#!/bin/bash

####################################################################
#####                                                          #####
#####            AUTHOR: BORIS KIEFER (08/2019)                #####
#####                                                          #####
####################################################################

# THIS SOFTWARE IS DISTRIBUTED AS IS WITHOUT ANY WARRANTY
# USE AT YOUR OWN DISGRESSION
#
# ==> WORK ON A COPY OF THE RECOVERED FILES 
#     IN CASE SOMETHING GOES WRONG

echo "REMOVE DUPLICATE FILES"
echo "COMMAND LINE ARGUMENT == TARGET DIRECTORY"
TARGET="$1"
echo "TARGET DIRECTORY: $TARGET"

# START PROCESSING THE FILES
# INITIALIZE COUNTERS
nfiles=0   # TOTAL NUMBER OF FILES
nfnew=0    # NUMBER OF DIFFERENT FILES
nfrm=0     # NUMBER OF REDUNDANT FILES
sizeold=0  # INITIAL VALUE FOR SIZE COMPARISON

cd ./ZREC_BK/$TARGET                 # MOVE INTO TARGET DIRECTORY

for cfile in $( ls -S -1 *.txt )     # LOOP OVER ALL TXT FILES
 do

# Count total number of files
 nfiles=$(( $nfiles + 1 ))

# DETERMINE CURRENT FILE SIZE
  size=`ls -ls $cfile | awk '{print $6}'`

 if [[ $size -ne $sizeold ]]; then         

  nfnew=$(( $nfnew + 1 ))
  sizeold=$size    # FIRST OCCURENCE OF SIZE

 else 

  nfrm=$(( $nfrm + 1 ))

  TEXT=`echo "$cfile" | rev | cut -d. -f 2- | rev`
#  TEXT=`echo "$cfile" | cut -d. -f1` # GENERATE PDF FILENAME
  TEXT=$TEXT.pdf
  echo "REMOVING $cfile $TEXT"
  rm $cfile $TEXT

 fi

done   # END LOOP OVER FILES

pwd

echo "SUMMARY: "
echo "NFILES                 : $nfiles"
echo "INDEPENDENT            : $nfnew"
echo "REDUNDANT              : $nfrm"
