| 1 |
2022
|
costa
|
/*
|
| 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 |
2086
|
costa
|
import java.io.PrintStream;
|
| 13 |
2022
|
costa
|
import java.io.StringReader;
|
| 14 |
|
|
import java.net.MalformedURLException;
|
| 15 |
|
|
import java.net.URL;
|
| 16 |
2036
|
costa
|
import java.sql.ResultSet;
|
| 17 |
|
|
import java.sql.SQLException;
|
| 18 |
|
|
import java.sql.Statement;
|
| 19 |
2022
|
costa
|
|
| 20 |
2031
|
costa
|
import edu.ucsb.nceas.metacat.client.InsufficientKarmaException;
|
| 21 |
|
|
import edu.ucsb.nceas.metacat.client.Metacat;
|
| 22 |
|
|
import edu.ucsb.nceas.metacat.client.MetacatException;
|
| 23 |
|
|
import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;
|
| 24 |
2022
|
costa
|
import edu.ucsb.nceas.utilities.IOUtil;
|
| 25 |
|
|
|
| 26 |
|
|
|
| 27 |
|
|
/**
|
| 28 |
|
|
* HarvestDocument manages operations and data for a single document to be
|
| 29 |
|
|
* harvested.
|
| 30 |
|
|
*
|
| 31 |
|
|
* @author costa
|
| 32 |
|
|
*/
|
| 33 |
|
|
public class HarvestDocument {
|
| 34 |
2036
|
costa
|
|
| 35 |
|
|
|
| 36 |
|
|
private String docid; // scope + identifier
|
| 37 |
|
|
private String docidFull; // scope + identifier + revision
|
| 38 |
2031
|
costa
|
String documentType;
|
| 39 |
|
|
String documentURL;
|
| 40 |
2022
|
costa
|
private Harvester harvester;
|
| 41 |
|
|
private HarvestSiteSchedule harvestSiteSchedule;
|
| 42 |
2031
|
costa
|
int identifier;
|
| 43 |
|
|
int revision;
|
| 44 |
|
|
String scope;
|
| 45 |
2022
|
costa
|
|
| 46 |
|
|
|
| 47 |
|
|
/**
|
| 48 |
|
|
* Creates a new instance of HarvestDocument. Initialized with the data
|
| 49 |
|
|
* that was read from a single <document> element in site document list.
|
| 50 |
|
|
*
|
| 51 |
|
|
* @param harvester the parent Harvester object
|
| 52 |
|
|
* @param harvestSiteSchedule the parent HarvestSiteSchedule object
|
| 53 |
|
|
* @param scope the value of the <scope> element
|
| 54 |
|
|
* @param identifier the value of the <identifier> element
|
| 55 |
|
|
* @param revision the value of the <revision> element
|
| 56 |
|
|
* @param documentType the value of the <documentType> element
|
| 57 |
|
|
* @param documentURL the value of the <documentURL> element
|
| 58 |
|
|
*/
|
| 59 |
|
|
public HarvestDocument(
|
| 60 |
|
|
Harvester harvester,
|
| 61 |
|
|
HarvestSiteSchedule harvestSiteSchedule,
|
| 62 |
|
|
String scope,
|
| 63 |
|
|
int identifier,
|
| 64 |
|
|
int revision,
|
| 65 |
|
|
String documentType,
|
| 66 |
|
|
String documentURL
|
| 67 |
|
|
) {
|
| 68 |
|
|
this.harvester = harvester;
|
| 69 |
|
|
this.harvestSiteSchedule = harvestSiteSchedule;
|
| 70 |
|
|
this.documentType = documentType;
|
| 71 |
|
|
this.documentURL = documentURL;
|
| 72 |
|
|
this.scope = scope;
|
| 73 |
|
|
this.identifier = identifier;
|
| 74 |
|
|
this.revision = revision;
|
| 75 |
|
|
|
| 76 |
2036
|
costa
|
this.docid = scope + "." + identifier;
|
| 77 |
|
|
this.docidFull = this.docid + "." + revision;
|
| 78 |
2022
|
costa
|
}
|
| 79 |
|
|
|
| 80 |
|
|
|
| 81 |
|
|
/**
|
| 82 |
|
|
* Retrieve the document from the site using its <documentURL> value.
|
| 83 |
|
|
*
|
| 84 |
|
|
* @return A StringReader containing the document string.
|
| 85 |
|
|
*/
|
| 86 |
|
|
private StringReader getSiteDocument() {
|
| 87 |
|
|
String documentString;
|
| 88 |
|
|
InputStream inputStream;
|
| 89 |
|
|
InputStreamReader inputStreamReader;
|
| 90 |
|
|
StringReader stringReader = null;
|
| 91 |
|
|
URL url;
|
| 92 |
|
|
|
| 93 |
|
|
try {
|
| 94 |
|
|
url = new URL(documentURL);
|
| 95 |
|
|
inputStream = url.openStream();
|
| 96 |
|
|
inputStreamReader = new InputStreamReader(inputStream);
|
| 97 |
|
|
documentString = IOUtil.getAsString(inputStreamReader, true);
|
| 98 |
|
|
stringReader = new StringReader(documentString);
|
| 99 |
2036
|
costa
|
harvester.addLogEntry(0,
|
| 100 |
|
|
"Retrieved: " + documentURL,
|
| 101 |
|
|
"GetDocSuccess",
|
| 102 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 103 |
|
|
null,
|
| 104 |
|
|
"");
|
| 105 |
2022
|
costa
|
}
|
| 106 |
|
|
catch (MalformedURLException e) {
|
| 107 |
2031
|
costa
|
harvester.addLogEntry(1, "MalformedURLException", "GetDocError",
|
| 108 |
|
|
harvestSiteSchedule.siteScheduleID, this,
|
| 109 |
|
|
"MalformedURLException: " + e.getMessage());
|
| 110 |
2022
|
costa
|
}
|
| 111 |
|
|
catch (IOException e) {
|
| 112 |
2031
|
costa
|
harvester.addLogEntry(1, "IOException", "GetDocError",
|
| 113 |
|
|
harvestSiteSchedule.siteScheduleID, this,
|
| 114 |
|
|
"IOException: " + e.getMessage());
|
| 115 |
2022
|
costa
|
}
|
| 116 |
|
|
|
| 117 |
|
|
return stringReader;
|
| 118 |
|
|
}
|
| 119 |
|
|
|
| 120 |
|
|
|
| 121 |
|
|
/**
|
| 122 |
|
|
* Harvest the document from the site. Unless Metacat already has the
|
| 123 |
|
|
* document, retrieve the document from the site and put (insert or
|
| 124 |
|
|
* update) it to Metacat. If Metacat already has the document, determine
|
| 125 |
|
|
* the highest revision stored in Metacat so that this can be reported
|
| 126 |
|
|
* back to the user.
|
| 127 |
|
|
*/
|
| 128 |
|
|
public void harvestDocument() {
|
| 129 |
|
|
int highestRevision;
|
| 130 |
2036
|
costa
|
boolean insert = false;
|
| 131 |
2022
|
costa
|
String metacatReturnString;
|
| 132 |
|
|
StringReader stringReader;
|
| 133 |
2036
|
costa
|
boolean update = false;
|
| 134 |
2022
|
costa
|
|
| 135 |
|
|
/* If metacat already has this document, determine the highest revision in
|
| 136 |
|
|
* metacat and report it to the user; else, insert or delete the document
|
| 137 |
|
|
* into metacat.
|
| 138 |
|
|
*/
|
| 139 |
2036
|
costa
|
highestRevision = metacatHighestRevision();
|
| 140 |
|
|
|
| 141 |
|
|
if (highestRevision == -1) {
|
| 142 |
|
|
insert = true;
|
| 143 |
|
|
}
|
| 144 |
|
|
else if (revision > highestRevision) {
|
| 145 |
|
|
update = true;
|
| 146 |
|
|
}
|
| 147 |
|
|
else {
|
| 148 |
2031
|
costa
|
harvester.addLogEntry(0,
|
| 149 |
2036
|
costa
|
"Attempting to update " + docid + " to revision " +
|
| 150 |
|
|
revision + ". Metacat has document revision " +
|
| 151 |
|
|
highestRevision + ".",
|
| 152 |
2031
|
costa
|
"MetacatHasDoc",
|
| 153 |
2036
|
costa
|
harvestSiteSchedule.siteScheduleID,
|
| 154 |
|
|
null,
|
| 155 |
|
|
"");
|
| 156 |
2022
|
costa
|
}
|
| 157 |
2036
|
costa
|
|
| 158 |
|
|
if (insert || update) {
|
| 159 |
2022
|
costa
|
stringReader = getSiteDocument();
|
| 160 |
|
|
if (stringReader != null) {
|
| 161 |
2036
|
costa
|
if (validateDocument()) {
|
| 162 |
|
|
putMetacatDocument(insert, update, stringReader);
|
| 163 |
2022
|
costa
|
}
|
| 164 |
|
|
}
|
| 165 |
|
|
}
|
| 166 |
|
|
}
|
| 167 |
2031
|
costa
|
|
| 168 |
2022
|
costa
|
|
| 169 |
|
|
/**
|
| 170 |
2031
|
costa
|
* Logs a metacat document error to the harvest detail log.
|
| 171 |
|
|
*
|
| 172 |
|
|
* @param insert true if insert operation, false is update
|
| 173 |
|
|
* @param metacatReturnString string returned from the insert or update
|
| 174 |
|
|
* @param exceptionName name of the exception class
|
| 175 |
|
|
* @param e the exception object
|
| 176 |
|
|
*/
|
| 177 |
|
|
private void logMetacatError (boolean insert,
|
| 178 |
|
|
String metacatReturnString,
|
| 179 |
|
|
String exceptionName,
|
| 180 |
|
|
Exception e
|
| 181 |
|
|
) {
|
| 182 |
|
|
if (insert) {
|
| 183 |
2036
|
costa
|
harvester.addLogEntry(1,
|
| 184 |
|
|
metacatReturnString,
|
| 185 |
|
|
"InsertDocError",
|
| 186 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 187 |
|
|
this,
|
| 188 |
|
|
exceptionName + ": " + e.getMessage());
|
| 189 |
2031
|
costa
|
}
|
| 190 |
|
|
else {
|
| 191 |
2036
|
costa
|
harvester.addLogEntry(1,
|
| 192 |
|
|
metacatReturnString,
|
| 193 |
|
|
"UpdateDocError",
|
| 194 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 195 |
|
|
this,
|
| 196 |
|
|
exceptionName + ": " + e.getMessage());
|
| 197 |
2031
|
costa
|
}
|
| 198 |
|
|
}
|
| 199 |
|
|
|
| 200 |
|
|
|
| 201 |
|
|
/**
|
| 202 |
2022
|
costa
|
* Determines the highest revision that Metacat has for this document.
|
| 203 |
|
|
*
|
| 204 |
2036
|
costa
|
* @return int representing the highest revision for this document in
|
| 205 |
|
|
* Metacat. Returns -1 if Metacat does not currently hold the
|
| 206 |
|
|
* document.
|
| 207 |
2022
|
costa
|
*/
|
| 208 |
|
|
private int metacatHighestRevision() {
|
| 209 |
2036
|
costa
|
int highestRevision = -1;
|
| 210 |
|
|
String query = "SELECT REV FROM XML_DOCUMENTS WHERE DOCID = " +
|
| 211 |
|
|
"'" + docid + "'";
|
| 212 |
|
|
Statement stmt;
|
| 213 |
2022
|
costa
|
|
| 214 |
2036
|
costa
|
try {
|
| 215 |
|
|
stmt = harvester.conn.createStatement();
|
| 216 |
|
|
ResultSet rs = stmt.executeQuery(query);
|
| 217 |
|
|
|
| 218 |
|
|
while (rs.next()) {
|
| 219 |
|
|
highestRevision = rs.getInt("REV");
|
| 220 |
|
|
}
|
| 221 |
|
|
|
| 222 |
|
|
stmt.close();
|
| 223 |
|
|
}
|
| 224 |
|
|
catch(SQLException e) {
|
| 225 |
|
|
System.out.println("SQLException: " + e.getMessage());
|
| 226 |
2031
|
costa
|
}
|
| 227 |
2036
|
costa
|
|
| 228 |
|
|
return highestRevision;
|
| 229 |
2022
|
costa
|
}
|
| 230 |
|
|
|
| 231 |
|
|
|
| 232 |
|
|
/**
|
| 233 |
|
|
* Print the data fields and values in this HarvestDocument object.
|
| 234 |
2086
|
costa
|
*
|
| 235 |
|
|
* @param out the PrintStream to write to
|
| 236 |
2022
|
costa
|
*/
|
| 237 |
2086
|
costa
|
void printOutput(PrintStream out) {
|
| 238 |
|
|
out.println("* scope: " + scope);
|
| 239 |
|
|
out.println("* identifier: " + identifier);
|
| 240 |
|
|
out.println("* revision: " + revision);
|
| 241 |
|
|
out.println("* documentType: " + documentType);
|
| 242 |
|
|
out.println("* documentURL: " + documentURL);
|
| 243 |
2022
|
costa
|
}
|
| 244 |
|
|
|
| 245 |
|
|
|
| 246 |
|
|
/**
|
| 247 |
|
|
* Insert or update this document to Metacat. If revision equals 1, do an
|
| 248 |
|
|
* insert; otherwise, do an update.
|
| 249 |
2036
|
costa
|
*
|
| 250 |
|
|
* @param insert true if this is an insert operation
|
| 251 |
|
|
* @param update true if this is an update operation
|
| 252 |
|
|
* @param stringReader the StringReader object holding the document text
|
| 253 |
2022
|
costa
|
*/
|
| 254 |
2036
|
costa
|
private void putMetacatDocument(boolean insert,
|
| 255 |
|
|
boolean update,
|
| 256 |
|
|
StringReader stringReader) {
|
| 257 |
2022
|
costa
|
Metacat metacat = harvester.metacat;
|
| 258 |
|
|
String metacatReturnString = "";
|
| 259 |
2031
|
costa
|
|
| 260 |
2022
|
costa
|
if (harvester.connectToMetacat()) {
|
| 261 |
|
|
try {
|
| 262 |
2031
|
costa
|
if (insert) {
|
| 263 |
2036
|
costa
|
metacatReturnString = metacat.insert(docidFull, stringReader, null);
|
| 264 |
|
|
harvester.addLogEntry(0, docidFull + " : " + metacatReturnString,
|
| 265 |
2031
|
costa
|
"InsertDocSuccess",
|
| 266 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 267 |
|
|
null, "");
|
| 268 |
2022
|
costa
|
}
|
| 269 |
2036
|
costa
|
else if (update) {
|
| 270 |
|
|
metacatReturnString = metacat.update(docidFull, stringReader, null);
|
| 271 |
|
|
harvester.addLogEntry(0, docidFull + " : " + metacatReturnString,
|
| 272 |
2031
|
costa
|
"UpdateDocSuccess",
|
| 273 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 274 |
|
|
null, "");
|
| 275 |
2022
|
costa
|
}
|
| 276 |
|
|
}
|
| 277 |
|
|
catch (MetacatInaccessibleException e) {
|
| 278 |
2031
|
costa
|
logMetacatError(insert, metacatReturnString,
|
| 279 |
|
|
"MetacatInaccessibleException", e);
|
| 280 |
2022
|
costa
|
}
|
| 281 |
|
|
catch (InsufficientKarmaException e) {
|
| 282 |
2031
|
costa
|
logMetacatError(insert, metacatReturnString,
|
| 283 |
|
|
"InsufficientKarmaException", e);
|
| 284 |
2022
|
costa
|
}
|
| 285 |
|
|
catch (MetacatException e) {
|
| 286 |
2031
|
costa
|
logMetacatError(insert, metacatReturnString, "MetacatException", e);
|
| 287 |
2022
|
costa
|
}
|
| 288 |
|
|
catch (IOException e) {
|
| 289 |
2031
|
costa
|
logMetacatError(insert, metacatReturnString, "IOException", e);
|
| 290 |
2022
|
costa
|
}
|
| 291 |
|
|
}
|
| 292 |
|
|
}
|
| 293 |
2036
|
costa
|
|
| 294 |
|
|
|
| 295 |
|
|
/**
|
| 296 |
|
|
* Validate the document to determine whether it is valid EML prior to
|
| 297 |
|
|
* inserting or updating it to Metacat. This is QA/QC measure.
|
| 298 |
|
|
* Not yet implemented.
|
| 299 |
|
|
*
|
| 300 |
|
|
* @return true if the document is valid EML, otherwise false
|
| 301 |
|
|
*/
|
| 302 |
|
|
private boolean validateDocument () {
|
| 303 |
|
|
boolean success = true;
|
| 304 |
|
|
|
| 305 |
|
|
/*if (success) {
|
| 306 |
|
|
harvester.addLogEntry(0,
|
| 307 |
|
|
"Validated: " + documentURL,
|
| 308 |
|
|
"ValidateDocSuccess",
|
| 309 |
|
|
harvestSiteSchedule.siteScheduleID,
|
| 310 |
|
|
null,
|
| 311 |
|
|
"");
|
| 312 |
|
|
}
|
| 313 |
|
|
else {
|
| 314 |
|
|
harvester.addLogEntry(1, "Error validating document", "ValidateDocError",
|
| 315 |
|
|
harvestSiteSchedule.siteScheduleID, this, "");
|
| 316 |
|
|
}*/
|
| 317 |
|
|
|
| 318 |
|
|
return success;
|
| 319 |
|
|
}
|
| 320 |
|
|
|
| 321 |
2022
|
costa
|
}
|