File: logresolvemerge.pl

package info (click to toggle)
awstats 8.0-4
  • links: PTS
  • area: main
  • in suites: forky
  • size: 13,244 kB
  • sloc: perl: 40,711; xml: 1,785; javascript: 1,493; java: 359; sh: 152; makefile: 40; php: 29
file content (813 lines) | stat: -rwxr-xr-x 33,291 bytes parent folder | download | duplicates (7)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
#!/usr/bin/perl
#-----------------------------------------------------------------------------
# Allows you to get one unique output log file, sorted on date,
# built from particular sources.
# This tool is part of AWStats log analyzer but can be use
# alone for any other log analyzer.
# See COPYING.TXT file about AWStats GNU General Public License.
#-----------------------------------------------------------------------------

use strict; no strict "refs";
#use diagnostics;
use POSIX qw( strftime );


#-----------------------------------------------------------------------------
# Defines
#-----------------------------------------------------------------------------

# ENABLETHREAD --> COMMENT THIS BLOCK TO USE A THREADED VERSION
my $UseThread=0;
&Check_Thread_Use();
my $NbOfDNSLookupAsked = 0;
my %threadarray = ();
my %MyDNSTable = ();
my %TmpDNSLookup = ();

# ENABLETHREAD --> UNCOMMENT THIS BLOCK TO USE A THREADED VERSION
#my $UseThread=1;
#&Check_Thread_Use();
#my $NbOfDNSLookupAsked : shared = 0;
#my %threadarray : shared = ();
#my %MyDNSTable : shared = ();
#my %TmpDNSLookup : shared = ();


# ---------- Init variables --------
use vars qw/ $REVISION $VERSION /;
$REVISION = '20140126';
$VERSION="1.2 (build $REVISION)";

use vars qw/ $NBOFLINESFORBENCHMARK /;
$NBOFLINESFORBENCHMARK=8192;

use vars qw/
$DIR $PROG $Extension
$Debug $ShowSteps $AddFileNum $AddFileName $LastLogNum $PrintFields
$MaxNbOfThread $DNSLookup $DNSCache $DirCgi $DirData $DNSLookupAlreadyDone
$NbOfLinesShowsteps $AFINET $QueueCursor $StopOnFirstEof $IgnoreMissing
/;
$DIR='';
$PROG='';
$Extension='';
$Debug=0;
$ShowSteps=0;
$AddFileNum=0;
$AddFileName=0;
$LastLogNum=0;
$PrintFields=0;
$MaxNbOfThread=0;
$DNSLookup=0;
$DNSCache='';
$DirCgi='';
$DirData='';
$DNSLookupAlreadyDone=0;
$NbOfLinesShowsteps=0;
$AFINET='';
$StopOnFirstEof=0;
$IgnoreMissing=0;

# ---------- Init arrays --------
use vars qw/
@SkipDNSLookupFor
@ParamFile
@Fields
/;
# ---------- Init hash arrays --------
use vars qw/
%LogFileToDo %linerecord %timerecord %corrupted
%QueueHostsToResolve %QueueRecords
/;
%LogFileToDo = %linerecord = %timerecord = %corrupted = ();
%QueueHostsToResolve = %QueueRecords = ();

# DRA2: the order of timerecords are kept here, each index in the array is the filerecordnumber, which
# DRA2: is used as the key for the other hashes
use vars qw/
@timerecordorder
/;
@timerecordorder = ();

# ---------- External Program variables ----------
# For gzip compression
my $zcat = 'gzip -cd';
my $zcat_file = '\.gz$';
# For bz2 compression
my $bzcat = 'bzip2 -cd';
my $bzcat_file = '\.bz2$';
# For xz compression
my $xzcat = 'xz -cd';
my $xzcat_file = '\.xz$';


#-----------------------------------------------------------------------------
# Functions
#-----------------------------------------------------------------------------

#------------------------------------------------------------------------------
# Function:		Add all files of a specific directory
# Parameters:	$message
# Input:		Directory path
# Output:		None
# Return:		Array with list of files
#------------------------------------------------------------------------------
sub addDirectory {
    my ($dir,@list) = @_;
    my $dirH;
    opendir($dirH, $dir) || die ("Can't open '$dir'");
    while ($_ = readdir($dirH) ) {
		if (-f "$dir/$_") {
		    push @list, "$dir/$_";
		}
    }
    closedir($dirH);
    return @list;
}

#------------------------------------------------------------------------------
# Function:		Write an error message and exit
# Parameters:	$message
# Input:		None
# Output:		None
# Return:		None
#------------------------------------------------------------------------------
sub error {
	print STDERR "Error: $_[0].\n";
    exit 1;
}

#------------------------------------------------------------------------------
# Function:		Write a debug message
# Parameters:	$message
# Input:		$Debug
# Output:		None
# Return:		None
#------------------------------------------------------------------------------
sub debug {
	my $level = $_[1] || 1;
	if ($Debug >= $level) { 
		my $debugstring = $_[0];
		print "DEBUG $level - ".localtime(time())." : $debugstring\n";
	}
}

#------------------------------------------------------------------------------
# Function:		Write a warning message
# Parameters:	$message
# Input:		$Debug
# Output:		None
# Return:		None
#------------------------------------------------------------------------------
sub warning {
	my $messagestring=shift;
	if ($Debug) { debug("$messagestring",1); }
   	print STDERR "$messagestring\n";
}

#-----------------------------------------------------------------------------
# Function:     Return 1 if string contains only ascii chars
# Input:        String
# Return:       0 or 1
#-----------------------------------------------------------------------------
sub IsAscii {
	my $string=shift;
	if ($Debug) { debug("IsAscii($string)",5); }
	if ($string =~ /^[\w\+\-\/\\\.%,;:=\"\'&?!\s]+$/) {
		if ($Debug) { debug(" Yes",5); }
		return 1;		# Only alphanum chars (and _) or + - / \ . % , ; : = " ' & ? space \t
	}
	if ($Debug) { debug(" No",5); }
	return 0;
}

#-----------------------------------------------------------------------------
# DRA Function:     Return 1 if DNS lookup should be skipped
# Input:        String
# Return:       0 or 1
#-----------------------------------------------------------------------------
sub SkipDNSLookup {
	foreach my $match (@SkipDNSLookupFor) { if ($_[0] =~ /$match/i) { return 1; } }
	0; # Not in @SkipDNSLookupFor
}

#-----------------------------------------------------------------------------
# Function:     Function that wait for DNS lookup (can be threaded)
# Input:        String
# Return:       0 or 1
#-----------------------------------------------------------------------------
sub MakeDNSLookup {
	my $ipaddress=shift;
 	$NbOfDNSLookupAsked++;
	use Socket; $AFINET=AF_INET;
	my $tid=0;
	$tid=$MaxNbOfThread?eval("threads->self->tid()"):0;
	if ($Debug) { debug("  ***** Thread id $tid: MakeDNSlookup started (for $ipaddress)",4); }
	my $lookupresult=gethostbyaddr(pack("C4",split(/\./,$ipaddress)),$AFINET);	# This is very slow, may took 20 seconds
	if (! $lookupresult || $lookupresult =~ /^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$/ || ! IsAscii($lookupresult)) {
		$TmpDNSLookup{$ipaddress}='*';
	}
	else {
		$TmpDNSLookup{$ipaddress}=$lookupresult;
	}
	if ($Debug) { debug("  ***** Thread id $tid: MakeDNSlookup done ($ipaddress resolved into $TmpDNSLookup{$ipaddress})",4); }
	delete $threadarray{$ipaddress};
	return;
}

#-----------------------------------------------------------------------------
# Function:     WriteRecordsReadyInQueue
# Input:        -
# Return:       0
#-----------------------------------------------------------------------------
sub WriteRecordsReadyInQueue {
	my $logfilechosen=shift;
	if ($Debug) { debug("Check head of queue to write records ready to flush (QueueCursor=$QueueCursor, QueueSize=".(scalar keys %QueueRecords).")",4); }
	while ( $QueueHostsToResolve{$QueueCursor} && ( ($QueueHostsToResolve{$QueueCursor} eq '*') || ($MyDNSTable{$QueueHostsToResolve{$QueueCursor}}) || ($TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}}) ) ) {
		# $QueueCursor point to a ready record
		if ($QueueHostsToResolve{$QueueCursor} eq '*') {
			if ($Debug) { debug(" First elem in queue is ready. No change on it. We pull it.",4); }
		}
		else {
			if ($MyDNSTable{$QueueHostsToResolve{$QueueCursor}}) {
				if ($MyDNSTable{$QueueHostsToResolve{$QueueCursor}} ne '*') {
					$QueueRecords{$QueueCursor}=~s/$QueueHostsToResolve{$QueueCursor}/$MyDNSTable{$QueueHostsToResolve{$QueueCursor}}/;
					if ($Debug) { debug(" First elem in queue has been resolved (found in MyDNSTable $MyDNSTable{$QueueHostsToResolve{$QueueCursor}}). We pull it.",4); }
				}
			}
			elsif ($TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}}) {
				if ($TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}} ne '*') {
					$QueueRecords{$QueueCursor}=~s/$QueueHostsToResolve{$QueueCursor}/$TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}}/;
					if ($Debug) { debug(" First elem in queue has been resolved (found in TmpDNSLookup $TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}}). We pull it.",4); }
				}
			}
		}
		# Record is ready, we output it.
		if ($AddFileNum)  { print "$logfilechosen "; }
		if ($AddFileName) { print "$LogFileToDo{$logfilechosen} "; }
		# see if we need to dump fields
		if ($PrintFields && $LastLogNum != $logfilechosen){
			print($Fields[$logfilechosen]."\n");
			$LastLogNum = $logfilechosen;
		}
		print "$QueueRecords{$QueueCursor}\n";
		delete $QueueRecords{$QueueCursor};
		delete $QueueHostsToResolve{$QueueCursor};
		$QueueCursor++;
	}
	return 0;
}

#-----------------------------------------------------------------------------
# Function:     Check if thread are enabled or not
# Input:        -
# Return:       -
#-----------------------------------------------------------------------------
sub Check_Thread_Use {
	if ($] >= 5.008) {	for (0..@ARGV-1) { if ($ARGV[$_] =~ /^-dnslookup[:=](\d{1,2})/i) {
		if ($UseThread) {
			if (!eval ('require "threads.pm";')) { &error("Failed to load perl module 'threads' required for multi-threaded DNS lookup".($@?": $@":"")); }
			if (!eval ('require "threads/shared.pm";')) { &error("Failed to load perl module 'threads::shared' required for multi-threaded DNS lookup".($@?": $@":"")); }
		}
		else { &error("Multi-thread is disabled in default version of this script.\nYou must manually edit the file '$0' to comment/uncomment all\nlines marked with 'ENABLETHREAD' string to enable multi-threading"); }
		} }
	}
}


#-----------------------------------------------------------------------------
# MAIN
#-----------------------------------------------------------------------------
($DIR=$0) =~ s/([^\/\\]*)$//; ($PROG=$1) =~ s/\.([^\.]*)$//; $Extension=$1;

# Get parameters (Note: $MaxNbOfThread is already known
my $cpt=1;
for (0..@ARGV-1) {
	if ($ARGV[$_] =~ /^-/) {
		if ($ARGV[$_] =~ /debug=(\d)/i) { $Debug=$1; }
		elsif ($ARGV[$_] =~ /dnscache=/i) { $DNSLookup||=2; $DNSCache=$ARGV[$_]; $DNSCache =~ s/-dnscache=//; }
		elsif ($ARGV[$_] =~ /dnslookup[:=](\d{1,2})/i) { $DNSLookup||=1; $MaxNbOfThread=$1; }
		elsif ($ARGV[$_] =~ /dnslookup/i) { $DNSLookup||=1; }
		elsif ($ARGV[$_] =~ /showsteps/i) { $ShowSteps=1; }
		elsif ($ARGV[$_] =~ /addfilenum/i) { $AddFileNum=1; }
		elsif ($ARGV[$_] =~ /addfilename/i) { $AddFileName=1; }
		elsif ($ARGV[$_] =~ /stoponfirsteof/i) { $StopOnFirstEof=1; }
		elsif ($ARGV[$_] =~ /printfields/i) { $PrintFields=1; }
		elsif ($ARGV[$_] =~ /ignoremissing/i) { $IgnoreMissing=1; }
		else { print "Unknown argument $ARGV[$_] ignored\n"; }
	}
	elsif ($ARGV[$_] =~ /addfolder=(.*)$/i) {
   		@ParamFile = addDirectory($1, @ParamFile);
	}
	else {
		push @ParamFile, $ARGV[$_];
		$cpt++;
	}
}
if ($Debug) { $|=1; }

if ($Debug) {
	debug(ucfirst($PROG)." - $VERSION - Perl $^X $]",1);
	debug("DNSLookup=$DNSLookup");
	debug("DNSCache=$DNSCache");
	debug("MaxNbOfThread=$MaxNbOfThread");
}

# Disallow MaxNbOfThread and Perl < 5.8
if ($] < 5.008 && $MaxNbOfThread) {
	error("Multi-threaded DNS lookup is only supported with Perl 5.8 or higher (not $]). Use -dnslookup option instead");
}

# Warning, there is a memory hole in ActiveState perl version (in delete functions)
if ($^X =~ /activestate/i || $^X =~ /activeperl/i) {
	# TODO Add a warning

}

if (scalar @ParamFile == 0) {
	print "----- $PROG $VERSION (c) Laurent Destailleur -----\n";
	print "$PROG allows you to get one unique output log file, sorted on date,\n";
	print "built from particular sources:\n";
	print " - It can read several input log files,\n";
	print " - It can read .gz/.bz2/.xz log files,\n";
	print " - It can also makes a fast reverse DNS lookup to replace\n";
	print "   all IP addresses into host names in resulting log file.\n";
	print "$PROG comes with ABSOLUTELY NO WARRANTY. It's a free software\n";
	print "distributed with a GNU General Public License (See COPYING.txt file).\n";
	print "$PROG is part of AWStats but can be used alone as a log merger\n";
	print "or resolver before using any other log analyzer.\n";
	print "\n";
	print "Usage:\n";
	print "  $PROG.$Extension [options] file\n";
	print "  $PROG.$Extension [options] file1 ... filen\n";
	print "  $PROG.$Extension [options] *.*\n";
	print "  $PROG.$Extension [options] addfolder=dirname\n";
	print "  perl $PROG.$Extension [options] *.* > newfile\n";
	print "Options:\n";
	print "  -dnslookup      make a reverse DNS lookup on IP adresses\n";
	print "  -dnslookup=n    same with a n parallel threads instead of serial requests\n";
	print "  -dnscache=file  make DNS lookup from cache file first before network lookup\n";
	print "  -showsteps      print on stderr benchmark information every $NBOFLINESFORBENCHMARK lines\n";
	print "  -addfilenum     if used with several files, file number can be added in first\n";
	print "  -addfilename    if used with several files, file name can be added in first\n";
	print "                  field of output file. This can be used to add a cluster id\n";
	print "                  when log files come from several load balanced computers.\n";
	print "  -stoponfirsteof Stop processing when any logfile reaches end-of-file.\n";
	print "  -printfields    For IIS or W3C logs, prints the latest field header for\n";
	print "                  the currentlog file when switching between log file entries\n";
	print "                  so that the parsercan automatically determine which fields\n";
	print "                  are avaiable.\n";
	print "  -ignoremissing  will not fail if a log file is missing\n";
	print "\n";
	
	print "This runs $PROG in command line to open one or several\n";
	print "server log files to merge them (sorted on date) and/or to make a reverse\n";
	print "DNS lookup (if asked). The result log file is sent on standard output.\n";
	print "Note: $PROG is not a 'sort' tool to sort one file. It's a\n";
	print "software able to output sorted log records (with a reverse DNS lookup\n";
	print "included or not) even if log records are dispatched in several files.\n";
	print "Each of thoose files must be already independently sorted itself\n";
	print "(but that is the case in all web server log files). So you can use it\n";
	print "for load balanced log files or to group several old log files.\n";
	print "\n";
	print "Don't forget that the main goal of logresolvemerge is to send log records to\n";
	print "a log analyzer in a sorted order without merging files on disk (NO NEED\n";
	print "OF DISK SPACE AT ALL) and without loading files into memory (NO NEED\n";
	print "OF MORE MEMORY). Choose of output records is done on the fly.\n";
	print "\n";
	print "So logresolvemerge is particularly useful when you want to output several\n";
	print "and/or large log files in a fast process, with no use of disk or\n";
	print "more memory, and in a chronological order through a pipe (to be used by a log\n";
	print "analyzer).\n";
	print "\n";
	print "Note: If input records are not 'exactly' sorted but 'nearly' sorted (this\n";
	print "occurs with heavy servers), this is not a problem, the output will also\n";
	print "be 'nearly' sorted but a few log analyzers (like AWStats) knowns how to deal\n";
	print "with such logs.\n";
	print "\n";
	print "WARNING: If log files are old MAC text files (lines ended with CR char), you\n";
	print "can't run this tool on Win or Unix platforms.\n";
	print "\n";
	print "WARNING: Because of memory holes in ActiveState Perl version, use another\n";
	print "Perl interpreter if you need to process large log files.\n";
	print "\n";
	print "Now supports/detects:\n";
	print "  Automatic detection of log format\n";
	print "  Files can be .gz/.bz2/.xz files if gzip/bzip2/xz tools are available in PATH.\n";
	print "  Multithreaded reverse DNS lookup (several parallel requests) with Perl 5.8+.\n";
	print "New versions and FAQ at http://www.awstats.org\n";
	exit 0;
}

# Get current time
my $nowtime=time;
my ($nowsec,$nowmin,$nowhour,$nowday,$nowmonth,$nowyear) = localtime($nowtime);
if ($nowyear < 100) { $nowyear+=2000; } else { $nowyear+=1900; }
my $nowsmallyear=$nowyear;$nowsmallyear =~ s/^..//;
if (++$nowmonth < 10) { $nowmonth = "0$nowmonth"; }
if ($nowday < 10) { $nowday = "0$nowday"; }
if ($nowhour < 10) { $nowhour = "0$nowhour"; }
if ($nowmin < 10) { $nowmin = "0$nowmin"; }
if ($nowsec < 10) { $nowsec = "0$nowsec"; }
# Get tomorrow time (will be used to discard some record with corrupted date (future date))
my ($tomorrowsec,$tomorrowmin,$tomorrowhour,$tomorrowday,$tomorrowmonth,$tomorrowyear) = localtime($nowtime+86400);
if ($tomorrowyear < 100) { $tomorrowyear+=2000; } else { $tomorrowyear+=1900; }
my $tomorrowsmallyear=$tomorrowyear;$tomorrowsmallyear =~ s/^..//;
if (++$tomorrowmonth < 10) { $tomorrowmonth = "0$tomorrowmonth"; }
if ($tomorrowday < 10) { $tomorrowday = "0$tomorrowday"; }
if ($tomorrowhour < 10) { $tomorrowhour = "0$tomorrowhour"; }
if ($tomorrowmin < 10) { $tomorrowmin = "0$tomorrowmin"; }
if ($tomorrowsec < 10) { $tomorrowsec = "0$tomorrowsec"; }
my $timetomorrow=$tomorrowyear.$tomorrowmonth.$tomorrowday.$tomorrowhour.$tomorrowmin.$tomorrowsec;	

# Init other parameters
$NBOFLINESFORBENCHMARK--;
if ($ENV{"GATEWAY_INTERFACE"}) { $DirCgi=''; }
if ($DirCgi && !($DirCgi =~ /\/$/) && !($DirCgi =~ /\\$/)) { $DirCgi .= '/'; }
if (! $DirData || $DirData eq '.') { $DirData=$DIR; }	# If not defined or chosen as "." value then DirData is current dir
if (! $DirData)  { $DirData='.'; }						# If current dir not defined then we put it to "."
$DirData =~ s/\/$//;

#my %monthlib =  ( "01","$Message[60]","02","$Message[61]","03","$Message[62]","04","$Message[63]","05","$Message[64]","06","$Message[65]","07","$Message[66]","08","$Message[67]","09","$Message[68]","10","$Message[69]","11","$Message[70]","12","$Message[71]" );
# monthnum must be in english because it's used to translate log date in apache log files which are always in english
my %monthnum =  ( "Jan","01","jan","01","Feb","02","feb","02","Mar","03","mar","03","Apr","04","apr","04","May","05","may","05","Jun","06","jun","06","Jul","07","jul","07","Aug","08","aug","08","Sep","09","sep","09","Oct","10","oct","10","Nov","11","nov","11","Dec","12","dec","12" );

if ($DNSCache) {
	if ($Debug) { debug("Load DNS Cache file $DNSCache",2); }
	open(CACHE, "<$DNSCache") or error("Can't open cache file $DNSCache");
	while (<CACHE>) {
		my ($time, $ip, $name) = split;
        if ($ip && $name) {
            $name="$ip" if $name eq '*';
    		$MyDNSTable{$ip}=$name;
        }
	}
	close CACHE;
}

#-----------------------------------------------------------------------------
# PROCESSING CURRENT LOG(s)
#-----------------------------------------------------------------------------
my $NbOfLinesRead=0;
my $NbOfLinesParsed=0;
my $logfilechosen=0;
my $starttime=time();

# Define the LogFileToDo list
$cpt=1;
foreach my $key (0..(@ParamFile-1)) {
	if (($ParamFile[$key] !~ /\*/ && $ParamFile[$key] !~ /\?/) || $ParamFile[$key] =~ /\|$/) {

		if ($Debug) { debug("DBG1 Log file $ParamFile[$key] is added to LogFileToDo with number $cpt."); }
		# Check for supported compression 
		if ($ParamFile[$key] =~ /$zcat_file/) {
			if ($Debug) { debug("GZIP compression detected for Log file $ParamFile[$key]."); }
			# Modify the name to include the zcat command
			$ParamFile[$key] = $zcat . ' ' . $ParamFile[$key] . ' |';
		}
		elsif ($ParamFile[$key] =~ /$bzcat_file/) {
			if ($Debug) { debug("BZ2 compression detected for Log file $ParamFile[$key]."); }
			# Modify the name to include the bzcat command
			$ParamFile[$key] = $bzcat . ' ' . $ParamFile[$key] . ' |';
		}
		elsif ($ParamFile[$key] =~ /$xzcat_file/) {
			if ($Debug) { debug("XZ compression detected for Log file $ParamFile[$key]."); }
			# Modify the name to include the xzcat command
			$ParamFile[$key] = $xzcat . ' ' . $ParamFile[$key] . ' |';
		}

		$LogFileToDo{$cpt}=@ParamFile[$key];
		$cpt++;
		
	}
    else {
        my $DirFile=$ParamFile[$key]; $DirFile =~ s/([^\/\\]*)$//;
        $ParamFile[$key] = $1;
        if ($DirFile eq '') { $DirFile = '.'; }
        $ParamFile[$key] =~ s/\./\\\./g;
        $ParamFile[$key] =~ s/\*/\.\*/g;
        $ParamFile[$key] =~ s/\?/\./g;
        if ($Debug) { debug("Search for file \"$ParamFile[$key]\" into \"$DirFile\""); }
        opendir(DIR,"$DirFile");
        my @filearray = sort readdir DIR;
        close DIR;
        foreach my $i (0..$#filearray) {
            if ("$filearray[$i]" =~ /^$ParamFile[$key]$/ && "$filearray[$i]" ne "." && "$filearray[$i]" ne "..") {

                if ($Debug) { debug("DBG2 Log file $filearray[$i] is added to LogFileToDo with number $cpt."); }
                # Check for supported compression
                if ($filearray[$i] =~ /$zcat_file/) {
                    if ($Debug) { debug("GZIP compression detected for Log file $filearray[$i]."); }
                    # Modify the name to include the zcat command
                    $LogFileToDo{$cpt}=$zcat . ' ' . "$DirFile/$filearray[$i]" . ' |';
                }
                elsif ($filearray[$i] =~ /$bzcat_file/) {
                    if ($Debug) { debug("BZ2 compression detected for Log file $filearray[$i]."); }
                    # Modify the name to include the bzcat command
                    $LogFileToDo{$cpt}=$bzcat . ' ' . "$DirFile/$filearray[$i]" . ' |';
                }
                elsif ($filearray[$i] =~ /$xzcat_file/) {
                    if ($Debug) { debug("XZ compression detected for Log file $filearray[$i]."); }
                    # Modify the name to include the xzcat command
                    $LogFileToDo{$cpt}=$xzcat . ' ' . "$DirFile/$filearray[$i]" . ' |';
                }
                else {
                    $LogFileToDo{$cpt}="$DirFile/$filearray[$i]";
                }
                $cpt++;
                
            }
        }
    }
}

# If no files to process
if (scalar keys %LogFileToDo == 0) {
	error("No input log file found");
}

# Open all log files
if ($Debug) { debug("Start of processing ".(scalar keys %LogFileToDo)." log file(s), $MaxNbOfThread threads max"); }
foreach my $logfilenb (keys %LogFileToDo) {
	if ($Debug) { debug("Open log file number $logfilenb: \"$LogFileToDo{$logfilenb}\""); }
	if ($IgnoreMissing){
		if (!open("LOG$logfilenb","$LogFileToDo{$logfilenb}")){
			debug("Couldn't open log file \"$LogFileToDo{$logfilenb}\" : $!");
			delete $LogFileToDo{$logfilenb};
		}
	}else{
		open("LOG$logfilenb","$LogFileToDo{$logfilenb}") || error("Couldn't open log file \"$LogFileToDo{$logfilenb}\" : $!");
	}
	binmode "LOG$logfilenb";	# To avoid pb of corrupted text log files with binary chars.
}

$QueueCursor=1;
STOPONFIRSTEOF: while (1 == 1)
{
	# BEGIN Read new record
	# For each log file if logfilechosen is 0
	# If not, we go directly to log file instead of iterating over all keys for a match
	#----------------------------------------------------------------------------------
    my @readlist;
	if($logfilechosen == 0) {
	    @readlist = keys %LogFileToDo;
	} else {
	    @readlist = ($logfilechosen);
	}
	foreach my $logfilenb (@readlist)
	{
		if ($Debug) { debug("Search next record in file number $logfilenb",3); }
		# Read chosen log file until we found a record with good date or reaching end of file
		while (1 == 1) {
			my $LOG="LOG$logfilenb";
			$_=<$LOG>;	# Read new line
			if (! $_) 
			{							# No more records in log file number $logfilenb
				if ($Debug) { debug(" No more records in file number $logfilenb",2); }
				delete $LogFileToDo{$logfilenb};
				if ($StopOnFirstEof) 
				{
					if ($Debug) { debug("Exiting loop due to EOF of logfile $logfilenb",1); }
					last STOPONFIRSTEOF;
				}
				last;
			}
		
			# Get the latest Fields header for printing IIS and W3C logs
			if ($PrintFields && $_ =~ m/#Fields:/){
				my $field = $_;
				# strip whitespace
				$field =~ s/^\s+|\s+$//g;
				if (!$Fields[$logfilenb] || $field != $Fields[$logfilenb]){
					$Fields[$logfilenb] = $field;
					debug("Found new fields in $logfilenb: $Fields[$logfilenb]");
				}
			}
			
			$NbOfLinesRead++;
			chomp $_; s/\r$//;

			if (/^#/) { next; }									# Ignore comment lines (ISS writes such comments)
			if (/^!!/) { next; }								# Ignore comment lines (Webstar writes such comments)
			if (/^$/) { next; }									# Ignore blank lines (With ISS: happens sometimes, with Apache: possible when editing log file)

			$linerecord{$logfilenb}=$_; 

			# Check filters
			#----------------------------------------------------------------------

			# Split YYYY-MM-DD HH:MM:SS
			#    or DD/Month/YYYY:HH:MM:SS
			#    or MM/DD/YY\tHH:MM:SS
			#    or 9999.999
 			#    or Month DD HH:MM:SS
			my $year=0; my $month=0; my $day=0; my $hour=0; my $minute=0; my $second=0;
			if ($_ =~ /(\d\d\d\d)-(\d\d)-(\d\d)\s(\d\d):(\d\d):(\d\d)/) { $year=$1; $month=$2; $day=$3; $hour=$4; $minute=$5; $second=$6; }
			elsif ($_ =~ /\[(\d?\d)[\/:\s](\w+)[\/:\s](\d\d\d\d)[\/:\s](\d\d)[\/:\s](\d\d)[\/:\s](\d\d) /) { $year=$3; $month=$2; $day=$1; $hour=$4; $minute=$5; $second=$6; }
			elsif ($_ =~ /\w+ (\w+) {1,2}(\d?\d) (\d\d)[\/:\s](\d\d)[\/:\s](\d\d) (\d\d\d\d)/) { $year=$6; $month=$1; $day=$2; $hour=$3; $minute=$4; $second=$5; }
			elsif ($_ =~ /^(\d\d\d\d+\.\d\d\d) /)
			{
				my $timetime = strftime('%Y-%m-%d-%T', gmtime($1));
				$timetime =~ /(\d\d\d\d)-(\d\d)-(\d\d)-(\d\d):(\d\d):(\d\d)/;
				$year=$1; $month=$2; $day=$3; $hour=$4; $minute=$5; $second=$6;
			}
 			elsif ($_ =~ /(\w+)\s\s?(\d?\d) (\d\d):(\d\d):(\d\d) /) {	# Month DD HH:MM:SS
 				$month=$1; $day=$2; $hour=$3; $minute=$4; $second=$5;
 				if (($monthnum{$month}>$monthnum{$nowmonth}) || ($monthnum{$month}==$monthnum{$nowmonth} &&  $day>$nowday)) {
 					$year=$nowyear-1;
 				}
                else { $year=$nowyear; }
 			}
			if (length $day == 1) { $day = "0".$day; }

			if ($monthnum{$month}) { $month=$monthnum{$month}; }	# Change lib month in num month if necessary

			# Create $timerecord like YYYYMMDDHHMMSS
	 		$timerecord{$logfilenb}=int("$year$month$day$hour$minute$second");
			if ($timerecord{$logfilenb}<10000000000000) {
				if ($Debug) { debug(" This record is corrupted (no date found)",3); }
				$corrupted{$logfilenb}++;
				next;
			}
			if ($Debug) { debug(" This is next record for file $logfilenb : timerecord=$timerecord{$logfilenb}",3); }
			
			# Sort and insert into timerecordorder, oldest at end/back of array
			# At the beginning, timerecordorder is empty. Then beceause the first pass is
			# a loop on each file to read each first line, the timerecordorder size is
			# number of input files.
			# After, each new loop, read only one new line, so timerecordorder size increase
			# by one but decrease just after by the pop command later.
			my $inserted=0;
			for(my $c=$#timerecordorder; $c>=0 ; $c--) {
			    if($timerecord{$logfilenb} <= $timerecord{$timerecordorder[$c]})
			    {
    				# Is older or equal than index at $c, add after
				    $timerecordorder[$c + 1]=$logfilenb;
				    $inserted = 1;
				    last;
			    } else {
				    $timerecordorder[$c + 1]=$timerecordorder[$c];
			    }
			}
			if(! $inserted) {
			    $timerecordorder[0] = $logfilenb;
			}

			last;
		}
	}
	# END Read new lines for each log file. After this, following var are filled
	# $timerecord{$logfilenb}
	# @timerecordorder array

	# We choose which record of which log file to process
	if ($Debug) { debug("Choose which record of which log file to process",3); }
	$logfilechosen=pop(@timerecordorder);
	if(!defined($logfilechosen)) { last; }              # No more record to process 
	
	# Record is chosen
	if ($Debug) { debug(" We chose to qualify record of file number $logfilechosen",3); }
	if ($Debug) { debug("  Record is $linerecord{$logfilechosen}",3); }
			
	# Record is approved. We found a new line to parse in file number $logfilechosen
	#-------------------------------------------------------------------------------
	$NbOfLinesParsed++;
	if ($ShowSteps) {
		if ((++$NbOfLinesShowsteps & $NBOFLINESFORBENCHMARK) == 0) {
			my $delay=(time()-$starttime)||1;
			print STDERR "$NbOfLinesParsed lines processed (".(1000*$delay)." ms, ".int($NbOfLinesShowsteps/$delay)." lines/seconds)\n";
		}
	}

	# Do DNS lookup
	#--------------------
	my $Host='';
	my $ip=0;
	if ($DNSLookup) {			# DNS lookup is 1 or 2
		if ($linerecord{$logfilechosen} =~ /(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})/) { $ip=4; $Host=$1; }	# IPv4
		elsif ($linerecord{$logfilechosen} =~ /([0-9A-F]*:)/i) { $ip=6; $Host=$1; }						# IPv6
		if ($ip) {
			# Check in static DNS cache file
			if ($MyDNSTable{$Host}) {
				if ($Debug) { debug("  DNS lookup asked for $Host and found in static DNS cache file: $MyDNSTable{$Host}",4); }
			}
			elsif ($DNSLookup==1) {
				# Check in session cache (dynamic DNS cache file + session DNS cache)
				if (! $threadarray{$Host} && ! $TmpDNSLookup{$Host}) {
					if (@SkipDNSLookupFor && &SkipDNSLookup($Host)) {
						$TmpDNSLookup{$Host}='*';
						if ($Debug) { debug("  No need of reverse DNS lookup for $Host, skipped at user request.",4); }
					}
					else {
						if ($ip == 4) {
							# Create or not a new thread
							if ($MaxNbOfThread) {
								if (! $threadarray{$Host}) {	# No thread already launched for $Host
									while ((scalar keys %threadarray) >= $MaxNbOfThread) {
										if ($Debug) { debug(" $MaxNbOfThread thread running reached, so we wait",4); }
										sleep 1;
									}
									$threadarray{$Host}=1;		# Semaphore to tell thread for $Host is active
#									my $t = new Thread \&MakeDNSLookup, $Host;
									my $t = threads->create(sub { MakeDNSLookup($Host) });
									if (! $t) { error("Failed to create new thread"); }
									if ($Debug) { debug(" Reverse DNS lookup for $Host queued in thread ".$t->tid,4); }
									$t->detach();	# We don't need to keep return code
								}
								else {
									if ($Debug) { debug(" Reverse DNS lookup for $Host already queued in a thread"); }
								}
								# Here, this is the only way, $TmpDNSLookup{$Host} can be not defined
							} else {
								&MakeDNSLookup($Host);
								if ($Debug) { debug("  Reverse DNS lookup for $Host done: $TmpDNSLookup{$Host}",4); }
							}				
						}
						elsif ($ip == 6) {
							$TmpDNSLookup{$Host}='*';
							if ($Debug) { debug("  Reverse DNS lookup for $Host not available for IPv6",4); }
						}
					}
				} else {
					if ($Debug) { debug("  Reverse DNS lookup already queued or done for $Host: $TmpDNSLookup{$Host}",4); }
				}
			}
			else {
				if ($Debug) { debug("  DNS lookup by static DNS cache file asked for $Host but not found.",4); }
			}
		}
		else {
			if ($Debug) { debug("  DNS lookup asked for $Host but this is not an IP address.",4); }
			$DNSLookupAlreadyDone=$LogFileToDo{$logfilechosen};
		}
	}
	else {
		if ($linerecord{$logfilechosen} =~ /(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})/) { $ip=4; $Host=$1; }	# IPv4
		elsif ($linerecord{$logfilechosen} =~ /([0-9A-F]*:)/i) { $ip=6; $Host=$1; }						# IPv6
		if ($Debug) { debug("  No DNS lookup asked.",4); }
	}

	# Put record in record queue
	if ($Debug) { debug("Add record $NbOfLinesParsed in record queue (with host to resolve = ".($Host?$Host:'*').")",4); }
	$QueueRecords{$NbOfLinesParsed}=$linerecord{$logfilechosen};

	# Put record in host queue
	# If there is a host to resolve, we add line to queue with value of host to resolve
	# $Host is '' (no ip found) or is ip
	if ($DNSLookup==0) {
		$QueueHostsToResolve{$NbOfLinesParsed}='*';
	}
	if ($DNSLookup==1) { 
		$QueueHostsToResolve{$NbOfLinesParsed}=$Host?$Host:'*';
	}
	if ($DNSLookup==2) {
		$QueueHostsToResolve{$NbOfLinesParsed}=$MyDNSTable{$Host}?$Host:'*';
	}

	# Print all records in head of queue that are ready
	&WriteRecordsReadyInQueue($logfilechosen);
	
}	# End of processing new record. Loop on next one.

if ($Debug) { debug("End of processing log file(s)"); }

# Close all log files
foreach my $logfilenb (keys %LogFileToDo) {
	if ($Debug) { debug("Close log file number $logfilenb"); }
	close("LOG$logfilenb") || error("Command for pipe '$LogFileToDo{$logfilenb}' failed");
}

while ( $QueueHostsToResolve{$QueueCursor} && $QueueHostsToResolve{$QueueCursor} ne '*' && ! $MyDNSTable{$QueueHostsToResolve{$QueueCursor}} && ! $TmpDNSLookup{$QueueHostsToResolve{$QueueCursor}} ) {
	sleep 1;
	# Print all records in head of queue that are ready
	&WriteRecordsReadyInQueue($logfilechosen);
}

# Waiting queue is empty
if ($MaxNbOfThread) {
	foreach my $t (threads->list()) {
		if ($Debug) { debug("Join thread $t"); }
		$t->join();
	}
}

# DNSLookup warning
if ($DNSLookup==1 && $DNSLookupAlreadyDone) {
	warning("Warning: $PROG has detected that some host names were already resolved in your logfile $DNSLookupAlreadyDone.\nIf DNS lookup was already made by the logger (web server) in ALL your log files, you should not use -dnslookup option to increase $PROG speed.");
}

if ($Debug) {
	debug("Total nb of read lines: $NbOfLinesRead");
	debug("Total nb of parsed lines: $NbOfLinesParsed");
	debug("Total nb of DNS lookup asked: $NbOfDNSLookupAsked");
}

#if ($DNSCache) {
#	open(CACHE, ">$DNSCache") or die;
#	foreach (keys %TmpDNSLookup) {
#		$TmpDNSLookup{$_}="*" if $TmpDNSLookup{$_} eq "ip";
#		print CACHE "0\t$_\t$TmpDNSLookup{$_}\n";
#	}
#	close CACHE;
#}

0;	# Do not remove this line