[16025] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # AcronymExtractor - helper plugin that extacts acronyms from text
|
---|
| 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 |
|
---|
[15867] | 27 | package AcronymExtractor;
|
---|
| 28 |
|
---|
| 29 | use acronym;
|
---|
| 30 | use PrintInfo;
|
---|
[15887] | 31 | use strict;
|
---|
[15867] | 32 |
|
---|
[25797] | 33 | use gsprintf 'gsprintf';
|
---|
| 34 |
|
---|
[15867] | 35 | BEGIN {
|
---|
| 36 | @AcronymExtractor::ISA = ('PrintInfo');
|
---|
| 37 | }
|
---|
| 38 |
|
---|
| 39 | my $arguments = [
|
---|
| 40 | { 'name' => "extract_acronyms",
|
---|
| 41 | 'desc' => "{AcronymExtractor.extract_acronyms}",
|
---|
| 42 | 'type' => "flag",
|
---|
| 43 | 'reqd' => "no" },
|
---|
| 44 | { 'name' => "markup_acronyms",
|
---|
| 45 | 'desc' => "{AcronymExtractor.markup_acronyms}",
|
---|
| 46 | 'type' => "flag",
|
---|
| 47 | 'reqd' => "no" } ];
|
---|
| 48 |
|
---|
| 49 | my $options = { 'name' => "AcronymExtractor",
|
---|
| 50 | 'desc' => "{AcronymExtractor.desc}",
|
---|
| 51 | 'abstract' => "yes",
|
---|
| 52 | 'inherits' => "yes",
|
---|
| 53 | 'args' => $arguments };
|
---|
| 54 |
|
---|
| 55 |
|
---|
| 56 | sub new {
|
---|
| 57 | my ($class) = shift (@_);
|
---|
| 58 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 59 | push(@$pluginlist, $class);
|
---|
| 60 |
|
---|
[15918] | 61 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 62 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[15867] | 63 |
|
---|
[15881] | 64 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists,1);
|
---|
[15867] | 65 |
|
---|
| 66 | return bless $self, $class;
|
---|
| 67 |
|
---|
| 68 | }
|
---|
| 69 |
|
---|
| 70 |
|
---|
| 71 | # initialise metadata extractors
|
---|
| 72 | sub initialise_acronym_extractor {
|
---|
| 73 | my $self = shift (@_);
|
---|
| 74 |
|
---|
| 75 | if ($self->{'extract_acronyms'} || $self->{'markup_acronyms'}) {
|
---|
| 76 | &acronym::initialise_acronyms();
|
---|
| 77 | }
|
---|
| 78 | }
|
---|
| 79 |
|
---|
| 80 | # finalise metadata extractors
|
---|
| 81 | sub finalise_acronym_extractor {
|
---|
| 82 | my $self = shift (@_);
|
---|
| 83 |
|
---|
| 84 | if ($self->{'extract_acronyms'} || $self->{'markup_acronyms'}) {
|
---|
| 85 | &acronym::finalise_acronyms();
|
---|
| 86 | }
|
---|
| 87 | }
|
---|
| 88 |
|
---|
| 89 | # extract metadata
|
---|
| 90 | sub extract_acronym_metadata {
|
---|
| 91 |
|
---|
| 92 | my $self = shift (@_);
|
---|
| 93 | my ($doc_obj) = @_;
|
---|
| 94 |
|
---|
| 95 |
|
---|
| 96 | if ($self->{'extract_acronyms'}) {
|
---|
| 97 | my $thissection = $doc_obj->get_top_section();
|
---|
| 98 | while (defined $thissection) {
|
---|
| 99 | my $text = $doc_obj->get_text($thissection);
|
---|
| 100 | $self->extract_acronyms (\$text, $doc_obj, $thissection) if $text =~ /./;
|
---|
| 101 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 102 | }
|
---|
| 103 | }
|
---|
| 104 |
|
---|
| 105 | if ($self->{'markup_acronyms'}) {
|
---|
| 106 | my $thissection = $doc_obj->get_top_section();
|
---|
| 107 | while (defined $thissection) {
|
---|
| 108 | my $text = $doc_obj->get_text($thissection);
|
---|
| 109 | $text = $self->markup_acronyms ($text, $doc_obj, $thissection);
|
---|
| 110 | $doc_obj->delete_text($thissection);
|
---|
| 111 | $doc_obj->add_text($thissection, $text);
|
---|
| 112 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 113 | }
|
---|
| 114 | }
|
---|
| 115 |
|
---|
| 116 | }
|
---|
| 117 |
|
---|
| 118 |
|
---|
| 119 |
|
---|
| 120 | # extract acronyms from a section in a document. progress is
|
---|
| 121 | # reported to outhandle based on the verbosity. both the Acronym
|
---|
| 122 | # and the AcronymKWIC metadata items are created.
|
---|
| 123 |
|
---|
| 124 | sub extract_acronyms {
|
---|
| 125 | my $self = shift (@_);
|
---|
| 126 | my ($textref, $doc_obj, $thissection) = @_;
|
---|
| 127 | my $outhandle = $self->{'outhandle'};
|
---|
| 128 |
|
---|
| 129 | # print $outhandle " extracting acronyms ...\n"
|
---|
[16013] | 130 | gsprintf($outhandle, " {AcronymExtractor.extracting_acronyms}...\n")
|
---|
[15867] | 131 | if ($self->{'verbosity'} > 2);
|
---|
| 132 |
|
---|
| 133 | my $acro_array = &acronym::acronyms($textref);
|
---|
| 134 |
|
---|
| 135 | foreach my $acro (@$acro_array) {
|
---|
| 136 |
|
---|
| 137 | #check that this is the first time ...
|
---|
| 138 | my $seen_before = "false";
|
---|
| 139 | my $previous_data = $doc_obj->get_metadata($thissection, "Acronym");
|
---|
| 140 | foreach my $thisAcro (@$previous_data) {
|
---|
| 141 | if ($thisAcro eq $acro->to_string()) {
|
---|
| 142 | $seen_before = "true";
|
---|
| 143 | if ($self->{'verbosity'} >= 4) {
|
---|
[16013] | 144 | gsprintf($outhandle, " {AcronymExtractor.already_seen} " .
|
---|
[15867] | 145 | $acro->to_string() . "\n");
|
---|
| 146 | }
|
---|
| 147 | }
|
---|
| 148 | }
|
---|
| 149 |
|
---|
| 150 | if ($seen_before eq "false") {
|
---|
| 151 | #write it to the file ...
|
---|
| 152 | $acro->write_to_file();
|
---|
| 153 |
|
---|
| 154 | #do the normal acronym
|
---|
| 155 | $doc_obj->add_utf8_metadata($thissection, "Acronym", $acro->to_string());
|
---|
[16013] | 156 | gsprintf($outhandle, " {AcronymExtractor.adding} ".$acro->to_string()."\n")
|
---|
[15867] | 157 | if ($self->{'verbosity'} > 3);
|
---|
| 158 | }
|
---|
| 159 | }
|
---|
| 160 |
|
---|
[16013] | 161 | gsprintf($outhandle, " {AcronymExtractor.done_acronym_extract}\n")
|
---|
[15867] | 162 | if ($self->{'verbosity'} > 2);
|
---|
| 163 | }
|
---|
| 164 |
|
---|
| 165 | sub markup_acronyms {
|
---|
| 166 | my $self = shift (@_);
|
---|
| 167 | my ($text, $doc_obj, $thissection) = @_;
|
---|
| 168 | my $outhandle = $self->{'outhandle'};
|
---|
| 169 |
|
---|
[16013] | 170 | gsprintf($outhandle, " {AcronymExtractor.marking_up_acronyms}...\n")
|
---|
[15867] | 171 | if ($self->{'verbosity'} > 2);
|
---|
| 172 |
|
---|
| 173 | #self is passed in to check for verbosity ...
|
---|
| 174 | $text = &acronym::markup_acronyms($text, $self);
|
---|
| 175 |
|
---|
[16013] | 176 | gsprintf($outhandle, " {AcronymExtractor.done_acronym_markup}\n")
|
---|
[15867] | 177 | if ($self->{'verbosity'} > 2);
|
---|
| 178 |
|
---|
| 179 | return $text;
|
---|
| 180 | }
|
---|
| 181 |
|
---|
| 182 | 1;
|
---|