#!/usr/local/bin/perl -w use strict; =head1 Black Box Model Given the data... 127.0.0.1 - - [15/Jun/2003:13:05:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:05:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:06:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:08:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:10:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:15:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:18:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:20:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:25:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:35:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:50:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:04:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:04:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:10:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:20:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 ...with 15 minute interval (period size of I<15>, unit of I), output is... Time Total pages Avg pages Min pages Max pages ------------------------------------------------------------------- 15/Jun/2003:13:05:00 6 1.2 1 2 15/Jun/2003:13:20:00 2 1.0 1 1 15/Jun/2003:13:35:00 1 1.0 1 1 15/Jun/2003:13:50:00 3 1.3 1 2 15/Jun/2003:14:20:00 1 1.0 1 1 =cut use Time::CTime; use Time::ParseDate; use constant SEC_PER_MINUTE => 60; use constant MIN_PER_HOUR => 60; use constant SEC_PER_HOUR => SEC_PER_MINUTE * MIN_PER_HOUR; # options my ($period_size , $unit , $log) = (15 , 'minute' , 'access_log_modified'); # skip unwanted files my $filter = sub { my $re = qr/ [.] (?: js | css | gif ) $/x; return ($_[0] =~ m/$re/) ? 1 : 0; }; my $period = period_in_seconds($period_size , $unit); show_stat( collect_count($log , $period , $filter) ); =head1 C Given a hash reference of array references with keys as the time (in seconds), prints the time in human parsable time, and basic statistics for each array reference. =cut sub show_stat { my %parsed = %{ +shift }; my @keys = sort { $a <=> $b } keys %parsed; printf "%-20s %11s %10s %9s %9s\n%s\n" , 'Time' , 'Total pages' , 'Avg pages' , 'Min pages' , 'Max pages' , '-' x (20 + 11 + 10 + 9 + 9 + (2 * 4)); foreach my $k (@keys) { printf "%20s %11d %9.1f %9d %9d\n" , strftime( "%d/%b/%Y:%H:%M:%S" , localtime $k) , @{ basic_stat( $parsed{$k} ) }; } } =head1 C<$hash_of_array_ref = collect_count($file_name , $period , $code_ref)> Given a file name and time period (in seconds), returns hash reference with time in seconds as keys and array reference containing hits for each time value in the given period. Optional third parameter, a code reference (that takes file name and returns true), will be used to filter out the unwanted files if given. =cut sub collect_count { my ($log , $period , $filter) = @_; open(LOGFILE, '<' , $log) || die "Cannot read from $log: $!\n"; my ($start , $old , %count); $filter = sub { 0; } unless $filter; while ( ) { my ($time , $file) = (split / /)[3,6] or next; next if $filter->($file); next if $time !~ m/ \[ (.+?) \] /x; $time = parsedate($1); $start = $time unless defined $start; $old = (0 == ($time - $start) % $period) ? $time : $old; push @{ $count{$old}->{$time} }, 1; } close(LOGFILE) || die "Could not close $log: $!\n"; return \%count; } =head1 C<$array_ref = basic_stat($hash_of_array_ref)> Given a hash reference of array references, returns an array reference composed of size, average, minimum, maximum based on the sizes of each array reference passed. It may return C values if passed hash is empty. =cut sub basic_stat { my $collection = shift; my @raw = map scalar @{ $_ } , values %{$collection}; my ($size , $avg , $min , $max) = (scalar @raw); return [ $size , $avg , $min , $max ] unless $size; $avg = sub { my $sum; $sum += $_ foreach @raw; return $sum; }->() / $size; $min = $max = $raw[0]; foreach ( @raw ) { $min = $_ if $min > $_; $max = $_ if $max < $_; } return [ $size , $avg , $min , $max ]; } =head1 C<$period = period_in_seconds($period_size , $unit)> Given period size and time unit, basically matching... C ...returns the period in seconds. If period size is not I, returns 1. =cut sub period_in_seconds { my ($size , $unit) = @_; return 1 unless $size; $size = abs($size); my $multiplier = $unit =~ m/^ hour | hr /ix ? SEC_PER_HOUR : $unit =~ m/^min/i ? SEC_PER_MINUTE : 1; return $size * $multiplier; } __DATA__ 127.0.0.1 - - [15/Jun/2003:13:05:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:05:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:06:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:08:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:10:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:15:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:18:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:20:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:25:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:35:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:13:50:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:04:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:04:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:10:00] -0100 "GET /xxxx HTTP/1.1" 200 34906 127.0.0.1 - - [15/Jun/2003:14:20:00] -0100 "GET /xxxx HTTP/1.1" 200 34906