Shell Programming and Scripting

12658699	ST5	XX2720	0	1	0	1					
53039541	ST5	XX2720	1	0	1.5	1

53039541	ST5	X23	0	1	0	1					
1267456	ST1	X23	1	0	1.4	1

12658699	ST5	XX2720	0	1	0	1	X23	0	0	0	0
53039541	ST5	XX2720	1	0	1.5	1	X23	0	1	0	1
1267456	ST1	XX2720	0	0	0	0	X23	1	0	1.4	1

join  -a1 -a2  -t$'\t'   -1 1,2 -2 1,2 file1 file2
join: invalid field number: `1,2'

awk -F"\t" 'FNR==NR{A[$1]=$0;next} ($1 in A){Q=$1;$1="";gsub(/^[[:space:]]+/,X,$0);print A[Q] OFS $0;delete A[Q];next} !($1 in A){$3="XX2720" OFS 0 OFS 0 OFS 0 OFS 0 OFS "X23";print $0} END{for(i in A){gsub(/[[:space:]]+$/,X,A[i]);print A[i] OFS "X23" OFS 0 OFS 0 OFS 0 OFS 0}}' OFS="\t" file1 file2

53039541 ST5    XX2720  1       0       1.5     1       X23     0       1       0       1
1267456  ST1    XX2720  0       0       0       0       X23     1       0       1.4     1
12658699 ST5    XX2720  0       1       0       1       X23     0       0       0       0

 awk -F"\t" 'FNR==NR{
                        A[$1]=$0;
                        next
                   }
                        ($1 in A){
                                        Q=$1;
                                        $1="";
                                        gsub(/^[[:space:]]+/,X,$0);
                                        print A[Q] OFS $0;
                                        delete A[Q];
                                        next
                                 }
                        !($1 in A){
                                        $3="XX2720" OFS 0 OFS 0 OFS 0 OFS 0 OFS "X23";
                                        print $0
                                  }
            END    {
                         for(i in A){
                                        gsub(/[[:space:]]+$/,X,A[i]);
                                        print A[i] OFS "X23" OFS 0 OFS 0 OFS 0 OFS 0
                                    }
                   }
           ' OFS="\t" file1 file2

#!/usr/bin/perl
#
use strict;
use warnings;

# two files must be given at command line
my $first_file = shift or die;
my $second_file = shift or die;

my %data;
my $f;

# process lines from first file
open $f, "<", $first_file or die "$!\n";
while(<$f>) {
    # split line into fields
    my @fields = split;
    # create a key based on first two fields separated by tab
    my $key = join "\t", @fields[0..1];
    # add to data structure and append a list as place holder
    # for second file data
    $data{$key} = [@fields[2..$#fields], ("X23", 0, 0, 0, 0)];
}
close $f;

# process all lines from second file
open $f, "<", $second_file or die "$!\n";
while(<$f>) {
    my @fields = split;
    my $key = join "\t", @fields[0..1];
    # the same key exist in first and second file
    # remove the place holder data
    if(exists $data{$key}){
        $data{$key} = [@{$data{$key}}[0..4], @fields[2..$#fields]];
    # key only exist in second file. Add padding in front.
    }else{
        $data{$key} = [("XX2720", 0, 0, 0, 0), @fields[2..$#fields]]
    }
}
close $f;

for my $k (keys %data) {
    print join "\t", ($k, @{$data{$k}});
    print "\n";
}

awk '
  BEGIN {
    OFS="\t"
  }
  FNR==1{
    X[++c]=$3                             # save the third fied; X[1] of the first file X[2] of the second one.
  }
  {
    $1=$1                                 # Discard last 5 trailing fields because FS is default
    i=$1 OFS $2                           # set i to the first two fields, separated by OFS
  } 
  NR==FNR {                               # process first file
    A[i]=$0                               # Put record from first file into array A with first two fields as index
    next
  }
                                          # process second file
  i in A {                                # if the record exist in A, print joined record
    print A[i],$3,$4,$5,$6,$7
    delete A[i]                           # delete record since index was matched
    next
  }
  {                                       # if the record does not exist in A
    print i,X[1],0,0,0,0,$3,$4,$5,$6,$7   # print it with the remaing fields zeroed and the saved 3rd field of file 1
  } 
  END {
    for(i in A)                           # For the remaining records in file 1 that were not matched
      print A[i],X[2],0,0,0,0             # print them with the remaing fields zeroed and the saved 3rd field of file 2
  }
' file1 file2                             # process file1 first and then file 2