#!/bin/perl                                                                                                        
                                                                                                                   
my @csv2 = ();                                                                                                     
open CSV2, "<csv2" or die;                                                                                         
@csv2=<CSV2>;                                                                                                      
close CSV2;                                                                                                        
                                                                                                                   
my %csv2hash = ();                                                                                                 
for (@csv2) {                                                                                                      
  chomp;                                                                                                           
  my ($title) = $_ =~ /^.+?,\s*([^,]+?),/; #/ match the title                                                      
  $csv2hash{$_} = $title;                                                                                          
}                                                                                                                  
                                                                                                                   
open CSV1, "<csv1" or die;                                                                                         
while (<CSV1>) {                                                                                                   
  chomp;                                                                                                           
  my ($title) = $_ =~ /^.+?,\s*([^,]+?),/; #/ match the title                                                      
    my %words;                                                                                                     
    $words{$_}++ for split /\s+/, $title;    #/ get words                                                          
    ## Collect unique words                                                                                        
    my @titlewords = keys(%words);                                                                                 
  my @new;                          #add exception words which shouldn't be matched                                
  foreach my $t (@titlewords){                                                                                     
        push(@new, $t) if $t !~ /^(rare|vol|volume|issue|double|magazine|mag)$/i;                                  
  }                                                                                                                
  @titlewords = @new;                                                                                              
  my $desired = 5;                                                                                                 
  my $matched = 0;                                                                                                 
  foreach my $csv2 (keys %csv2hash) {                                                                              
    my $count = 0;                                                                                                 
    my $value = $csv2hash{$csv2};                                                                                  
    foreach my $word (@titlewords) {                                                                               
            my @matches   = ( $value=~/\b$word\b/ig );                                                             
            my $numIncsv2 = scalar(@matches);                                                                      
            @matches      = ( $title=~/\b$word\b/ig );                                                             
            my $numIncsv1 = scalar(@matches);                                                                      
            ++$count if $value =~ /\b$word\b/i;                                                                    
            if ($count >= $desired || ($numIncsv1 >= $desired && $numIncsv2 >= $desired)) {                        
                $count = $desired+1;                                                                               
                last;                                                                                              
            }                                                                                                      
    }                                                                                                              
    if ($count >= $desired) {                                                                                      
      print "$csv2\n";                                                                                             
      ++$matched;                                                                                                  
    }                                                                                                              
  }                                                                                                                
  print "$_\n\n" if $matched;                                                                                      
}                                                                                                                  
close CSV1;