summaryrefslogtreecommitdiffstats
path: root/src/exigrep.src
blob: fd07fd8f1bd46fdef5a298e858f19b5faf6f95af (plain)
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
#! PERL_COMMAND

use warnings;
use strict;
BEGIN { pop @INC if $INC[-1] eq '.' };

use Pod::Usage;
use Getopt::Long qw(:config no_ignore_case);
use File::Basename;

# Copyright (c) 2007-2017 University of Cambridge.
# Copyright (c) The Exim Maintainers 2020
# See the file NOTICE for conditions of use and distribution.

# Except when they appear in comments, the following placeholders in this
# source are replaced when it is turned into a runnable script:
#
# PERL_COMMAND
# ZCAT_COMMAND
# COMPRESS_SUFFIX

# PROCESSED_FLAG

# This is a perl script which extracts from an Exim log all entries
# for all messages that have an entry that matches a given pattern.
# If *any* entry for a particular message matches the pattern, *all*
# entries for that message are displayed.

# We buffer up information on a per-message basis. It is done this way rather
# than reading the input twice so that the input can be a pipe.

# There must be one argument, which is the pattern. Subsequent arguments
# are the files to scan; if none, the standard input is read. If any file
# appears to be compressed, it is passed through zcat. We can't just do this
# for all files, because zcat chokes on non-compressed files.

# Performance optimized in 02/02/2007 by Jori Hamalainen
# Typical run time acceleration: 4 times


use POSIX qw(mktime);


# This subroutine converts a time/date string from an Exim log line into
# the number of seconds since the epoch. It handles optional timezone
# information.

sub seconds {
my($year,$month,$day,$hour,$min,$sec,$tzs,$tzh,$tzm) =
  $_[0] =~ /^(\d{4})-(\d\d)-(\d\d)\s(\d\d):(\d\d):(\d\d)(?:.\d+)?(?>\s([+-])(\d\d)(\d\d))?/o;

my $seconds = mktime $sec, $min, $hour, $day, $month - 1, $year - 1900;

if (defined $tzs)
  {
  $seconds -= $tzh * 3600 + $tzm * 60 if $tzs eq "+";
  $seconds += $tzh * 3600 + $tzm * 60 if $tzs eq "-";
  }

return $seconds;
}


# This subroutine processes a single line (in $_) from a log file. Program
# defensively against short lines finding their way into the log.

my (%saved, %id_list, $pattern);

my $queue_time  = -1;
my $insensitive = 1;
my $invert      = 0;
my $related     = 0;
my $use_pager   = 1;
my $literal     = 0;


# If using "related" option, have to track extra message IDs
my $related_re='';
my @Mids = ();

sub do_line {

# Convert syslog lines to mainlog format, as in eximstats.

if (!/^\d{4}-/o) { $_ =~ s/^.*? exim\b.*?: //o; }

return unless
  my($date,$id) = /^(\d{4}-\d\d-\d\d \d\d:\d\d:\d\d(?:\.\d+)? (?:[+-]\d{4} )?)(?:\[\d+\] )?(\w{6}\-\w{6}\-\w{2})?/o;

# Handle the case when the log line belongs to a specific message. We save
# lines for specific messages until the message is complete. Then either print
# or discard.

if (defined $id)
  {
  $saved{$id} = '' unless defined($saved{$id});

  # Save up the data for this message in case it becomes interesting later.

  $saved{$id} .= $_;

  # Are we interested in this id ? Short circuit if we already were interested.

  if ($invert)
    {
    $id_list{$id} = 1 if (!defined($id_list{$id}));
    $id_list{$id} = 0 if (($insensitive && /$pattern/io) || /$pattern/o);
    }
  else
    {
    if (defined $id_list{$id} ||
      ($insensitive && /$pattern/io) || /$pattern/o)
      {
      $id_list{$id} = 1;
      get_related_ids($id) if $related;
      }
    elsif ($related && $related_re)
      {
      grep_for_related($_, $id);
      }
    }

  # See if this is a completion for some message. If it is interesting,
  # print it, but in any event, throw away what was saved.

  if (index($_, 'Completed') != -1 ||
      index($_, 'SMTP data timeout') != -1 ||
        (index($_, 'rejected') != -1 &&
          /^(\d{4}-\d\d-\d\d \d\d:\d\d:\d\d(?:\.\d+)? (?:[+-]\d{4} )?)(?:\[\d+\] )?\w{6}\-\w{6}\-\w{2} rejected/o))
    {
    if ($queue_time != -1 &&
        $saved{$id} =~ /^(\d{4}-\d\d-\d\d \d\d:\d\d:\d\d ([+-]\d{4} )?)/o)
      {
      my $old_sec = &seconds($1);
      my $sec = &seconds($date);
      $id_list{$id} = 0 if $id_list{$id} && $sec - $old_sec <= $queue_time;
      }

    print "$saved{$id}\n" if ($id_list{$id});
    delete $id_list{$id};
    delete $saved{$id};
    }
  }

# Handle the case where the log line does not belong to a specific message.
# Print it if it is interesting.

elsif ( ($invert && (($insensitive && !/$pattern/io) || !/$pattern/o)) ||
       (!$invert && (($insensitive &&  /$pattern/io) ||  /$pattern/o)) )
  { print "$_\n"; }
}

# Rotated log files are frequently compressed and there are a variety of
# formats it could be compressed with. Rather than use just one that is
# detected and hardcoded at Exim compile time, detect and use what the
# logfile is compressed with on the fly.
#
# List of known compression extensions and their associated commands:
my $compressors = {
  gz   => { cmd => 'zcat',  args => '' },
  bz2  => { cmd => 'bzcat', args => '' },
  xz   => { cmd => 'xzcat', args => '' },
  lzma => { cmd => 'lzma',  args => '-dc' },
  zst  => { cmd => 'zstdcat', args => '' },
};
my $csearch = 0;

sub detect_compressor_bin
  {
  my $ext = shift();
  my $c = $compressors->{$ext}->{cmd};
  $compressors->{$ext}->{bin} = `which $c 2>/dev/null`;
  chomp($compressors->{$ext}->{bin});
  }

sub detect_compressor_capable
  {
  my $filename = shift();
  map { &detect_compressor_bin($_) } keys %$compressors
    if (!$csearch);
  $csearch = 1;
  return undef
    unless (grep {$filename =~ /\.(?:$_)$/} keys %$compressors);
  # Loop through them, figure out which one it detected,
  # and build the commandline.
  my $cmdline = undef;
  foreach my $ext (keys %$compressors)
    {
    if ($filename =~ /\.(?:$ext)$/)
      {
      # Just die if compressor not found; if this occurs in the middle of
      # two valid files with a lot of matches, error could easily be missed.
      die("Didn't find $ext decompressor for $filename\n")
        if ($compressors->{$ext}->{bin} eq '');
      $cmdline = $compressors->{$ext}->{bin} ." ".
                   $compressors->{$ext}->{args};
      last;
      }
    }
  return $cmdline;
  }

sub grep_for_related {
  my ($line,$id) = @_;
  $id_list{$id} = 1 if $line =~ m/$related_re/;
}

sub get_related_ids {
  my ($id) = @_;
  push @Mids, $id unless grep /\b$id\b/, @Mids;
  my $re = join '|', @Mids;
  $related_re = qr/$re/;
}

# The main program. Extract the pattern and make sure any relevant characters
# are quoted if the -l flag is given. The -t flag gives a time-on-queue value
# which is an additional condition. The -M flag will also display "related"
# loglines (msgid from matched lines is searched in following lines).

GetOptions(
    'I|sensitive' => sub { $insensitive = 0 },
      'l|literal' => \$literal,
      'M|related' => \$related,
      't|queue-time=i' => \$queue_time,
      'pager!'         => \$use_pager,
      'v|invert'       => \$invert,
      'h|help'         => sub { pod2usage(-exit => 0, -verbose => 1) },
      'm|man'          => sub {
        pod2usage(
            -exit      => 0,
            -verbose   => 2,
            -noperldoc => system('perldoc -V 2>/dev/null >&2')
        );
      },
      'version'        => sub {
            print basename($0) . ": $0\n",
                "build: EXIM_RELEASE_VERSIONEXIM_VARIANT_VERSION\n",
                "perl(runtime): $]\n";
            exit 0;
      },
) and @ARGV or pod2usage;

$pattern = shift @ARGV;
$pattern = quotemeta $pattern if $literal;

# Start a pager if output goes to a terminal
if (-t 1 and $use_pager)
  {
  # for perl >= v5.10.x: foreach ($ENV{PAGER}//(), 'less', 'more')
  foreach (defined $ENV{PAGER} ? $ENV{PAGER} : (), 'less', 'more')
    {
    local $ENV{LESS} .= ' --no-init --quit-if-one-screen';
    open(my $pager, '|-', $_) or next;
    select $pager;
    last;
    }
  }

# If file arguments are given, open each one and process according as it is
# is compressed or not.

if (@ARGV)
  {
  foreach (@ARGV)
    {
    my $filename = $_;
    if (-x 'ZCAT_COMMAND' && $filename =~ /\.(?:COMPRESS_SUFFIX)$/o)
      {
      open(LOG, "ZCAT_COMMAND $filename |") ||
        die "Unable to zcat $filename: $!\n";
      }
    elsif (my $cmdline = &detect_compressor_capable($filename))
      {
      open(LOG, "$cmdline $filename |") ||
        die "Unable to decompress $filename: $!\n";
      }
    else
      {
      open(LOG, "<$filename") || die "Unable to open $filename: $!\n";
      }
    do_line() while (<LOG>);
    close(LOG);
    }
  }

# If no files are named, process STDIN only

else { do_line() while (<STDIN>); }

# At the end of processing all the input, print any uncompleted messages.

for (keys %id_list)
  {
  print "+++ $_ has not completed +++\n$saved{$_}\n";
  }

__END__

=head1 NAME

exigrep - search Exim's main log

=head1 SYNOPSIS

B<exigrep> [options] pattern [log] ...

=head1 DESCRIPTION

The B<exigrep> utility is a Perl script that searches one or more main log
files for entries that match a given pattern.  When it finds  a  match,
it  extracts  all  the  log  entries for the relevant message, not just
those that match the pattern.  Thus, B<exigrep> can extract  complete  log
entries  for  a  given  message, or all mail for a given user, or for a
given host, for example.

If no file names are given on the command line, the standard input is read.

For known file extensions indicating compression (F<.gz>, F<.bz2>, F<.xz>,
F<.lzma>, and F<.zst>) a suitable de-compressor is used, if available.

The output is sent through a pager if a terminal is connected to STDOUT. As
pager are considered: C<$ENV{PAGER}>, C<less>, C<more>.

=head1 OPTIONS

=over

=item B<-l>|B<--literal>

This means 'literal', that is, treat all characters in the
pattern  as standing for themselves.  Otherwise the pattern must be a
Perl regular expression.  The pattern match is case-insensitive.

=item B<-t>|B<--queue-time> I<seconds>

Limit the output to messages that spent at least I<seconds> in the
queue.

=item B<-I>|B<--sensitive>

Do a case sensitive search.

=item B<-v>|B<--invert>

Invert the meaning of the search pattern. That is, print message log
entries that are not related to that pattern.

=item B<-M>|B<--related>

Search for related messages too.

=item B<--no-pager>

Do not use a pager, even if STDOUT is connected to a terminal.

=item B<-h>|B<--help>

Print a short reference help. For more detailed help try L<exigrep(8)>,
or C<exigrep --man>.

=item B<-m>|B<--man>

Print this manual page of B<exigrep>.

=back

=head1 SEE ALSO

L<exim(8)>, L<perlre(1)>, L<Exim|http://exim.org/>

=head1 AUTHOR

This  manual  page  was stitched together from spec.txt by Andreas Metzler L<ametzler at downhill.at.eu.org>
and updated by Heiko Schlittermann L<hs@schlittermann.de>.

=cut