1 | /**
|
---|
2 | *#########################################################################
|
---|
3 | *
|
---|
4 | * A component of the Gatherer application, part of the Greenstone digital
|
---|
5 | * library suite from the New Zealand Digital Library Project at the
|
---|
6 | * University of Waikato, New Zealand.
|
---|
7 | *
|
---|
8 | * <BR><BR>
|
---|
9 | *
|
---|
10 | * Author: John Thompson, Greenstone Digital Library, University of Waikato
|
---|
11 | *
|
---|
12 | * <BR><BR>
|
---|
13 | *
|
---|
14 | * Copyright (C) 1999 New Zealand Digital Library Project
|
---|
15 | *
|
---|
16 | * <BR><BR>
|
---|
17 | *
|
---|
18 | * This program is free software; you can redistribute it and/or modify
|
---|
19 | * it under the terms of the GNU General Public License as published by
|
---|
20 | * the Free Software Foundation; either version 2 of the License, or
|
---|
21 | * (at your option) any later version.
|
---|
22 | *
|
---|
23 | * <BR><BR>
|
---|
24 | *
|
---|
25 | * This program is distributed in the hope that it will be useful,
|
---|
26 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
27 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
28 | * GNU General Public License for more details.
|
---|
29 | *
|
---|
30 | * <BR><BR>
|
---|
31 | *
|
---|
32 | * You should have received a copy of the GNU General Public License
|
---|
33 | * along with this program; if not, write to the Free Software
|
---|
34 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
35 | *########################################################################
|
---|
36 | */
|
---|
37 | package org.greenstone.gatherer.msm;
|
---|
38 |
|
---|
39 | import java.io.*;
|
---|
40 | import java.net.*;
|
---|
41 | import java.util.*;
|
---|
42 | import org.greenstone.gatherer.Configuration;
|
---|
43 | import org.greenstone.gatherer.Dictionary;
|
---|
44 | import org.greenstone.gatherer.Gatherer;
|
---|
45 | import org.greenstone.gatherer.collection.Collection;
|
---|
46 | import org.greenstone.gatherer.collection.CollectionManager;
|
---|
47 | import org.greenstone.gatherer.file.FileNode;
|
---|
48 | import org.greenstone.gatherer.msm.ElementWrapper;
|
---|
49 | import org.greenstone.gatherer.msm.MetadataSet;
|
---|
50 | import org.greenstone.gatherer.msm.MetadataSetManager;
|
---|
51 | import org.greenstone.gatherer.msm.MSMUtils;
|
---|
52 | import org.greenstone.gatherer.shell.GShell;
|
---|
53 | import org.greenstone.gatherer.shell.GShellProgressMonitor;
|
---|
54 | import org.greenstone.gatherer.util.StaticStrings;
|
---|
55 | import org.greenstone.gatherer.util.Utility;
|
---|
56 | import org.greenstone.gatherer.valuetree.GValueModel;
|
---|
57 | import org.greenstone.gatherer.valuetree.GValueNode;
|
---|
58 | import org.w3c.dom.*;
|
---|
59 |
|
---|
60 | public class GreenstoneArchiveParser {
|
---|
61 |
|
---|
62 | private GShell shell;
|
---|
63 |
|
---|
64 | static final String ignore_list[] = {"assocfilepath", "gsdl", "Identifier", "URL"}; //"Source",
|
---|
65 |
|
---|
66 | public GreenstoneArchiveParser(GShellProgressMonitor progress, GShell shell) {
|
---|
67 | // We can only extract metadata if an extracted metadata set exists in our collection.
|
---|
68 | if(Gatherer.c_man.msm.getSet(Utility.EXTRACTED_METADATA_NAMESPACE) != null) {
|
---|
69 | this.shell = shell;
|
---|
70 | // The very firstist thing we do is remove any existing extracted metadata
|
---|
71 | if(Gatherer.c_man != null && Gatherer.c_man.getCollection() != null) {
|
---|
72 | Gatherer.c_man.getCollection().getGDM().removeExtractedMetadata();
|
---|
73 | }
|
---|
74 |
|
---|
75 | // Determine the collection archive directory.
|
---|
76 | File archive_directory = new File(Gatherer.c_man.getCollectionArchive());
|
---|
77 | // For each of the hash coded directories within.
|
---|
78 | File document_directories[] = archive_directory.listFiles();
|
---|
79 | for(int i = 0; i < document_directories.length; i++) {
|
---|
80 | // Find the doc.xml file within
|
---|
81 | if(document_directories[i].isDirectory()) {
|
---|
82 | File document_file = new File(document_directories[i], "doc.xml");
|
---|
83 | // Then extract the metadata from it.
|
---|
84 | if(document_file.exists()) {
|
---|
85 | int count = extractMetadata(document_file);
|
---|
86 | // Display a pretty progress message.
|
---|
87 | String[] args = new String[2];
|
---|
88 | args[0] = document_directories[i].getName();
|
---|
89 | args[1] = String.valueOf(count);
|
---|
90 | shell.fireMessage(GShell.IMPORT, shell.typeAsString(GShell.IMPORT) + "> " + Dictionary.get("GShell.Extracted", args), GShell.OK, null);
|
---|
91 | args = null;
|
---|
92 | progress.increment();
|
---|
93 | }
|
---|
94 | }
|
---|
95 | }
|
---|
96 | }
|
---|
97 | // All done. Outta here like a bald man.
|
---|
98 | }
|
---|
99 |
|
---|
100 | private int extractMetadata(File file) {
|
---|
101 | int count = 0;
|
---|
102 | // Retrieve the DOM of the file.
|
---|
103 | Document document = Utility.parse(file, false);
|
---|
104 |
|
---|
105 | Gatherer.println("Parsed greenstone archive document: " + file.getAbsolutePath());
|
---|
106 | // If we successfully parsed the document, then it is time to search through the DOM for the Metadata tags.
|
---|
107 | if(document != null) {
|
---|
108 | String file_path = null;
|
---|
109 | Element archive_element = document.getDocumentElement();
|
---|
110 | // Retrieve all of the Metadata sections.
|
---|
111 | NodeList metadata_elements = archive_element.getElementsByTagName("Metadata");
|
---|
112 | // We first zip through the retrieved metadata, and if we encounter the element 'SourceSegment' - a sure sign this collection came from a bibliographic type file - we break out of extracted metadata parsing as no sense could be made of the data extracted anyway (plus we suffer a death of thirty-thousand pointy bits of metadata!)
|
---|
113 | for(int i = 0; i < metadata_elements.getLength(); i++) {
|
---|
114 | Element metadata_element = (Element) metadata_elements.item(i);
|
---|
115 | String name = metadata_element.getAttribute("name");
|
---|
116 | if(name.equalsIgnoreCase(StaticStrings.SOURCESEGMENT_VALUE)) {
|
---|
117 | return 0;
|
---|
118 | }
|
---|
119 | }
|
---|
120 | // Now for each Metadata entry retrieved...
|
---|
121 | for(int i = 0; i < metadata_elements.getLength(); i++) {
|
---|
122 | Element metadata_element = (Element) metadata_elements.item(i);
|
---|
123 | String name = metadata_element.getAttribute("name");
|
---|
124 | // There is also a special case when the metadata name is gsdlsourcefilename, as we use this to find the FileRecord we want to add metadata to.
|
---|
125 | if(name.equals("gsdlsourcefilename")) {
|
---|
126 | file_path = MSMUtils.getValue(metadata_element);
|
---|
127 | }
|
---|
128 | else {
|
---|
129 | // Check if its name starts with, or is equal to, one of the values in our ignore list, and if so ignore this metadata.
|
---|
130 | boolean ignore = false;
|
---|
131 | for(int j = 0; !ignore && j < ignore_list.length; j++) {
|
---|
132 | ignore = name.startsWith(ignore_list[j]);
|
---|
133 | }
|
---|
134 | // Otherwise ensure the metadata is present in our collection.
|
---|
135 | if(!ignore && file_path != null) {
|
---|
136 | // If we successfully retrieved a record we can continue.
|
---|
137 | if(file_path != null) {
|
---|
138 | // We now retrieve the appropriate element. If no such element exists we create a new one in the greenstone mds. Remember that no element in the greenstone mds has an associated value tree, so it is perfect for metadata elements with a small number of repeated values but where the values have no relation between files (such as encoding, where many files will be iso_8859_1, but if you change one you don't intend to change them all).
|
---|
139 | ElementWrapper element = Gatherer.c_man.msm.getElement(name);
|
---|
140 | if(element == null) {
|
---|
141 | MetadataSet extracted_mds = Gatherer.c_man.msm.getSet(Utility.EXTRACTED_METADATA_NAMESPACE);
|
---|
142 | if(extracted_mds != null) {
|
---|
143 | element = extracted_mds.addElement(name, Gatherer.config.getLanguage());
|
---|
144 | }
|
---|
145 | }
|
---|
146 | // If we successfully retrieved an element (and we should have) we can continue.
|
---|
147 | // WARNING!! There is one known exception - MARC records. Adding the extracted elements is all good, but adding the extracted metadata causes the whole thing to collapse in a pile of unhappy.
|
---|
148 | if(element != null && !file_path.endsWith(StaticStrings.MARC_EXTENSION) && (element.getNamespace().equals("") || element.getNamespace().equals(Utility.EXTRACTED_METADATA_NAMESPACE))) {
|
---|
149 | // Retrieve the metadata for the current file
|
---|
150 | File target_file = new File(file_path);
|
---|
151 | String value = "";
|
---|
152 | try {
|
---|
153 | value = Utility.decodeGreenstone(URLDecoder.decode(MSMUtils.getValue(metadata_element), "UTF-8"));
|
---|
154 | }
|
---|
155 | catch(UnsupportedEncodingException error) {
|
---|
156 | Gatherer.printStackTrace(error);
|
---|
157 | }
|
---|
158 | // If we successfully retrieved a value we can continue.
|
---|
159 | if(value != null) {
|
---|
160 | // Create a new metadata object.
|
---|
161 | GValueModel value_tree = Gatherer.c_man.msm.getValueTree(element);
|
---|
162 | GValueNode value_node = null;
|
---|
163 | if(value_tree != null) {
|
---|
164 | value_node = value_tree.getValue(value);
|
---|
165 | }
|
---|
166 | else {
|
---|
167 | value_node = new GValueNode(element.toString(), value);
|
---|
168 | }
|
---|
169 | Metadata metadata = new Metadata(element, value_node);
|
---|
170 | element.inc();
|
---|
171 | ///ystem.err.println("Adding extracted metadata: " + metadata);
|
---|
172 | Gatherer.c_man.getCollection().msm.fireMetadataChanged(new MSMEvent(this, System.currentTimeMillis(), target_file, null, metadata));
|
---|
173 | count++;
|
---|
174 | // All done. On to next metadata.
|
---|
175 | }
|
---|
176 | value = null;
|
---|
177 | target_file = null;
|
---|
178 | }
|
---|
179 | else {
|
---|
180 | Gatherer.println("Cannot retrieve metadata element " + name);
|
---|
181 | }
|
---|
182 | }
|
---|
183 | }
|
---|
184 | }
|
---|
185 | }
|
---|
186 | }
|
---|
187 | return count;
|
---|
188 | }
|
---|
189 |
|
---|
190 | static final String metadata_ignore_list[] = {"assocfilepath", "gsdl", "Identifier","URL"};
|
---|
191 |
|
---|
192 | static public ArrayList extractMetadataElements(File archive_directory) {
|
---|
193 | ArrayList extracted_metadata_elements = new ArrayList();
|
---|
194 | File document_directories[] = archive_directory.listFiles();
|
---|
195 | for(int i = 0; i < document_directories.length; i++) {
|
---|
196 | // Find the doc.xml file within
|
---|
197 | if(document_directories[i].isDirectory()) {
|
---|
198 | File document_file = new File(document_directories[i], "doc.xml");
|
---|
199 | // Then extract the metadata from it.
|
---|
200 | if(document_file.exists()) {
|
---|
201 | try {
|
---|
202 | Document document = Utility.parse(document_file, false);
|
---|
203 | // Retrieve all of the Metadata sections.
|
---|
204 | Element archive_element = document.getDocumentElement();
|
---|
205 | NodeList metadata_elements = archive_element.getElementsByTagName("Metadata");
|
---|
206 | // Now for each Metadata entry retrieved...
|
---|
207 | for(int j = 0; j < metadata_elements.getLength(); j++) {
|
---|
208 | Element metadata_element = (Element) metadata_elements.item(j);
|
---|
209 | String name = metadata_element.getAttribute("name");
|
---|
210 | // Check if its name starts with, or is equal to, one of the values in our ignore list, and if so ignore this metadata.
|
---|
211 | boolean ignore = false;
|
---|
212 | for(int k = 0; !ignore && k < metadata_ignore_list.length; k++) {
|
---|
213 | ignore = name.startsWith(metadata_ignore_list[k]);
|
---|
214 | }
|
---|
215 | if(!ignore && !extracted_metadata_elements.contains(name)) {
|
---|
216 | extracted_metadata_elements.add(name);
|
---|
217 | }
|
---|
218 | name = null;
|
---|
219 | metadata_element = null;
|
---|
220 | }
|
---|
221 | metadata_elements = null;
|
---|
222 | archive_element = null;
|
---|
223 | document = null;
|
---|
224 | }
|
---|
225 | catch (Exception error) {
|
---|
226 | Gatherer.printStackTrace(error);
|
---|
227 | }
|
---|
228 | }
|
---|
229 | document_file = null;
|
---|
230 | }
|
---|
231 | }
|
---|
232 | document_directories = null;
|
---|
233 | return extracted_metadata_elements;
|
---|
234 | }
|
---|
235 | }
|
---|