pratik4891
New User
Nov 18, 2011, 1:58 AM
Post #1 of 1
(226 views)
|
|
Compare two flat file via sorting first
|
Can't Post
|
|
Hello Guys,
This is my first post to this wonderful forum
I am trying to compare two flat file based on third column(file separator is '|')For low volume file its working fine but for huge file its taking large amount of time
So I am trying to sort the data first in two flat file and then trying to compare them
My questions are
1)Will this approach work if not please suggest any
2)I am unable to put the sorted array into file or trying to compare the two arrays
I am sending you both the script .Please let me now how to code it through
Script for comparison
use strict;
use warnings;
use POSIX qw(strftime);
my $stmp = strftime "%Y%m%d_%H%M%S", localtime;
print "$stmp\n";
my $lx_path = '/opt/grpwhse/stage/';
my $file_prv = $ARGV[1];
my $file_prv1 = substr($file_prv,0,index($file_prv,'.'));
my $file_last = $ARGV[0];
my $file_curr = $ARGV[1];
my $delta = '_delta_';
my $file_ext = '.dat';
my ($file1, $file2, $file3) = ($file_last,$lx_path.$file_curr,$file_prv1.$delta.$stmp.$file_ext);
open my $fh1, '<', $file1 or die "Can't open $file1: $!";
open my $fh2, '<', $file2 or die "Can't open $file2: $!";
open my $fh3, '>', $file3 or die "Can't open $file3: $!";
my %save; #Hash of hashes to store records from file1 for comparison with file2
while (<$fh1>){
chomp;
my @rec = split /\|/;
my $key = $rec[2];
$save{$key}->{'data'} = $_; #Save current record in hash
$save{$key}->{'flag'} = 'D';
}
while (<$fh2>){
chomp;
my @rec = split /\|/;
my $key = $rec[2];
#$save{$key}->{'data_2'} = $_;
if (not exists $save{$key}){
$save{$key}->{'data'} = $_;
$save{$key}->{'flag'} = 'I';
}elsif (string_to_compare($_) ne string_to_compare($save{$key}->{'data'})){
$save{$key}->{'data'} = $_;
$save{$key}->{'flag'} = 'U';
}else{
delete $save{$key};
}
}
foreach (sort keys %save){
my $data_flag = string_to_compare($save{$_}->{'data'});
my $data_key = string_to_key($save{$_}->{'data'});
print $fh3 "$data_key|$save{$_}->{'flag'}|$data_flag\n";
}
sub string_to_compare{
my $line = shift;
my ($skip1, $skip2, $key, $remainder) = split /\|/, $line,4;
return $remainder;
}
sub string_to_key{
my $line = shift;
my ($id1, $id2, $key, $remainder) = split /\|/, $line,4;
return "$id1|$id2|$key";
}
Script for sorting
use strict;
use warnings;
open (my $data , '<', $ARGV[0])|| die "could not open $ARGV[0]:\n$!";
my @array=(<$data>);
my @sorted=sort {(split(/\|/,$a))[2]<=>(split(/\|/,$b))[2]} @array;
print @sorted;
I want to use the above sort functionality in the file comparison script
But I am not able to
Please help!!!Thanks a lot for your time!!!!!!!!!
|
MAIN
SEARCH
WHO'S 
LOG 