1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # ProCitePlugin.pm -- A plugin for (exported) ProCite databases
|
---|
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 1999-2004 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 ProCitePlugin;
|
---|
28 |
|
---|
29 |
|
---|
30 | use multiread;
|
---|
31 | use SplitTextFile;
|
---|
32 | use MetadataRead;
|
---|
33 |
|
---|
34 | use strict;
|
---|
35 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
36 |
|
---|
37 | # ProCitePlugin is a sub-class of SplitTextFile
|
---|
38 | sub BEGIN {
|
---|
39 | @ProCitePlugin::ISA = ('MetadataRead', 'SplitTextFile');
|
---|
40 | }
|
---|
41 |
|
---|
42 |
|
---|
43 | my $arguments =
|
---|
44 | [ { 'name' => "process_exp",
|
---|
45 | 'desc' => "{BaseImporter.process_exp}",
|
---|
46 | 'type' => "regexp",
|
---|
47 | 'reqd' => "no",
|
---|
48 | 'deft' => &get_default_process_exp() },
|
---|
49 | { 'name' => "split_exp",
|
---|
50 | 'desc' => "{SplitTextFile.split_exp}",
|
---|
51 | 'type' => "regexp",
|
---|
52 | 'deft' => &get_default_split_exp(),
|
---|
53 | 'reqd' => "no" },
|
---|
54 |
|
---|
55 | # The interesting options
|
---|
56 | { 'name' => "entry_separator",
|
---|
57 | 'desc' => "{ProCitePlugin.entry_separator}",
|
---|
58 | 'type' => "string",
|
---|
59 | 'reqd' => "no",
|
---|
60 | 'deft' => "//" },
|
---|
61 | ];
|
---|
62 |
|
---|
63 | my $options = { 'name' => "ProCitePlugin",
|
---|
64 | 'desc' => "{ProCitePlugin.desc}",
|
---|
65 | 'abstract' => "no",
|
---|
66 | 'inherits' => "yes",
|
---|
67 | 'explodes' => "yes",
|
---|
68 | 'args' => $arguments };
|
---|
69 |
|
---|
70 |
|
---|
71 | # This plugin processes exported ProCite files with the suffix ".txt"
|
---|
72 | sub get_default_process_exp
|
---|
73 | {
|
---|
74 | return q^(?i)(\.txt)$^;
|
---|
75 | }
|
---|
76 |
|
---|
77 |
|
---|
78 | # This plugin splits the input text at every line
|
---|
79 | sub get_default_split_exp
|
---|
80 | {
|
---|
81 | return q^\n^;
|
---|
82 | }
|
---|
83 |
|
---|
84 |
|
---|
85 | sub new
|
---|
86 | {
|
---|
87 | my ($class) = shift (@_);
|
---|
88 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
89 | push(@$pluginlist, $class);
|
---|
90 |
|
---|
91 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
92 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
93 |
|
---|
94 | my $self = new SplitTextFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
95 |
|
---|
96 | return bless $self, $class;
|
---|
97 | }
|
---|
98 |
|
---|
99 |
|
---|
100 | my %crazy_workform_mapping =
|
---|
101 | ( "A", "Book, Long Form",
|
---|
102 | "B", "Book, Short Form",
|
---|
103 | "C", "Journal, Long Form",
|
---|
104 | "D", "Journal, Short Form",
|
---|
105 | "E", "Report",
|
---|
106 | "F", "Newspaper",
|
---|
107 | "G", "Dissertation",
|
---|
108 | "H", "Trade Catalog",
|
---|
109 | "I", "Letter (Correspondence)",
|
---|
110 | "J", "Manuscript",
|
---|
111 | "K", "Conference Proceedings",
|
---|
112 | "L", "Map",
|
---|
113 | "M", "Music Score",
|
---|
114 | "N", "Sound Recording",
|
---|
115 | "O", "Motion Picture",
|
---|
116 | "P", "Audiovisual Material",
|
---|
117 | "Q", "Video Recording",
|
---|
118 | "R", "Art Work",
|
---|
119 | "S", "Computer Program",
|
---|
120 | "T", "Data File" );
|
---|
121 |
|
---|
122 |
|
---|
123 | sub read_file
|
---|
124 | {
|
---|
125 | my $self = shift (@_);
|
---|
126 | my ($filename, $encoding, $language, $textref) = @_;
|
---|
127 |
|
---|
128 | # Store the workform definitions for this file
|
---|
129 | my %workform_definitions = ();
|
---|
130 |
|
---|
131 | # Read the contents of the file into $textref
|
---|
132 | open(PROCITE_FILE, "<$filename");
|
---|
133 | my $reader = new multiread();
|
---|
134 | $reader->set_handle ('ProCitePlugin::PROCITE_FILE');
|
---|
135 | $reader->set_encoding ($encoding);
|
---|
136 | $reader->read_file ($textref);
|
---|
137 | close(PROCITE_FILE);
|
---|
138 |
|
---|
139 | # Read the workform definitions at the start of the file
|
---|
140 | while ($$textref =~ /^\<Workform Definition\>/) {
|
---|
141 | # Remove the workform definition line so it is not processed later as a record
|
---|
142 | $$textref =~ s/^\<Workform Definition\>(.*)\n//;
|
---|
143 | my $workform_definition = $1;
|
---|
144 | # Parse the workform definitions and store them for later
|
---|
145 | $workform_definition =~ s/^\"([^\"]*)\",//;
|
---|
146 | my $workform_name = $1;
|
---|
147 | my @workform_values;
|
---|
148 | while ($workform_definition !~ /^\s*$/) {
|
---|
149 | $workform_definition =~ s/^\"([^\"]*)\",?//;
|
---|
150 | my $workform_field = $1;
|
---|
151 | push(@workform_values, $workform_field);
|
---|
152 | }
|
---|
153 |
|
---|
154 | # Remember this workform definition for when we're reading the records
|
---|
155 | $workform_definitions{$workform_name} = \@workform_values;
|
---|
156 | }
|
---|
157 |
|
---|
158 | $self->{'workform_definitions'}->{$filename} = \%workform_definitions;
|
---|
159 | }
|
---|
160 |
|
---|
161 |
|
---|
162 | sub process
|
---|
163 | {
|
---|
164 | my $self = shift (@_);
|
---|
165 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
166 |
|
---|
167 | my $outhandle = $self->{'outhandle'};
|
---|
168 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
169 | my $cursection = $doc_obj->get_top_section();
|
---|
170 |
|
---|
171 | # Build up an HTML view of the record for easy display at run-time
|
---|
172 | my $html_record = "<table>";
|
---|
173 |
|
---|
174 | # Read the record's workform indicator and record number
|
---|
175 | #$$textref =~ s/^\"([^\"]*)\",\"([^\"]*)\",//;
|
---|
176 | $$textref =~ s/^\"([^\"]*)\",//;
|
---|
177 | my $workform_indicator = $1;
|
---|
178 |
|
---|
179 | # some procite files have a record number next
|
---|
180 |
|
---|
181 | my $recordnum = $$textref =~ s/^\"(\d*)\",//;
|
---|
182 | $recordnum = "undefined" unless defined $recordnum;
|
---|
183 |
|
---|
184 | # If necessary, map the workform indicator into something useful
|
---|
185 | if ($crazy_workform_mapping{$workform_indicator}) {
|
---|
186 | $workform_indicator = $crazy_workform_mapping{$workform_indicator};
|
---|
187 | }
|
---|
188 |
|
---|
189 | # Check we know about the workform of this record
|
---|
190 | my %workform_definitions = %{$self->{'workform_definitions'}->{$filename}};
|
---|
191 | if (!$workform_definitions{$workform_indicator}) {
|
---|
192 | print STDERR "Unknown workform $workform_indicator!\n";
|
---|
193 | return 0;
|
---|
194 | }
|
---|
195 |
|
---|
196 | # Store the full record as the document text
|
---|
197 | $doc_obj->add_utf8_text($cursection, $$textref);
|
---|
198 |
|
---|
199 | # Store workform and record number as metadata
|
---|
200 | $doc_obj->add_utf8_metadata($cursection, "Workform", $workform_indicator);
|
---|
201 | $doc_obj->add_utf8_metadata($cursection, "RecordNumber", $recordnum);
|
---|
202 |
|
---|
203 | # Store FileFormat metadata
|
---|
204 | $doc_obj->add_metadata($cursection, "FileFormat", "ProCite");
|
---|
205 |
|
---|
206 | $html_record .= "<tr><td valign=top><b>Record Number: </b></td><td valign=top>$recordnum</td></tr>";
|
---|
207 |
|
---|
208 | my @workform_values = @{$workform_definitions{$workform_indicator}};
|
---|
209 |
|
---|
210 | # Read each field (surrounded by quotes) of the record
|
---|
211 | my $fieldnum = 0;
|
---|
212 | while ($$textref !~ /^\s*$/) {
|
---|
213 | $$textref =~ s/^\"([^\"]*)\",?//;
|
---|
214 | my $field_value_raw = $1;
|
---|
215 |
|
---|
216 | # Add non-empty metadata values to the document
|
---|
217 | unless ($field_value_raw eq "") {
|
---|
218 | # Add the display name of the metadata field for format statement convenience
|
---|
219 | my $field_name = $workform_values[$fieldnum];
|
---|
220 | #unless ($field_name eq "---") {
|
---|
221 | # my $meta_name = "Field" . ($fieldnum + 1) . "Name";
|
---|
222 | # $doc_obj->add_utf8_metadata($cursection, $meta_name, $field_name);
|
---|
223 | # }
|
---|
224 | if ($field_name eq "---") {
|
---|
225 | $field_name = "Field" . ($fieldnum + 1);
|
---|
226 | }
|
---|
227 | $html_record .= "<tr><td valign=top><b>$field_name: </b></td><td valign=top>";
|
---|
228 |
|
---|
229 | # Multiple metadata values are separated with "//"
|
---|
230 | #foreach my $field_value (split(/\/\//, $field_value_raw)) {
|
---|
231 | foreach my $field_value (split($self->{'entry_separator'}, $field_value_raw)) {
|
---|
232 | #my $meta_name = "Field" . ($fieldnum + 1) . "Value";
|
---|
233 | #$doc_obj->add_utf8_metadata($cursection, $meta_name, $field_value);
|
---|
234 | $doc_obj->add_utf8_metadata($cursection, $field_name, $field_value);
|
---|
235 | $html_record .= $field_value . "<br>";
|
---|
236 | }
|
---|
237 |
|
---|
238 | $html_record .= "</td></tr>";
|
---|
239 | }
|
---|
240 |
|
---|
241 | $fieldnum++;
|
---|
242 | }
|
---|
243 |
|
---|
244 | $html_record .= "</table>";
|
---|
245 | # Store HTML view of record as metadata
|
---|
246 | $doc_obj->add_utf8_metadata($cursection, "HTMLDisplay", $html_record);
|
---|
247 |
|
---|
248 | # Record was processed successfully
|
---|
249 | return 1;
|
---|
250 | }
|
---|
251 |
|
---|
252 |
|
---|
253 | 1;
|
---|