1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # CICWordPlug.pm
|
---|
4 | #
|
---|
5 | # Copyright (C) 2006 New Zealand Digital Library Project
|
---|
6 | #
|
---|
7 | # This program is free software; you can redistribute it and/or modify
|
---|
8 | # it under the terms of the GNU General Public License as published by
|
---|
9 | # the Free Software Foundation; either version 2 of the License, or
|
---|
10 | # (at your option) any later version.
|
---|
11 | #
|
---|
12 | # This program is distributed in the hope that it will be useful,
|
---|
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
15 | # GNU General Public License for more details.
|
---|
16 | #
|
---|
17 | # You should have received a copy of the GNU General Public License
|
---|
18 | # along with this program; if not, write to the Free Software
|
---|
19 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
20 | #
|
---|
21 | ###########################################################################
|
---|
22 |
|
---|
23 | package CICWordPlug;
|
---|
24 |
|
---|
25 |
|
---|
26 | use ConvertToPlug;
|
---|
27 | use strict;
|
---|
28 | no strict 'refs';
|
---|
29 |
|
---|
30 |
|
---|
31 | sub BEGIN {
|
---|
32 | @CICWordPlug::ISA = ('ConvertToPlug');
|
---|
33 | }
|
---|
34 |
|
---|
35 |
|
---|
36 | my $arguments = [ ];
|
---|
37 |
|
---|
38 | my $options = { 'name' => "CICWordPlug",
|
---|
39 | 'desc' => "{CICWordPlug.desc}",
|
---|
40 | 'abstract' => "no",
|
---|
41 | 'inherits' => "yes",
|
---|
42 | 'args' => $arguments };
|
---|
43 |
|
---|
44 |
|
---|
45 | sub get_default_process_exp
|
---|
46 | {
|
---|
47 | return q^(?i)\.doc$^;
|
---|
48 | }
|
---|
49 |
|
---|
50 |
|
---|
51 | sub new {
|
---|
52 | my ($class) = shift (@_);
|
---|
53 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
54 | push(@$pluginlist, $class);
|
---|
55 |
|
---|
56 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
57 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
58 |
|
---|
59 | my $self = new ConvertToPlug($pluginlist, $inputargs, $hashArgOptLists);
|
---|
60 |
|
---|
61 | return bless $self, $class;
|
---|
62 | }
|
---|
63 |
|
---|
64 |
|
---|
65 | sub read
|
---|
66 | {
|
---|
67 | my $self = shift (@_);
|
---|
68 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
69 |
|
---|
70 | $self->{'file'} = $file;
|
---|
71 | $self->{'processor'} = $processor;
|
---|
72 | $self->{'gli'} = $gli;
|
---|
73 |
|
---|
74 | $self->SUPER::read($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli);
|
---|
75 | }
|
---|
76 |
|
---|
77 |
|
---|
78 | sub convert_post_process
|
---|
79 | {
|
---|
80 | my $self = shift(@_);
|
---|
81 | my $conv_filename = shift(@_);
|
---|
82 | my $fail_log_handle = $self->{'failhandle'};
|
---|
83 |
|
---|
84 | my $in_record = 0;
|
---|
85 | my $num_records = 0;
|
---|
86 | open(HTML_IN, $conv_filename);
|
---|
87 | while (my $line = <HTML_IN>) {
|
---|
88 | # Is this the end of a record?
|
---|
89 | if ($line =~ /^<\/p>/) {
|
---|
90 | $in_record = 0;
|
---|
91 | }
|
---|
92 | # Is this the start of a possible record?
|
---|
93 | if ($line =~ /^<p /) {
|
---|
94 | $in_record = 1;
|
---|
95 | }
|
---|
96 | elsif ($in_record == 1) {
|
---|
97 | # Ignore lines completely in bold
|
---|
98 | next if ($line =~ /^<b>(.*)<\/b>$/);
|
---|
99 |
|
---|
100 | my $line_sans_tags = $line;
|
---|
101 | $line_sans_tags =~ s/<.*?>//g;
|
---|
102 |
|
---|
103 | # Type 1: No author, title in double quotes
|
---|
104 | if ($line =~ /^“(.*)”/) {
|
---|
105 | $num_records++;
|
---|
106 | $self->add_reference_document($num_records, $line, $1, "");
|
---|
107 | }
|
---|
108 |
|
---|
109 | # Type 2: Author, title in italics or quotes
|
---|
110 | elsif ($line =~ /^(.*)<i>(.*)<\/i>/ || $line =~ /^(.*)"(.*)"/ || $line =~ /^(.*)“(.*)”/) {
|
---|
111 | $num_records++;
|
---|
112 | $self->add_reference_document($num_records, $line, $2, $1);
|
---|
113 | }
|
---|
114 |
|
---|
115 | # Warning: Could not parse record
|
---|
116 | elsif ($line_sans_tags =~ /\w/) {
|
---|
117 | print STDERR "<ProcessingError n='Bibliography' p='CICWordPlug' r='Could not parse reference: $line'>\n" if ($self->{'gli'});
|
---|
118 | print STDERR "Warning: Bibliography -- Could not parse reference: $line\n";
|
---|
119 | print $fail_log_handle "Warning: Bibliography -- Could not parse reference: $line\n";
|
---|
120 | $num_records++;
|
---|
121 | $self->add_reference_document($num_records, $line, "", "");
|
---|
122 | }
|
---|
123 | }
|
---|
124 | }
|
---|
125 | close(HTML_IN);
|
---|
126 | }
|
---|
127 |
|
---|
128 |
|
---|
129 | sub add_reference_document
|
---|
130 | {
|
---|
131 | my $self = shift(@_);
|
---|
132 | my $reference_id = shift(@_);
|
---|
133 | my $reference = shift(@_);
|
---|
134 | my $reference_title = shift(@_);
|
---|
135 | my $reference_author = shift(@_);
|
---|
136 |
|
---|
137 | my $reference_doc_obj = new doc($self->{'file'} . "-", "indexed_doc");
|
---|
138 | $reference_doc_obj->set_OID("r$reference_id");
|
---|
139 | &new_metadata_entry($reference_doc_obj, "DocumentType", "Reference");
|
---|
140 | &new_metadata_entry($reference_doc_obj, "Reference", $reference);
|
---|
141 | &new_metadata_entry($reference_doc_obj, "ReferenceAuthor", $reference_author);
|
---|
142 | &new_metadata_entry($reference_doc_obj, "ReferenceTitle", $reference_title);
|
---|
143 |
|
---|
144 | $reference_doc_obj->add_utf8_text($reference_doc_obj->get_top_section(), "Some dummy text.");
|
---|
145 | $self->{'processor'}->process($reference_doc_obj);
|
---|
146 | $self->{'num_processed'}++;
|
---|
147 | }
|
---|
148 |
|
---|
149 |
|
---|
150 | sub new_metadata_entry
|
---|
151 | {
|
---|
152 | my ($doc_obj, $metadata_name, $metadata_value) = (@_);
|
---|
153 |
|
---|
154 | # Don't bother with empty metadata
|
---|
155 | return if ($metadata_value eq "");
|
---|
156 |
|
---|
157 | # Spaces aren't allowed in metadata names
|
---|
158 | $metadata_name =~ s/ /_/g;
|
---|
159 |
|
---|
160 | # Anything from the database is ISO 8859-1 encoded, so convert to UTF-8
|
---|
161 | $metadata_value = &unicode::ascii2utf8(\$metadata_value);
|
---|
162 |
|
---|
163 | # Remove '#' characters around links
|
---|
164 | if ($metadata_value =~ /\#(.*?)\#/) {
|
---|
165 | $metadata_value = $1;
|
---|
166 | }
|
---|
167 |
|
---|
168 | # Remove any superscript tags
|
---|
169 | $metadata_value =~ s/\<sup\>//g;
|
---|
170 | $metadata_value =~ s/\<\/sup\>//g;
|
---|
171 |
|
---|
172 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), $metadata_name, $metadata_value);
|
---|
173 | }
|
---|
174 |
|
---|
175 |
|
---|
176 | 1;
|
---|
177 |
|
---|