[12330] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
[17202] | 3 | # BasePlugout.pm -- base class for all the plugout modules
|
---|
[12330] | 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) 2006 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 |
|
---|
[17202] | 26 | package BasePlugout;
|
---|
[12330] | 27 |
|
---|
| 28 | eval {require bytes};
|
---|
| 29 |
|
---|
| 30 | use strict;
|
---|
| 31 | no strict 'subs';
|
---|
[12459] | 32 | no strict 'refs';
|
---|
[12330] | 33 |
|
---|
[21565] | 34 | use dbutil;
|
---|
[12330] | 35 | use gsprintf 'gsprintf';
|
---|
| 36 | use printusage;
|
---|
[12546] | 37 | use parse2;
|
---|
[27306] | 38 | use util;
|
---|
| 39 | use FileUtils;
|
---|
[12330] | 40 |
|
---|
| 41 | # suppress the annoying "subroutine redefined" warning that various
|
---|
| 42 | # gets cause under perl 5.6
|
---|
| 43 | $SIG{__WARN__} = sub {warn($_[0]) unless ($_[0] =~ /Subroutine\s+\S+\sredefined/)};
|
---|
| 44 |
|
---|
| 45 | my $arguments = [
|
---|
[13172] | 46 | { 'name' => "group_size",
|
---|
[12330] | 47 | 'desc' => "{BasPlugout.group_size}",
|
---|
| 48 | 'type' => "int",
|
---|
| 49 | 'deft' => "1",
|
---|
| 50 | 'reqd' => "no",
|
---|
| 51 | 'hiddengli' => "no"},
|
---|
| 52 | { 'name' => "output_info",
|
---|
| 53 | 'desc' => "{BasPlugout.output_info}",
|
---|
| 54 | 'type' => "string",
|
---|
| 55 | 'reqd' => "yes",
|
---|
| 56 | 'hiddengli' => "yes"},
|
---|
| 57 | { 'name' => "xslt_file",
|
---|
| 58 | 'desc' => "{BasPlugout.xslt_file}",
|
---|
| 59 | 'type' => "string",
|
---|
| 60 | 'reqd' => "no",
|
---|
[20320] | 61 | 'deft' => "",
|
---|
[12330] | 62 | 'hiddengli' => "no"},
|
---|
| 63 | { 'name' => "output_handle",
|
---|
| 64 | 'desc' => "{BasPlugout.output_handle}",
|
---|
| 65 | 'type' => "string",
|
---|
| 66 | 'deft' => 'STDERR',
|
---|
| 67 | 'reqd' => "no",
|
---|
| 68 | 'hiddengli' => "yes"},
|
---|
| 69 | { 'name' => "verbosity",
|
---|
| 70 | 'desc' => "{BasPlugout.verbosity}",
|
---|
| 71 | 'type' => "int",
|
---|
| 72 | 'deft' => "0",
|
---|
| 73 | 'reqd' => "no",
|
---|
| 74 | 'hiddengli' => "no"},
|
---|
| 75 | { 'name' => "gzip_output",
|
---|
| 76 | 'desc' => "{BasPlugout.gzip_output}",
|
---|
| 77 | 'type' => "flag",
|
---|
| 78 | 'reqd' => "no",
|
---|
[13172] | 79 | 'hiddengli' => "no"},
|
---|
| 80 | { 'name' => "debug",
|
---|
| 81 | 'desc' => "{BasPlugout.debug}",
|
---|
| 82 | 'type' => "flag",
|
---|
| 83 | 'reqd' => "no",
|
---|
[27499] | 84 | 'hiddengli' => "yes"},
|
---|
| 85 | { 'name' => "subdir_split_length",
|
---|
| 86 | 'desc' => "{BasPlugout.subdir_split_length}",
|
---|
| 87 | 'type' => "int",
|
---|
| 88 | 'reqd' => "no",
|
---|
| 89 | 'deft' => "8",
|
---|
| 90 | 'hiddengli' => "no"},
|
---|
| 91 | { 'name' => "subdir_hash_prefix",
|
---|
| 92 | 'desc' => "{BasPlugout.subdir_hash_prefix}",
|
---|
| 93 | 'type' => "flag",
|
---|
| 94 | 'reqd' => "no",
|
---|
[28021] | 95 | 'deft' => "0",
|
---|
[27646] | 96 | 'hiddengli' => "no"},
|
---|
| 97 | { 'name' => 'no_rss',
|
---|
| 98 | 'desc' => '{BasPlugout.no_rss}',
|
---|
| 99 | 'type' => 'flag',
|
---|
| 100 | 'reqd' => 'no',
|
---|
| 101 | 'hiddengli' => 'yes'}
|
---|
[12330] | 102 | ];
|
---|
| 103 |
|
---|
[17202] | 104 | my $options = { 'name' => "BasePlugout",
|
---|
[12330] | 105 | 'desc' => "{BasPlugout.desc}",
|
---|
| 106 | 'abstract' => "yes",
|
---|
| 107 | 'inherits' => "no",
|
---|
| 108 | 'args' => $arguments};
|
---|
| 109 |
|
---|
| 110 | sub new
|
---|
| 111 | {
|
---|
| 112 | my $class = shift (@_);
|
---|
| 113 |
|
---|
| 114 | my ($plugoutlist,$args,$hashArgOptLists) = @_;
|
---|
| 115 | push(@$plugoutlist, $class);
|
---|
| 116 |
|
---|
[20320] | 117 | my $plugout_name = (defined $plugoutlist->[0]) ? $plugoutlist->[0] : $class;
|
---|
[12330] | 118 |
|
---|
[17202] | 119 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 120 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[12330] | 121 |
|
---|
| 122 | my $self = {};
|
---|
| 123 | $self->{'plugout_type'} = $class;
|
---|
| 124 | $self->{'option_list'} = $hashArgOptLists->{"OptList"};
|
---|
| 125 | $self->{"info_only"} = 0;
|
---|
| 126 |
|
---|
| 127 | # Check if gsdlinfo is in the argument list or not - if it is, don't parse
|
---|
| 128 | # the args, just return the object.
|
---|
| 129 | foreach my $strArg (@{$args})
|
---|
| 130 | {
|
---|
| 131 | if(defined $strArg && $strArg eq "-gsdlinfo")
|
---|
| 132 | {
|
---|
| 133 | $self->{"info_only"} = 1;
|
---|
| 134 | return bless $self, $class;
|
---|
| 135 | }
|
---|
| 136 | }
|
---|
| 137 |
|
---|
| 138 | delete $self->{"info_only"};
|
---|
| 139 |
|
---|
[12546] | 140 | if(parse2::parse($args,$hashArgOptLists->{"ArgList"},$self) == -1)
|
---|
[12330] | 141 | {
|
---|
| 142 | my $classTempClass = bless $self, $class;
|
---|
[20320] | 143 | print STDERR "<BadPlugout d=$plugout_name>\n";
|
---|
| 144 | &gsprintf(STDERR, "\n{BasPlugout.bad_general_option}\n", $plugout_name);
|
---|
[12330] | 145 | $classTempClass->print_txt_usage(""); # Use default resource bundle
|
---|
| 146 | die "\n";
|
---|
| 147 | }
|
---|
| 148 |
|
---|
| 149 |
|
---|
[12603] | 150 | if(defined $self->{'xslt_file'} && $self->{'xslt_file'} ne "")
|
---|
[12330] | 151 | {
|
---|
[20320] | 152 | my $full_file_path = &util::locate_config_file($self->{'xslt_file'});
|
---|
| 153 | if (!defined $full_file_path) {
|
---|
| 154 | print STDERR "Can not find $self->{'xslt_file'}, please make sure you have supplied the correct file path\n";
|
---|
| 155 | die "\n";
|
---|
| 156 | }
|
---|
| 157 | $self->{'xslt_file'} = $full_file_path;
|
---|
[12330] | 158 | }
|
---|
| 159 |
|
---|
[28021] | 160 | $self->{'gs_count'} = 0;
|
---|
[12330] | 161 |
|
---|
[28021] | 162 | $self->{'keep_import_structure'} = 0;
|
---|
[12330] | 163 |
|
---|
| 164 | return bless $self, $class;
|
---|
| 165 |
|
---|
| 166 | }
|
---|
| 167 |
|
---|
| 168 | sub print_xml_usage
|
---|
| 169 | {
|
---|
| 170 | my $self = shift(@_);
|
---|
| 171 | my $header = shift(@_);
|
---|
[12628] | 172 | my $high_level_information_only = shift(@_);
|
---|
[28021] | 173 |
|
---|
[12330] | 174 | # XML output is always in UTF-8
|
---|
| 175 | gsprintf::output_strings_in_UTF8;
|
---|
| 176 |
|
---|
| 177 | if ($header) {
|
---|
| 178 | &PrintUsage::print_xml_header("plugout");
|
---|
| 179 | }
|
---|
[12628] | 180 | $self->print_xml($high_level_information_only);
|
---|
[12330] | 181 | }
|
---|
| 182 |
|
---|
| 183 |
|
---|
| 184 | sub print_xml
|
---|
| 185 | {
|
---|
| 186 | my $self = shift(@_);
|
---|
[12628] | 187 | my $high_level_information_only = shift(@_);
|
---|
| 188 |
|
---|
[12330] | 189 | my $optionlistref = $self->{'option_list'};
|
---|
| 190 | my @optionlist = @$optionlistref;
|
---|
| 191 | my $plugoutoptions = shift(@$optionlistref);
|
---|
| 192 | return if (!defined($plugoutoptions));
|
---|
| 193 |
|
---|
| 194 | gsprintf(STDERR, "<PlugoutInfo>\n");
|
---|
| 195 | gsprintf(STDERR, " <Name>$plugoutoptions->{'name'}</Name>\n");
|
---|
| 196 | my $desc = gsprintf::lookup_string($plugoutoptions->{'desc'});
|
---|
| 197 | $desc =~ s/</&lt;/g; # doubly escaped
|
---|
| 198 | $desc =~ s/>/&gt;/g;
|
---|
| 199 | gsprintf(STDERR, " <Desc>$desc</Desc>\n");
|
---|
| 200 | gsprintf(STDERR, " <Abstract>$plugoutoptions->{'abstract'}</Abstract>\n");
|
---|
| 201 | gsprintf(STDERR, " <Inherits>$plugoutoptions->{'inherits'}</Inherits>\n");
|
---|
[12628] | 202 | unless (defined($high_level_information_only)) {
|
---|
| 203 | gsprintf(STDERR, " <Arguments>\n");
|
---|
| 204 | if (defined($plugoutoptions->{'args'})) {
|
---|
| 205 | &PrintUsage::print_options_xml($plugoutoptions->{'args'});
|
---|
| 206 | }
|
---|
| 207 | gsprintf(STDERR, " </Arguments>\n");
|
---|
[12330] | 208 |
|
---|
[12628] | 209 | # Recurse up the plugout hierarchy
|
---|
| 210 | $self->print_xml();
|
---|
[12330] | 211 | }
|
---|
| 212 | gsprintf(STDERR, "</PlugoutInfo>\n");
|
---|
| 213 | }
|
---|
| 214 |
|
---|
| 215 |
|
---|
| 216 | sub print_txt_usage
|
---|
| 217 | {
|
---|
| 218 | my $self = shift(@_);
|
---|
| 219 |
|
---|
| 220 | # Print the usage message for a plugout (recursively)
|
---|
| 221 | my $descoffset = $self->determine_description_offset(0);
|
---|
| 222 | $self->print_plugout_usage($descoffset, 1);
|
---|
| 223 | }
|
---|
| 224 |
|
---|
| 225 | sub determine_description_offset
|
---|
| 226 | {
|
---|
| 227 | my $self = shift(@_);
|
---|
| 228 | my $maxoffset = shift(@_);
|
---|
| 229 |
|
---|
| 230 | my $optionlistref = $self->{'option_list'};
|
---|
| 231 | my @optionlist = @$optionlistref;
|
---|
| 232 | my $plugoutoptions = pop(@$optionlistref);
|
---|
| 233 | return $maxoffset if (!defined($plugoutoptions));
|
---|
| 234 |
|
---|
| 235 | # Find the length of the longest option string of this download
|
---|
| 236 | my $plugoutargs = $plugoutoptions->{'args'};
|
---|
| 237 | if (defined($plugoutargs)) {
|
---|
| 238 | my $longest = &PrintUsage::find_longest_option_string($plugoutargs);
|
---|
| 239 | if ($longest > $maxoffset) {
|
---|
| 240 | $maxoffset = $longest;
|
---|
| 241 | }
|
---|
| 242 | }
|
---|
| 243 |
|
---|
| 244 | # Recurse up the download hierarchy
|
---|
| 245 | $maxoffset = $self->determine_description_offset($maxoffset);
|
---|
| 246 | $self->{'option_list'} = \@optionlist;
|
---|
| 247 | return $maxoffset;
|
---|
| 248 | }
|
---|
| 249 |
|
---|
| 250 |
|
---|
| 251 | sub print_plugout_usage
|
---|
| 252 | {
|
---|
| 253 | my $self = shift(@_);
|
---|
| 254 | my $descoffset = shift(@_);
|
---|
| 255 | my $isleafclass = shift(@_);
|
---|
| 256 |
|
---|
| 257 | my $optionlistref = $self->{'option_list'};
|
---|
| 258 | my @optionlist = @$optionlistref;
|
---|
| 259 | my $plugoutoptions = shift(@$optionlistref);
|
---|
| 260 | return if (!defined($plugoutoptions));
|
---|
| 261 |
|
---|
| 262 | my $plugoutname = $plugoutoptions->{'name'};
|
---|
| 263 | my $plugoutargs = $plugoutoptions->{'args'};
|
---|
| 264 | my $plugoutdesc = $plugoutoptions->{'desc'};
|
---|
| 265 |
|
---|
| 266 | # Produce the usage information using the data structure above
|
---|
| 267 | if ($isleafclass) {
|
---|
| 268 | if (defined($plugoutdesc)) {
|
---|
| 269 | gsprintf(STDERR, "$plugoutdesc\n\n");
|
---|
| 270 | }
|
---|
| 271 | gsprintf(STDERR, " {common.usage}: plugout $plugoutname [{common.options}]\n\n");
|
---|
| 272 | }
|
---|
| 273 |
|
---|
| 274 | # Display the download options, if there are some
|
---|
| 275 | if (defined($plugoutargs)) {
|
---|
| 276 | # Calculate the column offset of the option descriptions
|
---|
| 277 | my $optiondescoffset = $descoffset + 2; # 2 spaces between options & descriptions
|
---|
| 278 |
|
---|
| 279 | if ($isleafclass) {
|
---|
| 280 | gsprintf(STDERR, " {common.specific_options}:\n");
|
---|
| 281 | }
|
---|
| 282 | else {
|
---|
| 283 | gsprintf(STDERR, " {common.general_options}:\n", $plugoutname);
|
---|
| 284 | }
|
---|
| 285 |
|
---|
| 286 | # Display the download options
|
---|
| 287 | &PrintUsage::print_options_txt($plugoutargs, $optiondescoffset);
|
---|
| 288 | }
|
---|
| 289 |
|
---|
| 290 | # Recurse up the download hierarchy
|
---|
| 291 | $self->print_plugout_usage($descoffset, 0);
|
---|
| 292 | $self->{'option_list'} = \@optionlist;
|
---|
| 293 | }
|
---|
| 294 |
|
---|
| 295 |
|
---|
| 296 | sub error
|
---|
| 297 | {
|
---|
| 298 | my ($strFunctionName,$strError) = @_;
|
---|
| 299 | {
|
---|
[17202] | 300 | print "Error occoured in BasePlugout.pm\n".
|
---|
[12330] | 301 | "In Function: ".$strFunctionName."\n".
|
---|
| 302 | "Error Message: ".$strError."\n";
|
---|
| 303 | exit(-1);
|
---|
| 304 | }
|
---|
| 305 | }
|
---|
| 306 |
|
---|
[27352] | 307 | # OIDtype may be "hash" or "hash_on_full_filename" or "incremental" or "filename" or "dirname" or "full_filename" or "assigned"
|
---|
[12330] | 308 | sub set_OIDtype {
|
---|
| 309 | my $self = shift (@_);
|
---|
[12618] | 310 | my ($type, $metadata) = @_;
|
---|
[12330] | 311 |
|
---|
[27352] | 312 | if ($type =~ /^(hash|hash_on_full_filename|incremental|filename|dirname|full_filename|assigned)$/) {
|
---|
[12330] | 313 | $self->{'OIDtype'} = $type;
|
---|
| 314 | } else {
|
---|
| 315 | $self->{'OIDtype'} = "hash";
|
---|
| 316 | }
|
---|
[12618] | 317 | if ($type =~ /^assigned$/) {
|
---|
| 318 | if (defined $metadata) {
|
---|
| 319 | $self->{'OIDmetadata'} = $metadata;
|
---|
| 320 | } else {
|
---|
| 321 | $self->{'OIDmetadata'} = "dc.Identifier";
|
---|
| 322 | }
|
---|
| 323 | }
|
---|
[12330] | 324 | }
|
---|
| 325 |
|
---|
| 326 | sub set_output_dir
|
---|
| 327 | {
|
---|
| 328 | my $self = shift @_;
|
---|
| 329 | my ($output_dir) = @_;
|
---|
| 330 |
|
---|
| 331 | $self->{'output_dir'} = $output_dir;
|
---|
| 332 | }
|
---|
| 333 |
|
---|
| 334 | sub setoutputdir
|
---|
| 335 | {
|
---|
| 336 | my $self = shift @_;
|
---|
| 337 | my ($output_dir) = @_;
|
---|
| 338 |
|
---|
| 339 | $self->{'output_dir'} = $output_dir;
|
---|
| 340 | }
|
---|
| 341 |
|
---|
| 342 | sub get_output_dir
|
---|
| 343 | {
|
---|
| 344 | my $self = shift (@_);
|
---|
| 345 |
|
---|
| 346 | return $self->{'output_dir'};
|
---|
| 347 | }
|
---|
| 348 |
|
---|
| 349 | sub getoutputdir
|
---|
| 350 | {
|
---|
| 351 | my $self = shift (@_);
|
---|
| 352 |
|
---|
| 353 | return $self->{'output_dir'};
|
---|
| 354 | }
|
---|
| 355 |
|
---|
| 356 | sub getoutputinfo
|
---|
| 357 | {
|
---|
| 358 | my $self = shift (@_);
|
---|
| 359 |
|
---|
| 360 | return $self->{'output_info'};
|
---|
| 361 | }
|
---|
| 362 |
|
---|
| 363 |
|
---|
| 364 | sub get_output_handler
|
---|
| 365 | {
|
---|
| 366 | my $self = shift (@_);
|
---|
| 367 |
|
---|
| 368 | my ($output_file_name) = @_;
|
---|
| 369 |
|
---|
[27500] | 370 | my $fh;
|
---|
| 371 | &FileUtils::openFileHandle($output_file_name, '>', \$fh) or die('Can not open a file handler for: ' . $output_file_name . "\n");
|
---|
| 372 |
|
---|
| 373 | return $fh;
|
---|
[12330] | 374 | }
|
---|
| 375 |
|
---|
| 376 | sub release_output_handler
|
---|
| 377 | {
|
---|
| 378 | my $self = shift (@_);
|
---|
| 379 | my ($outhandler) = @_;
|
---|
| 380 |
|
---|
| 381 | close($outhandler);
|
---|
| 382 |
|
---|
| 383 | }
|
---|
| 384 |
|
---|
| 385 | sub output_xml_header {
|
---|
| 386 | my $self = shift (@_);
|
---|
| 387 | my ($handle,$docroot,$nondoctype) = @_;
|
---|
| 388 |
|
---|
[23824] | 389 |
|
---|
| 390 | #print $handle '<?xml version="1.0" encoding="UTF-8" standalone="no"?>' . "\n";
|
---|
| 391 |
|
---|
| 392 | #For Dspace must be UTF in lower case
|
---|
| 393 | print $handle '<?xml version="1.0" encoding="utf-8" standalone="no"?>' . "\n";
|
---|
[12330] | 394 |
|
---|
| 395 | if (!defined $nondoctype){
|
---|
[22818] | 396 | my $doctype = (defined $docroot) ? $docroot : "Section";
|
---|
| 397 |
|
---|
| 398 | # Used to be '<!DOCTYPE Archive SYSTEM ...'
|
---|
| 399 |
|
---|
| 400 | print $handle "<!DOCTYPE $doctype SYSTEM \"http://greenstone.org/dtd/Archive/1.0/Archive.dtd\">\n";
|
---|
[12330] | 401 | }
|
---|
| 402 |
|
---|
| 403 | print $handle "<$docroot>\n" if defined $docroot;
|
---|
| 404 | }
|
---|
| 405 |
|
---|
| 406 | sub output_xml_footer {
|
---|
| 407 | my $self = shift (@_);
|
---|
| 408 | my ($handle,$docroot) = @_;
|
---|
| 409 | print $handle "</$docroot>\n" if defined $docroot;
|
---|
| 410 | }
|
---|
| 411 |
|
---|
[23824] | 412 |
|
---|
| 413 | sub output_general_xml_header
|
---|
| 414 | {
|
---|
| 415 | my $self = shift (@_);
|
---|
| 416 | my ($handle,$docroot,$opt_attributes,$opt_dtd, $opt_doctype) = @_;
|
---|
| 417 |
|
---|
| 418 | print $handle '<?xml version="1.0" encoding="utf-8" standalone="no"?>' . "\n";
|
---|
| 419 |
|
---|
| 420 | if (defined $opt_dtd) {
|
---|
| 421 | my $doctype = (defined $opt_doctype) ? $opt_doctype : $docroot;
|
---|
| 422 | print $handle "<!DOCTYPE $doctype SYSTEM \"$opt_dtd\">\n";
|
---|
| 423 | }
|
---|
| 424 |
|
---|
| 425 | if (defined $docroot) {
|
---|
| 426 | my $full_docroot = $docroot;
|
---|
| 427 | if (defined $opt_attributes) {
|
---|
| 428 | $full_docroot .= " $opt_attributes";
|
---|
| 429 | }
|
---|
| 430 |
|
---|
| 431 | print $handle "<$full_docroot>\n"
|
---|
| 432 | }
|
---|
| 433 | }
|
---|
| 434 |
|
---|
| 435 | sub output_general_xml_footer
|
---|
| 436 | {
|
---|
| 437 | output_xml_footer(@_);
|
---|
| 438 | }
|
---|
| 439 |
|
---|
| 440 |
|
---|
[12330] | 441 | sub process {
|
---|
| 442 | my $self = shift (@_);
|
---|
| 443 | my ($doc_obj) = @_;
|
---|
[12459] | 444 |
|
---|
[23939] | 445 | # for OAI purposes
|
---|
[12330] | 446 | $doc_obj->set_lastmodified();
|
---|
[23939] | 447 | $doc_obj->set_oailastmodified();
|
---|
[12330] | 448 |
|
---|
| 449 | if ($self->{'group_size'} > 1) {
|
---|
[12459] | 450 | $self->group_process ($doc_obj);
|
---|
[12330] | 451 | return;
|
---|
| 452 | }
|
---|
| 453 |
|
---|
| 454 | my $OID = $doc_obj->get_OID();
|
---|
| 455 | $OID = "NULL" unless defined $OID;
|
---|
| 456 |
|
---|
| 457 | my $top_section = $doc_obj->get_top_section();
|
---|
| 458 |
|
---|
| 459 | #get document's directory
|
---|
| 460 | my $doc_dir = $self->get_doc_dir ($OID, $doc_obj->get_source_filename());
|
---|
| 461 |
|
---|
| 462 | my $output_info = $self->{'output_info'};
|
---|
| 463 | return if (!defined $output_info);
|
---|
| 464 |
|
---|
| 465 | ##############################
|
---|
| 466 | # call subclass' saveas method
|
---|
| 467 | ##############################
|
---|
| 468 | $self->saveas($doc_obj,$doc_dir);
|
---|
[21564] | 469 | $self->archiveinf_db($doc_obj,$doc_dir);
|
---|
[17087] | 470 |
|
---|
[12330] | 471 | }
|
---|
| 472 |
|
---|
[12363] | 473 | sub store_output_info_reference {
|
---|
[12330] | 474 | my $self = shift (@_);
|
---|
| 475 | my ($doc_obj) = @_;
|
---|
| 476 |
|
---|
[12363] | 477 | my $output_info = $self->{'output_info'};
|
---|
| 478 | my $metaname = $self->{'sortmeta'};
|
---|
[27697] | 479 |
|
---|
[12363] | 480 | if (!defined $metaname || $metaname !~ /\S/) {
|
---|
[27697] | 481 | my $OID = $doc_obj->get_OID();
|
---|
| 482 | $output_info->add_info($OID,$self->{'short_doc_file'}, undef, "");
|
---|
[12363] | 483 | return;
|
---|
| 484 | }
|
---|
[27697] | 485 |
|
---|
| 486 | if ($metaname eq "OID") { # sort by OID
|
---|
| 487 | my $OID = $doc_obj->get_OID();
|
---|
| 488 | $output_info->add_info($OID,$self->{'short_doc_file'}, undef, $OID);
|
---|
| 489 | return;
|
---|
| 490 | }
|
---|
[12330] | 491 |
|
---|
[12363] | 492 | my $metadata = "";
|
---|
| 493 | my $top_section = $doc_obj->get_top_section();
|
---|
| 494 |
|
---|
| 495 | my @commameta_list = split(/,/, $metaname);
|
---|
| 496 | foreach my $cmn (@commameta_list) {
|
---|
| 497 | my $meta = $doc_obj->get_metadata_element($top_section, $cmn);
|
---|
| 498 | if ($meta) {
|
---|
| 499 | # do remove prefix/suffix - this will apply to all values
|
---|
| 500 | $meta =~ s/^$self->{'removeprefix'}// if defined $self->{'removeprefix'};
|
---|
| 501 | $meta =~ s/$self->{'removesuffix'}$// if defined $self->{'removesuffix'};
|
---|
| 502 | $meta = &sorttools::format_metadata_for_sorting($cmn, $meta, $doc_obj);
|
---|
| 503 | $metadata .= $meta if ($meta);
|
---|
| 504 | }
|
---|
[12330] | 505 | }
|
---|
| 506 |
|
---|
| 507 | # store reference in the output_info
|
---|
| 508 | $output_info->add_info($doc_obj->get_OID(),$self->{'short_doc_file'}, undef, $metadata);
|
---|
| 509 |
|
---|
| 510 | }
|
---|
| 511 |
|
---|
| 512 | sub group_process {
|
---|
| 513 |
|
---|
| 514 | my $self = shift (@_);
|
---|
| 515 | my ($doc_obj) = @_;
|
---|
| 516 |
|
---|
| 517 | my $OID = $doc_obj->get_OID();
|
---|
| 518 | $OID = "NULL" unless defined $OID;
|
---|
| 519 |
|
---|
| 520 | my $groupsize = $self->{'group_size'};
|
---|
| 521 | my $gs_count = $self->{'gs_count'};
|
---|
| 522 | my $open_new_file = (($gs_count % $groupsize)==0);
|
---|
| 523 | my $outhandle = $self->{'output_handle'};
|
---|
| 524 |
|
---|
| 525 | # opening a new file, or document has assoicated files => directory needed
|
---|
[12459] | 526 | if (($open_new_file) || (scalar(@{$doc_obj->get_assoc_files()})>0)) {
|
---|
| 527 |
|
---|
[12330] | 528 | # The directory the archive file (doc.xml) and all associated files
|
---|
| 529 | # should end up in
|
---|
| 530 | my $doc_dir;
|
---|
| 531 | # If we've determined its time for a new file, open it now
|
---|
| 532 | if ($open_new_file || !defined($self->{'gs_doc_dir'}))
|
---|
| 533 | {
|
---|
| 534 | $doc_dir = $self->get_doc_dir ($OID, $doc_obj->get_source_filename());
|
---|
| 535 | # only if opening new file
|
---|
| 536 | my $output_dir = $self->get_output_dir();
|
---|
[27505] | 537 | &FileUtils::makeAllDirectories($output_dir) unless &FileUtils::directoryExists($output_dir);
|
---|
[27306] | 538 | my $doc_file = &FileUtils::filenameConcatenate($output_dir, $doc_dir, "doc.xml");
|
---|
| 539 | my $short_doc_file = &FileUtils::filenameConcatenate($doc_dir, "doc.xml");
|
---|
[12459] | 540 |
|
---|
[12330] | 541 | if ($gs_count>0)
|
---|
| 542 | {
|
---|
| 543 | return if (!$self->close_file_output());
|
---|
| 544 | }
|
---|
| 545 |
|
---|
[17202] | 546 | open (GROUPPROCESS, ">$doc_file") or (print $outhandle "BasePlugout::group_process could not write to file $doc_file\n" and return);
|
---|
[12330] | 547 |
|
---|
| 548 |
|
---|
| 549 | $self->{'gs_filename'} = $doc_file;
|
---|
[12459] | 550 | $self->{'short_doc_file'} = $short_doc_file;
|
---|
[12330] | 551 | $self->{'gs_OID'} = $OID;
|
---|
| 552 | $self->{'gs_doc_dir'} = $doc_dir;
|
---|
| 553 |
|
---|
[17202] | 554 | $self->output_xml_header('BasePlugout::GROUPPROCESS','Archive');
|
---|
[12330] | 555 | }
|
---|
| 556 | # Otherwise load the same archive document directory used last time
|
---|
| 557 | else
|
---|
| 558 | {
|
---|
| 559 | $doc_dir = $self->{'gs_doc_dir'};
|
---|
| 560 | }
|
---|
| 561 |
|
---|
| 562 | # copy all the associated files, add this information as metadata
|
---|
| 563 | # to the document
|
---|
[13172] | 564 | print $outhandle "Writing associated files to $doc_dir\n";
|
---|
[12330] | 565 | $self->process_assoc_files ($doc_obj, $doc_dir);
|
---|
[19494] | 566 |
|
---|
| 567 | # look up 'gsdlmetafile' metadata and store that information
|
---|
| 568 | # explicitly in $doc_obj
|
---|
| 569 | $self->process_metafiles_metadata ($doc_obj);
|
---|
[12330] | 570 | }
|
---|
| 571 |
|
---|
| 572 | # save this document
|
---|
[13172] | 573 | my $section_text = &docprint::get_section_xml($doc_obj,$doc_obj->get_top_section());
|
---|
| 574 | print GROUPPROCESS $section_text;
|
---|
[12330] | 575 |
|
---|
| 576 | $self->{'gs_count'}++;
|
---|
| 577 | }
|
---|
| 578 |
|
---|
| 579 |
|
---|
| 580 | sub saveas {
|
---|
| 581 | my $self = shift (@_);
|
---|
| 582 |
|
---|
| 583 | die "Basplug::saveas function must be implemented in sub classes\n";
|
---|
| 584 | }
|
---|
| 585 |
|
---|
| 586 | sub get_doc_dir {
|
---|
| 587 | my $self = shift (@_);
|
---|
| 588 | my ($OID, $source_filename) = @_;
|
---|
| 589 |
|
---|
| 590 | my $working_dir = $self->get_output_dir();
|
---|
[19775] | 591 | my $working_info = $self->{'output_info'};
|
---|
[12330] | 592 | return if (!defined $working_info);
|
---|
| 593 |
|
---|
| 594 | my $doc_info = $working_info->get_info($OID);
|
---|
| 595 | my $doc_dir = '';
|
---|
| 596 |
|
---|
[16252] | 597 | if (defined $doc_info && scalar(@$doc_info) >= 1)
|
---|
| 598 | {
|
---|
| 599 | # This OID already has an archives directory, so use it again
|
---|
[12330] | 600 | $doc_dir = $doc_info->[0];
|
---|
| 601 | $doc_dir =~ s/\/?((doc(mets)?)|(dublin_core))\.xml(\.gz)?$//;
|
---|
[16252] | 602 | }
|
---|
| 603 | elsif ($self->{'keep_import_structure'})
|
---|
| 604 | {
|
---|
[12330] | 605 | $source_filename = &File::Basename::dirname($source_filename);
|
---|
| 606 | $source_filename =~ s/[\\\/]+/\//g;
|
---|
| 607 | $source_filename =~ s/\/$//;
|
---|
| 608 |
|
---|
| 609 | $doc_dir = substr($source_filename, length($ENV{'GSDLIMPORTDIR'}) + 1);
|
---|
[16252] | 610 | }
|
---|
[12330] | 611 |
|
---|
[16252] | 612 | # We have to use a new archives directory for this document
|
---|
| 613 | if ($doc_dir eq "")
|
---|
| 614 | {
|
---|
| 615 | $doc_dir = $self->get_new_doc_dir ($working_info, $working_dir, $OID);
|
---|
[12330] | 616 | }
|
---|
| 617 |
|
---|
[12603] | 618 | if (!defined $self->{'group'} || !$self->{'group'}){
|
---|
[27306] | 619 | &FileUtils::makeAllDirectories(&FileUtils::filenameConcatenate($working_dir, $doc_dir));
|
---|
[12603] | 620 | }
|
---|
[16252] | 621 |
|
---|
[12330] | 622 | return $doc_dir;
|
---|
| 623 | }
|
---|
| 624 |
|
---|
[27880] | 625 | # Before parallel building, this was the method that created the new doc dirs in archives
|
---|
| 626 | sub get_new_doc_dir_OLD {
|
---|
| 627 | my $self = shift (@_);
|
---|
| 628 | my($working_info,$working_dir,$OID) = @_;
|
---|
| 629 |
|
---|
| 630 |
|
---|
| 631 | my $doc_dir = "";
|
---|
| 632 | my $doc_dir_rest = $OID;
|
---|
| 633 |
|
---|
| 634 | # remove any \ and / from the OID
|
---|
| 635 | $doc_dir_rest =~ s/[\\\/]//g;
|
---|
| 636 |
|
---|
| 637 | # Remove ":" if we are on Windows OS, as otherwise they get confused with the drive letters
|
---|
| 638 | $doc_dir_rest =~ s/\://g if ($ENV{'GSDLOS'} =~ /^windows$/i);
|
---|
| 639 |
|
---|
| 640 | my $doc_dir_num = 0;
|
---|
| 641 |
|
---|
| 642 | do {
|
---|
| 643 | $doc_dir .= "/" if $doc_dir_num > 0;
|
---|
| 644 | my $pattern = '^(.{1,' . $self->{'subdir_split_length'} . '})';
|
---|
| 645 | if ($self->{'subdir_hash_prefix'})
|
---|
| 646 | {
|
---|
| 647 | $pattern = '^((HASH)?.{1,' . $self->{'subdir_split_length'} . '})';
|
---|
| 648 | }
|
---|
| 649 | #if ($doc_dir_rest =~ s/^(.{1,$limit})//) {
|
---|
| 650 | if ($doc_dir_rest =~ s/$pattern//i)
|
---|
| 651 | {
|
---|
| 652 | $doc_dir .= $1;
|
---|
| 653 | $doc_dir_num++;
|
---|
| 654 | }
|
---|
| 655 | } while ($doc_dir_rest ne "" &&
|
---|
| 656 | ((-d &FileUtils::filenameConcatenate($working_dir, "$doc_dir.dir")) ||
|
---|
| 657 | ($working_info->size() >= 1024 && $doc_dir_num < 2)));
|
---|
| 658 | my $i = 1;
|
---|
| 659 | my $doc_dir_base = $doc_dir;
|
---|
| 660 | while (-d &FileUtils::filenameConcatenate($working_dir, "$doc_dir.dir")) {
|
---|
| 661 | $doc_dir = "$doc_dir_base-$i";
|
---|
| 662 | $i++;
|
---|
| 663 | }
|
---|
| 664 |
|
---|
| 665 | return "$doc_dir.dir";
|
---|
| 666 | }
|
---|
| 667 |
|
---|
[27513] | 668 | ## @function get_new_doc_dir()
|
---|
| 669 | #
|
---|
| 670 | # Once a doc object is ready to write to disk (and hence has a nice OID),
|
---|
| 671 | # generate a unique subdirectory to write the information to.
|
---|
[28021] | 672 | #
|
---|
[27513] | 673 | # - create the directory as part of this call, to try and avoid race conditions
|
---|
| 674 | # found in parallel processing [jmt12]
|
---|
| 675 | #
|
---|
[28021] | 676 | # @todo figure out what the rule regarding $work_info->size() is meant to do
|
---|
| 677 | #
|
---|
| 678 | # @todo determine what $self->{'group'} is, and whether it should affect
|
---|
| 679 | # directory creation
|
---|
| 680 | #
|
---|
[27513] | 681 | sub get_new_doc_dir
|
---|
| 682 | {
|
---|
| 683 | my $self = shift (@_);
|
---|
| 684 | my($working_info,$working_dir,$OID) = @_;
|
---|
[22232] | 685 |
|
---|
[27513] | 686 | my $doc_dir = "";
|
---|
| 687 | my $doc_dir_rest = $OID;
|
---|
[22232] | 688 |
|
---|
[27513] | 689 | # remove any \ and / from the OID
|
---|
| 690 | $doc_dir_rest =~ s/[\\\/]//g;
|
---|
[22232] | 691 |
|
---|
[27513] | 692 | # Remove ":" if we are on Windows OS, as otherwise they get confused with the drive letters
|
---|
| 693 | if ($ENV{'GSDLOS'} =~ /^windows$/i)
|
---|
| 694 | {
|
---|
| 695 | $doc_dir_rest =~ s/\://g;
|
---|
| 696 | }
|
---|
[27504] | 697 |
|
---|
[27513] | 698 | # we generally create a unique directory by adding consequtive fragments of
|
---|
| 699 | # the document identifier (split by some predefined length - defaulting to
|
---|
| 700 | # 8) until we find a directory that doesn't yet exist. Note that directories
|
---|
| 701 | # that contain a document have a suffix ".dir" (whereas those that contain
|
---|
| 702 | # only subdirectories have no suffix).
|
---|
| 703 | my $doc_dir_num = 0; # how many directories deep we are
|
---|
| 704 | my $created_directory = 0; # have we successfully created a new directory
|
---|
| 705 | do
|
---|
| 706 | {
|
---|
| 707 | # (does this work on windows? - jmt12)
|
---|
| 708 | if ($doc_dir_num > 0)
|
---|
| 709 | {
|
---|
| 710 | $doc_dir .= '/';
|
---|
| 711 | }
|
---|
[28021] | 712 |
|
---|
[27513] | 713 | # the default matching pattern grabs the next 'subdir_split_length'
|
---|
| 714 | # characters of the OID to act as the next subdirectory
|
---|
| 715 | my $pattern = '^(.{1,' . $self->{'subdir_split_length'} . '})';
|
---|
[28021] | 716 |
|
---|
[27513] | 717 | # Do we count any "HASH" prefix against the split length limit?
|
---|
[28021] | 718 | print "[DEBUG] SubDir Hash Prefix: |" . $self->{'subdir_hash_prefix'} . "|\n";
|
---|
[27513] | 719 | if ($self->{'subdir_hash_prefix'} && $doc_dir_num == 0)
|
---|
| 720 | {
|
---|
| 721 | $pattern = '^((HASH)?.{1,' . $self->{'subdir_split_length'} . '})';
|
---|
| 722 | }
|
---|
[28021] | 723 |
|
---|
| 724 | print "[DEBUG] Pattern: |" . $pattern . "|\n";
|
---|
| 725 |
|
---|
| 726 |
|
---|
[27513] | 727 | # Note the use of 's' to both capture the next chuck of OID and to remove
|
---|
| 728 | # it from OID at the same time
|
---|
| 729 | if ($doc_dir_rest =~ s/$pattern//i)
|
---|
| 730 | {
|
---|
| 731 | $doc_dir .= $1;
|
---|
| 732 | $doc_dir_num++;
|
---|
[28021] | 733 |
|
---|
| 734 | my $full_doc_dir = &FileUtils::filenameConcatenate($working_dir, $doc_dir . '.dir');
|
---|
| 735 | if(!FileUtils::directoryExists($full_doc_dir))
|
---|
| 736 | {
|
---|
| 737 | &FileUtils::makeAllDirectories($full_doc_dir);
|
---|
| 738 | $created_directory = 1;
|
---|
| 739 | }
|
---|
| 740 |
|
---|
| 741 | ###rint STDERR "[DEBUG] BasePlugout::get_new_doc_dir(<working_info>, $working_dir, $oid)\n";
|
---|
| 742 | ###rint STDERR " - create directory: $full_doc_dir => $created_directory\n";
|
---|
| 743 | ###rint STDERR " - rest: $doc_dir_rest\n";
|
---|
| 744 | ###rint STDERR " - working_info->size(): " . $working_info->size() . " [ < 1024 ?]\n";
|
---|
| 745 | ###rint STDERR " - doc_dir_num: " . $doc_dir_num . "\n";
|
---|
[27513] | 746 | }
|
---|
| 747 | }
|
---|
| 748 | while ($doc_dir_rest ne '' && ($created_directory == 0 || ($working_info->size() >= 1024 && $doc_dir_num < 2)));
|
---|
[27504] | 749 |
|
---|
[27513] | 750 | # not unique yet? Add on an incremental suffix until we are unique
|
---|
| 751 | my $i = 1;
|
---|
| 752 | my $doc_dir_base = $doc_dir;
|
---|
| 753 | while ($created_directory == 0)
|
---|
| 754 | {
|
---|
| 755 | $doc_dir = $doc_dir_base . '-' . $i;
|
---|
| 756 | $created_directory = &FileUtils::makeAllDirectories(&FileUtils::filenameConcatenate($working_dir, $doc_dir . '.dir'));
|
---|
| 757 | $i++;
|
---|
| 758 | }
|
---|
| 759 |
|
---|
| 760 | # in theory this should never happen
|
---|
| 761 | if (!$created_directory)
|
---|
| 762 | {
|
---|
| 763 | die("Error! Failed to create directory for document: " . $doc_dir_base . "\n");
|
---|
| 764 | }
|
---|
| 765 |
|
---|
| 766 | return $doc_dir . '.dir';
|
---|
[12330] | 767 | }
|
---|
[27513] | 768 | ## get_new_doc_dir()
|
---|
[12330] | 769 |
|
---|
[27513] | 770 |
|
---|
[12330] | 771 | sub process_assoc_files {
|
---|
| 772 | my $self = shift (@_);
|
---|
| 773 | my ($doc_obj, $doc_dir, $handle) = @_;
|
---|
| 774 |
|
---|
| 775 | my $outhandle = $self->{'output_handle'};
|
---|
| 776 |
|
---|
| 777 | my $output_dir = $self->get_output_dir();
|
---|
| 778 | return if (!defined $output_dir);
|
---|
| 779 |
|
---|
[27505] | 780 | &FileUtils::makeAllDirectories($output_dir) unless &FileUtils::directoryExists($output_dir);
|
---|
[12330] | 781 |
|
---|
[27306] | 782 | my $working_dir = &FileUtils::filenameConcatenate($output_dir, $doc_dir);
|
---|
[27505] | 783 | &FileUtils::makeAllDirectories($working_dir) unless &FileUtils::directoryExists($working_dir);
|
---|
[12330] | 784 |
|
---|
| 785 | my @assoc_files = ();
|
---|
| 786 | my $filename;;
|
---|
| 787 |
|
---|
| 788 | my $source_filename = $doc_obj->get_source_filename();
|
---|
| 789 |
|
---|
| 790 | my $collect_dir = $ENV{'GSDLCOLLECTDIR'};
|
---|
| 791 |
|
---|
| 792 | if (defined $collect_dir) {
|
---|
| 793 | my $dirsep_regexp = &util::get_os_dirsep();
|
---|
| 794 |
|
---|
| 795 | if ($collect_dir !~ /$dirsep_regexp$/) {
|
---|
| 796 | $collect_dir .= &util::get_dirsep(); # ensure there is a slash at the end
|
---|
| 797 | }
|
---|
| 798 |
|
---|
| 799 | # This test is never going to fail on Windows -- is this a problem?
|
---|
| 800 |
|
---|
| 801 | if ($source_filename !~ /^$dirsep_regexp/) {
|
---|
[27306] | 802 | $source_filename = &FileUtils::filenameConcatenate($collect_dir, $source_filename);
|
---|
[12330] | 803 | }
|
---|
| 804 | }
|
---|
| 805 |
|
---|
| 806 |
|
---|
| 807 | # set the assocfile path (even if we have no assoc files - need this for lucene)
|
---|
| 808 | $doc_obj->set_utf8_metadata_element ($doc_obj->get_top_section(),
|
---|
| 809 | "assocfilepath",
|
---|
| 810 | "$doc_dir");
|
---|
| 811 | foreach my $assoc_file_rec (@{$doc_obj->get_assoc_files()}) {
|
---|
| 812 | my ($dir, $afile) = $assoc_file_rec->[1] =~ /^(.*?)([^\/\\]+)$/;
|
---|
| 813 | $dir = "" unless defined $dir;
|
---|
| 814 |
|
---|
[23363] | 815 | my $utf8_real_filename = $assoc_file_rec->[0];
|
---|
| 816 |
|
---|
[12330] | 817 | # for some reasons the image associate file has / before the full path
|
---|
[23363] | 818 | $utf8_real_filename =~ s/^\\(.*)/$1/i;
|
---|
| 819 |
|
---|
[23387] | 820 | ## my $real_filename = &util::utf8_to_real_filename($utf8_real_filename);
|
---|
| 821 | my $real_filename = $utf8_real_filename;
|
---|
| 822 | $real_filename = &util::downgrade_if_dos_filename($real_filename);
|
---|
[23363] | 823 |
|
---|
[27505] | 824 | if (&FileUtils::fileExists($real_filename)) {
|
---|
[12330] | 825 |
|
---|
[27306] | 826 | $filename = &FileUtils::filenameConcatenate($working_dir, $afile);
|
---|
[12330] | 827 |
|
---|
[27306] | 828 | &FileUtils::hardLink($real_filename, $filename, $self->{'verbosity'});
|
---|
| 829 |
|
---|
[12330] | 830 | $doc_obj->add_utf8_metadata ($doc_obj->get_top_section(),
|
---|
| 831 | "gsdlassocfile",
|
---|
| 832 | "$afile:$assoc_file_rec->[2]:$dir");
|
---|
[23363] | 833 | } elsif ($self->{'verbosity'} > 1) {
|
---|
[17202] | 834 | print $outhandle "BasePlugout::process couldn't copy the associated file " .
|
---|
[12330] | 835 | "$real_filename to $afile\n";
|
---|
| 836 | }
|
---|
| 837 | }
|
---|
| 838 | }
|
---|
| 839 |
|
---|
[17087] | 840 |
|
---|
[19494] | 841 | sub process_metafiles_metadata
|
---|
| 842 | {
|
---|
| 843 | my $self = shift (@_);
|
---|
| 844 | my ($doc_obj) = @_;
|
---|
| 845 |
|
---|
| 846 | my $top_section = $doc_obj->get_top_section();
|
---|
| 847 | my $metafiles = $doc_obj->get_metadata($top_section,"gsdlmetafile");
|
---|
| 848 |
|
---|
| 849 | foreach my $metafile_pair (@$metafiles) {
|
---|
[19516] | 850 | my ($full_metafile,$metafile) = split(/ : /,$metafile_pair);
|
---|
[19494] | 851 |
|
---|
| 852 | $doc_obj->metadata_file($full_metafile,$metafile);
|
---|
| 853 | }
|
---|
| 854 |
|
---|
| 855 | $doc_obj->delete_metadata($top_section,"gsdlmetafile");
|
---|
| 856 | }
|
---|
| 857 |
|
---|
| 858 | sub archiveinf_files_to_field
|
---|
| 859 | {
|
---|
| 860 | my $self = shift(@_);
|
---|
| 861 | my ($files,$field,$collect_dir,$oid_files,$reverse_lookups) = @_;
|
---|
| 862 |
|
---|
| 863 | foreach my $file_rec (@$files) {
|
---|
[20777] | 864 | my $real_filename = (ref $file_rec eq "ARRAY") ? $file_rec->[0] : $file_rec;
|
---|
| 865 | my $full_file = (ref $file_rec eq "ARRAY") ? $file_rec->[1] : $file_rec;
|
---|
[19494] | 866 | # for some reasons the image associate file has / before the full path
|
---|
| 867 | $real_filename =~ s/^\\(.*)/$1/i;
|
---|
| 868 |
|
---|
[23387] | 869 | my $raw_filename = &util::downgrade_if_dos_filename($real_filename);
|
---|
[23363] | 870 |
|
---|
[27505] | 871 | if (&FileUtils::fileExists($raw_filename)) {
|
---|
[23363] | 872 |
|
---|
[20763] | 873 | # if (defined $collect_dir) {
|
---|
| 874 | # my $collect_dir_re_safe = $collect_dir;
|
---|
[24829] | 875 | # $collect_dir_re_safe =~ s/\\/\\\\/g; # use &util::filename_to_regex()
|
---|
[20763] | 876 | # $collect_dir_re_safe =~ s/\./\\./g;##
|
---|
[19494] | 877 |
|
---|
[20763] | 878 | # $real_filename =~ s/^$collect_dir_re_safe//;
|
---|
| 879 | # }
|
---|
[22328] | 880 |
|
---|
[20801] | 881 | if (defined $reverse_lookups) {
|
---|
| 882 | $reverse_lookups->{$real_filename} = 1;
|
---|
| 883 | }
|
---|
[23363] | 884 | ### push(@{$oid_files->{$field}},$full_file);
|
---|
| 885 | push(@{$oid_files->{$field}},$raw_filename);
|
---|
[19494] | 886 | }
|
---|
| 887 | else {
|
---|
[19516] | 888 | print STDERR "Warning: archiveinf_files_to_field()\n $real_filename does not appear to be on the file system\n";
|
---|
[19494] | 889 | }
|
---|
| 890 | }
|
---|
| 891 | }
|
---|
| 892 |
|
---|
[21564] | 893 | sub archiveinf_db
|
---|
[17087] | 894 | {
|
---|
| 895 | my $self = shift (@_);
|
---|
| 896 | my ($doc_obj) = @_;
|
---|
| 897 |
|
---|
| 898 | my $verbosity = $self->{'verbosity'};
|
---|
| 899 |
|
---|
| 900 | my $collect_dir = $ENV{'GSDLCOLLECTDIR'};
|
---|
| 901 | if (defined $collect_dir) {
|
---|
| 902 | my $dirsep_regexp = &util::get_os_dirsep();
|
---|
| 903 |
|
---|
| 904 | if ($collect_dir !~ /$dirsep_regexp$/) {
|
---|
| 905 | # ensure there is a slash at the end
|
---|
| 906 | $collect_dir .= &util::get_dirsep();
|
---|
| 907 | }
|
---|
| 908 | }
|
---|
| 909 |
|
---|
| 910 | my $oid = $doc_obj->get_OID();
|
---|
[19829] | 911 | my $source_filename = $doc_obj->get_unmodified_source_filename();
|
---|
[18441] | 912 | my $working_info = $self->{'output_info'};
|
---|
| 913 | my $doc_info = $working_info->get_info($oid);
|
---|
[20651] | 914 |
|
---|
[20747] | 915 | my ($doc_file,$index_status,$sortmeta) = @$doc_info;
|
---|
[22328] | 916 | # doc_file is the path to the archive doc.xml. Make sure it has unix
|
---|
| 917 | # slashes, then if the collection is copied to linux, it can be built without reimport
|
---|
| 918 | $doc_file =~ s/\\/\//g;
|
---|
[18441] | 919 | my $oid_files = { 'doc-file' => $doc_file,
|
---|
| 920 | 'index-status' => $index_status,
|
---|
| 921 | 'src-file' => $source_filename,
|
---|
[20747] | 922 | 'sort-meta' => $sortmeta,
|
---|
[19775] | 923 | 'assoc-file' => [],
|
---|
| 924 | 'meta-file' => [] };
|
---|
[17087] | 925 |
|
---|
[19494] | 926 | my $reverse_lookups = { $source_filename => "1" };
|
---|
[17087] | 927 |
|
---|
| 928 |
|
---|
[20777] | 929 | $self->archiveinf_files_to_field($doc_obj->get_source_assoc_files(),"assoc-file",
|
---|
[19494] | 930 | $collect_dir,$oid_files,$reverse_lookups);
|
---|
[17087] | 931 |
|
---|
[17120] | 932 |
|
---|
[19775] | 933 | $self->archiveinf_files_to_field($doc_obj->get_meta_files(),"meta-file",
|
---|
[20801] | 934 | $collect_dir,$oid_files);
|
---|
[17087] | 935 |
|
---|
[21584] | 936 | # Get the infodbtype value for this collection from the arcinfo object
|
---|
| 937 | my $infodbtype = $self->{'output_info'}->{'infodbtype'};
|
---|
[17087] | 938 | my $output_dir = $self->{'output_dir'};
|
---|
| 939 |
|
---|
[21584] | 940 | my $doc_db = &dbutil::get_infodb_file_path($infodbtype, "archiveinf-doc", $output_dir);
|
---|
| 941 | my $src_db = &dbutil::get_infodb_file_path($infodbtype, "archiveinf-src", $output_dir);
|
---|
[17087] | 942 |
|
---|
[18528] | 943 | ##print STDERR "*** To set in db: \n\t$doc_db\n\t$oid\n\t$doc_db_text\n";
|
---|
[17087] | 944 |
|
---|
[27646] | 945 | if (!$self->{'no_rss'})
|
---|
| 946 | {
|
---|
| 947 | if (($oid_files->{'index-status'} eq "I") || ($oid_files->{'index-status'} eq "R")) {
|
---|
[24958] | 948 | my $top_section = $doc_obj->get_top_section();
|
---|
| 949 |
|
---|
[27071] | 950 | my $dc_titles = $doc_obj->get_metadata($top_section,"dc.Title");
|
---|
[24958] | 951 | my $dc_title = join("; ", @$dc_titles);
|
---|
| 952 |
|
---|
| 953 | if ($oid_files->{'index-status'} eq "R") {
|
---|
| 954 | $dc_title .= " (Updated)";
|
---|
| 955 | }
|
---|
| 956 |
|
---|
[28021] | 957 | my $rss_entry = "<item>\n";
|
---|
| 958 | $rss_entry .= " <title>$dc_title</title>\n";
|
---|
| 959 | $rss_entry .= " <link>_httpdomain__httpcollection_/document/$oid</link>\n";
|
---|
| 960 | $rss_entry .= "</item>";
|
---|
| 961 |
|
---|
| 962 | if (defined(&dbutil::supportsRSS) && &dbutil::supportsRSS($infodbtype))
|
---|
| 963 | {
|
---|
| 964 | my $rss_db = &dbutil::get_infodb_file_path($infodbtype, 'rss-items', $output_dir);
|
---|
| 965 | my $rss_db_fh = &dbutil::open_infodb_write_handle($infodbtype, $rss_db, 'append');
|
---|
| 966 | &dbutil::write_infodb_rawentry($infodbtype, $rss_db_fh, $oid, $rss_entry);
|
---|
| 967 | &dbutil::close_infodb_write_handle($infodbtype, $rss_db_fh);
|
---|
| 968 | }
|
---|
| 969 | else
|
---|
| 970 | {
|
---|
| 971 | my $rss_filename = &FileUtils::filenameConcatenate($output_dir,"rss-items.rdf");
|
---|
| 972 | my $rss_fh;
|
---|
| 973 | if (&FileUtils::openFileHandle($rss_filename, '>>', \$rss_fh))
|
---|
| 974 | {
|
---|
| 975 | print $rss_fh $rss_entry . "\n";
|
---|
[27511] | 976 | &FileUtils::closeFileHandle($rss_filename, \$rss_fh);
|
---|
[28021] | 977 | }
|
---|
| 978 | else
|
---|
| 979 | {
|
---|
[27646] | 980 | print STDERR "**** Failed to open $rss_filename\n$!\n";
|
---|
[28021] | 981 | }
|
---|
| 982 | }
|
---|
[27646] | 983 | }
|
---|
[24958] | 984 | }
|
---|
| 985 |
|
---|
[19775] | 986 | $oid_files->{'doc-file'} = [ $oid_files->{'doc-file'} ];
|
---|
| 987 | $oid_files->{'index-status'} = [ $oid_files->{'index-status'} ];
|
---|
| 988 | $oid_files->{'src-file'} = [ $oid_files->{'src-file'} ];
|
---|
[20747] | 989 | $oid_files->{'sort-meta'} = [ $oid_files->{'sort-meta'} ];
|
---|
[19775] | 990 |
|
---|
[21584] | 991 | my $infodb_file_handle = &dbutil::open_infodb_write_handle($infodbtype, $doc_db, "append");
|
---|
| 992 | &dbutil::write_infodb_entry($infodbtype, $infodb_file_handle, $oid, $oid_files);
|
---|
| 993 | &dbutil::close_infodb_write_handle($infodbtype, $infodb_file_handle);
|
---|
[19775] | 994 |
|
---|
[19494] | 995 | foreach my $rl (keys %$reverse_lookups) {
|
---|
[19775] | 996 | $working_info->add_reverseinfo($rl,$oid);
|
---|
[20801] | 997 | }
|
---|
| 998 |
|
---|
| 999 | # meta files not set in reverese entry, but need to set the metadata flag
|
---|
[20814] | 1000 | if (defined $doc_obj->get_meta_files()) {
|
---|
| 1001 | foreach my $meta_file_rec(@{$doc_obj->get_meta_files()}) {
|
---|
| 1002 | my $full_file = (ref $meta_file_rec eq "ARRAY") ? $meta_file_rec->[0] : $meta_file_rec;
|
---|
| 1003 | $working_info->set_meta_file_flag($full_file);
|
---|
| 1004 | }
|
---|
[20801] | 1005 | }
|
---|
[17087] | 1006 | }
|
---|
| 1007 |
|
---|
| 1008 |
|
---|
[12330] | 1009 | sub set_sortmeta {
|
---|
| 1010 | my $self = shift (@_);
|
---|
| 1011 | my ($sortmeta, $removeprefix, $removesuffix) = @_;
|
---|
| 1012 |
|
---|
| 1013 | $self->{'sortmeta'} = $sortmeta;
|
---|
| 1014 | if (defined ($removeprefix) && $removeprefix ) {
|
---|
| 1015 | $removeprefix =~ s/^\^//; # don't need a leading ^
|
---|
| 1016 | $self->{'removeprefix'} = $removeprefix;
|
---|
| 1017 | }
|
---|
| 1018 | if (defined ($removesuffix) && $removesuffix) {
|
---|
| 1019 | $removesuffix =~ s/\$$//; # don't need a trailing $
|
---|
| 1020 | $self->{'removesuffix'} = $removesuffix;
|
---|
| 1021 | }
|
---|
| 1022 | }
|
---|
| 1023 |
|
---|
| 1024 | sub open_xslt_pipe
|
---|
| 1025 | {
|
---|
| 1026 | my $self = shift @_;
|
---|
| 1027 | my ($output_file_name, $xslt_file)=@_;
|
---|
| 1028 |
|
---|
[27505] | 1029 | return unless defined $xslt_file and $xslt_file ne "" and &FileUtils::fileExists($xslt_file);
|
---|
[20320] | 1030 |
|
---|
[27306] | 1031 | my $java_class_path = &FileUtils::filenameConcatenate($ENV{'GSDLHOME'},"bin","java","ApplyXSLT.jar");
|
---|
[13013] | 1032 |
|
---|
[15140] | 1033 | my $mapping_file_path = "";
|
---|
| 1034 |
|
---|
[13225] | 1035 | if ($ENV{'GSDLOS'} eq "windows"){
|
---|
[27306] | 1036 | $java_class_path .=";".&FileUtils::filenameConcatenate($ENV{'GSDLHOME'},"bin","java","xalan.jar");
|
---|
[20320] | 1037 | # this file:/// bit didn't work for me on windows XP
|
---|
| 1038 | #$xslt_file = "\"file:///".$xslt_file."\"";
|
---|
| 1039 | #$mapping_file_path = "\"file:///";
|
---|
[13225] | 1040 | }
|
---|
| 1041 | else{
|
---|
[27306] | 1042 | $java_class_path .=":".&FileUtils::filenameConcatenate($ENV{'GSDLHOME'},"bin","java","xalan.jar");
|
---|
[13225] | 1043 | }
|
---|
| 1044 |
|
---|
| 1045 |
|
---|
[13013] | 1046 | $java_class_path = "\"".$java_class_path."\"";
|
---|
[13024] | 1047 |
|
---|
[20902] | 1048 | my $cmd = "| java -cp $java_class_path org.nzdl.gsdl.ApplyXSLT -t \"$xslt_file\" ";
|
---|
[12330] | 1049 |
|
---|
[12603] | 1050 | if (defined $self->{'mapping_file'} and $self->{'mapping_file'} ne ""){
|
---|
[13064] | 1051 | my $mapping_file_path = "\"".$self->{'mapping_file'}."\"";
|
---|
[14969] | 1052 | $cmd .= "-m $mapping_file_path";
|
---|
[12603] | 1053 | }
|
---|
[20320] | 1054 |
|
---|
[12330] | 1055 | open(*XMLWRITER, $cmd)
|
---|
| 1056 | or die "can't open pipe to xslt: $!";
|
---|
| 1057 |
|
---|
| 1058 |
|
---|
| 1059 | $self->{'xslt_writer'} = *XMLWRITER;
|
---|
| 1060 |
|
---|
| 1061 | print XMLWRITER "<?DocStart?>\n";
|
---|
| 1062 | print XMLWRITER "$output_file_name\n";
|
---|
[14969] | 1063 |
|
---|
[12330] | 1064 |
|
---|
| 1065 | }
|
---|
| 1066 |
|
---|
| 1067 |
|
---|
| 1068 | sub close_xslt_pipe
|
---|
| 1069 | {
|
---|
| 1070 | my $self = shift @_;
|
---|
| 1071 |
|
---|
| 1072 |
|
---|
| 1073 | return unless defined $self->{'xslt_writer'} ;
|
---|
| 1074 |
|
---|
| 1075 | my $xsltwriter = $self->{'xslt_writer'};
|
---|
| 1076 |
|
---|
| 1077 | print $xsltwriter "<?DocEnd?>\n";
|
---|
| 1078 | close($xsltwriter);
|
---|
[13024] | 1079 |
|
---|
| 1080 | undef $self->{'xslt_writer'};
|
---|
| 1081 |
|
---|
[12330] | 1082 | }
|
---|
| 1083 |
|
---|
| 1084 | sub close_file_output
|
---|
| 1085 | {
|
---|
| 1086 | my ($self) = @_;
|
---|
| 1087 |
|
---|
| 1088 | # make sure that the handle has been opened - it won't be if we failed
|
---|
| 1089 | # to import any documents...
|
---|
| 1090 | if (defined(fileno(GROUPPROCESS))) {
|
---|
| 1091 | $self->output_xml_footer('GROUPPROCESS','Archive');
|
---|
| 1092 | close GROUPPROCESS;
|
---|
| 1093 | }
|
---|
| 1094 |
|
---|
| 1095 | my $OID = $self->{'gs_OID'};
|
---|
| 1096 | my $short_doc_file = $self->{'short_doc_file'};
|
---|
| 1097 |
|
---|
| 1098 | if ($self->{'gzip'}) {
|
---|
| 1099 | my $doc_file = $self->{'gs_filename'};
|
---|
| 1100 | `gzip $doc_file`;
|
---|
| 1101 | $doc_file .= ".gz";
|
---|
| 1102 | $short_doc_file .= ".gz";
|
---|
[27505] | 1103 | if (!&FileUtils::fileExists($doc_file)) {
|
---|
[12330] | 1104 | my $outhandle = $self->{'output_handle'};
|
---|
| 1105 | print $outhandle "error while gzipping: $doc_file doesn't exist\n";
|
---|
| 1106 | return 0;
|
---|
| 1107 | }
|
---|
| 1108 | }
|
---|
| 1109 |
|
---|
| 1110 | # store reference in output_info
|
---|
| 1111 | my $output_info = $self->{'output_info'};
|
---|
| 1112 | return 0 if (!defined $output_info);
|
---|
| 1113 | $output_info->add_info($OID, $short_doc_file, undef, undef);
|
---|
| 1114 | return 1;
|
---|
| 1115 | }
|
---|
| 1116 |
|
---|
[13172] | 1117 |
|
---|
[12330] | 1118 | #the subclass should implement this method if is_group method could return 1.
|
---|
| 1119 | sub close_group_output{
|
---|
| 1120 | my $self = shift (@_);
|
---|
| 1121 | }
|
---|
| 1122 |
|
---|
| 1123 | sub is_group {
|
---|
| 1124 | my $self = shift (@_);
|
---|
| 1125 | return 0;
|
---|
| 1126 | }
|
---|
| 1127 |
|
---|
[13172] | 1128 | my $dc_set = { Title => 1,
|
---|
| 1129 | Creator => 1,
|
---|
| 1130 | Subject => 1,
|
---|
| 1131 | Description => 1,
|
---|
| 1132 | Publisher => 1,
|
---|
| 1133 | Contributor => 1,
|
---|
| 1134 | Date => 1,
|
---|
| 1135 | Type => 1,
|
---|
| 1136 | Format => 1,
|
---|
| 1137 | Identifier => 1,
|
---|
| 1138 | Source => 1,
|
---|
| 1139 | Language => 1,
|
---|
| 1140 | Relation => 1,
|
---|
| 1141 | Coverage => 1,
|
---|
| 1142 | Rights => 1};
|
---|
| 1143 |
|
---|
| 1144 |
|
---|
| 1145 | # returns an XML representation of the dublin core metadata
|
---|
[24404] | 1146 | # if dc meta is not found, try ex meta
|
---|
| 1147 | # This method is not used by the DSpacePlugout, which has its
|
---|
| 1148 | # own method to save its dc metadata
|
---|
[13172] | 1149 | sub get_dc_metadata {
|
---|
| 1150 | my $self = shift(@_);
|
---|
| 1151 | my ($doc_obj, $section, $version) = @_;
|
---|
| 1152 |
|
---|
| 1153 | # build up string of dublin core metadata
|
---|
| 1154 | $section="" unless defined $section;
|
---|
| 1155 |
|
---|
| 1156 | my $section_ptr = $doc_obj->_lookup_section($section);
|
---|
| 1157 | return "" unless defined $section_ptr;
|
---|
| 1158 |
|
---|
| 1159 |
|
---|
| 1160 | my $explicit_dc = {};
|
---|
[24404] | 1161 | my $explicit_ex_dc = {};
|
---|
[13172] | 1162 | my $explicit_ex = {};
|
---|
| 1163 |
|
---|
| 1164 | my $all_text="";
|
---|
[24404] | 1165 |
|
---|
| 1166 | # We want high quality dc metadata to go in first, so we store all the
|
---|
| 1167 | # assigned dc.* values first. Then, for all those dc metadata names in
|
---|
| 1168 | # the official dc set that are as yet unassigned, we look to see whether
|
---|
| 1169 | # embedded ex.dc.* metadata has defined some values for them. If not,
|
---|
| 1170 | # then for the same missing dc metadata names, we look in ex metadata.
|
---|
| 1171 |
|
---|
[13172] | 1172 | foreach my $data (@{$section_ptr->{'metadata'}}){
|
---|
| 1173 | my $escaped_value = &docprint::escape_text($data->[1]);
|
---|
| 1174 | if ($data->[0]=~ m/^dc\./) {
|
---|
| 1175 | $data->[0] =~ tr/[A-Z]/[a-z]/;
|
---|
| 1176 |
|
---|
| 1177 | $data->[0] =~ m/^dc\.(.*)/;
|
---|
| 1178 | my $dc_element = $1;
|
---|
| 1179 |
|
---|
| 1180 | if (!defined $explicit_dc->{$dc_element}) {
|
---|
| 1181 | $explicit_dc->{$dc_element} = [];
|
---|
| 1182 | }
|
---|
| 1183 | push(@{$explicit_dc->{$dc_element}},$escaped_value);
|
---|
| 1184 |
|
---|
| 1185 | if (defined $version && ($version eq "oai_dc")) {
|
---|
| 1186 | $all_text .= " <dc:$dc_element>$escaped_value</dc:$dc_element>\n";
|
---|
| 1187 | }
|
---|
| 1188 | else {
|
---|
| 1189 | # qualifier???
|
---|
| 1190 | $all_text .= ' <dcvalue element="'. $dc_element.'">'. $escaped_value. "</dcvalue>\n";
|
---|
| 1191 | }
|
---|
| 1192 |
|
---|
[24404] | 1193 | } elsif ($data->[0]=~ m/^ex\.dc\./) { # now look through ex.dc.* to fill in as yet unassigned fields in dc metaset
|
---|
| 1194 | $data->[0] =~ m/^ex\.dc\.(.*)/;
|
---|
| 1195 | my $ex_dc_element = $1;
|
---|
| 1196 | my $lc_ex_dc_element = lc($ex_dc_element);
|
---|
| 1197 |
|
---|
| 1198 | # only store the ex.dc value for this dc metaname if no dc.* was assigned for it
|
---|
| 1199 | if (defined $dc_set->{$ex_dc_element}) {
|
---|
| 1200 | if (!defined $explicit_ex_dc->{$lc_ex_dc_element}) {
|
---|
| 1201 | $explicit_ex_dc->{$lc_ex_dc_element} = [];
|
---|
| 1202 | }
|
---|
| 1203 | push(@{$explicit_ex_dc->{$lc_ex_dc_element}},$escaped_value);
|
---|
| 1204 | }
|
---|
| 1205 | }
|
---|
| 1206 | elsif (($data->[0] =~ m/^ex\./) || ($data->[0] !~ m/\./)) { # look through ex. meta (incl. meta without prefix)
|
---|
[13172] | 1207 | $data->[0] =~ m/^(ex\.)?(.*)/;
|
---|
[24404] | 1208 | my $ex_element = $2;
|
---|
[13172] | 1209 | my $lc_ex_element = lc($ex_element);
|
---|
| 1210 |
|
---|
| 1211 | if (defined $dc_set->{$ex_element}) {
|
---|
| 1212 | if (!defined $explicit_ex->{$lc_ex_element}) {
|
---|
| 1213 | $explicit_ex->{$lc_ex_element} = [];
|
---|
| 1214 | }
|
---|
| 1215 | push(@{$explicit_ex->{$lc_ex_element}},$escaped_value);
|
---|
| 1216 | }
|
---|
| 1217 | }
|
---|
| 1218 | }
|
---|
| 1219 |
|
---|
| 1220 | # go through dc_set and for any element *not* defined in explicit_dc
|
---|
[14932] | 1221 | # that does exist in explicit_ex, add it in as metadata
|
---|
[13172] | 1222 | foreach my $k ( keys %$dc_set ) {
|
---|
| 1223 | my $lc_k = lc($k);
|
---|
| 1224 |
|
---|
| 1225 | if (!defined $explicit_dc->{$lc_k}) {
|
---|
[24404] | 1226 | # try to find if ex.dc.* defines this dc.* meta,
|
---|
| 1227 | # if not, then look for whether there's an ex.* equivalent
|
---|
[13172] | 1228 |
|
---|
[24404] | 1229 | if (defined $explicit_ex_dc->{$lc_k}) {
|
---|
| 1230 | foreach my $v (@{$explicit_ex_dc->{$lc_k}}) {
|
---|
| 1231 | my $dc_element = $lc_k;
|
---|
| 1232 | my $escaped_value = $v;
|
---|
| 1233 |
|
---|
| 1234 | if (defined $version && ($version eq "oai_dc")) {
|
---|
| 1235 | $all_text .= " <dc:$dc_element>$escaped_value</dc:$dc_element>\n";
|
---|
| 1236 | }
|
---|
| 1237 | else {
|
---|
| 1238 | $all_text .= ' <dcvalue element="'. $dc_element.'">'. $escaped_value. "</dcvalue>\n";
|
---|
| 1239 | }
|
---|
| 1240 | }
|
---|
| 1241 | } elsif (defined $explicit_ex->{$lc_k}) {
|
---|
[13172] | 1242 | foreach my $v (@{$explicit_ex->{$lc_k}}) {
|
---|
| 1243 | my $dc_element = $lc_k;
|
---|
| 1244 | my $escaped_value = $v;
|
---|
| 1245 |
|
---|
| 1246 | if (defined $version && ($version eq "oai_dc")) {
|
---|
| 1247 | $all_text .= " <dc:$dc_element>$escaped_value</dc:$dc_element>\n";
|
---|
| 1248 | }
|
---|
| 1249 | else {
|
---|
| 1250 | $all_text .= ' <dcvalue element="'. $dc_element.'">'. $escaped_value. "</dcvalue>\n";
|
---|
| 1251 | }
|
---|
| 1252 | }
|
---|
| 1253 | }
|
---|
| 1254 | }
|
---|
| 1255 | }
|
---|
| 1256 |
|
---|
| 1257 | if ($all_text eq "") {
|
---|
| 1258 | $all_text .= " There is no Dublin Core metatdata in this document\n";
|
---|
| 1259 | }
|
---|
| 1260 | $all_text =~ s/[\x00-\x09\x0B\x0C\x0E-\x1F]//g;
|
---|
| 1261 |
|
---|
| 1262 | return $all_text;
|
---|
| 1263 | }
|
---|
| 1264 |
|
---|
| 1265 | # Build up dublin_core metadata. Priority given to dc.* over ex.*
|
---|
| 1266 | # This method was apparently added by Jeffrey and committed by Shaoqun.
|
---|
| 1267 | # But we don't know why it was added, so not using it anymore.
|
---|
| 1268 | sub new_get_dc_metadata {
|
---|
| 1269 |
|
---|
| 1270 | my $self = shift(@_);
|
---|
| 1271 | my ($doc_obj, $section, $version) = @_;
|
---|
| 1272 |
|
---|
| 1273 | # build up string of dublin core metadata
|
---|
| 1274 | $section="" unless defined $section;
|
---|
| 1275 |
|
---|
| 1276 | my $section_ptr=$doc_obj->_lookup_section($section);
|
---|
| 1277 | return "" unless defined $section_ptr;
|
---|
| 1278 |
|
---|
| 1279 | my $all_text = "";
|
---|
| 1280 | foreach my $data (@{$section_ptr->{'metadata'}}){
|
---|
| 1281 | my $escaped_value = &docprint::escape_text($data->[1]);
|
---|
| 1282 | my $dc_element = $data->[0];
|
---|
| 1283 |
|
---|
| 1284 | my @array = split('\.',$dc_element);
|
---|
| 1285 | my ($type,$name);
|
---|
| 1286 |
|
---|
| 1287 | if(defined $array[1])
|
---|
| 1288 | {
|
---|
| 1289 | $type = $array[0];
|
---|
| 1290 | $name = $array[1];
|
---|
| 1291 | }
|
---|
| 1292 | else
|
---|
| 1293 | {
|
---|
| 1294 | $type = "ex";
|
---|
| 1295 | $name = $array[0];
|
---|
| 1296 | }
|
---|
| 1297 |
|
---|
| 1298 | $all_text .= ' <Metadata Type="'. $type.'" Name="'.$name.'">'. $escaped_value. "</Metadata>\n";
|
---|
| 1299 | }
|
---|
| 1300 | return $all_text;
|
---|
| 1301 | }
|
---|
| 1302 |
|
---|
| 1303 |
|
---|
[12330] | 1304 | 1;
|
---|