1
|
/**
|
2
|
* '$RCSfile$'
|
3
|
* Copyright: 2009 University of New Mexico and the
|
4
|
* Regents of the University of California
|
5
|
*
|
6
|
* '$Author: costa $'
|
7
|
* '$Date: 2009-07-27 17:47:44 -0400 (Mon, 27 Jul 2009) $'
|
8
|
* '$Revision: 4999 $'
|
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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
23
|
*
|
24
|
* Additional Copyright 2006 OCLC, Online Computer Library Center
|
25
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
26
|
* you may not use this file except in compliance with the License.
|
27
|
* You may obtain a copy of the License at
|
28
|
*
|
29
|
* http://www.apache.org/licenses/LICENSE-2.0
|
30
|
*
|
31
|
* Unless required by applicable law or agreed to in writing, software
|
32
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
33
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
34
|
* See the License for the specific language governing permissions and
|
35
|
* limitations under the License.
|
36
|
*/
|
37
|
|
38
|
package edu.ucsb.nceas.metacat.oaipmh.harvester;
|
39
|
|
40
|
import java.io.FileNotFoundException;
|
41
|
import java.io.IOException;
|
42
|
import java.io.InputStream;
|
43
|
import java.io.StringWriter;
|
44
|
import java.net.HttpURLConnection;
|
45
|
import java.net.URL;
|
46
|
import java.util.Date;
|
47
|
import java.util.HashMap;
|
48
|
import java.util.StringTokenizer;
|
49
|
import java.util.zip.GZIPInputStream;
|
50
|
import java.util.zip.InflaterInputStream;
|
51
|
import java.util.zip.ZipInputStream;
|
52
|
|
53
|
import javax.xml.parsers.DocumentBuilder;
|
54
|
import javax.xml.parsers.DocumentBuilderFactory;
|
55
|
import javax.xml.parsers.ParserConfigurationException;
|
56
|
import javax.xml.transform.OutputKeys;
|
57
|
import javax.xml.transform.Result;
|
58
|
import javax.xml.transform.Source;
|
59
|
import javax.xml.transform.Transformer;
|
60
|
import javax.xml.transform.TransformerException;
|
61
|
import javax.xml.transform.TransformerFactory;
|
62
|
import javax.xml.transform.dom.DOMSource;
|
63
|
import javax.xml.transform.stream.StreamResult;
|
64
|
|
65
|
import org.apache.log4j.Logger;
|
66
|
import org.apache.xpath.XPathAPI;
|
67
|
import org.w3c.dom.DOMImplementation;
|
68
|
import org.w3c.dom.Document;
|
69
|
import org.w3c.dom.Element;
|
70
|
import org.w3c.dom.NodeList;
|
71
|
import org.xml.sax.InputSource;
|
72
|
import org.xml.sax.SAXException;
|
73
|
|
74
|
|
75
|
/**
|
76
|
* HarvesterVerb is the parent class for each of the OAI verbs.
|
77
|
*
|
78
|
* @author Duane Costa, University of New Mexico, LTER Network Office
|
79
|
* @author Jeffrey A. Young, OCLC Online Computer Library Center
|
80
|
*/
|
81
|
public abstract class HarvesterVerb {
|
82
|
|
83
|
/* Class variables */
|
84
|
|
85
|
private static Logger logger = Logger.getLogger(HarvesterVerb.class);
|
86
|
|
87
|
public static final String SCHEMA_LOCATION_V2_0 =
|
88
|
"http://www.openarchives.org/OAI/2.0/ " +
|
89
|
"http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd";
|
90
|
|
91
|
private static HashMap<Thread, DocumentBuilder> builderMap =
|
92
|
new HashMap<Thread, DocumentBuilder>();
|
93
|
private static DocumentBuilderFactory documentBuilderFactory = null;
|
94
|
private static Element namespaceElement = null;
|
95
|
private static TransformerFactory transformerFactory =
|
96
|
TransformerFactory.newInstance();
|
97
|
|
98
|
|
99
|
/* Instance variables */
|
100
|
|
101
|
private Document document = null;
|
102
|
private String schemaLocation = null;
|
103
|
private String requestURL = null;
|
104
|
|
105
|
|
106
|
/* Constructors */
|
107
|
|
108
|
/**
|
109
|
* Mock object creator (for unit testing purposes)
|
110
|
*/
|
111
|
public HarvesterVerb() {
|
112
|
}
|
113
|
|
114
|
|
115
|
/**
|
116
|
* Performs the OAI request
|
117
|
*
|
118
|
* @param requestURL
|
119
|
* @throws IOException
|
120
|
* @throws ParserConfigurationException
|
121
|
* @throws SAXException
|
122
|
* @throws TransformerException
|
123
|
*/
|
124
|
public HarvesterVerb(String requestURL) throws IOException,
|
125
|
ParserConfigurationException, SAXException, TransformerException {
|
126
|
this.requestURL = requestURL;
|
127
|
}
|
128
|
|
129
|
|
130
|
/* Static initialization code */
|
131
|
|
132
|
static {
|
133
|
try {
|
134
|
/* Load DOM Document */
|
135
|
documentBuilderFactory = DocumentBuilderFactory.newInstance();
|
136
|
documentBuilderFactory.setNamespaceAware(true);
|
137
|
Thread thread = Thread.currentThread();
|
138
|
DocumentBuilder builder = documentBuilderFactory.newDocumentBuilder();
|
139
|
builderMap.put(thread, builder);
|
140
|
|
141
|
DOMImplementation impl = builder.getDOMImplementation();
|
142
|
|
143
|
Document namespaceHolder = impl.createDocument(
|
144
|
"http://www.oclc.org/research/software/oai/harvester",
|
145
|
"harvester:namespaceHolder",
|
146
|
null
|
147
|
);
|
148
|
|
149
|
namespaceElement = namespaceHolder.getDocumentElement();
|
150
|
|
151
|
namespaceElement.setAttributeNS(
|
152
|
"http://www.w3.org/2000/xmlns/",
|
153
|
"xmlns:harvester",
|
154
|
"http://www.oclc.org/research/software/oai/harvester"
|
155
|
);
|
156
|
|
157
|
namespaceElement.setAttributeNS(
|
158
|
"http://www.w3.org/2000/xmlns/",
|
159
|
"xmlns:xsi",
|
160
|
"http://www.w3.org/2001/XMLSchema-instance"
|
161
|
);
|
162
|
|
163
|
namespaceElement.setAttributeNS(
|
164
|
"http://www.w3.org/2000/xmlns/",
|
165
|
"xmlns:oai20",
|
166
|
"http://www.openarchives.org/OAI/2.0/"
|
167
|
);
|
168
|
}
|
169
|
catch (Exception e) {
|
170
|
e.printStackTrace();
|
171
|
}
|
172
|
|
173
|
}
|
174
|
|
175
|
|
176
|
/* Instance methods */
|
177
|
|
178
|
/* Primary OAI namespaces */
|
179
|
|
180
|
/**
|
181
|
* Get the OAI response as a DOM object
|
182
|
*
|
183
|
* @return the DOM for the OAI response
|
184
|
*/
|
185
|
public Document getDocument() {
|
186
|
return document;
|
187
|
}
|
188
|
|
189
|
|
190
|
/**
|
191
|
* Get the OAI errors
|
192
|
*
|
193
|
* @return a NodeList of /oai:OAI-PMH/oai:error elements
|
194
|
* @throws TransformerException
|
195
|
*/
|
196
|
public NodeList getErrors() throws TransformerException {
|
197
|
if (SCHEMA_LOCATION_V2_0.equals(getSchemaLocation())) {
|
198
|
return getNodeList("/oai20:OAI-PMH/oai20:error");
|
199
|
}
|
200
|
else {
|
201
|
return null;
|
202
|
}
|
203
|
}
|
204
|
|
205
|
|
206
|
/**
|
207
|
* Get a NodeList containing the nodes in the response DOM for the specified
|
208
|
* xpath
|
209
|
*
|
210
|
* @param xpath
|
211
|
* @return the NodeList for the xpath into the response DOM
|
212
|
* @throws TransformerException
|
213
|
*/
|
214
|
public NodeList getNodeList(String xpath) throws TransformerException {
|
215
|
Document document = getDocument();
|
216
|
return XPathAPI.selectNodeList(document, xpath, namespaceElement);
|
217
|
}
|
218
|
|
219
|
|
220
|
/**
|
221
|
* Get the OAI request URL for this response
|
222
|
*
|
223
|
* @return the OAI request URL as a String
|
224
|
*/
|
225
|
public String getRequestURL() {
|
226
|
return requestURL;
|
227
|
}
|
228
|
|
229
|
|
230
|
/**
|
231
|
* Get the xsi:schemaLocation for the OAI response
|
232
|
*
|
233
|
* @return the xsi:schemaLocation value
|
234
|
*/
|
235
|
public String getSchemaLocation() {
|
236
|
return schemaLocation;
|
237
|
}
|
238
|
|
239
|
|
240
|
/**
|
241
|
* Get the String value for the given XPath location in the response DOM
|
242
|
*
|
243
|
* @param xpath
|
244
|
* @return a String containing the value of the XPath location.
|
245
|
* @throws TransformerException
|
246
|
*/
|
247
|
public String getSingleString(String xpath) throws TransformerException {
|
248
|
Document document = getDocument();
|
249
|
org.apache.xpath.objects.XObject xobject;
|
250
|
|
251
|
xobject = XPathAPI.eval(document, xpath, namespaceElement);
|
252
|
String str = xobject.str();
|
253
|
|
254
|
return str;
|
255
|
}
|
256
|
|
257
|
|
258
|
/**
|
259
|
* Preforms the OAI request for this OAI-PMH verb
|
260
|
*
|
261
|
* @throws IOException
|
262
|
* @throws ParserConfigurationException
|
263
|
* @throws SAXException
|
264
|
* @throws TransformerException
|
265
|
*/
|
266
|
public void runVerb()
|
267
|
throws IOException, ParserConfigurationException,
|
268
|
SAXException, TransformerException {
|
269
|
//logger.debug("requestURL=" + requestURL);
|
270
|
InputStream in = null;
|
271
|
URL url = new URL(requestURL);
|
272
|
HttpURLConnection con = null;
|
273
|
int responseCode = 0;
|
274
|
|
275
|
do {
|
276
|
con = (HttpURLConnection) url.openConnection();
|
277
|
con.setRequestProperty("User-Agent", "OAIHarvester/2.0");
|
278
|
con.setRequestProperty("Accept-Encoding", "compress, gzip, identify");
|
279
|
|
280
|
try {
|
281
|
responseCode = con.getResponseCode();
|
282
|
//logger.debug("responseCode=" + responseCode);
|
283
|
}
|
284
|
catch (FileNotFoundException e) {
|
285
|
// assume it's a 503 response
|
286
|
logger.info(requestURL, e);
|
287
|
responseCode = HttpURLConnection.HTTP_UNAVAILABLE;
|
288
|
}
|
289
|
|
290
|
if (responseCode == HttpURLConnection.HTTP_UNAVAILABLE) {
|
291
|
long retrySeconds = con.getHeaderFieldInt("Retry-After", -1);
|
292
|
|
293
|
if (retrySeconds == -1) {
|
294
|
long now = (new Date()).getTime();
|
295
|
long retryDate = con.getHeaderFieldDate("Retry-After", now);
|
296
|
retrySeconds = retryDate - now;
|
297
|
}
|
298
|
|
299
|
if (retrySeconds == 0) { // Apparently, it's a bad URL
|
300
|
throw new FileNotFoundException("Bad URL?");
|
301
|
}
|
302
|
|
303
|
System.err.println("Server response: Retry-After=" + retrySeconds);
|
304
|
|
305
|
if (retrySeconds > 0) {
|
306
|
try {
|
307
|
Thread.sleep(retrySeconds * 1000);
|
308
|
}
|
309
|
catch (InterruptedException ex) {
|
310
|
ex.printStackTrace();
|
311
|
}
|
312
|
}
|
313
|
|
314
|
}
|
315
|
} while (responseCode == HttpURLConnection.HTTP_UNAVAILABLE);
|
316
|
|
317
|
String contentEncoding = con.getHeaderField("Content-Encoding");
|
318
|
//logger.debug("contentEncoding=" + contentEncoding);
|
319
|
if ("compress".equals(contentEncoding)) {
|
320
|
ZipInputStream zis = new ZipInputStream(con.getInputStream());
|
321
|
zis.getNextEntry();
|
322
|
in = zis;
|
323
|
}
|
324
|
else if ("gzip".equals(contentEncoding)) {
|
325
|
in = new GZIPInputStream(con.getInputStream());
|
326
|
}
|
327
|
else if ("deflate".equals(contentEncoding)) {
|
328
|
in = new InflaterInputStream(con.getInputStream());
|
329
|
}
|
330
|
else {
|
331
|
in = con.getInputStream();
|
332
|
}
|
333
|
|
334
|
InputSource data = new InputSource(in);
|
335
|
|
336
|
Thread t = Thread.currentThread();
|
337
|
DocumentBuilder builder = builderMap.get(t);
|
338
|
|
339
|
if (builder == null) {
|
340
|
builder = documentBuilderFactory.newDocumentBuilder();
|
341
|
builderMap.put(t, builder);
|
342
|
}
|
343
|
|
344
|
document = builder.parse(data);
|
345
|
|
346
|
String singleString = getSingleString("/*/@xsi:schemaLocation");
|
347
|
StringTokenizer tokenizer = new StringTokenizer(singleString, " ");
|
348
|
StringBuffer sb = new StringBuffer();
|
349
|
|
350
|
while (tokenizer.hasMoreTokens()) {
|
351
|
if (sb.length() > 0) sb.append(" ");
|
352
|
sb.append(tokenizer.nextToken());
|
353
|
}
|
354
|
|
355
|
String schemaLocationStr = sb.toString();
|
356
|
this.schemaLocation = schemaLocationStr;
|
357
|
}
|
358
|
|
359
|
|
360
|
/**
|
361
|
* Transform the document content to a string and return it.
|
362
|
*
|
363
|
* @return returnString - the string that results from transforming the
|
364
|
* document
|
365
|
*/
|
366
|
public String toString() {
|
367
|
Document document = getDocument();
|
368
|
Source source = new DOMSource(document);
|
369
|
StringWriter stringWriter = new StringWriter();
|
370
|
Result result = new StreamResult(stringWriter);
|
371
|
|
372
|
try {
|
373
|
Transformer idTransformer = transformerFactory.newTransformer();
|
374
|
idTransformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "no");
|
375
|
idTransformer.transform(source, result);
|
376
|
String returnString = stringWriter.toString();
|
377
|
return returnString;
|
378
|
}
|
379
|
catch (TransformerException e) {
|
380
|
return e.getMessage();
|
381
|
}
|
382
|
}
|
383
|
|
384
|
}
|