Shell Programming and Scripting

a.txt
------
x001;frtb70;xyz;109
x001;frvt65;sec;239
x003;wqax34;jul;659
x004;yhud43;yhn;760

b.txt
------
x001;abcd80;xyz;193
x001;crrp28;xse;456
x002;lmno10;xyz;784
x002;jfds65;jfd;739
x002;juop88;jup;879
x003;yulo90;rem;542
x003;kihl98;dnt;312
x004;urel25;ewb;342


c.txt [output]
------
x001;frtb70;xyz;109
x001;frvt65;sec;239
x002;lmno10;xyz;784
x002;jfds65;jfd;739
x003;wqax34;jul;659
x004;yhud43;yhn;760

#!/usr/bin/env perl

sub prepareHash {
	#my ($in_file, $primary_Key, $delimiter) = @_;
	my $in_file   = shift;
	my $key       = shift;
	my $delimiter = shift;
	
  my @line_tokens;
  my %FILE_Hash;
  open( IN_FILE, "< $in_file" ) or die "Can't open $in_file : $!";
	  
  while (<IN_FILE>) {
     my $in_line = $_;
     chomp($in_line);
     @line_tokens = split(/$delimiter/, $in_line);
	   $FILE_Hash{$line_tokens[$key]} = $in_line; 
  }
  
  close IN_FILE;

  return %FILE_Hash;
}

my $input1 = "/export/home/a.txt";
my $input2 = "/export/home/b.txt";
my $output = "/export/home/c.txt";

my %A_Hash  = prepareHash($input1, 0 , ";" );
my %B_Hash  = prepareHash($input2, 0 , ";" );

open( OUT_FILE, "> $c.txt" ) or die "Can't open $c.txt : $!";

for my $a_key ( sort keys %A_Hash ) {
   $a_key =~ s/\s+$//;
   my $a_line = $A_Hash{$a_key};
   print OUT_FILE $a_line . "\n";
}

  # Compare OBL and REPOOBL. Only write extra REPOOBL lines which are not in OBL into BOND file
  for my $b_key ( sort keys %B_Hash ) {
     $b_key =~ s/\s+$//;
     
     if ( ! exists $A_Hash{$b_key} ) {
      my $b_line = $B_Hash{$b_key};
      print OUT_FILE $b_line . "\n";
     } else {
      print "$B_Hash{$b_key} is the already writen into c.txt using a.txt, hence skipping\n";
     }
  }

close OUT_FILE;

$ 
$ cat a.txt
x001;frtb70;xyz;109
x001;frvt65;sec;239
x003;wqax34;jul;659
x004;yhud43;yhn;760
$ 
$ cat b.txt
x001;abcd80;xyz;193
x001;crrp28;xse;456
x002;lmno10;xyz;784
x002;jfds65;jfd;739
x002;juop88;jup;879
x003;yulo90;rem;542
x003;kihl98;dnt;312
x004;urel25;ewb;342
$ 
$ 
$ perl -F";" -lane 'if ($ARGV eq "a.txt") { push @{$x{$F[0]}},$_ }
                    else { push @{$y{$F[0]}},$_ if not defined $x{$F[0]} }
                    END {
                      @x {keys %y} = values %y;
                      foreach $k (sort keys %x) { print foreach (@{$x{$k}}) }
                    }' a.txt b.txt
x001;frtb70;xyz;109
x001;frvt65;sec;239
x002;lmno10;xyz;784
x002;jfds65;jfd;739
x002;juop88;jup;879
x003;wqax34;jul;659
x004;yhud43;yhn;760
$ 
$

perl -lane '$hash{@F[0]} = $_; END { foreach (sort keys %hash) {print $hash{$_}}}' b.txt a.txt > c.txt

#!/usr/bin/perl
#

use strict;

# vars we need
my $file_a = "a.txt";
my $file_b = "b.txt";
my $file_c = "c.txt";
my %HASH;
my @FILEA;
my @FILEB;
my @UNIQUE;

# open a.txt and b.txt in read mode and c.txt in append mode
open(FILEA, "<$file_a") or die "Unable to open $file_a.\n";
open(FILEB, "<$file_b") or die "Unable to open $file_b.\n";
open(FILEC, ">>$file_c") or die "Unable to write to $file_c.\n";

# store a.txt and b.txt into arrays
@FILEA = <FILEA>;
@FILEB = <FILEB>;

# write the contents of a.txt to c.txt
foreach(@FILEA) {
    print FILEC $_;
}

# map the contents of a.txt to a hash
%HASH = map{$_ => 1} @FILEA;

# use grep function to parse out lines that exist
# in both a.txt and b.txt
@UNIQUE = grep(! defined $HASH{$_}, @FILEB);

# write the results to c.txt
foreach(@UNIQUE) {
    print FILEC $_;
}

# close files
close(FILEA);
close(FILEB);
close(FILEC);

# done
exit(0);

@UNIQUE = grep(! defined $HASH{$_}, @FILEB);

input file: a.txt
------------------
x001;frtb70;xyz;109
x001;frvt65;sec;239
m003;wqax34;jul;659
y004;yhud43;yhn;760


input file: b.txt
------------------
x001;abcd80;xyz;193
x001;crrp28;xse;456
p002;lmno10;xyz;784
p002;jfds65;jfd;739
p002;juop88;jup;879
m003;yulo90;rem;542
m003;kihl98;dnt;312
y004;urel25;ewb;342


expected output file: c.txt
---------------------------
x001;frtb70;xyz;109
x001;frvt65;sec;239
p002;lmno10;xyz;784
p002;jfds65;jfd;739
p002;juop88;jup;879
m003;wqax34;jul;659
y004;yhud43;yhn;760