#!PERL_COMMAND -w
-# $Cambridge: exim/src/src/eximstats.src,v 1.3 2004/12/20 13:12:32 steve Exp $
+# $Cambridge: exim/src/src/eximstats.src,v 1.13 2007/01/31 16:52:12 ph10 Exp $
# Copyright (c) 2001 University of Cambridge.
# See the file NOTICE for conditions of use and distribution.
# Added warnings if required GD::Graph modules are not available or
# insufficient -chart* options are specified.
#
-# 2004-02-20 V1.31 Andrea Balzi
+# 2004-02-20 V1.31 Andrea Balzi
# Only show the Local Sender/Destination links if the tables exist.
#
# 2004-07-05 V1.32 Steve Campbell
# 2004-12-10 V1.34 Steve Campbell
# Eximstats can now parse syslog lines as well as mainlog lines.
#
-# 2004-12-20 V1.35 Andreas Metzler
-# Pie charts by volume were actually generated by count. Fixed.
-
+# 2004-12-20 V1.35 Wouter Verhelst
+# Pie charts by volume were actually generated by count. Fixed.
+#
+# 2005-02-07 V1.36 Gregor Herrmann / Steve Campbell
+# Added average sizes to HTML Top tables.
+#
+# 2005-04-26 V1.37 Frank Heydlauf
+# Added -xls and the ability to specify output files.
+#
+# 2005-04-29 V1.38 Steve Campbell
+# Use FileHandles for outputing results.
+# Allow any combination of xls, txt, and html output.
+# Fixed display of large numbers with -nvr option
+# Fixed merging of reports with empty tables.
+#
+# 2005-05-27 V1.39 Steve Campbell
+# Added the -include_original_destination flag
+# Removed tabs and trailing whitespace.
+#
+# 2005-06-03 V1.40 Steve Campbell
+# Whilst parsing the mainlog(s), store information about
+# the messages in a hash of arrays rather than using
+# individual hashes. This is a bit cleaner and results in
+# dramatic memory savings, albeit at a slight CPU cost.
+#
+# 2005-06-15 V1.41 Steve Campbell
+# Added the -show_rt<list> flag.
+# Added the -show_dt<list> flag.
+#
+# 2005-06-24 V1.42 Steve Campbell
+# Added Histograms for user specified patterns.
+#
+# 2005-06-30 V1.43 Steve Campbell
+# Bug fix for V1.42 with -h0 specified. Spotted by Chris Lear.
+#
+# 2005-07-26 V1.44 Steve Campbell
+# Use a glob alias rather than an array ref in the generated
+# parser. This improves both readability and performance.
+#
+# 2005-09-30 V1.45 Marco Gaiarin / Steve Campbell
+# Collect SpamAssassin and rejection statistics.
+# Don't display local sender or destination tables unless
+# there is data to show.
+# Added average volumes into the top table text output.
+#
+# 2006-02-07 V1.46 Steve Campbell
+# Collect data on the number of addresses (recipients)
+# as well as the number of messages.
+#
+# 2006-05-05 V1.47 Steve Campbell
+# Added 'Message too big' to the list of mail rejection
+# reasons (thanks to Marco Gaiarin).
+#
+# 2006-06-05 V1.48 Steve Campbell
+# Mainlog lines which have GMT offsets and are too short to
+# have a flag are now skipped.
+#
+# 2006-11-10 V1.49 Alain Williams
+# Added the -emptyok flag.
+#
+# 2006-11-16 V1.50 Steve Campbell
+# Fixes for obtaining the IP address from reject messages.
+#
+# 2006-11-27 V1.51 Steve Campbell
+# Another update for obtaining the IP address from reject messages.
+#
+# 2006-11-27 V1.52 Steve Campbell
+# Tally any reject message containing SpamAssassin.
+#
+# 2007-01-31 V1.53 Philip Hazel
+# Allow for [pid] after date in log lines
+#
+#
+#
+# For documentation on the logfile format, see
+# http://www.exim.org/exim-html-4.50/doc/html/spec_48.html#IX2793
=head1 NAME
=head1 SYNOPSIS
- eximstats [Options] mainlog1 mainlog2 ... > report.txt
- eximstats -html [Options] mainlog1 mainlog2 ... > report.html
+ eximstats [Output] [Options] mainlog1 mainlog2 ...
eximstats -merge [Options] report.1.txt report.2.txt ... > weekly_report.txt
-Options:
+=head2 Output:
+
+=over 4
+
+=item B<-txt>
+
+Output the results in plain text to STDOUT.
+
+=item B<-txt>=I<filename>
+
+Output the results in plain text. Filename '-' for STDOUT is accepted.
+
+=item B<-html>
+
+Output the results in HTML to STDOUT.
+
+=item B<-html>=I<filename>
+
+Output the results in HTML. Filename '-' for STDOUT is accepted.
+
+=item B<-xls>
+
+Output the results in Excel compatible Format to STDOUT.
+Requires the Spreadsheet::WriteExcel CPAN module.
+
+=item B<-xls>=I<filename>
+
+Output the results in Excel compatible format. Filename '-' for STDOUT is accepted.
+
+
+=back
+
+=head2 Options:
=over 4
Include remote users in the top source/destination listings.
+=item B<-include_original_destination>
+
+Include the original destination email addresses rather than just
+using the final ones.
+Useful for finding out which of your mailing lists are receiving mail.
+
+=item B<-show_dt>I<list>
+
+Show the delivery times (B<DT>)for all the messages.
+
+Exim must have been configured to use the +delivery_time logging option
+for this option to work.
+
+I<list> is an optional list of times. Eg -show_dt1,2,4,8 will show
+the number of messages with delivery times under 1 second, 2 seconds, 4 seconds,
+8 seconds, and over 8 seconds.
+
+=item B<-show_rt>I<list>
+
+Show the receipt times for all the messages. The receipt time is
+defined as the Completed hh:mm:ss - queue_time_overall - the Receipt hh:mm:ss.
+These figures will be skewed by pipelined messages so might not be that useful.
+
+Exim must have been configured to use the +queue_time_overall logging option
+for this option to work.
+
+I<list> is an optional list of times. Eg -show_rt1,2,4,8 will show
+the number of messages with receipt times under 1 second, 2 seconds, 4 seconds,
+8 seconds, and over 8 seconds.
+
=item B<-byhost>
Show results by sending host. This may be combined with
=back
-=item B<-html>
-
-Output the results in HTML.
-
=item B<-charts>
Create graphical charts to be displayed in HTML output.
+Only valid in combination with I<-html>.
This requires the following modules which can be obtained
from http://www.cpan.org/modules/01modules.index.html
Specify the relative directory for the "img src=" tags from where to include
the charts
+=item B<-emptyok>
+
+Specify that it's OK to not find any valid log lines. Without this
+we will output an error message if we don't find any.
+
=item B<-d>
Debug flag. This outputs the eval()'d parser onto STDOUT which makes it
Eximstats parses exim mainlog and syslog files to output a statistical
analysis of the messages processed. By default, a text
-analysis is generated, but you can request an html analysis
-by using the B<-html> flag. See the help (B<-help>) to learn
+analysis is generated, but you can request other output formats
+using flags. See the help (B<-help>) to learn
about how to create charts from the tables.
=head1 AUTHOR
when you have multiple mail servers and a message cannot be
immeadiately delivered. Fixing this could be tricky...
+Merging of xls files is not (yet) possible. Be free to implement :)
+
=cut
use integer;
use strict;
+use IO::File;
# use Time::Local; # PH/FANF
use POSIX;
-use vars qw($HAVE_GD_Graph_pie $HAVE_GD_Graph_linespoints);
+use vars qw($HAVE_GD_Graph_pie $HAVE_GD_Graph_linespoints $HAVE_Spreadsheet_WriteExcel);
eval { require GD::Graph::pie; };
$HAVE_GD_Graph_pie = $@ ? 0 : 1;
eval { require GD::Graph::linespoints; };
$HAVE_GD_Graph_linespoints = $@ ? 0 : 1;
+eval { require Spreadsheet::WriteExcel; };
+$HAVE_Spreadsheet_WriteExcel = $@ ? 0 : 1;
##################################################
use vars qw(@tab62 @days_per_month $gig);
use vars qw($VERSION);
use vars qw($COLUMN_WIDTHS);
+use vars qw($WEEK $DAY $HOUR $MINUTE);
@tab62 =
@days_per_month = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334);
$gig = 1024 * 1024 * 1024;
-$VERSION = '1.35';
+$VERSION = '1.53';
# How much space do we allow for the Hosts/Domains/Emails/Edomains column headers?
$COLUMN_WIDTHS = 8;
+$MINUTE = 60;
+$HOUR = 60 * $MINUTE;
+$DAY = 24 * $HOUR;
+$WEEK = 7 * $DAY;
+
# Declare global variables.
use vars qw($total_received_data $total_received_data_gigs $total_received_count);
-use vars qw($total_delivered_data $total_delivered_data_gigs $total_delivered_count);
-use vars qw(%arrival_time %size %from_host %from_address);
-use vars qw(%timestamp2time); #Hash of timestamp => time.
-use vars qw($last_timestamp $last_time); #The last time convertion done.
-use vars qw($last_date $date_seconds); #The last date convertion done.
-use vars qw($last_offset $offset_seconds); #The last time offset convertion done.
+use vars qw($total_delivered_data $total_delivered_data_gigs $total_delivered_messages $total_delivered_addresses);
+use vars qw(%timestamp2time); #Hash of timestamp => time.
+use vars qw($last_timestamp $last_time); #The last time convertion done.
+use vars qw($last_date $date_seconds); #The last date convertion done.
+use vars qw($last_offset $offset_seconds); #The last time offset convertion done.
use vars qw($localtime_offset);
-use vars qw($i); #General loop counter.
-use vars qw($debug); #Debug mode?
-use vars qw($ntopchart); #How many entries should make it into the chart?
-use vars qw($gddirectory); #Where to put files from GD::Graph
+use vars qw($i); #General loop counter.
+use vars qw($debug); #Debug mode?
+use vars qw($ntopchart); #How many entries should make it into the chart?
+use vars qw($gddirectory); #Where to put files from GD::Graph
+
+# SpamAssassin variables
+use vars qw($spam_score $spam_score_gigs);
+use vars qw($ham_score $ham_score_gigs);
+use vars qw(%ham_count_by_ip %spam_count_by_ip);
+use vars qw(%rejected_count_by_ip %rejected_count_by_reason);
+
+#For use in Speadsheed::WriteExcel
+use vars qw($workbook $ws_global $ws_relayed $ws_errors);
+use vars qw($row $col $row_hist $col_hist);
+use vars qw($run_hist);
+use vars qw($f_default $f_header1 $f_header2 $f_header2_m $f_headertab $f_percent); #Format Header
+
+# Output FileHandles
+use vars qw($txt_fh $htm_fh $xls_fh);
$ntopchart = 5;
# set by command line switches:
use vars qw($show_errors $show_relay $show_transport $transport_pattern);
use vars qw($topcount $local_league_table $include_remote_users);
-use vars qw($hist_opt $hist_interval $hist_number $volume_rounding);
-use vars qw($relay_pattern @queue_times $html @user_patterns @user_descriptions);
+use vars qw($hist_opt $hist_interval $hist_number $volume_rounding $emptyOK);
+use vars qw($relay_pattern @queue_times @user_patterns @user_descriptions);
+use vars qw(@rcpt_times @delivery_times);
+use vars qw($include_original_destination);
+use vars qw($txt_fh $htm_fh $xls_fh);
use vars qw(%do_sender); #Do sender by Host, Domain, Email, and/or Edomain tables.
use vars qw($charts $chartrel $chartdir $charts_option_specified);
-use vars qw($merge_reports); #Merge old reports ?
+use vars qw($merge_reports); #Merge old reports ?
# The following are modified in the parse() routine, and
# referred to in the print_*() routines.
-use vars qw($queue_more_than $delayed_count $relayed_unshown $begin $end);
+use vars qw($delayed_count $relayed_unshown $begin $end);
+use vars qw(%messages @message);
use vars qw(%received_count %received_data %received_data_gigs);
-use vars qw(%delivered_count %delivered_data %delivered_data_gigs);
+use vars qw(%delivered_messages %delivered_data %delivered_data_gigs %delivered_addresses);
use vars qw(%received_count_user %received_data_user %received_data_gigs_user);
-use vars qw(%delivered_count_user %delivered_data_user %delivered_data_gigs_user);
+use vars qw(%delivered_messages_user %delivered_addresses_user %delivered_data_user %delivered_data_gigs_user);
use vars qw(%transported_count %transported_data %transported_data_gigs);
-use vars qw(%remote_delivered %relayed %delayed %had_error %errors_count);
-use vars qw(@queue_bin @remote_queue_bin @received_interval_count @delivered_interval_count);
-use vars qw(@user_pattern_totals);
+use vars qw(%relayed %errors_count $message_errors);
+use vars qw(@qt_all_bin @qt_remote_bin);
+use vars qw($qt_all_overflow $qt_remote_overflow);
+use vars qw(@dt_all_bin @dt_remote_bin %rcpt_times_bin);
+use vars qw($dt_all_overflow $dt_remote_overflow %rcpt_times_overflow);
+use vars qw(@received_interval_count @delivered_interval_count);
+use vars qw(@user_pattern_totals @user_pattern_interval_count);
use vars qw(%report_totals);
+# Enumerations
+use vars qw($SIZE $FROM_HOST $FROM_ADDRESS $ARRIVAL_TIME $REMOTE_DELIVERED $PROTOCOL);
+use vars qw($DELAYED $HAD_ERROR);
+$SIZE = 0;
+$FROM_HOST = 1;
+$FROM_ADDRESS = 2;
+$ARRIVAL_TIME = 3;
+$REMOTE_DELIVERED = 4;
+$DELAYED = 5;
+$HAD_ERROR = 6;
+$PROTOCOL = 7;
# Subroutines #
##################################################
+#######################################################################
+# get_filehandle($file,\%output_files);
+# Return a filehandle writing to $file.
+#
+# If %output_files is defined, check that $output_files{$file}
+# doesn't exist and die if it does, or set it if it doesn't.
+#######################################################################
+sub get_filehandle {
+ my($file,$output_files_href) = @_;
+
+ $file = '-' if ($file eq '');
+
+ if (defined $output_files_href) {
+ die "You can only output to '$file' once! Use -h for help.\n" if exists $output_files_href->{$file};
+ $output_files_href->{$file} = 1;
+ }
+
+ if ($file eq '-') {
+ return \*STDOUT;
+ }
+
+ if (-e $file) {
+ unlink $file or die "Failed to rm $file: $!";
+ }
+
+ my $fh = new IO::File $file, O_WRONLY|O_CREAT|O_EXCL;
+ die "new IO::File $file failed: $!" unless (defined $fh);
+ return $fh;
+}
+
#######################################################################
# volume_rounded();
}
else {
# We don't want any rounding to be done.
- $rounded = sprintf("%4d", ($g * $gig) + $x);
+ # and we don't need broken formated output which on one hand avoids numbers from
+ # being interpreted as string by Spreadsheed Calculators, on the other hand
+ # breaks if more than 4 digits! -> flexible length instead of fixed length
+ # Format the return value at the output routine! -fh
+ #$rounded = sprintf("%d", ($g * $gig) + $x);
+ no integer;
+ $rounded = sprintf("%.0f", ($g * $gig) + $x);
}
return $rounded;
#######################################################################
# un_round();
-#
+#
# un_round($rounded_volume,\$bytes,\$gigabytes);
-#
+#
# Given a volume in KB, MB or GB, as generated by volume_rounded(),
# do the reverse transformation and convert it back into Bytes and Gigabytes.
# These are added to the $bytes and $gigabytes parameters.
-#
+#
# Given a data size in bytes, round it to KB, MB, or GB
# as appropriate.
-#
+#
# EG: 500 => (500,0), 14GB => (0,14), etc.
#######################################################################
sub un_round {
$$bytes_sref += ($1 % (1024 * 1024) * 1024);
}
elsif ($rounded =~ /(\d+)/) {
- $$gigabytes_sref += $1 / $gig;
+ # We need to turn off integer in case we are merging an -nvr report.
+ no integer;
+ $$gigabytes_sref += int($1 / $gig);
$$bytes_sref += $1 % $gig;
}
#######################################################################
# add_volume();
-#
+#
# add_volume(\$bytes,\$gigs,$size);
-#
+#
# Add $size to $bytes/$gigs where this is a number split into
# bytes ($bytes) and gigabytes ($gigs). This is significantly
# faster than using Math::BigInt.
#######################################################################
# format_time();
-#
+#
# $formatted_time = format_time($seconds);
-#
+#
# Given a time in seconds, break it down into
# weeks, days, hours, minutes, and seconds.
-#
+#
# Eg 12005 => 3h20m5s
#######################################################################
sub format_time {
#######################################################################
# unformat_time();
-#
+#
# $seconds = unformat_time($formatted_time);
-#
+#
# Given a time in weeks, days, hours, minutes, or seconds, convert it to seconds.
-#
+#
# Eg 3h20m5s => 12005
#######################################################################
sub unformat_time {
#######################################################################
# seconds();
-#
+#
# $time = seconds($timestamp);
-#
+#
# Given a time-of-day timestamp, convert it into a time() value using
# POSIX::mktime. We expect the timestamp to be of the form
# "$year-$mon-$day $hour:$min:$sec", with month going from 1 to 12,
# (with the -utc option), then we adjust the time by the current local
# time offset so that it can be compared with the time recorded in message
# IDs, which is UTC.
-#
+#
# To improve performance, we only use mktime on the date ($year-$mon-$day),
# and only calculate it if the date is different to the previous time we
# came here. We then add on seconds for the '$hour:$min:$sec'.
-#
+#
# We also store the results of the last conversion done, and only
# recalculate if the date is different.
-#
+#
# We used to have the '-cache' flag which would store the results of the
# mktime() call. However, the current way of just using mktime() on the
# date obsoletes this.
#######################################################################
# id_seconds();
-#
+#
# $time = id_seconds($message_id);
-#
+#
# Given a message ID, convert it into a time() value.
#######################################################################
sub id_seconds {
$s;
}
+#######################################################################
+# wdhms_seconds();
+#
+# $seconds = wdhms_seconds($string);
+#
+# Convert a string in a week/day/hour/minute/second format (eg 4h10s)
+# into seconds.
+#######################################################################
+sub wdhms_seconds {
+ if ($_[0] =~ /^(?:(\d+)w)?(?:(\d+)d)?(?:(\d+)h)?(?:(\d+)m)?(?:(\d+)s)?/) {
+ return((($1||0) * $WEEK) + (($2||0) * $DAY) + (($3||0) * $HOUR) + (($4||0) * $MINUTE) + ($5||0));
+ }
+ return undef;
+}
+
+#######################################################################
+# queue_time();
+#
+# $queued = queue_time($completed_tod, $arrival_time, $id);
+#
+# Given the completed time of day and either the arrival time
+# (preferred), or the message ID, calculate how long the message has
+# been on the queue.
+#
+#######################################################################
+sub queue_time {
+ my($completed_tod, $arrival_time, $id) = @_;
+
+ # Note: id_seconds() benchmarks as 42% slower than seconds()
+ # and computing the time accounts for a significant portion of
+ # the run time.
+ if (defined $arrival_time) {
+ return(seconds($completed_tod) - seconds($arrival_time));
+ }
+ else {
+ return(seconds($completed_tod) - id_seconds($id));
+ }
+}
#######################################################################
# calculate_localtime_offset();
-#
+#
# $localtime_offset = calculate_localtime_offset();
-#
+#
# Calculate the the localtime offset from gmtime in seconds.
-#
+#
# $localtime = time() + $localtime_offset.
-#
+#
# These are the same semantics as ISO 8601 and RFC 2822 timezone offsets.
# (West is negative, East is positive.)
#######################################################################
}
+
#######################################################################
-# print_queue_times();
-#
-# $time = print_queue_times($message_type,\@queue_times,$queue_more_than);
-#
-# Given the type of messages being output, the array of message queue times,
-# and the number of messages which exceeded the queue times, print out
-# a table.
+# print_duration_table();
+#
+# print_duration_table($title, $message_type, \@times, \@values, $overflow);
+#
+# Print a table showing how long a particular step took for
+# the messages. The parameters are:
+# $title Eg "Time spent on the queue"
+# $message_type Eg "Remote"
+# \@times The maximum time a message took for it to increment
+# the corresponding @values counter.
+# \@values An array of message counters.
+# $overflow The number of messages which exceeded the maximum
+# time.
#######################################################################
-sub print_queue_times {
+sub print_duration_table {
no integer;
-my($string,$array,$queue_more_than) = @_;
+my($title, $message_type, $times_aref, $values_aref, $overflow) = @_;
my(@chartdatanames);
my(@chartdatavals);
my $printed_one = 0;
my $cumulative_percent = 0;
-#$queue_unknown += keys %arrival_time;
-my $queue_total = $queue_more_than;
-for ($i = 0; $i <= $#queue_times; $i++) { $queue_total += $$array[$i] }
+my $queue_total = $overflow;
+map {$queue_total += $_} @$values_aref;
+
+my $temp = "$title: $message_type";
-my $temp = "Time spent on the queue: $string";
-my($format);
-if ($html) {
- print "<hr><a name=\"$string time\"></a><h2>$temp</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td>\n";
- print "<table border=1>\n";
- print "<tr><th>Time</th><th>Messages</th><th>Percentage</th><th>Cumulative Percentage</th>\n";
- $format = "<tr><td align=\"right\">%s %s</td><td align=\"right\">%d</td><td align=\"right\">%5.1f%%</td><td align=\"right\">%5.1f%%</td>\n";
+my $txt_format = "%5s %4s %6d %5.1f%% %5.1f%%\n";
+my $htm_format = "<tr><td align=\"right\">%s %s</td><td align=\"right\">%d</td><td align=\"right\">%5.1f%%</td><td align=\"right\">%5.1f%%</td>\n";
+
+# write header
+printf $txt_fh ("%s\n%s\n\n", $temp, "-" x length($temp)) if $txt_fh;
+if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"$title $message_type\"></a><h2>$temp</h2>\n";
+ print $htm_fh "<table border=0 width=\"100%\"><tr><td><table border=1>\n";
+ print $htm_fh "<tr><th>Time</th><th>Messages</th><th>Percentage</th><th>Cumulative Percentage</th>\n";
}
-else
-{
- printf("%s\n%s\n\n", $temp, "-" x length($temp));
- $format = "%5s %4s %6d %5.1f%% %5.1f%%\n";
+if ($xls_fh) {
+ $ws_global->write($row++, $col, "$title: ".$message_type, $f_header2);
+ my @content=("Time", "Messages", "Percentage", "Cumulative Percentage");
+ &set_worksheet_line($ws_global, $row++, 1, \@content, $f_headertab);
}
-for ($i = 0; $i <= $#queue_times; $i++) {
- if ($$array[$i] > 0)
+
+for ($i = 0; $i <= $#$times_aref; ++$i) {
+ if ($$values_aref[$i] > 0)
{
- my $percent = ($$array[$i] * 100)/$queue_total;
+ my $percent = ($values_aref->[$i] * 100)/$queue_total;
$cumulative_percent += $percent;
- printf($format,
- $printed_one? " " : "Under",
- format_time($queue_times[$i]),
- $$array[$i], $percent, $cumulative_percent);
- if (!defined($queue_times[$i])) {
- print "Not defined";
+
+ my @content=($printed_one? " " : "Under",
+ format_time($times_aref->[$i]),
+ $values_aref->[$i], $percent, $cumulative_percent);
+
+ if ($htm_fh) {
+ printf $htm_fh ($htm_format, @content);
+ if (!defined($values_aref->[$i])) {
+ print $htm_fh "Not defined";
+ }
+ }
+ if ($txt_fh) {
+ printf $txt_fh ($txt_format, @content);
+ if (!defined($times_aref->[$i])) {
+ print $txt_fh "Not defined";
+ }
+ }
+ if ($xls_fh)
+ {
+ no integer;
+ &set_worksheet_line($ws_global, $row, 0, [@content[0,1,2]], $f_default);
+ &set_worksheet_line($ws_global, $row++, 3, [$content[3]/100,$content[4]/100], $f_percent);
+
+ if (!defined($times_aref->[$i])) {
+ $col=0;
+ $ws_global->write($row++, $col, "Not defined" );
+ }
}
+
push(@chartdatanames,
- ($printed_one? "" : "Under") . format_time($queue_times[$i]));
- push(@chartdatavals, $$array[$i]);
+ ($printed_one? "" : "Under") . format_time($times_aref->[$i]));
+ push(@chartdatavals, $$values_aref[$i]);
$printed_one = 1;
}
}
-if ($queue_more_than > 0) {
- my $percent = ($queue_more_than * 100)/$queue_total;
+if ($overflow && $overflow > 0) {
+ my $percent = ($overflow * 100)/$queue_total;
$cumulative_percent += $percent;
- printf($format,
- "Over ",
- format_time($queue_times[$#queue_times]),
- $queue_more_than, $percent, $cumulative_percent);
+
+ my @content = ("Over ", format_time($times_aref->[-1]),
+ $overflow, $percent, $cumulative_percent);
+
+ printf $txt_fh ($txt_format, @content) if $txt_fh;
+ printf $htm_fh ($htm_format, @content) if $htm_fh;
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_global, $row, 0, [@content[0,1,2]], $f_default);
+ &set_worksheet_line($ws_global, $row++, 3, [$content[3]/100,$content[4]/100], $f_percent);
+ }
+
}
-push(@chartdatanames, "Over " . format_time($queue_times[$#queue_times]));
-push(@chartdatavals, $queue_more_than);
+
+push(@chartdatanames, "Over " . format_time($times_aref->[-1]));
+push(@chartdatavals, $overflow);
#printf("Unknown %6d\n", $queue_unknown) if $queue_unknown > 0;
-if ($html) {
- print "</table>\n";
- print "</td><td>\n";
+if ($htm_fh) {
+ print $htm_fh "</table></td><td>";
- if ($HAVE_GD_Graph_pie && $charts) {
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals > 0)) {
my @data = (
\@chartdatanames,
\@chartdatavals
);
my $graph = GD::Graph::pie->new(200, 200);
- my $pngname;
- my $title;
- if ($string =~ /all/) { $pngname = "queue_all.png"; $title = "Queue (all)"; }
- if ($string =~ /remote/) { $pngname = "queue_rem.png"; $title = "Queue (remote)"; }
- $graph->set(
- title => $title,
- );
+ my $pngname = "$title-$message_type.png";
+ $pngname =~ s/[^\w\-\.]/_/;
+
+ my $graph_title = "$title ($message_type)";
+ $graph->set(title => $graph_title) if (length($graph_title) < 21);
+
my $gd = $graph->plot(\@data) or warn($graph->error);
if ($gd) {
- open(IMG, ">$chartdir/$pngname") or die $!;
+ open(IMG, ">$chartdir/$pngname") or die "Could not write $chartdir/$pngname: $!\n";
binmode IMG;
print IMG $gd->png;
close IMG;
- print "<img src=\"$chartrel/$pngname\">";
+ print
$htm_fh "<img src=\"$chartrel/$pngname\">";
}
}
- print "</td></tr></table>\n";
+ print $htm_fh "</td></tr></table>\n";
}
-print "\n";
+
+if ($xls_fh)
+{
+ $row++;
}
+print $txt_fh "\n" if $txt_fh;
+print $htm_fh "\n" if $htm_fh;
+}
#######################################################################
# print_histogram();
-#
-# print_histogram('Deliverieds|Messages received',@interval_count);
-#
+#
+# print_histogram('Deliveries|Messages received|$pattern', $unit, @interval_count);
+#
# Print a histogram of the messages delivered/received per time slot
# (hour by default).
#######################################################################
sub print_histogram {
-my($text) = shift;
-my(@interval_count) = @_;
+my($text, $unit, @interval_count) = @_;
my(@chartdatanames);
my(@chartdatavals);
my($maxd) = 0;
+
+# save first row of print_histogram for xls output
+if (!$run_hist) {
+ $row_hist = $row;
+}
+else {
+ $row = $row_hist;
+}
+
for ($i = 0; $i < $hist_number; $i++)
{ $maxd = $interval_count[$i] if $interval_count[$i] > $maxd; }
my $scale = int(($maxd + 25)/50);
$scale = 1 if $scale == 0;
-my($type);
-if ($text eq "Deliveries")
- {
- $type = ($scale == 1)? "delivery" : "deliveries";
- }
-else
- {
- $type = ($scale == 1)? "message" : "messages";
+if ($scale != 1) {
+ if ($unit !~ s/y$/ies/) {
+ $unit .= 's';
}
+}
+
+# make and output title
+my $title = sprintf("$text per %s",
+ ($hist_interval == 60)? "hour" :
+ ($hist_interval == 1)? "minute" : "$hist_interval minutes");
-my($title) = sprintf("$text per %s (each dot is $scale $type)",
- ($hist_interval == 60)? "hour" :
- ($hist_interval == 1)? "minute" : "$hist_interval minutes");
+my $txt_htm_title = $title . " (each dot is $scale $unit)";
-if ($html) {
- print "<hr><a name=\"$text\"></a><h2>$title</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td><pre>\n";
+printf $txt_fh ("%s\n%s\n\n", $txt_htm_title, "-" x length($txt_htm_title)) if $txt_fh;
+
+if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"$text\"></a><h2>$txt_htm_title</h2>\n";
+ print $htm_fh "<table border=0 width=\"100%\">\n";
+ print $htm_fh "<tr><td><pre>\n";
}
-else {
- printf("%s\n%s\n\n", $title, "-" x length($title));
+
+if ($xls_fh) {
+ $title =~ s/Messages/Msg/ ;
+ $row += 2;
+ $ws_global->write($row++, $col_hist+1, $title, $f_headertab);
}
+
my $hour = 0;
my $minutes = 0;
-for ($i = 0; $i < $hist_number; $i++)
- {
+for ($i = 0; $i < $hist_number; $i++) {
my $c = $interval_count[$i];
# If the interval is an hour (the maximum) print the starting and
# minutes, which take up the same space.
my $temp;
- if ($hist_opt == 1)
- {
+ if ($hist_opt == 1) {
$temp = sprintf("%02d-%02d", $hour, $hour + 1);
- print $temp;
+
+ print $txt_fh $temp if $txt_fh;
+ print $htm_fh $temp if $htm_fh;
+
+ if ($xls_fh) {
+ if ($run_hist==0) {
+ # only on first run
+ $ws_global->write($row, 0, [$temp], $f_default);
+ }
+ }
+
push(@chartdatanames, $temp);
$hour++;
- }
- else
- {
+ }
+ else {
if ($minutes == 0)
{ $temp = sprintf("%02d:%02d", $hour, $minutes) }
else
{ $temp = sprintf(" :%02d", $minutes) }
- print $temp;
+
+ print $txt_fh $temp if $txt_fh;
+ print $htm_fh $temp if $htm_fh;
+ if (($xls_fh) and ($run_hist==0)) {
+ # only on first run
+ $temp = sprintf("%02d:%02d", $hour, $minutes);
+ $ws_global->write($row, 0, [$temp], $f_default);
+ }
+
push(@chartdatanames, $temp);
$minutes += $hist_interval;
- if ($minutes >= 60)
- {
+ if ($minutes >= 60) {
$minutes = 0;
$hour++;
- }
}
- push(@chartdatavals, $c);
- printf(" %6d %s\n", $c, "." x ($c/$scale));
}
-print "\n";
-if ($html)
- {
- print "</pre>\n";
- print "</td><td>\n";
- if ($HAVE_GD_Graph_linespoints && $charts) {
+ push(@chartdatavals, $c);
+
+ printf $txt_fh (" %6d %s\n", $c, "." x ($c/$scale)) if $txt_fh;
+ printf $htm_fh (" %6d %s\n", $c, "." x ($c/$scale)) if $htm_fh;
+ $ws_global->write($row++, $col_hist+1, [$c], $f_default) if $xls_fh;
+
+} #end for
+
+printf $txt_fh "\n" if $txt_fh;
+printf $htm_fh "\n" if $htm_fh;
+
+if ($htm_fh)
+{
+ print $htm_fh "</pre>\n";
+ print $htm_fh "</td><td>\n";
+ if ($HAVE_GD_Graph_linespoints && $charts && ($#chartdatavals > 0)) {
# calculate the graph
my @data = (
\@chartdatanames,
title => $text,
x_labels_vertical => 1
);
- my($pngname);
- if ($text =~ /Deliveries/) { $pngname = "histogram_del.png"; }
- if ($text =~ /Messages/) { $pngname = "histogram_mes.png"; }
+ my $pngname = "histogram_$text.png";
+ $pngname =~ s/[^\w\._]/_/g;
+
my $gd = $graph->plot(\@data) or warn($graph->error);
if ($gd) {
- open(IMG, ">$chartdir/$pngname") or die $!;
+ open(IMG, ">$chartdir/$pngname") or die "Could not write $chartdir/$pngname: $!\n";
binmode IMG;
print IMG $gd->png;
close IMG;
- print "<img src=\"$chartrel/$pngname\">";
+ print
$htm_fh "<img src=\"$chartrel/$pngname\">";
}
}
- print "</td></tr></table>\n";
+ print $htm_fh "</td></tr></table>\n";
}
+
+$col_hist++; # where to continue next times
+
+$row+=2; # leave some space after history block
+$run_hist=1; # we have done this once or more
}
#######################################################################
# print_league_table();
-#
-# print_league_table($league_table_type,\%message_count,\%message_data,\%message_data_gigs);
-#
-# Given hashes of message count and message data, which are keyed by
-# the table type (eg by the sending host), print a league table
-# showing the top $topcount (defaults to 50).
+#
+# print_league_table($league_table_type,\%message_count,\%address_count,\%message_data,\%message_data_gigs, $spreadsheet, $row_sref);
+#
+# Given hashes of message count, address count, and message data,
+# which are keyed by the table type (eg by the sending host), print a
+# league table showing the top $topcount (defaults to 50).
#######################################################################
sub print_league_table {
-my($text,$m_count,$m_data,$m_data_gigs) = @_;
-my($name) = ($topcount == 1)? "$text" : "$topcount ${text}s";
-my($temp) = "Top $name by message count";
-my(@chartdatanames) = ();
-my(@chartdatavals) = ();
-my $chartotherval = 0;
-
-my($format);
-if ($html) {
- print "<hr><a name=\"$text count\"></a><h2>$temp</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td>\n";
- print "<table border=1>\n";
- print "<tr><th>Messages</th><th>Bytes</th><th>\u$text</th>\n";
+ my($text,$m_count,$a_count,$m_data,$m_data_gigs,$spreadsheet, $row_sref) = @_;
+ my($name) = ($topcount == 1)? "$text" : "$topcount ${text}s";
+ my($title) = "Top $name by message count";
+ my(@chartdatanames) = ();
+ my(@chartdatavals) = ();
+ my $chartotherval = 0;
+ $text = ucfirst($text);
# Align non-local addresses to the right (so all the .com's line up).
# Local addresses are aligned on the left as they are userids.
my $align = ($text !~ /local/i) ? 'right' : 'left';
- $format = "<tr><td align=\"right\">%d</td><td align=\"right\">%s</td><td align=\"$align\" nowrap>%s</td>\n";
-}
-else {
- printf("%s\n%s\n\n", $temp, "-" x length($temp));
- $format = "%7d %10s %s\n";
-}
-my($key,$htmlkey);
-foreach $key (top_n_sort($topcount,$m_count,$m_data_gigs,$m_data)) {
- if ($html) {
- $htmlkey = $key;
- $htmlkey =~ s/>/\>\;/g;
- $htmlkey =~ s/</\<\;/g;
- printf($format, $$m_count{$key}, volume_rounded($$m_data{$key},$$m_data_gigs{$key}), $htmlkey);
- }
- else {
- printf($format, $$m_count{$key}, volume_rounded($$m_data{$key},$$m_data_gigs{$key}), $key);
+
+ ################################################
+ # Generate the printf formats and table headers.
+ ################################################
+ my(@headers) = ('Messages');
+ push(@headers,'Addresses') if defined $a_count;
+ push(@headers,'Bytes','Average') if defined $m_data;
+
+ my $txt_format = "%10s " x @headers . " %s\n";
+ my $txt_col_headers = sprintf $txt_format, @headers, $text;
+ my $htm_format = "<tr>" . '<td align="right">%s</td>'x@headers . "<td align=\"$align\" nowrap>%s</td></tr>\n";
+ my $htm_col_headers = sprintf $htm_format, @headers, $text;
+ $htm_col_headers =~ s/(<\/?)td/$1th/g; #Convert <td>'s to <th>'s for the header.
+
+
+ ################################################
+ # Write the table headers
+ ################################################
+ printf $txt_fh ("%s\n%s\n%s", $title, "-" x length($title),$txt_col_headers) if $txt_fh;
+
+ if ($htm_fh) {
+ print $htm_fh <<EoText;
+<hr><a name="$text count"></a><h2>$title</h2>
+<table border=0 width="100%">
+<tr><td>
+<table border=1>
+EoText
+ print $htm_col_headers;
}
- if (scalar @chartdatanames < $ntopchart)
- {
- push(@chartdatanames, $key);
- push(@chartdatavals, $$m_count{$key});
- }
- else
- {
- $chartotherval += $$m_count{$key};
- }
+
+ if ($xls_fh) {
+ $spreadsheet->write(${$row_sref}++, 0, $title, $f_header2);
+ $spreadsheet->write(${$row_sref}++, 0, [@headers, $text], $f_headertab);
}
-push(@chartdatanames, "Other");
-push(@chartdatavals, $chartotherval);
-if ($html)
- {
- print "</table>\n";
- print "</td><td>\n";
- if ($HAVE_GD_Graph_pie && $charts)
- {
- # calculate the graph
- my @data = (
- \@chartdatanames,
- \@chartdatavals
- );
- my $graph = GD::Graph::pie->new(300, 300);
- $graph->set(
- x_label => 'Name',
- y_label => 'Amount',
- title => 'By count',
- );
- my $gd = $graph->plot(\@data) or warn($graph->error);
- if ($gd) {
- my $temp = $text;
- $temp =~ s/ /_/g;
- open(IMG, ">$chartdir/${temp}_count.png") or die $!;
- binmode IMG;
- print IMG $gd->png;
- close IMG;
- print "<img src=\"$chartrel/${temp}_count.png\">";
+
+ # write content
+ foreach my $key (top_n_sort($topcount,$m_count,$m_data_gigs,$m_data)) {
+
+ # When displaying the average figures, we calculate the average of
+ # the rounded data, as the user would calculate it. This reduces
+ # the accuracy slightly, but we have to do it this way otherwise
+ # when using -merge to convert results from text to HTML and
+ # vice-versa discrepencies would occur.
+ my $messages = $$m_count{$key};
+ my @content = ($messages);
+ push(@content, $$a_count{$key}) if defined $a_count;
+ if (defined $m_data) {
+ my $rounded_volume = volume_rounded($$m_data{$key},$$m_data_gigs{$key});
+ my($data,$gigs) = (0,0);
+ un_round($rounded_volume,\$data,\$gigs);
+ my $rounded_average = volume_rounded($data/$messages,$gigs/$messages);
+ push(@content, $rounded_volume, $rounded_average);
}
- }
- print "</td><td>\n";
- print "</td></tr></table>\n";
-}
-print "\n";
-
-$temp = "Top $name by volume";
-if ($html) {
- print "<hr><a name=\"$text volume\"></a><h2>$temp</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td>\n";
- print "<table border=1>\n";
- print "<tr><th>Messages</th><th>Bytes</th><th>\u$text</th>\n";
-}
-else {
- printf("%s\n%s\n\n", $temp, "-" x length($temp));
-}
-@chartdatanames = ();
-@chartdatavals = ();
-$chartotherval = 0;
-my $use_gig = 0;
-foreach $key (top_n_sort($topcount,$m_data_gigs,$m_data,$m_count)) {
- if ($$m_data_gigs{$key}) {
- $use_gig = 1;
- }
- if ($html) {
- $htmlkey = $key;
- $htmlkey =~ s/>/\>\;/g;
- $htmlkey =~ s/</\<\;/g;
- printf($format, $$m_count{$key}, volume_rounded($$m_data{$key},$$m_data_gigs{$key}), $htmlkey);
- }
- else {
- printf($format, $$m_count{$key}, volume_rounded($$m_data{$key},$$m_data_gigs{$key}), $key);
- }
+ # write content
+ printf $txt_fh ($txt_format, @content, $key) if $txt_fh;
- if (scalar @chartdatanames < $ntopchart) {
- if ($use_gig) {
- if ($$m_data_gigs{$key}) {
- push(@chartdatanames, $key);
- push(@chartdatavals, $$m_data_gigs{$key});
- }
+ if ($htm_fh) {
+ my $htmlkey = $key;
+ $htmlkey =~ s/>/\>\;/g;
+ $htmlkey =~ s/</\<\;/g;
+ printf $htm_fh ($htm_format, @content, $htmlkey);
}
- else {
+ $spreadsheet->write(${$row_sref}++, 0, [@content, $key], $f_default) if $xls_fh;
+
+ if (scalar @chartdatanames < $ntopchart) {
push(@chartdatanames, $key);
- push(@chartdatavals, $$m_data{$key});
+ push(@chartdatavals, $$m_count{$key});
}
- }
- else {
- $chartotherval += ($use_gig) ? $$m_data_gigs{$key} : $$m_data{$key};
- }
-}
-push(@chartdatanames, "Other");
-push(@chartdatavals, $chartotherval);
-
-if ($html) {
- print "</table>\n";
- print "</td><td>\n";
- if ($HAVE_GD_Graph_pie && $charts) {
- # calculate the graph
- my @data = (
- \@chartdatanames,
- \@chartdatavals
- );
- my $graph = GD::Graph::pie->new(300, 300);
- $graph->set(
- x_label => 'Name',
- y_label => 'Volume' ,
- title => 'By Volume',
- );
- my $gd = $graph->plot(\@data) or warn($graph->error);
- if ($gd) {
- my $temp = $text;
- $temp =~ s/ /_/g;
- open(IMG, ">$chartdir/${temp}_volume.png") or die $!;
- binmode IMG;
- print IMG $gd->png;
- close IMG;
- print "<img src=\"$chartrel/${temp}_volume.png\">";
+ else {
+ $chartotherval += $$m_count{$key};
}
}
- print "</td><td>\n";
- print "</td></tr></table>\n";
-}
-print "\n";
-}
+ push(@chartdatanames, "Other");
+ push(@chartdatavals, $chartotherval);
+
+ print $txt_fh "\n" if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh "</table>\n";
+ print $htm_fh "</td><td>\n";
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals > 0))
+ {
+ # calculate the graph
+ my @data = (
+ \@chartdatanames,
+ \@chartdatavals
+ );
+ my $graph = GD::Graph::pie->new(300, 300);
+ $graph->set(
+ x_label => 'Name',
+ y_label => 'Amount',
+ title => 'By count',
+ );
+ my $gd = $graph->plot(\@data) or warn($graph->error);
+ if ($gd) {
+ my $temp = $text;
+ $temp =~ s/ /_/g;
+ open(IMG, ">$chartdir/${temp}_count.png") or die "Could not write $chartdir/${temp}_count.png: $!\n";
+ binmode IMG;
+ print IMG $gd->png;
+ close IMG;
+ print $htm_fh "<img src=\"$chartrel/${temp}_count.png\">";
+ }
+ }
+ print $htm_fh "</td><td>\n";
+ print $htm_fh "</td></tr></table>\n\n";
+ }
+ ++${$row_sref} if $xls_fh;
+
+
+ if (defined $m_data) {
+ # write header
+
+ $title = "Top $name by volume";
+
+ printf $txt_fh ("%s\n%s\n%s", $title, "-" x length($title),$txt_col_headers) if $txt_fh;
+
+ if ($htm_fh) {
+ print $htm_fh <<EoText;
+<hr><a name="$text volume"></a><h2>$title</h2>
+<table border=0 width="100%">
+<tr><td>
+<table border=1>
+EoText
+ print $htm_col_headers;
+ }
+ if ($xls_fh) {
+ $spreadsheet->write(${$row_sref}++, 0, $title, $f_header2);
+ $spreadsheet->write(${$row_sref}++, 0, [@headers, $text], $f_headertab);
+ }
+
+ @chartdatanames = ();
+ @chartdatavals = ();
+ $chartotherval = 0;
+ my $use_gig = 0;
+ foreach my $key (top_n_sort($topcount,$m_data_gigs,$m_data,$m_count)) {
+ # The largest volume will be the first (top of the list).
+ # If it has at least 1 gig, then just use gigabytes to avoid
+ # risking an integer overflow when generating the pie charts.
+ if ($$m_data_gigs{$key}) {
+ $use_gig = 1;
+ }
+
+ my $messages = $$m_count{$key};
+ my @content = ($messages);
+ push(@content, $$a_count{$key}) if defined $a_count;
+ my $rounded_volume = volume_rounded($$m_data{$key},$$m_data_gigs{$key});
+ my($data ,$gigs) = (0,0);
+ un_round($rounded_volume,\$data,\$gigs);
+ my $rounded_average = volume_rounded($data/$messages,$gigs/$messages);
+ push(@content, $rounded_volume, $rounded_average );
+
+ # write content
+ printf $txt_fh ($txt_format, @content, $key) if $txt_fh;
+ if ($htm_fh) {
+ my $htmlkey = $key;
+ $htmlkey =~ s/>/\>\;/g;
+ $htmlkey =~ s/</\<\;/g;
+ printf $htm_fh ($htm_format, @content, $htmlkey);
+ }
+ $spreadsheet->write(${$row_sref}++, 0, [@content, $key], $f_default) if $xls_fh;
+
+
+ if (scalar @chartdatanames < $ntopchart) {
+ if ($use_gig) {
+ if ($$m_data_gigs{$key}) {
+ push(@chartdatanames, $key);
+ push(@chartdatavals, $$m_data_gigs{$key});
+ }
+ }
+ else {
+ push(@chartdatanames, $key);
+ push(@chartdatavals, $$m_data{$key});
+ }
+ }
+ else {
+ $chartotherval += ($use_gig) ? $$m_data_gigs{$key} : $$m_data{$key};
+ }
+ }
+ push(@chartdatanames, "Other");
+ push(@chartdatavals, $chartotherval);
+
+ print $txt_fh "\n" if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh "</table>\n";
+ print $htm_fh "</td><td>\n";
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals > 0)) {
+ # calculate the graph
+ my @data = (
+ \@chartdatanames,
+ \@chartdatavals
+ );
+ my $graph = GD::Graph::pie->new(300, 300);
+ $graph->set(
+ x_label => 'Name',
+ y_label => 'Volume' ,
+ title => 'By Volume',
+ );
+ my $gd = $graph->plot(\@data) or warn($graph->error);
+ if ($gd) {
+ my $temp = $text;
+ $temp =~ s/ /_/g;
+ open(IMG, ">$chartdir/${temp}_volume.png") or die "Could not write $chartdir/${temp}_volume.png: $!\n";
+ binmode IMG;
+ print IMG $gd->png;
+ close IMG;
+ print $htm_fh "<img src=\"$chartrel/${temp}_volume.png\">";
+ }
+ }
+ print $htm_fh "</td><td>\n";
+ print $htm_fh "</td></tr></table>\n\n";
+ }
+
+ ++${$row_sref} if $xls_fh;
+ }
+}
#######################################################################
# top_n_sort();
-#
+#
# @sorted_keys = top_n_sort($n,$href1,$href2,$href3);
-#
+#
# Given a hash which has numerical values, return the sorted $n keys which
# point to the top values. The second and third hashes are used as
# tiebreakers. They all must have the same keys.
-#
+#
# The idea behind this routine is that when you only want to see the
# top n members of a set, rather than sorting the entire set and then
# plucking off the top n, sort through the stack as you go, discarding
# any member which is lower than your current n'th highest member.
-#
+#
# This proves to be an order of magnitude faster for large hashes.
# On 200,000 lines of mainlog it benchmarked 9 times faster.
# On 700,000 lines of mainlog it benchmarked 13.8 times faster.
-#
+#
# We assume the values are > 0.
#######################################################################
sub top_n_sort {
my $n_minus_1 = $n - 1;
my $n_minus_2 = $n - 2;
- # Pick out the top $n keys.
+ # Create a dummy hash incase the user has not provided us with
+ # tiebreaker hashes.
+ my(%dummy_hash);
+ $href2 = \%dummy_hash unless defined $href2;
+ $href3 = \%dummy_hash unless defined $href3;
+
+ # Pick out the top $n keys.
my($key,$value1,$value2,$value3,$i,$comparison,$insert_position);
while (($key,$value1) = each %$href1) {
#print STDERR "key $key ($value1,",$href2->{$key},",",$href3->{$key},") <=> ($minimum_value1,$minimum_value2,$minimum_value3)\n";
-
+
# Check to see that the new value is bigger than the lowest of the
- # top n keys that we're keeping.
- $comparison = $value1 <=> $minimum_value1 ||
- $href2->{$key} <=> $minimum_value2 ||
- $href3->{$key} <=> $minimum_value3 ||
- $top_n_key cmp $key;
+ # top n keys that we're keeping. We test the main key first, because
+ # for the majority of cases we can skip creating dummy hash values
+ # should the user have not provided real tie-breaking hashes.
+ next unless $value1 >= $minimum_value1;
+
+ # Create a dummy hash entry for the key if required.
+ # Note that setting the dummy_hash value sets it for both href2 &
+ # href3. Also note that currently we are guarenteed to have a real
+ # value for href3 if a real value for href2 exists so don't need to
+ # test for it as well.
+ $dummy_hash{$key} = 0 unless exists $href2->{$key};
+
+ $comparison = $value1 <=> $minimum_value1 ||
+ $href2->{$key} <=> $minimum_value2 ||
+ $href3->{$key} <=> $minimum_value3 ||
+ $top_n_key cmp $key;
next unless ($comparison == 1);
# As we will be using these values a few times, extract them into scalars.
for ($i = 0; $i < $n_minus_1; $i++) {
$top_n_key = $top_n_keys[$i];
if ( ($top_n_key eq '_') ||
- ( ($value1 <=> $href1->{$top_n_key} ||
+ ( ($value1 <=> $href1->{$top_n_key} ||
$value2 <=> $href2->{$top_n_key} ||
- $value3 <=> $href3->{$top_n_key} ||
- $top_n_key cmp $key) == 1
- )
- ) {
- $insert_position = $i;
- last;
+ $value3 <=> $href3->{$top_n_key} ||
+ $top_n_key cmp $key) == 1
+ )
+ ) {
+ $insert_position = $i;
+ last;
}
}
}
+
#######################################################################
# html_header();
-#
+#
# $header = html_header($title);
-#
+#
# Print our HTML header and start the <body> block.
#######################################################################
sub html_header {
#######################################################################
# help();
-#
+#
# help();
-#
+#
# Display usage instructions and exit.
#######################################################################
sub help {
eximstats Version $VERSION
-Usage: eximstats [Options] mainlog1 mainlog2 ... > report.txt
- eximstats -html [Options] mainlog1 mainlog2 ... > report.html
- eximstats -merge [Options] report.1.txt report.2.txt ... > weekly_rep.txt
- eximstats -merge -html [Options] report.1.html ... > weekly_rep.html
+Usage:
+ eximstats [Output] [Options] mainlog1 mainlog2 ...
+ eximstats -merge -html [Options] report.1.html ... > weekly_rep.html
+
+Examples:
+ eximstats -html=eximstats.html mainlog1 mainlog2 ...
+ eximstats mainlog1 mainlog2 ... > report.txt
Parses exim mainlog or syslog files and generates a statistical analysis
-of the messages processed. Valid options are:
+of the messages processed.
+Valid output types are:
+-txt[=<file>] plain text (default unless no other type is specified)
+-html[=<file>] HTML
+-xls[=<file>] Excel
+With no type and file given, defaults to -txt and STDOUT.
+
+Valid options are:
-h<number> histogram divisions per hour. The default is 1, and
0 suppresses histograms. Other valid values are:
- 2, 3, 5, 10, 15, 20, 30 or 60.
+ 2, 3, 5, 10, 15, 20, 30 or 60.
-ne don't display error information
-nr don't display relaying information
-nr/pattern/ don't display relaying information that matches
-nt don't display transport information
-nt/pattern/ don't display transport information that matches
--nvr don't do volume rounding. Display in bytes, not KB/MB/GB.
--q<list> list of times for queuing information
- single 0 item suppresses
+-nvr don't do volume rounding. Display in bytes, not KB/MB/GB.
-t<number> display top <number> sources/destinations
default is 50, 0 suppresses top listing
-tnl omit local sources/destinations in top listing
-t_remote_users show top user sources/destinations from non-local domains
+-q<list> list of times for queuing information. -q0 suppresses.
+-show_rt<list> Show the receipt times for all the messages.
+-show_dt<list> Show the delivery times for all the messages.
+ <list> is an optional list of times in seconds.
+ Eg -show_rt1,2,4,8.
+
+-include_original_destination show both the final and original
+ destinations in the results rather than just the final ones.
--byhost show results by sending host (default unless bydomain or
+-byhost show results by sending host (default unless bydomain or
byemail is specified)
--bydomain show results by sending domain.
--byemail show results by sender's email address
--byedomain show results by sender's email domain
+-bydomain show results by sending domain.
+-byemail show results by sender's email address
+-byedomain show results by sender's email domain
-pattern "Description" /pattern/
Count lines matching specified patterns and show them in
- the results. It can be specified multiple times. Eg:
- -pattern 'Refused connections' '/refused connection/'
+ the results. It can be specified multiple times. Eg:
+ -pattern 'Refused connections' '/refused connection/'
-merge merge previously generated reports into a new report
--html output the results in HTML
--charts Create charts (this requires the GD::Graph modules)
+-charts Create charts (this requires the GD::Graph modules).
+ Only valid with -html.
-chartdir <dir> Create the charts' png files in the directory <dir>
-chartrel <dir> Specify the relative directory for the "img src=" tags
from where to include the charts in the html file
- -chartdir and -chartrel default to '.'
+ -chartdir and -chartrel default to '.'
+
+-emptyok It is OK if there is no valid input, don't print an error.
--d Debug mode - dump the eval'ed parser onto STDERR.
+-d Debug mode - dump the eval'ed parser onto STDERR.
EoText
#######################################################################
# generate_parser();
-#
+#
# $parser = generate_parser();
-#
+#
# This subroutine generates the parsing routine which will be
# used to parse the mainlog. We take the base operation, and remove bits not in use.
# This improves performance depending on what bits you take out or add.
-#
+#
# I've tested using study(), but this does not improve performance.
-#
+#
# We store our parsing routing in a variable, and process it looking for #IFDEF (Expression)
# or #IFNDEF (Expression) statements and corresponding #ENDIF (Expression) statements. If
# the expression evaluates to true, then it is included/excluded accordingly.
sub generate_parser {
my $parser = '
my($ip,$host,$email,$edomain,$domain,$thissize,$size,$old,$new);
- my($tod,$m_hour,$m_min,$id,$flag);
+ my($tod,$m_hour,$m_min,$id,$flag,$extra,$length);
+ my($seconds,$queued,$rcpt_time);
+ my $rej_id = 0;
while (<$fh>) {
# Convert syslog lines to mainlog format.
next unless s/^.*? exim\\b.*?: //;
}
- next if length($_) < 38;
- next unless /^(\\d{4}\\-\\d\\d-\\d\\d\\s(\\d\\d):(\\d\\d):\\d\\d( [-+]\\d\\d\\d\\d)?)/o;
+ $length = length($_);
+ next if ($length < 38);
+ next unless /^(\\d{4}\\-\\d\\d-\\d\\d\\s(\\d\\d):(\\d\\d):\\d\\d( [-+]\\d\\d\\d\\d)?)( \\[\\d+\\])?/o;
($tod,$m_hour,$m_min) = ($1,$2,$3);
- # PH
- my($extra) = defined($4)? 6 : 0;
+ # PH - watch for GMT offsets in the timestamp.
+ if (defined($4)) {
+ $extra = 6;
+ next if ($length < 44);
+ }
+ else {
+ $extra = 0;
+ }
+
+ # PH - watch for PID added after the timestamp.
+ if (defined($5)) {
+ $extra += length($5);
+ next if ($length < 38 + $extra);
+ }
+
$id = substr($_, 20 + $extra, 16);
$flag = substr($_, 37 + $extra, 2);
+
+ if ($flag !~ /^([<>=*-]+|SA)$/ && /rejected|refused|dropped/) {
+ $flag = "Re";
+ $extra -= 3;
+ }
+
+ # Rejects can have no MSGID...
+ if ($flag eq "Re" && $id !~ /^[-0-9a-zA-Z]+$/) {
+ $id = "reject:" . ++$rej_id;
+ $extra -= 17;
+ }
';
# Watch for user specified patterns.
my $user_pattern_index = 0;
foreach (@user_patterns) {
$user_pattern_totals[$user_pattern_index] = 0;
- $parser .= " \$user_pattern_totals[$user_pattern_index]++ if $_;\n";
+ $parser .= " if ($_) {\n";
+ $parser .= " \$user_pattern_totals[$user_pattern_index]++;\n";
+ $parser .= " \$user_pattern_interval_count[$user_pattern_index][(\$m_hour*60 + \$m_min)/$hist_interval]++;\n" if ($hist_opt > 0);
+ $parser .= " }\n";
$user_pattern_index++;
}
$parser .= '
- next unless ($flag =~ /<=|=>|->|==|\\*\\*|Co/);
-
- #Strip away the timestamp, ID and flag (which could be "Com" for completed)
- #This speeds up the later pattern matches.
- # $_ = substr($_, 40);
+ next unless ($flag =~ /<=|=>|->|==|\\*\\*|Co|SA|Re/);
+ #Strip away the timestamp, ID and flag to speed up later pattern matches.
+ #The flags include Co (Completed), Re (Rejected), and SA (SpamAssassin).
$_ = substr($_, 40 + $extra); # PH
+ # Alias @message to the array of information about the message.
+ # This minimises the number of calls to hash functions.
+ $messages{$id} = [] unless exists $messages{$id};
+ *message = $messages{$id};
+
+
# JN - Skip over certain transports as specified via the "-nt/.../" command
# line switch (where ... is a perl style regular expression). This is
# required so that transports that skew stats such as SpamAssassin can be
#ENDIF ($transport_pattern)
- $host = "local"; #Host is local unless otherwise specified.
- $domain = "localdomain"; #Domain is localdomain unless otherwise specified.
-
# Do some pattern matches to get the host and IP address.
# We expect lines to be of the form "H=[IpAddr]" or "H=Host [IpAddr]" or
# "H=Host (UnverifiedHost) [IpAddr]" or "H=(UnverifiedHost) [IpAddr]".
# We do 2 separate matches to keep the matches simple and fast.
- if (/\\sH=(\\S+)/) {
- $host = $1;
-
- ($ip) = /\\sH=.*?(\\s\\[[^]]+\\])/;
- # If there is only an IP address, it will be in $host and $ip will be
- # unset. That is OK, because we only use $ip in conjunction with $host
- # below. But make it empty to avoid warning messages.
- $ip = "" if !defined $ip;
-
- #IFDEF ($do_sender{Domain})
- if ($host !~ /^\\[/ && $host =~ /^(\\(?)[^\\.]+\\.([^\\.]+\\..*)/) {
- # Remove the host portion from the DNS name. We ensure that we end up with
- # at least xxx.yyy. $host can be "(x.y.z)" or "x.y.z".
- $domain = lc("$1.$2");
- $domain =~ s/^\\.//; #Remove preceding dot.
- }
- #ENDIF ($do_sender{Domain})
-
+ # Host is local unless otherwise specified.
+ $ip = (/\\bH=.*?(\\[[^]]+\\])/) ? $1 : "local";
+ $host = (/\\bH=(\\S+)/) ? $1 : "local";
+
+ $domain = "localdomain"; #Domain is localdomain unless otherwise specified.
+
+ #IFDEF ($do_sender{Domain})
+ if ($host !~ /^\\[/ && $host =~ /^(\\(?)[^\\.]+\\.([^\\.]+\\..*)/) {
+ # Remove the host portion from the DNS name. We ensure that we end up
+ # with at least xxx.yyy. $host can be "(x.y.z)" or "x.y.z".
+ $domain = lc("$1.$2");
+ $domain =~ s/^\\.//; #Remove preceding dot.
}
+ #ENDIF ($do_sender{Domain})
#IFDEF ($do_sender{Email})
- $email = (/^(\S+)/) ? $1 : "";
+ #IFDEF ($include_original_destination)
+ # Catch both "a@b.com <c@d.com>" and "e@f.com"
+ #$email = (/^(\S+) (<(\S*?)>)?/) ? $3 || $1 : "";
+ $email = (/^(\S+ (<[^@>]+@?[^>]*>)?)/) ? $1 : "";
+ chomp($email);
+ #ENDIF ($include_original_destination)
+
+ #IFNDEF ($include_original_destination)
+ $email = (/^(\S+)/) ? $1 : "";
+ #ENDIF ($include_original_destination)
#ENDIF ($do_sender{Email})
#IFDEF ($do_sender{Edomain})
- $edomain = (/^\S*?\\@(\S+)/) ? lc($1) : "";
+ #IFDEF ($include_original_destination)
+ #$edomain = (/^(\S+) (<\S*?\\@(\S+)>)?/) ? $3 || $1 : "";
+ $edomain = (/^(\S+ (<\S*?\\@(\S+?)>)?)/) ? $1 : "";
+ chomp($edomain);
+ lc($edomain);
+ #ENDIF ($include_original_destination)
+
+ #IFNDEF ($include_original_destination)
+ $edomain = (/^\S*?\\@(\S+)/) ? lc($1) : "";
+ #ENDIF ($include_original_destination)
#ENDIF ($do_sender{Edomain})
if ($tod lt $begin) {
if ($flag eq "<=") {
$thissize = (/\\sS=(\\d+)( |$)/) ? $1 : 0;
- $size{$id} = $thissize;
+ $message[$SIZE] = $thissize;
+ $message[$PROTOCOL] = (/ P=(\S+)/) ? $1 : undef;
#IFDEF ($show_relay)
if ($host ne "local") {
- # Save incoming information in case it becomes interesting
- # later, when delivery lines are read.
- my($from) = /^(\\S+)/;
- $from_host{$id} = "$host$ip";
- $from_address{$id} = $from;
+ # Save incoming information in case it becomes interesting
+ # later, when delivery lines are read.
+ my($from) = /^(\\S+)/;
+ $message[$FROM_HOST] = "$host$ip";
+ $message[$FROM_ADDRESS] = $from;
}
#ENDIF ($show_relay)
#IFDEF ($local_league_table || $include_remote_users)
- if (/\sU=(\\S+)/) {
- my $user = $1;
+ if (/\sU=(\\S+)/) {
+ my $user = $1;
- #IFDEF ($local_league_table && $include_remote_users)
- { #Store both local and remote users.
- #ENDIF ($local_league_table && $include_remote_users)
+ #IFDEF ($local_league_table && $include_remote_users)
+ { #Store both local and remote users.
+ #ENDIF ($local_league_table && $include_remote_users)
- #IFDEF ($local_league_table && ! $include_remote_users)
- if ($host eq "local") { #Store local users only.
- #ENDIF ($local_league_table && ! $include_remote_users)
+ #IFDEF ($local_league_table && ! $include_remote_users)
+ if ($host eq "local") { #Store local users only.
+ #ENDIF ($local_league_table && ! $include_remote_users)
- #IFDEF ($include_remote_users && ! $local_league_table)
- if ($host ne "local") { #Store remote users only.
- #ENDIF ($include_remote_users && ! $local_league_table)
+ #IFDEF ($include_remote_users && ! $local_league_table)
+ if ($host ne "local") { #Store remote users only.
+ #ENDIF ($include_remote_users && ! $local_league_table)
- $received_count_user{$user}++;
- add_volume(\\$received_data_user{$user},\\$received_data_gigs_user{$user},$thissize);
+ ++$received_count_user{$user};
+ add_volume(\\$received_data_user{$user},\\$received_data_gigs_user{$user},$thissize);
}
- }
+ }
#ENDIF ($local_league_table || $include_remote_users)
#IFDEF ($do_sender{Host})
- $received_count{Host}{$host}++;
- add_volume(\\$received_data{Host}{$host},\\$received_data_gigs{Host}{$host},$thissize);
+ ++$received_count{Host}{$host};
+ add_volume(\\$received_data{Host}{$host},\\$received_data_gigs{Host}{$host},$thissize);
#ENDIF ($do_sender{Host})
#IFDEF ($do_sender{Domain})
if ($domain) {
- $received_count{Domain}{$domain}++;
- add_volume(\\$received_data{Domain}{$domain},\\$received_data_gigs{Domain}{$domain},$thissize);
- }
+ ++$received_count{Domain}{$domain};
+ add_volume(\\$received_data{Domain}{$domain},\\$received_data_gigs{Domain}{$domain},$thissize);
+ }
#ENDIF ($do_sender{Domain})
#IFDEF ($do_sender{Email})
- $received_count{Email}{$email}++;
- add_volume(\\$received_data{Email}{$email},\\$received_data_gigs{Email}{$email},$thissize);
+ ++$received_count{Email}{$email};
+ add_volume(\\$received_data{Email}{$email},\\$received_data_gigs{Email}{$email},$thissize);
#ENDIF ($do_sender{Email})
#IFDEF ($do_sender{Edomain})
- $received_count{Edomain}{$edomain}++;
- add_volume(\\$received_data{Edomain}{$edomain},\\$received_data_gigs{Edomain}{$edomain},$thissize);
+ ++$received_count{Edomain}{$edomain};
+ add_volume(\\$received_data{Edomain}{$edomain},\\$received_data_gigs{Edomain}{$edomain},$thissize);
#ENDIF ($do_sender{Edomain})
- $total_received_count++;
+ ++$total_received_count;
add_volume(\\$total_received_data,\\$total_received_data_gigs,$thissize);
- #IFDEF ($#queue_times >= 0)
- $arrival_time{$id} = $tod;
- #ENDIF ($#queue_times >= 0)
+ #IFDEF ($#queue_times >= 0 || $#rcpt_times >= 0)
+ $message[$ARRIVAL_TIME] = $tod;
+ #ENDIF ($#queue_times >= 0 || $#rcpt_times >= 0)
#IFDEF ($hist_opt > 0)
- $received_interval_count[($m_hour*60 + $m_min)/$hist_interval]++;
+ $received_interval_count[($m_hour*60 + $m_min)/$hist_interval]++;
#ENDIF ($hist_opt > 0)
}
elsif ($flag eq "=>") {
- $size = $size{$id} || 0;
+ $size = $message[$SIZE] || 0;
if ($host ne "local") {
- $remote_delivered{$id} = 1;
+ $message[$REMOTE_DELIVERED] = 1;
#IFDEF ($show_relay)
# addresses, there may be a further address between the first
# and last.
- if (defined $from_host{$id}) {
+ if (defined $message[$FROM_HOST]) {
if (/^(\\S+)(?:\\s+\\([^)]\\))?\\s+<([^>]+)>/) {
($old,$new) = ($1,$2);
- }
+ }
else {
- $old = $new = "";
- }
+ $old = $new = "";
+ }
if ("\\L$new" eq "\\L$old") {
($old) = /^(\\S+)/ if $old eq "";
- my $key = "H=\\L$from_host{$id}\\E A=\\L$from_address{$id}\\E => " .
+ my $key = "H=\\L$message[$FROM_HOST]\\E A=\\L$message[$FROM_ADDRESS]\\E => " .
"H=\\L$host\\E$ip A=\\L$old\\E";
if (!defined $relay_pattern || $key !~ /$relay_pattern/o) {
$relayed{$key} = 0 if !defined $relayed{$key};
- $relayed{$key}++;
- }
+ ++$relayed{$key};
+ }
else {
- $relayed_unshown++
+ ++$relayed_unshown;
}
}
}
}
#IFDEF ($local_league_table || $include_remote_users)
- #IFDEF ($local_league_table && $include_remote_users)
- { #Store both local and remote users.
- #ENDIF ($local_league_table && $include_remote_users)
-
- #IFDEF ($local_league_table && ! $include_remote_users)
- if ($host eq "local") { #Store local users only.
- #ENDIF ($local_league_table && ! $include_remote_users)
-
- #IFDEF ($include_remote_users && ! $local_league_table)
- if ($host ne "local") { #Store remote users only.
- #ENDIF ($include_remote_users && ! $local_league_table)
-
- if (my($user) = split((/\\s</)? " <" : " ", $_)) {
- if ($user =~ /^[\\/|]/) {
- my($parent) = $_ =~ /(<[^@]+@?[^>]*>)/;
- $user = "$user $parent" if defined $parent;
- }
- $delivered_count_user{$user}++;
- add_volume(\\$delivered_data_user{$user},\\$delivered_data_gigs_user{$user},$size);
- }
- }
+ #IFDEF ($local_league_table && $include_remote_users)
+ { #Store both local and remote users.
+ #ENDIF ($local_league_table && $include_remote_users)
+
+ #IFDEF ($local_league_table && ! $include_remote_users)
+ if ($host eq "local") { #Store local users only.
+ #ENDIF ($local_league_table && ! $include_remote_users)
+
+ #IFDEF ($include_remote_users && ! $local_league_table)
+ if ($host ne "local") { #Store remote users only.
+ #ENDIF ($include_remote_users && ! $local_league_table)
+
+ if (my($user) = split((/\\s</)? " <" : " ", $_)) {
+ #IFDEF ($include_original_destination)
+ {
+ #ENDIF ($include_original_destination)
+ #IFNDEF ($include_original_destination)
+ if ($user =~ /^[\\/|]/) {
+ #ENDIF ($include_original_destination)
+ my($parent) = $_ =~ /(<[^@]+@?[^>]*>)/;
+ $user = "$user $parent" if defined $parent;
+ }
+ ++$delivered_messages_user{$user};
+ ++$delivered_addresses_user{$user};
+ add_volume(\\$delivered_data_user{$user},\\$delivered_data_gigs_user{$user},$size);
+ }
+ }
#ENDIF ($local_league_table || $include_remote_users)
#IFDEF ($do_sender{Host})
- $delivered_count{Host}{$host}++;
- add_volume(\\$delivered_data{Host}{$host},\\$delivered_data_gigs{Host}{$host},$size);
+ $delivered_messages{Host}{$host}++;
+ $delivered_addresses{Host}{$host}++;
+ add_volume(\\$delivered_data{Host}{$host},\\$delivered_data_gigs{Host}{$host},$size);
#ENDIF ($do_sender{Host})
#IFDEF ($do_sender{Domain})
if ($domain) {
- $delivered_count{Domain}{$domain}++;
- add_volume(\\$delivered_data{Domain}{$domain},\\$delivered_data_gigs{Domain}{$domain},$size);
- }
+ ++$delivered_messages{Domain}{$domain};
+ ++$delivered_addresses{Domain}{$domain};
+ add_volume(\\$delivered_data{Domain}{$domain},\\$delivered_data_gigs{Domain}{$domain},$size);
+ }
#ENDIF ($do_sender{Domain})
#IFDEF ($do_sender{Email})
- $delivered_count{Email}{$email}++;
- add_volume(\\$delivered_data{Email}{$email},\\$delivered_data_gigs{Email}{$email},$size);
+ ++$delivered_messages{Email}{$email};
+ ++$delivered_addresses{Email}{$email};
+ add_volume(\\$delivered_data{Email}{$email},\\$delivered_data_gigs{Email}{$email},$size);
#ENDIF ($do_sender{Email})
#IFDEF ($do_sender{Edomain})
- $delivered_count{Edomain}{$edomain}++;
- add_volume(\\$delivered_data{Edomain}{$edomain},\\$delivered_data_gigs{Edomain}{$edomain},$size);
+ ++$delivered_messages{Edomain}{$edomain};
+ ++$delivered_addresses{Edomain}{$edomain};
+ add_volume(\\$delivered_data{Edomain}{$edomain},\\$delivered_data_gigs{Edomain}{$edomain},$size);
#ENDIF ($do_sender{Edomain})
- $total_delivered_count++;
+ ++$total_delivered_messages;
+ ++$total_delivered_addresses;
add_volume(\\$total_delivered_data,\\$total_delivered_data_gigs,$size);
#IFDEF ($show_transport)
my $transport = (/\\sT=(\\S+)/) ? $1 : ":blackhole:";
- $transported_count{$transport}++;
+ ++$transported_count{$transport};
add_volume(\\$transported_data{$transport},\\$transported_data_gigs{$transport},$size);
#ENDIF ($show_transport)
$delivered_interval_count[($m_hour*60 + $m_min)/$hist_interval]++;
#ENDIF ($hist_opt > 0)
+ #IFDEF ($#delivery_times > 0)
+ if (/ DT=(\S+)/) {
+ $seconds = wdhms_seconds($1);
+ for ($i = 0; $i <= $#delivery_times; $i++) {
+ if ($seconds < $delivery_times[$i]) {
+ ++$dt_all_bin[$i];
+ ++$dt_remote_bin[$i] if $message[$REMOTE_DELIVERED];
+ last;
+ }
+ }
+ if ($i > $#delivery_times) {
+ ++$dt_all_overflow;
+ ++$dt_remote_overflow if $message[$REMOTE_DELIVERED];
+ }
+ }
+ #ENDIF ($#delivery_times > 0)
+
+ }
+
+ elsif ($flag eq "->") {
+
+ #IFDEF ($local_league_table || $include_remote_users)
+ #IFDEF ($local_league_table && $include_remote_users)
+ { #Store both local and remote users.
+ #ENDIF ($local_league_table && $include_remote_users)
+
+ #IFDEF ($local_league_table && ! $include_remote_users)
+ if ($host eq "local") { #Store local users only.
+ #ENDIF ($local_league_table && ! $include_remote_users)
+
+ #IFDEF ($include_remote_users && ! $local_league_table)
+ if ($host ne "local") { #Store remote users only.
+ #ENDIF ($include_remote_users && ! $local_league_table)
+
+ if (my($user) = split((/\\s</)? " <" : " ", $_)) {
+ #IFDEF ($include_original_destination)
+ {
+ #ENDIF ($include_original_destination)
+ #IFNDEF ($include_original_destination)
+ if ($user =~ /^[\\/|]/) {
+ #ENDIF ($include_original_destination)
+ my($parent) = $_ =~ /(<[^@]+@?[^>]*>)/;
+ $user = "$user $parent" if defined $parent;
+ }
+ ++$delivered_addresses_user{$user};
+ }
+ }
+ #ENDIF ($local_league_table || $include_remote_users)
+
+ #IFDEF ($do_sender{Host})
+ $delivered_addresses{Host}{$host}++;
+ #ENDIF ($do_sender{Host})
+ #IFDEF ($do_sender{Domain})
+ if ($domain) {
+ ++$delivered_addresses{Domain}{$domain};
+ }
+ #ENDIF ($do_sender{Domain})
+ #IFDEF ($do_sender{Email})
+ ++$delivered_addresses{Email}{$email};
+ #ENDIF ($do_sender{Email})
+ #IFDEF ($do_sender{Edomain})
+ ++$delivered_addresses{Edomain}{$edomain};
+ #ENDIF ($do_sender{Edomain})
+
+ ++$total_delivered_addresses;
}
- elsif ($flag eq "==" && defined($size{$id}) && !defined($delayed{$id})) {
- $delayed_count++;
- $delayed{$id} = 1;
+ elsif ($flag eq "==" && defined($message[$SIZE]) && !defined($message[$DELAYED])) {
+ ++$delayed_count;
+ $message[$DELAYED] = 1;
}
elsif ($flag eq "**") {
- $had_error{$id} = 1 if defined ($size{$id});
+ if (defined ($message[$SIZE])) {
+ unless (defined $message[$HAD_ERROR]) {
+ ++$message_errors;
+ $message[$HAD_ERROR] = 1;
+ }
+ }
#IFDEF ($show_errors)
- $errors_count{$_}++;
+ ++$errors_count{$_};
#ENDIF ($show_errors)
}
elsif ($flag eq "Co") {
#Completed?
#IFDEF ($#queue_times >= 0)
- #Note: id_seconds() benchmarks as 42% slower than seconds() and computing
- #the time accounts for a significant portion of the run time.
- my($queued);
- if (defined $arrival_time{$id}) {
- $queued = seconds($tod) - seconds($arrival_time{$id});
- delete($arrival_time{$id});
- }
- else {
- $queued = seconds($tod) - id_seconds($id);
- }
+ $queued = queue_time($tod, $message[$ARRIVAL_TIME], $id);
for ($i = 0; $i <= $#queue_times; $i++) {
if ($queued < $queue_times[$i]) {
- $queue_bin[$i]++;
- $remote_queue_bin[$i]++ if $remote_delivered{$id};
+ ++$qt_all_bin[$i];
+ ++$qt_remote_bin[$i] if $message[$REMOTE_DELIVERED];
last;
- }
- }
- $queue_more_than++ if $i > $#queue_times;
+ }
+ }
+ if ($i > $#queue_times) {
+ ++$qt_all_overflow;
+ ++$qt_remote_overflow if $message[$REMOTE_DELIVERED];
+ }
#ENDIF ($#queue_times >= 0)
- #IFDEF ($show_relay)
- delete($from_host{$id});
- delete($from_address{$id});
- #ENDIF ($show_relay)
+ #IFDEF ($#rcpt_times >= 0)
+ if (/ QT=(\S+)/) {
+ $seconds = wdhms_seconds($1);
+ #Calculate $queued if not previously calculated above.
+ #IFNDEF ($#queue_times >= 0)
+ $queued = queue_time($tod, $message[$ARRIVAL_TIME], $id);
+ #ENDIF ($#queue_times >= 0)
+ $rcpt_time = $seconds - $queued;
+ my($protocol);
+
+ if (defined $message[$PROTOCOL]) {
+ $protocol = $message[$PROTOCOL];
+
+ # Create the bin if its not already defined.
+ unless (exists $rcpt_times_bin{$protocol}) {
+ initialise_rcpt_times($protocol);
+ }
+ }
+
+
+ for ($i = 0; $i <= $#rcpt_times; ++$i) {
+ if ($rcpt_time < $rcpt_times[$i]) {
+ ++$rcpt_times_bin{all}[$i];
+ ++$rcpt_times_bin{$protocol}[$i] if defined $protocol;
+ last;
+ }
+ }
+
+ if ($i > $#rcpt_times) {
+ ++$rcpt_times_overflow{all};
+ ++$rcpt_times_overflow{$protocol} if defined $protocol;
+ }
+ }
+ #ENDIF ($#rcpt_times >= 0)
+
+ delete($messages{$id});
+ }
+ elsif ($flag eq "SA") {
+ $ip = (/From.*?(\\[[^]]+\\])/ || /\\((local)\\)/) ? $1 : "";
+ #SpamAssassin message
+ if (/Action: ((permanently|temporarily) rejected message|flagged as Spam but accepted): score=(\d+\.\d)/) {
+ #add_volume(\\$spam_score,\\$spam_score_gigs,$3);
+ ++$spam_count_by_ip{$ip};
+ } elsif (/Action: scanned but message isn\'t spam: score=(-?\d+\.\d)/) {
+ #add_volume(\\$ham_score,\\$ham_score_gigs,$1);
+ ++$ham_count_by_ip{$ip};
+ } elsif (/(Not running SA because SAEximRunCond expanded to false|check skipped due to message size)/) {
+ ++$ham_count_by_ip{$ip};
+ }
+ }
+ # Look for Reject messages or blackholed messages (deliveries
+ # without a transport)
+ if ($flag eq "Re" || ($flag eq "=>" && ! /\\sT=\\S+/)) {
+ # Correct the IP address for rejects:
+ # rejected EHLO from my.test.net [10.0.0.5]: syntactically invalid argument(s):
+ # rejected EHLO from [10.0.0.6]: syntactically invalid argument(s):
+ $ip = $1 if ($ip eq "local" && /^rejected [HE][HE]LO from .*?(\[.+?\]):/);
+ ++$rejected_count_by_ip{$ip};
+ if (/SpamAssassin/) {
+ ++$rejected_count_by_reason{"Rejected by SpamAssassin"};
+ }
+ elsif (
+ /(listed at [^ ]+)/ ||
+ /(Forged IP detected in HELO)/ ||
+ /(Invalid domain or IP given in HELO\/EHLO)/ ||
+ /(unqualified recipient rejected)/ ||
+ /(closed connection (after|in response) .*?)\s*$/ ||
+ /(sender rejected)/ ||
+ # 2005-09-23 15:07:49 1EInHJ-0007Ex-Au H=(a.b.c) [10.0.0.1] F=<> rejected after DATA: This message contains a virus: (Eicar-Test-Signature) please scan your system.
+ # 2005-10-06 10:50:07 1ENRS3-0000Nr-Kt => blackhole (DATA ACL discarded recipients): This message contains a virus: (Worm.SomeFool.P) please scan your system.
+ / rejected after DATA: (.*)/ ||
+ /.DATA ACL discarded recipients.: (.*)/ ||
+ /rejected after DATA: (unqualified address not permitted)/ ||
+ /(VRFY rejected)/ ||
+# /(sender verify (defer|fail))/i ||
+ /(too many recipients)/ ||
+ /(refused relay.*?) to/ ||
+ /(rejected by non-SMTP ACL: .*)/ ||
+ /(rejected by local_scan.*)/ ||
+ # SMTP call from %s dropped: too many syntax or protocol errors (last command was "%s"
+ # SMTP call from %s dropped: too many nonmail commands
+ /(dropped: too many ((nonmail|unrecognized) commands|syntax or protocol errors))/ ||
+
+ # local_scan() function crashed with signal %d - message temporarily rejected
+ # local_scan() function timed out - message temporarily rejected
+ /(local_scan.. function .* - message temporarily rejected)/ ||
+ /(temporarily refused connection)/ ||
+ # SMTP protocol synchronization error (input sent without waiting for greeting): rejected connection from %s
+ /(SMTP protocol .*?(error|violation))/ ||
+ /(message too big)/
+ ) {
+ ++$rejected_count_by_reason{"\u$1"};
+ }
+ elsif (/rejected [HE][HE]LO from [^:]*: syntactically invalid argument/) {
+ ++$rejected_count_by_reason{"Rejected HELO/EHLO: syntactically invalid argument"};
+ }
+ elsif (/response to "RCPT TO.*? was: (.*)/) {
+ ++$rejected_count_by_reason{"Response to RCPT TO was: $1"};
+ }
+ elsif (
+ /(lookup of host )\S+ (failed)/ ||
+
+ # rejected from <%s>%s%s%s%s: message too big:
+ /(rejected [A-Z]*) .*?(: .*?)(:|\s*$)/ ||
+ # refused connection from %s (host_reject_connection)
+ # refused connection from %s (tcp wrappers)
+ /(refused connection )from.*? (\(.*)/ ||
+
+ # error from remote mailer after RCPT TO:<a@b.c>: host a.b.c [10.0.0.1]: 450 <a@b.c>: Recipient address rejected: Greylisted for 60 seconds
+ # error from remote mailer after MAIL FROM:<> SIZE=3468: host a.b.c [10.0.0.1]: 421 a.b.c has refused your connection because your server did not have a PTR record.
+ /(error from remote mailer after .*?:).*(: .*?)(:|\s*$)/ ||
+
+ # a.b.c F=<a@b.c> rejected after DATA: "@" or "." expected after "Undisclosed-Recipient": failing address in "To" header is: <Undisclosed-Recipient:;>
+ /rejected after DATA: ("." or "." expected).*?(: failing address in .*? header)/ ||
+
+ # connection from %s refused load average = %.2f
+ /(Connection )from.*? (refused: load average)/ ||
+ # connection from %s refused (IP options)
+ # Connection from %s refused: too many connections
+ # connection from %s refused
+ /([Cc]onnection )from.*? (refused.*)/ ||
+ # [10.0.0.1]: connection refused
+ /: (Connection refused)()/
+ ) {
+ ++$rejected_count_by_reason{"\u$1$2"};
+ }
+ else {
+ ++$rejected_count_by_reason{Unknown};
+ print STDERR "Unknown rejection: $_" if $debug;
+ }
}
}';
my(%defines_in_operation,$removing_lines,$processed_parser);
foreach (split (/\n/,$parser)) {
if ((/^\s*#\s*IFDEF\s*\((.*?)\)/i && ! eval $1) ||
- (/^\s*#\s*IFNDEF\s*\((.*?)\)/i && eval $1) ) {
+ (/^\s*#\s*IFNDEF\s*\((.*?)\)/i && eval $1) ) {
$defines_in_operation{$1} = 1;
$removing_lines = 1;
}
+ # Convert constants.
+ while (/(\$[A-Z][A-Z_]*)\b/) {
+ my $constant = eval $1;
+ s/(\$[A-Z][A-Z_]*)\b/$constant/;
+ }
+
$processed_parser .= $_."\n" unless $removing_lines;
if (/^\s*#\s*ENDIF\s*\((.*?)\)/i) {
delete $defines_in_operation{$1};
unless (keys %defines_in_operation) {
- $removing_lines = 0;
+ $removing_lines = 0;
}
}
}
- print STDERR "# START OF PARSER:\n$processed_parser\n# END OF PARSER\n\n" if $debug;
+ print STDERR "# START OF PARSER:$processed_parser\n# END OF PARSER\n\n" if $debug;
return $processed_parser;
}
#######################################################################
# parse();
-#
+#
# parse($parser,\*FILEHANDLE);
-#
+#
# This subroutine accepts a parser and a filehandle from main and parses each
# line. We store the results into global variables.
#######################################################################
#######################################################################
# print_header();
-#
+#
# print_header();
-#
+#
# Print our headers and contents.
#######################################################################
sub print_header {
+
my $title = "Exim statistics from $begin to $end";
- if ($html) {
- print html_header($title);
- print "<ul>\n";
- print "<li><a href=\"#grandtotal\">Grand total summary</a>\n";
- print "<li><a href=\"#patterns\">User Specified Patterns</a>\n" if @user_patterns;
- print "<li><a href=\"#transport\">Deliveries by Transport</a>\n" if $show_transport;
+ print $txt_fh "\n$title\n" if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh html_header($title);
+ print $htm_fh "<ul>\n";
+ print $htm_fh "<li><a href=\"#grandtotal\">Grand total summary</a>\n";
+ print $htm_fh "<li><a href=\"#patterns\">User Specified Patterns</a>\n" if @user_patterns;
+ print $htm_fh "<li><a href=\"#transport\">Deliveries by Transport</a>\n" if $show_transport;
if ($hist_opt) {
- print "<li><a href=\"#Messages received\">Messages received per hour</a>\n";
- print "<li><a href=\"#Deliveries\">Deliveries per hour</a>\n";
+ print
$htm_fh "<li><a href=\"#Messages received\">Messages received per hour</a>\n";
+ print
$htm_fh "<li><a href=\"#Deliveries\">Deliveries per hour</a>\n";
}
+
if ($#queue_times >= 0) {
- print "<li><a href=\"#all messages time\">Time spent on the queue: all messages</a>\n";
- print "<li><a href=\"#messages with at least one remote delivery time\">Time spent on the queue: messages with at least one remote delivery</a>\n";
+ print $htm_fh "<li><a href=\"#Time spent on the queue all messages\">Time spent on the queue: all messages</a>\n";
+ print $htm_fh "<li><a href=\"#Time spent on the queue messages with at least one remote delivery\">Time spent on the queue: messages with at least one remote delivery</a>\n";
}
- print "<li><a href=\"#Relayed messages\">Relayed messages</a>\n" if $show_relay;
+
+ if ($#delivery_times >= 0) {
+ print $htm_fh "<li><a href=\"#Delivery times all messages\">Delivery times: all messages</a>\n";
+ print $htm_fh "<li><a href=\"#Delivery times messages with at least one remote delivery\">Delivery times: messages with at least one remote delivery</a>\n";
+ }
+
+ if ($#rcpt_times >= 0) {
+ print $htm_fh "<li><a href=\"#Receipt times all messages\">Receipt times</a>\n";
+ }
+
+ print $htm_fh "<li><a href=\"#Relayed messages\">Relayed messages</a>\n" if $show_relay;
if ($topcount) {
+ print $htm_fh "<li><a href=\"#mail rejection reason count\">Top $topcount mail rejection reasons by message count</a>\n" if %rejected_count_by_reason;
foreach ('Host','Domain','Email','Edomain') {
- next unless $do_sender{$_};
-
print "<li><a href=\"#sending \l$_ count\">Top $topcount sending \l${_}s by message count</a>\n";
-
print "<li><a href=\"#sending \l$_ volume\">Top $topcount sending \l${_}s by volume</a>\n";
+ next unless $do_sender{$_};
+
print $htm_fh "<li><a href=\"#sending \l$_ count\">Top $topcount sending \l${_}s by message count</a>\n";
+
print $htm_fh "<li><a href=\"#sending \l$_ volume\">Top $topcount sending \l${_}s by volume</a>\n";
}
- if ($local_league_table || $include_remote_users) {
-
print "<li><a href=\"#local sender count\">Top $topcount local senders by message count</a>\n";
-
print "<li><a href=\"#local sender volume\">Top $topcount local senders by volume</a>\n";
+ if (($local_league_table || $include_remote_users) && %received_count_user) {
+
print $htm_fh "<li><a href=\"#local sender count\">Top $topcount local senders by message count</a>\n";
+
print $htm_fh "<li><a href=\"#local sender volume\">Top $topcount local senders by volume</a>\n";
}
foreach ('Host','Domain','Email','Edomain') {
- next unless $do_sender{$_};
-
print "<li><a href=\"#\l$_ destination count\">Top $topcount \l$_ destinations by message count</a>\n";
-
print "<li><a href=\"#\l$_ destination volume\">Top $topcount \l$_ destinations by volume</a>\n";
+ next unless $do_sender{$_};
+
print $htm_fh "<li><a href=\"#\l$_ destination count\">Top $topcount \l$_ destinations by message count</a>\n";
+
print $htm_fh "<li><a href=\"#\l$_ destination volume\">Top $topcount \l$_ destinations by volume</a>\n";
}
- if ($local_league_table || $include_remote_users) {
-
print "<li><a href=\"#local destination count\">Top $topcount local destinations by message count</a>\n";
-
print "<li><a href=\"#local destination volume\">Top $topcount local destinations by volume</a>\n";
+ if (($local_league_table || $include_remote_users) && %delivered_messages_user) {
+
print $htm_fh "<li><a href=\"#local destination count\">Top $topcount local destinations by message count</a>\n";
+
print $htm_fh "<li><a href=\"#local destination volume\">Top $topcount local destinations by volume</a>\n";
}
- }
- print "<li><a href=\"#errors\">List of errors</a>\n" if %errors_count;
- print "</ul>\n<hr>\n";
+ print $htm_fh "<li><a href=\"#rejected ip count\">Top $topcount rejected ips by message count</a>\n" if %rejected_count_by_ip;
+ print $htm_fh "<li><a href=\"#non-rejected spamming ip count\">Top $topcount non-rejected spamming ips by message count</a>\n" if %spam_count_by_ip;
+
+ }
+ print $htm_fh "<li><a href=\"#errors\">List of errors</a>\n" if %errors_count;
+ print $htm_fh "</ul>\n<hr>\n";
}
- else {
- print "\n$title\n";
+ if ($xls_fh)
+ {
+ $ws_global->write($row++, $col+0, "Exim Statistics", $f_header1);
+ &set_worksheet_line($ws_global, $row, $col, ["from:", $begin, "to:", $end], $f_default);
+ $row+=2;
}
}
#######################################################################
# print_grandtotals();
-#
+#
# print_grandtotals();
-#
+#
# Print the grand totals.
#######################################################################
sub print_grandtotals {
# Get the sender by headings and results. This is complicated as we can have
# different numbers of columns.
- my($sender_txt_header,$sender_html_header,$sender_txt_format,$sender_html_format);
+ my($sender_txt_header,$sender_txt_format,$sender_html_format);
my(@received_totals,@delivered_totals);
+ my($row_tablehead, $row_max);
+ my(@col_headers) = ('TOTAL', 'Volume', 'Messages', 'Addresses');
+
foreach ('Host','Domain','Email','Edomain') {
next unless $do_sender{$_};
if ($merge_reports) {
push(@received_totals,scalar(keys %{$received_data{$_}}));
push(@delivered_totals,scalar(keys %{$delivered_data{$_}}));
}
- $sender_html_header .= "<th>${_}s</th>";
$sender_txt_header .= " " x ($COLUMN_WIDTHS - length($_)) . $_ . 's';
$sender_html_format .= "<td align=\"right\">%d</td>";
$sender_txt_format .= " " x ($COLUMN_WIDTHS - 5) . "%6d";
+ push(@col_headers,"${_}s");
}
- my($format1,$format2);
- if ($html) {
- print << "EoText";
-<a name="grandtotal"></a>
-<h2>Grand total summary</h2>
-<table border=1>
-<tr><th>TOTAL</th><th>Volume</th><th>Messages</th>$sender_html_header<th colspan=2>At least one addr<br>Delayed</th><th colspan=2>At least one addr<br>Failed</th>
-EoText
+ my $txt_format1 = " %-16s %9s %6d %6s $sender_txt_format";
+ my $txt_format2 = " %6d %4.1f%% %6d %4.1f%%",
+ my $htm_format1 = "<tr><td>%s</td><td align=\"right\">%s</td><td align=\"right\">%s</td><td align=\"right\">%s</td>$sender_html_format";
+ my $htm_format2 = "<td align=\"right\">%d</td><td align=\"right\">%4.1f%%</td><td align=\"right\">%d</td><td align=\"right\">%4.1f%%</td>";
- $format1 = "<tr><td>%s</td><td align=\"right\">%s</td>$sender_html_format<td align=\"right\">%d</td>";
- $format2 = "<td align=\"right\">%d</td><td align=\"right\">%4.1f%%</td><td align=\"right\">%d</td><td align=\"right\">%4.1f%%</td>";
- }
- else {
+ if ($txt_fh) {
my $sender_spaces = " " x length($sender_txt_header);
- print << "EoText";
-
-Grand total summary
--------------------
- $sender_spaces At least one address
- TOTAL Volume Messages $sender_txt_header Delayed Failed
-EoText
- $format1 = " %-16s %9s %6d $sender_txt_format";
- $format2 = " %6d %4.1f%% %6d %4.1f%%",
+ print $txt_fh "\n";
+ print $txt_fh "Grand total summary\n";
+ print $txt_fh "-------------------\n";
+ print $txt_fh " $sender_spaces At least one address\n";
+ print $txt_fh " TOTAL Volume Messages Addresses $sender_txt_header Delayed Failed\n";
}
+ if ($htm_fh) {
+ print $htm_fh "<a name=\"grandtotal\"></a>\n";
+ print $htm_fh "<h2>Grand total summary</h2>\n";
+ print $htm_fh "<table border=1>\n";
+ print $htm_fh "<tr><th>" . join('</th><th>',@col_headers) . "</th><th colspan=2>At least one addr<br>Delayed</th><th colspan=2>At least one addr<br>Failed</th>\n";
+ }
+ if ($xls_fh) {
+ $ws_global->write($row++, 0, "Grand total summary", $f_header2);
+ $ws_global->write($row, 0, \@col_headers, $f_header2);
+ $ws_global->merge_range($row, scalar(@col_headers), $row, scalar(@col_headers)+1, "At least one addr Delayed", $f_header2_m);
+ $ws_global->merge_range($row, scalar(@col_headers)+2, $row, scalar(@col_headers)+3, "At least one addr Failed", $f_header2_m);
+ #$ws_global->write(++$row, scalar(@col_headers), ['Total','Percent','Total','Percent'], $f_header2);
+ }
+
my($volume,$failed_count);
if ($merge_reports) {
}
else {
$volume = volume_rounded($total_received_data, $total_received_data_gigs);
- $failed_count = keys %had_error;
+ $failed_count = $message_errors;
}
{
no integer;
- printf("$format1$format2\n",'Received',$volume,$total_received_count,
- @received_totals,$delayed_count,
- ($total_received_count) ? ($delayed_count*100/$total_received_count) : 0,
- $failed_count,
- ($total_received_count) ? ($failed_count*100/$total_received_count) : 0);
+
+ my @content=(
+ $volume,$total_received_count,'',
+ @received_totals,
+ $delayed_count,
+ ($total_received_count) ? ($delayed_count*100/$total_received_count) : 0,
+ $failed_count,
+ ($total_received_count) ? ($failed_count*100/$total_received_count) : 0
+ );
+
+ printf $txt_fh ("$txt_format1$txt_format2\n", 'Received', @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1$htm_format2\n", 'Received', @content) if $htm_fh;
+ if ($xls_fh) {
+ $ws_global->write(++$row, 0, 'Received', $f_default);
+ for (my $i=0; $i < scalar(@content); $i++) {
+ if ($i == 4 || $i == 6) {
+ $ws_global->write($row, $i+1, $content[$i]/100, $f_percent);
+ }
+ else {
+ $ws_global->write($row, $i+1, $content[$i], $f_default);
+ }
+ }
+ }
}
if ($merge_reports) {
$volume = volume_rounded($report_totals{Delivered}{Volume}, $report_totals{Delivered}{'Volume-gigs'});
- $total_delivered_count = get_report_total($report_totals{Delivered},'Messages');
+ $total_delivered_messages = get_report_total($report_totals{Delivered},'Messages');
+ $total_delivered_addresses = get_report_total($report_totals{Delivered},'Addresses');
}
else {
$volume = volume_rounded($total_delivered_data, $total_delivered_data_gigs);
}
- printf("$format1\n\n",'Delivered',$volume,$total_delivered_count,@delivered_totals);
- print "</table>\n" if $html;
+
+ my @content=($volume, $total_delivered_messages, $total_delivered_addresses, @delivered_totals);
+ printf $txt_fh ("$txt_format1\n", 'Delivered', @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n", 'Delivered', @content) if $htm_fh;
+
+ if ($xls_fh) {
+ $ws_global->write(++$row, 0, 'Delivered', $f_default);
+ for (my $i=0; $i < scalar(@content); $i++) {
+ $ws_global->write($row, $i+1, $content[$i], $f_default);
+ }
+ }
+
+ if ($merge_reports) {
+ foreach ('Rejects', 'Ham', 'Spam') {
+ my $messages = get_report_total($report_totals{$_},'Messages');
+ my $addresses = get_report_total($report_totals{$_},'Addresses');
+ if ($messages) {
+ @content = ($_, '', $messages, '');
+ push(@content,get_report_total($report_totals{$_},'Hosts')) if $do_sender{Host};
+ printf $txt_fh ("$txt_format1\n", @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n", @content) if $htm_fh;
+ $ws_global->write(++$row, 0, \@content) if $xls_fh;
+ }
+ }
+ }
+ else {
+ foreach my $total_aref (['Rejects',\%rejected_count_by_ip],
+ ['Ham',\%ham_count_by_ip],
+ ['Spam',\%spam_count_by_ip]) {
+ my $messages = 0;
+ map {$messages += $_} values %{$total_aref->[1]};
+
+ if ($messages > 0) {
+ @content = ($total_aref->[0], '', $messages, '');
+ push(@content,scalar(keys %{$total_aref->[1]})) if $do_sender{Host};
+
+ printf $txt_fh ("$txt_format1\n", @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n", @content) if $htm_fh;
+ $ws_global->write(++$row, 0, \@content) if $xls_fh;
+ }
+ }
+ }
+
+ printf $txt_fh "\n" if $txt_fh;
+ printf $htm_fh "</table>\n" if $htm_fh;
+ ++$row;
}
#######################################################################
# print_user_patterns()
-#
+#
# print_user_patterns();
-#
+#
# Print the counts of user specified patterns.
#######################################################################
sub print_user_patterns {
- my($format1);
+ my $txt_format1 = " %-18s %6d";
+ my $htm_format1 = "<tr><td>%s</td><td align=\"right\">%d</td>";
- if ($html) {
- print "<hr><a name=\"patterns\"></a><h2>User Specified Patterns</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td>\n";
- print "<table border=1>\n";
- print "<tr><th> </th><th>Total</th>\n";
- $format1 = "<tr><td>%s</td><td align=\"right\">%d</td>";
+ if ($txt_fh) {
+ print $txt_fh "User Specified Patterns\n";
+ print $txt_fh "-----------------------";
+ print $txt_fh "\n Total\n";
}
- else {
- print "User Specified Patterns\n";
- print "-----------------------";
- print "\n Total\n";
- $format1 = " %-18s %6d";
+ if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"patterns\"></a><h2>User Specified Patterns</h2>\n";
+ print $htm_fh "<table border=0 width=\"100%\">\n";
+ print $htm_fh "<tr><td>\n";
+ print $htm_fh "<table border=1>\n";
+ print $htm_fh "<tr><th> </th><th>Total</th>\n";
}
+ if ($xls_fh) {
+ $ws_global->write($row++, $col, "User Specified Patterns", $f_header2);
+ &set_worksheet_line($ws_global, $row++, 1, ["Total"], $f_headertab);
+ }
+
my($key);
if ($merge_reports) {
# We are getting our data from previous reports.
foreach $key (@user_descriptions) {
my $count = get_report_total($report_totals{patterns}{$key},'Total');
- printf("$format1\n",$key,$count);
+ printf $txt_fh ("$txt_format1\n",$key,$count) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n",$key,$count) if $htm_fh;
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_global, $row++, 0, [$key,$count], $f_default);
+ }
}
}
else {
# We are getting our data from mainlog files.
my $user_pattern_index = 0;
foreach $key (@user_descriptions) {
- printf("$format1\n",$key,$user_pattern_totals[$user_pattern_index]);
+ printf $txt_fh ("$txt_format1\n",$key,$user_pattern_totals[$user_pattern_index]) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n",$key,$user_pattern_totals[$user_pattern_index]) if $htm_fh;
+ $ws_global->write($row++, 0, [$key,$user_pattern_totals[$user_pattern_index]]) if $xls_fh;
$user_pattern_index++;
}
}
- if ($html) {
- print "</table>\n";
+ print $txt_fh "\n" if $txt_fh;
+ print $htm_fh "</table>\n\n" if $htm_fh;
+ if ($xls_fh)
+ {
+ ++$row;
+ }
+
+ if ($hist_opt > 0) {
+ my $user_pattern_index = 0;
+ foreach $key (@user_descriptions) {
+ print_histogram($key, 'occurence', @{$user_pattern_interval_count[$user_pattern_index]});
+ $user_pattern_index++;
+ }
}
- print "\n";
}
+#######################################################################
+# print_rejects()
+#
+# print_rejects();
+#
+# Print statistics about rejected mail.
+#######################################################################
+sub print_rejects {
+ my($format1,$reason);
+
+ my $txt_format1 = " %-40s %6d";
+ my $htm_format1 = "<tr><td>%s</td><td align=\"right\">%d</td>";
+
+ if ($txt_fh) {
+ print $txt_fh "Rejected mail by reason\n";
+ print $txt_fh "-----------------------";
+ print $txt_fh "\n Total\n";
+ }
+ if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"patterns\"></a><h2>Rejected mail by reason</h2>\n";
+ print $htm_fh "<table border=0 width=\"100%\"><tr><td><table border=1>\n";
+ print $htm_fh "<tr><th> </th><th>Total</th>\n";
+ }
+ if ($xls_fh) {
+ $ws_global->write($row++, $col, "Rejected mail by reason", $f_header2);
+ &set_worksheet_line($ws_global, $row++, 1, ["Total"], $f_headertab);
+ }
+
+
+ my $href = ($merge_reports) ? $report_totals{rejected_mail_by_reason} : \%rejected_count_by_reason;
+ my(@chartdatanames, @chartdatavals_count);
+
+ foreach $reason (top_n_sort($topcount, $href, undef, undef)) {
+ printf $txt_fh ("$txt_format1\n",$reason,$href->{$reason}) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n",$reason,$href->{$reason}) if $htm_fh;
+ set_worksheet_line($ws_global, $row++, 0, [$reason,$href->{$reason}], $f_default) if $xls_fh;
+ push(@chartdatanames, $reason);
+ push(@chartdatavals_count, $href->{$reason});
+ }
+
+ $row++ if $xls_fh;
+ print $txt_fh "\n" if $txt_fh;
+
+ if ($htm_fh) {
+ print $htm_fh "</tr></table></td><td>";
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals_count > 0)) {
+ # calculate the graph
+ my @data = (
+ \@chartdatanames,
+ \@chartdatavals_count
+ );
+ my $graph = GD::Graph::pie->new(200, 200);
+ $graph->set(
+ x_label => 'Rejection Reasons',
+ y_label => 'Messages',
+ title => 'By count',
+ );
+ my $gd = $graph->plot(\@data) or warn($graph->error);
+ if ($gd) {
+ open(IMG, ">$chartdir/rejections_count.png") or die "Could not write $chartdir/rejections_count.png: $!\n";
+ binmode IMG;
+ print IMG $gd->png;
+ close IMG;
+ print $htm_fh "<img src=\"$chartrel/rejections_count.png\">";
+ }
+ }
+ print $htm_fh "</td></tr></table>\n\n";
+ }
+}
+
+
+
+
#######################################################################
# print_transport();
-#
+#
# print_transport();
-#
+#
# Print totals by transport.
#######################################################################
sub print_transport {
- my($format1);
my(@chartdatanames);
my(@chartdatavals_count);
my(@chartdatavals_vol);
- no integer; #Lose this for charting the data.
+ no integer; #Lose this for charting the data.
+
+ my $txt_format1 = " %-18s %6s %6d";
+ my $htm_format1 = "<tr><td>%s</td><td align=\"right\">%s</td><td align=\"right\">%d</td>";
- if ($html) {
- print "<hr><a name=\"transport\"></a><h2>Deliveries by Transport</h2>\n";
- print "<table border=0 width=\"100%\">\n";
- print "<tr><td>\n";
- print "<table border=1>\n";
- print "<tr><th> </th><th>Volume</th><th>Messages</th>\n";
- $format1 = "<tr><td>%s</td><td align=\"right\">%s</td><td align=\"right\">%d</td>";
+ if ($txt_fh) {
+ print $txt_fh "Deliveries by transport\n";
+ print $txt_fh "-----------------------";
+ print $txt_fh "\n Volume Messages\n";
}
- else {
- print "Deliveries by transport\n";
- print "-----------------------";
- print "\n Volume Messages\n";
- $format1 = " %-18s %6s %6d";
+ if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"transport\"></a><h2>Deliveries by Transport</h2>\n";
+ print $htm_fh "<table border=0 width=\"100%\"><tr><td><table border=1>\n";
+ print $htm_fh "<tr><th> </th><th>Volume</th><th>Messages</th>\n";
+ }
+ if ($xls_fh) {
+ $ws_global->write(++$row, $col, "Deliveries by transport", $f_header2);
+ $ws_global->write(++$row, 1, ["Volume", "Messages"], $f_headertab);
}
my($key);
# We are getting our data from previous reports.
foreach $key (sort keys %{$report_totals{transport}}) {
my $count = get_report_total($report_totals{transport}{$key},'Messages');
- printf("$format1\n",$key,
- volume_rounded($report_totals{transport}{$key}{Volume},$report_totals{transport}{$key}{'Volume-gigs'}),
- $count);
+ my @content=($key, volume_rounded($report_totals{transport}{$key}{Volume},
+ $report_totals{transport}{$key}{'Volume-gigs'}), $count);
push(@chartdatanames, $key);
push(@chartdatavals_count, $count);
push(@chartdatavals_vol, $report_totals{transport}{$key}{'Volume-gigs'}*$gig + $report_totals{transport}{$key}{Volume} );
+ printf $txt_fh ("$txt_format1\n", @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n", @content) if $htm_fh;
+ $ws_global->write(++$row, 0, \@content) if $xls_fh;
}
}
else {
# We are getting our data from mainlog files.
foreach $key (sort keys %transported_data) {
- printf("$format1\n",$key,
- volume_rounded($transported_data{$key},$transported_data_gigs{$key}),
- $transported_count{$key});
+ my @content=($key, volume_rounded($transported_data{$key},$transported_data_gigs{$key}),
+ $transported_count{$key});
push(@chartdatanames, $key);
push(@chartdatavals_count, $transported_count{$key});
push(@chartdatavals_vol, $transported_data_gigs{$key}*$gig + $transported_data{$key});
+ printf $txt_fh ("$txt_format1\n", @content) if $txt_fh;
+ printf $htm_fh ("$htm_format1\n", @content) if $htm_fh;
+ $ws_global->write(++$row, 0, \@content) if $xls_fh;
}
}
- if ($html) {
- print "</table>\n";
- print "</td><td>\n";
- if ($HAVE_GD_Graph_pie && $charts)
+ print $txt_fh "\n" if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh "</tr></table></td><td>";
+
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals_count > 0))
{
# calculate the graph
my @data = (
);
my $gd = $graph->plot(\@data) or warn($graph->error);
if ($gd) {
- open(IMG, ">$chartdir/transports_count.png") or die $!;
- binmode IMG;
- print IMG $gd->png;
- close IMG;
-
print "<img src=\"$chartrel/transports_count.png\">";
+ open(IMG, ">$chartdir/transports_count.png") or die "Could not write $chartdir/transports_count.png: $!\n";
+ binmode IMG;
+ print IMG $gd->png;
+ close IMG;
+
print $htm_fh "<img src=\"$chartrel/transports_count.png\">";
}
}
- print "</td><td>\n";
+ print $htm_fh "</td><td>";
- if ($HAVE_GD_Graph_pie && $charts) {
+ if ($HAVE_GD_Graph_pie && $charts && ($#chartdatavals_vol > 0)) {
my @data = (
\@chartdatanames,
\@chartdatavals_vol
);
my $gd = $graph->plot(\@data) or warn($graph->error);
if ($gd) {
- open(IMG, ">$chartdir/transports_vol.png") or die $!;
- binmode IMG;
- print IMG $gd->png;
- close IMG;
-
print "<img src=\"$chartrel/transports_vol.png\">";
+ open(IMG, ">$chartdir/transports_vol.png") or die "Could not write $chartdir/transports_vol.png: $!\n";
+ binmode IMG;
+ print IMG $gd->png;
+ close IMG;
+
print $htm_fh "<img src=\"$chartrel/transports_vol.png\">";
}
}
- print "</td></tr></table>\n";
+
+ print $htm_fh "</td></tr></table>\n\n";
}
- print "\n";
}
#######################################################################
# print_relay();
-#
+#
# print_relay();
-#
+#
# Print our totals by relay.
#######################################################################
sub print_relay {
+ my $row_print_relay=1;
my $temp = "Relayed messages";
- print "<hr><a name=\"$temp\"></a><h2>$temp</h2>\n" if $html;
+ print $htm_fh "<hr><a name=\"$temp\"></a><h2>$temp</h2>\n" if $htm_fh;
if (scalar(keys %relayed) > 0 || $relayed_unshown > 0) {
my $shown = 0;
my $spacing = "";
- my($format);
+ my $txt_format = "%7d %s\n => %s\n";
+ my $htm_format = "<tr><td align=\"right\">%d</td><td>%s</td><td>%s</td>\n";
- if ($html) {
- print "<table border=1>\n";
- print "<tr><th>Count</th><th>From</th><th>To</th>\n";
- $format = "<tr><td align=\"right\">%d</td><td>%s</td><td>%s</td>\n";
+ printf $txt_fh ("%s\n%s\n\n", $temp, "-" x length($temp)) if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh "<table border=1>\n";
+ print $htm_fh "<tr><th>Count</th><th>From</th><th>To</th>\n";
}
- else {
- printf("%s\n%s\n\n", $temp, "-" x length($temp));
- $format = "%7d %s\n => %s\n";
+ if ($xls_fh) {
+ $ws_relayed->write($row_print_relay++, $col, $temp, $f_header2);
+ &set_worksheet_line($ws_relayed, $row_print_relay++, 0, ["Count", "From", "To"], $f_headertab);
}
+
my($key);
foreach $key (sort keys %relayed) {
my $count = $relayed{$key};
$shown += $count;
$key =~ s/[HA]=//g;
my($one,$two) = split(/=> /, $key);
- printf($format, $count, $one, $two);
+ my @content=($count, $one, $two);
+ printf $txt_fh ($txt_format, @content) if $txt_fh;
+ printf $htm_fh ($htm_format, @content) if $htm_fh;
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_relayed, $row_print_relay++, 0, \@content);
+ }
$spacing = "\n";
}
- print "</table>\n<p>\n" if $html;
- print "${spacing}Total: $shown (plus $relayed_unshown unshown)\n";
+
+ print $htm_fh "</table>\n<p>\n" if $htm_fh;
+ print $txt_fh "${spacing}Total: $shown (plus $relayed_unshown unshown)\n\n" if $txt_fh;
+ print $htm_fh "${spacing}Total: $shown (plus $relayed_unshown unshown)\n\n" if $htm_fh;
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_relayed, $row_print_relay++, 0, [$shown, "Sum of shown" ]);
+ &set_worksheet_line($ws_relayed, $row_print_relay++, 0, [$relayed_unshown, "unshown"]);
+ $row_print_relay++;
+ }
}
else {
- print "No relayed messages\n";
- print "-------------------\n" unless $html;
+ print $txt_fh "No relayed messages\n-------------------\n\n" if $txt_fh;
+ print $htm_fh "No relayed messages\n\n" if $htm_fh;
+ if ($xls_fh)
+ {
+ $row_print_relay++;
+ }
}
- print "\n";
}
#######################################################################
# print_errors();
-#
+#
# print_errors();
-#
+#
# Print our errors. In HTML, we display them as a list rather than a table -
# Netscape doesn't like large tables!
#######################################################################
sub print_errors {
my $total_errors = 0;
+ $row=1;
if (scalar(keys %errors_count) != 0) {
my $temp = "List of errors";
- my($format);
- if ($html) {
- print "<hr><a name=\"errors\"></a><h2>$temp</h2>\n";
- print "<ul><li><b>Count - Error</b>\n";
- $format = "<li>%d - %s\n";
+ my $htm_format = "<li>%d - %s\n";
+
+ printf $txt_fh ("%s\n%s\n\n", $temp, "-" x length($temp)) if $txt_fh;
+ if ($htm_fh) {
+ print $htm_fh "<hr><a name=\"errors\"></a><h2>$temp</h2>\n";
+ print $htm_fh "<ul><li><b>Count - Error</b>\n";
}
- else {
- printf("%s\n%s\n\n", $temp, "-" x length($temp));
+ if ($xls_fh)
+ {
+ $ws_errors->write($row++, 0, $temp, $f_header2);
+ &set_worksheet_line($ws_errors, $row++, 0, ["Count", "Error"], $f_headertab);
}
+
my($key);
foreach $key (sort keys %errors_count) {
my $text = $key;
chomp($text);
- $text =~ s/\s\s+/ /g; #Convert multiple spaces to a single space.
+ $text =~ s/\s\s+/ /g; #Convert multiple spaces to a single space.
$total_errors += $errors_count{$key};
- if ($html) {
-
+
+ if ($txt_fh) {
+ printf $txt_fh ("%5d ", $errors_count{$key});
+ my $text_remaining = $text;
+ while (length($text_remaining) > 65) {
+ my($first,$rest) = $text_remaining =~ /(.{50}\S*)\s+(.+)/;
+ last if !$first;
+ printf $txt_fh ("%s\n\t ", $first);
+ $text_remaining = $rest;
+ }
+ printf $txt_fh ("%s\n\n", $text_remaining);
+ }
+
+ if ($htm_fh) {
+
#Translate HTML tag characters. Sergey Sholokh.
$text =~ s/\</\<\;/g;
$text =~ s/\>/\>\;/g;
- printf($format,$errors_count{$key},$text);
+ printf $htm_fh ($htm_format,$errors_count{$key},$text);
}
- else {
- printf("%5d ", $errors_count{$key});
- while (length($text) > 65) {
- my($first,$rest) = $text =~ /(.{50}\S*)\s+(.+)/;
- last if !$first;
- printf("%s\n ", $first);
- $text = $rest;
- }
- printf("%s\n\n", $text);
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_errors, $row++, 0, [$errors_count{$key},$text]);
}
}
- print "</ul>\n<p>\n" if $html;
$temp = "Errors encountered: $total_errors";
- print $temp,"\n";
- print "-" x length($temp),"\n" unless $html;
+
+ if ($txt_fh) {
+ print $txt_fh $temp, "\n";
+ print $txt_fh "-" x length($temp),"\n";
+ }
+ if ($htm_fh) {
+ print $htm_fh "</ul>\n<p>\n";
+ print $htm_fh $temp, "\n";
+ }
+ if ($xls_fh)
+ {
+ &set_worksheet_line($ws_errors, $row++, 0, [$total_errors, "Sum of Errors encountered"]);
+ }
}
}
#######################################################################
# parse_old_eximstat_reports();
-#
+#
# parse_old_eximstat_reports($fh);
-#
+#
# Parse old eximstat output so we can merge daily stats to weekly stats and weekly to monthly etc.
-#
+#
# To test that the merging still works after changes, do something like the following.
# All the diffs should produce no output.
-#
+#
# options='-bydomain -byemail -byhost -byedomain'
+# options="$options -show_rt1,2,4 -show_dt 1,2,4"
# options="$options -pattern 'Completed Messages' /Completed/"
# options="$options -pattern 'Received Messages' /<=/"
-#
+#
# ./eximstats $options mainlog > mainlog.txt
# ./eximstats $options -merge mainlog.txt > mainlog.2.txt
# diff mainlog.txt mainlog.2.txt
-#
+#
# ./eximstats $options -html mainlog > mainlog.html
# ./eximstats $options -merge -html mainlog.txt > mainlog.2.html
# diff mainlog.html mainlog.2.html
-#
+#
# ./eximstats $options -merge mainlog.html > mainlog.3.txt
# diff mainlog.txt mainlog.3.txt
-#
+#
# ./eximstats $options -merge -html mainlog.html > mainlog.3.html
# diff mainlog.html mainlog.3.html
-#
+#
# ./eximstats $options -nvr mainlog > mainlog.nvr.txt
# ./eximstats $options -merge mainlog.nvr.txt > mainlog.4.txt
# diff mainlog.txt mainlog.4.txt
-#
+#
# # double_mainlog.txt should have twice the values that mainlog.txt has.
# ./eximstats $options mainlog mainlog > double_mainlog.txt
#######################################################################
my(%league_table_value_entered, %league_table_value_was_zero, %table_order);
+ my(%user_pattern_index);
+ my $user_pattern_index = 0;
+ map {$user_pattern_index{$_} = $user_pattern_index++} @user_descriptions;
+ my $user_pattern_keys = join('|', @user_descriptions);
+
while (<$fh>) {
+ PARSE_OLD_REPORT_LINE:
if (/Exim statistics from ([\d\-]+ [\d:]+(\s+[\+\-]\d+)?) to ([\d\-]+ [\d:]+(\s+[\+\-]\d+)?)/) {
$begin = $1 if ($1 lt $begin);
$end = $3 if ($3 gt $end);
}
elsif (/Grand total summary/) {
- # Fill in $report_totals{Received|Delivered}{Volume|Messages|Hosts|Domains|...|Delayed|DelayedPercent|Failed|FailedPercent}
- my(@fields);
+ # Fill in $report_totals{Received|Delivered}{Volume|Messages|Addresses|Hosts|Domains|...|Delayed|DelayedPercent|Failed|FailedPercent}
+ my(@fields, @delivered_fields);
+ my $doing_table = 0;
while (<$fh>) {
- $_ = html2txt($_); #Convert general HTML markup to text.
- s/At least one addr//g; #Another part of the HTML output we don't want.
-
-# TOTAL Volume Messages Hosts Domains Delayed Failed
-# Received 26MB 237 177 23 8 3.4% 28 11.8%
-# Delivered 13MB 233 99 88
- if (/TOTAL\s+(.*?)\s*$/) {
- @fields = split(/\s+/,$1);
+ $_ = html2txt($_); #Convert general HTML markup to text.
+ s/At least one addr//g; #Another part of the HTML output we don't want.
+
+# TOTAL Volume Messages Addresses Hosts Domains Delayed Failed
+# Received 26MB 237 177 23 8 3.4% 28 11.8%
+# Delivered 13MB 233 250 99 88
+ if (/TOTAL\s+(.*?)\s*$/) {
+ $doing_table = 1;
+ @delivered_fields = split(/\s+/,$1);
+
#Delayed and Failed have two columns each, so add the extra field names in.
- splice(@fields,-1,1,'DelayedPercent','Failed','FailedPercent');
- }
- elsif (/(Received|Delivered)\s+(.*?)\s*$/) {
- print STDERR "Parsing $_" if $debug;
- add_to_totals($report_totals{$1},\@fields,$2);
- }
- last if (/Delivered/); #Last line of this section.
+ splice(@delivered_fields,-1,1,'DelayedPercent','Failed','FailedPercent');
+
+ # Addresses only figure in the Delivered row, so remove them from the
+ # normal fields.
+ @fields = grep !/Addresses/, @delivered_fields;
+ }
+ elsif (/(Received)\s+(.*?)\s*$/) {
+ print STDERR "Parsing $_" if $debug;
+ add_to_totals($report_totals{$1},\@fields,$2);
+ }
+ elsif (/(Delivered)\s+(.*?)\s*$/) {
+ print STDERR "Parsing $_" if $debug;
+ add_to_totals($report_totals{$1},\@delivered_fields,$2);
+ my $data = $2;
+ # If we're merging an old report which doesn't include addresses,
+ # then use the Messages field instead.
+ unless (grep(/Addresses/, @delivered_fields)) {
+ my %tmp;
+ line_to_hash(\%tmp,\@delivered_fields,$data);
+ add_to_totals($report_totals{Delivered},['Addresses'],$tmp{Messages});
+ }
+ }
+ elsif (/(Rejects|Ham|Spam)\s+(.*?)\s*$/) {
+ print STDERR "Parsing $_" if $debug;
+ add_to_totals($report_totals{$1},['Messages','Hosts'],$2);
+ }
+ else {
+ last if $doing_table;
+ }
}
}
# Total
# Description 85
- while (<$fh>) { last if (/Total/); } #Wait until we get the table headers.
+ while (<$fh>) { last if (/Total/); } #Wait until we get the table headers.
while (<$fh>) {
- print STDERR "Parsing $_" if $debug;
- $_ = html2txt($_); #Convert general HTML markup to text.
- if (/^\s*(.*?)\s+(\d+)\s*$/) {
- $report_totals{patterns}{$1} = {} unless (defined $report_totals{patterns}{$1});
- add_to_totals($report_totals{patterns}{$1},['Total'],$2);
- }
- last if (/^\s*$/); #Finished if we have a blank line.
+ print STDERR "Parsing $_" if $debug;
+ $_ = html2txt($_); #Convert general HTML markup to text.
+ if (/^\s*(.*?)\s+(\d+)\s*$/) {
+ $report_totals{patterns}{$1} = {} unless (defined $report_totals{patterns}{$1});
+ add_to_totals($report_totals{patterns}{$1},['Total'],$2);
+ }
+ last if (/^\s*$/); #Finished if we have a blank line.
}
}
+ elsif (/(^|<h2>)($user_pattern_keys) per /o) {
+ # Parse User defined pattern histograms if they exist.
+ parse_histogram($fh, $user_pattern_interval_count[$user_pattern_index{$2}] );
+ }
+
+
elsif (/Deliveries by transport/i) {
#Deliveries by transport
#-----------------------
# address_pipe 655KB 1
# smtp 11MB 151
- while (<$fh>) { last if (/Volume/); } #Wait until we get the table headers.
+ while (<$fh>) { last if (/Volume/); } #Wait until we get the table headers.
while (<$fh>) {
- print STDERR "Parsing $_" if $debug;
- $_ = html2txt($_); #Convert general HTML markup to text.
- if (/(\S+)\s+(\d+\S*\s+\d+)/) {
- $report_totals{transport}{$1} = {} unless (defined $report_totals{transport}{$1});
- add_to_totals($report_totals{transport}{$1},['Volume','Messages'],$2);
- }
- last if (/^\s*$/); #Finished if we have a blank line.
+ print STDERR "Parsing $_" if $debug;
+ $_ = html2txt($_); #Convert general HTML markup to text.
+ if (/(\S+)\s+(\d+\S*\s+\d+)/) {
+ $report_totals{transport}{$1} = {} unless (defined $report_totals{transport}{$1});
+ add_to_totals($report_totals{transport}{$1},['Volume','Messages'],$2);
+ }
+ last if (/^\s*$/); #Finished if we have a blank line.
}
}
- elsif (/(Messages received|Deliveries) per/) {
-# Messages received per hour (each dot is 2 messages)
-#---------------------------------------------------
-#
-#00-01 106 .....................................................
-#01-02 103 ...................................................
-
- # Set a pointer to the interval array so we can use the same code
- # block for both messages received and delivered.
- my $interval_aref = ($1 eq 'Deliveries') ? \@delivered_interval_count : \@received_interval_count;
- my $reached_table = 0;
- while (<$fh>) {
- $reached_table = 1 if (/^00/);
- next unless $reached_table;
- print STDERR "Parsing $_" if $debug;
- if (/^(\d+):(\d+)\s+(\d+)/) { #hh:mm start time format ?
- $$interval_aref[($1*60 + $2)/$hist_interval] += $3 if $hist_opt;
- }
- elsif (/^(\d+)-(\d+)\s+(\d+)/) { #hh-hh start-end time format ?
- $$interval_aref[($1*60)/$hist_interval] += $3 if $hist_opt;
- }
- else { #Finished the table ?
- last;
- }
- }
+ elsif (/Messages received per/) {
+ parse_histogram($fh, \@received_interval_count);
+ }
+ elsif (/Deliveries per/) {
+ parse_histogram($fh, \@delivered_interval_count);
}
- elsif (/Time spent on the queue: (all messages|messages with at least one remote delivery)/) {
+ #elsif (/Time spent on the queue: (all messages|messages with at least one remote delivery)/) {
+ elsif (/(Time spent on the queue|Delivery times|Receipt times): ((\S+) messages|messages with at least one remote delivery)((<[^>]*>)*\s*)$/) {
#Time spent on the queue: all messages
#-------------------------------------
#
# Set a pointer to the queue bin so we can use the same code
# block for both all messages and remote deliveries.
- my $bin_aref = ($1 eq 'all messages') ? \@queue_bin : \@remote_queue_bin;
- my $reached_table = 0;
+ #my $bin_aref = ($1 eq 'all messages') ? \@qt_all_bin : \@qt_remote_bin;
+ my($bin_aref, $times_aref, $overflow_sref);
+ if ($1 eq 'Time spent on the queue') {
+ $times_aref = \@queue_times;
+ if ($2 eq 'all messages') {
+ $bin_aref = \@qt_all_bin;
+ $overflow_sref = \$qt_all_overflow;
+ }
+ else {
+ $bin_aref = \@qt_remote_bin;
+ $overflow_sref = \$qt_remote_overflow;
+ }
+ }
+ elsif ($1 eq 'Delivery times') {
+ $times_aref = \@delivery_times;
+ if ($2 eq 'all messages') {
+ $bin_aref = \@dt_all_bin;
+ $overflow_sref = \$dt_all_overflow;
+ }
+ else {
+ $bin_aref = \@dt_remote_bin;
+ $overflow_sref = \$dt_remote_overflow;
+ }
+ }
+ else {
+ unless (exists $rcpt_times_bin{$3}) {
+ initialise_rcpt_times($3);
+ }
+ $bin_aref = $rcpt_times_bin{$3};
+ $times_aref = \@rcpt_times;
+ $overflow_sref = \$rcpt_times_overflow{$3};
+ }
+
+
+ my ($blank_lines, $reached_table) = (0,0);
while (<$fh>) {
- $_ = html2txt($_); #Convert general HTML markup to text.
- $reached_table = 1 if (/^\s*Under/);
- next unless $reached_table;
- my $previous_seconds_on_queue = 0;
- if (/^\s*(Under|Over|)\s+(\d+[smhdw])\s+(\d+)/) {
- print STDERR "Parsing $_" if $debug;
- my($modifier,$formated_time,$count) = ($1,$2,$3);
- my $seconds = unformat_time($formated_time);
- my $time_on_queue = ($seconds + $previous_seconds_on_queue) / 2;
- $previous_seconds_on_queue = $seconds;
- $time_on_queue = $seconds * 2 if ($modifier eq 'Over');
- my($i);
- for ($i = 0; $i <= $#queue_times; $i++) {
- if ($time_on_queue < $queue_times[$i]) {
- $$bin_aref[$i] += $count;
- last;
- }
- }
- # There's only one counter for messages going over the queue
- # times so make sure we only count it once.
- $queue_more_than += $count if (($bin_aref == \@queue_bin) && ($i > $#queue_times));
- }
- else {
- last; #Finished the table ?
- }
+ $_ = html2txt($_); #Convert general HTML markup to text.
+ # The table is preceded by one blank line, and has one blank line
+ # following it. As the table may be empty, the best way to determine
+ # that we've finished it is to look for the second blank line.
+ ++$blank_lines if /^\s*$/;
+ last if ($blank_lines >=2); #Finished the table ?
+ $reached_table = 1 if (/\d/);
+ next unless $reached_table;
+ my $previous_seconds_on_queue = 0;
+ if (/^\s*(Under|Over|)\s+(\d+[smhdw])\s+(\d+)/) {
+ print STDERR "Parsing $_" if $debug;
+ my($modifier,$formated_time,$count) = ($1,$2,$3);
+ my $seconds = unformat_time($formated_time);
+ my $time_on_queue = ($seconds + $previous_seconds_on_queue) / 2;
+ $previous_seconds_on_queue = $seconds;
+ $time_on_queue = $seconds * 2 if ($modifier eq 'Over');
+ my($i);
+ for ($i = 0; $i <= $#$times_aref; $i++) {
+ if ($time_on_queue < $times_aref->[$i]) {
+ $$bin_aref[$i] += $count;
+ last;
+ }
+ }
+ $$overflow_sref += $count if ($i > $#$times_aref);
+
+ }
}
}
my $reached_table = 0;
my($count,$sender);
while (<$fh>) {
- unless ($reached_table) {
- last if (/No relayed messages/);
- $reached_table = 1 if (/^\s*\d/ || />\d+</);
- next unless $reached_table;
- }
- if (/>(\d+)<.td><td>(.*?) ?<.td><td>(.*?)</) {
- update_relayed($1,$2,$3);
- }
- elsif (/^\s*(\d+)\s+(.*?)\s*$/) {
- ($count,$sender) = ($1,$2);
- }
- elsif (/=>\s+(.*?)\s*$/) {
- update_relayed($count,$sender,$1);
- }
- else {
- last; #Finished the table ?
- }
+ unless ($reached_table) {
+ last if (/No relayed messages/);
+ $reached_table = 1 if (/^\s*\d/ || />\d+</);
+ next unless $reached_table;
+ }
+ if (/>(\d+)<.td><td>(.*?) ?<.td><td>(.*?)</) {
+ update_relayed($1,$2,$3);
+ }
+ elsif (/^\s*(\d+)\s+(.*?)\s*$/) {
+ ($count,$sender) = ($1,$2);
+ }
+ elsif (/=>\s+(.*?)\s*$/) {
+ update_relayed($count,$sender,$1);
+ }
+ else {
+ last; #Finished the table ?
+ }
}
}
#-------------------------------------
#
# 48 1468KB local
+# Could also have average values for HTML output.
+# 48 1468KB 30KB local
+
my($category,$by_count_or_volume) = ($1,$2);
#As we show 2 views of each table (by count and by volume),
#Set up a hash to record which entries we have already seen
#and one to record which ones we are seeing for the first time.
if ($by_count_or_volume =~ /count/) {
- undef %league_table_value_entered;
- undef %league_table_value_was_zero;
- undef %table_order;
+ undef %league_table_value_entered;
+ undef %league_table_value_was_zero;
+ undef %table_order;
}
#As this section processes multiple different table categories,
#set up pointers to the hashes to be updated.
- my($count_href,$data_href,$data_gigs_href);
+ my($messages_href,$addresses_href,$data_href,$data_gigs_href);
if ($category =~ /local sender/) {
- $count_href = \%received_count_user;
- $data_href = \%received_data_user;
- $data_gigs_href = \%received_data_gigs_user;
+ $messages_href = \%received_count_user;
+ $addresses_href = undef;
+ $data_href = \%received_data_user;
+ $data_gigs_href = \%received_data_gigs_user;
}
elsif ($category =~ /sending (\S+?)s?\b/) {
#Top 50 sending (host|domain|email|edomain)s
#Top sending (host|domain|email|edomain)
- $count_href = \%{$received_count{"\u$1"}};
- $data_href = \%{$received_data{"\u$1"}};
- $data_gigs_href = \%{$received_data_gigs{"\u$1"}};
+ $messages_href = \%{$received_count{"\u$1"}};
+ $data_href = \%{$received_data{"\u$1"}};
+ $data_gigs_href = \%{$received_data_gigs{"\u$1"}};
}
elsif ($category =~ /local destination/) {
- $count_href = \%delivered_count_user;
- $data_href = \%delivered_data_user;
- $data_gigs_href = \%delivered_data_gigs_user;
+ $messages_href = \%delivered_messages_user;
+ $addresses_href = \%delivered_addresses_user;
+ $data_href = \%delivered_data_user;
+ $data_gigs_href = \%delivered_data_gigs_user;
}
elsif ($category =~ /(\S+) destination/) {
#Top 50 (host|domain|email|edomain) destinations
#Top (host|domain|email|edomain) destination
- $count_href = \%{$delivered_count{"\u$1"}};
- $data_href = \%{$delivered_data{"\u$1"}};
- $data_gigs_href = \%{$delivered_data_gigs{"\u$1"}};
+ $messages_href = \%{$delivered_messages{"\u$1"}};
+ $addresses_href = \%{$delivered_addresses{"\u$1"}};
+ $data_href = \%{$delivered_data{"\u$1"}};
+ $data_gigs_href = \%{$delivered_data_gigs{"\u$1"}};
+ }
+ elsif ($category =~ /rejected ips/) {
+ $messages_href = \%rejected_count_by_ip;
+ }
+ elsif ($category =~ /non-rejected spamming ips/) {
+ $messages_href = \%spam_count_by_ip;
+ }
+ elsif ($category =~ /mail rejection reasons/) {
+ $messages_href = \%rejected_count_by_reason;
}
my $reached_table = 0;
+ my $row_re;
while (<$fh>) {
- $_ = html2txt($_); #Convert general HTML markup to text.
- $reached_table = 1 if (/^\s*\d/);
- next unless $reached_table;
- if (/^\s*(\d+)\s+(\S+)\s*(.*?)\s*$/) {
- my($count,$rounded_volume,$entry) = ($1,$2,$3);
- #Note: $entry fields can be both null and can contain spaces.
-
- #Add the entry into the %table_order hash if it has a rounded volume (KB/MB/GB).
- push(@{$table_order{$rounded_volume}{$by_count_or_volume}},$entry) if ($rounded_volume =~ /\D/);
-
- unless ($league_table_value_entered{$entry}) {
- $league_table_value_entered{$entry} = 1;
- unless ($$count_href{$entry}) {
- $$count_href{$entry} = 0;
- $$data_href{$entry} = 0;
- $$data_gigs_href{$entry} = 0;
- $league_table_value_was_zero{$entry} = 1;
- }
-
- $$count_href{$entry} += $count;
- #Add the rounded value to the data and data_gigs hashes.
- un_round($rounded_volume,\$$data_href{$entry},\$$data_gigs_href{$entry});
- print STDERR "$category by $by_count_or_volume: added $count,$rounded_volume to $entry\n" if $debug;
- }
- }
- else { #Finished the table ?
- if ($by_count_or_volume =~ /volume/) {
- #Add a few bytes to appropriate entries to preserve the order.
-
- my($rounded_volume);
- foreach $rounded_volume (keys %table_order) {
- #For each rounded volume, we want to create a list which has things
- #ordered from the volume table at the front, and additional things
- #from the count table ordered at the back.
- @{$table_order{$rounded_volume}{volume}} = () unless defined $table_order{$rounded_volume}{volume};
- @{$table_order{$rounded_volume}{'message count'}} = () unless defined $table_order{$rounded_volume}{'message count'};
- my(@order,%mark);
- map {$mark{$_} = 1} @{$table_order{$rounded_volume}{volume}};
- @order = @{$table_order{$rounded_volume}{volume}};
- map {push(@order,$_)} grep(!$mark{$_},@{$table_order{$rounded_volume}{'message count'}});
-
- my $bonus_bytes = $#order;
- $bonus_bytes = 511 if ($bonus_bytes > 511); #Don't go over the half-K boundary!
- while (@order and ($bonus_bytes > 0)) {
- my $entry = shift(@order);
- if ($league_table_value_was_zero{$entry}) {
- $$data_href{$entry} += $bonus_bytes;
- print STDERR "$category by $by_count_or_volume: added $bonus_bytes bonus bytes to $entry\n" if $debug;
- }
- $bonus_bytes--;
- }
- }
- }
-
- last;
- }
+ # Watch out for empty tables.
+ goto PARSE_OLD_REPORT_LINE if (/<h2>/ or (/^\s*[a-zA-Z]/ && !/^\s*Messages/));
+
+ $_ = html2txt($_); #Convert general HTML markup to text.
+
+ # Messages Addresses Bytes Average
+ if (/^\s*Messages/) {
+ my $pattern = '^\s*(\d+)';
+ $pattern .= (/Addresses/) ? '\s+(\d+)' : '()';
+ $pattern .= (/Bytes/) ? '\s+([\dKMGB]+)' : '()';
+ $pattern .= (/Average/) ? '\s+[\dKMGB]+' : '';
+ $pattern .= '\s+(.*?)\s*$';
+ $row_re = qr/$pattern/;
+ $reached_table = 1;
+ next;
+ }
+ next unless $reached_table;
+
+ my($messages, $addresses, $rounded_volume, $entry);
+
+ if (/$row_re/) {
+ ($messages, $addresses, $rounded_volume, $entry) = ($1, $2, $3, $4);
+ }
+ else {
+ #Else we have finished the table and we may need to do some
+ #kludging to retain the order of the entries.
+
+ if ($by_count_or_volume =~ /volume/) {
+ #Add a few bytes to appropriate entries to preserve the order.
+ foreach $rounded_volume (keys %table_order) {
+ #For each rounded volume, we want to create a list which has things
+ #ordered from the volume table at the front, and additional things
+ #from the count table ordered at the back.
+ @{$table_order{$rounded_volume}{volume}} = () unless defined $table_order{$rounded_volume}{volume};
+ @{$table_order{$rounded_volume}{'message count'}} = () unless defined $table_order{$rounded_volume}{'message count'};
+ my(@order,%mark);
+ map {$mark{$_} = 1} @{$table_order{$rounded_volume}{volume}};
+ @order = @{$table_order{$rounded_volume}{volume}};
+ map {push(@order,$_)} grep(!$mark{$_},@{$table_order{$rounded_volume}{'message count'}});
+
+ my $bonus_bytes = $#order;
+ $bonus_bytes = 511 if ($bonus_bytes > 511); #Don't go over the half-K boundary!
+ while (@order and ($bonus_bytes > 0)) {
+ my $entry = shift(@order);
+ if ($league_table_value_was_zero{$entry}) {
+ $$data_href{$entry} += $bonus_bytes;
+ print STDERR "$category by $by_count_or_volume: added $bonus_bytes bonus bytes to $entry\n" if $debug;
+ }
+ $bonus_bytes--;
+ }
+ }
+ }
+ last;
+ }
+
+ # Store a new table entry.
+
+ # Add the entry into the %table_order hash if it has a rounded
+ # volume (KB/MB/GB).
+ push(@{$table_order{$rounded_volume}{$by_count_or_volume}},$entry) if ($rounded_volume =~ /\D/);
+
+ unless ($league_table_value_entered{$entry}) {
+ $league_table_value_entered{$entry} = 1;
+ unless ($$messages_href{$entry}) {
+ $$messages_href{$entry} = 0;
+ $$addresses_href{$entry} = 0;
+ $$data_href{$entry} = 0;
+ $$data_gigs_href{$entry} = 0;
+ $league_table_value_was_zero{$entry} = 1;
+ }
+
+ $$messages_href{$entry} += $messages;
+
+ # When adding the addresses, be aware that we could be merging
+ # an old report which does not include addresses. In this case,
+ # we add the messages instead.
+ $$addresses_href{$entry} += ($addresses) ? $addresses : $messages;
+
+ #Add the rounded value to the data and data_gigs hashes.
+ un_round($rounded_volume,\$$data_href{$entry},\$$data_gigs_href{$entry}) if $rounded_volume;
+ print STDERR "$category by $by_count_or_volume: added $messages,$rounded_volume to $entry\n" if $debug;
+ }
+
}
}
elsif (/List of errors/) {
my $reached_table = 0;
my($count,$error,$blanks);
while (<$fh>) {
- $reached_table = 1 if (/^( *|<li>)(\d+)/);
- next unless $reached_table;
+ $reached_table = 1 if (/^( *|<li>)(\d+)/);
+ next unless $reached_table;
- s/^<li>(\d+) -/$1/; #Convert an HTML line to a text line.
- $_ = html2txt($_); #Convert general HTML markup to text.
+ s/^<li>(\d+) -/$1/; #Convert an HTML line to a text line.
+ $_ = html2txt($_); #Convert general HTML markup to text.
- if (/\t\s*(.*)/) {
- $error .= ' ' . $1; #Join a multiline error.
- }
- elsif (/^\s*(\d+)\s+(.*)/) {
- if ($error) {
+ if (/\t\s*(.*)/) {
+ $error .= ' ' . $1; #Join a multiline error.
+ }
+ elsif (/^\s*(\d+)\s+(.*)/) {
+ if ($error) {
#Finished with a previous multiline error so save it.
- $errors_count{$error} = 0 unless $errors_count{$error};
- $errors_count{$error} += $count;
- }
- ($count,$error) = ($1,$2);
- }
- elsif (/Errors encountered/) {
- if ($error) {
+ $errors_count{$error} = 0 unless $errors_count{$error};
+ $errors_count{$error} += $count;
+ }
+ ($count,$error) = ($1,$2);
+ }
+ elsif (/Errors encountered/) {
+ if ($error) {
#Finished the section, so save our stored last error.
- $errors_count{$error} = 0 unless $errors_count{$error};
- $errors_count{$error} += $count;
- }
- last;
- }
+ $errors_count{$error} = 0 unless $errors_count{$error};
+ $errors_count{$error} += $count;
+ }
+ last;
+ }
}
}
}
}
+#######################################################################
+# parse_histogram($fh, \@delivered_interval_count);
+# Parse a histogram into the provided array of counters.
+#######################################################################
+sub parse_histogram {
+ my($fh, $counters_aref) = @_;
+
+ # Messages received per hour (each dot is 2 messages)
+ #---------------------------------------------------
+ #
+ #00-01 106 .....................................................
+ #01-02 103 ...................................................
+
+ my $reached_table = 0;
+ while (<$fh>) {
+ $reached_table = 1 if (/^00/);
+ next unless $reached_table;
+ print STDERR "Parsing $_" if $debug;
+ if (/^(\d+):(\d+)\s+(\d+)/) { #hh:mm start time format ?
+ $$counters_aref[($1*60 + $2)/$hist_interval] += $3 if $hist_opt;
+ }
+ elsif (/^(\d+)-(\d+)\s+(\d+)/) { #hh-hh start-end time format ?
+ $$counters_aref[($1*60)/$hist_interval] += $3 if $hist_opt;
+ }
+ else { #Finished the table ?
+ last;
+ }
+ }
+}
#######################################################################
# update_relayed();
-#
+#
# update_relayed($count,$sender,$recipient);
-#
+#
# Adds an entry into the %relayed hash. Currently only used when
# merging reports.
#######################################################################
#######################################################################
# add_to_totals();
-#
+#
# add_to_totals(\%totals,\@keys,$values);
-#
+#
# Given a line of space seperated values, add them into the provided hash using @keys
# as the hash keys.
-#
+#
# If the value contains a '%', then the value is set rather than added. Otherwise, we
# convert the value to bytes and gigs. The gigs get added to I<Key>-gigs.
#######################################################################
sub add_to_totals {
my($totals_href,$keys_aref,$values) = @_;
my(@values) = split(/\s+/,$values);
- my(@keys) = @$keys_aref; #Make a copy as we destroy the one we use.
- my($value);
- foreach $value (@values) {
- my $key = shift(@keys) or next;
- if ($value =~ /%/) {
- $$totals_href{$key} = $value;
+
+ for(my $i = 0; $i < @values && $i < @$keys_aref; ++$i) {
+ my $key = $keys_aref->[$i];
+ if ($values[$i] =~ /%/) {
+ $$totals_href{$key} = $values[$i];
}
else {
$$totals_href{$key} = 0 unless ($$totals_href{$key});
$$totals_href{"$key-gigs"} = 0 unless ($$totals_href{"$key-gigs"});
- un_round($value, \$$totals_href{$key}, \$$totals_href{"$key-gigs"});
- print STDERR "Added $value to $key - $$totals_href{$key} , " . $$totals_href{"$key-gigs"} . "GB.\n" if $debug;
+ un_round($values[$i], \$$totals_href{$key}, \$$totals_href{"$key-gigs"});
+ print STDERR "Added $values[$i] to $key - $$totals_href{$key} , " . $$totals_href{"$key-gigs"} . "GB.\n" if $debug;
}
}
}
+
+#######################################################################
+# line_to_hash();
+#
+# line_to_hash(\%hash,\@keys,$line);
+#
+# Given a line of space seperated values, set them into the provided hash
+# using @keys as the hash keys.
+#######################################################################
+sub line_to_hash {
+ my($href,$keys_aref,$values) = @_;
+ my(@values) = split(/\s+/,$values);
+ for(my $i = 0; $i < @values && $i < @$keys_aref; ++$i) {
+ $$href{$keys_aref->[$i]} = $values[$i];
+ }
+}
+
+
#######################################################################
# get_report_total();
-#
+#
# $total = get_report_total(\%hash,$key);
-#
+#
# If %hash contains values split into Units and Gigs, we calculate and return
-#
+#
# $hash{$key} + 1024*1024*1024 * $hash{"${key}-gigs"}
#######################################################################
sub get_report_total {
#######################################################################
# html2txt();
-#
+#
# $text_line = html2txt($html_line);
-#
+#
# Convert a line from html to text. Currently we just convert HTML tags to spaces
# and convert >, <, and tags back.
#######################################################################
# <Userid@Domain> words, so explicitly specify the HTML tags we will remove
# (the ones used by this program). If someone is careless enough to have their
# Userid the same as an HTML tag, there's not much we can do about it.
- s/<\/?(html|head|title|body|h\d|ul|li|a\s+|table|tr|td|th|pre|hr|p|br)\b.*?>/ /og;
+ s/<\/?(html|head|title|body|h\d|ul|li|a\s+|table|tr|td|th|pre|hr|p|br)\b.*?>/ /g;
s/\<\;/\</og; #Convert '<' to '<'.
s/\>\;/\>/og; #Convert '>' to '>'.
#######################################################################
# get_next_arg();
-#
+#
# $arg = get_next_arg();
-#
+#
# Because eximstats arguments are often passed as variables,
# we can't rely on shell parsing to deal with quotes. This
# subroutine returns $ARGV[1] and does a shift. If $ARGV[1]
# starts with a quote (' or "), and doesn't end in one, then
# we append the next argument to it and shift again. We repeat
# until we've got all of the argument.
-#
+#
# This isn't perfect as all white space gets reduced to one space,
# but it's as good as we can get! If it's esential that spacing
# be preserved precisely, then you get that by not using shell
return $arg;
}
+#######################################################################
+# set_worksheet_line($ws_global, $startrow, $startcol, \@content, $format);
+#
+# set values to a sequence of cells in a row.
+#
+#######################################################################
+sub set_worksheet_line {
+ my ($worksheet, $row, $col, $content, $format) = @_;
+
+ foreach my $token (@$content)
+ {
+ $worksheet->write($row, $col++, $token, $format );
+ }
+
+}
+
+#######################################################################
+# @rcpt_times = parse_time_list($string);
+#
+# Parse a comma seperated list of time values in seconds given by
+# the user and fill an array.
+#
+# Return a default list if $string is undefined.
+# Return () if $string eq '0'.
+#######################################################################
+sub parse_time_list {
+ my($string) = @_;
+ if (! defined $string) {
+ return(60, 5*60, 15*60, 30*60, 60*60, 3*60*60, 6*60*60, 12*60*60, 24*60*60);
+ }
+ my(@times) = split(/,/, $string);
+ foreach my $q (@times) { $q = eval($q) + 0 }
+ @times = sort { $a <=> $b } @times;
+ @times = () if ($#times == 0 && $times[0] == 0);
+ return(@times);
+}
+
+
+#######################################################################
+# initialise_rcpt_times($protocol);
+# Initialise an array of rcpt_times to 0 for the specified protocol.
+#######################################################################
+sub initialise_rcpt_times {
+ my($protocol) = @_;
+ for (my $i = 0; $i <= $#rcpt_times; ++$i) {
+ $rcpt_times_bin{$protocol}[$i] = 0;
+ }
+ $rcpt_times_overflow{$protocol} = 0;
+}
##################################################
$topcount = 50;
$local_league_table = 1;
$include_remote_users = 0;
+$include_original_destination = 0;
$hist_opt = 1;
$volume_rounding = 1;
$localtime_offset = calculate_localtime_offset(); # PH/FANF
$chartrel = ".";
$chartdir = ".";
-@queue_times = (60, 5*60, 15*60, 30*60, 60*60, 3*60*60, 6*60*60,
- 12*60*60, 24*60*60);
+@queue_times = parse_time_list();
+@rcpt_times = ();
+@delivery_times = ();
$last_offset = '';
$offset_seconds = 0;
+$row=1;
+$col=0;
+$col_hist=0;
+$run_hist=0;
+my(%output_files); # What output files have been specified?
+
# Decode options
-while (@ARGV > 0 && substr($ARGV[0], 0, 1) eq '-')
- {
+while (@ARGV > 0 && substr($ARGV[0], 0, 1) eq '-') {
if ($ARGV[0] =~ /^\-h(\d+)$/) { $hist_opt = $1 }
elsif ($ARGV[0] =~ /^\-ne$/) { $show_errors = 0 }
- elsif ($ARGV[0] =~ /^\-nr(.?)(.*)\1$/)
- {
+ elsif ($ARGV[0] =~ /^\-nr(.?)(.*)\1$/) {
if ($1 eq "") { $show_relay = 0 } else { $relay_pattern = $2 }
- }
- elsif ($ARGV[0] =~ /^\-q([,\d\+\-\*\/]+)$/)
- {
- @queue_times = split(/,/, $1);
- my($q);
- foreach $q (@queue_times) { $q = eval($q) + 0 }
- @queue_times = sort { $a <=> $b } @queue_times;
- @queue_times = () if ($#queue_times == 0 && $queue_times[0] == 0);
- }
+ }
+ elsif ($ARGV[0] =~ /^\-q([,\d\+\-\*\/]+)$/) { @queue_times = parse_time_list($1) }
elsif ($ARGV[0] =~ /^-nt$/) { $show_transport = 0 }
elsif ($ARGV[0] =~ /^\-nt(.?)(.*)\1$/)
{
}
elsif ($ARGV[0] =~ /^-t(\d+)$/) { $topcount = $1 }
elsif ($ARGV[0] =~ /^-tnl$/) { $local_league_table = 0 }
- elsif ($ARGV[0] =~ /^-html$/) { $html = 1 }
+ elsif ($ARGV[0] =~ /^-txt=?(\S*)$/) { $txt_fh = get_filehandle($1,\%output_files) }
+ elsif ($ARGV[0] =~ /^-html=?(\S*)$/) { $htm_fh = get_filehandle($1,\%output_files) }
+ elsif ($ARGV[0] =~ /^-xls=?(\S*)$/) {
+ if ($HAVE_Spreadsheet_WriteExcel) {
+ $xls_fh = get_filehandle($1,\%output_files);
+ }
+ else {
+ warn "WARNING: CPAN Module Spreadsheet::WriteExcel not installed. Obtain from www.cpan.org\n";
+ }
+ }
elsif ($ARGV[0] =~ /^-merge$/) { $merge_reports = 1 }
elsif ($ARGV[0] =~ /^-charts$/) {
$charts = 1;
}
elsif ($ARGV[0] =~ /^-chartdir$/) { $chartdir = $ARGV[1]; shift; $charts_option_specified = 1; }
elsif ($ARGV[0] =~ /^-chartrel$/) { $chartrel = $ARGV[1]; shift; $charts_option_specified = 1; }
- elsif ($ARGV[0] =~ /^-cache$/) { } #Not currently used.
+ elsif ($ARGV[0] =~ /^-include_original_destination$/) { $include_original_destination = 1 }
+ elsif ($ARGV[0] =~ /^-cache$/) { } #Not currently used.
elsif ($ARGV[0] =~ /^-byhost$/) { $do_sender{Host} = 1 }
elsif ($ARGV[0] =~ /^-bydomain$/) { $do_sender{Domain} = 1 }
elsif ($ARGV[0] =~ /^-byemail$/) { $do_sender{Email} = 1 }
elsif ($ARGV[0] =~ /^-byemaildomain$/) { $do_sender{Edomain} = 1 }
elsif ($ARGV[0] =~ /^-byedomain$/) { $do_sender{Edomain} = 1 }
+ elsif ($ARGV[0] =~ /^-emptyok$/) { $emptyOK = 1 }
elsif ($ARGV[0] =~ /^-nvr$/) { $volume_rounding = 0 }
+ elsif ($ARGV[0] =~ /^-show_rt([,\d\+\-\*\/]+)?$/) { @rcpt_times = parse_time_list($1) }
+ elsif ($ARGV[0] =~ /^-show_dt([,\d\+\-\*\/]+)?$/) { @delivery_times = parse_time_list($1) }
elsif ($ARGV[0] =~ /^-d$/) { $debug = 1 }
elsif ($ARGV[0] =~ /^--?h(elp)?$/){ help() }
elsif ($ARGV[0] =~ /^-t_remote_users$/) { $include_remote_users = 1 }
shift;
}
+ # keep old default behaviour
+ if (! ($xls_fh or $htm_fh or $txt_fh)) {
+ $txt_fh = \*STDOUT;
+ }
+
# Check that all the charts options are specified.
warn "-charts option not specified. Use -help for help.\n" if ($charts_option_specified && ! $charts);
# Default to display tables by sending Host.
$do_sender{Host} = 1 unless ($do_sender{Domain} || $do_sender{Email} || $do_sender{Edomain});
+ # prepare xls Excel Workbook
+ if (defined $xls_fh) {
+
+ # Create a new Excel workbook
+ $workbook = Spreadsheet::WriteExcel->new($xls_fh);
+
+ # Add worksheets
+ $ws_global = $workbook->addworksheet('Exim Statistik');
+ # show $ws_global as initial sheet
+ $ws_global->set_first_sheet();
+ $ws_global->activate();
+
+ if ($show_relay) {
+ $ws_relayed = $workbook->addworksheet('Relayed Messages');
+ $ws_relayed->set_column(1, 2, 80);
+ }
+ if ($show_errors) {
+ $ws_errors = $workbook->addworksheet('Errors');
+ }
+
+
+ # set column widths
+ $ws_global->set_column(0, 2, 20); # Columns B-D width set to 30
+ $ws_global->set_column(3, 3, 15); # Columns B-D width set to 30
+ $ws_global->set_column(4, 4, 25); # Columns B-D width set to 30
+ # Define Formats
+ $f_default = $workbook->add_format();
+
+ $f_header1 = $workbook->add_format();
+ $f_header1->set_bold();
+ #$f_header1->set_color('red');
+ $f_header1->set_size('15');
+ $f_header1->set_valign();
+ # $f_header1->set_align('center');
+ # $ws_global->write($row++, 2, "Testing Headers 1", $f_header1);
+
+ $f_header2 = $workbook->add_format();
+ $f_header2->set_bold();
+ $f_header2->set_size('12');
+ $f_header2->set_valign();
+ # $ws_global->write($row++, 2, "Testing Headers 2", $f_header2);
+
+ # Create another header2 for use in merged cells.
+ $f_header2_m = $workbook->add_format();
+ $f_header2_m->set_bold();
+ $f_header2_m->set_size('8');
+ $f_header2_m->set_valign();
+ $f_header2_m->set_align('center');
+
+ $f_percent = $workbook->add_format();
+ $f_percent->set_num_format('0.0%');
+
+ $f_headertab = $workbook->add_format();
+ $f_headertab->set_bold();
+ $f_headertab->set_valign();
+ # $ws_global->write($row++, 2, "Testing Headers tab", $f_headertab);
+
+ }
+
+
+# Initialise the queue/delivery/rcpt time counters.
for (my $i = 0; $i <= $#queue_times; $i++) {
- $queue_bin[$i] = 0;
- $remote_queue_bin[$i] = 0;
+ $qt_all_bin[$i] = 0;
+ $qt_remote_bin[$i] = 0;
+}
+for (my $i = 0; $i <= $#delivery_times; $i++) {
+ $dt_all_bin[$i] = 0;
+ $dt_remote_bin[$i] = 0;
}
+initialise_rcpt_times('all');
-# Compute the number of slots for the histogram
+# Compute the number of slots for the histogram
if ($hist_opt > 0)
{
if ($hist_opt > 60 || 60 % $hist_opt != 0)
{
- print "Eximstats: -h must specify a factor of 60\n";
+ print STDERR "Eximstats: -h must specify a factor of 60\n";
exit 1;
}
- $hist_interval = 60/$hist_opt; #Interval in minutes.
- $hist_number = (24*60)/$hist_interval; #Number of intervals per day.
+ $hist_interval = 60/$hist_opt; #Interval in minutes.
+ $hist_number = (24*60)/$hist_interval; #Number of intervals per day.
@received_interval_count = (0) x $hist_number;
@delivered_interval_count = (0) x $hist_number;
+ my $user_pattern_index = 0;
+ for (my $user_pattern_index = 0; $user_pattern_index <= $#user_patterns; ++$user_pattern_index) {
+ @{$user_pattern_interval_count[$user_pattern_index]} = (0) x $hist_number;
}
+ @dt_all_bin = (0) x $hist_number;
+ @dt_remote_bin = (0) x $hist_number;
+}
#$queue_unknown = 0;
$total_delivered_data = 0;
$total_delivered_data_gigs = 0;
-$total_delivered_count = 0;
+$total_delivered_messages = 0;
+$total_delivered_addresses = 0;
-$queue_more_than = 0;
+$qt_all_overflow = 0;
+$qt_remote_overflow = 0;
+$dt_all_overflow = 0;
+$dt_remote_overflow = 0;
$delayed_count = 0;
$relayed_unshown = 0;
+$message_errors = 0;
$begin = "9999-99-99 99:99:99";
$end = "0000-00-00 00:00:00";
my($section,$type);
-foreach $section ('Received','Delivered') {
+foreach $section ('Received','Delivered','Rejects','Ham','Spam') {
foreach $type ('Volume','Messages','Delayed','Failed','Hosts','Domains','Emails','Edomains') {
$report_totals{$section}{$type} = 0;
}
foreach my $file (@ARGV) {
if ($file =~ /\.gz/) {
unless (open(FILE,"gunzip -c $file |")) {
- print STDERR "Failed to gunzip -c $file: $!";
- next;
+ print STDERR "Failed to gunzip -c $file: $!";
+ next;
}
}
elsif ($file =~ /\.Z/) {
unless (open(FILE,"uncompress -c $file |")) {
- print STDERR "Failed to uncompress -c $file: $!";
- next;
+ print STDERR "Failed to uncompress -c $file: $!";
+ next;
}
}
else {
unless (open(FILE,$file)) {
- print STDERR "Failed to read $file: $!";
- next;
+ print STDERR "Failed to read $file: $!";
+ next;
}
}
#Now parse the filehandle, updating the global variables.
}
-if ($begin eq "9999-99-99 99:99:99") {
- print "**** No valid log lines read\n";
+if ($begin eq "9999-99-99 99:99:99" && ! $emptyOK) {
+ print STDERR "**** No valid log lines read\n";
exit 1;
}
# Print counts of user specified patterns if required.
print_user_patterns() if @user_patterns;
+# Print rejection reasons.
+# print_rejects();
+
# Print totals by transport if required.
print_transport() if $show_transport;
# Print the deliveries per interval as a histogram, unless configured not to.
# First find the maximum in one interval and scale accordingly.
if ($hist_opt > 0) {
- print_histogram("Messages received", @received_interval_count);
- print_histogram("Deliveries", @delivered_interval_count);
+ print_histogram("Messages received", 'message', @received_interval_count);
+ print_histogram("Deliveries", 'delivery', @delivered_interval_count);
}
# Print times on queue if required.
if ($#queue_times >= 0) {
- print_queue_times("all messages", \@queue_bin,$queue_more_than);
- print_queue_times("messages with at least one remote delivery",\@remote_queue_bin,$queue_more_than);
+ print_duration_table("Time spent on the queue", "all messages", \@queue_times, \@qt_all_bin,$qt_all_overflow);
+ print_duration_table("Time spent on the queue", "messages with at least one remote delivery", \@queue_times, \@qt_remote_bin,$qt_remote_overflow);
+}
+
+# Print delivery times if required.
+if ($#delivery_times >= 0) {
+ print_duration_table("Delivery times", "all messages", \@delivery_times, \@dt_all_bin,$dt_all_overflow);
+ print_duration_table("Delivery times", "messages with at least one remote delivery", \@delivery_times, \@dt_remote_bin,$dt_remote_overflow);
+}
+
+# Print rcpt times if required.
+if ($#rcpt_times >= 0) {
+ foreach my $protocol ('all', grep(!/^all$/, sort keys %rcpt_times_bin)) {
+ print_duration_table("Receipt times", "$protocol messages", \@rcpt_times, $rcpt_times_bin{$protocol}, $rcpt_times_overflow{$protocol});
+ }
}
# Print relay information if required.
# Print the league tables, if topcount isn't zero.
if ($topcount > 0) {
+ my($ws_rej, $ws_top50, $ws_rej_row, $ws_top50_row);
+ $ws_rej_row = $ws_top50_row = 0;
+ if ($xls_fh) {
+ $ws_top50 = $workbook->addworksheet('Deliveries');
+ $ws_rej = $workbook->addworksheet('Rejections') if (%rejected_count_by_reason || %rejected_count_by_ip || %spam_count_by_ip);
+ }
+
+ print_league_table("mail rejection reason", \%rejected_count_by_reason, undef, undef, undef, $ws_rej, \$ws_rej_row) if %rejected_count_by_reason;
+
foreach ('Host','Domain','Email','Edomain') {
next unless $do_sender{$_};
- print_league_table("sending \l$_", $received_count{$_}, $received_data{$_},$received_data_gigs{$_});
+ print_league_table("sending \l$_", $received_count{$_}, undef, $received_data{$_},$received_data_gigs{$_}, $ws_top50, \$ws_top50_row);
}
- print_league_table("local sender", \%received_count_user,
- \%received_data_user,\%received_data_gigs_user) if ($local_league_table || $include_remote_users);
+ print_league_table("local sender", \%received_count_user, undef,
+ \%received_data_user,\%received_data_gigs_user, $ws_top50, \$ws_top50_row) if (($local_league_table || $include_remote_users) && %received_count_user);
foreach ('Host','Domain','Email','Edomain') {
next unless $do_sender{$_};
- print_league_table("\l$_ destination", $delivered_count{$_}, $delivered_data{$_},$delivered_data_gigs{$_});
+ print_league_table("\l$_ destination", $delivered_messages{$_}, $delivered_addresses{$_}, $delivered_data{$_},$delivered_data_gigs{$_}, $ws_top50, \$ws_top50_row);
}
- print_league_table("local destination", \%delivered_count_user,
- \%delivered_data_user,\%delivered_data_gigs_user) if ($local_league_table || $include_remote_users);
+ print_league_table("local destination", \%delivered_messages_user, \%delivered_addresses_user, \%delivered_data_user,\%delivered_data_gigs_user, $ws_top50, \$ws_top50_row) if (($local_league_table || $include_remote_users) && %delivered_messages_user);
+
+ print_league_table("rejected ip", \%rejected_count_by_ip, undef, undef, undef, $ws_rej, \$ws_rej_row) if %rejected_count_by_ip;
+ print_league_table("non-rejected spamming ip", \%spam_count_by_ip, undef, undef, undef, $ws_rej, \$ws_rej_row) if %spam_count_by_ip;
+
}
# Print the error statistics if required.
print_errors() if $show_errors;
-if ($html) {
- print "</body>\n</html>\n"
+print $htm_fh "</body>\n</html>\n" if $htm_fh;
+
+
+$txt_fh->close if $txt_fh && ref $txt_fh;
+$htm_fh->close if $htm_fh;
+
+if ($xls_fh) {
+ # close Excel Workbook
+ $ws_global->set_first_sheet();
+ # FIXME: whyever - activate does not work :-/
+ $ws_global->activate();
+ $workbook->close();
}
+
# End of eximstats
git://git.exim.org / exim.git / blobdiff