# No.50 Perl Sample (code key - 78)
# Programs: compare words in two files （複数ファイル間の単語の出現頻度を比べる）
# Tomonori Nagano <tnagano@gc.cuny.edu>
# Last Update: January 18, 2008
#
# This file is encoded in Unicode (UTF-8). If you see gibberish characters, 
# please re-encode the file in utf-8. 
# 

my @files = @ARGV ;

for ($i=0; $i<=$#files; $i++){
	open (INFILE1,$files[$i]) or die "cannot open $files[$i]: $!" ;
		while(<INFILE1>){
		chomp ;
		tr/A-Z/a-z/ ;					# normalize to lower case
		s/([^\- a-zA-Z0-9])/ \1 /g ;	# a negative definition of punctuation
		my @words = split ;
		foreach (@words) {
			$nToken[$i]++ ;
			${$seen[$i]}{$_}++ ;
			$seen{$_}++ ;
		}
	}
}

for ($i=0; $i<=$#files;$i++){
	print "num of words in the".$i."st/th file: $nToken[$i]\n" ;
}


print "ID\tWord\t" ;
for (my $i=0; $i<=$#files; $i++) {
	my $fNum = $i+1 ;
	print $fNum."th file\t" ;
}

print "\n" ;
print "----------------------------------------------------------------------\n" ;
my $j = 1 ;
foreach my $key (sort keys %seen) {
	print "$j\t$key\t" ;
	for (my $i=0; $i<=$#files; $i++ ){
		if (!defined ${$seen[$i]}{$key}) {
			print "0\t" ;
		}
		else {
			print "${$seen[$i]}{$key}\t" ;
		}
	}
	print "\n" ;
	$j++ ;
}