[15869] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # AutoExtractMetadata.pm -- base plugin for all plugins that want to do metadata extraction from text and/or metadata
|
---|
| 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) 2008 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 | # This plugin uses the supporting Extractors to add metadata extraction
|
---|
| 27 | # functionality to BasePlugin.
|
---|
| 28 |
|
---|
| 29 |
|
---|
| 30 | package AutoExtractMetadata;
|
---|
| 31 |
|
---|
| 32 | use strict;
|
---|
| 33 | no strict 'subs';
|
---|
| 34 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
| 35 |
|
---|
| 36 | use BasePlugin;
|
---|
| 37 | use AcronymExtractor;
|
---|
| 38 | use KeyphraseExtractor;
|
---|
| 39 | use EmailAddressExtractor;
|
---|
| 40 | use DateExtractor;
|
---|
| 41 | use GISExtractor;
|
---|
| 42 |
|
---|
| 43 | sub BEGIN {
|
---|
[17112] | 44 | @AutoExtractMetadata::ISA = ( 'BasePlugin', 'AcronymExtractor', 'KeyphraseExtractor', 'EmailAddressExtractor', 'DateExtractor','GISExtractor' );
|
---|
[15869] | 45 | }
|
---|
| 46 |
|
---|
[16011] | 47 | my $arguments = [
|
---|
| 48 | {'name' => "first",
|
---|
| 49 | 'desc' => "{AutoExtractMetadata.first}",
|
---|
| 50 | 'type' => "string",
|
---|
| 51 | 'reqd' => "no" }
|
---|
| 52 | ];
|
---|
[15869] | 53 |
|
---|
| 54 |
|
---|
| 55 | my $options = { 'name' => "AutoExtractMetadata",
|
---|
| 56 | 'desc' => "{AutoExtractMetadata.desc}",
|
---|
| 57 | 'abstract' => "yes",
|
---|
[22859] | 58 | 'inherits' => "yes",
|
---|
[15869] | 59 | 'args' => $arguments };
|
---|
| 60 |
|
---|
| 61 |
|
---|
| 62 | sub new {
|
---|
| 63 |
|
---|
| 64 | # Start the AutoExtractMetadata Constructor
|
---|
| 65 | my $class = shift (@_);
|
---|
[16698] | 66 | my ($pluginlist,$inputargs,$hashArgOptLists,$auxiliary) = @_;
|
---|
[15869] | 67 | push(@$pluginlist, $class);
|
---|
| 68 |
|
---|
| 69 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 70 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
| 71 |
|
---|
| 72 | # load up the options and args for the supporting plugins
|
---|
| 73 | new AcronymExtractor($pluginlist, $inputargs, $hashArgOptLists);
|
---|
| 74 | new KeyphraseExtractor($pluginlist, $inputargs, $hashArgOptLists);
|
---|
| 75 | new EmailAddressExtractor($pluginlist, $inputargs, $hashArgOptLists);
|
---|
| 76 | new DateExtractor($pluginlist, $inputargs, $hashArgOptLists);
|
---|
| 77 | new GISExtractor($pluginlist, $inputargs, $hashArgOptLists);
|
---|
[16698] | 78 | my $self = new BasePlugin($pluginlist, $inputargs, $hashArgOptLists,$auxiliary);
|
---|
[15869] | 79 |
|
---|
| 80 | return bless $self, $class;
|
---|
| 81 |
|
---|
| 82 | }
|
---|
| 83 |
|
---|
| 84 | sub begin {
|
---|
| 85 | my $self = shift (@_);
|
---|
| 86 | my ($pluginfo, $base_dir, $processor, $maxdocs) = @_;
|
---|
| 87 |
|
---|
[17026] | 88 | $self->SUPER::begin(@_);
|
---|
| 89 |
|
---|
[15869] | 90 | #initialise those extractors that need initialisation
|
---|
| 91 | $self->initialise_acronym_extractor();
|
---|
[15919] | 92 | $self->initialise_gis_extractor();
|
---|
[17026] | 93 |
|
---|
[15869] | 94 | }
|
---|
| 95 |
|
---|
| 96 | sub end {
|
---|
| 97 | # potentially called at the end of each plugin pass
|
---|
| 98 | # import.pl only has one plugin pass, but buildcol.pl has multiple ones
|
---|
| 99 |
|
---|
| 100 | my ($self) = @_;
|
---|
| 101 | # finalise those extractors that need finalisation
|
---|
| 102 | $self->finalise_acronym_extractor();
|
---|
| 103 | }
|
---|
| 104 |
|
---|
[16011] | 105 | # here is where we call methods from the supporting extractor plugins
|
---|
[15869] | 106 | sub auto_extract_metadata {
|
---|
| 107 | my $self = shift(@_);
|
---|
| 108 | my ($doc_obj) = @_;
|
---|
| 109 |
|
---|
[16011] | 110 | if ($self->{'first'}) {
|
---|
| 111 | my $thissection = $doc_obj->get_top_section();
|
---|
| 112 | while (defined $thissection) {
|
---|
| 113 | my $text = $doc_obj->get_text($thissection);
|
---|
| 114 | $self->extract_first_NNNN_characters (\$text, $doc_obj, $thissection) if $text =~ /./;
|
---|
| 115 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 116 | }
|
---|
| 117 | }
|
---|
[15869] | 118 | $self->extract_acronym_metadata($doc_obj);
|
---|
| 119 | $self->extract_keyphrase_metadata($doc_obj);
|
---|
| 120 | $self->extract_email_metadata($doc_obj);
|
---|
| 121 | $self->extract_date_metadata($doc_obj);
|
---|
| 122 | $self->extract_gis_metadata($doc_obj);
|
---|
| 123 |
|
---|
| 124 | }
|
---|
| 125 |
|
---|
[16011] | 126 |
|
---|
| 127 | # FIRSTNNN: extract the first NNN characters as metadata
|
---|
| 128 | sub extract_first_NNNN_characters {
|
---|
| 129 | my $self = shift (@_);
|
---|
| 130 | my ($textref, $doc_obj, $thissection) = @_;
|
---|
| 131 |
|
---|
| 132 | foreach my $size (split /,/, $self->{'first'}) {
|
---|
| 133 | my $tmptext = $$textref;
|
---|
| 134 | $tmptext =~ s/^\s+//;
|
---|
| 135 | $tmptext =~ s/\s+$//;
|
---|
| 136 | $tmptext =~ s/\s+/ /gs;
|
---|
| 137 | $tmptext = substr ($tmptext, 0, $size);
|
---|
| 138 | $tmptext =~ s/\s\S*$/…/;
|
---|
| 139 | $doc_obj->add_utf8_metadata ($thissection, "First$size", $tmptext);
|
---|
| 140 | }
|
---|
| 141 | }
|
---|
| 142 |
|
---|
[15869] | 143 | sub clean_up_after_doc_obj_processing {
|
---|
| 144 | my $self = shift(@_);
|
---|
| 145 |
|
---|
| 146 | $self->SUPER::clean_up_after_doc_obj_processing();
|
---|
| 147 | $self->GISExtractor::clean_up_temp_files();
|
---|
| 148 | }
|
---|
| 149 |
|
---|
| 150 | 1;
|
---|