1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # getoai.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 |
|
---|
35 | BEGIN {
|
---|
36 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
37 | die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
|
---|
38 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
39 | }
|
---|
40 |
|
---|
41 | use colcfg;
|
---|
42 | use util;
|
---|
43 | use parsargv;
|
---|
44 | use FileHandle;
|
---|
45 |
|
---|
46 |
|
---|
47 | sub print_usage {
|
---|
48 | print STDERR "\n usage: $0 [options] collection-name\n\n";
|
---|
49 | print STDERR " options:\n";
|
---|
50 | print STDERR " -verbosity number 0=none, 3=lots\n";
|
---|
51 | print STDERR " -getid Also download if source document if present\n";
|
---|
52 | print STDERR " -importdir directory Where the original material lives\n";
|
---|
53 | print STDERR " -keepold Will not destroy the current contents of the\n";
|
---|
54 | print STDERR " import directory (the default)\n";
|
---|
55 | print STDERR " -removeold Will remove the old contents of the import\n";
|
---|
56 | print STDERR " directory -- use with care\n";
|
---|
57 | print STDERR " -gzip Use gzip to compress exported documents\n";
|
---|
58 | print STDERR " (don't forget to include ZIPPlug in your plugin\n";
|
---|
59 | print STDERR " -maxdocs number Maximum number of documents to import\n";
|
---|
60 | print STDERR " -debug Print imported text to STDOUT\n";
|
---|
61 | print STDERR " -collectdir directory Collection directory (defaults to " .
|
---|
62 | &util::filename_cat ($ENV{'GSDLHOME'}, "collect") . ")\n";
|
---|
63 | print STDERR " -out Filename or handle to print output status to.\n";
|
---|
64 | print STDERR " The default is STDERR\n\n";
|
---|
65 | }
|
---|
66 |
|
---|
67 |
|
---|
68 |
|
---|
69 |
|
---|
70 | sub print_usage_old
|
---|
71 | {
|
---|
72 | my ($prog_name) = @_;
|
---|
73 |
|
---|
74 | print STDERR "Usage: $prog_name OAI-base-URL\n";
|
---|
75 | exit 1;
|
---|
76 | }
|
---|
77 |
|
---|
78 | sub get_oai_ids
|
---|
79 | {
|
---|
80 | my ($base_url, $out) = @_;
|
---|
81 |
|
---|
82 | print $out "Requesting list of identifiers ...\n";
|
---|
83 |
|
---|
84 | open (OAIIN,"wget -q -O - $base_url?verb=ListIdentifiers|")
|
---|
85 | || die "wget request failed: $!\n";
|
---|
86 |
|
---|
87 | my $li_record = "";
|
---|
88 |
|
---|
89 | my $line;
|
---|
90 | while (defined($line=<OAIIN>))
|
---|
91 | {
|
---|
92 | $li_record .= $line;
|
---|
93 | # print $out $line;
|
---|
94 | }
|
---|
95 |
|
---|
96 | close(OAIIN);
|
---|
97 | print $out "... Done.\n";
|
---|
98 |
|
---|
99 | return $li_record;
|
---|
100 | }
|
---|
101 |
|
---|
102 | sub parse_oai_ids
|
---|
103 | {
|
---|
104 | my ($li_record, $out) = @_;
|
---|
105 |
|
---|
106 | # extract identifier list
|
---|
107 | $li_record =~ s/^.*?<identifier>/<identifier>/s;
|
---|
108 | $li_record =~ s/^(.*<\/identifier>).*$/$1/s;
|
---|
109 |
|
---|
110 | my @ids = ();
|
---|
111 |
|
---|
112 | while ($li_record =~ m/<identifier>(.*?)<\/identifier>(.*)$/s)
|
---|
113 | {
|
---|
114 | $li_record = $2;
|
---|
115 | push(@ids,$1);
|
---|
116 | }
|
---|
117 |
|
---|
118 | return \@ids;
|
---|
119 | }
|
---|
120 |
|
---|
121 |
|
---|
122 | sub dir_file_split
|
---|
123 | {
|
---|
124 | my ($file) = @_;
|
---|
125 |
|
---|
126 | my @dirs = split("/",$file);
|
---|
127 | my $local_file = pop(@dirs);
|
---|
128 | my $sub_dirs = join("/",@dirs);
|
---|
129 |
|
---|
130 | return ($sub_dirs,$local_file);
|
---|
131 | }
|
---|
132 |
|
---|
133 | sub get_oai_document
|
---|
134 | {
|
---|
135 | my ($doc_url,$output_dir, $out) = @_;
|
---|
136 |
|
---|
137 | my ($id_dir,$id_fname) = dir_file_split($doc_url);
|
---|
138 |
|
---|
139 | print $out "Getting document $doc_url\n";
|
---|
140 |
|
---|
141 | `mkdir $output_dir/srcdocs` if (!-e "$output_dir/srcdocs");
|
---|
142 |
|
---|
143 | my $wget_cmd = "wget -q -O $output_dir/srcdocs/$id_fname \"$doc_url\"";
|
---|
144 |
|
---|
145 | (system($wget_cmd)==0)
|
---|
146 | || print STDERR "Error: failed to execute $wget_cmd\n";
|
---|
147 |
|
---|
148 | }
|
---|
149 |
|
---|
150 | sub get_oai_records
|
---|
151 | {
|
---|
152 | my ($base_url,$ids,$output_dir, $get_id, $maxdocs, $out) = @_;
|
---|
153 |
|
---|
154 | my $doc_count = 0;
|
---|
155 |
|
---|
156 | my $i;
|
---|
157 | foreach $i ( @$ids )
|
---|
158 | {
|
---|
159 | # wget it;
|
---|
160 | my $url = "$base_url?verb=GetRecord&metadataPrefix=oai_dc";
|
---|
161 | $url .= "&identifier=$i";
|
---|
162 | print $out "Downloading metadata record for $i\n";
|
---|
163 |
|
---|
164 | my $file_i = "$output_dir/$i.oai";
|
---|
165 | $file_i =~ s/:/\//g;
|
---|
166 |
|
---|
167 | # obtain record
|
---|
168 | my $wget_cmd = "wget -q -O - \"$url\"";
|
---|
169 |
|
---|
170 | open (OAIIN,"$wget_cmd|")
|
---|
171 | || die "wget request failed: $!\n";
|
---|
172 | my $i_record = "";
|
---|
173 |
|
---|
174 | my $line;
|
---|
175 | while (defined($line=<OAIIN>))
|
---|
176 | {
|
---|
177 | $i_record .= $line;
|
---|
178 | }
|
---|
179 |
|
---|
180 | close(OAIIN);
|
---|
181 |
|
---|
182 | # prepare subdirectory for record (if needed)
|
---|
183 | my ($i_dir,$unused) = dir_file_split($file_i);
|
---|
184 | `mkdir -p $i_dir`;
|
---|
185 |
|
---|
186 | # look out for identifier tag in metadata section
|
---|
187 | if ($i_record =~ m/<metadata>(.*)<\/metadata>/s)
|
---|
188 | {
|
---|
189 | my $m_record = $1;
|
---|
190 |
|
---|
191 | if ($get_id)
|
---|
192 | {
|
---|
193 | if ($m_record =~ m/<identifier>(.*?)<\/identifier>/s)
|
---|
194 | {
|
---|
195 | my $doc_url = $1;
|
---|
196 | get_oai_document($doc_url,$i_dir, $out);
|
---|
197 |
|
---|
198 |
|
---|
199 | my ($id_dir,$id_fname) = dir_file_split($doc_url);
|
---|
200 |
|
---|
201 | $i_record =~ s/<metadata>(.*?)<identifier>$doc_url<\/identifier>(.*?)<\/metadata>/<metadata>$1<OrigURL>$doc_url<\/OrigURL><identifier>srcdocs\/$id_fname<\/identifier>$2<\/metadata>/s;
|
---|
202 | }
|
---|
203 | }
|
---|
204 | }
|
---|
205 |
|
---|
206 | # save record
|
---|
207 | open (OAIOUT,">$file_i")
|
---|
208 | || die "Unable to save oai metadata record: $!\n";
|
---|
209 | print OAIOUT $i_record;
|
---|
210 | close(OAIOUT);
|
---|
211 |
|
---|
212 | $doc_count++;
|
---|
213 | last if ($doc_count == $maxdocs);
|
---|
214 | }
|
---|
215 | }
|
---|
216 |
|
---|
217 |
|
---|
218 | sub main {
|
---|
219 | my ($verbosity, $importdir, $keepold,
|
---|
220 | $removeold, $gzip, $groupsize, $debug, $maxdocs, $collection,
|
---|
221 | $configfilename, $collectcfg,
|
---|
222 | $out, $collectdir);
|
---|
223 |
|
---|
224 | if (!parsargv::parse(\@ARGV,
|
---|
225 | 'verbosity/\d+/2', \$verbosity,
|
---|
226 | 'getid', \$getid,
|
---|
227 | 'importdir/.*/', \$importdir,
|
---|
228 | 'keepold', \$keepold,
|
---|
229 | 'removeold', \$removeold,
|
---|
230 | 'gzip', \$gzip,
|
---|
231 | 'debug', \$debug,
|
---|
232 | 'maxdocs/^\-?\d+/-1', \$maxdocs,
|
---|
233 | 'collectdir/.*/', \$collectdir,
|
---|
234 | 'out/.*/STDERR', \$out)) {
|
---|
235 | &print_usage();
|
---|
236 | die "\n";
|
---|
237 | }
|
---|
238 |
|
---|
239 | my $close_out = 0;
|
---|
240 | if ($out !~ /^(STDERR|STDOUT)$/i) {
|
---|
241 | open (OUT, ">$out") || die "Couldn't open output file $out\n";
|
---|
242 | $out = 'import::OUT';
|
---|
243 | $close_out = 1;
|
---|
244 | }
|
---|
245 | $out->autoflush(1);
|
---|
246 |
|
---|
247 | # set removeold to false if it has been defined
|
---|
248 | $removeold = 0 if ($keepold);
|
---|
249 |
|
---|
250 | # get and check the collection name
|
---|
251 | if (($collection = &util::use_collection(@ARGV, $collectdir)) eq "") {
|
---|
252 | &print_usage();
|
---|
253 | die "\n";
|
---|
254 | }
|
---|
255 |
|
---|
256 |
|
---|
257 | # get the list of export servers for this collection
|
---|
258 | my $export = [];
|
---|
259 | $configfilename = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc", "collect.cfg");
|
---|
260 | if (-e $configfilename) {
|
---|
261 | $collectcfg = &colcfg::read_collect_cfg ($configfilename);
|
---|
262 | if (defined $collectcfg->{'export'}) {
|
---|
263 | $export = $collectcfg->{'export'};
|
---|
264 | }
|
---|
265 | if (defined $collectcfg->{'importdir'} && $importdir eq "") {
|
---|
266 | $importdir = $collectcfg->{'importdir'};
|
---|
267 | }
|
---|
268 | if (defined $collectcfg->{'removeold'}) {
|
---|
269 | if ($collectcfg->{'removeold'} =~ /^true$/i && !$keepold) {
|
---|
270 | $removeold = 1;
|
---|
271 | }
|
---|
272 | if ($collectcfg->{'removeold'} =~ /^false$/i && !$removeold) {
|
---|
273 | $removeold = 0;
|
---|
274 | }
|
---|
275 | }
|
---|
276 | } else {
|
---|
277 | die "Couldn't find the configuration file $configfilename\n";
|
---|
278 | }
|
---|
279 |
|
---|
280 | # fill in the default import directory if none
|
---|
281 | # were supplied, turn all \ into / and remove trailing /
|
---|
282 | $importdir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "import") if $importdir eq "";
|
---|
283 | $importdir =~ s/[\\\/]+/\//g;
|
---|
284 | $importdir =~ s/\/$//;
|
---|
285 |
|
---|
286 | # remove the old contents of the import directory if needed
|
---|
287 | if ($removeold && -e $importdir) {
|
---|
288 | print $out "Warning - removing current contents of the import directory\n";
|
---|
289 | print $out " in preparation for the export\n";
|
---|
290 | sleep(5); # just in case...
|
---|
291 | &util::rm_r ($importdir);
|
---|
292 | }
|
---|
293 |
|
---|
294 | my $e;
|
---|
295 | foreach $e ( @$export )
|
---|
296 | {
|
---|
297 | print $out "Exporting from $e->[0]\n";
|
---|
298 |
|
---|
299 | my $base_url = $e->[0];
|
---|
300 |
|
---|
301 | my $li_record = get_oai_ids($base_url,$out);
|
---|
302 | my $ids = parse_oai_ids($li_record,$out);
|
---|
303 |
|
---|
304 | get_oai_records($base_url,$ids,$importdir, $getid, $maxdocs, $out);
|
---|
305 | }
|
---|
306 |
|
---|
307 | close OUT if $close_out;
|
---|
308 | }
|
---|
309 |
|
---|
310 |
|
---|
311 | &main();
|
---|
312 |
|
---|
313 |
|
---|
314 |
|
---|
315 |
|
---|
316 |
|
---|
317 |
|
---|
318 |
|
---|
319 |
|
---|