1
|
/**
|
2
|
* '$RCSfile$'
|
3
|
* Copyright: 2004 University of New Mexico and the
|
4
|
* Regents of the University of California
|
5
|
*
|
6
|
* '$Author: costa $'
|
7
|
* '$Date: 2004-11-09 15:34:25 -0800 (Tue, 09 Nov 2004) $'
|
8
|
* '$Revision: 2330 $'
|
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
|
|
25
|
package edu.ucsb.nceas.metacat.harvesterClient;
|
26
|
|
27
|
import com.oreilly.servlet.MailMessage;
|
28
|
import java.io.FileNotFoundException;
|
29
|
import java.io.IOException;
|
30
|
import java.io.InputStream;
|
31
|
import java.io.InputStreamReader;
|
32
|
import java.io.PrintStream;
|
33
|
import java.io.Reader;
|
34
|
import java.net.MalformedURLException;
|
35
|
import java.net.URL;
|
36
|
import java.sql.Connection;
|
37
|
import java.sql.SQLException;
|
38
|
import java.sql.Statement;
|
39
|
import java.text.DateFormat;
|
40
|
import java.text.ParseException;
|
41
|
import java.text.SimpleDateFormat;
|
42
|
import java.util.ArrayList;
|
43
|
import java.util.Date;
|
44
|
import javax.xml.parsers.ParserConfigurationException;
|
45
|
import org.xml.sax.Attributes;
|
46
|
import org.xml.sax.ContentHandler;
|
47
|
import org.xml.sax.ErrorHandler;
|
48
|
import org.xml.sax.InputSource;
|
49
|
import org.xml.sax.SAXException;
|
50
|
import org.xml.sax.SAXParseException;
|
51
|
import org.xml.sax.XMLReader;
|
52
|
import org.xml.sax.helpers.DefaultHandler;
|
53
|
import org.xml.sax.helpers.XMLReaderFactory;
|
54
|
|
55
|
import edu.ucsb.nceas.metacat.client.Metacat;
|
56
|
import edu.ucsb.nceas.metacat.client.MetacatException;
|
57
|
import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;
|
58
|
|
59
|
|
60
|
/**
|
61
|
* HarvestSiteSchedule manages a single entry in the HARVEST_SITE_SCHEDULE
|
62
|
* table, determining when and how to harvest the documents for a given site.
|
63
|
*
|
64
|
* @author costa
|
65
|
*/
|
66
|
public class HarvestSiteSchedule {
|
67
|
|
68
|
private String contactEmail;
|
69
|
private String dateLastHarvest;
|
70
|
private String dateNextHarvest;
|
71
|
private long delta;
|
72
|
private String documentListURL;
|
73
|
private Harvester harvester;
|
74
|
private ArrayList harvestDocumentList = new ArrayList();
|
75
|
private String harvestSiteEndTime;
|
76
|
private String harvestSiteStartTime;
|
77
|
private String ldapDN;
|
78
|
private String ldapPwd;
|
79
|
final private long millisecondsPerDay = (1000 * 60 * 60 * 24);
|
80
|
private String schemaLocation =
|
81
|
"eml://ecoinformatics.org/harvestList ../../lib/harvester/harvestList.xsd";
|
82
|
int siteScheduleID;
|
83
|
private String unit;
|
84
|
private int updateFrequency;
|
85
|
|
86
|
/**
|
87
|
* Creates a new instance of HarvestSiteSchedule. Initialized with the data
|
88
|
* that was read from a single row in the HARVEST_SITE_SCHEDULE table.
|
89
|
*
|
90
|
* @param harvester the parent Harvester object
|
91
|
* @param siteScheduleID the value of the SITE_SCHEDULE_ID field
|
92
|
* @param documentListURL the value of the DOCUMENTLISTURL field
|
93
|
* @param ldapDN the value of the LDAPDN field
|
94
|
* @param ldapPwd the value of the LDAPPASSWORD field
|
95
|
* @param dateNextHarvest the value of the DATENEXTHARVEST field
|
96
|
* @param dateLastHarvest the value of the DATELASTHARVEST field
|
97
|
* @param updateFrequency the value of the UPDATEFREQUENCY field
|
98
|
* @param unit the value of the UNIT field
|
99
|
* @param contactEmail the value of the CONTACT_EMAIL field
|
100
|
*/
|
101
|
public HarvestSiteSchedule(
|
102
|
Harvester harvester,
|
103
|
int siteScheduleID,
|
104
|
String documentListURL,
|
105
|
String ldapDN,
|
106
|
String ldapPwd,
|
107
|
String dateNextHarvest,
|
108
|
String dateLastHarvest,
|
109
|
int updateFrequency,
|
110
|
String unit,
|
111
|
String contactEmail
|
112
|
)
|
113
|
{
|
114
|
this.harvester = harvester;
|
115
|
this.siteScheduleID = siteScheduleID;
|
116
|
this.documentListURL = documentListURL;
|
117
|
this.ldapDN = ldapDN;
|
118
|
this.ldapPwd = ldapPwd;
|
119
|
this.dateNextHarvest = dateNextHarvest;
|
120
|
this.dateLastHarvest = dateLastHarvest;
|
121
|
this.updateFrequency = updateFrequency;
|
122
|
this.unit = unit;
|
123
|
this.contactEmail = contactEmail;
|
124
|
|
125
|
// Calculate the value of delta, the number of milliseconds between the
|
126
|
// last harvest date and the next harvest date.
|
127
|
delta = updateFrequency * millisecondsPerDay;
|
128
|
|
129
|
if (unit.equals("weeks")) {
|
130
|
delta *= 7;
|
131
|
}
|
132
|
else if (unit.equals("months")) {
|
133
|
delta *= 30;
|
134
|
}
|
135
|
}
|
136
|
|
137
|
|
138
|
/**
|
139
|
* Updates the DATELASTHARVEST and DATENEXTHARVEST values of the
|
140
|
* HARVEST_SITE_SCHEDULE table after a harvest operation has completed.
|
141
|
* Calculates the date of the next harvest based on today's date and the
|
142
|
* update frequency.
|
143
|
*/
|
144
|
private void dbUpdateHarvestDates() {
|
145
|
Connection conn;
|
146
|
long currentTime; // Current time in milliseconds
|
147
|
Date dateNextHarvest; // Date of next harvest
|
148
|
String lastHarvest;
|
149
|
String nextHarvest;
|
150
|
Date now = new Date();
|
151
|
SimpleDateFormat simpleDateFormat = new SimpleDateFormat("dd-MMM-yyyy");
|
152
|
Statement stmt;
|
153
|
long timeNextHarvest;
|
154
|
|
155
|
conn = harvester.getConnection();
|
156
|
now = new Date();
|
157
|
currentTime = now.getTime();
|
158
|
timeNextHarvest = currentTime + delta;
|
159
|
dateNextHarvest = new Date(timeNextHarvest);
|
160
|
nextHarvest = "'" + simpleDateFormat.format(dateNextHarvest) + "'";
|
161
|
lastHarvest = "'" + simpleDateFormat.format(now) + "'";
|
162
|
|
163
|
try {
|
164
|
stmt = conn.createStatement();
|
165
|
stmt.executeUpdate("UPDATE HARVEST_SITE_SCHEDULE SET DATENEXTHARVEST = " +
|
166
|
nextHarvest +
|
167
|
" WHERE SITE_SCHEDULE_ID = " +
|
168
|
siteScheduleID);
|
169
|
stmt.executeUpdate("UPDATE HARVEST_SITE_SCHEDULE SET DATELASTHARVEST = " +
|
170
|
lastHarvest +
|
171
|
" WHERE SITE_SCHEDULE_ID = " +
|
172
|
siteScheduleID);
|
173
|
stmt.close();
|
174
|
}
|
175
|
catch(SQLException e) {
|
176
|
System.out.println("SQLException: " + e.getMessage());
|
177
|
}
|
178
|
}
|
179
|
|
180
|
|
181
|
/**
|
182
|
* Boolean to determine whether this site is currently due for its next
|
183
|
* harvest.
|
184
|
*
|
185
|
* @retrun true if due for harvest, otherwise false
|
186
|
*/
|
187
|
public boolean dueForHarvest() {
|
188
|
boolean dueForHarvest = false;
|
189
|
// DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.S");
|
190
|
DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd");
|
191
|
Date now = new Date();
|
192
|
Date dnh; // Date of next harvest
|
193
|
long currentTime = now.getTime(); // Current time in milliseconds
|
194
|
long timeNextHarvest = 0;
|
195
|
|
196
|
try {
|
197
|
dnh = dateFormat.parse(dateNextHarvest);
|
198
|
timeNextHarvest = dnh.getTime();
|
199
|
|
200
|
if (timeNextHarvest < currentTime) {
|
201
|
dueForHarvest = true;
|
202
|
System.out.println("Due for harvest: " + documentListURL);
|
203
|
}
|
204
|
else {
|
205
|
System.out.println("Not due for harvest: " + documentListURL);
|
206
|
}
|
207
|
}
|
208
|
catch (ParseException e) {
|
209
|
System.out.println("Error parsing date: " + e.getMessage());
|
210
|
}
|
211
|
|
212
|
return dueForHarvest;
|
213
|
}
|
214
|
|
215
|
|
216
|
/**
|
217
|
* Accessor method for the schemaLocation field.
|
218
|
*
|
219
|
* @return schemaLocation the schema location string
|
220
|
*/
|
221
|
public String getSchemaLocation() {
|
222
|
return schemaLocation;
|
223
|
}
|
224
|
|
225
|
|
226
|
/**
|
227
|
* Harvests each document in the site document list.
|
228
|
*
|
229
|
* @throws SAXException
|
230
|
* @throws IOException
|
231
|
* @throws ParserConfigurationException
|
232
|
*/
|
233
|
public void harvestDocumentList() {
|
234
|
HarvestDocument harvestDocument;
|
235
|
boolean success;
|
236
|
|
237
|
if (dueForHarvest()) {
|
238
|
try {
|
239
|
success = parseHarvestList();
|
240
|
|
241
|
/* If the document list was validated, then proceed with harvesting
|
242
|
* the documents
|
243
|
*/
|
244
|
if (success) {
|
245
|
metacatLogin();
|
246
|
|
247
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
248
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
249
|
|
250
|
if (harvestDocument != null) {
|
251
|
harvestDocument.harvestDocument();
|
252
|
}
|
253
|
}
|
254
|
|
255
|
metacatLogout();
|
256
|
dbUpdateHarvestDates(); // Update the schedule
|
257
|
}
|
258
|
}
|
259
|
catch (ParserConfigurationException e) {
|
260
|
System.out.println("ParserConfigurationException: " + e.getMessage());
|
261
|
}
|
262
|
|
263
|
reportToSiteContact();
|
264
|
}
|
265
|
}
|
266
|
|
267
|
|
268
|
/**
|
269
|
* Login to Metacat using the ldapDN and ldapPwd
|
270
|
*/
|
271
|
public void metacatLogin() {
|
272
|
Metacat metacat = harvester.metacat;
|
273
|
String response;
|
274
|
|
275
|
if (harvester.connectToMetacat()) {
|
276
|
try {
|
277
|
System.out.println("Logging in to Metacat: " + ldapDN);
|
278
|
response = metacat.login(ldapDN, ldapPwd);
|
279
|
//System.out.println("Metacat login response: " + response);
|
280
|
}
|
281
|
catch (MetacatInaccessibleException e) {
|
282
|
System.out.println("Metacat login failed." + e.getMessage());
|
283
|
}
|
284
|
catch (Exception e) {
|
285
|
System.out.println("Metacat login failed." + e.getMessage());
|
286
|
}
|
287
|
}
|
288
|
}
|
289
|
|
290
|
|
291
|
/**
|
292
|
* Logout from Metacat
|
293
|
*/
|
294
|
private void metacatLogout() {
|
295
|
Metacat metacat = harvester.metacat;
|
296
|
|
297
|
if (harvester.connectToMetacat()) {
|
298
|
try {
|
299
|
// Log out from the Metacat session
|
300
|
System.out.println("Logging out from Metacat");
|
301
|
metacat.logout();
|
302
|
}
|
303
|
catch (MetacatInaccessibleException e) {
|
304
|
System.out.println("Metacat inaccessible: " + e.getMessage());
|
305
|
}
|
306
|
catch (MetacatException e) {
|
307
|
System.out.println("Metacat exception: " + e.getMessage());
|
308
|
}
|
309
|
}
|
310
|
}
|
311
|
|
312
|
|
313
|
/**
|
314
|
* Parses the site harvest list XML file to find out which documents to
|
315
|
* harvest.
|
316
|
*
|
317
|
* @return true if successful, otherwise false
|
318
|
*/
|
319
|
public boolean parseHarvestList()
|
320
|
throws ParserConfigurationException {
|
321
|
DocumentListHandler documentListHandler = new DocumentListHandler();
|
322
|
InputStream inputStream;
|
323
|
InputStreamReader inputStreamReader;
|
324
|
String schemaLocation = getSchemaLocation();
|
325
|
boolean success = false;
|
326
|
URL url;
|
327
|
|
328
|
try {
|
329
|
url = new URL(documentListURL);
|
330
|
inputStream = url.openStream();
|
331
|
harvester.addLogEntry(0,
|
332
|
"Retrieved: " + documentListURL,
|
333
|
"GetHarvestListSuccess",
|
334
|
siteScheduleID,
|
335
|
null,
|
336
|
"");
|
337
|
inputStreamReader = new InputStreamReader(inputStream);
|
338
|
documentListHandler.runParser(inputStreamReader, schemaLocation);
|
339
|
harvester.addLogEntry(0,
|
340
|
"Validated: " + documentListURL,
|
341
|
"ValidateHarvestListSuccess",
|
342
|
siteScheduleID,
|
343
|
null,
|
344
|
"");
|
345
|
success = true;
|
346
|
}
|
347
|
catch (MalformedURLException e){
|
348
|
harvester.addLogEntry(1, "MalformedURLException: " + e.getMessage(),
|
349
|
"GetHarvestListError", siteScheduleID, null, "");
|
350
|
}
|
351
|
catch (FileNotFoundException e) {
|
352
|
harvester.addLogEntry(1, "FileNotFoundException: " + e.getMessage(),
|
353
|
"GetHarvestListError", siteScheduleID, null, "");
|
354
|
}
|
355
|
catch (SAXException e) {
|
356
|
harvester.addLogEntry(1, "SAXException: " + e.getMessage(),
|
357
|
"ValidateHarvestListError", siteScheduleID, null, "");
|
358
|
}
|
359
|
catch (ClassNotFoundException e) {
|
360
|
harvester.addLogEntry(1, "ClassNotFoundException: " + e.getMessage(),
|
361
|
"ValidateHarvestListError", siteScheduleID, null, "");
|
362
|
}
|
363
|
catch (IOException e) {
|
364
|
harvester.addLogEntry(1, "IOException: " + e.getMessage(),
|
365
|
"GetHarvestListError", siteScheduleID, null, "");
|
366
|
}
|
367
|
|
368
|
return success;
|
369
|
}
|
370
|
|
371
|
|
372
|
/**
|
373
|
* Prints the data that is stored in this HarvestSiteSchedule object.
|
374
|
*
|
375
|
* @param out the PrintStream to write to
|
376
|
*/
|
377
|
public void printOutput(PrintStream out) {
|
378
|
out.println("* siteScheduleID: " + siteScheduleID);
|
379
|
out.println("* documentListURL: " + documentListURL);
|
380
|
out.println("* ldapDN: " + ldapDN);
|
381
|
out.println("* dateNextHarvest: " + dateNextHarvest);
|
382
|
out.println("* dateLastHarvest: " + dateLastHarvest);
|
383
|
out.println("* updateFrequency: " + updateFrequency);
|
384
|
out.println("* unit: " + unit);
|
385
|
out.println("* contactEmail: " + contactEmail);
|
386
|
}
|
387
|
|
388
|
/**
|
389
|
* Reports a summary of the site harvest. Includes the following:
|
390
|
* A list of documents that were successfully inserted.
|
391
|
* A list of documents that were successfully updated.
|
392
|
* A list of documents that could not be accessed at the site.
|
393
|
* A list of documents that could not be uploaded to Metacat.
|
394
|
* A list of documents that were already found in Metacat.
|
395
|
*
|
396
|
* @param out the PrintStream to write to
|
397
|
*/
|
398
|
void printSiteSummary(PrintStream out) {
|
399
|
HarvestDocument harvestDocument;
|
400
|
int nAccessError = 0;
|
401
|
int nInserted = 0;
|
402
|
int nMetacatHasIt = 0;
|
403
|
int nUpdated = 0;
|
404
|
int nUploadError = 0;
|
405
|
|
406
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
407
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
408
|
|
409
|
if (harvestDocument != null) {
|
410
|
if (harvestDocument.accessError) { nAccessError++; }
|
411
|
if (harvestDocument.inserted) { nInserted++; }
|
412
|
if (harvestDocument.metacatHasIt) { nMetacatHasIt++; }
|
413
|
if (harvestDocument.updated) { nUpdated++; }
|
414
|
if (harvestDocument.uploadError) { nUploadError++; }
|
415
|
}
|
416
|
}
|
417
|
|
418
|
if (nInserted > 0) {
|
419
|
printSiteSummaryHeader(out);
|
420
|
out.println("* The following document(s) were successfully inserted:");
|
421
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
422
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
423
|
if (harvestDocument != null) {
|
424
|
if (harvestDocument.inserted) {
|
425
|
harvestDocument.prettyPrint(out);
|
426
|
}
|
427
|
}
|
428
|
}
|
429
|
printSiteSummaryTrailer(out);
|
430
|
}
|
431
|
|
432
|
if (nUpdated > 0) {
|
433
|
printSiteSummaryHeader(out);
|
434
|
out.println("* The following document(s) were successfully updated:");
|
435
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
436
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
437
|
if (harvestDocument != null) {
|
438
|
if (harvestDocument.updated) {
|
439
|
harvestDocument.prettyPrint(out);
|
440
|
}
|
441
|
}
|
442
|
}
|
443
|
printSiteSummaryTrailer(out);
|
444
|
}
|
445
|
|
446
|
if (nAccessError > 0) {
|
447
|
printSiteSummaryHeader(out);
|
448
|
out.println("* The following document(s) could not be accessed");
|
449
|
out.println("* at the site. Please check the URL to ensure that it is");
|
450
|
out.println("* accessible at the site.");
|
451
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
452
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
453
|
if (harvestDocument != null) {
|
454
|
if (harvestDocument.accessError) {
|
455
|
harvestDocument.prettyPrint(out);
|
456
|
}
|
457
|
}
|
458
|
}
|
459
|
printSiteSummaryTrailer(out);
|
460
|
}
|
461
|
|
462
|
if (nUploadError > 0) {
|
463
|
printSiteSummaryHeader(out);
|
464
|
out.println("* The following document(s) could not be uploaded to");
|
465
|
out.println("* Metacat because an error of some kind occurred.");
|
466
|
out.println("* See log entries below for additional details.) :");
|
467
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
468
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
469
|
if (harvestDocument != null) {
|
470
|
if (harvestDocument.uploadError) {
|
471
|
harvestDocument.prettyPrint(out);
|
472
|
}
|
473
|
}
|
474
|
}
|
475
|
printSiteSummaryTrailer(out);
|
476
|
}
|
477
|
|
478
|
if (nMetacatHasIt > 0) {
|
479
|
printSiteSummaryHeader(out);
|
480
|
out.println("* The following document(s) were already found in Metacat.");
|
481
|
out.println("* See log entries below for additional details.) :");
|
482
|
for (int i = 0; i < harvestDocumentList.size(); i++) {
|
483
|
harvestDocument = (HarvestDocument) harvestDocumentList.get(i);
|
484
|
if (harvestDocument != null) {
|
485
|
if (harvestDocument.metacatHasIt) {
|
486
|
harvestDocument.prettyPrint(out);
|
487
|
}
|
488
|
}
|
489
|
}
|
490
|
printSiteSummaryTrailer(out);
|
491
|
}
|
492
|
|
493
|
}
|
494
|
|
495
|
|
496
|
/**
|
497
|
* Prints the header lines of a site summary entry.
|
498
|
*
|
499
|
* @param out the PrintStream to write to
|
500
|
*/
|
501
|
void printSiteSummaryHeader(PrintStream out) {
|
502
|
final String filler = Harvester.filler;
|
503
|
final String marker = Harvester.marker;
|
504
|
|
505
|
out.println("");
|
506
|
out.println(marker);
|
507
|
out.println(filler);
|
508
|
}
|
509
|
|
510
|
|
511
|
/**
|
512
|
* Prints the trailing lines of a site summary entry.
|
513
|
*
|
514
|
* @param out the PrintStream to write to
|
515
|
*/
|
516
|
void printSiteSummaryTrailer(PrintStream out) {
|
517
|
final String filler = Harvester.filler;
|
518
|
final String marker = Harvester.marker;
|
519
|
|
520
|
out.println(filler);
|
521
|
out.println(marker);
|
522
|
}
|
523
|
|
524
|
|
525
|
/**
|
526
|
* Sends a report to the Site Contact summarizing the results of the harvest
|
527
|
* at that site.
|
528
|
*/
|
529
|
void reportToSiteContact() {
|
530
|
PrintStream body;
|
531
|
String from = harvester.harvesterAdministrator;
|
532
|
String[] fromArray;
|
533
|
String maxCodeLevel = "info";
|
534
|
MailMessage msg;
|
535
|
int nErrors = 0;
|
536
|
String subject = "Report from Metacat Harvester: " + harvester.timestamp;
|
537
|
String to = contactEmail;
|
538
|
String[] toArray;
|
539
|
|
540
|
if (!to.equals("")) {
|
541
|
System.out.println("Sending report to siteScheduleID=" + siteScheduleID +
|
542
|
" at address: " + contactEmail);
|
543
|
try {
|
544
|
msg = new MailMessage(harvester.smtpServer);
|
545
|
|
546
|
if (from.indexOf(',') > 0) {
|
547
|
fromArray = from.split(",");
|
548
|
|
549
|
for (int i = 0; i < fromArray.length; i++) {
|
550
|
if (i == 0) {
|
551
|
msg.from(fromArray[i]);
|
552
|
}
|
553
|
|
554
|
msg.cc(fromArray[i]);
|
555
|
|
556
|
}
|
557
|
}
|
558
|
else if (from.indexOf(';') > 0) {
|
559
|
fromArray = from.split(";");
|
560
|
|
561
|
for (int i = 0; i < fromArray.length; i++) {
|
562
|
if (i == 0) {
|
563
|
msg.from(fromArray[i]);
|
564
|
}
|
565
|
|
566
|
msg.cc(fromArray[i]);
|
567
|
|
568
|
}
|
569
|
}
|
570
|
else {
|
571
|
msg.from(from);
|
572
|
msg.cc(from);
|
573
|
}
|
574
|
|
575
|
if (to.indexOf(',') > 0) {
|
576
|
toArray = to.split(",");
|
577
|
|
578
|
for (int i = 0; i < toArray.length; i++) {
|
579
|
msg.to(toArray[i]);
|
580
|
}
|
581
|
}
|
582
|
else if (to.indexOf(';') > 0) {
|
583
|
toArray = to.split(";");
|
584
|
|
585
|
for (int i = 0; i < toArray.length; i++) {
|
586
|
msg.to(toArray[i]);
|
587
|
}
|
588
|
}
|
589
|
else {
|
590
|
msg.to(to);
|
591
|
}
|
592
|
|
593
|
msg.setSubject(subject);
|
594
|
body = msg.getPrintStream();
|
595
|
harvester.printHarvestHeader(body, siteScheduleID);
|
596
|
printSiteSummary(body);
|
597
|
harvester.printHarvestLog(body, maxCodeLevel, siteScheduleID);
|
598
|
msg.sendAndClose();
|
599
|
}
|
600
|
catch (IOException e) {
|
601
|
System.out.println("There was a problem sending email to " + to);
|
602
|
System.out.println("IOException: " + e.getMessage());
|
603
|
}
|
604
|
}
|
605
|
}
|
606
|
|
607
|
|
608
|
/**
|
609
|
* Accessor method for setting the value of the schemaLocation field.
|
610
|
*
|
611
|
* @param schemaLocation the new value of the schemaLocation field
|
612
|
*/
|
613
|
public void setSchemaLocation(String schemaLocation) {
|
614
|
this.schemaLocation = schemaLocation;
|
615
|
}
|
616
|
|
617
|
|
618
|
/**
|
619
|
* This inner class extends DefaultHandler. It parses the document list,
|
620
|
* creating a new HarvestDocument object every time it finds a </Document>
|
621
|
* end tag.
|
622
|
*/
|
623
|
class DocumentListHandler extends DefaultHandler implements ErrorHandler {
|
624
|
|
625
|
public String scope;
|
626
|
public int identifier;
|
627
|
public String identifierString;
|
628
|
public String documentType;
|
629
|
public int revision;
|
630
|
public String revisionString;
|
631
|
public String documentURL;
|
632
|
private String currentQname;
|
633
|
public final static String DEFAULT_PARSER =
|
634
|
"org.apache.xerces.parsers.SAXParser";
|
635
|
private boolean schemaValidate = true;
|
636
|
|
637
|
|
638
|
/**
|
639
|
* This method is called for any plain text within an element.
|
640
|
* It parses the value for any of the following elements:
|
641
|
* <scope>, <identifier>, <revision>, <documentType>, <documentURL>
|
642
|
*
|
643
|
* @param ch the character array holding the parsed text
|
644
|
* @param start the start index
|
645
|
* @param length the text length
|
646
|
*
|
647
|
*/
|
648
|
public void characters (char ch[], int start, int length) {
|
649
|
String s = new String(ch, start, length);
|
650
|
|
651
|
if (length > 0) {
|
652
|
if (currentQname.equals("scope")) {
|
653
|
scope += s;
|
654
|
}
|
655
|
else if (currentQname.equals("identifier")) {
|
656
|
identifierString += s;
|
657
|
}
|
658
|
else if (currentQname.equals("revision")) {
|
659
|
revisionString += s;
|
660
|
}
|
661
|
else if (currentQname.equals("documentType")) {
|
662
|
documentType += s;
|
663
|
}
|
664
|
else if (currentQname.equals("documentURL")) {
|
665
|
documentURL += s;
|
666
|
}
|
667
|
}
|
668
|
}
|
669
|
|
670
|
|
671
|
/**
|
672
|
* Handles an end-of-document event.
|
673
|
*/
|
674
|
public void endDocument () {
|
675
|
System.out.println("Finished parsing " + documentListURL);
|
676
|
}
|
677
|
|
678
|
|
679
|
/**
|
680
|
* Handles an end-of-element event. If the end tag is </Document>, then
|
681
|
* creates a new HarvestDocument object and pushes it to the document
|
682
|
* list.
|
683
|
*
|
684
|
* @param uri
|
685
|
* @param localname
|
686
|
* @param qname
|
687
|
*/
|
688
|
public void endElement(String uri,
|
689
|
String localname,
|
690
|
String qname) {
|
691
|
|
692
|
HarvestDocument harvestDocument;
|
693
|
|
694
|
if (qname.equals("identifier")) {
|
695
|
identifier = Integer.parseInt(identifierString);
|
696
|
}
|
697
|
else if (qname.equals("revision")) {
|
698
|
revision = Integer.parseInt(revisionString);
|
699
|
}
|
700
|
else if (qname.equals("document")) {
|
701
|
harvestDocument = new HarvestDocument(
|
702
|
harvester,
|
703
|
HarvestSiteSchedule.this,
|
704
|
scope,
|
705
|
identifier,
|
706
|
revision,
|
707
|
documentType,
|
708
|
documentURL
|
709
|
);
|
710
|
harvestDocumentList.add(harvestDocument);
|
711
|
}
|
712
|
|
713
|
currentQname = "";
|
714
|
}
|
715
|
|
716
|
|
717
|
/**
|
718
|
* Method for handling errors during a parse
|
719
|
*
|
720
|
* @param exception The parsing error
|
721
|
* @exception SAXException Description of Exception
|
722
|
*/
|
723
|
public void error(SAXParseException e) throws SAXParseException {
|
724
|
System.out.println("SAXParseException: " + e.getMessage());
|
725
|
throw e;
|
726
|
}
|
727
|
|
728
|
|
729
|
/**
|
730
|
* Run the validating parser
|
731
|
*
|
732
|
* @param xml the xml stream to be validated
|
733
|
* @schemaLocation relative path the to XML Schema file, e.g. "."
|
734
|
* @exception IOException thrown when test files can't be opened
|
735
|
* @exception ClassNotFoundException thrown when SAX Parser class not found
|
736
|
* @exception SAXException
|
737
|
* @exception SAXParserException
|
738
|
*/
|
739
|
public void runParser(Reader xml, String schemaLocation)
|
740
|
throws IOException, ClassNotFoundException,
|
741
|
SAXException, SAXParseException {
|
742
|
|
743
|
// Get an instance of the parser
|
744
|
XMLReader parser;
|
745
|
|
746
|
parser = XMLReaderFactory.createXMLReader(DEFAULT_PARSER);
|
747
|
// Set Handlers in the parser
|
748
|
parser.setContentHandler((ContentHandler)this);
|
749
|
parser.setErrorHandler((ErrorHandler)this);
|
750
|
parser.setFeature("http://xml.org/sax/features/namespaces", true);
|
751
|
parser.setFeature("http://xml.org/sax/features/namespace-prefixes", true);
|
752
|
parser.setFeature("http://xml.org/sax/features/validation", true);
|
753
|
parser.setProperty(
|
754
|
"http://apache.org/xml/properties/schema/external-schemaLocation",
|
755
|
schemaLocation);
|
756
|
|
757
|
if (schemaValidate) {
|
758
|
parser.setFeature("http://apache.org/xml/features/validation/schema",
|
759
|
true);
|
760
|
}
|
761
|
|
762
|
// Parse the document
|
763
|
parser.parse(new InputSource(xml));
|
764
|
}
|
765
|
/**
|
766
|
* Handles a start-of-document event.
|
767
|
*/
|
768
|
public void startDocument () {
|
769
|
System.out.println("Started parsing " + documentListURL);
|
770
|
}
|
771
|
|
772
|
|
773
|
/**
|
774
|
* Handles a start-of-element event.
|
775
|
*
|
776
|
* @param uri
|
777
|
* @param localname
|
778
|
* @param qname
|
779
|
* @param attributes
|
780
|
*/
|
781
|
public void startElement(String uri,
|
782
|
String localname,
|
783
|
String qname,
|
784
|
Attributes attributes) {
|
785
|
|
786
|
currentQname = qname;
|
787
|
|
788
|
if (qname.equals("scope")) {
|
789
|
scope = "";
|
790
|
}
|
791
|
else if (qname.equals("identifier")) {
|
792
|
identifierString = "";
|
793
|
}
|
794
|
else if (qname.equals("revision")) {
|
795
|
revisionString = "";
|
796
|
}
|
797
|
else if (qname.equals("documentType")) {
|
798
|
documentType = "";
|
799
|
}
|
800
|
else if (qname.equals("documentURL")) {
|
801
|
documentURL = "";
|
802
|
}
|
803
|
}
|
804
|
}
|
805
|
}
|