> -----Original Message-----
> From: news [mailto:n...@ger.gmane.org] On Behalf Of Richard Loveland
> Sent: Friday, May 08, 2009 11:59
> To: beginners@perl.org
> Subject: Re: Perl code for comparing two files
>
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> Mr. Adhikary,
>
> The following will take any number of files as arguments, in
> the format
> you described (I even tested it! :-)). It goes through each line of
> those files, stuffing (the relevant part of) each line in a
> 'seen' hash
> (more on that, and other, hash techniques here if you're interested:
> http://www.perl.com/pub/a/2006/11/02/all-about-hashes.html).
>
> The code below does not keep track of line numbers as you
> requested, but
> I think the hash technique used here could help you as you approach a
> solution to your particular problem.
>
>
> #!/usr/bin/perl
>
> use strict;
> use warnings;
> use File::Slurp; # This is where 'read_file' lives
>
> my %seen;
>
> for my $arg ( @ARGV ) {
> my @lines = read_file( $arg );
> for my $line ( @lines ) {
> chomp $line;
> my @elems = split / /, $line;
> my $value = $elems[1];
> $seen{$value}++;
> }
> }
>
> for my $k ( keys %seen ) {
> print $k, "\n" if $seen{$k} > 1;
> }
>
This is similar to above, but no File::Slurp and uses an hash
combined with an array with [0] being the count of seen items, [> zero]
is line number and index is the file it was from. I have given you a
Data::Dumper. I ran with the fieles you provided.
#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;
my %seen;
my $MyLineNbr = 1;
my %MFN = ();
my $MyFilenames = \%MFN;
my $MyFileCnt = 1;
my $MyCurrFile = q[];
while ( <> ) {
if ( $ARGV ne $MyCurrFile ) {
printf "Filename: %s (%d)\n", $ARGV, $MyFileCnt;
$MyCurrFile = $ARGV;
$MyFilenames->{$MyCurrFile} = $MyFileCnt++;
$MyLineNbr = 0;
}
chomp;
$MyLineNbr++;
next if ( /^\s*$/ );
my @elems = split (/ /, $_);
my $value = $elems[1];
$seen{$value}[0]++;
$seen{$value}[$MyFilenames->{$MyCurrFile}] = $MyLineNbr;
}
print Dumper(\%seen);
>
> Regards,
> Rich Loveland
>
>
> Anirban Adhikary wrote:
> > Hi List
> > I am writing a perl code which will takes 2 more files as
> argument. Then It
> > will check the the values of each line of a file with
> respect with another
> > file. If some value matches then it will write the value
> along with line
> > number to another ( say outputfile) file.
> >
> > The source files are as follow
> >
> > Contents of abc.txt
> > 1 2325278241,P0
> > 2 2296250723,MH
> > 3 2296250724,MH
> > 4 2325277178,P0
> > 5 7067023316,WL
> > 6 7067023329,WL
> > 7 2296250759,MH
> > 8 7067023453,WL
> > 9 7067023455,WL
> > 10 5000055413,EA05
> > #######################################################
> > Contents of xyz.txt
> > 1 7067023453,WL
> > 2 31-DEC-27,2O,7038590671
> > 3 31-DEC-27,2O,7038596464
> > 4 31-DEC-27,2O,7038596482
> > 5 2296250724,MH
> > 6 31-DEC-27,2O,7038597632
> > 7 31-DEC-27,2O,7038589511
> > 8 31-DEC-11,2O,7038590671
> > 9 7067023455,WL
> > 10 31-DEC-27,2O,7038555744
> > ###############################################################
> > Contents of pqr.txt
> > 1 2325278241,P0
> > 2 7067023316,WL
> > 3 7067023455,WL
> > 4 2296250724,MH
> >
> >
> >
> >
> > ########################################################
> >
> > For this requirement I have written the following code
> which works fine for
> > 2 input files
> >
> > use strict;
> > use warnings;
> >
> > use Benchmark;
> >
> > if(@ARGV < 2) {
> > print "Please enter atleast two or more .orig file names \n";
> > exit 0;
> > }
> > my @file_names = @ARGV;
> > chomp(@file_names);
> > my @files_to_process;
> >
> > for(@file_names) {
> > if( -s $_){
> > print "File $_ exists\n";
> > push(@files_to_process,$_);
> > }
> > elsif( -e $_) {
> > print "File $_ exists but it has zero byte size\n";
> > }
> > else {
> > print "File $_ does not exists \n";
> > }
> > }
> >
> > my $count = @files_to_process;
> > if( $count < 2 ) {
> > print "Atleast 2 .orig files are required to continue this
> > program\n";
> > exit 0;
> > }
> >
> > my $output_file = "outputfile";
> > my $value = 0;
> > my $start_time = new Benchmark;
> >
> >
> > if( $count >= 2 ) {
> > while ($count) {
> > my
> ($files_after_processing_pointer,$return_val) =
> > create_itermediate_file (\...@files_to_process,$value);
> > my @files_after_processing =
> > @$files_after_processing_pointer;
> > $count = @files_after_processing;
> > $value = $return_val;
> > @files_to_process = @files_after_processing;
> >
> > }
> >
> > my $end_time = new Benchmark;
> > my $difference = timediff($end_time, $start_time);
> > print "It took ", timestr($difference), " to execute
> the program\n";
> >
> > }
> >
> >
> >
> >
> > sub create_itermediate_file {
> > my $file_pointer = $_[0];
> > my $counter = $_[1];
> > my @file_content = @$file_pointer;
> >
> > if($counter == 0) {
> > my($first_file,$second_file) =
> splice
> > (@file_content, 0, 2);
> > open my $orig_first, "<", $first_file
> > or die "could not open
> $first_file: $!";
> > open my $orig_second, "<", $second_file
> > or die "could not open
> $second_file:
> > $!";
> > open my $output_fh, ">", $output_file
> > or die "could not open
> $output_file:
> > $!";
> >
> > my %content_first;
> > while (my $line =
> <$orig_first>) {
> > chomp $line;
> > if ($line) {
> >
> > my($line_num,$value) = split(" ",$line);
> >
> > $content_first{$value} = $line_num;
> > }
> > }
> >
> > my %content_second;
> > while (my $line =
> <$orig_second>) {
> > chomp $line;
> > if ($line) {
> >
> > my($line_num,$value) = split(" ",$line);
> >
> > $content_second{$value} = $line_num;
> > }
> > }
> >
> > foreach my $key (sort keys
> > %content_second) {
> > if (exists
> > $content_first{$key} ) {
> >
> print $output_fh
> > "$content_second{$key} $key" ,"\n";
> > }
> > }
> > $counter += 1;
> > return (\...@file_content,$counter);
> > }
> > if ($counter != 0) {
> > my $file_pointer = $_[0];
> > my $counter = $_[1];
> > my @file_content_mod = @$file_pointer;
> > my($file_to_process) =
> shift(@file_content_mod);
> >
> >
> > open my $orig_file, "<",
> $file_to_process
> > or die "could not open
> $file_to_process:
> > $!";
> > open my $output_fh, "<", $output_file
> > or die "could not open
> $output_file:
> > $!";
> > open my $output_fh_mod, ">",
> $output_file."_mod"
> > or die "could not open",
> > $output_file."_mod : $!";
> >
> > my %content_file_to_process;
> > while (my $line =<$orig_file>) {
> > chomp $line;
> > if ($line) {
> >
> > my($line_num,$value) = split(" ",$line);
> >
> > $content_file_to_process{$value} = $line_num;
> > }
> > }
> >
> > my %content_output_file;
> > while (my $line =<$output_fh>) {
> > chomp $line;
> > if ($line) {
> >
> > my($line_num,$value) = split(" ",$line);
> >
> > $content_output_file{$value} = $line_num;
> > }
> > }
> >
> > foreach my $key (sort keys
> > %content_output_file) {
> > if (exists
> > $content_file_to_process{$key} ) {
> > print
> > $output_fh_mod "$content_file_to_process{$key} $key" ,"\n";
> > }
> > }
> > $counter += 1;
> > return (\...@file_content_mod,$counter);
> >
> > }
> > }
> >
> >
> > But when I am entering 3 file names as argument this is not
> working.It is
> > working properly though I am using another file
> $output_file_mod> It was
> > only written the similar lines between two compared files
> where it should be
> > written the common lines of two compared files as well as
> lines which were
> > not present in the last file but present in the
> $output_file. I was trying
> > to use open my $output_fh, "+>>", $output_file or die
> "could not open
> > $output_file: $!"; syntax but it was not working.)
> >
> > Thanks & Regards in advance
> > Anirban Adhikary.
> >
>
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.6 (GNU/Linux)
> Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
>
> iD8DBQFKBHLI4EG8v4hpG/ERAvcXAJ9YH9vEnpcgtvPPAqlJlpy9N5lXZQCfQlJM
> zmPRzzSRHCzpi/EwAzDZM8E=
> =8YbD
> -----END PGP SIGNATURE-----
>
>
> --
> To unsubscribe, e-mail: beginners-unsubscr...@perl.org
> For additional commands, e-mail: beginners-h...@perl.org
> http://learn.perl.org/
>
>
>
--
To unsubscribe, e-mail: beginners-unsubscr...@perl.org
For additional commands, e-mail: beginners-h...@perl.org
http://learn.perl.org/
