misc/cronjobs/update_totalissues.pl

   1 #!/usr/bin/perl
   2
   3 # Copyright 2012 C & P Bibliography Services
   4 #
   5 # This file is part of Koha.
   6 #
   7 # Koha is free software; you can redistribute it and/or modify it
   8 # under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 3 of the License, or
  10 # (at your option) any later version.
  11 #
  12 # Koha is distributed in the hope that it will be useful, but
  13 # WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with Koha; if not, see <http://www.gnu.org/licenses>.
  19
  20 use strict;
  21 use warnings;
  22
  23 BEGIN {
  24
  25     # find Koha's Perl modules
  26     # test carefully before changing this
  27     use FindBin;
  28     eval { require "$FindBin::Bin/../kohalib.pl" };
  29 }
  30
  31 use Getopt::Long;
  32 use Pod::Usage;
  33
  34 use Koha::Script -cron;
  35 use Koha::DateUtils qw/ dt_from_string /;
  36 use C4::Context;
  37 use C4::Biblio;
  38 use C4::Log;
  39 use DateTime;
  40 use DateTime::Format::MySQL;
  41 use Time::HiRes qw/time/;
  42 use POSIX qw/strftime ceil/;
  43
  44 sub usage {
  45     pod2usage( -verbose => 2 );
  46     exit;
  47 }
  48
  49 $| = 1;
  50
  51 # command-line parameters
  52 my $verbose   = 0;
  53 my $test_only = 0;
  54 my $want_help = 0;
  55 my $since;
  56 my $interval;
  57 my $usestats    = 0;
  58 my $useitems    = 0;
  59 my $incremental = 0;
  60 my $commit      = 100;
  61 my $unit;
  62
  63 my $result = GetOptions(
  64     'v|verbose'    => \$verbose,
  65     't|test'       => \$test_only,
  66     's|since=s'    => \$since,
  67     'i|interval=s' => \$interval,
  68     'use-stats'    => \$usestats,
  69     'use-items'    => \$useitems,
  70     'incremental'  => \$incremental,
  71     'c|commit=i'   => \$commit,
  72     'h|help'       => \$want_help
  73 );
  74
  75 binmode( STDOUT, ":encoding(UTF-8)" );
  76
  77 if ( defined $since && defined $interval ) {
  78     print "The --since and --interval options are mutually exclusive.\n\n";
  79     $want_help = 1;
  80 }
  81
  82 if ( $useitems && $incremental ) {
  83     print
  84       "The --use-items and --incremental options are mutually exclusive.\n\n";
  85     $want_help = 1;
  86 }
  87
  88 if ( $incremental && !( defined $since || defined $interval ) ) {
  89     $interval = '24h';
  90 }
  91
  92 unless ( $usestats || $useitems ) {
  93     print "You must specify either --use-stats and/or --use-items.\n\n";
  94     $want_help = 1;
  95 }
  96
  97 if ( not $result or $want_help ) {
  98     usage();
  99 }
 100
 101 cronlogaction();
 102
 103 my $dbh = C4::Context->dbh;
 104 $dbh->{AutoCommit} = 0;
 105
 106 my $num_bibs_processed = 0;
 107 my $num_bibs_error = 0;
 108
 109 my $starttime = time();
 110
 111 process_items() if $useitems;
 112 process_stats() if $usestats;
 113
 114 report();
 115
 116 exit 0;
 117
 118 sub process_items {
 119     my $query =
 120 "SELECT items.biblionumber, SUM(items.issues) FROM items GROUP BY items.biblionumber;";
 121     process_query($query);
 122 }
 123
 124 sub process_stats {
 125     if ($interval) {
 126         my $dt = dt_from_string();
 127
 128         my %units = (
 129             h => 'hours',
 130             d => 'days',
 131             w => 'weeks',
 132             m => 'months',
 133             y => 'years'
 134         );
 135
 136         $interval =~ m/([0-9]*)([hdwmy]?)$/;
 137         $unit = $2 || 'd';
 138         $since = DateTime::Format::MySQL->format_datetime(
 139             $dt->subtract( $units{$unit} => $1 ) );
 140     }
 141     my $limit = '';
 142     $limit = " WHERE statistics.datetime >= ?" if ( $interval || $since );
 143
 144     my $query =
 145 "SELECT biblio.biblionumber, COUNT(statistics.itemnumber) FROM biblio\
 146  LEFT JOIN items ON (biblio.biblionumber=items.biblionumber)\
 147  LEFT JOIN statistics ON (items.itemnumber=statistics.itemnumber AND statistics.type = 'issue')
 148  $limit\
 149  GROUP BY biblio.biblionumber";
 150     process_query( $query, $limit );
 151
 152     $dbh->commit();
 153 }
 154
 155 sub process_query {
 156     my $query    = shift;
 157     my $uselimit = shift;
 158     my $sth      = $dbh->prepare($query);
 159
 160     if ( $since && $uselimit ) {
 161         $sth->execute($since);
 162     }
 163     else {
 164         $sth->execute();
 165     }
 166
 167     while ( my ( $biblionumber, $totalissues ) = $sth->fetchrow_array() ) {
 168         $num_bibs_processed++;
 169         $totalissues = 0 unless $totalissues;
 170         print "Processing bib $biblionumber ($totalissues issues)\n"
 171           if $verbose;
 172         if ( not $test_only ) {
 173             my $ret;
 174             if ( $incremental && $totalissues > 0 ) {
 175                 $ret = UpdateTotalIssues( $biblionumber, $totalissues );
 176             }
 177             else {
 178                 $ret = UpdateTotalIssues( $biblionumber, 0, $totalissues );
 179             }
 180             unless ($ret) {
 181                 print "Error while processing bib $biblionumber\n" if $verbose;
 182                 $num_bibs_error++;
 183             }
 184         }
 185         if ( not $test_only and ( $num_bibs_processed % $commit ) == 0 ) {
 186             print_progress_and_commit($num_bibs_processed);
 187         }
 188     }
 189
 190     $dbh->commit();
 191 }
 192
 193 sub report {
 194     my $endtime = time();
 195     my $totaltime = ceil( ( $endtime - $starttime ) * 1000 );
 196     $starttime = strftime( '%D %T', localtime($starttime) );
 197     $endtime   = strftime( '%D %T', localtime($endtime) );
 198
 199     my $summary = <<_SUMMARY_;
 200
 201 Update total issues count script report
 202 =======================================================
 203 Run started at:                         $starttime
 204 Run ended at:                           $endtime
 205 Total run time:                         $totaltime ms
 206 Number of bibs modified:                $num_bibs_processed
 207 Number of bibs with error:              $num_bibs_error
 208 _SUMMARY_
 209     $summary .= "\n****  Ran in test mode only  ****\n" if $test_only;
 210     print $summary;
 211 }
 212
 213 sub print_progress_and_commit {
 214     my $recs = shift;
 215     $dbh->commit();
 216     print "... processed $recs records\n";
 217 }
 218
 219 =head1 NAME
 220
 221 update_totalissues.pl
 222
 223 =head1 SYNOPSIS
 224
 225   update_totalissues.pl --use-stats
 226   update_totalissues.pl --use-items
 227   update_totalissues.pl --commit=1000
 228   update_totalissues.pl --since='2012-01-01'
 229   update_totalissues.pl --interval=30d
 230
 231 =head1 DESCRIPTION
 232
 233 This batch job populates bibliographic records' total issues count based
 234 on historical issue statistics.
 235
 236 =over 8
 237
 238 =item B<--help>
 239
 240 Prints this help
 241
 242 =item B<-v|--verbose>
 243
 244 Provide verbose log information (list every bib modified).
 245
 246 =item B<--use-stats>
 247
 248 Use the data in the statistics table for populating total issues.
 249
 250 =item B<--use-items>
 251
 252 Use items.issues data for populating total issues. Note that issues
 253 data from the items table does not respect the --since or --interval
 254 options, by definition. Also note that if both --use-stats and
 255 --use-items are specified, the count of biblios processed will be
 256 misleading.
 257
 258 =item B<-s|--since=DATE>
 259
 260 Only process issues recorded in the statistics table since DATE.
 261
 262 =item B<-i|--interval=S>
 263
 264 Only process issues recorded in the statistics table in the last N
 265 units of time. The interval should consist of a number with a one-letter
 266 unit suffix. The valid suffixes are h (hours), d (days), w (weeks),
 267 m (months), and y (years). The default unit is days.
 268
 269 =item B<--incremental>
 270
 271 Add the number of issues found in the statistics table to the existing
 272 total issues count. Intended so that this script can be used as a cron
 273 job to update popularity information during low-usage periods. If neither
 274 --since or --interval are specified, incremental mode will default to
 275 processing the last twenty-four hours.
 276
 277 =item B<--commit=N>
 278
 279 Commit the results to the database after every N records are processed.
 280
 281 =item B<--test>
 282
 283 Only test the popularity population script.
 284
 285 =back
 286
 287 =head1 WARNING
 288
 289 If the time on your database server does not match the time on your Koha
 290 server you will need to take that into account, and probably use the
 291 --since argument instead of the --interval argument for incremental
 292 updating.
 293
 294 =head1 CREDITS
 295
 296 This patch to Koha was sponsored by the Arcadia Public Library and the
 297 Arcadia Public Library Foundation in honor of Jackie Faust-Moreno, late
 298 director of the Arcadia Public Library.
 299
 300 =head1 AUTHOR
 301
 302 Jared Camins-Esakov <jcamins AT cpbibliography DOT com>
 303
 304 =cut