[16640] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # CJKTextSegmenter - helper plugin that segments chinese/japanese/korean text
|
---|
| 4 | # into single characters
|
---|
| 5 | #
|
---|
| 6 | # A component of the Greenstone digital library software
|
---|
| 7 | # from the New Zealand Digital Library Project at the
|
---|
| 8 | # University of Waikato, New Zealand.
|
---|
| 9 | #
|
---|
| 10 | # Copyright (C) 2008 New Zealand Digital Library Project
|
---|
| 11 | #
|
---|
| 12 | # This program is free software; you can redistribute it and/or modify
|
---|
| 13 | # it under the terms of the GNU General Public License as published by
|
---|
| 14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 15 | # (at your option) any later version.
|
---|
| 16 | #
|
---|
| 17 | # This program is distributed in the hope that it will be useful,
|
---|
| 18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 20 | # GNU General Public License for more details.
|
---|
| 21 | #
|
---|
| 22 | # You should have received a copy of the GNU General Public License
|
---|
| 23 | # along with this program; if not, write to the Free Software
|
---|
| 24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 25 | #
|
---|
| 26 | ###########################################################################
|
---|
| 27 |
|
---|
| 28 | package CJKTextSegmenter;
|
---|
| 29 |
|
---|
| 30 | use cnseg;
|
---|
| 31 | use PrintInfo;
|
---|
| 32 | use strict;
|
---|
| 33 |
|
---|
| 34 | BEGIN {
|
---|
| 35 | @CJKTextSegmenter::ISA = ('PrintInfo');
|
---|
| 36 | }
|
---|
| 37 |
|
---|
| 38 | my $arguments = [
|
---|
| 39 | { 'name' => "separate_cjk",
|
---|
| 40 | 'desc' => "{CJKTextSegmenter.separate_cjk}",
|
---|
| 41 | 'type' => "flag",
|
---|
| 42 | 'reqd' => "no" }
|
---|
| 43 | ];
|
---|
| 44 | my $options = { 'name' => "CJKTextSegmenter",
|
---|
| 45 | 'desc' => "{CJKTextSegmenter.desc}",
|
---|
| 46 | 'abstract' => "yes",
|
---|
| 47 | 'inherits' => "yes",
|
---|
| 48 | 'args' => $arguments };
|
---|
| 49 |
|
---|
| 50 |
|
---|
| 51 | sub new {
|
---|
| 52 | my ($class) = shift (@_);
|
---|
| 53 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 54 | push(@$pluginlist, $class);
|
---|
| 55 |
|
---|
| 56 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 57 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
| 58 |
|
---|
| 59 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
| 60 |
|
---|
| 61 | return bless $self, $class;
|
---|
| 62 |
|
---|
| 63 | }
|
---|
| 64 |
|
---|
| 65 |
|
---|
| 66 | sub separate_cjk_text {
|
---|
| 67 |
|
---|
| 68 | my $self = shift (@_);
|
---|
| 69 | my ($doc_obj) = @_;
|
---|
| 70 |
|
---|
| 71 | if($self->{'separate_cjk'}) {
|
---|
| 72 | my $thissection = $doc_obj->get_top_section();
|
---|
| 73 | while (defined $thissection) {
|
---|
| 74 |
|
---|
[16646] | 75 | # segment the text
|
---|
[16640] | 76 | my $text = $doc_obj->get_text($thissection);
|
---|
| 77 | $text = &cnseg::segment($text);
|
---|
| 78 | $doc_obj->add_utf8_text($thissection, $text);
|
---|
[16646] | 79 |
|
---|
| 80 | # and now the metadata
|
---|
| 81 | my $metadataref = $doc_obj->get_all_metadata($thissection);
|
---|
| 82 | foreach my $data (@$metadataref) {
|
---|
| 83 | $data->[1] = &cnseg::segment($data->[1]);
|
---|
| 84 | }
|
---|
[16640] | 85 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 86 | }
|
---|
| 87 | }
|
---|
| 88 | }
|
---|
| 89 |
|
---|
| 90 | 1;
|
---|