1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # KeyphraseExtractor - helper plugin to extract key phrases
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software
|
---|
6 | # from the New Zealand Digital Library Project at the
|
---|
7 | # University of Waikato, New Zealand.
|
---|
8 | #
|
---|
9 | # Copyright (C) 2008 New Zealand Digital Library Project
|
---|
10 | #
|
---|
11 | # This program is free software; you can redistribute it and/or modify
|
---|
12 | # it under the terms of the GNU General Public License as published by
|
---|
13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
14 | # (at your option) any later version.
|
---|
15 | #
|
---|
16 | # This program is distributed in the hope that it will be useful,
|
---|
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | # GNU General Public License for more details.
|
---|
20 | #
|
---|
21 | # You should have received a copy of the GNU General Public License
|
---|
22 | # along with this program; if not, write to the Free Software
|
---|
23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | #
|
---|
25 | ###########################################################################
|
---|
26 |
|
---|
27 | package KeyphraseExtractor;
|
---|
28 |
|
---|
29 | use Kea;
|
---|
30 | use PrintInfo;
|
---|
31 | use gsprintf 'gsprintf';
|
---|
32 |
|
---|
33 | use strict;
|
---|
34 | no strict 'subs';
|
---|
35 |
|
---|
36 | BEGIN {
|
---|
37 | @KeyphraseExtractor::ISA = ('PrintInfo');
|
---|
38 | }
|
---|
39 |
|
---|
40 | my $arguments = [
|
---|
41 | { 'name' => "extract_keyphrases",
|
---|
42 | 'desc' => "{KeyphraseExtractor.extract_keyphrases}",
|
---|
43 | 'type' => "flag",
|
---|
44 | 'reqd' => "no" },
|
---|
45 | { 'name' => "extract_keyphrases_kea4",
|
---|
46 | 'desc' => "{KeyphraseExtractor.extract_keyphrases_kea4}",
|
---|
47 | 'type' => "flag",
|
---|
48 | 'reqd' => "no" },
|
---|
49 | { 'name' => "extract_keyphrase_options",
|
---|
50 | 'desc' => "{KeyphraseExtractor.extract_keyphrase_options}",
|
---|
51 | 'type' => "string",
|
---|
52 | 'deft' => "",
|
---|
53 | 'reqd' => "no" }
|
---|
54 | ];
|
---|
55 |
|
---|
56 | my $options = { 'name' => "KeyphraseExtractor",
|
---|
57 | 'desc' => "{KeyphraseExtractor.desc}",
|
---|
58 | 'abstract' => "yes",
|
---|
59 | 'inherits' => "yes",
|
---|
60 | 'args' => $arguments };
|
---|
61 |
|
---|
62 |
|
---|
63 | sub new {
|
---|
64 | my ($class) = shift (@_);
|
---|
65 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
66 | push(@$pluginlist, $class);
|
---|
67 |
|
---|
68 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
69 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
70 |
|
---|
71 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
72 |
|
---|
73 | return bless $self, $class;
|
---|
74 |
|
---|
75 | }
|
---|
76 | # extract metadata
|
---|
77 | sub extract_keyphrase_metadata {
|
---|
78 |
|
---|
79 | my $self = shift (@_);
|
---|
80 | my ($doc_obj) = @_;
|
---|
81 |
|
---|
82 | if ($self->{'extract_keyphrases'} || $self->{'extract_keyphrases_kea4'}) {
|
---|
83 | $self->extract_keyphrases($doc_obj);
|
---|
84 | }
|
---|
85 |
|
---|
86 | }
|
---|
87 |
|
---|
88 |
|
---|
89 | #adding kea keyphrases
|
---|
90 | sub extract_keyphrases
|
---|
91 | {
|
---|
92 | my $self = shift(@_);
|
---|
93 | my $doc_obj = shift(@_);
|
---|
94 |
|
---|
95 | # Use Kea 3.0 unless 4.0 has been specified
|
---|
96 | my $kea_version = "3.0";
|
---|
97 | if ($self->{'extract_keyphrases_kea4'}) {
|
---|
98 | $kea_version = "4.0";
|
---|
99 | }
|
---|
100 |
|
---|
101 | # Check that Kea exists, and tell the user where to get it if not
|
---|
102 | my $keahome = &Kea::get_Kea_directory($kea_version);
|
---|
103 | if (!-e $keahome) {
|
---|
104 | gsprintf(STDERR, "{KeyphraseExtractor.missing_kea}\n", $keahome, $kea_version);
|
---|
105 | return;
|
---|
106 | }
|
---|
107 |
|
---|
108 | my $thissection = $doc_obj->get_top_section();
|
---|
109 | my $text = "";
|
---|
110 | my $list;
|
---|
111 |
|
---|
112 | #loop through sections to gather whole doc
|
---|
113 | while (defined $thissection) {
|
---|
114 | my $sectiontext = $doc_obj->get_text($thissection);
|
---|
115 | $text = $text.$sectiontext;
|
---|
116 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
117 | }
|
---|
118 |
|
---|
119 | if($self->{'extract_keyphrase_options'}) { #if kea options flag is set, call Kea with specified options
|
---|
120 | $list = &Kea::extract_KeyPhrases ($kea_version, $text, $self->{'extract_keyphrase_options'});
|
---|
121 | } else { #otherwise call Kea with no options
|
---|
122 | $list = &Kea::extract_KeyPhrases ($kea_version, $text);
|
---|
123 | }
|
---|
124 |
|
---|
125 | if ($list){
|
---|
126 | # if a list of kea keyphrases was returned (ie not empty)
|
---|
127 | if ($self->{'verbosity'}) {
|
---|
128 | gsprintf(STDERR, "{KeyphraseExtractor.keyphrases}: $list\n");
|
---|
129 | }
|
---|
130 |
|
---|
131 | #add metadata to top section
|
---|
132 | $thissection = $doc_obj->get_top_section();
|
---|
133 |
|
---|
134 | # add all key phrases as one metadata
|
---|
135 | $doc_obj->add_metadata($thissection, "Keyphrases", $list);
|
---|
136 |
|
---|
137 | # add individual key phrases as multiple metadata
|
---|
138 | foreach my $keyphrase (split(',', $list)) {
|
---|
139 | $keyphrase =~ s/^\s+|\s+$//g;
|
---|
140 | $doc_obj->add_metadata($thissection, "Keyphrase", $keyphrase);
|
---|
141 | }
|
---|
142 | }
|
---|
143 | }
|
---|
144 |
|
---|
145 | 1;
|
---|