Koha/Sitemapper/Writer.pm

   1 package Koha::Sitemapper::Writer;
   2
   3 #
   4 # Copyright 2015 Tamil s.a.r.l.
   5 #
   6 # This file is part of Koha.
   7 #
   8 # Koha is free software; you can redistribute it and/or modify it under the
   9 # terms of the GNU General Public License as published by the Free Software
  10 # Foundation; either version 3 of the License, or (at your option) any later
  11 # version.
  12 #
  13 # Koha is distributed in the hope that it will be useful, but WITHOUT ANY
  14 # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
  15 # A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License along
  18 # with Koha; if not, write to the Free Software Foundation, Inc.,
  19 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  20
  21
  22 use Moo;
  23 use Modern::Perl;
  24 use XML::Writer;
  25 use IO::File;
  26 use DateTime;
  27
  28
  29 my $MAX = 50000;
  30
  31
  32 has sitemapper => (is => 'rw', );
  33
  34 has current => ( is => 'rw', default => sub { $MAX } );
  35
  36 has count => ( is => 'rw', default => sub { 0 } );
  37
  38 has writer => ( is => 'rw',  );
  39
  40
  41
  42 sub _writer_create {
  43     my ($self, $name) = @_;
  44     $name = $self->sitemapper->dir . "/$name";
  45     my $fh = IO::File->new(">$name");
  46     unless ($fh) {
  47         say "Impossible to create file: $name";
  48         exit;
  49     }
  50     my $writer = XML::Writer->new(
  51         OUTPUT => $fh,
  52         DATA_MODE => 1,
  53         DATA_INDENT => 2,
  54     );
  55     $writer->xmlDecl("UTF-8");
  56     return $writer;
  57 }
  58
  59
  60 sub _writer_end {
  61     my $self = shift;
  62     return unless $self->writer;
  63     $self->writer->endTag();
  64     $self->writer->end();
  65     $self->writer->getOutput()->close();
  66 }
  67
  68
  69 sub write {
  70     my ($self, $biblionumber, $timestamp) = @_;
  71
  72     if ( $self->current == $MAX ) {
  73         $self->_writer_end();
  74         $self->count( $self->count + 1 );
  75         my $w = $self->_writer_create( sprintf("sitemap%04d.xml", $self->count) );
  76         $w->startTag(
  77             'urlset',
  78             'xmlns' => 'http://www.sitemaps.org/schemas/sitemap/0.9',
  79             'xmlns:xsi' => 'http://www.w3.org/2001/XMLSchema-instance',
  80             'xsi:schemaLocation' => 'http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd');
  81         $self->writer($w);
  82         $self->current(0);
  83     }
  84
  85     $self->current( $self->current + 1 );
  86     my $writer = $self->writer;
  87     my $url = $self->sitemapper->url .
  88               ($self->sitemapper->short ? '/bib/' : '/cgi-bin/koha/opac-detail.pl?biblionumber=') .
  89               $biblionumber;
  90     $writer->startTag('url');
  91         $writer->startTag('loc');
  92             $writer->characters($url);
  93         $writer->endTag();
  94         $writer->startTag('lastmod');
  95             $timestamp = substr($timestamp, 0, 10);
  96             $writer->characters($timestamp);
  97         $writer->endTag();
  98     $writer->endTag();
  99 }
 100
 101
 102 sub end {
 103     my $self = shift;
 104
 105     $self->_writer_end();
 106
 107     my $w = $self->_writer_create("sitemapindex.xml");
 108     $w->startTag('sitemapindex', 'xmlns' => 'http://www.sitemaps.org/schemas/sitemap/0.9');
 109     my $now = DateTime->now()->ymd;
 110     for my $i ( 1..$self->count ) {
 111         $w->startTag('sitemap');
 112             $w->startTag('loc');
 113                 my $name = sprintf("sitemap%04d.xml", $i);
 114                 $w->characters($self->sitemapper->url . "/$name");
 115             $w->endTag();
 116             $w->startTag('lastmod');
 117                 $w->characters($now);
 118             $w->endTag();
 119         $w->endTag();
 120     }
 121     $w->endTag();
 122 }
 123
 124
 125 1;