#!/bin/bash

# base file to check for duplicate names
base_file=$1

# set input field separator to newline so each line is stored in an array element
IFS=$'\n'
# use sort and uniq to output duplicate lines in to array
dup_list=( $(cat "$base_file" | sort -k2 | uniq  -f1 -D) )

# count for indexed name
name_count=0
# to identify when we have a new duplicate
current_dup=''

# loop on duplicate names
for dup_name in "${dup_list[@]}"
do

   # use second field for name
   unset FIELD; IFS=$'\t' read -a FIELD <<< "$dup_name"

   # set name value
   current_name="${FIELD[1]}"

   # if no current dup has been set
   if [ "$current_dup" == "" ]; then
      # set base to check for new duplicate
      current_dup=$current_name
      #create new dup name
      # name count is already 0 so no need to increment
      new_name='dup_'$name_count'_'$current_name
   # if the current name matches the current dup, increment counter
   elif [ "$current_dup" == "$current_name" ]; then
      # increment counter
      name_count=$((name_count+1))
      # create name based on incremented counter
      new_name='dup_'$name_count'_'$current_name
   # if there is a new dup series
   elif [ "$current_dup" != "$current_name" ]; then
      # set base to new duplicate
      current_dup=$current_name
      # reset name counter
      name_count=0
      #create new dup name
      new_name='dup_'$name_count'_'$current_name
   fi

   # test print
   echo $new_name
 
   # find first instance of dup name in base file and replace
   sed "0,/$current_name/s//$new_name/" $base_file > 'revised_'$base_file

   # make changes in other files

done

dup_0_(1R)-1,2,3,3-tetraamino-2-propen-1-ol
dup_1_(1R)-1,2,3,3-tetraamino-2-propen-1-ol
dup_2_(1R)-1,2,3,3-tetraamino-2-propen-1-ol
dup_0_2-[2-hydroxyethyl(methyl)amino]ethanol
dup_1_2-[2-hydroxyethyl(methyl)amino]ethanol
dup_2_2-[2-hydroxyethyl(methyl)amino]ethanol