1
|
/*
|
2
|
* HarvestDocument.java
|
3
|
*
|
4
|
* Created on January 14, 2004, 4:37 PM
|
5
|
*/
|
6
|
|
7
|
package edu.ucsb.nceas.metacat.harvesterClient;
|
8
|
|
9
|
import java.io.InputStream;
|
10
|
import java.io.InputStreamReader;
|
11
|
import java.io.IOException;
|
12
|
import java.io.StringReader;
|
13
|
import java.net.MalformedURLException;
|
14
|
import java.net.URL;
|
15
|
|
16
|
import edu.ucsb.nceas.metacat.client.*;
|
17
|
import edu.ucsb.nceas.utilities.IOUtil;
|
18
|
|
19
|
|
20
|
/**
|
21
|
* HarvestDocument manages operations and data for a single document to be
|
22
|
* harvested.
|
23
|
*
|
24
|
* @author costa
|
25
|
*/
|
26
|
public class HarvestDocument {
|
27
|
|
28
|
private String documentName;
|
29
|
private String documentType;
|
30
|
private String documentURL;
|
31
|
private Harvester harvester;
|
32
|
private HarvestSiteSchedule harvestSiteSchedule;
|
33
|
private int identifier;
|
34
|
private int revision;
|
35
|
private String scope;
|
36
|
|
37
|
|
38
|
/**
|
39
|
* Creates a new instance of HarvestDocument. Initialized with the data
|
40
|
* that was read from a single <document> element in site document list.
|
41
|
*
|
42
|
* @param harvester the parent Harvester object
|
43
|
* @param harvestSiteSchedule the parent HarvestSiteSchedule object
|
44
|
* @param scope the value of the <scope> element
|
45
|
* @param identifier the value of the <identifier> element
|
46
|
* @param revision the value of the <revision> element
|
47
|
* @param documentType the value of the <documentType> element
|
48
|
* @param documentURL the value of the <documentURL> element
|
49
|
*/
|
50
|
public HarvestDocument(
|
51
|
Harvester harvester,
|
52
|
HarvestSiteSchedule harvestSiteSchedule,
|
53
|
String scope,
|
54
|
int identifier,
|
55
|
int revision,
|
56
|
String documentType,
|
57
|
String documentURL
|
58
|
) {
|
59
|
this.harvester = harvester;
|
60
|
this.harvestSiteSchedule = harvestSiteSchedule;
|
61
|
this.documentType = documentType;
|
62
|
this.documentURL = documentURL;
|
63
|
this.scope = scope;
|
64
|
this.identifier = identifier;
|
65
|
this.revision = revision;
|
66
|
|
67
|
this.documentName = scope + "." + identifier;
|
68
|
}
|
69
|
|
70
|
|
71
|
/**
|
72
|
* Retrieve the document from the site using its <documentURL> value.
|
73
|
*
|
74
|
* @return A StringReader containing the document string.
|
75
|
*/
|
76
|
private StringReader getSiteDocument() {
|
77
|
String documentString;
|
78
|
InputStream inputStream;
|
79
|
InputStreamReader inputStreamReader;
|
80
|
StringReader stringReader = null;
|
81
|
URL url;
|
82
|
|
83
|
try {
|
84
|
url = new URL(documentURL);
|
85
|
inputStream = url.openStream();
|
86
|
inputStreamReader = new InputStreamReader(inputStream);
|
87
|
documentString = IOUtil.getAsString(inputStreamReader, true);
|
88
|
stringReader = new StringReader(documentString);
|
89
|
System.out.println(" Successfully read document: " + documentURL);
|
90
|
}
|
91
|
catch (MalformedURLException e) {
|
92
|
System.err.println("MalformedURLException: " + e.getMessage());
|
93
|
}
|
94
|
catch (IOException e) {
|
95
|
System.err.println("IOException: " + e.getMessage());
|
96
|
}
|
97
|
|
98
|
return stringReader;
|
99
|
}
|
100
|
|
101
|
|
102
|
/**
|
103
|
* Harvest the document from the site. Unless Metacat already has the
|
104
|
* document, retrieve the document from the site and put (insert or
|
105
|
* update) it to Metacat. If Metacat already has the document, determine
|
106
|
* the highest revision stored in Metacat so that this can be reported
|
107
|
* back to the user.
|
108
|
*/
|
109
|
public void harvestDocument() {
|
110
|
int highestRevision;
|
111
|
String metacatReturnString;
|
112
|
StringReader stringReader;
|
113
|
|
114
|
/* If metacat already has this document, determine the highest revision in
|
115
|
* metacat and report it to the user; else, insert or delete the document
|
116
|
* into metacat.
|
117
|
*/
|
118
|
if (metacatHasDocument()) {
|
119
|
System.out.println(" metacat has document");
|
120
|
highestRevision = metacatHighestRevision();
|
121
|
System.out.println(" metacatHighestRevision: " + highestRevision);
|
122
|
}
|
123
|
else {
|
124
|
stringReader = getSiteDocument();
|
125
|
if (stringReader != null) {
|
126
|
if (parseDocument()) {
|
127
|
metacatReturnString = putMetacatDocument(stringReader);
|
128
|
System.out.println(" " + metacatReturnString);
|
129
|
}
|
130
|
else {
|
131
|
System.out.println("Error parsing document.");
|
132
|
}
|
133
|
}
|
134
|
else {
|
135
|
System.out.print(" Error reading document at URL: ");
|
136
|
System.out.println(documentURL);
|
137
|
}
|
138
|
}
|
139
|
}
|
140
|
|
141
|
|
142
|
/**
|
143
|
* Boolean to determine whether Metacat already has this document.
|
144
|
*
|
145
|
* @return true if Metacat has the document, otherwise false
|
146
|
*/
|
147
|
private boolean metacatHasDocument() {
|
148
|
boolean hasDocument = false;
|
149
|
|
150
|
return hasDocument;
|
151
|
}
|
152
|
|
153
|
|
154
|
/**
|
155
|
* Determines the highest revision that Metacat has for this document.
|
156
|
*
|
157
|
* @return int representing the highest revision for this document in Metacat
|
158
|
*/
|
159
|
private int metacatHighestRevision() {
|
160
|
int highestRevision = 0;
|
161
|
|
162
|
return highestRevision;
|
163
|
}
|
164
|
|
165
|
|
166
|
/**
|
167
|
* Parse the document to determine whether it is valid EML prior to inserting
|
168
|
* or updating it to Metacat. This is QA/QC measure. Currently unimplemented.
|
169
|
*
|
170
|
* @return true if the document is valid EML, otherwise false
|
171
|
*/
|
172
|
private boolean parseDocument () {
|
173
|
boolean success = true;
|
174
|
|
175
|
return success;
|
176
|
}
|
177
|
|
178
|
|
179
|
/**
|
180
|
* Print the data fields and values in this HarvestDocument object.
|
181
|
*/
|
182
|
void printOutput()
|
183
|
{
|
184
|
System.out.println("");
|
185
|
System.out.println(" scope: " + scope);
|
186
|
System.out.println(" identifier: " + identifier);
|
187
|
System.out.println(" revision: " + revision);
|
188
|
System.out.println(" documentType: " + documentType);
|
189
|
System.out.println(" documentURL: " + documentURL);
|
190
|
System.out.println(" documentName: " + documentName);
|
191
|
}
|
192
|
|
193
|
|
194
|
/**
|
195
|
* Insert or update this document to Metacat. If revision equals 1, do an
|
196
|
* insert; otherwise, do an update.
|
197
|
*
|
198
|
* @return the Metacat return string from the insert or update operation
|
199
|
*/
|
200
|
private String putMetacatDocument(StringReader stringReader) {
|
201
|
String docid = scope + "." + identifier + "." + revision;
|
202
|
Metacat metacat = harvester.metacat;
|
203
|
String metacatReturnString = "";
|
204
|
|
205
|
if (harvester.connectToMetacat()) {
|
206
|
try {
|
207
|
if (revision == 1) {
|
208
|
System.out.println(" Inserting document to metacat: " + docid);
|
209
|
metacatReturnString = metacat.insert(docid, stringReader, null);
|
210
|
}
|
211
|
else {
|
212
|
System.out.println(" Updating document to metacat: " + docid);
|
213
|
metacatReturnString = metacat.update(docid, stringReader, null);
|
214
|
}
|
215
|
}
|
216
|
catch (MetacatInaccessibleException e) {
|
217
|
System.err.println("MetacatInaccessibleException: " + e.getMessage());
|
218
|
}
|
219
|
catch (InsufficientKarmaException e) {
|
220
|
System.err.println("InsufficientKarmaException: " + e.getMessage());
|
221
|
}
|
222
|
catch (MetacatException e) {
|
223
|
System.err.println("MetacatException: " + e.getMessage());
|
224
|
}
|
225
|
catch (IOException e) {
|
226
|
System.err.println("IOException: " + e.getMessage());
|
227
|
}
|
228
|
}
|
229
|
else {
|
230
|
metacatReturnString = "Not putting document to metacat";
|
231
|
}
|
232
|
|
233
|
return metacatReturnString;
|
234
|
}
|
235
|
|
236
|
}
|