1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # ArchivesInfPlugin.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 | # plugin which reads through an archives.inf (or GDBM equivalent,
|
---|
27 | # archiveinf-doc.gdb file (i.e. the file generated in the
|
---|
28 | # archives directory when an import is done), processing each file it
|
---|
29 | # finds
|
---|
30 |
|
---|
31 | package ArchivesInfPlugin;
|
---|
32 |
|
---|
33 | use util;
|
---|
34 | use doc;
|
---|
35 | use PrintInfo;
|
---|
36 | use plugin;
|
---|
37 | use arcinfo;
|
---|
38 | use gsprintf;
|
---|
39 |
|
---|
40 | use strict;
|
---|
41 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
42 |
|
---|
43 | BEGIN {
|
---|
44 | @ArchivesInfPlugin::ISA = ('PrintInfo');
|
---|
45 | }
|
---|
46 |
|
---|
47 | my $arguments = [
|
---|
48 | ];
|
---|
49 |
|
---|
50 | my $options = { 'name' => "ArchivesInfPlugin",
|
---|
51 | 'desc' => "{ArchivesInfPlugin.desc}",
|
---|
52 | 'abstract' => "no",
|
---|
53 | 'inherits' => "yes" };
|
---|
54 |
|
---|
55 | sub gsprintf
|
---|
56 | {
|
---|
57 | return &gsprintf::gsprintf(@_);
|
---|
58 | }
|
---|
59 |
|
---|
60 | sub new {
|
---|
61 | my ($class) = shift (@_);
|
---|
62 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
63 | push(@$pluginlist, $class);
|
---|
64 |
|
---|
65 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
66 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
67 |
|
---|
68 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists);
|
---|
69 |
|
---|
70 | return bless $self, $class;
|
---|
71 | }
|
---|
72 |
|
---|
73 | # called once, at the start of processing
|
---|
74 | sub init {
|
---|
75 | my $self = shift (@_);
|
---|
76 | my ($verbosity, $outhandle, $failhandle) = @_;
|
---|
77 |
|
---|
78 | # verbosity is passed through from the processor
|
---|
79 | $self->{'verbosity'} = $verbosity;
|
---|
80 |
|
---|
81 | # as are the outhandle and failhandle
|
---|
82 | $self->{'outhandle'} = $outhandle if defined $outhandle;
|
---|
83 | $self->{'failhandle'} = $failhandle;
|
---|
84 |
|
---|
85 | }
|
---|
86 |
|
---|
87 | sub deinit {
|
---|
88 | my ($self) = @_;
|
---|
89 |
|
---|
90 | my $archive_info = $self->{'archive_info'};
|
---|
91 | my $verbosity = $self->{'verbosity'};
|
---|
92 | my $outhandle = $self->{'outhandle'};
|
---|
93 |
|
---|
94 | if (defined $archive_info) {
|
---|
95 | my $archive_info_filename = $self->{'archive_info_filename'};
|
---|
96 |
|
---|
97 | my $file_list = $archive_info->get_file_list();
|
---|
98 |
|
---|
99 | foreach my $subfile (@$file_list) {
|
---|
100 | my $doc_oid = $subfile->[1];
|
---|
101 |
|
---|
102 | my $index_status = $archive_info->get_status_info($doc_oid);
|
---|
103 |
|
---|
104 | if ($index_status eq "D") {
|
---|
105 | # delete
|
---|
106 | $archive_info->delete_info($doc_oid);
|
---|
107 | &GDBMUtils::gdbmDatabaseRemove($archive_info_filename,$doc_oid);
|
---|
108 |
|
---|
109 | my $doc_file = $subfile->[0];
|
---|
110 | my $base_dir =$self->{'base_dir'};
|
---|
111 |
|
---|
112 | my $doc_filename = &util::filename_cat($base_dir,$doc_file);
|
---|
113 |
|
---|
114 | my ($doc_tailname, $doc_dirname, $suffix)
|
---|
115 | = File::Basename::fileparse($doc_filename, "\\.[^\\.]+\$");
|
---|
116 |
|
---|
117 | print $outhandle "Removing $doc_dirname\n" if ($verbosity>2);
|
---|
118 |
|
---|
119 | &util::rm_r($doc_dirname);
|
---|
120 |
|
---|
121 |
|
---|
122 | }
|
---|
123 | elsif ($index_status =~ m/^(I|R)$/) {
|
---|
124 | # mark as "been indexed"
|
---|
125 | $archive_info->set_status_info($doc_oid,"B");
|
---|
126 | }
|
---|
127 | }
|
---|
128 |
|
---|
129 | $archive_info->save_info($archive_info_filename);
|
---|
130 | }
|
---|
131 | }
|
---|
132 |
|
---|
133 | # called at the beginning of each plugin pass (import has one, buildin has many)
|
---|
134 | sub begin {
|
---|
135 | my $self = shift (@_);
|
---|
136 | my ($pluginfo, $base_dir, $processor, $maxdocs) = @_;
|
---|
137 |
|
---|
138 | $self->{'base_dir'} = $base_dir;
|
---|
139 | }
|
---|
140 |
|
---|
141 | # called at the end of each plugin pass
|
---|
142 | sub end {
|
---|
143 | my ($self) = shift (@_);
|
---|
144 |
|
---|
145 | }
|
---|
146 |
|
---|
147 | # called if we are doing incremental building
|
---|
148 | sub set_incremental {
|
---|
149 | my $self = shift(@_);
|
---|
150 | my ($incremental) = @_;
|
---|
151 |
|
---|
152 | $self->{'incremental'} = $incremental;
|
---|
153 | }
|
---|
154 |
|
---|
155 | # return 1 if this class might recurse using $pluginfo
|
---|
156 | sub is_recursive {
|
---|
157 | my $self = shift (@_);
|
---|
158 |
|
---|
159 | return 1;
|
---|
160 | }
|
---|
161 |
|
---|
162 |
|
---|
163 | sub compile_stats {
|
---|
164 | my $self = shift(@_);
|
---|
165 | my ($stats) = @_;
|
---|
166 | }
|
---|
167 |
|
---|
168 | # We don't do metadata_read
|
---|
169 | sub metadata_read {
|
---|
170 | my $self = shift (@_);
|
---|
171 | my ($pluginfo, $base_dir, $file, $block_hash, $extrametakeys, $extrametadata, $processor, $maxdocs, $gli) = @_;
|
---|
172 |
|
---|
173 | return undef;
|
---|
174 | }
|
---|
175 |
|
---|
176 | sub file_block_read {
|
---|
177 |
|
---|
178 | my $self = shift (@_);
|
---|
179 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $gli) = @_;
|
---|
180 |
|
---|
181 | if ($file eq "OIDcount") {
|
---|
182 | my ($filename_full_path, $filename_no_path)
|
---|
183 | = &util::get_full_filenames($base_dir, $file);
|
---|
184 | $block_hash->{'file_blocks'}->{$filename_full_path} = 1;
|
---|
185 | return 1;
|
---|
186 | }
|
---|
187 |
|
---|
188 | # otherwise, we don't do any file blocking
|
---|
189 |
|
---|
190 | return undef;
|
---|
191 | }
|
---|
192 |
|
---|
193 |
|
---|
194 | # return number of files processed, undef if can't process
|
---|
195 | # Note that $base_dir might be "" and that $file might
|
---|
196 | # include directories
|
---|
197 | sub read {
|
---|
198 | my $self = shift (@_);
|
---|
199 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs,$total_count, $gli) = @_;
|
---|
200 | my $outhandle = $self->{'outhandle'};
|
---|
201 |
|
---|
202 | my $count = 0;
|
---|
203 |
|
---|
204 | # see if this has a archives information file within it
|
---|
205 | ## my $archive_info_filename = &util::filename_cat($base_dir,$file,"archives.inf");
|
---|
206 |
|
---|
207 | my $doc_db = "archiveinf-doc.gdb";
|
---|
208 | my $archive_info_filename = &util::filename_cat($base_dir,$file,$doc_db);
|
---|
209 |
|
---|
210 | if (-e $archive_info_filename) {
|
---|
211 |
|
---|
212 | # found an archives.inf file
|
---|
213 | &gsprintf($outhandle, "ArchivesInfPlugin: {common.processing} $archive_info_filename\n") if $self->{'verbosity'} > 1;
|
---|
214 |
|
---|
215 | # read in the archives information file
|
---|
216 | my $archive_info = new arcinfo ();
|
---|
217 | $self->{'archive_info'} = $archive_info;
|
---|
218 | $self->{'archive_info_filename'} = $archive_info_filename;
|
---|
219 |
|
---|
220 | $archive_info->load_info ($archive_info_filename);
|
---|
221 |
|
---|
222 | my $file_list = $archive_info->get_file_list();
|
---|
223 |
|
---|
224 | # process each file
|
---|
225 | foreach my $subfile (@$file_list) {
|
---|
226 |
|
---|
227 | last if ($maxdocs != -1 && ($total_count + $count) >= $maxdocs);
|
---|
228 |
|
---|
229 | my $tmp = &util::filename_cat ($file, $subfile->[0]);
|
---|
230 | next if $tmp eq $file;
|
---|
231 |
|
---|
232 | my $doc_oid = $subfile->[1];
|
---|
233 | my $index_status = $archive_info->get_status_info($doc_oid);
|
---|
234 |
|
---|
235 | my $curr_mode = $processor->get_mode();
|
---|
236 | my $new_mode = $curr_mode;
|
---|
237 |
|
---|
238 | # Start by assuming we want to process the file...
|
---|
239 | my $process_file = 1;
|
---|
240 |
|
---|
241 | # ...unless the build processor is incremental capable and -incremental was specified, in which case we need to check its index_status flag
|
---|
242 | if ($processor->is_incremental_capable() && $self->{'incremental'})
|
---|
243 | {
|
---|
244 | # Check to see if the file needs indexing
|
---|
245 | if ($index_status eq "B")
|
---|
246 | {
|
---|
247 | # Don't process this file as it has already been indexed
|
---|
248 | $process_file = 0;
|
---|
249 | }
|
---|
250 | elsif ($index_status eq "D") {
|
---|
251 | # Need to be delete it from the index.
|
---|
252 | $new_mode = $curr_mode."delete";
|
---|
253 | $process_file = 1;
|
---|
254 | }
|
---|
255 | elsif ($index_status eq "R") {
|
---|
256 | # Need to be reindexed/replaced
|
---|
257 | $new_mode = $curr_mode."reindex";
|
---|
258 |
|
---|
259 | $process_file = 1;
|
---|
260 | }
|
---|
261 | }
|
---|
262 | # ... or we're being asked to delete it (in which case skip it)
|
---|
263 | elsif ($index_status eq "D") {
|
---|
264 | # Non-incremental Delete
|
---|
265 | # It's already been deleted from the archives directory
|
---|
266 | # (done during import.pl)
|
---|
267 | # => All we need to do here is not process it
|
---|
268 |
|
---|
269 | $process_file = 0;
|
---|
270 | }
|
---|
271 |
|
---|
272 | if (!$processor->is_incremental_capable() && $self->{'incremental'}) {
|
---|
273 | # Nag feature
|
---|
274 | if (!defined $self->{'incremental-warning'}) {
|
---|
275 | print $outhandle "\n";
|
---|
276 | print $outhandle "Warning: command-line option '-incremental' used with *non-incremental*\n";
|
---|
277 | print $outhandle " processor '", ref $processor, "'. Some conflicts may arise.\n";
|
---|
278 | print $outhandle "\n";
|
---|
279 | sleep 10;
|
---|
280 | $self->{'incremental-warning'} = 1;
|
---|
281 | }
|
---|
282 | }
|
---|
283 |
|
---|
284 | if ($process_file) {
|
---|
285 | # note: metadata is not carried on to the next level
|
---|
286 |
|
---|
287 | $processor->set_mode($new_mode) if ($new_mode ne $curr_mode);
|
---|
288 |
|
---|
289 | $count += &plugin::read ($pluginfo, $base_dir, $tmp, $block_hash, {}, $processor, $maxdocs, ($total_count+$count), $gli);
|
---|
290 |
|
---|
291 | $processor->set_mode($curr_mode) if ($new_mode ne $curr_mode);
|
---|
292 | }
|
---|
293 | }
|
---|
294 |
|
---|
295 | return $count;
|
---|
296 | }
|
---|
297 |
|
---|
298 |
|
---|
299 | # wasn't an archives directory, someone else will have to process it
|
---|
300 | return undef;
|
---|
301 | }
|
---|
302 |
|
---|
303 | 1;
|
---|