#! perl -slw
use strict;
use G; ## Expands command line wildcards
use Data::Dumper;
use Digest::MD5 qw[ md5_hex ];

local $/ = ''; ## paragraph mode.

my( $pos, %index ) = 0; ## The first para start at offset 0

while( <> ) {
	## build a HoAoAs, MD5 is the key 
      ## The values are arrays of [ filename, offset ].
	push @{ $index{ md5_hex( $_ ) } }, [ $ARGV, $pos ];
	
	## Getthe next offset
	$pos = tell ARGV;
	
	## Back to 0 if we reached the EOF
	$pos = 0 if eof( ARGV );
}

print Dumper \%index;
__END__
C:\Perl\html>p:359522 *.html *\*.html *\*\*.html
Processed 512 files and 5829 paragraphs into 3293 unique signatures.