source: main/trunk/greenstone2/perllib/classify/HTML.pm@ 23116

Last change on this file since 23116 was 23116, checked in by kjdon, 14 years ago

for incremental build, classifiers are not really done incrementally. Previously, we reconstructed all the docs from the database, and classified them, then processed any new/edited/deleted docs, updating the classifier as necessary. Now, we process all new/updated docs, then reconstruct the docs from the database, but only classify those not changed/deleted. This means that we are only ever adding docs to a classifier, never updating or deleting. I have removed edit_mode and all code handling deleting stuff from the classifier.

  • Property svn:executable set to *
  • Property svn:keywords set to Author Date Id Revision
File size: 2.8 KB
Line 
1###########################################################################
2#
3# HTML.pm --
4# A component of the Greenstone digital library software
5# from the New Zealand Digital Library Project at the
6# University of Waikato, New Zealand.
7#
8# Copyright (C) 1999 New Zealand Digital Library Project
9#
10# This program is free software; you can redistribute it and/or modify
11# it under the terms of the GNU General Public License as published by
12# the Free Software Foundation; either version 2 of the License, or
13# (at your option) any later version.
14#
15# This program is distributed in the hope that it will be useful,
16# but WITHOUT ANY WARRANTY; without even the implied warranty of
17# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18# GNU General Public License for more details.
19#
20# You should have received a copy of the GNU General Public License
21# along with this program; if not, write to the Free Software
22# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
23#
24###########################################################################
25
26# html classifier plugin - creates an empty classification
27# that's simply a link to a web page
28
29package HTML;
30
31use BaseClassifier;
32
33use strict;
34no strict 'refs'; # allow filehandles to be variables and viceversa
35
36sub BEGIN {
37 @HTML::ISA = ('BaseClassifier');
38}
39
40my $arguments =
41 [ { 'name' => "url",
42 'desc' => "{HTML.url}",
43 'type' => "string",
44 'reqd' => "yes" } ,
45 { 'name' => "buttonname",
46 'desc' => "{BasClas.buttonname}",
47 'type' => "string",
48 'deft' => "Browse",
49 'reqd' => "no" } ];
50
51my $options = { 'name' => "HTML",
52 'desc' => "{HTML.desc}",
53 'abstract' => "no",
54 'inherits' => "yes",
55 'args' => $arguments };
56
57
58sub new {
59 my ($class) = shift (@_);
60 my ($classifierslist,$inputargs,$hashArgOptLists) = @_;
61 push(@$classifierslist, $class);
62
63 push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
64 push(@{$hashArgOptLists->{"OptList"}},$options);
65
66 my $self = new BaseClassifier($classifierslist, $inputargs, $hashArgOptLists);
67
68 if ($self->{'info_only'}) {
69 # don't worry about any options etc
70 return bless $self, $class;
71 }
72
73 if (!$self->{'url'}) {
74 my $outhandle = $self->{'outhandle'};
75 print $outhandle "HTML Error: required option -url not supplied\n";
76 $self->print_txt_usage("");
77 die "HTML Error: required option -url not supplied\n";
78 }
79 return bless $self, $class;
80}
81
82sub init {
83 my $self = shift (@_);
84}
85
86sub classify {
87 my $self = shift (@_);
88 my ($doc_obj) = @_;
89
90 # we don't do anything for individual documents
91}
92
93sub get_classify_info {
94 my $self = shift (@_);
95
96 my %classifyinfo = ('thistype'=>'Invisible',
97 'childtype'=>'HTML',
98 'Title'=>$self->{'buttonname'},
99 'contains'=>[]);
100
101 push (@{$classifyinfo{'contains'}}, {'OID'=>$self->{'url'}});
102
103 return \%classifyinfo;
104}
105
106
1071;
Note: See TracBrowser for help on using the repository browser.