1
|
/**
|
2
|
* '$RCSfile$'
|
3
|
* Copyright: 2004 University of New Mexico and the
|
4
|
* Regents of the University of California
|
5
|
*
|
6
|
* '$Author: daigle $'
|
7
|
* '$Date: 2008-07-28 17:07:03 -0700 (Mon, 28 Jul 2008) $'
|
8
|
* '$Revision: 4175 $'
|
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 java.io.InputStream;
|
28
|
import java.io.InputStreamReader;
|
29
|
import java.io.IOException;
|
30
|
import java.io.PrintStream;
|
31
|
import java.io.StringReader;
|
32
|
import java.net.MalformedURLException;
|
33
|
import java.net.URL;
|
34
|
import java.sql.Connection;
|
35
|
import java.sql.ResultSet;
|
36
|
import java.sql.SQLException;
|
37
|
import java.sql.Statement;
|
38
|
|
39
|
import edu.ucsb.nceas.metacat.client.InsufficientKarmaException;
|
40
|
import edu.ucsb.nceas.metacat.client.Metacat;
|
41
|
import edu.ucsb.nceas.metacat.client.MetacatException;
|
42
|
import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;
|
43
|
import edu.ucsb.nceas.utilities.IOUtil;
|
44
|
|
45
|
|
46
|
/**
|
47
|
* HarvestDocument manages operations and data for a single document to be
|
48
|
* harvested.
|
49
|
*
|
50
|
* @author costa
|
51
|
*/
|
52
|
public class HarvestDocument {
|
53
|
|
54
|
|
55
|
private String docid; // scope + identifier
|
56
|
private String docidFull; // scope + identifier + revision
|
57
|
String documentType;
|
58
|
String documentURL;
|
59
|
private Harvester harvester;
|
60
|
private HarvestSiteSchedule harvestSiteSchedule;
|
61
|
int identifier;
|
62
|
int revision;
|
63
|
String scope;
|
64
|
|
65
|
/* These booleans keep track of status information. They are used when
|
66
|
* generating email reports.
|
67
|
*/
|
68
|
boolean accessError = false;
|
69
|
boolean inserted = false;
|
70
|
boolean metacatHasIt = false;
|
71
|
boolean updated = false;
|
72
|
boolean uploadError = false;
|
73
|
|
74
|
|
75
|
/**
|
76
|
* Creates a new instance of HarvestDocument. Initialized with the data
|
77
|
* that was read from a single <document> element in site document list.
|
78
|
*
|
79
|
* @param harvester the parent Harvester object
|
80
|
* @param harvestSiteSchedule the parent HarvestSiteSchedule object
|
81
|
* @param scope the value of the <scope> element
|
82
|
* @param identifier the value of the <identifier> element
|
83
|
* @param revision the value of the <revision> element
|
84
|
* @param documentType the value of the <documentType> element
|
85
|
* @param documentURL the value of the <documentURL> element
|
86
|
*/
|
87
|
public HarvestDocument (
|
88
|
Harvester harvester,
|
89
|
HarvestSiteSchedule harvestSiteSchedule,
|
90
|
String scope,
|
91
|
int identifier,
|
92
|
int revision,
|
93
|
String documentType,
|
94
|
String documentURL
|
95
|
) {
|
96
|
this.harvester = harvester;
|
97
|
this.harvestSiteSchedule = harvestSiteSchedule;
|
98
|
this.documentType = documentType;
|
99
|
this.documentURL = documentURL;
|
100
|
this.scope = scope;
|
101
|
this.identifier = identifier;
|
102
|
this.revision = revision;
|
103
|
|
104
|
this.docid = scope + "." + identifier;
|
105
|
this.docidFull = this.docid + "." + revision;
|
106
|
}
|
107
|
|
108
|
|
109
|
/**
|
110
|
* Retrieve the document from the site using its <documentURL> value.
|
111
|
*
|
112
|
* @return A StringReader containing the document string.
|
113
|
*/
|
114
|
public StringReader getSiteDocument() {
|
115
|
String documentString;
|
116
|
InputStream inputStream;
|
117
|
InputStreamReader inputStreamReader;
|
118
|
StringReader stringReader = null;
|
119
|
URL url;
|
120
|
|
121
|
try {
|
122
|
url = new URL(documentURL);
|
123
|
inputStream = url.openStream();
|
124
|
inputStreamReader = new InputStreamReader(inputStream);
|
125
|
documentString = IOUtil.getAsString(inputStreamReader, true);
|
126
|
stringReader = new StringReader(documentString);
|
127
|
harvester.addLogEntry(0,
|
128
|
"Retrieved: " + documentURL,
|
129
|
"harvester.GetDocSuccess",
|
130
|
harvestSiteSchedule.siteScheduleID,
|
131
|
null,
|
132
|
"");
|
133
|
}
|
134
|
catch (MalformedURLException e) {
|
135
|
accessError = true;
|
136
|
harvester.addLogEntry(1, "MalformedURLException", "harvester.GetDocError",
|
137
|
harvestSiteSchedule.siteScheduleID, this,
|
138
|
"MalformedURLException: " + e.getMessage());
|
139
|
}
|
140
|
catch (IOException e) {
|
141
|
accessError = true;
|
142
|
harvester.addLogEntry(1, "IOException", "harvester.GetDocError",
|
143
|
harvestSiteSchedule.siteScheduleID, this,
|
144
|
"IOException: " + e.getMessage());
|
145
|
}
|
146
|
|
147
|
return stringReader;
|
148
|
}
|
149
|
|
150
|
|
151
|
/**
|
152
|
* Harvest the document from the site. Unless Metacat already has the
|
153
|
* document, retrieve the document from the site and put (insert or
|
154
|
* update) it to Metacat. If Metacat already has the document, determine
|
155
|
* the highest revision stored in Metacat so that this can be reported
|
156
|
* back to the user.
|
157
|
*/
|
158
|
public void harvestDocument() {
|
159
|
int highestRevision;
|
160
|
boolean insert = false;
|
161
|
String metacatReturnString;
|
162
|
StringReader stringReader;
|
163
|
boolean update = false;
|
164
|
|
165
|
/* If metacat already has this document, determine the highest revision in
|
166
|
* metacat and report it to the user; else, insert or delete the document
|
167
|
* into metacat.
|
168
|
*/
|
169
|
highestRevision = metacatHighestRevision();
|
170
|
|
171
|
if (highestRevision == -1) {
|
172
|
insert = true;
|
173
|
}
|
174
|
else if (revision > highestRevision) {
|
175
|
update = true;
|
176
|
}
|
177
|
else {
|
178
|
metacatHasIt = true;
|
179
|
harvester.addLogEntry(0,
|
180
|
"Attempting to update " + docid + " to revision " +
|
181
|
revision + ". Metacat has document revision " +
|
182
|
highestRevision + ".",
|
183
|
"harvester.MetacatHasDoc",
|
184
|
harvestSiteSchedule.siteScheduleID,
|
185
|
null,
|
186
|
"");
|
187
|
}
|
188
|
|
189
|
if (insert || update) {
|
190
|
stringReader = getSiteDocument();
|
191
|
if (stringReader != null) {
|
192
|
if (validateDocument()) {
|
193
|
putMetacatDocument(insert, update, stringReader);
|
194
|
}
|
195
|
}
|
196
|
}
|
197
|
}
|
198
|
|
199
|
|
200
|
/**
|
201
|
* Logs a metacat document error to the harvest detail log.
|
202
|
*
|
203
|
* @param insert true if insert operation, false is update
|
204
|
* @param metacatReturnString string returned from the insert or update
|
205
|
* @param exceptionName name of the exception class
|
206
|
* @param e the exception object
|
207
|
*/
|
208
|
private void logMetacatError (boolean insert,
|
209
|
String metacatReturnString,
|
210
|
String exceptionName,
|
211
|
Exception e
|
212
|
) {
|
213
|
uploadError = true;
|
214
|
|
215
|
if (insert) {
|
216
|
harvester.addLogEntry(1,
|
217
|
metacatReturnString,
|
218
|
"harvester.InsertDocError",
|
219
|
harvestSiteSchedule.siteScheduleID,
|
220
|
this,
|
221
|
exceptionName + ": " + e.getMessage());
|
222
|
}
|
223
|
else {
|
224
|
harvester.addLogEntry(1,
|
225
|
metacatReturnString,
|
226
|
"harvester.UpdateDocError",
|
227
|
harvestSiteSchedule.siteScheduleID,
|
228
|
this,
|
229
|
exceptionName + ": " + e.getMessage());
|
230
|
}
|
231
|
}
|
232
|
|
233
|
|
234
|
/**
|
235
|
* Determines the highest revision that Metacat has for this document.
|
236
|
*
|
237
|
* @return int representing the highest revision for this document in
|
238
|
* Metacat. Returns -1 if Metacat does not currently hold the
|
239
|
* document.
|
240
|
*/
|
241
|
public int metacatHighestRevision() {
|
242
|
Connection conn = harvester.getConnection();
|
243
|
int highestRevision = -1;
|
244
|
String query = "SELECT REV FROM XML_DOCUMENTS WHERE DOCID = " +
|
245
|
"'" + docid + "'";
|
246
|
Statement stmt;
|
247
|
|
248
|
try {
|
249
|
stmt = conn.createStatement();
|
250
|
ResultSet rs = stmt.executeQuery(query);
|
251
|
|
252
|
while (rs.next()) {
|
253
|
highestRevision = rs.getInt("REV");
|
254
|
}
|
255
|
|
256
|
stmt.close();
|
257
|
}
|
258
|
catch(SQLException e) {
|
259
|
System.out.println("SQLException: " + e.getMessage());
|
260
|
}
|
261
|
|
262
|
return highestRevision;
|
263
|
}
|
264
|
|
265
|
|
266
|
/**
|
267
|
* Print the data fields and values in this HarvestDocument object.
|
268
|
*
|
269
|
* @param out the PrintStream to write to
|
270
|
*/
|
271
|
public void printOutput(PrintStream out) {
|
272
|
out.println("* scope: " + scope);
|
273
|
out.println("* identifier: " + identifier);
|
274
|
out.println("* revision: " + revision);
|
275
|
out.println("* documentType: " + documentType);
|
276
|
out.println("* documentURL: " + documentURL);
|
277
|
}
|
278
|
|
279
|
|
280
|
/**
|
281
|
* Print the document URL following by its scope.identifier.revision.
|
282
|
* Used for report generation.
|
283
|
*
|
284
|
* @param out the PrintStream to write to
|
285
|
*/
|
286
|
public void prettyPrint(PrintStream out) {
|
287
|
out.println("* " + docidFull + " (" + documentURL + ")");
|
288
|
}
|
289
|
|
290
|
|
291
|
/**
|
292
|
* Insert or update this document to Metacat. If revision equals 1, do an
|
293
|
* insert; otherwise, do an update.
|
294
|
*
|
295
|
* @param insert true if this is an insert operation
|
296
|
* @param update true if this is an update operation
|
297
|
* @param stringReader the StringReader object holding the document text
|
298
|
*/
|
299
|
private void putMetacatDocument(boolean insert,
|
300
|
boolean update,
|
301
|
StringReader stringReader) {
|
302
|
Metacat metacat = harvester.metacat;
|
303
|
String metacatReturnString = "";
|
304
|
|
305
|
if (harvester.connectToMetacat()) {
|
306
|
try {
|
307
|
if (insert) {
|
308
|
metacatReturnString = metacat.insert(docidFull, stringReader, null);
|
309
|
inserted = true;
|
310
|
harvester.addLogEntry(0, docidFull + " : " + metacatReturnString,
|
311
|
"harvester.InsertDocSuccess",
|
312
|
harvestSiteSchedule.siteScheduleID,
|
313
|
null, "");
|
314
|
}
|
315
|
else if (update) {
|
316
|
metacatReturnString = metacat.update(docidFull, stringReader, null);
|
317
|
updated = true;
|
318
|
harvester.addLogEntry(0, docidFull + " : " + metacatReturnString,
|
319
|
"harvester.UpdateDocSuccess",
|
320
|
harvestSiteSchedule.siteScheduleID,
|
321
|
null, "");
|
322
|
}
|
323
|
}
|
324
|
catch (MetacatInaccessibleException e) {
|
325
|
logMetacatError(insert, metacatReturnString,
|
326
|
"MetacatInaccessibleException", e);
|
327
|
}
|
328
|
catch (InsufficientKarmaException e) {
|
329
|
logMetacatError(insert, metacatReturnString,
|
330
|
"InsufficientKarmaException", e);
|
331
|
}
|
332
|
catch (MetacatException e) {
|
333
|
logMetacatError(insert, metacatReturnString, "MetacatException", e);
|
334
|
}
|
335
|
catch (IOException e) {
|
336
|
logMetacatError(insert, metacatReturnString, "IOException", e);
|
337
|
}
|
338
|
}
|
339
|
}
|
340
|
|
341
|
|
342
|
/**
|
343
|
* Validate the document to determine whether it is valid EML prior to
|
344
|
* inserting or updating it to Metacat. This is QA/QC measure.
|
345
|
* Not yet implemented.
|
346
|
*
|
347
|
* @return true if the document is valid EML, otherwise false
|
348
|
*/
|
349
|
private boolean validateDocument () {
|
350
|
boolean success = true;
|
351
|
|
352
|
/*if (success) {
|
353
|
harvester.addLogEntry(0,
|
354
|
"Validated: " + documentURL,
|
355
|
"harvester.ValidateDocSuccess",
|
356
|
harvestSiteSchedule.siteScheduleID,
|
357
|
null,
|
358
|
"");
|
359
|
}
|
360
|
else {
|
361
|
harvester.addLogEntry(1, "Error validating document", "harvester.ValidateDocError",
|
362
|
harvestSiteSchedule.siteScheduleID, this, "");
|
363
|
}*/
|
364
|
|
365
|
return success;
|
366
|
}
|
367
|
|
368
|
}
|