#!/local/bin/perl5

#    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: dailylog.pl <log-file> {<sort-dir>}
#

if ( !defined($ARGV[0]) )
{
    print "\n\aERROR: In dailylog.pl, arguments are incorrect.\n";
    print "Called as:  dailylog.pl <log-file> {<sort-dir>}\n";
    print "   <log-file> -- Name of Squid proxy log file.\n";
    print "   <sort-dir> -- Optional directory for sort() temp files.\n\n";
    exit(1);
}

$log_file = $ARGV[0];

if ( !defined($ARGV[1]) ) { $ARGV[1] = "/tmp"; }
$sort_dir = $ARGV[1];

#
# Get filename prefix from <log-file>.
#

$log_name = $log_file;
$log_name =~ s/.*\///;      # get rid of path parts
$log_name =~ s/\..*//;      # get rid of extension parts

#
# Cut out unneeded fields of log records.
#
# NOTE: GNU version of cut, gcut, is used in place of cut.
#       cut has a line length limit that is sometimes too small.
#       Rediculously long URLs are sometimes specified by buggy
#       browsers.
#

print "gcut -f 1,3,4,5,7 -d ' '   $log_file > $log_file.cut\n";

if (system "gcut -f 1,3,4,5,7 -d ' '   $log_file > $log_file.cut")
{
    print "\n\aIn dailylog.pl unable to cut file: $log_file.\n";
    print "Error: $!.\n\n";
    exit(1);
}

#
# Delete the uncut log file.
#

unlink $log_file;

#
# Sort the cut log file by URL.
#
# NOTE:  The GNU version of the sort() program, gsort(), is used.
#        Due to browser bugs, URL specifications can sometimes be as
#        longs as several thousand characters.  The standard sort()
#        program cannot deal with that, whereas gsort() can.
#

$dst_sort = "$log_file.sorted";
$dst_sort =~ s/\.sanitized-access//i;

print "gsort +4 -o $dst_sort -T $sort_dir $log_file.cut\n";

if (system "gsort +4 -o $dst_sort -T $sort_dir $log_file.cut")
{
    print "\n\aIn dailylog.pl unable to sort file: $log_file.cut\n";
    print "Error: $!.\n\n";
    exit(1);
};

#
# Delete the unsorted cut log file.
#

unlink "$log_file.cut";

# Filter out of the sorted log file those references that would not be
# made if client caches were all operating and all URLs were cacheable.

$dst_filter = $dst_sort;
$dst_filter =~ s/sorted/filtered/;
$dst_drop = $dst_sort;
$dst_drop =~ s/sorted/dropped/;

print "ccachefilter.pl $dst_sort $dst_filter $dst_drop\n";

if (system "ccachefilter.pl $dst_sort $dst_filter $dst_drop")
{
    print "\n\aIn dailylog.pl ccachefilter.pl failed for: $dst_sort.\n";
    exit(1);
}

#
# Build the request matrix file for the filtered, sorted log file.
#

$dst_reqmat = $dst_sort;
$dst_reqmat =~ s/sorted/filtered.reqmat/;

print "reqmat.pl $dst_filter $dst_reqmat $log_name.summary.filtered\n";

if (system "reqmat.pl $dst_filter $dst_reqmat $log_name.summary.filtered")
{
    print "\n\aIn dailylog.pl reqmat.pl failed for: $dst_filter.\n";
    exit(1);
}

#
# Delete the filtered log file.
#

unlink $dst_filter;

#
# Build the request matrix file for the dropped, sorted log file.
#

$dst_reqmat =~ s/filtered/dropped/;

print "reqmat.pl $dst_drop $dst_reqmat $log_name.summary.dropped\n";

if (system "reqmat.pl $dst_drop $dst_reqmat $log_name.summary.dropped")
{
    print "\n\aIn dailylog.pl reqmat.pl failed for: $dst_drop.\n";
    exit(1);
}

#
# Delete the dropped log file and the dropped.reqmat file.
# Keep the summary.dropped file.
#

unlink $dst_reqmat;
unlink $dst_drop;

#
# Build the request matrix file for the non-filtered sorted log file.
#

$dst_reqmat =~ s/.dropped//;

print "reqmat.pl $dst_sort $dst_reqmat $log_name.summary\n";

if (system "reqmat.pl $dst_sort $dst_reqmat $log_name.summary")
{
    print "\n\aIn dailylog.pl reqmat.pl failed for: $dst_sort.\n";
    exit(1);
}

#
# Delete the non-filtered file.
#

unlink $dst_sort;

exit(0);