X-Git-Url: https://git.exim.org/exim.git/blobdiff_plain/514ee161db1166e94b9ee889953f2e9774cee973..96f8f12e212bb3a98f2b1e9ab94a916a62ebd68b:/src/src/eximstats.src

diff --git a/src/src/eximstats.src b/src/src/eximstats.src
index 56721ed62..5e1a0847b 100644
--- a/src/src/eximstats.src
+++ b/src/src/eximstats.src
@@ -1,6 +1,6 @@
-#!PERL_COMMAND -w
+#!PERL_COMMAND
 
-# Copyright (c) 2001 University of Cambridge.
+# Copyright (c) 2001-2017 University of Cambridge.
 # See the file NOTICE for conditions of use and distribution.
 
 # Perl script to generate statistics from one or more Exim log files.
@@ -73,7 +73,7 @@
 # 2001-10-21  Removed -domain flag and added -bydomain, -byhost, and -byemail.
 #             We now generate our main parsing subroutine as an eval statement
 #             which improves performance dramatically when not all the results
-#             are required. We also cache the last timestamp to time convertion.
+#             are required. We also cache the last timestamp to time conversion.
 #
 #             NOTE: 'Top 50 destinations by (message count|volume)' lines are
 #             now 'Top N (host|email|domain) destinations by (message count|volume)'
@@ -142,7 +142,7 @@
 #             in HTML output. Also added code to convert them back with -merge.
 #             Fixed timestamp offsets to convert to seconds rather than minutes.
 #             Updated -merge to work with output files using timezones.
-#             Added cacheing to speed up the calculation of timezone offsets.
+#             Added caching to speed up the calculation of timezone offsets.
 #
 # 2003-02-07  V1.25 Steve Campbell
 #             Optimised the usage of mktime() in the seconds subroutine.
@@ -162,7 +162,7 @@
 #             Bernard Massot.
 #
 # 2003-06-03  V1.28 John Newman
-#             Added in the ability to skip over the parsing and evaulation of
+#             Added in the ability to skip over the parsing and evaluation of
 #             specific transports as passed to eximstats via the new "-nt/.../"
 #             command line argument.  This new switch allows the viewing of
 #             not more accurate statistics but more applicable statistics when
@@ -200,7 +200,7 @@
 #             Added -xls and the ability to specify output files.
 #
 # 2005-04-29  V1.38 Steve Campbell
-#             Use FileHandles for outputing results.
+#             Use FileHandles for outputting 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.
@@ -533,7 +533,7 @@ about how to create charts from the tables.
 
 =head1 AUTHOR
 
-There is a web site at http://www.exim.org - this contains details of the
+There is a website at https://www.exim.org - this contains details of the
 mailing list exim-users@exim.org.
 
 =head1 TO DO
@@ -547,13 +547,23 @@ Merging of xls files is not (yet) possible. Be free to implement :)
 
 =cut
 
+use warnings;
 use integer;
+BEGIN { pop @INC if $INC[-1] eq '.' };
 use strict;
 use IO::File;
+use File::Basename;
 
 # use Time::Local;  # PH/FANF
 use POSIX;
 
+if (@ARGV and $ARGV[0] eq '--version') {
+    print basename($0) . ": $0\n",
+        "build: EXIM_RELEASE_VERSIONEXIM_VARIANT_VERSION\n",
+        "perl(runtime): $]\n";
+        exit 0;
+}
+
 use vars qw($HAVE_GD_Graph_pie $HAVE_GD_Graph_linespoints $HAVE_Spreadsheet_WriteExcel);
 eval { require GD::Graph::pie; };
 $HAVE_GD_Graph_pie = $@ ? 0 : 1;
@@ -598,9 +608,9 @@ $WEEK   =  7 * $DAY;
 use vars qw($total_received_data  $total_received_data_gigs  $total_received_count);
 use vars qw($total_delivered_data $total_delivered_data_gigs $total_delivered_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 $offset_seconds);      #The last time offset convertion done.
+use vars qw($last_timestamp $last_time);        #The last time conversion done.
+use vars qw($last_date $date_seconds);          #The last date conversion done.
+use vars qw($last_offset $offset_seconds);      #The last time offset conversion done.
 use vars qw($localtime_offset);
 use vars qw($i);                                #General loop counter.
 use vars qw($debug);                            #Debug mode?
@@ -614,7 +624,7 @@ use vars qw(%ham_count_by_ip %spam_count_by_ip);
 use vars qw(%rejected_count_by_ip %rejected_count_by_reason);
 use vars qw(%temporarily_rejected_count_by_ip %temporarily_rejected_count_by_reason);
 
-#For use in Speadsheed::WriteExcel
+#For use in Spreadsheet::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);
@@ -757,8 +767,8 @@ sub volume_rounded {
   }
   else {
     # We don't want any rounding to be done.
-    # 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
+    # and we don't need broken formatted output which on one hand avoids numbers from
+    # being interpreted as string by Spreadsheet 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);
@@ -871,10 +881,10 @@ $p;
 # Eg 3h20m5s => 12005
 #######################################################################
 sub unformat_time {
-  my($formated_time) = pop @_;
+  my($formatted_time) = pop @_;
   my $time = 0;
 
-  while ($formated_time =~ s/^(\d+)([wdhms]?)//) {
+  while ($formatted_time =~ s/^(\d+)([wdhms]?)//) {
     $time +=  $1 if ($2 eq '' || $2 eq 's');
     $time +=  $1 * 60 if ($2 eq 'm');
     $time +=  $1 * 60 * 60 if ($2 eq 'h');
@@ -894,6 +904,7 @@ sub unformat_time {
 # POSIX::mktime.  We expect the timestamp to be of the form
 # "$year-$mon-$day $hour:$min:$sec", with month going from 1 to 12,
 # and the year to be absolute (we do the necessary conversions). The
+# seconds value can be followed by decimals, which we ignore. The
 # timestamp may be followed with an offset from UTC like "+$hh$mm"; if the
 # offset is not present, and we have not been told that the log is in UTC
 # (with the -utc option), then we adjust the time by the current local
@@ -917,7 +928,7 @@ sub seconds {
   # Is the timestamp the same as the last one?
   return $last_time if ($last_timestamp eq $timestamp);
 
-  return 0 unless ($timestamp =~ /^((\d{4})\-(\d\d)-(\d\d))\s(\d\d):(\d\d):(\d\d)( ([+-])(\d\d)(\d\d))?/o);
+  return 0 unless ($timestamp =~ /^((\d{4})\-(\d\d)-(\d\d))\s(\d\d):(\d\d):(\d\d)(?:\.\d+)?( ([+-])(\d\d)(\d\d))?/o);
 
   unless ($last_date eq $1) {
     $last_date = $1;
@@ -928,8 +939,8 @@ sub seconds {
   }
   my $time = $date_seconds + ($5 * 3600) + ($6 * 60) + $7;
 
-  # SC. Use cacheing. Also note we want seconds not minutes.
-  #my($this_offset) = ($10 * 60 + $11) * ($9 . "1") if defined $8;
+  # SC. Use caching. Also note we want seconds not minutes.
+  #my($this_offset) = ($10 * 60 + $12) * ($9 . "1") if defined $8;
   if (defined $8 && ($8 ne $last_offset)) {
     $last_offset = $8;
     $offset_seconds = ($10 * 60 + $11) * 60;
@@ -937,7 +948,7 @@ sub seconds {
   }
 
 
-  if (defined $7) {
+  if (defined $8) {
     #$time -= $this_offset;
     $time -= $offset_seconds;
   } elsif (defined $localtime_offset) {
@@ -1650,7 +1661,7 @@ sub top_n_sort {
 
     # 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
+    # href3. Also note that currently we are guaranteed 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};
@@ -1851,12 +1862,23 @@ sub generate_parser {
 
     $length = length($_);
     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);
+    next unless /^
+		(\\d{4}\\-\\d\\d-\\d\\d\\s	# 1: YYYYMMDD HHMMSS
+			(\\d\\d)		# 2: HH
+			:
+			(\\d\\d)		# 3: MM
+			:\\d\\d
+		)
+		(\\.\\d+)?			# 4: subseconds
+		(\s[-+]\\d\\d\\d\\d)?		# 5: tz-offset
+		(\s\\[\\d+\\])?			# 6: pid
+		/ox;
+
+    $tod = defined($5) ?  $1 . $5 : $1;
+    ($m_hour,$m_min) = ($2,$3);
 
     # PH - watch for GMT offsets in the timestamp.
-    if (defined($4)) {
+    if (defined($5)) {
       $extra = 6;
       next if ($length < 44);
     }
@@ -1864,9 +1886,15 @@ sub generate_parser {
       $extra = 0;
     }
 
+    # watch for subsecond precision
+    if (defined($4)) {
+      $extra += length($4);
+      next if ($length < 38 + $extra);
+    }
+
     # PH - watch for PID added after the timestamp.
-    if (defined($5)) {
-      $extra += length($5);
+    if (defined($6)) {
+      $extra += length($6);
       next if ($length < 38 + $extra);
     }
 
@@ -2729,7 +2757,7 @@ sub print_grandtotals {
       if ($messages > 0) {
         @content = ($total_aref->[0], '', $messages, '');
 
-        #Count the number of distict IPs for the Hosts column.
+        #Count the number of distinct IPs for the Hosts column.
         push(@content,scalar(keys %{$total_aref->[1]})) if $do_sender{Host};
 
         #These rows do not have entries for the following columns (if specified)
@@ -3360,8 +3388,8 @@ sub parse_old_eximstat_reports {
         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($modifier,$formatted_time,$count) = ($1,$2,$3);
+          my $seconds = unformat_time($formatted_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');
@@ -3676,7 +3704,7 @@ sub update_relayed {
 #
 #  add_to_totals(\%totals,\@keys,$values);
 #
-# Given a line of space seperated values, add them into the provided hash using @keys
+# Given a line of space separated values, add them into the provided hash using @keys
 # as the hash keys.
 #
 # If the value contains a '%', then the value is set rather than added. Otherwise, we
@@ -3706,7 +3734,7 @@ sub add_to_totals {
 #
 #  line_to_hash(\%hash,\@keys,$line);
 #
-# Given a line of space seperated values, set them into the provided hash
+# Given a line of space separated values, set them into the provided hash
 # using @keys as the hash keys.
 #######################################################################
 sub line_to_hash {
@@ -3772,7 +3800,7 @@ sub html2txt {
 # 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
+# but it's as good as we can get! If it's essential that spacing
 # be preserved precisely, then you get that by not using shell
 # variables.
 #######################################################################
@@ -3814,7 +3842,7 @@ sub set_worksheet_line {
 #######################################################################
 # @rcpt_times = parse_time_list($string);
 #
-# Parse a comma seperated list of time values in seconds given by
+# Parse a comma separated list of time values in seconds given by
 # the user and fill an array.
 #
 # Return a default list if $string is undefined.