[9919] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # basebuildproc.pm --
|
---|
| 4 | # A component of the Greenstone digital library software
|
---|
| 5 | # from the New Zealand Digital Library Project at the
|
---|
| 6 | # University of Waikato, New Zealand.
|
---|
| 7 | #
|
---|
| 8 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
| 9 | #
|
---|
| 10 | # This program is free software; you can redistribute it and/or modify
|
---|
| 11 | # it under the terms of the GNU General Public License as published by
|
---|
| 12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 13 | # (at your option) any later version.
|
---|
| 14 | #
|
---|
| 15 | # This program is distributed in the hope that it will be useful,
|
---|
| 16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 18 | # GNU General Public License for more details.
|
---|
| 19 | #
|
---|
| 20 | # You should have received a copy of the GNU General Public License
|
---|
| 21 | # along with this program; if not, write to the Free Software
|
---|
| 22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 23 | #
|
---|
| 24 | ###########################################################################
|
---|
| 25 |
|
---|
| 26 | # This document processor outputs a document for indexing (should be
|
---|
| 27 | # implemented by subclass) and storing in gdbm database
|
---|
| 28 |
|
---|
| 29 | package basebuildproc;
|
---|
| 30 |
|
---|
| 31 | eval {require bytes};
|
---|
| 32 |
|
---|
| 33 | use classify;
|
---|
| 34 | use doc;
|
---|
| 35 | use docproc;
|
---|
| 36 | use util;
|
---|
| 37 |
|
---|
| 38 | BEGIN {
|
---|
| 39 | @basebuildproc::ISA = ('docproc');
|
---|
| 40 | }
|
---|
| 41 |
|
---|
| 42 | sub new {
|
---|
[10159] | 43 | my ($class, $collection, $source_dir, $build_dir, $keepold,
|
---|
[9919] | 44 | $verbosity, $outhandle) = @_;
|
---|
| 45 | my $self = new docproc ();
|
---|
| 46 |
|
---|
| 47 | # outhandle is where all the debugging info goes
|
---|
| 48 | # output_handle is where the output of the plugins is piped
|
---|
| 49 | # to (i.e. mg, gdbm etc.)
|
---|
| 50 | $outhandle = STDERR unless defined $outhandle;
|
---|
| 51 |
|
---|
| 52 | $self->{'collection'} = $collection;
|
---|
| 53 | $self->{'source_dir'} = $source_dir;
|
---|
[10159] | 54 | $self->{'build_dir'} = $build_dir;
|
---|
| 55 | $self->{'keepold'} = $keepold;
|
---|
| 56 | $self->{'verbosity'} = $verbosity;
|
---|
| 57 | $self->{'outhandle'} = $outhandle;
|
---|
[9919] | 58 |
|
---|
| 59 | $self->{'classifiers'} = [];
|
---|
| 60 | $self->{'mode'} = "text";
|
---|
| 61 | $self->{'assocdir'} = $build_dir;
|
---|
| 62 | $self->{'dontgdbm'} = {};
|
---|
| 63 |
|
---|
| 64 | $self->{'index'} = "section:text";
|
---|
| 65 | $self->{'indexexparr'} = [];
|
---|
| 66 |
|
---|
[10159] | 67 | my $found_num_data = 0;
|
---|
| 68 | my $buildconfigfile = undef;
|
---|
| 69 |
|
---|
| 70 | if ($keepold) {
|
---|
| 71 | # For incremental building need to seed num_docs etc from values
|
---|
| 72 | # stored in build.cfg (if present)
|
---|
| 73 |
|
---|
| 74 | $buildconfigfile = &util::filename_cat($build_dir, "build.cfg");
|
---|
| 75 |
|
---|
| 76 | if (-e $buildconfigfile) {
|
---|
| 77 | $found_num_data = 1;
|
---|
| 78 | }
|
---|
| 79 | else {
|
---|
| 80 | # try the index dir
|
---|
| 81 | $buildconfigfile = &util::filename_cat($ENV{'GSDLCOLLECTDIR'},
|
---|
| 82 | "index", "build.cfg");
|
---|
| 83 | if (-e $buildconfigfile) {
|
---|
| 84 | $found_num_data = 1;
|
---|
| 85 | }
|
---|
| 86 | }
|
---|
| 87 |
|
---|
| 88 | }
|
---|
| 89 |
|
---|
| 90 | if ($found_num_data) {
|
---|
| 91 | my $buildcfg = &colcfg::read_build_cfg($buildconfigfile);
|
---|
| 92 |
|
---|
| 93 | $self->{'starting_num_docs'} = $buildcfg->{'numdocs'};
|
---|
| 94 | $self->{'starting_num_sections'} = $buildcfg->{'numsections'};
|
---|
| 95 | $self->{'starting_num_bytes'} = $buildcfg->{'numbytes'};
|
---|
| 96 | }
|
---|
| 97 | else {
|
---|
| 98 | $self->{'starting_num_docs'} = 0;
|
---|
| 99 | $self->{'starting_num_sections'} = 0;
|
---|
| 100 | $self->{'starting_num_bytes'} = 0;
|
---|
| 101 | }
|
---|
| 102 |
|
---|
[9919] | 103 | $self->{'output_handle'} = "STDOUT";
|
---|
[10159] | 104 | $self->{'num_docs'} = $self->{'starting_num_docs'};
|
---|
| 105 | $self->{'num_sections'} = $self->{'starting_num_sections'};
|
---|
| 106 | $self->{'num_bytes'} = $self->{'starting_num_bytes'};
|
---|
| 107 |
|
---|
[9919] | 108 | $self->{'num_processed_bytes'} = 0;
|
---|
| 109 | $self->{'store_text'} = 1;
|
---|
| 110 |
|
---|
| 111 | # what level (section/document) the gdbm database - indexer intersection is
|
---|
| 112 | $self->{'gdbm_level'} = "section";
|
---|
| 113 | #used by browse interface
|
---|
| 114 | $self->{'doclist'} = [];
|
---|
| 115 |
|
---|
| 116 | $self->{'indexing_text'} = 0;
|
---|
| 117 |
|
---|
| 118 | return bless $self, $class;
|
---|
| 119 |
|
---|
| 120 | }
|
---|
| 121 |
|
---|
| 122 | sub reset {
|
---|
| 123 | my $self = shift (@_);
|
---|
[10159] | 124 |
|
---|
| 125 | $self->{'num_docs'} = $self->{'starting_num_docs'};
|
---|
| 126 | $self->{'num_sections'} = $self->{'starting_num_sections'};
|
---|
| 127 | $self->{'num_bytes'} = $self->{'starting_num_bytes'};
|
---|
[9919] | 128 |
|
---|
| 129 | $self->{'num_processed_bytes'} = 0;
|
---|
| 130 | }
|
---|
| 131 |
|
---|
[10159] | 132 | sub zero_reset {
|
---|
| 133 | my $self = shift (@_);
|
---|
| 134 |
|
---|
| 135 | $self->{'num_docs'} = 0;
|
---|
| 136 | $self->{'num_sections'} = 0;
|
---|
| 137 | $self->{'num_bytes'} = 0;
|
---|
| 138 |
|
---|
| 139 | $self->{'num_processed_bytes'} = 0;
|
---|
| 140 | }
|
---|
| 141 |
|
---|
[10419] | 142 | sub is_incremental_capable
|
---|
[10304] | 143 | {
|
---|
| 144 | # By default we return 'no' as the answer
|
---|
| 145 | # Safer to assume non-incremental to start with, and then override in
|
---|
| 146 | # inherited classes that are.
|
---|
| 147 |
|
---|
| 148 | return 0;
|
---|
| 149 | }
|
---|
| 150 |
|
---|
[9919] | 151 | sub get_num_docs {
|
---|
| 152 | my $self = shift (@_);
|
---|
| 153 |
|
---|
| 154 | return $self->{'num_docs'};
|
---|
| 155 | }
|
---|
| 156 |
|
---|
| 157 | sub get_num_sections {
|
---|
| 158 | my $self = shift (@_);
|
---|
| 159 |
|
---|
| 160 | return $self->{'num_sections'};
|
---|
| 161 | }
|
---|
| 162 |
|
---|
| 163 | # num_bytes is the actual number of bytes in the collection
|
---|
| 164 | # this is normally the same as what's processed during text compression
|
---|
| 165 | sub get_num_bytes {
|
---|
| 166 | my $self = shift (@_);
|
---|
| 167 |
|
---|
| 168 | return $self->{'num_bytes'};
|
---|
| 169 | }
|
---|
| 170 |
|
---|
| 171 | # num_processed_bytes is the number of bytes actually passed
|
---|
| 172 | # to mg for the current index
|
---|
| 173 | sub get_num_processed_bytes {
|
---|
| 174 | my $self = shift (@_);
|
---|
| 175 |
|
---|
| 176 | return $self->{'num_processed_bytes'};
|
---|
| 177 | }
|
---|
| 178 |
|
---|
| 179 | sub set_output_handle {
|
---|
| 180 | my $self = shift (@_);
|
---|
| 181 | my ($handle) = @_;
|
---|
| 182 |
|
---|
| 183 | $self->{'output_handle'} = $handle;
|
---|
| 184 | }
|
---|
| 185 |
|
---|
| 186 |
|
---|
| 187 | sub set_mode {
|
---|
| 188 | my $self = shift (@_);
|
---|
| 189 | my ($mode) = @_;
|
---|
| 190 |
|
---|
| 191 | $self->{'mode'} = $mode;
|
---|
| 192 | }
|
---|
| 193 |
|
---|
[10159] | 194 | sub get_mode {
|
---|
| 195 | my $self = shift (@_);
|
---|
| 196 |
|
---|
| 197 | return $self->{'mode'};
|
---|
| 198 | }
|
---|
| 199 |
|
---|
[9919] | 200 | sub set_assocdir {
|
---|
| 201 | my $self = shift (@_);
|
---|
| 202 | my ($assocdir) = @_;
|
---|
| 203 |
|
---|
| 204 | $self->{'assocdir'} = $assocdir;
|
---|
| 205 | }
|
---|
| 206 |
|
---|
| 207 | sub set_dontgdbm {
|
---|
| 208 | my $self = shift (@_);
|
---|
| 209 | my ($dontgdbm) = @_;
|
---|
| 210 |
|
---|
| 211 | $self->{'dontgdbm'} = $dontgdbm;
|
---|
| 212 | }
|
---|
| 213 |
|
---|
| 214 | sub set_index {
|
---|
| 215 | my $self = shift (@_);
|
---|
| 216 | my ($index, $indexexparr) = @_;
|
---|
| 217 |
|
---|
| 218 | $self->{'index'} = $index;
|
---|
| 219 | $self->{'indexexparr'} = $indexexparr if defined $indexexparr;
|
---|
| 220 | }
|
---|
| 221 |
|
---|
| 222 | sub set_index_languages {
|
---|
| 223 | my $self = shift (@_);
|
---|
| 224 | my ($lang_meta, $langarr) = @_;
|
---|
| 225 | $self->{'lang_meta'} = $lang_meta;
|
---|
| 226 | $self->{'langarr'} = $langarr;
|
---|
| 227 | }
|
---|
| 228 |
|
---|
| 229 | sub get_index {
|
---|
| 230 | my $self = shift (@_);
|
---|
| 231 |
|
---|
| 232 | return $self->{'index'};
|
---|
| 233 | }
|
---|
| 234 |
|
---|
| 235 | sub set_classifiers {
|
---|
| 236 | my $self = shift (@_);
|
---|
| 237 | my ($classifiers) = @_;
|
---|
| 238 |
|
---|
| 239 | $self->{'classifiers'} = $classifiers;
|
---|
| 240 | }
|
---|
| 241 |
|
---|
| 242 | sub set_indexing_text {
|
---|
| 243 | my $self = shift (@_);
|
---|
| 244 | my ($indexing_text) = @_;
|
---|
| 245 |
|
---|
| 246 | $self->{'indexing_text'} = $indexing_text;
|
---|
| 247 | }
|
---|
| 248 |
|
---|
| 249 | sub get_indexing_text {
|
---|
| 250 | my $self = shift (@_);
|
---|
| 251 |
|
---|
| 252 | return $self->{'indexing_text'};
|
---|
| 253 | }
|
---|
| 254 |
|
---|
| 255 | sub set_store_text {
|
---|
| 256 | my $self = shift (@_);
|
---|
| 257 | my ($store_text) = @_;
|
---|
| 258 |
|
---|
| 259 | $self->{'store_text'} = $store_text;
|
---|
| 260 | }
|
---|
| 261 | sub get_doc_list {
|
---|
| 262 | my $self = shift(@_);
|
---|
| 263 |
|
---|
| 264 | return @{$self->{'doclist'}};
|
---|
| 265 | }
|
---|
| 266 |
|
---|
| 267 | # the standard gdbm level is section, but you may want to change it to document
|
---|
| 268 | sub set_gdbm_level {
|
---|
| 269 | my $self= shift (@_);
|
---|
| 270 | my ($gdbm_level) = @_;
|
---|
| 271 |
|
---|
| 272 | $self->{'gdbm_level'} = $gdbm_level;
|
---|
| 273 | }
|
---|
| 274 |
|
---|
| 275 | sub process {
|
---|
| 276 | my $self = shift (@_);
|
---|
| 277 | my $method = $self->{'mode'};
|
---|
| 278 |
|
---|
| 279 | $self->$method(@_);
|
---|
| 280 | }
|
---|
| 281 |
|
---|
| 282 | sub infodb {
|
---|
| 283 | my $self = shift (@_);
|
---|
| 284 | my ($doc_obj, $filename) = @_;
|
---|
| 285 | my $handle = $self->{'output_handle'};
|
---|
| 286 |
|
---|
| 287 | my $doctype = $doc_obj->get_doc_type();
|
---|
| 288 |
|
---|
| 289 | # only output this document if it is one to be indexed
|
---|
| 290 | return if ($doctype ne "indexed_doc");
|
---|
| 291 |
|
---|
| 292 | my ($archivedir) = $filename =~ /^(.*?)(?:\/|\\)[^\/\\]*$/;
|
---|
| 293 | $archivedir = "" unless defined $archivedir;
|
---|
| 294 | $archivedir =~ s/\\/\//g;
|
---|
| 295 | $archivedir =~ s/^\/+//;
|
---|
| 296 | $archivedir =~ s/\/+$//;
|
---|
| 297 |
|
---|
| 298 | # resolve the final filenames of the files associated with this document
|
---|
| 299 | $self->assoc_files ($doc_obj, $archivedir);
|
---|
| 300 |
|
---|
| 301 | #GRB: moved 1/06/2004 from GRB01062004
|
---|
| 302 | #add this document to the browse structure
|
---|
| 303 | push(@{$self->{'doclist'}},$doc_obj->get_OID())
|
---|
| 304 | unless ($doctype eq "classification");
|
---|
| 305 |
|
---|
| 306 | # classify this document
|
---|
| 307 | &classify::classify_doc ($self->{'classifiers'}, $doc_obj);
|
---|
| 308 | #GRB: end of moved block
|
---|
| 309 |
|
---|
| 310 | # this is another document
|
---|
| 311 | $self->{'num_docs'} += 1 unless ($doctype eq "classification");
|
---|
| 312 |
|
---|
| 313 | # is this a paged or a hierarchical document
|
---|
| 314 | my ($thistype, $childtype) = $self->get_document_type ($doc_obj);
|
---|
| 315 |
|
---|
| 316 | my $section = $doc_obj->get_top_section ();
|
---|
| 317 | my $doc_OID = $doc_obj->get_OID();
|
---|
| 318 | my $first = 1;
|
---|
| 319 | my $url = "";
|
---|
| 320 | while (defined $section) {
|
---|
| 321 | # update a few statistics
|
---|
| 322 | $self->{'num_bytes'} += $doc_obj->get_text_length ($section);
|
---|
| 323 | $self->{'num_sections'} += 1 unless ($doctype eq "classification");
|
---|
| 324 |
|
---|
| 325 | # output the section name
|
---|
| 326 | if ($section eq "") { print $handle "[$doc_OID]\n"; }
|
---|
| 327 | else { print $handle "[$doc_OID.$section]\n"; }
|
---|
| 328 |
|
---|
| 329 | # output the fact that this document is a document (unless doctype
|
---|
| 330 | # has been set to something else from within a plugin
|
---|
| 331 | my $dtype = $doc_obj->get_metadata_element ($section, "doctype");
|
---|
| 332 | if (!defined $dtype || $dtype !~ /\w/) {
|
---|
| 333 | print $handle "<doctype>doc\n";
|
---|
| 334 | }
|
---|
| 335 |
|
---|
| 336 | # output whether this node contains text
|
---|
| 337 | if ($doc_obj->get_text_length($section) > 0) {
|
---|
| 338 | print $handle "<hastxt>1\n";
|
---|
| 339 | } else {
|
---|
| 340 | print $handle "<hastxt>0\n";
|
---|
| 341 | }
|
---|
| 342 |
|
---|
| 343 | # output all the section metadata
|
---|
| 344 | my $metadata = $doc_obj->get_all_metadata ($section);
|
---|
| 345 | foreach my $pair (@$metadata) {
|
---|
| 346 | my ($field, $value) = (@$pair);
|
---|
| 347 |
|
---|
| 348 | if ($field ne "Identifier" && $field !~ /^gsdl/ &&
|
---|
| 349 | defined $value && $value ne "") {
|
---|
| 350 |
|
---|
| 351 | # escape problematic stuff
|
---|
| 352 | $value =~ s/\\/\\\\/g;
|
---|
| 353 | $value =~ s/\n/\\n/g;
|
---|
| 354 | $value =~ s/\r/\\r/g;
|
---|
| 355 | if ($value =~ /-{70,}/) {
|
---|
| 356 | # if value contains 70 or more hyphens in a row we need
|
---|
| 357 | # to escape them to prevent txt2db from treating them
|
---|
| 358 | # as a separator
|
---|
| 359 | $value =~ s/-/&\#045;/gi;
|
---|
| 360 | }
|
---|
| 361 |
|
---|
| 362 | # special case for URL metadata
|
---|
| 363 | if ($field =~ /^URL$/i) {
|
---|
| 364 | $url .= "[$value]\n";
|
---|
| 365 | if ($section eq "") {$url .= "<section>$doc_OID\n";}
|
---|
| 366 | else {$url .= "<section>$doc_OID.$section\n";}
|
---|
| 367 | $url .= '-' x 70 . "\n";
|
---|
| 368 | }
|
---|
| 369 |
|
---|
| 370 | if (!defined $self->{'dontgdbm'}->{$field}) {
|
---|
| 371 | print $handle "<$field>$value\n";
|
---|
| 372 | }
|
---|
| 373 | }
|
---|
| 374 | }
|
---|
| 375 |
|
---|
| 376 | # output archivedir if at top level
|
---|
| 377 | if ($section eq $doc_obj->get_top_section()) {
|
---|
| 378 | print $handle "<archivedir>$archivedir\n";
|
---|
| 379 | }
|
---|
| 380 |
|
---|
| 381 | # output document display type
|
---|
| 382 | if ($first) {
|
---|
| 383 | print $handle "<thistype>$thistype\n";
|
---|
| 384 | }
|
---|
| 385 |
|
---|
| 386 | if ($self->{'gdbm_level'} eq "document") {
|
---|
| 387 | # doc num is num_docs not num_sections
|
---|
| 388 | # output the matching document number
|
---|
| 389 | print $handle "<docnum>$self->{'num_docs'}\n";
|
---|
| 390 | } else {
|
---|
| 391 | # output a list of children
|
---|
| 392 | my $children = $doc_obj->get_children ($section);
|
---|
| 393 | if (scalar(@$children) > 0) {
|
---|
| 394 | print $handle "<childtype>$childtype\n";
|
---|
| 395 | print $handle "<contains>";
|
---|
| 396 | my $firstchild = 1;
|
---|
| 397 | foreach my $child (@$children) {
|
---|
| 398 | print $handle ";" unless $firstchild;
|
---|
| 399 | $firstchild = 0;
|
---|
| 400 | if ($child =~ /^.*?\.(\d+)$/) {
|
---|
| 401 | print $handle "\".$1";
|
---|
| 402 | } else {
|
---|
| 403 | print $handle "\".$child";
|
---|
| 404 | }
|
---|
| 405 | # if ($child eq "") { print $handle "$doc_OID"; }
|
---|
| 406 | # elsif ($section eq "") { print $handle "$doc_OID.$child"; }
|
---|
| 407 | # else { print $handle "$doc_OID.$section.$child"; }
|
---|
| 408 | }
|
---|
| 409 | print $handle "\n";
|
---|
| 410 | }
|
---|
| 411 | #output the matching doc number
|
---|
| 412 | print $handle "<docnum>$self->{'num_sections'}\n";
|
---|
| 413 |
|
---|
| 414 | }
|
---|
| 415 |
|
---|
| 416 | print $handle '-' x 70, "\n";
|
---|
| 417 |
|
---|
| 418 |
|
---|
| 419 | # output a database entry for the document number
|
---|
| 420 | if ($self->{'gdbm_level'} eq "document") {
|
---|
| 421 | print $handle "[$self->{'num_docs'}]\n";
|
---|
| 422 | print $handle "<section>$doc_OID\n";
|
---|
| 423 | }
|
---|
| 424 | else {
|
---|
| 425 | print $handle "[$self->{'num_sections'}]\n";
|
---|
| 426 | if ($section eq "") { print $handle "<section>$doc_OID\n"; }
|
---|
| 427 | else { print $handle "<section>$doc_OID.$section\n"; }
|
---|
| 428 | }
|
---|
| 429 | print $handle '-' x 70, "\n";
|
---|
| 430 |
|
---|
| 431 | # output entry for url
|
---|
| 432 | if ($url ne "") {
|
---|
| 433 | print $handle $url;
|
---|
| 434 | }
|
---|
| 435 |
|
---|
| 436 | $first = 0;
|
---|
| 437 | $section = $doc_obj->get_next_section($section);
|
---|
| 438 | last if ($self->{'gdbm_level'} eq "document"); # if no sections wanted, only gdbm the docs
|
---|
| 439 | }
|
---|
| 440 |
|
---|
| 441 | #GRB01062004: see code above moved from here
|
---|
| 442 | }
|
---|
| 443 |
|
---|
| 444 |
|
---|
| 445 | sub text {
|
---|
| 446 | my $self = shift (@_);
|
---|
| 447 | my ($doc_obj) = @_;
|
---|
| 448 |
|
---|
| 449 | my $handle = $self->{'outhandle'};
|
---|
| 450 | print $handle "basebuildproc::text function must be implemented in sub classes\n";
|
---|
| 451 | die "\n";
|
---|
| 452 | }
|
---|
| 453 |
|
---|
| 454 | # should the document be indexed - according to the subcollection and language
|
---|
| 455 | # specification.
|
---|
| 456 | sub is_subcollection_doc {
|
---|
| 457 | my $self = shift (@_);
|
---|
| 458 | my ($doc_obj) = @_;
|
---|
| 459 |
|
---|
| 460 | my $indexed_doc = 1;
|
---|
| 461 | foreach my $indexexp (@{$self->{'indexexparr'}}) {
|
---|
| 462 | $indexed_doc = 0;
|
---|
| 463 | my ($field, $exp, $options) = split /\//, $indexexp;
|
---|
| 464 | if (defined ($field) && defined ($exp)) {
|
---|
| 465 | my ($bool) = $field =~ /^(.)/;
|
---|
| 466 | $field =~ s/^.// if $bool eq '!';
|
---|
[10028] | 467 | my @metadata_values;
|
---|
[9919] | 468 | if ($field =~ /^filename$/i) {
|
---|
[10028] | 469 | push(@metadata_values, $doc_obj->get_source_filename());
|
---|
[9919] | 470 | }
|
---|
[10028] | 471 | else {
|
---|
| 472 | @metadata_values = @{$doc_obj->get_metadata($doc_obj->get_top_section(), $field)};
|
---|
| 473 | }
|
---|
| 474 | next unless @metadata_values;
|
---|
| 475 | foreach my $metadata_value (@metadata_values) {
|
---|
| 476 | if ($bool eq '!') {
|
---|
| 477 | if ($options =~ /^i$/i) {
|
---|
| 478 | if ($metadata_value !~ /$exp/i) {$indexed_doc = 1; last;}
|
---|
| 479 | } else {
|
---|
| 480 | if ($metadata_value !~ /$exp/) {$indexed_doc = 1; last;}
|
---|
| 481 | }
|
---|
[9919] | 482 | } else {
|
---|
[10028] | 483 | if ($options =~ /^i$/i) {
|
---|
| 484 | if ($metadata_value =~ /$exp/i) {$indexed_doc = 1; last;}
|
---|
| 485 | } else {
|
---|
| 486 | if ($metadata_value =~ /$exp/) {$indexed_doc = 1; last;}
|
---|
| 487 | }
|
---|
[9919] | 488 | }
|
---|
| 489 | }
|
---|
[10028] | 490 |
|
---|
| 491 | last if ($indexed_doc == 1);
|
---|
[9919] | 492 | }
|
---|
| 493 | }
|
---|
| 494 |
|
---|
| 495 | # if this doc is so far in the sub collection, and we have lang info,
|
---|
| 496 | # now we check the languages to see if it matches
|
---|
| 497 | if($indexed_doc && defined $self->{'lang_meta'}) {
|
---|
| 498 | $indexed_doc = 0;
|
---|
| 499 | my $field = $doc_obj->get_metadata_element($doc_obj->get_top_section(), $self->{'lang_meta'});
|
---|
| 500 | if (defined $field) {
|
---|
| 501 | foreach my $lang (@{$self->{'langarr'}}) {
|
---|
| 502 | my ($bool) = $lang =~ /^(.)/;
|
---|
| 503 | if ($bool eq '!') {
|
---|
| 504 | $lang =~ s/^.//;
|
---|
| 505 | if ($field !~ /$lang/) {
|
---|
| 506 | $indexed_doc = 1; last;
|
---|
| 507 | }
|
---|
| 508 | } else {
|
---|
| 509 | if ($field =~ /$lang/) {
|
---|
| 510 | $indexed_doc = 1; last;
|
---|
| 511 | }
|
---|
| 512 | }
|
---|
| 513 | }
|
---|
| 514 | }
|
---|
| 515 | }
|
---|
| 516 | return $indexed_doc;
|
---|
| 517 |
|
---|
| 518 | }
|
---|
| 519 |
|
---|
| 520 | # use 'Paged' if document has no more than 2 levels
|
---|
| 521 | # and each section at second level has a number for
|
---|
| 522 | # Title metadata
|
---|
| 523 | # also use Paged if gsdlthistype metadata is set to Paged
|
---|
| 524 | sub get_document_type {
|
---|
| 525 | my $self = shift (@_);
|
---|
| 526 | my ($doc_obj) = @_;
|
---|
| 527 |
|
---|
| 528 | my $thistype = "VList";
|
---|
| 529 | my $childtype = "VList";
|
---|
| 530 | my $title;
|
---|
| 531 | my @tmp = ();
|
---|
| 532 |
|
---|
| 533 | my $section = $doc_obj->get_top_section ();
|
---|
| 534 |
|
---|
| 535 | my $gsdlthistype = $doc_obj->get_metadata_element ($section, "gsdlthistype");
|
---|
| 536 | if (defined $gsdlthistype) {
|
---|
| 537 | if ($gsdlthistype eq "Paged") {
|
---|
| 538 | $childtype = "Paged";
|
---|
| 539 | if ($doc_obj->get_text_length ($doc_obj->get_top_section())) {
|
---|
| 540 | $thistype = "Paged";
|
---|
| 541 | } else {
|
---|
| 542 | $thistype = "Invisible";
|
---|
| 543 | }
|
---|
| 544 |
|
---|
| 545 | return ($thistype, $childtype);
|
---|
| 546 | } elsif ($gsdlthistype eq "Hierarchy") {
|
---|
| 547 | return ($thistype, $childtype); # use VList, VList
|
---|
| 548 | }
|
---|
| 549 | }
|
---|
| 550 | my $first = 1;
|
---|
| 551 | while (defined $section) {
|
---|
| 552 | @tmp = split /\./, $section;
|
---|
| 553 | if (scalar(@tmp) > 1) {
|
---|
| 554 | return ($thistype, $childtype);
|
---|
| 555 | }
|
---|
| 556 | if (!$first) {
|
---|
| 557 | $title = $doc_obj->get_metadata_element ($section, "Title");
|
---|
| 558 | if (!defined $title || $title !~ /^\d+$/) {
|
---|
| 559 | return ($thistype, $childtype);
|
---|
| 560 | }
|
---|
| 561 | }
|
---|
| 562 | $first = 0;
|
---|
| 563 | $section = $doc_obj->get_next_section($section);
|
---|
| 564 | }
|
---|
| 565 | if ($doc_obj->get_text_length ($doc_obj->get_top_section())) {
|
---|
| 566 | $thistype = "Paged";
|
---|
| 567 | } else {
|
---|
| 568 | $thistype = "Invisible";
|
---|
| 569 | }
|
---|
| 570 | $childtype = "Paged";
|
---|
| 571 | return ($thistype, $childtype);
|
---|
| 572 | }
|
---|
| 573 |
|
---|
| 574 | sub assoc_files {
|
---|
| 575 | my $self = shift (@_);
|
---|
| 576 | my ($doc_obj, $archivedir) = @_;
|
---|
| 577 | my ($afile);
|
---|
| 578 |
|
---|
| 579 | foreach my $assoc_file (@{$doc_obj->get_assoc_files()}) {
|
---|
| 580 | # if assoc file starts with a slash, we put it relative to the assoc
|
---|
| 581 | # dir, otherwise it is relative to the HASH... directory
|
---|
| 582 | if ($assoc_file->[1] =~ m@^[/\\]@) {
|
---|
| 583 | $afile = &util::filename_cat($self->{'assocdir'},$assoc_file->[1]);
|
---|
| 584 | } else {
|
---|
| 585 | $afile = &util::filename_cat($self->{'assocdir'}, $archivedir, $assoc_file->[1]);
|
---|
| 586 | }
|
---|
| 587 | &util::hard_link ($assoc_file->[0], $afile);
|
---|
| 588 | }
|
---|
| 589 | }
|
---|
| 590 |
|
---|