#!/usr/bin/perl 
use File::Copy;
use Time::Local;

# makeCabanissJpegs

# jody DeRidder, 5/3/10

# expects share drive content under /cifs-mount/
# requests collection directory on share drive
# locates all Scans directories and Transcript directories
# creates jpegs and dumps them into /home/jeremiah/UploadArea/jpegs
# for testing and distribution into Acumen.

# will make another version of this to pull content from share
# into deposits directory, verify the copies, and then delete on share.

## Copyright (c) 2010, The University of Alabama Libraries. 
## Contributed by Jody DeRidder, 10/10/10.
## 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.


&timestamp;
# location hardcoded here:
$inbase = "/cifs-mount/Digital_Coll_Complete/u0003_0000252_Cabaniss/";
$newdir = "/home/jeremiah/CABANISS/jpegs/";
$collnum = "u0003_0000252";




opendir(BASE, $inbase) or die "can't open $inbase\n";
while ($file = readdir(BASE)){
#  print "looking at $file\n";
  if ($file =~ /^\./){next;}  # skip dot files
  $path = $inbase.$file;
  if (-d $path){
    push (@dirs, $file);
    }
  }
close(BASE);
 
RESELECT:
$dircount = scalar @dirs;

print "\n\nI'm looking through $inbase. \n Here are the directories there.  \n\n";
$ans = "y";
while ($ans =~ /y/i){
  for ($i = 1; $i <= $dircount; $i ++){
    print $i.")  ".$dirs[$i-1]."\n";
    }

  print "\nWhich directory do you want? \n Type the number and press enter:\n\n";

  $num = <STDIN>;
  chop $num;
  $num --;
  push (@scansdirs, $inbase.$dirs[$num]."/");  
  print "Do you want to select another directory also?  Y or N:\n";
  $ans = <STDIN>;
  }


# output file will be based on collection number and timestamp
$output = "/home/jeremiah/CABANISS/output/".$collnum."_".$timestamp.".txt";
$out = "CABANISS/output/".$collnum."_".$timestamp.".txt";
open (OUT, ">".$output) or die "can't open $output\n";


print "Performing a bit of QC first.  Please be patient...\n";
@mydirs = @scansdirs;
foreach $dir (@mydirs){


  opendir(DIR, $dir) or die "can't read through $dir directory\n";
  while ($file = readdir(DIR)){
    if ($file =~ /^\./ || $file =~ /Admin/){
      next;  # skip dot files
      }
    $path = $dir.$file;
    if (-d $path){

      if ($file =~ /^([a-z]{1}\d{4}\_\d{7})\_(\d{7})$/){
          $collnum = $1;
          $itemID = $1."_".$2;
          $thisItem = $2;
          if ($thisItem =~ /^(\d{2})(\d{2})(\d{3})/){
             $boxnum = $1;
             $foldernum = $2;
             $item_sequence = $3 + 0; # gets rid of padding zeros
             $bf = $boxnum."_".$foldernum;
             push (@{$ItemSeq{$bf}}, $item_sequence);

           #  print OUT "$boxnum $foldernum $item_sequence  $file\n";
             }
          }

       push (@mydirs, $path."/");
       }
    elsif ($file =~ /^([a-z]{1}\d{4}\_\d{7})\_(\d{7})(\_(\d{4})(\_(\d{3}))?)?\.tif$/){
       $collnum = $1;
       $itemID = $1."_".$2;
       $thisItem = $2;
       $thisPage = $4 +0 ;
       $thisSubpage = $6 + 0;
       if ($4){ $apage = 1;}
       else{ undef $apage;}
       if ($6) {$asubpage = 1;}
       else{ undef $asubpage;}


     #  print "collnum $collnum, item $itemID this Item $thisItem, this page $thisPage\n";
       if ($thisItem =~ /^(\d{2})(\d{2})(\d{3})/){
          $boxnum = $1;
          $foldernum = $2;
          $item_sequence = $3 + 0; # gets rid of padding zeros
          }
       else{  push (@badform, "Can't get boxnum, foldernum, item sequence from $thisItem");}

      $bf = $boxnum."_".$foldernum;
      if (! $apage){
         # print OUT "$boxnum $foldernum $item_sequence  $file\n";
          push (@{$ItemSeq{$bf}}, $item_sequence);
          } # this catches tifs not in subdirectories

       if ($asubpage){
         push(@{$itemPageSubs{$thisItem."_".$thisPage}}, $thisSubpage);
         }

       $tifcount ++;
       push (@{$collnumItems{$collnum}{$file}}, $dir);   # keeps list of directories where items are found
       undef $box;
       undef $folder;

       ($checkdir = $dir) =~ s,.*?(u0003\_0000252),u0003\_0000252,;  # pull off first part of this directory name


      # what is the series number and folder number?
        if ($checkdir =~ /Box\_(\d{1,2})(_[^\/]*)?\/Folder\_(\d{1,2})(_[^\/]*)?\/([^\/]+\/)?/i){
              $box = sprintf ("%02d", $1);  # left pad if needed
              $folder = sprintf ("%02d",$3);
              $itemdir = $5;
              if (($box ne $boxnum) || ($folder ne $foldernum)){ push(@badform, "$file  name does not reflect Box $box Folder $folder at $path");}
              $itemdir =~ s,\/,,g;

              if ($itemdir){
                if (!$thisPage){push (@errors, "$file is in $itemdir directory, but has no page number\n");}
                elsif ($itemdir ne $itemID){ push (@wrongdir, "$file is in $itemdir;  no match on item id\n");}
                elsif (! $asubpage){  push (@{$pages{$itemdir}}, $thisPage );}   # get page number sequence without the padding
                }
              }
          elsif ($checkdir =~ /Box\_(\d{1,2})(_[^\/]*)?\/([^\/]+\/)?/i){
              $box = sprintf ("%02d", $1);  # left pad if needed
              $itemdir = $3;
              if (($foldernum != 0) || ($box ne $boxnum)){ push(@badform, "$file  name does not reflect Box $box (no subfolders) at $path");}
              $itemdir =~ s,\/,,g;
              if ($itemdir){
                if (!$thisPage){push (@errors, "$file is in $itemdir directory, but has no page number\n");}
                elsif ($itemdir ne $itemID){ push (@wrongdir, "$file is in $itemdir;  no match on item id\n");}
                elsif (! $asubpage){  push (@{$pages{$itemdir}}, $thisPage );}   # get page number sequence without the padding
                }
              }

          else{  push (@errors, "cannot parse out box and folder from $path\n");}
          }
       else{
         if ($file =~ /thumbs\.db/i  || $path =~ /Admin/){ next;}
         push (@badform, "$file in $checkdir");
         }
       }
   close(DIR);
   }
$subtract = 0;
@allfiles = sort by_number (keys (%{$collnumItems{$collnum}}));
foreach $file (@allfiles){
#   print "found $file\n";
   @mydirs = @{$collnumItems{$collnum}{$file}};
   $numdirs = scalar (@mydirs);
   if ($numdirs > 1){
     $collect = join ("   \n", @mydirs);
     push (@dupes, "$file exists in more than one place:\n $collect");
     $subtract += $numdirs -1;  # subtract from total count of files
     }
   }

@boxfolders = sort keys(%ItemSeq);
foreach $bf (@boxfolders){
   ($box, $folder) = split ("_", $bf);
   $count = 1;
  # print "Box $box   Folder $folder";
   @myItems = sort by_number( @{$ItemSeq{$bf}});
   $numItems = scalar (@myItems);
   push (@foldercount, "Box $box   Folder $folder contains $numItems items");
   $totalItems += $numItems;
   foreach $mynum (@myItems){

             if ($mynum != $count){
                   $diff = $mynum - $count;
                   if ($diff < 0){ print "error:  $mynum item, expected count is $count\n";}
                   $lastmissing = $mynum -1;
                   if ($lastmissing != $count){
                      push (@badcount,  "In Box $box Folder $folder: $diff missing files:  $count through $lastmissing");
                      }
                   else{ push (@badcount,  "In Box $box Folder $folder:  $count is missing");}
                   }
             $count  = $mynum + 1;
             }
          }

#   for ($i = 1;  $i <= $numItems; $i++){
#     if ($myItems[$i-1] ne $i){
#       push (@badcount, "In Box $box Folder $folder: expected sequence $i instead of ".$myItems[$i-1]);
#       }
#     }
@hasPages = sort keys(%pages);
foreach $doc (@hasPages){
   @mypages = sort by_number( @{$pages{$doc}});
   $numItems = scalar (@mypages);
   push (@pagecounts, "$doc has  $numItems pages");
   $count = 1;

   foreach $mynum (@mypages){

             if ($mynum != $count){
                   $diff = $mynum - $count;
                   if ($diff < 0){ print "error:  $mynum item, expected count is $count\n";}
                   $lastmissing = $mynum -1;
                   if ($lastmissing != $count){
                      push (@badcount,  "$doc page problem: $diff missing files:  $count through $lastmissing");
                      }
                   else{ push (@badcount,  "$folder $doc page problem:  $count is missing");}
                   }
             $count  = $mynum + 1;
             }
          }

#   for ($i = 1;  $i <= $numItems; $i++){
#     if ($mypages[$i-1] ne $i){
#       push (@badcount, "$doc page problem:  expected sequence $i instead of ".$mypages[$i-1]);
#       }
#     }
#   }


#push(@{$itemPageSubs{$thisItem."_"$thisPage}}, $thisSubpage);

@itempages = sort keys (%itemPageSubs);
foreach $itempage (@itempages){
   @mypages = sort by_number( @{$pages{$doc}});
   $numItems = scalar (@mypages);
   push (@pagecounts, "$doc has  $numItems pages");
   $count = 1;

   foreach $mynum (@mypages){

             if ($mynum != $count){
                   $diff = $mynum - $count;
                   if ($diff < 0){ print "error:  $mynum item, expected count is $count\n";}
                   $lastmissing = $mynum -1;
                   if ($lastmissing != $count){
                      push (@badcount,  "$itempage subpage problem: $diff missing files:  $count through $lastmissing");
                      }
                   else{ push (@badcount,  "$itempage subpage problem:  $count is missing");}
                   }
             $count  = $mynum + 1;
             }
          }



$all = (scalar @allfiles) - $subtract;
print  "\nTotal count of valid content in this upload:\n  $totalItems items and $all digital files\n";

#print "tiffcount $tifcount\n";
if (@badform || @badcount || @wrongdir || @errors){
     print OUT "\nTROUBLE: \n";
     print OUT "-------------------------------------------\n";
     }
 else{
     print OUT "All is GREAT!!  GOOD WORK!!  :-) \n";
    }

   if (@errors){
        print OUT "\nThese general errors impeded this script, so everything may NOT have been checked:\n";
        print OUT "Please repair and run this again.\n";
        foreach (@errors){ print OUT "    $_\n";}
        }
   if (@wrongdir){
        print OUT "\nThe following files or directories do NOT reflect the name of their parent directory\n";
        foreach (@wrongdir){ print OUT "    $_\n";}
        }

   if (@badform){
        print OUT "\nThe following filenames or directories are not in the correct format:\n";
        foreach (@badform){ print OUT "    $_\n";}
        }

    if (@badcount){
        print OUT "\nThe following folders or items have sequence problems:\n";
        foreach (@badcount){ print OUT "    $_\n";}
        }


print OUT "\n\nHere's some more info:\nFOLDER COUNTS:\n_________________\n";

foreach (@foldercount){ print  OUT $_."\n";}
print OUT "\n\nPAGE COUNTS:\n_______________________\n";
foreach (@pagecounts){ print OUT $_."\n";}

if (@errors){
   print "Errors were found;  please check $out and correct them\n then rerun this script.\n";
   close OUT;
   exit;
   }



# call another process to make the jpegs, using nohup so it won't stop when the ssh window closes.
print "\n\nQC complete!  It all looks great!!\n";
print "\n\nWe are starting to make the JPEGS now.\n";

print "I will be picking up the following directories.  Y or N?\n";
foreach (@scansdirs){ print "   $_\n";}
$ans = <STDIN>;
if ($ans =~ /n/i){
  print "Let's try again, then.\n";
  goto RESELECT;
  }


unless (fork){
   # the child process does this stuff

# we have all scans directories in @scansdirs and all transcript directories in @transdirs


# now, let's make the jpegs for the scans 
  foreach $dir (@scansdirs){
      opendir(DIR, $dir) or die "can't open $dir\n";
      while ($file = readdir(DIR)){
         if ($file =~ /^\./ || $file =~ /thumbs\.db/i){ next;}
         $path = $dir.$file;
     #    print "looking at $file\n";
         if ($file =~ /^(.*?)(\.tif)/ ){   # if a tiff, make the jpegs and drop them on the server

      #     print "file number is $1\n";
            $filenum = $1;
            $big = $newdir."/".$filenum."_2048.jpg";
  #          $mid = $newdir."/".$filenum."_512.jpg";
            $small = $newdir."/".$filenum."_128.jpg";

        # create the derivatives if they don't exist

       #  print "convert $path -strip -density 96 -resample 96x96  -resize 2048x2048 -filter Cubic -quiet $big\n\n";
           if (! -e $small){
              `convert $path -strip -density 96 -resample 96x96  -resize 128x128 -filter Cubic -quiet $small`;
              }

           if (! -e $big){
              `convert $path -strip -density 96 -resample 96x96  -resize 2048x2048 -filter Cubic -quiet $big`;
              }
   #      if (! -e $mid){
    #        `convert $path -strip -density 96 -resample 96x96  -resize 512x512 -filter Cubic -quiet $mid`;
     #       }

           sleep(1);  # give it time to write the files
           if (! -e $small){
               print OUT "ERROR:  Failed to make a 128 size jpeg for $filenum!\n";
               }
           if (! -e $big ){
               print OUT "ERROR:  Failed to make a 2048 size jpeg for $filenum!\n";
               }


            }
        elsif (-d $path){
           push (@scansdirs, $path."/");
           }
        else{ print OUT "Not a tif;  ignoring:  $file\n";}
        }
     close(DIR);
     }
# these for repair, later
  push (@dirlist, $newdir);




# now repair the problems caused by thumbs in the tiffs.
# goes through  the directories
# finds jpg files with -1.jpg and -0.jpg
# renames the -0 ones, removing the -0, and 
# deletes the -1 files

  foreach $dir (@dirlist){
    opendir (DIR, $dir) or die "can't look through $dir\n";
    while ($file = readdir(DIR)){
#     print "looking at $file in $dir\n";
     if ($file =~ /^\./ ){ next;  }  # skip dot files
       $path = $dir."/".$file;
       if ( -d $path){   # must be a directory
         push (@dirlist, $path);
         }
       elsif ($file =~ /^(.*)\-1\.jpg/){  # jpg file
         `rm $path`;
          }
       elsif ($file =~ /^(.*)\-0\.jpg/){
       $filenum = $1.".jpg";
       $good = $dir."/".$filenum;
       `mv $path $good`;
      if (! -e $good){ print OUT "ERROR: Repair failed to move $path to $good!\n";}

        }
     }

   }

  print OUT "Upload of JPEGs and any transcript material is complete.\n";
  print OUT "Please check content in UploadArea, then run relocate_all\n to distribute into Acumen.\n";
  print OUT "\n\nGREAT WORK!!!  :-)\n\n";
  close(OUT);
  exit;
  }


# parent process gives a little more info, then exits
print "Please check back in a few hours\n";
print "Any problems found will be in the \n$out file.\n";
print "\n\nThank you!!\n\n";
exit;


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";
}

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