Perl: Compare Two CSV Files and Print out matches (modifying this code) - perl

Question

I am very new at perl and had discovered the solution at:
Perl: Compare Two CSV Files and Print out differences
I have gone through dozens of other solutions and this comes closest, except that instead of finding the differences between 2 CSV files, I want to find where the second CSV file matches the first one in column and row. How could I modify the following script to find the matches in column/row instead of the differences. I am hoping to dissect this code and learn arrays from there, but wanted to find out the solution to this application. Much thanks.
use strict;
my #arr1;
my #arr2;
my $a;
open(FIL,"a.txt") or die("$!");
while (<FIL>)
{chomp; $a=$_; $a =~ s/[\t;, ]*//g; push #arr1, $a if ($a ne '');};
close(FIL);
open(FIL,"b.txt") or die("$!");
while (<FIL>)
{chomp; $a=$_; $a =~ s/[\t;, ]*//g; push #arr2, $a if ($a ne '');};
close(FIL);
my %arr1hash;
my %arr2hash;
my #diffarr;
foreach(#arr1) {$arr1hash{$_} = 1; }
foreach(#arr2) {$arr2hash{$_} = 1; }
foreach $a(#arr1)
{
if (not defined($arr2hash{$a}))
{
push #diffarr, $a;
}
}
foreach $a(#arr2)
{
if (not defined($arr1hash{$a}))
{
push #diffarr, $a;
}
}
print "Diff:\n";
foreach $a(#diffarr)
{
print "$a\n";
}
# You can print to a file instead, by: print FIL "$a\n";
ok, I realize that this was more what I was looking for:
use strict;
use warnings;
use feature qw(say);
use autodie;
use constant {
FILE_1 => "file1.txt",
FILE_2 => "file2.txt",
};
#
# Load Hash #1 with value from File #1
#
my %hash1;
open my $file1_fh, "<", FILE_1;
while ( my $value = <$file1_fh> ) {
chomp $value;
$hash1{$value} = 1;
}
close $file1_fh;
#
# Load Hash #2 with value from File #2
#
my %hash2;
open my $file2_fh, "<", FILE_2;
while ( my $value = <$file2_fh> ) {
chomp $value;
$hash2{$value} = 1;
}
close $file2_fh;
Now I want to search file2's hash to check if there are ANY matches from file1's hash. That is where I am stuck
With new code suggestion, code now looks like this
#!/usr/bin/env perl
use strict;
use warnings;
use feature qw(say);
use autodie;
use constant {
FILE_1 => "masterlist.csv",
FILE_2 => "pastebin.csv",
};
#
# Load Hash #1 with value from File #1
#
my %hash1;
open my $file1_fh, "<", FILE_1;
while ( my $value = <$file1_fh> ) {
chomp $value;
$hash1{$value} = 1;
}
close $file1_fh;
my %hash2;
open my $file2_fh, "<", FILE_2;
while ( my $value = <$file2_fh> ) {
chomp $value;
if ( $hash1{$value} ) {
print "Match found $value\n";
$hash2{$value}++;
}
}
close $file2_fh;
print "Matches found:\n";
foreach my $key ( keys %hash2 ) {
print "$key found $hash2{$key} times\n";
}
I updated one part with split() and it seems to work, but have to test more to confirm if it fits the solution I'm looking for or I have more work to do one it
#
# Load Hash #1 with value from File #1
#
my %hash1;
open my $file1_fh, "<", FILE_1;
while ( my $value = <$file1_fh> ) {
chomp $value;
$hash1{$value} = ( %hash1, (split(/,/, $_))[1,2] );
}
close $file1_fh;

Answer 1

So, with your code there - you've read in 'file1' to a hash.
Why not instead of reading file 2 into a hash, do instead:
my %hash2;
open my $file2_fh, "<", FILE_2;
while ( my $value = <$file2_fh> ) {
chomp $value;
if ( $hash1{$value} ) {
print "Match found $value\n";
$hash2{$value}++;
}
}
close $file2_fh;
print "Matches found:\n";
foreach my $key ( keys %hash2 ) {
print "$key found $hash2{$key} times\n";
}

Answer 2

I think this code identifies every place that a data field in file A matches a data field in file B (at least it does on my limited test data):
use strict;
use warnings;
my #arr1;
my #arr2;
# a.txt -> #arr1
my $file_a_name = "poster_a.txt";
open(FIL,$file_a_name) or die("$!");
my $a_line_counter = 0;
while (my $a_line = <FIL>)
{
$a_line_counter = $a_line_counter + 1;
chomp($a_line);
my #fields = (split /,/,$a_line);
my $num_fields = scalar(#fields);
s{^\s+|\s+$}{}g foreach #fields;
push #arr1, \#fields if ( $num_fields ne 0);
};;
close(FIL);
my $file_b_name = "poster_b.txt";
open(FIL,$file_b_name) or die("$!");
while (my $b_line = <FIL>)
{
chomp($b_line);
my #fields = (split /,/,$b_line);
my $num_fields = scalar(#fields);
s{^\s+|\s+$}{}g foreach #fields;
push #arr2, \#fields if ( $num_fields ne 0)
};
close(FIL);
# b.txt -> #arr2
#print "\n",#arr2, "\n";
my #match_array;
my $file_a_line_ctr = 1;
foreach my $file_a_line_fields (#arr1)
{
my $file_a_column_ctr = 1;
foreach my $file_a_line_field (#{$file_a_line_fields})
{
my $file_b_line_ctr = 1;
foreach my $file_b_line_fields(#arr2)
{
my $file_b_column_ctr = 1;
foreach my $file_b_field (#{$file_b_line_fields})
{
if ( $file_b_field eq $file_a_line_field )
{
my $match_info =
"$file_a_name line $file_a_line_ctr column $file_a_column_ctr" .
" (${file_a_line_field}) matches: " .
"$file_b_name line $file_b_line_ctr column $file_b_column_ctr ";
push(#match_array, $match_info);
print "$match_info \n";
}
$file_b_column_ctr = $file_b_column_ctr + 1;
}
$file_b_line_ctr = $file_b_line_ctr + 1;
}
$file_a_column_ctr = $file_a_column_ctr + 1;
}
$file_a_line_ctr = $file_a_line_ctr + 1;
}
print "there were ", scalar(#match_array)," matches\n";