| 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 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); |
| 23 | |
| 24 | use DBI; |
| 25 | |
| 26 | ################################# Definitions ################################## |
| 27 | |
| 28 | # define types of information that can be gathered |
| 29 | # all / groups (/ clients / hosts) |
| 30 | my %LegalTypes; |
| 31 | @LegalTypes{('all','groups')} = (); |
| 32 | |
| 33 | ################################# Main program ################################# |
| 34 | |
| 35 | ### read commandline options |
| 36 | my %Options = &ReadOptions('dom:p:t:n:r:g:c:s:'); |
| 37 | |
| 38 | ### read configuration |
| 39 | my %Conf = %{ReadConfig('newsstats.conf')}; |
| 40 | |
| 41 | ### override configuration via commandline options |
| 42 | my %ConfOverride; |
| 43 | $ConfOverride{'DBTableRaw'} = $Options{'r'} if $Options{'r'}; |
| 44 | $ConfOverride{'DBTableGrps'} = $Options{'g'} if $Options{'g'}; |
| 45 | $ConfOverride{'DBTableClnts'} = $Options{'c'} if $Options{'c'}; |
| 46 | $ConfOverride{'DBTableHosts'} = $Options{'s'} if $Options{'s'}; |
| 47 | $ConfOverride{'TLH'} = $Options{'n'} if $Options{'n'}; |
| 48 | &OverrideConfig(\%Conf,\%ConfOverride); |
| 49 | |
| 50 | ### get type of information to gather, defaulting to 'all' |
| 51 | $Options{'t'} = 'all' if !$Options{'t'}; |
| 52 | die "$MySelf: E: Unknown type '-t $Options{'t'}'!\n" if !exists($LegalTypes{$Options{'t'}}); |
| 53 | |
| 54 | ### get time period (-m or -p) |
| 55 | my ($StartMonth,$EndMonth) = &GetTimePeriod($Options{'m'},$Options{'p'}); |
| 56 | |
| 57 | ### init database |
| 58 | my $DBHandle = InitDB(\%Conf,1); |
| 59 | |
| 60 | ### get data for each month |
| 61 | warn "$MySelf: W: Output only mode. Database is not updated.\n" if $Options{'o'}; |
| 62 | foreach my $Month (&ListMonth($StartMonth,$EndMonth)) { |
| 63 | |
| 64 | print "---------- $Month ----------\n" if $Options{'d'}; |
| 65 | |
| 66 | if ($Options{'t'} eq 'all' or $Options{'t'} eq 'groups') { |
| 67 | ### ---------------------------------------------- |
| 68 | ### get groups data (number of postings per group) |
| 69 | # get groups data from raw table for given month |
| 70 | my $DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroups FROM %s.%s WHERE day LIKE ? AND NOT disregard",$Conf{'DBDatabase'},$Conf{'DBTableRaw'})); |
| 71 | $DBQuery->execute($Month.'-%') or die sprintf("$MySelf: E: Can't get groups data for %s from %s.%s: $DBI::errstr\n",$Month,$Conf{'DBDatabase'},$Conf{'DBTableRaw'}); |
| 72 | |
| 73 | # count postings per group |
| 74 | my %Postings; |
| 75 | |
| 76 | while (($_) = $DBQuery->fetchrow_array) { |
| 77 | # get list oft newsgroups and hierarchies from Newsgroups: |
| 78 | my %Newsgroups = ListNewsgroups($_); |
| 79 | # count each newsgroup and hierarchy once |
| 80 | foreach (sort keys %Newsgroups) { |
| 81 | # don't count newsgroup/hierarchy in wrong TLH |
| 82 | next if(defined($Conf{'TLH'}) and !/^$Conf{'TLH'}/); |
| 83 | $Postings{$_}++; |
| 84 | }; |
| 85 | }; |
| 86 | |
| 87 | print "----- GroupStats -----\n" if $Options{'d'}; |
| 88 | foreach my $Newsgroup (sort keys %Postings) { |
| 89 | print "$Newsgroup => $Postings{$Newsgroup}\n" if $Options{'d'}; |
| 90 | if (!$Options{'o'}) { |
| 91 | # write to database |
| 92 | $DBQuery = $DBHandle->prepare(sprintf("REPLACE INTO %s.%s (month,newsgroup,postings) VALUES (?, ?, ?)",$Conf{'DBDatabase'},$Conf{'DBTableGrps'})); |
| 93 | $DBQuery->execute($Month, $Newsgroup, $Postings{$Newsgroup}) or die sprintf("$MySelf: E: Can't write groups data for %s/%s to %s.%s: $DBI::errstr\n",$Month,$Newsgroup,$Conf{'DBDatabase'},$Conf{'DBTableGrps'}); |
| 94 | $DBQuery->finish; |
| 95 | }; |
| 96 | }; |
| 97 | } else { |
| 98 | # other types of information go here - later on |
| 99 | }; |
| 100 | }; |
| 101 | |
| 102 | ### close handles |
| 103 | $DBHandle->disconnect; |
| 104 | |
| 105 | __END__ |
| 106 | |
| 107 | ################################ Documentation ################################# |
| 108 | |
| 109 | =head1 NAME |
| 110 | |
| 111 | gatherstats - process statistical data from a raw source |
| 112 | |
| 113 | =head1 SYNOPSIS |
| 114 | |
| 115 | B<gatherstats> [B<-Vhdo>] [B<-m> I<YYYY-MM>] [B<-p> I<YYYY-MM:YYYY-MM>] [B<-t> I<type>] [B<-n> I<TLH>] [B<-r> I<database table>] [B<-g> I<database table>] [B<-c> I<database table>] [B<-s> I<database table>] |
| 116 | |
| 117 | =head1 REQUIREMENTS |
| 118 | |
| 119 | See doc/README: Perl 5.8.x itself and the following modules from CPAN: |
| 120 | |
| 121 | =over 2 |
| 122 | |
| 123 | =item - |
| 124 | |
| 125 | Config::Auto |
| 126 | |
| 127 | =item - |
| 128 | |
| 129 | DBI |
| 130 | |
| 131 | =back |
| 132 | |
| 133 | =head1 DESCRIPTION |
| 134 | |
| 135 | This script will extract and process statistical information from a |
| 136 | database table which is fed from F<feedlog.pl> for a given time period |
| 137 | and write its results to (an)other database table(s). Entries marked |
| 138 | with I<'disregard'> in the database will be ignored; currently, you have |
| 139 | to set this flag yourself, using your database management tools. You |
| 140 | can exclude erroneous entries that way (e.g. automatic reposts (think |
| 141 | of cancels flood and resurrectors); spam; ...). |
| 142 | |
| 143 | The time period to act on defaults to last month; you can assign |
| 144 | another month via the B<-m> switch or a time period via the B<-p> |
| 145 | switch; the latter takes preference. |
| 146 | |
| 147 | By default B<gatherstats> will process all types of information; you |
| 148 | can change that using the B<-t> switch and assigning the type of |
| 149 | information to process. Currently only processing of the number of |
| 150 | postings per group per month is implemented anyway, so that doesn't |
| 151 | matter yet. |
| 152 | |
| 153 | Possible information types include: |
| 154 | |
| 155 | =over 3 |
| 156 | |
| 157 | =item B<groups> (postings per group per month) |
| 158 | |
| 159 | B<gatherstats> will examine Newsgroups: headers. Crosspostings will be |
| 160 | counted for each single group they appear in. Groups not in I<TLH> |
| 161 | will be ignored. |
| 162 | |
| 163 | B<gatherstats> will also add up the number of postings for each |
| 164 | hierarchy level, but only count each posting once. A posting to |
| 165 | de.alt.test will be counted for de.alt.test, de.alt.ALL and de.ALL, |
| 166 | respectively. A crossposting to de.alt.test and de.alt.admin, on the |
| 167 | other hand, will be counted for de.alt.test and de.alt.admin each, but |
| 168 | only once for de.alt.ALL and de.ALL. |
| 169 | |
| 170 | Data is written to I<DBTableGrps> (see doc/INSTALL). |
| 171 | |
| 172 | =back |
| 173 | |
| 174 | =head2 Configuration |
| 175 | |
| 176 | F<gatherstats.pl> will read its configuration from F<newsstats.conf> |
| 177 | which should be present in the same directory via Config::Auto. |
| 178 | |
| 179 | See doc/INSTALL for an overview of possible configuration options. |
| 180 | |
| 181 | You can override configuration options via the B<-n>, B<-r>, B<-g>, |
| 182 | B<-c> and B<-s> switches, respectively. |
| 183 | |
| 184 | =head1 OPTIONS |
| 185 | |
| 186 | =over 3 |
| 187 | |
| 188 | =item B<-V> (version) |
| 189 | |
| 190 | Print out version and copyright information on B<yapfaq> and exit. |
| 191 | |
| 192 | =item B<-h> (help) |
| 193 | |
| 194 | Print this man page and exit. |
| 195 | |
| 196 | =item B<-d> (debug) |
| 197 | |
| 198 | Output debugging information to STDOUT while processing (number of |
| 199 | postings per group). |
| 200 | |
| 201 | =item B<-o> (output only) |
| 202 | |
| 203 | Do not write results to database. You should use B<-d> in conjunction |
| 204 | with B<-o> ... everything else seems a bit pointless. |
| 205 | |
| 206 | =item B<-m> I<YYYY-MM> (month) |
| 207 | |
| 208 | Set processing period to a month in YYYY-MM format. Ignored if B<-p> |
| 209 | is set. |
| 210 | |
| 211 | =item B<-p> I<YYYY-MM:YYYY-MM> (period) |
| 212 | |
| 213 | Set processing period to a time period between two month, each in |
| 214 | YYYY-MM format, separated by a colon. Overrides B<-m>. |
| 215 | |
| 216 | =item B<-t> I<type> (type) |
| 217 | |
| 218 | Set processing type to one of I<all> and I<groups>. Defaults to all |
| 219 | (and is currently rather pointless as only I<groups> has been |
| 220 | implemented). |
| 221 | |
| 222 | =item B<-n> I<TLH> (newsgroup hierarchy) |
| 223 | |
| 224 | Override I<TLH> from F<newsstats.conf>. |
| 225 | |
| 226 | =item B<-r> I<table> (raw data table) |
| 227 | |
| 228 | Override I<DBTableRaw> from F<newsstats.conf>. |
| 229 | |
| 230 | =item B<-g> I<table> (postings per group table) |
| 231 | |
| 232 | Override I<DBTableGrps> from F<newsstats.conf>. |
| 233 | |
| 234 | =item B<-c> I<table> (client data table) |
| 235 | |
| 236 | Override I<DBTableClnts> from F<newsstats.conf>. |
| 237 | |
| 238 | =item B<-s> I<table> (server/host data table) |
| 239 | |
| 240 | Override I<DBTableHosts> from F<newsstats.conf>. |
| 241 | |
| 242 | =back |
| 243 | |
| 244 | =head1 INSTALLATION |
| 245 | |
| 246 | See doc/INSTALL. |
| 247 | |
| 248 | =head1 EXAMPLES |
| 249 | |
| 250 | Process all types of information for lasth month: |
| 251 | |
| 252 | gatherstats |
| 253 | |
| 254 | Do a dry run, showing results of processing: |
| 255 | |
| 256 | gatherstats -do |
| 257 | |
| 258 | Process all types of information for January of 2010: |
| 259 | |
| 260 | gatherstats -m 2010-01 |
| 261 | |
| 262 | Process only number of postings for the year of 2010: |
| 263 | |
| 264 | gatherstats -p 2010-01:2010-12 -t groups |
| 265 | |
| 266 | =head1 FILES |
| 267 | |
| 268 | =over 4 |
| 269 | |
| 270 | =item F<gatherstats.pl> |
| 271 | |
| 272 | The script itself. |
| 273 | |
| 274 | =item F<NewsStats.pm> |
| 275 | |
| 276 | Library functions for the NewsStats package. |
| 277 | |
| 278 | =item F<newsstats.conf> |
| 279 | |
| 280 | Runtime configuration file for B<yapfaq>. |
| 281 | |
| 282 | =back |
| 283 | |
| 284 | =head1 BUGS |
| 285 | |
| 286 | Please report any bugs or feature requests to the author or use the |
| 287 | bug tracker at L<http://bugs.th-h.de/>! |
| 288 | |
| 289 | =head1 SEE ALSO |
| 290 | |
| 291 | =over 2 |
| 292 | |
| 293 | =item - |
| 294 | |
| 295 | doc/README |
| 296 | |
| 297 | =item - |
| 298 | |
| 299 | doc/INSTALL |
| 300 | |
| 301 | =back |
| 302 | |
| 303 | This script is part of the B<NewsStats> package. |
| 304 | |
| 305 | =head1 AUTHOR |
| 306 | |
| 307 | Thomas Hochstein <thh@inter.net> |
| 308 | |
| 309 | =head1 COPYRIGHT AND LICENSE |
| 310 | |
| 311 | Copyright (c) 2010 Thomas Hochstein <thh@inter.net> |
| 312 | |
| 313 | This program is free software; you may redistribute it and/or modify it |
| 314 | under the same terms as Perl itself. |
| 315 | |
| 316 | =cut |