#!/bin/bash                                                                                             
#check to see if there is an input file:                                                                
if [ "$#" -lt 1 ]
then
  echo "Usage: $0 input_file ..."
  exit 1
fi

#Check if the file is empty or not                                                                      
file=$1
if [[ -s $1 ]]                   # if not empty:
then
  echo ""
  echo "**** $file has data."
  cat $1 | sed 's/>/\n>/g' > temp1.txt
  cat temp1.txt | sed '/^>/ d' > temp2.txt
  awk '!NF{if(++n <=1) print; next}; {n=0; print}' < temp2.txt > dna.out
  awk '/./{printf "%s",$0;next} {print "\n";} END{if (/./)print""}' dna.out > DNA.out
  echo "**** Number of DNA sequences:"
  grep -cve '^\s*$' DNA.out
  echo "**** Mumber of empty lines:"
  grep -ce '^\s*$' DNA.out
  echo ""
  #Remove duplicate empty lines:                                                                        
  awk '!NF{if(++n <=1) print; next}; {n=0; print}' < temp2.txt > DNA.out                               
  echo "**** DNA.out created (removed FASTA header)"
  #convert to mRNA and remove temp1, temp2 to avoid confusion                                           
  tr ACGT ACGU < DNA.out > RNA.out
  echo "**** RNA.out created (T -> U)"
  echo ""
  rm temp1.txt temp2.txt
  moved to conversion:                                                                                
  while read rna; do                                                                                  
      aawork=$(echo "${rna}" | sed -n -e 's/\(...\)\1 /gp' | sed -f rna.sed)                          
      echo "$aawork" | sed 's/ //g'                                                                   
      echo "$aawork" | tr ' ' '\012' | sort | sed '/^$/d' | uniq -c | sed 's/[ ]*\([0-9]*\) \(.*\)/\2\
: \1/'                                                                                                  
  done                                                                                                
  echo "**** creating AminoAcid from DNA:"
  ./convert_dna.sh < DNA.out > DNA_AminoAcid.out
  echo "**** Amino Acids from DNA saved in DAN_AminoAcid.out."
  echo "**** creating AminoAcid from RNA:"
  ./convert_rna.sh < RNA.out > RNA_AminoAcid.out
  echo "**** Amino Acids from RNA saved in RAN_AminoAcid.out."
  echo ""

else    # if the file is empty.                                                                         
  echo "**** $1 has no data, or file does not exist."
  echo "**** done!"
  echo ""
#clean the FASTA file and remove all lines starting with >, adding a new line first to avoid mixing all DNA samples:                                                                                           
fi;