1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # IncrementalDocument.pm -- An object to encapsulate the Greenstone
|
---|
4 | # document retrieved from the info database.
|
---|
5 | #
|
---|
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) 2006 DL Consulting Ltd and 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 | package IncrementalDocument;
|
---|
28 |
|
---|
29 | use strict;
|
---|
30 |
|
---|
31 |
|
---|
32 | # /**
|
---|
33 | # */
|
---|
34 | sub new()
|
---|
35 | {
|
---|
36 | my ($class, $collection, $infodbtype, $oid) = @_;
|
---|
37 |
|
---|
38 | #rint STDERR "IncrementalDocument::new($collection, $infodbtype, $oid)\n";
|
---|
39 |
|
---|
40 | # Test the parameters
|
---|
41 | die ("Error! Can't create a document that doesn't belong to a collection!") unless $collection;
|
---|
42 | die ("Error! Can't create a document that doesn't have a unique id (OID)!") unless $oid;
|
---|
43 |
|
---|
44 | # Store the variables
|
---|
45 | my $self = {};
|
---|
46 |
|
---|
47 | # The collection this document object has been loaded from.
|
---|
48 | $self->{'collection'} = $collection;
|
---|
49 |
|
---|
50 | # The infodbtype for the collection
|
---|
51 | $self->{'infodbtype'} = $infodbtype;
|
---|
52 |
|
---|
53 | # An associative array of information retrieved from the info database
|
---|
54 | # which maps a key string to a nested associative array listing values.
|
---|
55 | $self->{'data'} = {};
|
---|
56 |
|
---|
57 | # The unique identifier of the document loaded
|
---|
58 | $self->{'oid'} = $oid;
|
---|
59 |
|
---|
60 | # Stores the order in which metadata keys where discovered/added.
|
---|
61 | $self->{'order'} = {};
|
---|
62 |
|
---|
63 | bless $self, $class;
|
---|
64 | return $self;
|
---|
65 | }
|
---|
66 | # /** new() **/
|
---|
67 |
|
---|
68 | # /**
|
---|
69 | # */
|
---|
70 | sub addMetadata()
|
---|
71 | {
|
---|
72 | my ($self, $key, $value, $internal) = @_;
|
---|
73 |
|
---|
74 | # Validate the arguments
|
---|
75 | die ("Error! Can't add a metadata value to a document without a valid key!") unless $key =~ /[\w]+/;
|
---|
76 | die ("Error! Can't add a metadata key to a document without a valid value!") unless $value =~ /[\w\d]+/;
|
---|
77 |
|
---|
78 | # Is this a new key that we haven't encountered before? If so ensure an
|
---|
79 | # array exists for its values, and record the order in which we encountered
|
---|
80 | # this key.
|
---|
81 | if (!defined($self->{'data'}->{$key}))
|
---|
82 | {
|
---|
83 | # Determine how many data keys we're already storing, so we can add the next
|
---|
84 | # one at the appropriate index
|
---|
85 | my $index = scalar(keys %{$self->{'order'}});
|
---|
86 | $self->{'order'}->{$index} = $key;
|
---|
87 | $self->{'data'}->{$key} = {};
|
---|
88 | }
|
---|
89 |
|
---|
90 | # Set the value of the associative path to 1.
|
---|
91 | $self->{'data'}->{$key}->{$value} = 1;
|
---|
92 | }
|
---|
93 | # /** addMetadata() **/
|
---|
94 |
|
---|
95 | # /** Retrieve all the metadata of this document as an array of pairs.
|
---|
96 | # *
|
---|
97 | # */
|
---|
98 | sub getAllMetadata()
|
---|
99 | {
|
---|
100 | my ($self) = @_;
|
---|
101 | my @all_metadata;
|
---|
102 |
|
---|
103 | print STDERR "IncrementalDocument.getAllMetadata()\n";
|
---|
104 |
|
---|
105 | my $key_count = scalar(keys %{$self->{'order'}});
|
---|
106 | for (my $i = 0; $i < $key_count; $i++)
|
---|
107 | {
|
---|
108 | my $key = $self->{'order'}->{$i};
|
---|
109 | # Check if this key has been set
|
---|
110 | if ($self->{'data'}->{$key})
|
---|
111 | {
|
---|
112 | # Note: there may be zero values left
|
---|
113 | foreach my $value (sort keys %{$self->{'data'}->{$key}})
|
---|
114 | {
|
---|
115 | if ($self->{'data'}->{$key}->{$value})
|
---|
116 | {
|
---|
117 | print STDERR "* Storing $key => $value\n";
|
---|
118 | push(@all_metadata, [$key, $value]);
|
---|
119 | }
|
---|
120 | }
|
---|
121 | }
|
---|
122 | }
|
---|
123 | print STDERR "Complete!\n";
|
---|
124 | return \@all_metadata;
|
---|
125 | }
|
---|
126 | # /** getAllMetadata() **/
|
---|
127 |
|
---|
128 | # /**
|
---|
129 | # */
|
---|
130 | sub getDocNum()
|
---|
131 | {
|
---|
132 | my ($self) = @_;
|
---|
133 | my $docnum = -1;
|
---|
134 | # Check the docnum path exists in the associated data
|
---|
135 | if(defined($self->{'data'}->{'docnum'}))
|
---|
136 | {
|
---|
137 | # Get the list of keys from that associative path
|
---|
138 | my @values = keys (%{$self->{'data'}->{'docnum'}});
|
---|
139 | # And since we know there will only ever be one value for docnum
|
---|
140 | $docnum = $values[0];
|
---|
141 | }
|
---|
142 | return $docnum;
|
---|
143 | }
|
---|
144 | # /** getDocNum() **/
|
---|
145 |
|
---|
146 | # /**
|
---|
147 | # */
|
---|
148 | sub loadDocument()
|
---|
149 | {
|
---|
150 | my ($self) = @_;
|
---|
151 | #rint STDERR "IncrementalDocument::loadDocument()\n";
|
---|
152 | # Load the raw text for the document object from the info database
|
---|
153 | my $collection = $self->{'collection'};
|
---|
154 | my $index_text_directory_path = &util::filename_cat($ENV{'GSDLHOME'}, "collect", $collection, "index", "text");
|
---|
155 | my $infodb_file_path = &dbutil::get_infodb_file_path($self->{'infodbtype'}, $collection, $index_text_directory_path);
|
---|
156 | my $text = &dbutil::read_infodb_rawentry($self->{'infodbtype'}, $infodb_file_path, $self->{'oid'});
|
---|
157 | # For each line in the raw text, extract the key (enclosed in angle
|
---|
158 | # brackets) and the value
|
---|
159 | $text =~ s/<([\w\d\.]+)>(.+?)\r?\n/&addMetadata($self, $1, $2, 1)/egs;
|
---|
160 | # Done
|
---|
161 | }
|
---|
162 | # /** loadDocument() **/
|
---|
163 |
|
---|
164 | # /** Locates and removes the given key/value mappings from this document
|
---|
165 | # * object.
|
---|
166 | # *
|
---|
167 | # * @param $self A reference to this IncrementalDocument object
|
---|
168 | # * @param $key The metadata key as a string
|
---|
169 | # * @param $value The obsolete metadata value as a string
|
---|
170 | # *
|
---|
171 | # * @author John Thompson, DL Consulting Ltd.
|
---|
172 | # */
|
---|
173 | sub removeMetadata()
|
---|
174 | {
|
---|
175 | my ($self, $key, $value) = @_;
|
---|
176 | # Ensure the value doesn't exist by simply setting to 0 the correct
|
---|
177 | # associative path
|
---|
178 | $self->{'data'}->{$key}->{$value} = 0;
|
---|
179 | }
|
---|
180 | # /*** removeMetadat() **/
|
---|
181 |
|
---|
182 | # /**
|
---|
183 | # */
|
---|
184 | sub saveDocument()
|
---|
185 | {
|
---|
186 | my ($self) = @_;
|
---|
187 | # Get a textual version of this object
|
---|
188 | my $text = $self->toString();
|
---|
189 |
|
---|
190 | # Now store the object in the info database
|
---|
191 | my $collection = $self->{'collection'};
|
---|
192 |
|
---|
193 | my $index_text_directory_path = &util::filename_cat($ENV{'GSDLHOME'}, "collect", $collection, "index", "text");
|
---|
194 | my $infodb_file_path = &dbutil::get_infodb_file_path($self->{'infodbtype'}, $collection, $index_text_directory_path);
|
---|
195 | my $infodb_file_handle = &dbutil::open_infodb_write_handle($self->{'infodbtype'}, $infodb_file_path, "append");
|
---|
196 | &dbutil::write_infodb_entry($self->{'infodbtype'}, $infodb_file_handle, $self->{'oid'}, &dbutil::convert_infodb_string_to_hash($text));
|
---|
197 | &dbutil::close_infodb_write_handle($self->{'infodbtype'}, $infodb_file_handle);
|
---|
198 |
|
---|
199 | # There is a little bit of extra complexity when saving an incremental
|
---|
200 | # document in that we should ensure that a reverse lookup-from DocNum or
|
---|
201 | # nodeID to Greenstone document hash-exists in the database.
|
---|
202 | my $doc_num = $self->getDocNum();
|
---|
203 | if($doc_num >= 0)
|
---|
204 | {
|
---|
205 | my $text = &dbutil::read_infodb_rawentry($self->{'infodbtype'}, $infodb_file_path, $doc_num);
|
---|
206 |
|
---|
207 | # If there is no reverse lookup, then add one now
|
---|
208 | if($text !~ /<section>/)
|
---|
209 | {
|
---|
210 | $infodb_file_handle = &dbutil::open_infodb_write_handle($self->{'infodbtype'}, $infodb_file_path, "append");
|
---|
211 | &dbutil::write_infodb_entry($self->{'infodbtype'}, $infodb_file_handle, $doc_num, &dbutil::convert_infodb_string_to_hash("<section>" . $self->{'oid'}));
|
---|
212 | &dbutil::close_infodb_write_handle($self->{'infodbtype'}, $infodb_file_handle);
|
---|
213 | }
|
---|
214 | }
|
---|
215 | # Done
|
---|
216 | #rint STDERR "Stored document:\n[" . $self->{'oid'} . "]\n$text\n";
|
---|
217 | }
|
---|
218 | # /** saveDocument() **/
|
---|
219 |
|
---|
220 | # /** Produces a textual representation of this object.
|
---|
221 | # *
|
---|
222 | # * @return A string which describes this incremental document object
|
---|
223 | # *
|
---|
224 | # * @author John Thompson, DL Consulting Ltd.
|
---|
225 | # */
|
---|
226 | sub toString()
|
---|
227 | {
|
---|
228 | my ($self) = @_;
|
---|
229 | my $text = "";
|
---|
230 |
|
---|
231 | my $key_count = scalar(keys %{$self->{'order'}});
|
---|
232 | for (my $i = 0; $i < $key_count; $i++)
|
---|
233 | {
|
---|
234 | my $key = $self->{'order'}->{$i};
|
---|
235 | # Check if this key has been set
|
---|
236 | if ($self->{'data'}->{$key})
|
---|
237 | {
|
---|
238 | # Note: there may be zero values left
|
---|
239 | foreach my $value (sort keys %{$self->{'data'}->{$key}})
|
---|
240 | {
|
---|
241 | if ($self->{'data'}->{$key}->{$value})
|
---|
242 | {
|
---|
243 | $text .= "<$key>$value\n";
|
---|
244 | }
|
---|
245 | }
|
---|
246 | }
|
---|
247 | }
|
---|
248 | return $text;
|
---|
249 | }
|
---|
250 | # /** toString() **/
|
---|
251 |
|
---|
252 | 1;
|
---|