1
|
/*
|
2
|
* HarvestSiteSchedule.java
|
3
|
*
|
4
|
* Created on January 14, 2004, 4:47 PM
|
5
|
*/
|
6
|
|
7
|
package edu.ucsb.nceas.metacat.harvesterClient;
|
8
|
|
9
|
import com.oreilly.servlet.MailMessage;
|
10
|
import java.io.FileNotFoundException;
|
11
|
import java.io.IOException;
|
12
|
import java.io.InputStream;
|
13
|
import java.io.InputStreamReader;
|
14
|
import java.io.PrintStream;
|
15
|
import java.io.Reader;
|
16
|
import java.net.MalformedURLException;
|
17
|
import java.net.URL;
|
18
|
import java.sql.Connection;
|
19
|
import java.sql.SQLException;
|
20
|
import java.sql.Statement;
|
21
|
import java.text.DateFormat;
|
22
|
import java.text.ParseException;
|
23
|
import java.text.SimpleDateFormat;
|
24
|
import java.util.ArrayList;
|
25
|
import java.util.Date;
|
26
|
import javax.xml.parsers.ParserConfigurationException;
|
27
|
import org.xml.sax.Attributes;
|
28
|
import org.xml.sax.ContentHandler;
|
29
|
import org.xml.sax.ErrorHandler;
|
30
|
import org.xml.sax.InputSource;
|
31
|
import org.xml.sax.SAXException;
|
32
|
import org.xml.sax.SAXParseException;
|
33
|
import org.xml.sax.XMLReader;
|
34
|
import org.xml.sax.helpers.DefaultHandler;
|
35
|
import org.xml.sax.helpers.XMLReaderFactory;
|
36
|
|
37
|
import edu.ucsb.nceas.metacat.client.Metacat;
|
38
|
import edu.ucsb.nceas.metacat.client.MetacatException;
|
39
|
import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;
|
40
|
|
41
|
|
42
|
/**
|
43
|
* HarvestSiteSchedule manages a single entry in the HARVEST_SITE_SCHEDULE
|
44
|
* table, determining when and how to harvest the documents for a given site.
|
45
|
*
|
46
|
* @author costa
|
47
|
*/
|
48
|
class HarvestSiteSchedule {
|
49
|
|
50
|
private String contactEmail;
|
51
|
private String dateLastHarvest;
|
52
|
private String dateNextHarvest;
|
53
|
private long delta;
|
54
|
private String documentListURL;
|
55
|
private Harvester harvester;
|
56
|
private ArrayList harvestDocumentList = new ArrayList();
|
57
|
private String harvestSiteEndTime;
|
58
|
private String harvestSiteStartTime;
|
59
|
private String ldapDN;
|
60
|
private String ldapPwd;
|
61
|
final private long millisecondsPerDay = (1000 * 60 * 60 * 24);
|
62
|
int siteScheduleID;
|
63
|
private String unit;
|
64
|
private int updateFrequency;
|
65
|
|
66
|
/**
|
67
|
* Creates a new instance of HarvestSiteSchedule. Initialized with the data
|
68
|
* that was read from a single row in the HARVEST_SITE_SCHEDULE table.
|
69
|
*
|
70
|
* @param harvester the parent Harvester object
|
71
|
* @param siteScheduleID the value of the SITE_SCHEDULE_ID field
|
72
|
* @param documentListURL the value of the DOCUMENTLISTURL field
|
73
|
* @param ldapDN the value of the LDAPDN field
|
74
|
* @param ldapPwd the value of the LDAPPASSWORD field
|
75
|
* @param dateNextHarvest the value of the DATENEXTHARVEST field
|
76
|
* @param dateLastHarvest the value of the DATELASTHARVEST field
|
77
|
* @param updateFrequency the value of the UPDATEFREQUENCY field
|
78
|
* @param unit the value of the UNIT field
|
79
|
* @param contactEmail the value of the CONTACT_EMAIL field
|
80
|
*/
|
81
|
public HarvestSiteSchedule(
|
82
|
Harvester harvester,
|
83
|
int siteScheduleID,
|
84
|
String documentListURL,
|
85
|
String ldapDN,
|
86
|
String ldapPwd,
|
87
|
String dateNextHarvest,
|
88
|
String dateLastHarvest,
|
89
|
int updateFrequency,
|
90
|
String unit,
|
91
|
String contactEmail
|
92
|
)
|
93
|
{
|
94
|
this.harvester = harvester;
|
95
|
this.siteScheduleID = siteScheduleID;
|
96
|
this.documentListURL = documentListURL;
|
97
|
this.ldapDN = ldapDN;
|
98
|
this.ldapPwd = ldapPwd;
|
99
|
this.dateNextHarvest = dateNextHarvest;
|
100
|
this.dateLastHarvest = dateLastHarvest;
|
101
|
this.updateFrequency = updateFrequency;
|
102
|
this.unit = unit;
|
103
|
this.contactEmail = contactEmail;
|
104
|
|
105
|
// Calculate the value of delta, the number of milliseconds between the
|
106
|
// last harvest date and the next harvest date.
|
107
|
delta = updateFrequency * millisecondsPerDay;
|
108
|
|
109
|
if (unit.equals("weeks")) {
|
110
|
delta *= 7;
|
111
|
}
|
112
|
else if (unit.equals("months")) {
|
113
|
delta *= 30;
|
114
|
}
|
115
|
}
|
116
|
|
117
|
|
118
|
/**
|
119
|
* Updates the DATELASTHARVEST and DATENEXTHARVEST values of the
|
120
|
* HARVEST_SITE_SCHEDULE table after a harvest operation has completed.
|
121
|
* Calculates the date of the next harvest based on today's date and the
|
122
|
* update frequency.
|
123
|
*/
|
124
|
private void dbUpdateHarvestDates() {
|
125
|
Connection conn;
|
126
|
long currentTime; // Current time in milliseconds
|
127
|
Date dateNextHarvest; // Date of next harvest
|
128
|
String lastHarvest;
|
129
|
String nextHarvest;
|
130
|
Date now = new Date();
|
131
|
SimpleDateFormat simpleDateFormat = new SimpleDateFormat("dd-MMM-yyyy");
|
132
|
Statement stmt;
|
133
|
long timeNextHarvest;
|
134
|
|
135
|
conn = harvester.conn;
|
136
|
now = new Date();
|
137
|
currentTime = now.getTime();
|
138
|
timeNextHarvest = currentTime + delta;
|
139
|
dateNextHarvest = new Date(timeNextHarvest);
|
140
|
nextHarvest = "'" + simpleDateFormat.format(dateNextHarvest) + "'";
|
141
|
lastHarvest = "'" + simpleDateFormat.format(now) + "'";
|
142
|
|
143
|
try {
|
144
|
stmt = conn.createStatement();
|
145
|
stmt.executeUpdate("UPDATE HARVEST_SITE_SCHEDULE SET DATENEXTHARVEST = " +
|
146
|
nextHarvest +
|
147
|
" WHERE SITE_SCHEDULE_ID = " +
|
148
|
siteScheduleID);
|
149
|
stmt.executeUpdate("UPDATE HARVEST_SITE_SCHEDULE SET DATELASTHARVEST = " +
|
150
|
lastHarvest +
|
151
|
" WHERE SITE_SCHEDULE_ID = " +
|
152
|
siteScheduleID);
|
153
|
stmt.close();
|
154
|
}
|
155
|
catch(SQLException e) {
|
156
|
System.out.println("SQLException: " + e.getMessage());
|
157
|
}
|
158
|
}
|
159
|
|
160
|
|
161
|
/**
|
162
|
* Boolean to determine whether this site is currently due for its next
|
163
|
* harvest.
|
164
|
*
|
165
|
* @retrun true if due for harvest, otherwise false
|
166
|
*/
|
167
|
private boolean dueForHarvest() {
|
168
|
boolean dueForHarvest = false;
|
169
|
DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.S");
|
170
|
Date now = new Date();
|
171
|
Date dnh; // Date of next harvest
|
172
|
long currentTime = now.getTime(); // Current time in milliseconds
|
173
|
long timeNextHarvest = 0;
|
174
|
|
175
|
try {
|
176
|
dnh = dateFormat.parse(dateNextHarvest);
|
177
|
timeNextHarvest = dnh.getTime();
|
178
|
|
179
|
if (timeNextHarvest < currentTime) {
|
180
|
dueForHarvest = true;
|
181
|
System.out.println("Due for harvest: " + documentListURL);
|
182
|
}
|
183
|
else {
|
184
|
System.out.println("Not due for harvest: " + documentListURL);
|
185
|
}
|
186
|
}
|
187
|
catch (ParseException e) {
|
188
|
System.out.println("Error parsing date: " + e.getMessage());
|
189
|
}
|
190
|
|
191
|
return dueForHarvest;
|
192
|
}
|
193
|
|
194
|
|
195
|
/**
|
196
|
* Harvests each document in the site document list.
|
197
|
*
|
198
|
* @throws SAXException
|
199
|
* @throws IOException
|
200
|
* @throws ParserConfigurationException
|
201
|
*/
|
202
|
public void harvestDocumentList() {
|
203
|
HarvestDocument harvestDocument;
|
204
|
boolean success;
|
205
|
|
206
|
if (dueForHarvest()) {
|
207
|
try {
|
208
|
success = parseDocumentList();
|
209
|
|
210
|
/* If the document list was validated, then proceed with harvesting
|
211
|
* the documents
|
212
|
*/
|
213
|
if (success) {
|
214
|
metacatLogin();
|
215
|
|
216
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
217
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
218
|
|
219
|
if (harvestDocument != null) {
|
220
|
harvestDocument.harvestDocument();
|
221
|
}
|
222
|
}
|
223
|
|
224
|
metacatLogout();
|
225
|
dbUpdateHarvestDates(); // Update the schedule
|
226
|
}
|
227
|
}
|
228
|
catch (ParserConfigurationException e) {
|
229
|
System.out.println("ParserConfigurationException: " + e.getMessage());
|
230
|
}
|
231
|
|
232
|
reportToSite();
|
233
|
}
|
234
|
}
|
235
|
|
236
|
|
237
|
/**
|
238
|
* Login to Metacat using the ldapDN and ldapPwd
|
239
|
*/
|
240
|
private void metacatLogin() {
|
241
|
Metacat metacat = harvester.metacat;
|
242
|
|
243
|
if (harvester.connectToMetacat()) {
|
244
|
try {
|
245
|
System.out.println("Logging in to Metacat: " + ldapDN);
|
246
|
metacat.login(ldapDN, ldapPwd);
|
247
|
//System.out.println("Metacat login response: " + response);
|
248
|
//sessionId = metacat.getSessionId();
|
249
|
//System.out.println("Session ID: " + sessionId);
|
250
|
}
|
251
|
catch (MetacatInaccessibleException e) {
|
252
|
System.out.println("Metacat login failed." + e.getMessage());
|
253
|
}
|
254
|
catch (Exception e) {
|
255
|
System.out.println("Metacat login failed." + e.getMessage());
|
256
|
}
|
257
|
}
|
258
|
}
|
259
|
|
260
|
|
261
|
/**
|
262
|
* Logout from Metacat
|
263
|
*/
|
264
|
private void metacatLogout() {
|
265
|
Metacat metacat = harvester.metacat;
|
266
|
|
267
|
if (harvester.connectToMetacat()) {
|
268
|
try {
|
269
|
// Log out from the Metacat session
|
270
|
System.out.println("Logging out from Metacat");
|
271
|
metacat.logout();
|
272
|
}
|
273
|
catch (MetacatInaccessibleException e) {
|
274
|
System.out.println("Metacat inaccessible: " + e.getMessage());
|
275
|
}
|
276
|
catch (MetacatException e) {
|
277
|
System.out.println("Metacat exception: " + e.getMessage());
|
278
|
}
|
279
|
}
|
280
|
}
|
281
|
|
282
|
|
283
|
/**
|
284
|
* Parse the site document list to find out which documents to harvest.
|
285
|
*
|
286
|
* @return true if successful, otherwise false
|
287
|
*/
|
288
|
private boolean parseDocumentList()
|
289
|
throws ParserConfigurationException {
|
290
|
DocumentListHandler documentListHandler = new DocumentListHandler();
|
291
|
InputStream inputStream;
|
292
|
InputStreamReader inputStreamReader;
|
293
|
String schemaLocation = ".";
|
294
|
boolean success = false;
|
295
|
URL url;
|
296
|
|
297
|
try {
|
298
|
url = new URL(documentListURL);
|
299
|
inputStream = url.openStream();
|
300
|
harvester.addLogEntry(0,
|
301
|
"Retrieved: " + documentListURL,
|
302
|
"GetDocListSuccess",
|
303
|
siteScheduleID,
|
304
|
null,
|
305
|
"");
|
306
|
inputStreamReader = new InputStreamReader(inputStream);
|
307
|
documentListHandler.runParser(inputStreamReader, schemaLocation);
|
308
|
harvester.addLogEntry(0,
|
309
|
"Validated: " + documentListURL,
|
310
|
"ValidateDocListSuccess",
|
311
|
siteScheduleID,
|
312
|
null,
|
313
|
"");
|
314
|
success = true;
|
315
|
}
|
316
|
catch (MalformedURLException e){
|
317
|
harvester.addLogEntry(1, "MalformedURLException: " + e.getMessage(),
|
318
|
"GetDocListError", siteScheduleID, null, "");
|
319
|
}
|
320
|
catch (FileNotFoundException e) {
|
321
|
harvester.addLogEntry(1, "FileNotFoundException: " + e.getMessage(),
|
322
|
"GetDocListError", siteScheduleID, null, "");
|
323
|
}
|
324
|
catch (SAXException e) {
|
325
|
harvester.addLogEntry(1, "SAXException: " + e.getMessage(),
|
326
|
"ValidateDocListError", siteScheduleID, null, "");
|
327
|
}
|
328
|
catch (ClassNotFoundException e) {
|
329
|
harvester.addLogEntry(1, "ClassNotFoundException: " + e.getMessage(),
|
330
|
"ValidateDocListError", siteScheduleID, null, "");
|
331
|
}
|
332
|
catch (IOException e) {
|
333
|
harvester.addLogEntry(1, "IOException: " + e.getMessage(),
|
334
|
"GetDocListError", siteScheduleID, null, "");
|
335
|
}
|
336
|
|
337
|
return success;
|
338
|
}
|
339
|
|
340
|
|
341
|
/**
|
342
|
* Prints the data that is stored in this HarvestSiteSchedule object.
|
343
|
*
|
344
|
* @param out the PrintStream to write to
|
345
|
*/
|
346
|
void printOutput(PrintStream out) {
|
347
|
out.println("* siteScheduleID: " + siteScheduleID);
|
348
|
out.println("* documentListURL: " + documentListURL);
|
349
|
out.println("* ldapDN: " + ldapDN);
|
350
|
out.println("* dateNextHarvest: " + dateNextHarvest);
|
351
|
out.println("* dateLastHarvest: " + dateLastHarvest);
|
352
|
out.println("* updateFrequency: " + updateFrequency);
|
353
|
out.println("* unit: " + unit);
|
354
|
out.println("* contactEmail: " + contactEmail);
|
355
|
}
|
356
|
|
357
|
|
358
|
/**
|
359
|
* Sends a report to the site summarizing the results of the harvest
|
360
|
* operation.
|
361
|
*/
|
362
|
void reportToSite() {
|
363
|
PrintStream body;
|
364
|
String from = "Metacat Harvester";
|
365
|
MailMessage msg;
|
366
|
String subject = "Report from Metacat Harvester";
|
367
|
String to = contactEmail;
|
368
|
|
369
|
if (!to.equals("")) {
|
370
|
System.out.println("Sending report to siteScheduleID=" + siteScheduleID +
|
371
|
" at address: " + contactEmail);
|
372
|
|
373
|
try {
|
374
|
msg = new MailMessage();
|
375
|
msg.from(from);
|
376
|
msg.to(to);
|
377
|
msg.setSubject(subject);
|
378
|
body = msg.getPrintStream();
|
379
|
|
380
|
}
|
381
|
catch (IOException e) {
|
382
|
System.out.println("There was a problem sending email to " + to);
|
383
|
System.out.println("IOException: " + e.getMessage());
|
384
|
}
|
385
|
|
386
|
}
|
387
|
}
|
388
|
|
389
|
|
390
|
/**
|
391
|
* This inner class extends DefaultHandler. It parses the document list,
|
392
|
* creating a new HarvestDocument object every time it finds a </Document>
|
393
|
* end tag.
|
394
|
*/
|
395
|
class DocumentListHandler extends DefaultHandler implements ErrorHandler {
|
396
|
|
397
|
public String scope;
|
398
|
public int identifier;
|
399
|
public String identifierString;
|
400
|
public String documentType;
|
401
|
public int revision;
|
402
|
public String revisionString;
|
403
|
public String documentURL;
|
404
|
private String currentQname;
|
405
|
public final static String DEFAULT_PARSER =
|
406
|
"org.apache.xerces.parsers.SAXParser";
|
407
|
private boolean schemaValidate = true;
|
408
|
|
409
|
|
410
|
/**
|
411
|
* This method is called for any plain text within an element.
|
412
|
* It parses the value for any of the following elements:
|
413
|
* <scope>, <identifier>, <revision>, <documentType>, <documentURL>
|
414
|
*
|
415
|
* @param ch the character array holding the parsed text
|
416
|
* @param start the start index
|
417
|
* @param length the text length
|
418
|
*
|
419
|
*/
|
420
|
public void characters (char ch[], int start, int length) {
|
421
|
String s = new String(ch, start, length);
|
422
|
|
423
|
if (length > 0) {
|
424
|
if (currentQname.equals("scope")) {
|
425
|
scope += s;
|
426
|
}
|
427
|
else if (currentQname.equals("identifier")) {
|
428
|
identifierString += s;
|
429
|
}
|
430
|
else if (currentQname.equals("revision")) {
|
431
|
revisionString += s;
|
432
|
}
|
433
|
else if (currentQname.equals("documentType")) {
|
434
|
documentType += s;
|
435
|
}
|
436
|
else if (currentQname.equals("documentURL")) {
|
437
|
documentURL += s;
|
438
|
}
|
439
|
}
|
440
|
}
|
441
|
|
442
|
|
443
|
/**
|
444
|
* Handles an end-of-document event.
|
445
|
*/
|
446
|
public void endDocument () {
|
447
|
System.out.println("Finished parsing " + documentListURL);
|
448
|
}
|
449
|
|
450
|
|
451
|
/**
|
452
|
* Handles an end-of-element event. If the end tag is </Document>, then
|
453
|
* creates a new HarvestDocument object and pushes it to the document
|
454
|
* list.
|
455
|
*
|
456
|
* @param uri
|
457
|
* @param localname
|
458
|
* @param qname
|
459
|
*/
|
460
|
public void endElement(String uri,
|
461
|
String localname,
|
462
|
String qname) {
|
463
|
|
464
|
HarvestDocument harvestDocument;
|
465
|
|
466
|
if (qname.equals("identifier")) {
|
467
|
identifier = Integer.parseInt(identifierString);
|
468
|
}
|
469
|
else if (qname.equals("revision")) {
|
470
|
revision = Integer.parseInt(revisionString);
|
471
|
}
|
472
|
else if (qname.equals("document")) {
|
473
|
harvestDocument = new HarvestDocument(
|
474
|
harvester,
|
475
|
HarvestSiteSchedule.this,
|
476
|
scope,
|
477
|
identifier,
|
478
|
revision,
|
479
|
documentType,
|
480
|
documentURL
|
481
|
);
|
482
|
harvestDocumentList.add(harvestDocument);
|
483
|
}
|
484
|
|
485
|
currentQname = "";
|
486
|
}
|
487
|
|
488
|
|
489
|
/**
|
490
|
* Method for handling errors during a parse
|
491
|
*
|
492
|
* @param exception The parsing error
|
493
|
* @exception SAXException Description of Exception
|
494
|
*/
|
495
|
public void error(SAXParseException e) throws SAXParseException {
|
496
|
System.out.println("SAXParseException: " + e.getMessage());
|
497
|
throw e;
|
498
|
}
|
499
|
|
500
|
|
501
|
/**
|
502
|
* Run the validating parser
|
503
|
*
|
504
|
* @param xml the xml stream to be validated
|
505
|
* @schemaLocation relative path the to XML Schema file, e.g. "."
|
506
|
* @exception IOException thrown when test files can't be opened
|
507
|
* @exception ClassNotFoundException thrown when SAX Parser class not found
|
508
|
* @exception SAXException
|
509
|
* @exception SAXParserException
|
510
|
*/
|
511
|
public void runParser(Reader xml, String schemaLocation)
|
512
|
throws IOException, ClassNotFoundException,
|
513
|
SAXException, SAXParseException {
|
514
|
|
515
|
// Get an instance of the parser
|
516
|
XMLReader parser;
|
517
|
|
518
|
parser = XMLReaderFactory.createXMLReader(DEFAULT_PARSER);
|
519
|
// Set Handlers in the parser
|
520
|
parser.setContentHandler((ContentHandler)this);
|
521
|
parser.setErrorHandler((ErrorHandler)this);
|
522
|
parser.setFeature("http://xml.org/sax/features/namespaces", true);
|
523
|
parser.setFeature("http://xml.org/sax/features/namespace-prefixes", true);
|
524
|
parser.setFeature("http://xml.org/sax/features/validation", true);
|
525
|
parser.setProperty(
|
526
|
"http://apache.org/xml/properties/schema/external-schemaLocation",
|
527
|
schemaLocation);
|
528
|
|
529
|
if (schemaValidate) {
|
530
|
parser.setFeature("http://apache.org/xml/features/validation/schema",
|
531
|
true);
|
532
|
}
|
533
|
|
534
|
// Parse the document
|
535
|
parser.parse(new InputSource(xml));
|
536
|
}
|
537
|
/**
|
538
|
* Handles a start-of-document event.
|
539
|
*/
|
540
|
public void startDocument () {
|
541
|
System.out.println("Started parsing " + documentListURL);
|
542
|
}
|
543
|
|
544
|
|
545
|
/**
|
546
|
* Handles a start-of-element event.
|
547
|
*
|
548
|
* @param uri
|
549
|
* @param localname
|
550
|
* @param qname
|
551
|
* @param attributes
|
552
|
*/
|
553
|
public void startElement(String uri,
|
554
|
String localname,
|
555
|
String qname,
|
556
|
Attributes attributes) {
|
557
|
|
558
|
currentQname = qname;
|
559
|
|
560
|
if (qname.equals("scope")) {
|
561
|
scope = "";
|
562
|
}
|
563
|
else if (qname.equals("identifier")) {
|
564
|
identifierString = "";
|
565
|
}
|
566
|
else if (qname.equals("revision")) {
|
567
|
revisionString = "";
|
568
|
}
|
569
|
else if (qname.equals("documentType")) {
|
570
|
documentType = "";
|
571
|
}
|
572
|
else if (qname.equals("documentURL")) {
|
573
|
documentURL = "";
|
574
|
}
|
575
|
}
|
576
|
}
|
577
|
}
|