[usenet/newsstats.git] / gatherstats.pl

#! /usr/bin/perl -W
#
# gatherstats.pl
#
# This script will gather statistical information from a database
# containing headers and other information from a INN feed.
# 
# It is part of the NewsStats package.
#
# Copyright (c) 2010-2012 Thomas Hochstein <thh@inter.net>
#
# It can be redistributed and/or modified under the same terms under 
# which Perl itself is published.

BEGIN {
  our $VERSION = "0.01";
  use File::Basename;
  push(@INC, dirname($0));
}
use strict;

use NewsStats qw(:DEFAULT :TimePeriods ListNewsgroups ReadGroupList);

use DBI;
use Getopt::Long qw(GetOptions);
Getopt::Long::config ('bundling');

################################# Definitions ##################################

# define types of information that can be gathered
# all / groups (/ clients / hosts)
my %LegalStats;
@LegalStats{('all','groups')} = ();

################################# Main program #################################

### read commandline options
my ($OptCheckgroupsFile,$OptClientsDB,$OptDebug,$OptGroupsDB,$OptTLH,
    $OptHostsDB,$OptMonth,$OptRawDB,$OptStatsType,$OptTest);
GetOptions ('c|checkgroups=s' => \$OptCheckgroupsFile,
            'clientsdb=s'     => \$OptClientsDB,
            'd|debug!'        => \$OptDebug,
            'groupsdb=s'      => \$OptGroupsDB,
            'hierarchy=s'     => \$OptTLH,
            'hostsdb=s'       => \$OptHostsDB,
            'm|month=s'       => \$OptMonth,
            'rawdb=s'         => \$OptRawDB,
            's|stats=s'       => \$OptStatsType,
            't|test!'         => \$OptTest,
            'h|help'          => \&ShowPOD,
            'V|version'       => \&ShowVersion) or exit 1;

### read configuration
my %Conf = %{ReadConfig($HomePath.'/newsstats.conf')};

### override configuration via commandline options
my %ConfOverride;
$ConfOverride{'DBTableRaw'}   = $OptRawDB if $OptRawDB;
$ConfOverride{'DBTableGrps'}  = $OptGroupsDB if $OptGroupsDB;
$ConfOverride{'DBTableClnts'} = $OptClientsDB if $OptClientsDB;
$ConfOverride{'DBTableHosts'} = $OptHostsDB if $OptHostsDB;
$ConfOverride{'TLH'} = $OptTLH if $OptTLH;
&OverrideConfig(\%Conf,\%ConfOverride);

### get type of information to gather, defaulting to 'all'
$OptStatsType = 'all' if !$OptStatsType;
&Bleat(2, sprintf("Unknown type '%s'!", $OptStatsType))
  if !exists($LegalStats{$OptStatsType});

### get time period from --month
# get verbal description of time period, drop SQL code
my ($Period) = &GetTimePeriod($OptMonth);
&Bleat(2,"--month option has an invalid format - please use 'YYYY-MM' or ".
         "'YYYY-MM:YYYY-MM'!") if (!$Period or $Period eq 'all time');

### reformat $Conf{'TLH'}
my $TLH;
if ($Conf{'TLH'}) {
  # $Conf{'TLH'} is parsed as an array by Config::Auto;
  # make a flat list again, separated by :
  if (ref($Conf{'TLH'}) eq 'ARRAY') {
    $TLH = join(':',@{$Conf{'TLH'}});
  } else {
    $TLH  = $Conf{'TLH'};
  }
  # strip whitespace
  $TLH =~ s/\s//g;
  # add trailing dots if none are present yet
  # (using negative look-behind assertions)
  $TLH =~ s/(?<!\.):/.:/g;
  $TLH =~ s/(?<!\.)$/./;
  # check for illegal characters
  &Bleat(2,'Config error - illegal characters in TLH definition!')
    if ($TLH !~ /^[a-zA-Z0-9:+.-]+$/);
  # escape dots
  $TLH =~ s/\./\\./g;
  if ($TLH =~ /:/) {
    # reformat $TLH from a:b to (a)|(b),
    # e.g. replace ':' by ')|('
    $TLH =~ s/:/)|(/g;
    $TLH = '(' . $TLH . ')';
  };
};

### init database
my $DBHandle = InitDB(\%Conf,1);

### get data for each month
&Bleat(1,'Test mode. Database is not updated.') if $OptTest;
foreach my $Month (&ListMonth($Period)) {

  print "---------- $Month ----------\n" if $OptDebug;

  if ($OptStatsType eq 'all' or $OptStatsType eq 'groups') {
    # read list of newsgroups from --checkgroups
    # into a hash
    my %ValidGroups = %{ReadGroupList(sprintf('%s-%s',$OptCheckgroupsFile,$Month))}
      if $OptCheckgroupsFile;

    ### ----------------------------------------------
    ### get groups data (number of postings per group)
    # get groups data from raw table for given month
    my $DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroups FROM %s.%s ".
                                             "WHERE day LIKE ? AND NOT disregard",
                                             $Conf{'DBDatabase'},
                                             $Conf{'DBTableRaw'}));
    $DBQuery->execute($Month.'-%')
      or &Bleat(2,sprintf("Can't get groups data for %s from %s.%s: ".
                          "$DBI::errstr\n",$Month,
                          $Conf{'DBDatabase'},$Conf{'DBTableRaw'}));

    # count postings per group
    my %Postings;
    while (($_) = $DBQuery->fetchrow_array) {
      # get list oft newsgroups and hierarchies from Newsgroups:
      my %Newsgroups = ListNewsgroups($_,$TLH,
                                      $OptCheckgroupsFile ? \%ValidGroups : '');
      # count each newsgroup and hierarchy once
      foreach (sort keys %Newsgroups) {
        $Postings{$_}++;
      };
    };

    # add valid but empty groups if --checkgroups is set
    if (%ValidGroups) {
      foreach (sort keys %ValidGroups) {
        if (!defined($Postings{$_})) {
          $Postings{$_} = 0 ;
          warn (sprintf("ADDED: %s as empty group\n",$_));
        }
      };
    };

    # delete old data for that month
    if (!$OptTest) {
      $DBQuery = $DBHandle->do(sprintf("DELETE FROM %s.%s WHERE month = ?",
                                       $Conf{'DBDatabase'},$Conf{'DBTableGrps'}),
                                       undef,$Month)
        or &Bleat(2,sprintf("Can't delete old groups data for %s from %s.%s: ".
                            "$DBI::errstr\n",$Month,
                            $Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
    };

    print "----- GroupStats -----\n" if $OptDebug;
    foreach my $Newsgroup (sort keys %Postings) {
      print "$Newsgroup => $Postings{$Newsgroup}\n" if $OptDebug;
      if (!$OptTest) {
        # write to database
        $DBQuery = $DBHandle->prepare(sprintf("INSERT INTO %s.%s ".
                                              "(month,newsgroup,postings) ".
                                              "VALUES (?, ?, ?)",
                                              $Conf{'DBDatabase'},
                                              $Conf{'DBTableGrps'}));
        $DBQuery->execute($Month, $Newsgroup, $Postings{$Newsgroup})
          or &Bleat(2,sprintf("Can't write groups data for %s/%s to %s.%s: ".
                              "$DBI::errstr\n",$Month,$Newsgroup,
                              $Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
        $DBQuery->finish;
      };
    };
  } else {
    # other types of information go here - later on
  };
};

### close handles
$DBHandle->disconnect;

__END__

################################ Documentation #################################

=head1 NAME

gatherstats - process statistical data from a raw source

=head1 SYNOPSIS

B<gatherstats> [B<-Vhdt>] [B<-m> I<YYYY-MM> | I<YYYY-MM:YYYY-MM>] [B<-s> I<stats] [B<-c> I<filename template>]] [B<--hierarchy> I<TLH>] [B<--rawdb> I<database table>] [B<-groupsdb> I<database table>] [B<--clientsdb> I<database table>] [B<--hostsdb> I<database table>]

=head1 REQUIREMENTS

See L<doc/README>.

=head1 DESCRIPTION

This script will extract and process statistical information from a
database table which is fed from F<feedlog.pl> for a given time period
and write its results to (an)other database table(s). Entries marked
with I<'disregard'> in the database will be ignored; currently, you
have to set this flag yourself, using your database management tools.
You can exclude erroneous entries that way (e.g. automatic reposts
(think of cancels flood and resurrectors); spam; ...).

The time period to act on defaults to last month; you can assign
another time period or a single month via the B<--month> option (see
below).

By default B<gatherstats> will process all types of information; you
can change that using the B<--stats> option and assigning the type of
information to process. Currently that doesn't matter yet as only
processing of the number of postings per group per month is
implemented anyway.

Possible information types include:

=over 3

=item B<groups> (postings per group per month)

B<gatherstats> will examine Newsgroups: headers. Crosspostings will be
counted for each single group they appear in. Groups not in I<TLH>
will be ignored.

B<gatherstats> will also add up the number of postings for each
hierarchy level, but only count each posting once. A posting to
de.alt.test will be counted for de.alt.test, de.alt.ALL and de.ALL,
respectively. A crossposting to de.alt.test and de.alt.admin, on the
other hand, will be counted for de.alt.test and de.alt.admin each, but
only once for de.alt.ALL and de.ALL.

Data is written to I<DBTableGrps> (see L<doc/INSTALL>); you can
override that default through the B<--groupsdb> option.

=back

=head2 Configuration

B<gatherstats> will read its configuration from F<newsstats.conf>
which should be present in the same directory via Config::Auto.

See L<doc/INSTALL> for an overview of possible configuration options.

You can override configuration options via the B<--hierarchy>,
B<--rawdb>, B<--groupsdb>, B<--clientsdb> and B<--hostsdb> options,
respectively.

=head1 OPTIONS

=over 3

=item B<-V>, B<--version>

Print out version and copyright information and exit.

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

Print this man page and exit.

=item B<-d>, B<--debug>

Output debugging information to STDOUT while processing (number of
postings per group).

=item B<-t>, B<--test>

Do not write results to database. You should use B<--debug> in
conjunction with B<--test> ... everything else seems a bit pointless.

=item B<-m>, B<--month> I<YYYY-MM[:YYYY-MM]>

Set processing period to a single month in YYYY-MM format or to a time
period between two month in YYYY-MM:YYYY-MM format (two month, separated
by a colon). 


=item B<-s>, B<--stats> I<type>

Set processing type to one of I<all> and I<groups>. Defaults to all
(and is currently rather pointless as only I<groups> has been
implemented).

=item B<-c>, B<--checkgroups> I<filename template>

Check each group against a list of valid newsgroups read from a file,
one group on each line and ignoring everything after the first
whitespace (so you can use a file in checkgroups format or (part of)
your INN active file).

The filename is taken from I<filename template>, amended by each B<--
month> B<gatherstats> is processing, so that

    gatherstats -m 2010-01:2010-12 -c checkgroups

will check against F<checkgroups-2010-01> for January 2010, against
F<checkgroups-2010-02> for February 2010 and so on.

Newsgroups not found in the checkgroups file will be dropped (and
logged to STDERR), and newsgroups found there but having no postings
will be added with a count of 0 (and logged to STDERR).

=item B<--hierarchy> I<TLH> (newsgroup hierarchy)

Override I<TLH> from F<newsstats.conf>.

=item B<--rawdb> I<table> (raw data table)

Override I<DBTableRaw> from F<newsstats.conf>.

=item B<--groupsdb> I<table> (postings per group table)

Override I<DBTableGrps> from F<newsstats.conf>.

=item B<--clientsdb> I<table> (client data table)

Override I<DBTableClnts> from F<newsstats.conf>.

=item B<--hostsdb> I<table> (host data table)

Override I<DBTableHosts> from F<newsstats.conf>.

=back

=head1 INSTALLATION

See L<doc/INSTALL>.

=head1 EXAMPLES

Process all types of information for lasth month:

    gatherstats

Do a dry run, showing results of processing:

    gatherstats --debug --test

Process all types of information for January of 2010:

    gatherstats --month 2010-01

Process only number of postings for the year of 2010,
checking against checkgroups-*:

    gatherstats -m 2010-01:2010-12 -s groups -c checkgroups

=head1 FILES

=over 4

=item F<gatherstats.pl>

The script itself.

=item F<NewsStats.pm>

Library functions for the NewsStats package.

=item F<newsstats.conf>

Runtime configuration file.

=back

=head1 BUGS

Please report any bugs or feature requests to the author or use the
bug tracker at L<http://bugs.th-h.de/>!

=head1 SEE ALSO

=over 2

=item -

L<doc/README>

=item -

L<doc/INSTALL>

=back

This script is part of the B<NewsStats> package.

=head1 AUTHOR

Thomas Hochstein <thh@inter.net>

=head1 COPYRIGHT AND LICENSE

Copyright (c) 2010-2012 Thomas Hochstein <thh@inter.net>

This program is free software; you may redistribute it and/or modify it
under the same terms as Perl itself.

=cut
Commit	Line	Data
	1	#! /usr/bin/perl -W
	2	#
	3	# gatherstats.pl
	4	#
	5	# This script will gather statistical information from a database
	6	# containing headers and other information from a INN feed.
	7	#
	8	# It is part of the NewsStats package.
	9	#
	10	# Copyright (c) 2010-2012 Thomas Hochstein <thh@inter.net>
	11	#
	12	# It can be redistributed and/or modified under the same terms under
	13	# which Perl itself is published.
	14
	15	BEGIN {
	16	our $VERSION = "0.01";
	17	use File::Basename;
	18	push(@INC, dirname($0));
	19	}
	20	use strict;
	21
	22	use NewsStats qw(:DEFAULT :TimePeriods ListNewsgroups ReadGroupList);
	23
	24	use DBI;
	25	use Getopt::Long qw(GetOptions);
	26	Getopt::Long::config ('bundling');
	27
	28	################################# Definitions ##################################
	29
	30	# define types of information that can be gathered
	31	# all / groups (/ clients / hosts)
	32	my %LegalStats;
	33	@LegalStats{('all','groups')} = ();
	34
	35	################################# Main program #################################
	36
	37	### read commandline options
	38	my ($OptCheckgroupsFile,$OptClientsDB,$OptDebug,$OptGroupsDB,$OptTLH,
	39	$OptHostsDB,$OptMonth,$OptRawDB,$OptStatsType,$OptTest);
	40	GetOptions ('c\|checkgroups=s' => \$OptCheckgroupsFile,
	41	'clientsdb=s' => \$OptClientsDB,
	42	'd\|debug!' => \$OptDebug,
	43	'groupsdb=s' => \$OptGroupsDB,
	44	'hierarchy=s' => \$OptTLH,
	45	'hostsdb=s' => \$OptHostsDB,
	46	'm\|month=s' => \$OptMonth,
	47	'rawdb=s' => \$OptRawDB,
	48	's\|stats=s' => \$OptStatsType,
	49	't\|test!' => \$OptTest,
	50	'h\|help' => \&ShowPOD,
	51	'V\|version' => \&ShowVersion) or exit 1;
	52
	53	### read configuration
	54	my %Conf = %{ReadConfig($HomePath.'/newsstats.conf')};
	55
	56	### override configuration via commandline options
	57	my %ConfOverride;
	58	$ConfOverride{'DBTableRaw'} = $OptRawDB if $OptRawDB;
	59	$ConfOverride{'DBTableGrps'} = $OptGroupsDB if $OptGroupsDB;
	60	$ConfOverride{'DBTableClnts'} = $OptClientsDB if $OptClientsDB;
	61	$ConfOverride{'DBTableHosts'} = $OptHostsDB if $OptHostsDB;
	62	$ConfOverride{'TLH'} = $OptTLH if $OptTLH;
	63	&OverrideConfig(\%Conf,\%ConfOverride);
	64
	65	### get type of information to gather, defaulting to 'all'
	66	$OptStatsType = 'all' if !$OptStatsType;
	67	&Bleat(2, sprintf("Unknown type '%s'!", $OptStatsType))
	68	if !exists($LegalStats{$OptStatsType});
	69
	70	### get time period from --month
	71	# get verbal description of time period, drop SQL code
	72	my ($Period) = &GetTimePeriod($OptMonth);
	73	&Bleat(2,"--month option has an invalid format - please use 'YYYY-MM' or ".
	74	"'YYYY-MM:YYYY-MM'!") if (!$Period or $Period eq 'all time');
	75
	76	### reformat $Conf{'TLH'}
	77	my $TLH;
	78	if ($Conf{'TLH'}) {
	79	# $Conf{'TLH'} is parsed as an array by Config::Auto;
	80	# make a flat list again, separated by :
	81	if (ref($Conf{'TLH'}) eq 'ARRAY') {
	82	$TLH = join(':',@{$Conf{'TLH'}});
	83	} else {
	84	$TLH = $Conf{'TLH'};
	85	}
	86	# strip whitespace
	87	$TLH =~ s/\s//g;
	88	# add trailing dots if none are present yet
	89	# (using negative look-behind assertions)
	90	$TLH =~ s/(?<!\.):/.:/g;
	91	$TLH =~ s/(?<!\.)$/./;
	92	# check for illegal characters
	93	&Bleat(2,'Config error - illegal characters in TLH definition!')
	94	if ($TLH !~ /^[a-zA-Z0-9:+.-]+$/);
	95	# escape dots
	96	$TLH =~ s/\./\\./g;
	97	if ($TLH =~ /:/) {
	98	# reformat $TLH from a:b to (a)\|(b),
	99	# e.g. replace ':' by ')\|('
	100	$TLH =~ s/:/)\|(/g;
	101	$TLH = '(' . $TLH . ')';
	102	};
	103	};
	104
	105	### init database
	106	my $DBHandle = InitDB(\%Conf,1);
	107
	108	### get data for each month
	109	&Bleat(1,'Test mode. Database is not updated.') if $OptTest;
	110	foreach my $Month (&ListMonth($Period)) {
	111
	112	print "---------- $Month ----------\n" if $OptDebug;
	113
	114	if ($OptStatsType eq 'all' or $OptStatsType eq 'groups') {
	115	# read list of newsgroups from --checkgroups
	116	# into a hash
	117	my %ValidGroups = %{ReadGroupList(sprintf('%s-%s',$OptCheckgroupsFile,$Month))}
	118	if $OptCheckgroupsFile;
	119
	120	### ----------------------------------------------
	121	### get groups data (number of postings per group)
	122	# get groups data from raw table for given month
	123	my $DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroups FROM %s.%s ".
	124	"WHERE day LIKE ? AND NOT disregard",
	125	$Conf{'DBDatabase'},
	126	$Conf{'DBTableRaw'}));
	127	$DBQuery->execute($Month.'-%')
	128	or &Bleat(2,sprintf("Can't get groups data for %s from %s.%s: ".
	129	"$DBI::errstr\n",$Month,
	130	$Conf{'DBDatabase'},$Conf{'DBTableRaw'}));
	131
	132	# count postings per group
	133	my %Postings;
	134	while (($_) = $DBQuery->fetchrow_array) {
	135	# get list oft newsgroups and hierarchies from Newsgroups:
	136	my %Newsgroups = ListNewsgroups($_,$TLH,
	137	$OptCheckgroupsFile ? \%ValidGroups : '');
	138	# count each newsgroup and hierarchy once
	139	foreach (sort keys %Newsgroups) {
	140	$Postings{$_}++;
	141	};
	142	};
	143
	144	# add valid but empty groups if --checkgroups is set
	145	if (%ValidGroups) {
	146	foreach (sort keys %ValidGroups) {
	147	if (!defined($Postings{$_})) {
	148	$Postings{$_} = 0 ;
	149	warn (sprintf("ADDED: %s as empty group\n",$_));
	150	}
	151	};
	152	};
	153
	154	# delete old data for that month
	155	if (!$OptTest) {
	156	$DBQuery = $DBHandle->do(sprintf("DELETE FROM %s.%s WHERE month = ?",
	157	$Conf{'DBDatabase'},$Conf{'DBTableGrps'}),
	158	undef,$Month)
	159	or &Bleat(2,sprintf("Can't delete old groups data for %s from %s.%s: ".
	160	"$DBI::errstr\n",$Month,
	161	$Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
	162	};
	163
	164	print "----- GroupStats -----\n" if $OptDebug;
	165	foreach my $Newsgroup (sort keys %Postings) {
	166	print "$Newsgroup => $Postings{$Newsgroup}\n" if $OptDebug;
	167	if (!$OptTest) {
	168	# write to database
	169	$DBQuery = $DBHandle->prepare(sprintf("INSERT INTO %s.%s ".
	170	"(month,newsgroup,postings) ".
	171	"VALUES (?, ?, ?)",
	172	$Conf{'DBDatabase'},
	173	$Conf{'DBTableGrps'}));
	174	$DBQuery->execute($Month, $Newsgroup, $Postings{$Newsgroup})
	175	or &Bleat(2,sprintf("Can't write groups data for %s/%s to %s.%s: ".
	176	"$DBI::errstr\n",$Month,$Newsgroup,
	177	$Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
	178	$DBQuery->finish;
	179	};
	180	};
	181	} else {
	182	# other types of information go here - later on
	183	};
	184	};
	185
	186	### close handles
	187	$DBHandle->disconnect;
	188
	189	__END__
	190
	191	################################ Documentation #################################
	192
	193	=head1 NAME
	194
	195	gatherstats - process statistical data from a raw source
	196
	197	=head1 SYNOPSIS
	198
	199	B<gatherstats> [B<-Vhdt>] [B<-m> I<YYYY-MM> \| I<YYYY-MM:YYYY-MM>] [B<-s> I<stats] [B<-c> I<filename template>]] [B<--hierarchy> I<TLH>] [B<--rawdb> I<database table>] [B<-groupsdb> I<database table>] [B<--clientsdb> I<database table>] [B<--hostsdb> I<database table>]
	200
	201	=head1 REQUIREMENTS
	202
	203	See L<doc/README>.
	204
	205	=head1 DESCRIPTION
	206
	207	This script will extract and process statistical information from a
	208	database table which is fed from F<feedlog.pl> for a given time period
	209	and write its results to (an)other database table(s). Entries marked
	210	with I<'disregard'> in the database will be ignored; currently, you
	211	have to set this flag yourself, using your database management tools.
	212	You can exclude erroneous entries that way (e.g. automatic reposts
	213	(think of cancels flood and resurrectors); spam; ...).
	214
	215	The time period to act on defaults to last month; you can assign
	216	another time period or a single month via the B<--month> option (see
	217	below).
	218
	219	By default B<gatherstats> will process all types of information; you
	220	can change that using the B<--stats> option and assigning the type of
	221	information to process. Currently that doesn't matter yet as only
	222	processing of the number of postings per group per month is
	223	implemented anyway.
	224
	225	Possible information types include:
	226
	227	=over 3
	228
	229	=item B<groups> (postings per group per month)
	230
	231	B<gatherstats> will examine Newsgroups: headers. Crosspostings will be
	232	counted for each single group they appear in. Groups not in I<TLH>
	233	will be ignored.
	234
	235	B<gatherstats> will also add up the number of postings for each
	236	hierarchy level, but only count each posting once. A posting to
	237	de.alt.test will be counted for de.alt.test, de.alt.ALL and de.ALL,
	238	respectively. A crossposting to de.alt.test and de.alt.admin, on the
	239	other hand, will be counted for de.alt.test and de.alt.admin each, but
	240	only once for de.alt.ALL and de.ALL.
	241
	242	Data is written to I<DBTableGrps> (see L<doc/INSTALL>); you can
	243	override that default through the B<--groupsdb> option.
	244
	245	=back
	246
	247	=head2 Configuration
	248
	249	B<gatherstats> will read its configuration from F<newsstats.conf>
	250	which should be present in the same directory via Config::Auto.
	251
	252	See L<doc/INSTALL> for an overview of possible configuration options.
	253
	254	You can override configuration options via the B<--hierarchy>,
	255	B<--rawdb>, B<--groupsdb>, B<--clientsdb> and B<--hostsdb> options,
	256	respectively.
	257
	258	=head1 OPTIONS
	259
	260	=over 3
	261
	262	=item B<-V>, B<--version>
	263
	264	Print out version and copyright information and exit.
	265
	266	=item B<-h>, B<--help>
	267
	268	Print this man page and exit.
	269
	270	=item B<-d>, B<--debug>
	271
	272	Output debugging information to STDOUT while processing (number of
	273	postings per group).
	274
	275	=item B<-t>, B<--test>
	276
	277	Do not write results to database. You should use B<--debug> in
	278	conjunction with B<--test> ... everything else seems a bit pointless.
	279
	280	=item B<-m>, B<--month> I<YYYY-MM[:YYYY-MM]>
	281
	282	Set processing period to a single month in YYYY-MM format or to a time
	283	period between two month in YYYY-MM:YYYY-MM format (two month, separated
	284	by a colon).
	285
	286
	287	=item B<-s>, B<--stats> I<type>
	288
	289	Set processing type to one of I<all> and I<groups>. Defaults to all
	290	(and is currently rather pointless as only I<groups> has been
	291	implemented).
	292
	293	=item B<-c>, B<--checkgroups> I<filename template>
	294
	295	Check each group against a list of valid newsgroups read from a file,
	296	one group on each line and ignoring everything after the first
	297	whitespace (so you can use a file in checkgroups format or (part of)
	298	your INN active file).
	299
	300	The filename is taken from I<filename template>, amended by each B<--
	301	month> B<gatherstats> is processing, so that
	302
	303	gatherstats -m 2010-01:2010-12 -c checkgroups
	304
	305	will check against F<checkgroups-2010-01> for January 2010, against
	306	F<checkgroups-2010-02> for February 2010 and so on.
	307
	308	Newsgroups not found in the checkgroups file will be dropped (and
	309	logged to STDERR), and newsgroups found there but having no postings
	310	will be added with a count of 0 (and logged to STDERR).
	311
	312	=item B<--hierarchy> I<TLH> (newsgroup hierarchy)
	313
	314	Override I<TLH> from F<newsstats.conf>.
	315
	316	=item B<--rawdb> I<table> (raw data table)
	317
	318	Override I<DBTableRaw> from F<newsstats.conf>.
	319
	320	=item B<--groupsdb> I<table> (postings per group table)
	321
	322	Override I<DBTableGrps> from F<newsstats.conf>.
	323
	324	=item B<--clientsdb> I<table> (client data table)
	325
	326	Override I<DBTableClnts> from F<newsstats.conf>.
	327
	328	=item B<--hostsdb> I<table> (host data table)
	329
	330	Override I<DBTableHosts> from F<newsstats.conf>.
	331
	332	=back
	333
	334	=head1 INSTALLATION
	335
	336	See L<doc/INSTALL>.
	337
	338	=head1 EXAMPLES
	339
	340	Process all types of information for lasth month:
	341
	342	gatherstats
	343
	344	Do a dry run, showing results of processing:
	345
	346	gatherstats --debug --test
	347
	348	Process all types of information for January of 2010:
	349
	350	gatherstats --month 2010-01
	351
	352	Process only number of postings for the year of 2010,
	353	checking against checkgroups-*:
	354
	355	gatherstats -m 2010-01:2010-12 -s groups -c checkgroups
	356
	357	=head1 FILES
	358
	359	=over 4
	360
	361	=item F<gatherstats.pl>
	362
	363	The script itself.
	364
	365	=item F<NewsStats.pm>
	366
	367	Library functions for the NewsStats package.
	368
	369	=item F<newsstats.conf>
	370
	371	Runtime configuration file.
	372
	373	=back
	374
	375	=head1 BUGS
	376
	377	Please report any bugs or feature requests to the author or use the
	378	bug tracker at L<http://bugs.th-h.de/>!
	379
	380	=head1 SEE ALSO
	381
	382	=over 2
	383
	384	=item -
	385
	386	L<doc/README>
	387
	388	=item -
	389
	390	L<doc/INSTALL>
	391
	392	=back
	393
	394	This script is part of the B<NewsStats> package.
	395
	396	=head1 AUTHOR
	397
	398	Thomas Hochstein <thh@inter.net>
	399
	400	=head1 COPYRIGHT AND LICENSE
	401
	402	Copyright (c) 2010-2012 Thomas Hochstein <thh@inter.net>
	403
	404	This program is free software; you may redistribute it and/or modify it
	405	under the same terms as Perl itself.
	406
	407	=cut