| 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 | 'hiddengli' => "yes" },
|
|---|
| 59 |
|
|---|
| 60 | # The interesting options
|
|---|
| 61 | { 'name' => "entry_separator",
|
|---|
| 62 | 'desc' => "{ISISPlug.entry_separator}",
|
|---|
| 63 | 'type' => "string",
|
|---|
| 64 | 'reqd' => "no",
|
|---|
| 65 | 'deft' => "<br>" },
|
|---|
| 66 | { 'name' => "subfield_separator",
|
|---|
| 67 | 'desc' => "{ISISPlug.subfield_separator}",
|
|---|
| 68 | 'type' => "string",
|
|---|
| 69 | 'reqd' => "no",
|
|---|
| 70 | 'deft' => ", " }
|
|---|
| 71 | ];
|
|---|
| 72 |
|
|---|
| 73 | my $options = { 'name' => "ISISPlug",
|
|---|
| 74 | 'desc' => "{ISISPlug.desc}",
|
|---|
| 75 | 'abstract' => "no",
|
|---|
| 76 | 'inherits' => "yes",
|
|---|
| 77 | 'explodes' => "yes",
|
|---|
| 78 | 'args' => $arguments };
|
|---|
| 79 |
|
|---|
| 80 |
|
|---|
| 81 | # This plugin processes files with the suffix ".mst"
|
|---|
| 82 | sub get_default_process_exp {
|
|---|
| 83 | return q^(?i)(\.mst)$^;
|
|---|
| 84 | }
|
|---|
| 85 |
|
|---|
| 86 |
|
|---|
| 87 | # This plugin blocks files with the suffix ".fdt" and ".xrf"
|
|---|
| 88 | sub get_default_block_exp {
|
|---|
| 89 | return q^(?i)(\.fdt|\.xrf)$^;
|
|---|
| 90 | }
|
|---|
| 91 |
|
|---|
| 92 |
|
|---|
| 93 | # This plugin splits the input text at the "----------" lines
|
|---|
| 94 | sub get_default_split_exp {
|
|---|
| 95 | return q^\r?\n----------\r?\n^;
|
|---|
| 96 | }
|
|---|
| 97 |
|
|---|
| 98 |
|
|---|
| 99 | sub new
|
|---|
| 100 | {
|
|---|
| 101 | my ($class) = shift (@_);
|
|---|
| 102 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 103 | push(@$pluginlist, $class);
|
|---|
| 104 |
|
|---|
| 105 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
|---|
| 106 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
|---|
| 107 |
|
|---|
| 108 | my $self = (defined $hashArgOptLists)? new SplitPlug($pluginlist,$inputargs,$hashArgOptLists): new SplitPlug($pluginlist,$inputargs);
|
|---|
| 109 |
|
|---|
| 110 | return bless $self, $class;
|
|---|
| 111 | }
|
|---|
| 112 |
|
|---|
| 113 |
|
|---|
| 114 | sub read_file
|
|---|
| 115 | {
|
|---|
| 116 | my $self = shift (@_);
|
|---|
| 117 | my ($filename, $encoding, $language, $textref) = @_;
|
|---|
| 118 |
|
|---|
| 119 | my ($databasename) = ($filename =~ /(.*)\.mst$/i);
|
|---|
| 120 |
|
|---|
| 121 | # Check the associated .fdt and .xrf files exist
|
|---|
| 122 | # These files must have a lowercase extension for the IsisGdl program to work
|
|---|
| 123 | # Bailing out because of this is kind of crappy but it is only an issue on Unix
|
|---|
| 124 | my $fdtfilename = $databasename . ".fdt";
|
|---|
| 125 | if (! -e $fdtfilename) {
|
|---|
| 126 | die "Error: Could not find ISIS FDT file $fdtfilename.\n";
|
|---|
| 127 | }
|
|---|
| 128 | my $xrffilename = $databasename . ".xrf";
|
|---|
| 129 | if (! -e $xrffilename) {
|
|---|
| 130 | die "Error: Could not find ISIS XRF file $xrffilename.\n";
|
|---|
| 131 | }
|
|---|
| 132 |
|
|---|
| 133 | # The text to split is exported from the database by the IsisGdl program
|
|---|
| 134 | open(FILE, "IsisGdl \"$filename\" |");
|
|---|
| 135 |
|
|---|
| 136 | my $reader = new multiread();
|
|---|
| 137 | $reader->set_handle('ISISPlug::FILE');
|
|---|
| 138 | $reader->set_encoding($encoding);
|
|---|
| 139 | $reader->read_file($textref);
|
|---|
| 140 |
|
|---|
| 141 | close(FILE);
|
|---|
| 142 |
|
|---|
| 143 | # Parse the associated ISIS database Field Definition Table file (.fdt)
|
|---|
| 144 | my %fdtmapping = &parse_field_definition_table($fdtfilename, $encoding);
|
|---|
| 145 | $self->{'fdt_mapping'} = \%fdtmapping;
|
|---|
| 146 |
|
|---|
| 147 | # Remove the line at the start so it is split and processed properly
|
|---|
| 148 | $$textref =~ s/^----------\n//;
|
|---|
| 149 | }
|
|---|
| 150 |
|
|---|
| 151 |
|
|---|
| 152 | sub process
|
|---|
| 153 | {
|
|---|
| 154 | my $self = shift (@_);
|
|---|
| 155 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
|---|
| 156 | my $outhandle = $self->{'outhandle'};
|
|---|
| 157 |
|
|---|
| 158 | my $section = $doc_obj->get_top_section();
|
|---|
| 159 | my $fdt_mapping = $self->{'fdt_mapping'};
|
|---|
| 160 | my $subfield_separator = $self->{'subfield_separator'};
|
|---|
| 161 | my $entry_separator = $self->{'entry_separator'};
|
|---|
| 162 |
|
|---|
| 163 | # Report that we're processing the file
|
|---|
| 164 | print STDERR "<Processing n='$file' p='ISISPlug'>\n" if ($gli);
|
|---|
| 165 | print $outhandle "IsisPlug: processing $file\n" if ($self->{'verbosity'}) > 1;
|
|---|
| 166 |
|
|---|
| 167 | # Process each line of the ISIS record, one at a time
|
|---|
| 168 | foreach my $line (split(/\n/, $$textref)) {
|
|---|
| 169 | $line =~ /^tag=(.*) data=(.+)$/;
|
|---|
| 170 | my $tag = $1;
|
|---|
| 171 | my $tag_data = $2;
|
|---|
| 172 | # print STDERR "\nTag: $tag, Data: $tag_data\n";
|
|---|
| 173 |
|
|---|
| 174 | # Convert the tag number into a name, and remove any invalid characters
|
|---|
| 175 | my $raw_metadata_name = $fdt_mapping->{$tag}{'name'} || "";
|
|---|
| 176 | $raw_metadata_name =~ s/[,&\#\.\-\/]/ /g;
|
|---|
| 177 | next if ($raw_metadata_name eq "");
|
|---|
| 178 |
|
|---|
| 179 | # Metadata field names: title case, then remove spaces
|
|---|
| 180 | my $metadata_name = "";
|
|---|
| 181 | foreach my $word (split(/\s+/, $raw_metadata_name)) {
|
|---|
| 182 | substr($word, 0, 1) =~ tr/a-z/A-Z/;
|
|---|
| 183 | $metadata_name .= $word;
|
|---|
| 184 | }
|
|---|
| 185 |
|
|---|
| 186 | my $all_metadata_name = $metadata_name . "^all";
|
|---|
| 187 | my $all_metadata_value = "";
|
|---|
| 188 |
|
|---|
| 189 | # Handle repeatable fields
|
|---|
| 190 | if ($fdt_mapping->{$tag}{'repeatable'}) {
|
|---|
| 191 | # Multiple values are separated using the '%' character
|
|---|
| 192 | foreach my $raw_metadata_value (split(/%/, $tag_data)) {
|
|---|
| 193 | my $metadata_value = "";
|
|---|
| 194 |
|
|---|
| 195 | # Handle subfields
|
|---|
| 196 | while ($raw_metadata_value ne "") {
|
|---|
| 197 | # If there is a subfield specifier, parse it off
|
|---|
| 198 | my $sub_metadata_name = $metadata_name;
|
|---|
| 199 | if ($raw_metadata_value =~ s/^\^// && $raw_metadata_value =~ s/^([a-z])//) {
|
|---|
| 200 | $sub_metadata_name .= "^$1";
|
|---|
| 201 | }
|
|---|
| 202 |
|
|---|
| 203 | # Parse the value off and add it as metadata
|
|---|
| 204 | $raw_metadata_value =~ s/^([^\^]*)//;
|
|---|
| 205 | my $sub_metadata_value = $1;
|
|---|
| 206 |
|
|---|
| 207 | # Escape any '<' and '>' characters so they appear correctly in the final collection
|
|---|
| 208 | $sub_metadata_value =~ s/\</</g;
|
|---|
| 209 | $sub_metadata_value =~ s/\>/>/g;
|
|---|
| 210 |
|
|---|
| 211 | # print STDERR "Sub metadata name: $sub_metadata_name, value: $sub_metadata_value\n";
|
|---|
| 212 | if ($sub_metadata_name ne $metadata_name) {
|
|---|
| 213 | $doc_obj->add_utf8_metadata($section, $sub_metadata_name, $sub_metadata_value);
|
|---|
| 214 | }
|
|---|
| 215 |
|
|---|
| 216 | $metadata_value .= $subfield_separator unless ($metadata_value eq "");
|
|---|
| 217 | $metadata_value .= $sub_metadata_value;
|
|---|
| 218 | }
|
|---|
| 219 |
|
|---|
| 220 | # Add the metadata value
|
|---|
| 221 | # print STDERR "Metadata name: $metadata_name, value: $metadata_value\n";
|
|---|
| 222 | $doc_obj->add_utf8_metadata($section, $metadata_name, $metadata_value);
|
|---|
| 223 |
|
|---|
| 224 | $all_metadata_value .= $entry_separator unless ($all_metadata_value eq "");
|
|---|
| 225 | $all_metadata_value .= $metadata_value;
|
|---|
| 226 | }
|
|---|
| 227 | }
|
|---|
| 228 |
|
|---|
| 229 | # Handle non-repeatable fields
|
|---|
| 230 | else {
|
|---|
| 231 | my $raw_metadata_value = $tag_data;
|
|---|
| 232 | my $metadata_value = "";
|
|---|
| 233 |
|
|---|
| 234 | # Handle subfields
|
|---|
| 235 | while ($raw_metadata_value ne "") {
|
|---|
| 236 | # If there is a subfield specifier, parse it off
|
|---|
| 237 | my $sub_metadata_name = $metadata_name;
|
|---|
| 238 | if ($raw_metadata_value =~ s/^(\^[a-z])//) {
|
|---|
| 239 | $sub_metadata_name .= $1;
|
|---|
| 240 | }
|
|---|
| 241 |
|
|---|
| 242 | # Parse the value off and add it as metadata
|
|---|
| 243 | $raw_metadata_value =~ s/^([^\^]*)//;
|
|---|
| 244 | my $sub_metadata_value = $1;
|
|---|
| 245 |
|
|---|
| 246 | # Deal with the case when multiple values are specified using <...>
|
|---|
| 247 | if ($sub_metadata_value =~ /\<(.*)\>$/) {
|
|---|
| 248 | my $sub_sub_metadata_name = $sub_metadata_name . "^sub";
|
|---|
| 249 | my $tmp_sub_metadata_value = $sub_metadata_value;
|
|---|
| 250 | while ($tmp_sub_metadata_value =~ s/\<(.*?)\>//) {
|
|---|
| 251 | my $sub_sub_metadata_value = $1;
|
|---|
| 252 | $doc_obj->add_utf8_metadata($section, $sub_sub_metadata_name, $sub_sub_metadata_value);
|
|---|
| 253 | }
|
|---|
| 254 | }
|
|---|
| 255 |
|
|---|
| 256 | # Escape any '<' and '>' characters so they appear correctly in the final collection
|
|---|
| 257 | $sub_metadata_value =~ s/\</</g;
|
|---|
| 258 | $sub_metadata_value =~ s/\>/>/g;
|
|---|
| 259 |
|
|---|
| 260 | # print STDERR "Sub metadata name: $sub_metadata_name, value: $sub_metadata_value\n";
|
|---|
| 261 | if ($sub_metadata_name ne $metadata_name) {
|
|---|
| 262 | $doc_obj->add_utf8_metadata($section, $sub_metadata_name, $sub_metadata_value);
|
|---|
| 263 | }
|
|---|
| 264 |
|
|---|
| 265 | $metadata_value .= $subfield_separator unless ($metadata_value eq "");
|
|---|
| 266 | $metadata_value .= $sub_metadata_value;
|
|---|
| 267 | }
|
|---|
| 268 |
|
|---|
| 269 | # Add the metadata value
|
|---|
| 270 | # print STDERR "Metadata name: $metadata_name, value: $metadata_value\n";
|
|---|
| 271 | $doc_obj->add_utf8_metadata($section, $metadata_name, $metadata_value);
|
|---|
| 272 |
|
|---|
| 273 | $all_metadata_value .= $entry_separator unless ($all_metadata_value eq "");
|
|---|
| 274 | $all_metadata_value .= $metadata_value;
|
|---|
| 275 | }
|
|---|
| 276 |
|
|---|
| 277 | # Add the "^all" metadata value
|
|---|
| 278 | # print STDERR "All metadata name: $all_metadata_name, value: $all_metadata_value\n";
|
|---|
| 279 | $doc_obj->add_utf8_metadata($section, $all_metadata_name, $all_metadata_value);
|
|---|
| 280 | }
|
|---|
| 281 |
|
|---|
| 282 | # Add the full record as the document text
|
|---|
| 283 | $$textref =~ s/\</</g;
|
|---|
| 284 | $$textref =~ s/\>/>/g;
|
|---|
| 285 | $doc_obj->add_utf8_text($section, $$textref);
|
|---|
| 286 |
|
|---|
| 287 | # Add FileFormat metadata
|
|---|
| 288 | $doc_obj->add_utf8_metadata($section, "FileFormat", "CDS/ISIS");
|
|---|
| 289 |
|
|---|
| 290 | # Record was processed successfully
|
|---|
| 291 | return 1;
|
|---|
| 292 | }
|
|---|
| 293 |
|
|---|
| 294 |
|
|---|
| 295 | sub parse_field_definition_table
|
|---|
| 296 | {
|
|---|
| 297 | my $fdtfilename = shift(@_);
|
|---|
| 298 | my $encoding = shift(@_);
|
|---|
| 299 |
|
|---|
| 300 | my %fdtmapping = ();
|
|---|
| 301 |
|
|---|
| 302 | open(FDT_FILE, "<$fdtfilename") || die "Error: Could not open file $fdtfilename.\n";
|
|---|
| 303 |
|
|---|
| 304 | my $fdtfiletext = "";
|
|---|
| 305 | my $reader = new multiread();
|
|---|
| 306 | $reader->set_handle('ISISPlug::FDT_FILE');
|
|---|
| 307 | $reader->set_encoding($encoding);
|
|---|
| 308 | $reader->read_file($fdtfiletext);
|
|---|
| 309 |
|
|---|
| 310 | my $amongstdefinitions = 0;
|
|---|
| 311 | foreach my $fdtfileline (split(/\n/, $$fdtfiletext)) {
|
|---|
| 312 | $fdtfileline =~ s/(\s*)$//; # Remove any nasty spaces at the end of the lines
|
|---|
| 313 |
|
|---|
| 314 | if ($amongstdefinitions) {
|
|---|
| 315 | my $fieldname = substr($fdtfileline, 0, 30);
|
|---|
| 316 | my $fieldsubfields = substr($fdtfileline, 30, 20);
|
|---|
| 317 | my $fieldspecs = substr($fdtfileline, 50);
|
|---|
| 318 |
|
|---|
| 319 | # Remove extra spaces
|
|---|
| 320 | $fieldname =~ s/(\s*)$//;
|
|---|
| 321 | $fieldsubfields =~ s/(\s*)$//;
|
|---|
| 322 | $fieldspecs =~ s/(\s*)$//;
|
|---|
| 323 |
|
|---|
| 324 | # Map from tag number to metadata field title, subfields, and repeatability
|
|---|
| 325 | my $fieldtag = (split(/ /, $fieldspecs))[0];
|
|---|
| 326 | my $fieldrepeatable = (split(/ /, $fieldspecs))[3];
|
|---|
| 327 | $fdtmapping{$fieldtag} = { 'name' => $fieldname,
|
|---|
| 328 | 'subfields' => $fieldsubfields,
|
|---|
| 329 | 'repeatable' => $fieldrepeatable };
|
|---|
| 330 | }
|
|---|
| 331 | elsif ($fdtfileline eq "***") {
|
|---|
| 332 | $amongstdefinitions = 1;
|
|---|
| 333 | }
|
|---|
| 334 | }
|
|---|
| 335 |
|
|---|
| 336 | close(FDT_FILE);
|
|---|
| 337 |
|
|---|
| 338 | return %fdtmapping;
|
|---|
| 339 | }
|
|---|
| 340 |
|
|---|
| 341 |
|
|---|
| 342 | 1;
|
|---|
