#!/local/bin/perl5 -w

#    Copyright (c) 1998 University of Southern California.
#    All rights reserved.                                            
#                                                                   
#    Redistribution and use in source and binary forms are permitted
#    provided that the above copyright notice and this paragraph are
#    duplicated in all such forms and that any documentation, advertising
#    materials, and other materials related to such distribution and use
#    acknowledge that the software was developed by the University of
#    Southern California, Information Sciences Institute.  The name of the
#    University may not be used to endorse or promote products derived from
#    this software without specific prior written permission.
#    
#    THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED
#    WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
#    MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.

#
# Program: hsurlplot.pl <in_file> <out_file> <urls_total>
#

if ( !(defined ($ARGV[0])) || !(-r $ARGV[0]) || !(defined ($ARGV[1]))  || !(defined $ARGV[2]) )
{
    print "\a\nRequires three arguments.\n";
    print "\t1st argument: An inter-arrival-times file reverse sorted by hit count.\n";
    print "\t2nd argument: A GNUPLOT output file.\n";
    print "\t3rd argument: Count of unique URLs.\n";
    exit (0);
}

# Open the input and output files.  Shift the two leading
# args off @ARGV leaving the expression to evaluate.

open (INFILE,"<$ARGV[0]");
shift;
open (PLOTFILE,">$ARGV[0]");
shift;
$urlstotal = $ARGV[0];

# Create a vector of boolean expressions that filter on hit count.
# Create a vector of boolean expressions that filter on standard deviation.

@hitexprs = ();
@stdexprs = ();

$low_hit_limit = 30;

for ($hits = $low_hit_limit;  $hits <= 300;  $hits += 30)
{  push @hitexprs, "\$_[2] >= $hits";  };

for ($std = 8640;  $std <= 86400;  $std += 8640)
{  push @stdexprs, "\$_[5] <= $std";  }

# Create hash of hashes, where keys are boolean expressions
# that are later both applied to each line the input file.

%HoEs = ();

foreach $hitexpr (@hitexprs)
{
    foreach $stdexpr (@stdexprs)
    {  $HoEs{$hitexpr}{$stdexpr} = 0;  }
}

# Iterate across the lines of the input file.  For each line, iterate
# across the outer and inner hashes, making a conjunctive boolean
# expression out of the keys.  Apply that expression to the input line.
# The values associated with the inner hash are the percentage of
# URLs associated with that input line.

$linecount = 0;

LINE: while (<INFILE>)
{
    split;

    foreach $hitselem (keys %HoEs)
    {
	foreach $stdelem (keys %{$HoEs{$hitselem}})
	{
	    if (eval "($hitselem && $stdelem)" )
	    {  $HoEs{$hitselem}{$stdelem} += 100 / $urlstotal;  }
	}
    }

    if (!(++$linecount % 1000)) {  print "$linecount\n";  }

    # When the source file is reverse sorted by hit count, the last
    # line that needs to be processed can be determined.

    last LINE if ($_[2] < $low_hit_limit);
}

# Print the results of the expression applications to each input line
# as a two-dimensional surface suited for GNUPLOT's splot command.

foreach $hitselem (@hitexprs)
{
    $_ = $hitselem;
    split;
    $hprint = $_[2];
    foreach $stdelem (@stdexprs)
    {
	$_ = $stdelem;
	split;
	$_[2] /= 86400;
	print PLOTFILE "$hprint $_[2] $HoEs{$hitselem}{$stdelem}\n";
    }
    print PLOTFILE "\n";
}

close (INFILE);
close (PLOTFILE);

exit(0);