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

# ocrSelected

# jody DeRidder, 10/12/10

# looks in /srv/deposits/ocrMe for files ending in ocrList.txt
# each of which contains a list of item numbers to be digitized followed by 1 (yes) or 0 (no)
# collects the item numbers followed by a 1
# goes through /srv/archive
# finds tiff files
# checks to see if OCR files for this already exist in /srv/www/htdocs/content
# if not, creates directories for them there
# creates derivatives
# puts the derivatives there

## Copyright (c) 2010, The University of Alabama Libraries. 
## Contributed by Jody DeRidder, 7/30/10.
## 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.

$lists = "/srv/deposits/ocrMe/";
opendir(LISTS, $lists) or die "can't look in $lists\n";
while ($file = readdir(LISTS)){
   if ($file =~ /^\./){ next;}  # no dot files
   if ($file =~ /ocrList\.txt/i){
      $gotone = $lists.$file;
    #  print "found $gotone\n";
      open (IN, $gotone) or die "can't open $gotone\n";
      while ($line = <IN>){
        if ($line =~ /^(([a-z]{1}\d{4}\_\d{7})\_\d{7})\s+1/){
          $coll = $2;
          $id = $1;
          push (@{$idlist{$coll}}, $id);   # hash of collection numbers as keys, arrays of ids as values
          push (@items, $id);
          }
        else { print "no match:  $line\n";}
       }
     close(IN);
     }
   }
close(LISTS);

@colls = keys(%idlist);
#foreach $coll (@colls){
#    @mylist = @{$idlist{$coll}};
#    print "\n$coll:\n";
#    foreach (@mylist){ print "    $_\n";}
#    }

#exit;


# location hardcoded here:
$inbase = "/srv/archive/";
$outbase = "/srv/www/htdocs/content/";


foreach $coll (@colls){
    ($adir = $coll) =~ s,\_,\/,g;  # substitute forward slash for underscores
    push (@dirlist, $inbase.$adir);
    }    

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
   if ($file =~ /^[a-z]{1}\d{4}/ || $file =~ /Transcripts/ || $file =~ /^\d{3,7}$/){ 
  # if ($file =~ /^[a-z]{1}\d{4}/ || $file =~ /\d{3,7}/ )  # not using Transcripts directories
          # must match pattern u0003, p0004,(etc) 3-7 numbers, etc
     $path = $dir."/".$file;
     if ( -d $path){   # must be a directory

        push (@dirlist, $path);
        }
     elsif ($file =~ /^(.*)\.tif/){  # tif file
 
       $filenum = $1;
       undef $found;
       foreach $id (@items){
         if ($filenum =~ /$id/){  
            $found = 1;
            last;
            }
         }
      if ($found){

       # here, capture the path.
       ($newdir = $dir) =~ s,archive,www\/htdocs\/content,;
       $newdir .= "/Transcripts";
       print "$file from $dir to $newdir\n";

 # create the path in the new location if it doesn't exist
       if (! -e $newdir){
         undef $test;
         $mypath = $newdir;
         $mypath =~ s,$outbase,,;

         while ($mypath =~ /(.*?\/)(.*)/){
             $test .= $1;
             $mypath = $2;
             $apath = $outbase.$test;
             if (!-e $apath){
               `mkdir -m 0775 $apath`;
                }
             }
          $test .= $mypath;
          $apath = $outbase.$test;
          if (!-e $apath){
            `mkdir -m 0775 $apath`;
             }
          }
 
       # create the derivatives if they don't exist
# name them appropriately and put them in the new location

       $ocr = $newdir."/".$filenum.".ocr";

       if (! -e $ocr){ 
           $val = `tesseract $path $ocr`;
           if ($val){ print "ERROR $val creating $ocr.txt\n";}
           else {print "created $ocr.txt\n";}
           }

         }
       }
      }
    }
  close(DIR);
  }

# clean up
`chown -R taloewald:www $outbase`;
`chmod -R 775 $outbase`;