-i input filename (instead of having it hard-coded)
-s output .stat file (to a certain location)
-o output .csv file (to a certain location)

##</code><code>##

# This program parses a error_log for necessary information and outputs a CSV file with the highest busy value for each 5 minute interval.  
# The program also outputs a STAT file with the last 5 minute interval of the CSV.

use strict;
use warnings;

# Ignore theses values
my %ignorables = map { $_ => 1 } qw([notice mpmstats: rdy bsy rd wr ka log dns cls bsy: in);  

# Open the error log - Change the name of the file as needed.
open my $error_fh, '<', 'iset_error_log';   

# Subroutine to pull the line containing AP22,SM22, and Apache stats
sub findLines {
	my($item,@result)=("");
	
	# Iterates over the lines in the file, putting each into $_ 
	while (<$error_fh>) {      
		
		# Select only those fields that have the word 'notice'
		if (/\[notice/) {          
			
			# Place those lines with the word 'rdy' on the next line
			if (/\brdy\b/){
				push @result,"$item\n";
				$item="";
				
			}
			else {
				$item.=",";
			}
			
			# Split the line into fields, separated by spaces, skip the %ignorables         
			my @line = grep { not defined $ignorables{$_} } split /\s+/;    
			
			# More cleanup         
			s/|^\[|notice|[]]//g for @line; # remove unnecessary elements from the array
			
			# Output the line.  
			@line = join(",", @line);          
			s/,,/,/g for @line;
			map $item.=$_, @line;
			}
		} 
		@result
	}  
	
# Place the subroutine contents into an array
my @array = &findLines;
my $line;

# Create an subroutine to place the contents of AP22, SM22, and Apache in the correct order
sub Program{
	my @return = ();
	chomp @array;

	my ($dow,$mon,$day,$time,$year,$rdy,$bsy,$rd,$wr,$ka,$log,$dns,$cls,$dow2,$mon2,$day2,$time2,$year2,$val1,$mod1,$val2,$mod2,$val3,$mod3,$ap22,$sm22,$apache);
	foreach $line (@array){
	($dow,$mon,$day,$time,$year,$rdy,$bsy,$rd,$wr,$ka,$log,$dns,$cls,$dow2,$mon2,$day2,$time2,$year2,$val1,$mod1,$val2,$mod2,$val3,$mod3) = ((split /[,]/, $line),("")x24); 
	$line = "$dow,$mon,$day,$time,$year,$rdy,$bsy,$rd,$wr,$ka,$log,$dns,$cls";
	
	# For lines with no variables
	if ($mod1 eq ""){
		$line = $line.","."0".","."0".","."0";
	}
	
	# For lines with only SM22
	if ($mod1 eq "mod_sm22.cpp" && $mod2 eq ""){
		$line = $line.",".$val1.","."0".","."0";
	}
	
	# For lines with only AP22
	if ($mod1 eq "mod_was_ap22_http.c" && $mod2 eq "" && $mod3 eq ""){
		$line = $line.",".$val1.","."0".","."0";
	}
	
	# For lines with AP22-SM22-Apache
	if ($mod1 eq "mod_was_ap22_http.c" && $mod2 eq "mod_sm22.cpp" && $mod3 eq "ApacheModule.cpp"){
		$line = $line.",".$val1.",".$val2.",".$val3;
	}
	
	# For lines with SM22-AP22-Apache
	if ($mod1 eq "mod_sm22.cpp" && $mod2 eq "mod_was_ap22_http.c" && $mod3 eq "ApacheModule.cpp"){
		$line = $line.",".$val2.",".$val1.",".$val3;
	}

	# For lines with AP22-SM22
	if ($mod1 eq "mod_was_ap22_http.c" && $mod2 eq "mod_sm22.cpp" && $mod3 eq ""){
		$line = $line.",".$val1.",".$val2.","."0";
	}
	
	# For lines with SM22-AP22
	if ($mod1 eq "mod_sm22.cpp" && $mod2 eq "mod_was_ap22_http.c" && $mod3 eq ""){
		$line = $line.",".$val2.",".$val1.","."0";
	}

	# For lines with SM22-Apache
	if ($mod1 eq "mod_sm22.cpp" && $mod2 eq "ApacheModule.cpp" && $mod3 eq ""){
		$line = $line.","."0".",".$val2.",".$val2;
	}
	
	# For lines with AP22-Apache
	if ($mod1 eq "mod_was_ap22_http.c" && $mod2 eq "ApacheModule.cpp" && $mod3 eq ""){
		$line = $line.",".$val1.","."0".",".$val2;
	}
	
	# Push the array out of the subroutine
	($dow,$mon,$day,$time,$year,$rdy,$bsy,$rd,$wr,$ka,$log,$dns,$cls,$ap22,$sm22,$apache) = ((split/[,]/, $line),("")x16);
	push @return, ("$line\n");
	}
	return @return;
}

# Initialize the hashes
my %interval; 
my %month; @month{qw/ jan feb mar apr may jun jul aug sep oct nov dec /} = '01' .. '12';  

# Put the contents of the subroutine into an array
my @finalArray = &Program;

# Delete the first line of the array
$finalArray[0] = "";

# Create a new array without the first line
my @lastArray = @finalArray;

# Initialize CSV file and STAT file and print the header for the CSV file
open my $fh, ">", 'log_5min.csv' or die $!;
print $fh "Time Interval,rdy,bsy,rd,wr,ka,log,dns,cls,ap22,sm22,apache\n";
open my $FILE, ">", 'last_5min.stat' or die $!;

# Select only those lines with the highest busy count in each 5 minute interval
my @maxima;  
for my $record (@lastArray) {    
	my @fields = $record =~ /([^,\s]+)/g;   
	next unless @fields;    
	my @range = @fields[1..4];
	$range[2] =~ s|(\d+):\d\d$|5*int($1/5)|e;  
	my $range = join ' ', @range;   
	my $value = $fields[5];  
	my ($dow, $mon, $day, $time, $year, $rdy, $by, $rd, $wr, $ka, $log, $dns, $cls, $ap22, $sm22, $apache) = split /[,]/, $record;
	my $record2 = "$range,$rdy,$by,$rd,$wr,$ka,$log,$dns,$cls,$ap22,$sm22,$apache";
	if (@maxima == 0 or $range ne $maxima[-1][0]) {     
		push @maxima, [$range, $value, $record2];   
	}   
	else {     
		@{$maxima[-1]}[1,2] = ($value, $record2) if $maxima[-1][1] > $value;   
	} 
}  

# Print the contents to the CSV file
print $fh $_->[2] for @maxima; 

# Print the last line to the STAT file
my $string = ();
$string = $_->[2] for $maxima[-1];
my ($timeStamp, $rdy, $by, $rd, $wr, $ka, $log, $dns, $cls, $ap22, $sm22, $apache) = split /[,]/, $string; 
print $FILE "<ED>$by</ED>\n<ECO>Max Busy</ECO>\n<ECE></ECE>";