth->execute()
       or die "Can't select for $coll : ", $sth->errstr(),"\n";

     $title = $sth->fetchrow_array();
     $sth->finish();
     }

   opendir(COLL, $mydir) or die "can't open $mydir\n";
   while ($file = readdir(COLL)){   # looking through the collection directory
#     if ($file =~ /^\./|| $file =~ /Documentation/ || $file =~ /Metadata/){ next;}
    if ($file =~ /^\./ || $file =~ /Documentation/){ next;}
    elsif ($file =~ /Metadata/){
      $path = $mydir."/".$file;
      opendir (MD, $path) or die "can't look in $path\n";
      undef $found;
      while ($afile = readdir(MD)){
        if ($afile =~ /^(.*?)\.ead\.xml/){
          push (@eads, $1);
          $found = 1;
          }
        }
      if (!$found){ push (@noEads, $mydir);} 
      close (MD);
      next;
      }
   }
  
   push (@mydirs, $mydir);

   undef @items;
   undef @files;
   undef @filedirs;  # use this for getting file count. use mydirs for getting item count
   push (@filedirs, $mydir);
  
   foreach $dir (@mydirs){
      opendir(DIR, $dir) or die "can't look through $dir\n";
      while ($file = readdir(DIR)){
        if ($file =~ /^\./ || $file =~ /Metadata/ || $file =~ /Documentation/ ||
           $file =~ /\_512\.jpg/ || $file =~ /\_128\.jpg/ || $file =~ /\.ocr\.txt/ ){ next;}  # skip these 
        $path = $dir.$file;
     
      # print " looking at $path\n"; 
       if (-d $path){
         if ($path =~ /Transcripts/){
            next;
            }

         ($id = $path) =~ s,\/srv\/www\/htdocs\/content\/,,;
          $id =~ s,\/,\_,g;
          $id =~ s,\_$,,;
          $id =~ s,^\_,,;
          $mods = $path."/Metadata/".$id.".mods.xml";
     #     print " looking for MODS for $id in $mods\n";
          if (-e $mods){
            push (@items, $file);
            next;   # do NOT go into lower directories
            }
        #  elsif (!($file =~ /^\d{3}$/)){print "no MODS for $id at $mods\n";}
          push (@mydirs, $path."/");
          }           
      elsif ($file =~ /\.txt/ || $file =~ /\_2048\.jpg/ || $file =~ /\.pdf/ || $file =~ /\.mp3/){
         push (@files, $file);
         }
      }
    close(DIR);
    }
  
# now for the filecount
  foreach $dir (@filedirs){
      opendir(DIR, $dir) or die "can't look through $dir\n";
      while ($file = readdir(DIR)){
        if ($file =~ /^\./ || $file =~ /Metadata/ || $file =~ /Documentation/ ||
           $file =~ /\_512\.jpg/ || $file =~ /\_128\.jpg/ || $file =~ /\.ocr\.txt/ ){ next;}  # skip these 
        $path = $dir.$file;
     #   print " looking at $path\n";
        if (-d $path){
          push (@filedirs, $path."/");
          }
      elsif ($file =~ /\.txt/ || $file =~ /\_2048\.jpg/ || $file =~ /\.pdf/ || $file =~ /\.mp3/){
         push (@files, $file);
         }
      else{ print "what is this? $path\n";}
      }
    close(DIR);
    }

  
  $itemcount = scalar (@items);
  $filecount = scalar (@files);
#  if ($coll =~ /u0003\_0000252/){
#     open (OUT2, ">./cabanissFiles") or die "can't write to cabanissFiles\n";
#     foreach (@files){  print OUT2 $_."\n";}
#     close(OUT2);
#     }
  $totalItems += $itemcount;
  $totalFiles += $filecount;
  print OUT "$coll\t$title\t$itemcount\t$filecount\t$found\n";
  } 

$numEADs = scalar (@eads);
print OUT "\n\nTotal items: $totalItems\nTotal files:  $totalFiles\nNumber of collections:  $numcolls\n";
print OUT "Number of EADs: $numEADs\n";
$numNoEADs = scalar (@noEads);
print "Number of collections with no EAD: $numNoEADs\n\n";
print "\n\nLook in $out to find counts by collection in Acumen. \n Open in Excel with tabs as delimiters.\n\n";

close(OUT);
#close(OUT2);    

sub by_number {$a <=> $b;}

sub timestamp{
#following for Windows
#print "hit enter twice please\n";
#$date = `date`;
#$time = `time`;

#print $date."\n";
#if ($date =~ /.*? (\d*)\/(\d*)\/(\d*)/){
 #    $date = $3.$1.$2;
  #    }
#print $date."\n";
#if ($time =~ /.*? (\d*)\:(\d*)\:(\d*)\./){
 #    $time = $1.$2.$3;
  #   }
#print $time."\n";
#$timestamp = $date."T".$time;
#print $timestamp."\n";

# following for unix
($sec, $min, $hour, $mday, $mon, $year, $wday, $yday, $isdst) = gmtime();
##$year += 1900;
$mon ++;
if ($mon < 10){ $mon="0".$mon;}  #need 2 digits
if ($sec < 10){ $sec="0".$sec;}
if ($min < 10){ $min="0".$min;}
if ($hour < 10){ $hour="0".$hour;}
if ($mday < 10){ $mday="0".$mday;}

$year = $year + 1900;
$timestamp= "$year-$mon-$mday\T$hour:$min:$sec\Z";
}