| 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 | 'hiddengli' => "yes" },
|
|---|
| 54 | { 'name' => "split_exp",
|
|---|
| 55 | 'desc' => "{SplitPlug.split_exp}",
|
|---|
| 56 | 'type' => "regexp",
|
|---|
| 57 | 'reqd' => "no",
|
|---|
| 58 | 'deft' => &get_default_split_exp(),
|
|---|
| 59 | 'hiddengli' => "yes" },
|
|---|
| 60 |
|
|---|
| 61 | # The interesting options
|
|---|
| 62 | { 'name' => "entry_separator",
|
|---|
| 63 | 'desc' => "{ISISPlug.entry_separator}",
|
|---|
| 64 | 'type' => "string",
|
|---|
| 65 | 'reqd' => "no",
|
|---|
| 66 | 'deft' => "<br>" },
|
|---|
| 67 | { 'name' => "subfield_separator",
|
|---|
| 68 | 'desc' => "{ISISPlug.subfield_separator}",
|
|---|
| 69 | 'type' => "string",
|
|---|
| 70 | 'reqd' => "no",
|
|---|
| 71 | 'deft' => ", " }
|
|---|
| 72 | ];
|
|---|
| 73 |
|
|---|
| 74 | my $options = { 'name' => "ISISPlug",
|
|---|
| 75 | 'desc' => "{ISISPlug.desc}",
|
|---|
| 76 | 'abstract' => "no",
|
|---|
| 77 | 'inherits' => "yes",
|
|---|
| 78 | 'explodes' => "yes",
|
|---|
| 79 | 'args' => $arguments };
|
|---|
| 80 |
|
|---|
| 81 |
|
|---|
| 82 | # This plugin processes files with the suffix ".mst"
|
|---|
| 83 | sub get_default_process_exp {
|
|---|
| 84 | return q^(?i)(\.mst)$^;
|
|---|
| 85 | }
|
|---|
| 86 |
|
|---|
| 87 |
|
|---|
| 88 | # This plugin blocks files with the suffix ".fdt" and ".xrf"
|
|---|
| 89 | sub get_default_block_exp {
|
|---|
| 90 | return q^(?i)(\.fdt|\.xrf)$^;
|
|---|
| 91 | }
|
|---|
| 92 |
|
|---|
| 93 |
|
|---|
| 94 | # This plugin splits the input text at the "----------" lines
|
|---|
| 95 | sub get_default_split_exp {
|
|---|
| 96 | return q^\r?\n----------\r?\n^;
|
|---|
| 97 | }
|
|---|
| 98 |
|
|---|
| 99 |
|
|---|
| 100 | sub new
|
|---|
| 101 | {
|
|---|
| 102 | my ($class) = shift (@_);
|
|---|
| 103 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 104 | push(@$pluginlist, $class);
|
|---|
| 105 |
|
|---|
| 106 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
|---|
| 107 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
|---|
| 108 |
|
|---|
| 109 | my $self = (defined $hashArgOptLists)? new SplitPlug($pluginlist,$inputargs,$hashArgOptLists): new SplitPlug($pluginlist,$inputargs);
|
|---|
| 110 |
|
|---|
| 111 | return bless $self, $class;
|
|---|
| 112 | }
|
|---|
| 113 |
|
|---|
| 114 |
|
|---|
| 115 | sub read_file
|
|---|
| 116 | {
|
|---|
| 117 | my $self = shift (@_);
|
|---|
| 118 | my ($filename, $encoding, $language, $textref) = @_;
|
|---|
| 119 |
|
|---|
| 120 | my ($databasename) = ($filename =~ /(.*)\.mst$/i);
|
|---|
| 121 |
|
|---|
| 122 | # Check the associated .fdt and .xrf files exist
|
|---|
| 123 | # These files must have a lowercase extension for the IsisGdl program to work
|
|---|
| 124 | # Bailing out because of this is kind of crappy but it is only an issue on Unix
|
|---|
| 125 | $self->{'fdt_filename'} = $databasename . ".fdt";
|
|---|
| 126 | if (!-e $self->{'fdt_filename'}) {
|
|---|
| 127 | die "Error: Could not find ISIS FDT file " . $self->{'fdt_filename'} . ".\n";
|
|---|
| 128 | }
|
|---|
| 129 | $self->{'xrf_filename'} = $databasename . ".xrf";
|
|---|
| 130 | if (!-e $self->{'xrf_filename'}) {
|
|---|
| 131 | die "Error: Could not find ISIS XRF file " . $self->{'xrf_filename'} . ".\n";
|
|---|
| 132 | }
|
|---|
| 133 |
|
|---|
| 134 | # The text to split is exported from the database by the IsisGdl program
|
|---|
| 135 | open(FILE, "IsisGdl \"$filename\" |");
|
|---|
| 136 |
|
|---|
| 137 | my $reader = new multiread();
|
|---|
| 138 | $reader->set_handle('ISISPlug::FILE');
|
|---|
| 139 | $reader->set_encoding($encoding);
|
|---|
| 140 | $reader->read_file($textref);
|
|---|
| 141 |
|
|---|
| 142 | close(FILE);
|
|---|
| 143 |
|
|---|
| 144 | # Parse the associated ISIS database Field Definition Table file (.fdt)
|
|---|
| 145 | my %fdt_mapping = &parse_field_definition_table($self->{'fdt_filename'}, $encoding);
|
|---|
| 146 | $self->{'fdt_mapping'} = \%fdt_mapping;
|
|---|
| 147 |
|
|---|
| 148 | # Remove the line at the start so it is split and processed properly
|
|---|
| 149 | $$textref =~ s/^----------\n//;
|
|---|
| 150 | }
|
|---|
| 151 |
|
|---|
| 152 |
|
|---|
| 153 | sub process
|
|---|
| 154 | {
|
|---|
| 155 | my $self = shift (@_);
|
|---|
| 156 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
|---|
| 157 | my $outhandle = $self->{'outhandle'};
|
|---|
| 158 |
|
|---|
| 159 | my $section = $doc_obj->get_top_section();
|
|---|
| 160 | my $fdt_mapping = $self->{'fdt_mapping'};
|
|---|
| 161 | my $subfield_separator = $self->{'subfield_separator'};
|
|---|
| 162 | my $entry_separator = $self->{'entry_separator'};
|
|---|
| 163 |
|
|---|
| 164 | # Report that we're processing the file
|
|---|
| 165 | print STDERR "<Processing n='$file' p='ISISPlug'>\n" if ($gli);
|
|---|
| 166 | print $outhandle "IsisPlug: processing $file\n" if ($self->{'verbosity'}) > 1;
|
|---|
| 167 |
|
|---|
| 168 | # Process each line of the ISIS record, one at a time
|
|---|
| 169 | foreach my $line (split(/\n/, $$textref)) {
|
|---|
| 170 | $line =~ /^tag=(.*) data=(.+)$/;
|
|---|
| 171 | my $tag = $1;
|
|---|
| 172 | my $tag_data = $2;
|
|---|
| 173 | # print STDERR "\nTag: $tag, Data: $tag_data\n";
|
|---|
| 174 |
|
|---|
| 175 | # Convert the tag number into a name, and remove any invalid characters
|
|---|
| 176 | my $raw_metadata_name = $fdt_mapping->{$tag}{'name'} || "";
|
|---|
| 177 | $raw_metadata_name =~ s/[,&\#\.\-\/]/ /g;
|
|---|
| 178 | next if ($raw_metadata_name eq "");
|
|---|
| 179 |
|
|---|
| 180 | # Metadata field names: title case, then remove spaces
|
|---|
| 181 | my $metadata_name = "";
|
|---|
| 182 | foreach my $word (split(/\s+/, $raw_metadata_name)) {
|
|---|
| 183 | substr($word, 0, 1) =~ tr/a-z/A-Z/;
|
|---|
| 184 | $metadata_name .= $word;
|
|---|
| 185 | }
|
|---|
| 186 |
|
|---|
| 187 | my $all_metadata_name = $metadata_name . "^all";
|
|---|
| 188 | my $all_metadata_value = "";
|
|---|
| 189 |
|
|---|
| 190 | # Handle repeatable fields
|
|---|
| 191 | if ($fdt_mapping->{$tag}{'repeatable'}) {
|
|---|
| 192 | # Multiple values are separated using the '%' character
|
|---|
| 193 | foreach my $raw_metadata_value (split(/%/, $tag_data)) {
|
|---|
| 194 | my $metadata_value = "";
|
|---|
| 195 |
|
|---|
| 196 | # Handle subfields
|
|---|
| 197 | while ($raw_metadata_value ne "") {
|
|---|
| 198 | # If there is a subfield specifier, parse it off
|
|---|
| 199 | my $sub_metadata_name = $metadata_name;
|
|---|
| 200 | if ($raw_metadata_value =~ s/^\^// && $raw_metadata_value =~ s/^([a-z])//) {
|
|---|
| 201 | $sub_metadata_name .= "^$1";
|
|---|
| 202 | }
|
|---|
| 203 |
|
|---|
| 204 | # Parse the value off and add it as metadata
|
|---|
| 205 | $raw_metadata_value =~ s/^([^\^]*)//;
|
|---|
| 206 | my $sub_metadata_value = $1;
|
|---|
| 207 |
|
|---|
| 208 | # Escape any '<' and '>' characters so they appear correctly in the final collection
|
|---|
| 209 | $sub_metadata_value =~ s/\</</g;
|
|---|
| 210 | $sub_metadata_value =~ s/\>/>/g;
|
|---|
| 211 |
|
|---|
| 212 | # print STDERR "Sub metadata name: $sub_metadata_name, value: $sub_metadata_value\n";
|
|---|
| 213 | if ($sub_metadata_name ne $metadata_name) {
|
|---|
| 214 | $doc_obj->add_utf8_metadata($section, $sub_metadata_name, $sub_metadata_value);
|
|---|
| 215 | }
|
|---|
| 216 |
|
|---|
| 217 | $metadata_value .= $subfield_separator unless ($metadata_value eq "");
|
|---|
| 218 | $metadata_value .= $sub_metadata_value;
|
|---|
| 219 | }
|
|---|
| 220 |
|
|---|
| 221 | # Add the metadata value
|
|---|
| 222 | # print STDERR "Metadata name: $metadata_name, value: $metadata_value\n";
|
|---|
| 223 | $doc_obj->add_utf8_metadata($section, $metadata_name, $metadata_value);
|
|---|
| 224 |
|
|---|
| 225 | $all_metadata_value .= $entry_separator unless ($all_metadata_value eq "");
|
|---|
| 226 | $all_metadata_value .= $metadata_value;
|
|---|
| 227 | }
|
|---|
| 228 | }
|
|---|
| 229 |
|
|---|
| 230 | # Handle non-repeatable fields
|
|---|
| 231 | else {
|
|---|
| 232 | my $raw_metadata_value = $tag_data;
|
|---|
| 233 | my $metadata_value = "";
|
|---|
| 234 |
|
|---|
| 235 | # Handle subfields
|
|---|
| 236 | while ($raw_metadata_value ne "") {
|
|---|
| 237 | # If there is a subfield specifier, parse it off
|
|---|
| 238 | my $sub_metadata_name = $metadata_name;
|
|---|
| 239 | if ($raw_metadata_value =~ s/^(\^[a-z])//) {
|
|---|
| 240 | $sub_metadata_name .= $1;
|
|---|
| 241 | }
|
|---|
| 242 |
|
|---|
| 243 | # Parse the value off and add it as metadata
|
|---|
| 244 | $raw_metadata_value =~ s/^([^\^]*)//;
|
|---|
| 245 | my $sub_metadata_value = $1;
|
|---|
| 246 |
|
|---|
| 247 | # Deal with the case when multiple values are specified using <...>
|
|---|
| 248 | if ($sub_metadata_value =~ /\<(.*)\>$/) {
|
|---|
| 249 | my $sub_sub_metadata_name = $sub_metadata_name . "^sub";
|
|---|
| 250 | my $tmp_sub_metadata_value = $sub_metadata_value;
|
|---|
| 251 | while ($tmp_sub_metadata_value =~ s/\<(.*?)\>//) {
|
|---|
| 252 | my $sub_sub_metadata_value = $1;
|
|---|
| 253 | $doc_obj->add_utf8_metadata($section, $sub_sub_metadata_name, $sub_sub_metadata_value);
|
|---|
| 254 | }
|
|---|
| 255 | }
|
|---|
| 256 |
|
|---|
| 257 | # Escape any '<' and '>' characters so they appear correctly in the final collection
|
|---|
| 258 | $sub_metadata_value =~ s/\</</g;
|
|---|
| 259 | $sub_metadata_value =~ s/\>/>/g;
|
|---|
| 260 |
|
|---|
| 261 | # print STDERR "Sub metadata name: $sub_metadata_name, value: $sub_metadata_value\n";
|
|---|
| 262 | if ($sub_metadata_name ne $metadata_name) {
|
|---|
| 263 | $doc_obj->add_utf8_metadata($section, $sub_metadata_name, $sub_metadata_value);
|
|---|
| 264 | }
|
|---|
| 265 |
|
|---|
| 266 | $metadata_value .= $subfield_separator unless ($metadata_value eq "");
|
|---|
| 267 | $metadata_value .= $sub_metadata_value;
|
|---|
| 268 | }
|
|---|
| 269 |
|
|---|
| 270 | # Add the metadata value
|
|---|
| 271 | # print STDERR "Metadata name: $metadata_name, value: $metadata_value\n";
|
|---|
| 272 | $doc_obj->add_utf8_metadata($section, $metadata_name, $metadata_value);
|
|---|
| 273 |
|
|---|
| 274 | $all_metadata_value .= $entry_separator unless ($all_metadata_value eq "");
|
|---|
| 275 | $all_metadata_value .= $metadata_value;
|
|---|
| 276 | }
|
|---|
| 277 |
|
|---|
| 278 | # Add the "^all" metadata value
|
|---|
| 279 | # print STDERR "All metadata name: $all_metadata_name, value: $all_metadata_value\n";
|
|---|
| 280 | $doc_obj->add_utf8_metadata($section, $all_metadata_name, $all_metadata_value);
|
|---|
| 281 | }
|
|---|
| 282 |
|
|---|
| 283 | # Add the full record as the document text
|
|---|
| 284 | $$textref =~ s/\</</g;
|
|---|
| 285 | $$textref =~ s/\>/>/g;
|
|---|
| 286 | $doc_obj->add_utf8_text($section, $$textref);
|
|---|
| 287 |
|
|---|
| 288 | # Add FileFormat metadata
|
|---|
| 289 | $doc_obj->add_utf8_metadata($section, "FileFormat", "CDS/ISIS");
|
|---|
| 290 |
|
|---|
| 291 | # Record was processed successfully
|
|---|
| 292 | return 1;
|
|---|
| 293 | }
|
|---|
| 294 |
|
|---|
| 295 |
|
|---|
| 296 | sub parse_field_definition_table
|
|---|
| 297 | {
|
|---|
| 298 | my $fdtfilename = shift(@_);
|
|---|
| 299 | my $encoding = shift(@_);
|
|---|
| 300 |
|
|---|
| 301 | my %fdtmapping = ();
|
|---|
| 302 |
|
|---|
| 303 | open(FDT_FILE, "<$fdtfilename") || die "Error: Could not open file $fdtfilename.\n";
|
|---|
| 304 |
|
|---|
| 305 | my $fdtfiletext = "";
|
|---|
| 306 | my $reader = new multiread();
|
|---|
| 307 | $reader->set_handle('ISISPlug::FDT_FILE');
|
|---|
| 308 | $reader->set_encoding($encoding);
|
|---|
| 309 | $reader->read_file($fdtfiletext);
|
|---|
| 310 |
|
|---|
| 311 | my $amongstdefinitions = 0;
|
|---|
| 312 | foreach my $fdtfileline (split(/\n/, $$fdtfiletext)) {
|
|---|
| 313 | $fdtfileline =~ s/(\s*)$//; # Remove any nasty spaces at the end of the lines
|
|---|
| 314 |
|
|---|
| 315 | if ($amongstdefinitions) {
|
|---|
| 316 | my $fieldname = substr($fdtfileline, 0, 30);
|
|---|
| 317 | my $fieldsubfields = substr($fdtfileline, 30, 20);
|
|---|
| 318 | my $fieldspecs = substr($fdtfileline, 50);
|
|---|
| 319 |
|
|---|
| 320 | # Remove extra spaces
|
|---|
| 321 | $fieldname =~ s/(\s*)$//;
|
|---|
| 322 | $fieldsubfields =~ s/(\s*)$//;
|
|---|
| 323 | $fieldspecs =~ s/(\s*)$//;
|
|---|
| 324 |
|
|---|
| 325 | # Map from tag number to metadata field title, subfields, and repeatability
|
|---|
| 326 | my $fieldtag = (split(/ /, $fieldspecs))[0];
|
|---|
| 327 | my $fieldrepeatable = (split(/ /, $fieldspecs))[3];
|
|---|
| 328 | $fdtmapping{$fieldtag} = { 'name' => $fieldname,
|
|---|
| 329 | 'subfields' => $fieldsubfields,
|
|---|
| 330 | 'repeatable' => $fieldrepeatable };
|
|---|
| 331 | }
|
|---|
| 332 | elsif ($fdtfileline eq "***") {
|
|---|
| 333 | $amongstdefinitions = 1;
|
|---|
| 334 | }
|
|---|
| 335 | }
|
|---|
| 336 |
|
|---|
| 337 | close(FDT_FILE);
|
|---|
| 338 |
|
|---|
| 339 | return %fdtmapping;
|
|---|
| 340 | }
|
|---|
| 341 |
|
|---|
| 342 |
|
|---|
| 343 | sub clean_up_after_exploding
|
|---|
| 344 | {
|
|---|
| 345 | my $self = shift(@_);
|
|---|
| 346 |
|
|---|
| 347 | # Delete the FDT and XRF files too
|
|---|
| 348 | &util::rm($self->{'fdt_filename'});
|
|---|
| 349 | &util::rm($self->{'xrf_filename'});
|
|---|
| 350 | }
|
|---|
| 351 |
|
|---|
| 352 |
|
|---|
| 353 | 1;
|
|---|
