1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # importfrom.pl --
|
---|
6 | # A component of the Greenstone digital library software
|
---|
7 | # from the New Zealand Digital Library Project at the
|
---|
8 | # University of Waikato, New Zealand.
|
---|
9 | #
|
---|
10 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful,
|
---|
18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | # GNU General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 |
|
---|
29 | # This program will contact the named DL server
|
---|
30 | # and export its metadata and (optionally) it documents.
|
---|
31 |
|
---|
32 | # Currently only designed for OAI exporting
|
---|
33 |
|
---|
34 | BEGIN {
|
---|
35 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
36 | die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
|
---|
37 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
38 | }
|
---|
39 |
|
---|
40 | use colcfg;
|
---|
41 | use util;
|
---|
42 | use parsargv;
|
---|
43 | use FileHandle;
|
---|
44 |
|
---|
45 | my $wgetopt = "";
|
---|
46 |
|
---|
47 | my $num_processed = 0;
|
---|
48 |
|
---|
49 | sub print_usage {
|
---|
50 | print STDERR "\n usage: $0 [options] collection-name\n\n";
|
---|
51 | print STDERR " options:\n";
|
---|
52 | print STDERR " -verbosity number 0=none, 3=lots\n";
|
---|
53 | print STDERR " -getdoc Also download if source document if present\n";
|
---|
54 | print STDERR " -importdir directory Where the original material lives\n";
|
---|
55 | print STDERR " -keepold Will not destroy the current contents of the\n";
|
---|
56 | print STDERR " import directory (the default)\n";
|
---|
57 | print STDERR " -removeold Will remove the old contents of the import\n";
|
---|
58 | print STDERR " directory -- use with care\n";
|
---|
59 | print STDERR " -gzip Use gzip to compress exported documents\n";
|
---|
60 | print STDERR " (don't forget to include ZIPPlugin in your plugin\n";
|
---|
61 | print STDERR " -maxdocs number Maximum number of documents to import\n";
|
---|
62 | print STDERR " -debug Print imported text to STDOUT\n";
|
---|
63 | print STDERR " -collectdir directory Collection directory (defaults to " .
|
---|
64 | &util::filename_cat ($ENV{'GSDLHOME'}, "collect") . ")\n";
|
---|
65 | print STDERR " -out Filename or handle to print output status to.\n";
|
---|
66 | print STDERR " The default is STDERR\n\n";
|
---|
67 | }
|
---|
68 |
|
---|
69 |
|
---|
70 |
|
---|
71 | sub xml_pretty_print
|
---|
72 | {
|
---|
73 | my ($text,$out,$verbosity) = @_;
|
---|
74 |
|
---|
75 | if (system("xmllint --version >/dev/null 2>&1")!=0) {
|
---|
76 | if ($verbosity>1) {
|
---|
77 | print STDERR "Warning: Unable to find xmllint for pretty printing.\n";
|
---|
78 | print STDERR " XML will be shown verbatim.\n\n";
|
---|
79 | }
|
---|
80 | print $out $text;
|
---|
81 | }
|
---|
82 | else {
|
---|
83 |
|
---|
84 | if (!open (PPOUT,"|xmllint --format -")) {
|
---|
85 | print STDERR "Error running xmllint: $!\n\n";
|
---|
86 | print $out $text;
|
---|
87 | return;
|
---|
88 | }
|
---|
89 |
|
---|
90 | print PPOUT $text;
|
---|
91 | close(PPOUT);
|
---|
92 | }
|
---|
93 | }
|
---|
94 |
|
---|
95 | sub wget_oai_url
|
---|
96 | {
|
---|
97 | my ($wget_cmd,$out,$verbosity) = @_;
|
---|
98 |
|
---|
99 | if ($verbosity>2) {
|
---|
100 | print $out " $wget_cmd\n";
|
---|
101 | }
|
---|
102 |
|
---|
103 | open (OAIIN,"$wget_cmd |")
|
---|
104 | || die "wget request failed: $!\n";
|
---|
105 |
|
---|
106 | my $li_record = "";
|
---|
107 |
|
---|
108 | my $line;
|
---|
109 | while (defined($line=<OAIIN>))
|
---|
110 | {
|
---|
111 | $li_record .= $line;
|
---|
112 | # print $out $line;
|
---|
113 | }
|
---|
114 |
|
---|
115 | close(OAIIN);
|
---|
116 |
|
---|
117 | return $li_record;
|
---|
118 | }
|
---|
119 |
|
---|
120 | sub oai_info
|
---|
121 | {
|
---|
122 | my ($base_url,$out,$verbosity) = @_;
|
---|
123 |
|
---|
124 | my $base_wget_cmd = "wget $wgetopt -q -O - \"$base_url?_OPTS_\"";
|
---|
125 |
|
---|
126 | my $identify = "verb=Identify";
|
---|
127 | my $list_sets = "verb=ListSets";
|
---|
128 | my $list_md_formats = "ListMetadataFormats"; # not currently used
|
---|
129 |
|
---|
130 | my $identify_cmd = $base_wget_cmd;
|
---|
131 | $identify_cmd =~ s/_OPTS_/$identify/;
|
---|
132 | print $out "-------------------\n";
|
---|
133 | print $out "General Information\n";
|
---|
134 | print $out "-------------------\n";
|
---|
135 | my $identify_text = wget_oai_url($identify_cmd,$out,$verbosity);
|
---|
136 | xml_pretty_print($identify_text,$out,$verbosity);
|
---|
137 |
|
---|
138 |
|
---|
139 | my $list_sets_cmd = $base_wget_cmd;
|
---|
140 | $list_sets_cmd =~ s/_OPTS_/$list_sets/;
|
---|
141 | print $out "-------------------\n";
|
---|
142 | print $out "Set Information\n";
|
---|
143 | print $out "-------------------\n";
|
---|
144 | my $list_sets_text = wget_oai_url($list_sets_cmd,$out,$verbosity);
|
---|
145 | xml_pretty_print($list_sets_text,$out,$verbosity);
|
---|
146 | }
|
---|
147 |
|
---|
148 |
|
---|
149 | sub get_oai_ids
|
---|
150 | {
|
---|
151 | my ($base_url, $set, $format, $out, $verbosity) = @_;
|
---|
152 |
|
---|
153 | print $out "Requesting list of identifiers ...\n";
|
---|
154 |
|
---|
155 | my $base_wget_cmd = "wget $wgetopt -q -O - \"$base_url?_OPTS_\"";
|
---|
156 | my $identifiers_cmd = $base_wget_cmd;
|
---|
157 |
|
---|
158 | my $identifiers_opts = "verb=ListIdentifiers&metadataPrefix=$format";
|
---|
159 |
|
---|
160 | if (defined $set && ($set ne "")) {
|
---|
161 | $identifiers_opts .= "&set=$set";
|
---|
162 | }
|
---|
163 |
|
---|
164 | $identifiers_cmd =~ s/_OPTS_/$identifiers_opts/;
|
---|
165 |
|
---|
166 | my $li_record = wget_oai_url($identifiers_cmd,$out,$verbosity);
|
---|
167 |
|
---|
168 | print $out "... Done.\n";
|
---|
169 |
|
---|
170 | return $li_record;
|
---|
171 | }
|
---|
172 |
|
---|
173 | sub parse_oai_ids
|
---|
174 | {
|
---|
175 | my ($li_record, $out, $verbosity) = @_;
|
---|
176 |
|
---|
177 | # extract identifier list
|
---|
178 | $li_record =~ s/^.*?<identifier>/<identifier>/s;
|
---|
179 | $li_record =~ s/^(.*<\/identifier>).*$/$1/s;
|
---|
180 |
|
---|
181 | my @ids = ();
|
---|
182 |
|
---|
183 | while ($li_record =~ m/<identifier>(.*?)<\/identifier>(.*)$/s)
|
---|
184 | {
|
---|
185 | $li_record = $2;
|
---|
186 | push(@ids,$1);
|
---|
187 | }
|
---|
188 |
|
---|
189 | return \@ids;
|
---|
190 | }
|
---|
191 |
|
---|
192 |
|
---|
193 | sub dir_file_split
|
---|
194 | {
|
---|
195 | my ($file) = @_;
|
---|
196 |
|
---|
197 | my @dirs = split("/",$file);
|
---|
198 | my $local_file = pop(@dirs);
|
---|
199 | my $sub_dirs = join("/",@dirs);
|
---|
200 |
|
---|
201 | return ($sub_dirs,$local_file);
|
---|
202 | }
|
---|
203 |
|
---|
204 | sub get_oai_document
|
---|
205 | {
|
---|
206 | my ($doc_url,$output_dir, $out) = @_;
|
---|
207 |
|
---|
208 | my ($id_dir,$id_fname) = dir_file_split($doc_url);
|
---|
209 |
|
---|
210 | print $out "Getting document $doc_url\n";
|
---|
211 |
|
---|
212 | &util::mk_dir($output_dir) if (!-e "$output_dir");
|
---|
213 |
|
---|
214 | my $full_id_fname = &util::filename_cat($output_dir,$id_fname);
|
---|
215 |
|
---|
216 | my $wget_cmd = "wget $wgetopt --quiet -O \"$full_id_fname\" \"$doc_url\"";
|
---|
217 |
|
---|
218 | if (system($wget_cmd)!=0) {
|
---|
219 | print STDERR "Error: failed to execute $wget_cmd\n";
|
---|
220 | return 0;
|
---|
221 | }
|
---|
222 |
|
---|
223 | return 1;
|
---|
224 | }
|
---|
225 |
|
---|
226 | sub get_oai_records
|
---|
227 | {
|
---|
228 | my ($base_url,$format, $ids,$output_dir, $get_id, $maxdocs, $out) = @_;
|
---|
229 |
|
---|
230 | my $doc_count = 0;
|
---|
231 |
|
---|
232 | my $i;
|
---|
233 | foreach $i ( @$ids )
|
---|
234 | {
|
---|
235 | # wget it;
|
---|
236 | my $url = "$base_url?verb=GetRecord&metadataPrefix=$format";
|
---|
237 | $url .= "&identifier=$i";
|
---|
238 | print $out "Downloading metadata record for $i\n";
|
---|
239 |
|
---|
240 | my $i_url = $i; #convert OAI set separators (:) to directory sep
|
---|
241 | $i_url =~ s/:/\//g;
|
---|
242 | my $file_i_url = "$output_dir/$i_url.oai";
|
---|
243 |
|
---|
244 | my $ds = &util::get_dirsep();
|
---|
245 | my $i_os = $i; #convert OAI set separators (:) to OS dir sep
|
---|
246 | $i_os =~ s/:/$ds/g;
|
---|
247 | my $file_i = &util::filename_cat($output_dir,"$i_os.oai");
|
---|
248 |
|
---|
249 | # obtain record
|
---|
250 | my $wget_cmd = "wget $wgetopt -q -O - \"$url\"";
|
---|
251 |
|
---|
252 | open (OAIIN,"$wget_cmd|")
|
---|
253 | || die "wget request failed: $!\n";
|
---|
254 | my $i_record = "";
|
---|
255 |
|
---|
256 | my $line;
|
---|
257 | while (defined($line=<OAIIN>))
|
---|
258 | {
|
---|
259 | $i_record .= $line;
|
---|
260 | }
|
---|
261 |
|
---|
262 | close(OAIIN);
|
---|
263 |
|
---|
264 | $num_processed++;
|
---|
265 |
|
---|
266 | # prepare subdirectory for record (if needed)
|
---|
267 | my ($i_dir,$unused) = dir_file_split($file_i_url);
|
---|
268 |
|
---|
269 | &util::mk_all_dir($i_dir);
|
---|
270 |
|
---|
271 | # look out for identifier tag in metadata section
|
---|
272 | if ($i_record =~ m/<metadata>(.*)<\/metadata>/s)
|
---|
273 | {
|
---|
274 | my $m_record = $1;
|
---|
275 |
|
---|
276 | if ($get_id)
|
---|
277 | {
|
---|
278 | my $got_doc = 0;
|
---|
279 |
|
---|
280 | my @url_matches = ($m_record =~ m/<(?:dc:)?identifier>(.*?)<\/(?:dc:)?identifier>/gs);
|
---|
281 | foreach my $doc_url (@url_matches)
|
---|
282 | {
|
---|
283 | if ($doc_url =~ m/^(http|ftp):/) {
|
---|
284 |
|
---|
285 | my $revised_doc_url = $doc_url;
|
---|
286 | ## $revised_doc_url =~ s/hdl\.handle\.net/mcgonagall.cs.waikato.ac.nz:8080\/dspace\/handle/;
|
---|
287 |
|
---|
288 | my $srcdocs_dir = &util::filename_cat($i_dir,"srcdocs");
|
---|
289 |
|
---|
290 | if (get_oai_document($revised_doc_url,$srcdocs_dir, $out)) {
|
---|
291 |
|
---|
292 | $got_doc = 1;
|
---|
293 | my ($id_dir,$id_fname) = dir_file_split($revised_doc_url);
|
---|
294 |
|
---|
295 | $i_record =~ s/<metadata>(.*?)<(dc:)?identifier>$doc_url<\/(dc:)?identifier>(.*?)<\/metadata>/<metadata>$1<OrigURL>$doc_url<\/OrigURL>\n <identifier>srcdocs\/$id_fname<\/identifier>$4<\/metadata>/s;
|
---|
296 |
|
---|
297 | }
|
---|
298 | }
|
---|
299 |
|
---|
300 | if (!$got_doc) {
|
---|
301 | $i_record =~ s/<metadata>(.*?)<(dc:)?identifier>$doc_url<\/(dc:)?identifier>(.*?)<\/metadata>/<metadata>$1<OrigIdentifier>$doc_url<\/OrigIdentifier>$4<\/metadata>/s;
|
---|
302 | }
|
---|
303 | }
|
---|
304 | }
|
---|
305 | }
|
---|
306 |
|
---|
307 | # save record
|
---|
308 | open (OAIOUT,">$file_i")
|
---|
309 | || die "Unable to save oai metadata record: $!\n";
|
---|
310 | print OAIOUT $i_record;
|
---|
311 | close(OAIOUT);
|
---|
312 |
|
---|
313 | $doc_count++;
|
---|
314 | last if ($doc_count == $maxdocs);
|
---|
315 | }
|
---|
316 | }
|
---|
317 |
|
---|
318 |
|
---|
319 | sub main {
|
---|
320 | my ($verbosity, $importdir, $keepold,
|
---|
321 | $getdoc, $acquire_info, $acquire_set,
|
---|
322 | $removeold, $gzip, $groupsize, $debug, $maxdocs, $collection,
|
---|
323 | $configfilename, $collectcfg,
|
---|
324 | $out, $collectdir);
|
---|
325 |
|
---|
326 | if (!parsargv::parse(\@ARGV,
|
---|
327 | 'verbosity/\d+/2', \$verbosity,
|
---|
328 | 'getdoc', \$getdoc,
|
---|
329 | 'info', \$acquire_info,
|
---|
330 | 'importdir/.*/', \$importdir,
|
---|
331 | 'keepold', \$keepold,
|
---|
332 | 'removeold', \$removeold,
|
---|
333 | 'gzip', \$gzip,
|
---|
334 | 'debug', \$debug,
|
---|
335 | 'maxdocs/^\-?\d+/-1', \$maxdocs,
|
---|
336 | 'collectdir/.*/', \$collectdir,
|
---|
337 | 'out/.*/STDERR', \$out)) {
|
---|
338 | &print_usage();
|
---|
339 | die "\n";
|
---|
340 | }
|
---|
341 |
|
---|
342 | my $close_out = 0;
|
---|
343 | if ($out !~ /^(STDERR|STDOUT)$/i) {
|
---|
344 | open (OUT, ">$out") || die "Couldn't open output file $out\n";
|
---|
345 | $out = 'import::OUT';
|
---|
346 | $close_out = 1;
|
---|
347 | }
|
---|
348 | $out->autoflush(1);
|
---|
349 |
|
---|
350 | # set removeold to false if it has been defined
|
---|
351 | $removeold = 0 if ($keepold);
|
---|
352 |
|
---|
353 | # get and check the collection name
|
---|
354 | if (($collection = &util::use_collection(@ARGV, $collectdir)) eq "") {
|
---|
355 | &print_usage();
|
---|
356 | die "\n";
|
---|
357 | }
|
---|
358 |
|
---|
359 |
|
---|
360 | # get acquire list
|
---|
361 | my $acquire = [];
|
---|
362 | $configfilename = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc", "collect.cfg");
|
---|
363 | if (-e $configfilename) {
|
---|
364 | $collectcfg = &colcfg::read_collect_cfg ($configfilename);
|
---|
365 | if (defined $collectcfg->{'acquire'}) {
|
---|
366 | $acquire = $collectcfg->{'acquire'};
|
---|
367 | }
|
---|
368 | if (defined $collectcfg->{'importdir'} && $importdir eq "") {
|
---|
369 | $importdir = $collectcfg->{'importdir'};
|
---|
370 | }
|
---|
371 | if (defined $collectcfg->{'removeold'}) {
|
---|
372 | if ($collectcfg->{'removeold'} =~ /^true$/i && !$keepold) {
|
---|
373 | $removeold = 1;
|
---|
374 | }
|
---|
375 | if ($collectcfg->{'removeold'} =~ /^false$/i && !$removeold) {
|
---|
376 | $removeold = 0;
|
---|
377 | }
|
---|
378 | }
|
---|
379 | } else {
|
---|
380 | die "Couldn't find the configuration file $configfilename\n";
|
---|
381 | }
|
---|
382 |
|
---|
383 | # fill in the default import directory if none
|
---|
384 | # were supplied, turn all \ into / and remove trailing /
|
---|
385 | $importdir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "import") if $importdir eq "";
|
---|
386 | $importdir =~ s/[\\\/]+/\//g;
|
---|
387 | $importdir =~ s/\/$//;
|
---|
388 |
|
---|
389 | # remove the old contents of the import directory if needed
|
---|
390 | if ($removeold && -e $importdir) {
|
---|
391 | print $out "Warning - removing current contents of the import directory\n";
|
---|
392 | print $out " in preparation for the acquire\n";
|
---|
393 | &util::rm_r ($importdir);
|
---|
394 | }
|
---|
395 |
|
---|
396 | my $e;
|
---|
397 | foreach $e ( @$acquire )
|
---|
398 | {
|
---|
399 | my $acquire_type = shift @$e;
|
---|
400 | my $acquire_src = undef;
|
---|
401 |
|
---|
402 | if ($acquire_type ne "OAI") {
|
---|
403 | print STDERR "Warning: $acquire_type not currently supported. Skipping.\n";
|
---|
404 | next;
|
---|
405 | }
|
---|
406 |
|
---|
407 | my $store_getdoc = $getdoc;
|
---|
408 |
|
---|
409 | if (!parsargv::parse($e,
|
---|
410 | 'getdoc', \$getdoc,
|
---|
411 | 'set/.*/', \$acquire_set,
|
---|
412 | 'format/.*/oai_dc', \$metadata_format,
|
---|
413 | 'src/.*/', \$acquire_src)) {
|
---|
414 | &print_usage();
|
---|
415 | die "\n";
|
---|
416 | }
|
---|
417 |
|
---|
418 | if (!defined $acquire_src) {
|
---|
419 | print STDERR "Warning: Not -src flag defined. Skipping.\n";
|
---|
420 | next;
|
---|
421 | }
|
---|
422 |
|
---|
423 | if (defined $acquire_info && ($acquire_info)) {
|
---|
424 | oai_info($acquire_src,$out,$verbosity);
|
---|
425 | next;
|
---|
426 | }
|
---|
427 |
|
---|
428 | print $out "$acquire_type Acquire: from $acquire_src\n";
|
---|
429 |
|
---|
430 | my $li_record = get_oai_ids($acquire_src,$acquire_set,$metadata_format,
|
---|
431 | $out,$verbosity);
|
---|
432 | my $ids = parse_oai_ids($li_record,$out,$verbosity);
|
---|
433 |
|
---|
434 | get_oai_records($acquire_src,$metadata_format, $ids,$importdir,
|
---|
435 | $getdoc, $maxdocs, $out);
|
---|
436 | $getdoc = $store_getdoc;
|
---|
437 | }
|
---|
438 |
|
---|
439 | print "\nNumber of documents processed: $num_processed\n";
|
---|
440 |
|
---|
441 | close OUT if $close_out;
|
---|
442 | }
|
---|
443 |
|
---|
444 |
|
---|
445 | &main();
|
---|
446 |
|
---|
447 |
|
---|
448 |
|
---|
449 |
|
---|
450 |
|
---|
451 |
|
---|
452 |
|
---|
453 |
|
---|