1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # ISISPlug.pm -- A plugin for CDS/ISIS 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 ISISPlug;
|
---|
28 |
|
---|
29 |
|
---|
30 | use multiread;
|
---|
31 | use SplitPlug;
|
---|
32 |
|
---|
33 | use strict;
|
---|
34 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
35 |
|
---|
36 | # ISISPlug is a sub-class of SplitPlug.
|
---|
37 | sub BEGIN {
|
---|
38 | @ISISPlug::ISA = ('SplitPlug');
|
---|
39 | }
|
---|
40 |
|
---|
41 |
|
---|
42 | my $arguments =
|
---|
43 | [ { 'name' => "process_exp",
|
---|
44 | 'desc' => "{BasPlug.process_exp}",
|
---|
45 | 'type' => "regexp",
|
---|
46 | 'reqd' => "no",
|
---|
47 | 'deft' => &get_default_process_exp() },
|
---|
48 | { 'name' => "block_exp",
|
---|
49 | 'desc' => "{BasPlug.block_exp}",
|
---|
50 | 'type' => "regexp",
|
---|
51 | 'reqd' => "no",
|
---|
52 | 'deft' => &get_default_block_exp() },
|
---|
53 | { 'name' => "split_exp",
|
---|
54 | 'desc' => "{SplitPlug.split_exp}",
|
---|
55 | 'type' => "regexp",
|
---|
56 | 'reqd' => "no",
|
---|
57 | 'deft' => &get_default_split_exp() },
|
---|
58 |
|
---|
59 | # The interesting options
|
---|
60 | { 'name' => "entry_separator",
|
---|
61 | 'desc' => "{ISISPlug.entry_separator}",
|
---|
62 | 'type' => "string",
|
---|
63 | 'reqd' => "no",
|
---|
64 | 'deft' => "<br>" },
|
---|
65 | { 'name' => "subfield_separator",
|
---|
66 | 'desc' => "{ISISPlug.subfield_separator}",
|
---|
67 | 'type' => "string",
|
---|
68 | 'reqd' => "no",
|
---|
69 | 'deft' => ", " }
|
---|
70 | ];
|
---|
71 |
|
---|
72 | my $options = { 'name' => "ISISPlug",
|
---|
73 | 'desc' => "{ISISPlug.desc}",
|
---|
74 | 'abstract' => "no",
|
---|
75 | 'inherits' => "yes",
|
---|
76 | 'explodes' => "yes",
|
---|
77 | 'args' => $arguments };
|
---|
78 |
|
---|
79 |
|
---|
80 | # This plugin processes files with the suffix ".mst"
|
---|
81 | sub get_default_process_exp {
|
---|
82 | return q^(?i)(\.mst)$^;
|
---|
83 | }
|
---|
84 |
|
---|
85 |
|
---|
86 | # This plugin blocks files with the suffix ".fdt" and ".xrf"
|
---|
87 | sub get_default_block_exp {
|
---|
88 | return q^(?i)(\.fdt|\.xrf)$^;
|
---|
89 | }
|
---|
90 |
|
---|
91 |
|
---|
92 | # This plugin splits the input text at the "----------" lines
|
---|
93 | sub get_default_split_exp {
|
---|
94 | return q^\r?\n----------\r?\n^;
|
---|
95 | }
|
---|
96 |
|
---|
97 |
|
---|
98 | sub new
|
---|
99 | {
|
---|
100 | my ($class) = shift (@_);
|
---|
101 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
102 | push(@$pluginlist, $class);
|
---|
103 |
|
---|
104 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
105 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
106 |
|
---|
107 | my $self = (defined $hashArgOptLists)? new SplitPlug($pluginlist,$inputargs,$hashArgOptLists): new SplitPlug($pluginlist,$inputargs);
|
---|
108 |
|
---|
109 | return bless $self, $class;
|
---|
110 | }
|
---|
111 |
|
---|
112 |
|
---|
113 | sub read_file
|
---|
114 | {
|
---|
115 | my $self = shift (@_);
|
---|
116 | my ($filename, $encoding, $language, $textref) = @_;
|
---|
117 |
|
---|
118 | my ($databasename) = ($filename =~ /(.*)\.mst$/i);
|
---|
119 |
|
---|
120 | # Check the associated .fdt and .xrf files exist
|
---|
121 | # These files must have a lowercase extension for the IsisGdl program to work
|
---|
122 | # Bailing out because of this is kind of crappy but it is only an issue on Unix
|
---|
123 | my $fdtfilename = $databasename . ".fdt";
|
---|
124 | if (! -e $fdtfilename) {
|
---|
125 | die "Error: Could not find ISIS FDT file $fdtfilename.\n";
|
---|
126 | }
|
---|
127 | my $xrffilename = $databasename . ".xrf";
|
---|
128 | if (! -e $xrffilename) {
|
---|
129 | die "Error: Could not find ISIS XRF file $xrffilename.\n";
|
---|
130 | }
|
---|
131 |
|
---|
132 | # The text to split is exported from the database by the IsisGdl program
|
---|
133 | open(FILE, "IsisGdl \"$filename\" |");
|
---|
134 |
|
---|
135 | my $reader = new multiread();
|
---|
136 | $reader->set_handle('ISISPlug::FILE');
|
---|
137 | $reader->set_encoding($encoding);
|
---|
138 | $reader->read_file($textref);
|
---|
139 |
|
---|
140 | close(FILE);
|
---|
141 |
|
---|
142 | # Parse the associated ISIS database Field Definition Table file (.fdt)
|
---|
143 | my %fdtmapping = &parse_field_definition_table($fdtfilename);
|
---|
144 |
|
---|
145 | # Map the tag numbers to tag names, using the FDT mapping
|
---|
146 | $$textref =~ s/\r?\ntag=(\d+) /\ntag=$fdtmapping{$1}{'title'} /g;
|
---|
147 |
|
---|
148 | # Remove the line at the start so it is split and processed properly
|
---|
149 | $$textref =~ s/^----------\n//;
|
---|
150 | }
|
---|
151 |
|
---|
152 |
|
---|
153 | sub process
|
---|
154 | {
|
---|
155 | my $self = shift (@_);
|
---|
156 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
157 | my $outhandle = $self->{'outhandle'};
|
---|
158 |
|
---|
159 | my $cursection = $doc_obj->get_top_section();
|
---|
160 | my $subfield_separator = $self->{'subfield_separator'};
|
---|
161 | my $entry_separator = $self->{'entry_separator'};
|
---|
162 |
|
---|
163 | # Report that we're processing the file
|
---|
164 | print STDERR "<Processing n='$file' p='ISISPlug'>\n" if ($gli);
|
---|
165 | print $outhandle "IsisPlug: processing $file\n"
|
---|
166 | if ($self->{'verbosity'}) > 1;
|
---|
167 |
|
---|
168 | # Process each line of the ISIS record, one at a time
|
---|
169 | foreach my $line (split(/\n/, $$textref)) {
|
---|
170 | $line =~ /^tag=(.*) data=(.+)$/;
|
---|
171 | my $rawtagname = $1;
|
---|
172 | my $rawtagdata = $2;
|
---|
173 | # print STDERR "Raw tag: $rawtagname, Raw data: $rawtagdata\n";
|
---|
174 | next if ($rawtagname eq "");
|
---|
175 |
|
---|
176 | # Metadata field names: title case, then remove spaces
|
---|
177 | my $tagname = "";
|
---|
178 | foreach my $word (split(/\s+/, $rawtagname)) {
|
---|
179 | substr($word, 0, 1) =~ tr/a-z/A-Z/;
|
---|
180 | $tagname .= $word;
|
---|
181 | }
|
---|
182 |
|
---|
183 | # Make sure there is nothing bad in the tag names
|
---|
184 | $tagname =~ s/&//g;
|
---|
185 |
|
---|
186 | # Handle each piece of metadata ('%' separated)
|
---|
187 | my $completetagvalue = "";
|
---|
188 | foreach my $rawtagvalue (split(/%/, $rawtagdata)) {
|
---|
189 | $completetagvalue .= $entry_separator unless ($completetagvalue eq "");
|
---|
190 |
|
---|
191 | # Metadata field values: take care with subfields
|
---|
192 | my $completeentryvalue = "";
|
---|
193 | while ($rawtagvalue ne "") {
|
---|
194 | # If there is a subfield specifier, parse it off
|
---|
195 | my $subfieldname = "";
|
---|
196 | if ($rawtagvalue =~ s/^\^// && $rawtagvalue =~ s/([a-z])//) {
|
---|
197 | $subfieldname = "^$1";
|
---|
198 | }
|
---|
199 |
|
---|
200 | # Parse the metadata value off
|
---|
201 | $rawtagvalue =~ s/^([^\^]*)//;
|
---|
202 | my $metadatafieldname = $tagname . $subfieldname;
|
---|
203 | my $metadatafieldvalue = $1;
|
---|
204 |
|
---|
205 | # Handle Keywords specially
|
---|
206 | if ($metadatafieldname eq "Keywords") {
|
---|
207 | my $keywordmetadatavalue = $metadatafieldvalue;
|
---|
208 | my $keywordlist = "";
|
---|
209 | while ($keywordmetadatavalue =~ s/\<(.+?)\>//) {
|
---|
210 | my $keyword = $1;
|
---|
211 | $doc_obj->add_utf8_metadata($cursection, $metadatafieldname, $keyword);
|
---|
212 | $keywordlist .= ", " unless ($keywordlist eq "");
|
---|
213 | $keywordlist .= $keyword;
|
---|
214 | }
|
---|
215 |
|
---|
216 | $metadatafieldvalue = $keywordlist;
|
---|
217 | }
|
---|
218 |
|
---|
219 | # Escape any '<' and '>' characters so they appear correctly in the final collection
|
---|
220 | $metadatafieldvalue =~ s/\</</g;
|
---|
221 | $metadatafieldvalue =~ s/\>/>/g;
|
---|
222 |
|
---|
223 | # We have already added Keywords metadata above
|
---|
224 | unless ($metadatafieldname eq "Keywords") {
|
---|
225 | $doc_obj->add_utf8_metadata($cursection, $metadatafieldname, $metadatafieldvalue);
|
---|
226 | }
|
---|
227 |
|
---|
228 | $completeentryvalue .= $subfield_separator unless ($completeentryvalue eq "");
|
---|
229 | $completeentryvalue .= $metadatafieldvalue;
|
---|
230 | }
|
---|
231 |
|
---|
232 | $completetagvalue .= $completeentryvalue;
|
---|
233 | }
|
---|
234 |
|
---|
235 | $doc_obj->add_utf8_metadata($cursection, $tagname . "^all", $completetagvalue);
|
---|
236 | }
|
---|
237 |
|
---|
238 | # Add the full record as the document text
|
---|
239 | $$textref =~ s/\</</g;
|
---|
240 | $$textref =~ s/\>/>/g;
|
---|
241 | $doc_obj->add_utf8_text($cursection, $$textref);
|
---|
242 |
|
---|
243 | # Add FileFormat metadata
|
---|
244 | $doc_obj->add_utf8_metadata($cursection, "FileFormat", "CDS/ISIS");
|
---|
245 |
|
---|
246 | # Record was processed successfully (and there was no document obtained)
|
---|
247 | return 1;
|
---|
248 | }
|
---|
249 |
|
---|
250 |
|
---|
251 | sub parse_field_definition_table
|
---|
252 | {
|
---|
253 | my $fdtfilename = shift(@_);
|
---|
254 |
|
---|
255 | my %fdtmapping = ();
|
---|
256 |
|
---|
257 | open(FDT_FILE, "<$fdtfilename") || die "Error: Could not open file $fdtfilename.\n";
|
---|
258 |
|
---|
259 | my $amongstdefinitions = 0;
|
---|
260 | foreach my $fdtfileline (<FDT_FILE>) {
|
---|
261 | $fdtfileline =~ s/(\s*)$//; # Remove any nasty spaces at the end of the lines
|
---|
262 |
|
---|
263 | if ($amongstdefinitions) {
|
---|
264 | my $fieldtitle = substr($fdtfileline, 0, 30);
|
---|
265 | my $fieldsubfields = substr($fdtfileline, 30, 20);
|
---|
266 | my $fieldspecs = substr($fdtfileline, 50);
|
---|
267 |
|
---|
268 | # Remove extra spaces
|
---|
269 | $fieldtitle =~ s/(\s*)$//;
|
---|
270 | $fieldsubfields =~ s/(\s*)$//;
|
---|
271 |
|
---|
272 | # Map from tag number to metadata field title and subfields
|
---|
273 | my $fieldtag = (split(/ /, $fieldspecs))[0];
|
---|
274 | $fdtmapping{$fieldtag} = { 'title' => $fieldtitle,
|
---|
275 | 'subfields' => $fieldsubfields };
|
---|
276 | }
|
---|
277 | elsif ($fdtfileline eq "***") {
|
---|
278 | $amongstdefinitions = 1;
|
---|
279 | }
|
---|
280 | }
|
---|
281 |
|
---|
282 | close(FDT_FILE);
|
---|
283 |
|
---|
284 | return %fdtmapping;
|
---|
285 | }
|
---|
286 |
|
---|
287 |
|
---|
288 | 1;
|
---|