Revision 2139
Added by Duane Costa about 20 years ago
| HarvestSiteSchedule.java | ||
|---|---|---|
| 63 | 63 |
* |
| 64 | 64 |
* @author costa |
| 65 | 65 |
*/ |
| 66 |
class HarvestSiteSchedule {
|
|
| 66 |
public class HarvestSiteSchedule {
|
|
| 67 | 67 |
|
| 68 | 68 |
private String contactEmail; |
| 69 | 69 |
private String dateLastHarvest; |
| ... | ... | |
| 77 | 77 |
private String ldapDN; |
| 78 | 78 |
private String ldapPwd; |
| 79 | 79 |
final private long millisecondsPerDay = (1000 * 60 * 60 * 24); |
| 80 |
private String schemaLocation = |
|
| 81 |
"eml://ecoinformatics.org/harvestList ../../lib/harvester/harvestList.xsd"; |
|
| 80 | 82 |
int siteScheduleID; |
| 81 | 83 |
private String unit; |
| 82 | 84 |
private int updateFrequency; |
| ... | ... | |
| 150 | 152 |
Statement stmt; |
| 151 | 153 |
long timeNextHarvest; |
| 152 | 154 |
|
| 153 |
conn = harvester.conn;
|
|
| 155 |
conn = harvester.getConnection();
|
|
| 154 | 156 |
now = new Date(); |
| 155 | 157 |
currentTime = now.getTime(); |
| 156 | 158 |
timeNextHarvest = currentTime + delta; |
| ... | ... | |
| 182 | 184 |
* |
| 183 | 185 |
* @retrun true if due for harvest, otherwise false |
| 184 | 186 |
*/ |
| 185 |
private boolean dueForHarvest() {
|
|
| 187 |
public boolean dueForHarvest() {
|
|
| 186 | 188 |
boolean dueForHarvest = false; |
| 187 | 189 |
DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.S");
|
| 188 | 190 |
Date now = new Date(); |
| ... | ... | |
| 208 | 210 |
|
| 209 | 211 |
return dueForHarvest; |
| 210 | 212 |
} |
| 213 |
|
|
| 211 | 214 |
|
| 215 |
/** |
|
| 216 |
* Accessor method for the schemaLocation field. |
|
| 217 |
* |
|
| 218 |
* @return schemaLocation the schema location string |
|
| 219 |
*/ |
|
| 220 |
public String getSchemaLocation() {
|
|
| 221 |
return schemaLocation; |
|
| 222 |
} |
|
| 212 | 223 |
|
| 224 |
|
|
| 213 | 225 |
/** |
| 214 | 226 |
* Harvests each document in the site document list. |
| 215 | 227 |
* |
| ... | ... | |
| 223 | 235 |
|
| 224 | 236 |
if (dueForHarvest()) {
|
| 225 | 237 |
try {
|
| 226 |
success = parseDocumentList();
|
|
| 238 |
success = parseHarvestList();
|
|
| 227 | 239 |
|
| 228 | 240 |
/* If the document list was validated, then proceed with harvesting |
| 229 | 241 |
* the documents |
| ... | ... | |
| 255 | 267 |
/** |
| 256 | 268 |
* Login to Metacat using the ldapDN and ldapPwd |
| 257 | 269 |
*/ |
| 258 |
private void metacatLogin() {
|
|
| 270 |
public void metacatLogin() {
|
|
| 259 | 271 |
Metacat metacat = harvester.metacat; |
| 272 |
String response; |
|
| 260 | 273 |
|
| 261 | 274 |
if (harvester.connectToMetacat()) {
|
| 262 | 275 |
try {
|
| 263 | 276 |
System.out.println("Logging in to Metacat: " + ldapDN);
|
| 264 |
metacat.login(ldapDN, ldapPwd); |
|
| 277 |
response = metacat.login(ldapDN, ldapPwd);
|
|
| 265 | 278 |
//System.out.println("Metacat login response: " + response);
|
| 266 |
//sessionId = metacat.getSessionId(); |
|
| 267 |
//System.out.println("Session ID: " + sessionId);
|
|
| 268 | 279 |
} |
| 269 | 280 |
catch (MetacatInaccessibleException e) {
|
| 270 | 281 |
System.out.println("Metacat login failed." + e.getMessage());
|
| ... | ... | |
| 299 | 310 |
|
| 300 | 311 |
|
| 301 | 312 |
/** |
| 302 |
* Parse the site document list to find out which documents to harvest. |
|
| 313 |
* Parses the site harvest list XML file to find out which documents to |
|
| 314 |
* harvest. |
|
| 303 | 315 |
* |
| 304 | 316 |
* @return true if successful, otherwise false |
| 305 | 317 |
*/ |
| 306 |
private boolean parseDocumentList()
|
|
| 318 |
public boolean parseHarvestList()
|
|
| 307 | 319 |
throws ParserConfigurationException {
|
| 308 | 320 |
DocumentListHandler documentListHandler = new DocumentListHandler(); |
| 309 | 321 |
InputStream inputStream; |
| 310 | 322 |
InputStreamReader inputStreamReader; |
| 311 |
String schemaLocation = |
|
| 312 |
"eml://ecoinformatics.org/harvestList ../../lib/harvester/harvestList.xsd"; |
|
| 323 |
String schemaLocation = getSchemaLocation(); |
|
| 313 | 324 |
boolean success = false; |
| 314 | 325 |
URL url; |
| 315 | 326 |
|
| ... | ... | |
| 318 | 329 |
inputStream = url.openStream(); |
| 319 | 330 |
harvester.addLogEntry(0, |
| 320 | 331 |
"Retrieved: " + documentListURL, |
| 321 |
"GetDocListSuccess",
|
|
| 332 |
"GetHarvestListSuccess",
|
|
| 322 | 333 |
siteScheduleID, |
| 323 | 334 |
null, |
| 324 | 335 |
""); |
| ... | ... | |
| 326 | 337 |
documentListHandler.runParser(inputStreamReader, schemaLocation); |
| 327 | 338 |
harvester.addLogEntry(0, |
| 328 | 339 |
"Validated: " + documentListURL, |
| 329 |
"ValidateDocListSuccess",
|
|
| 340 |
"ValidateHarvestListSuccess",
|
|
| 330 | 341 |
siteScheduleID, |
| 331 | 342 |
null, |
| 332 | 343 |
""); |
| ... | ... | |
| 334 | 345 |
} |
| 335 | 346 |
catch (MalformedURLException e){
|
| 336 | 347 |
harvester.addLogEntry(1, "MalformedURLException: " + e.getMessage(), |
| 337 |
"GetDocListError", siteScheduleID, null, "");
|
|
| 348 |
"GetHarvestListError", siteScheduleID, null, "");
|
|
| 338 | 349 |
} |
| 339 | 350 |
catch (FileNotFoundException e) {
|
| 340 | 351 |
harvester.addLogEntry(1, "FileNotFoundException: " + e.getMessage(), |
| 341 |
"GetDocListError", siteScheduleID, null, "");
|
|
| 352 |
"GetHarvestListError", siteScheduleID, null, "");
|
|
| 342 | 353 |
} |
| 343 | 354 |
catch (SAXException e) {
|
| 344 | 355 |
harvester.addLogEntry(1, "SAXException: " + e.getMessage(), |
| 345 |
"ValidateDocListError", siteScheduleID, null, "");
|
|
| 356 |
"ValidateHarvestListError", siteScheduleID, null, "");
|
|
| 346 | 357 |
} |
| 347 | 358 |
catch (ClassNotFoundException e) {
|
| 348 | 359 |
harvester.addLogEntry(1, "ClassNotFoundException: " + e.getMessage(), |
| 349 |
"ValidateDocListError", siteScheduleID, null, "");
|
|
| 360 |
"ValidateHarvestListError", siteScheduleID, null, "");
|
|
| 350 | 361 |
} |
| 351 | 362 |
catch (IOException e) {
|
| 352 | 363 |
harvester.addLogEntry(1, "IOException: " + e.getMessage(), |
| 353 |
"GetDocListError", siteScheduleID, null, "");
|
|
| 364 |
"GetHarvestListError", siteScheduleID, null, "");
|
|
| 354 | 365 |
} |
| 355 | 366 |
|
| 356 | 367 |
return success; |
| ... | ... | |
| 362 | 373 |
* |
| 363 | 374 |
* @param out the PrintStream to write to |
| 364 | 375 |
*/ |
| 365 |
void printOutput(PrintStream out) {
|
|
| 376 |
public void printOutput(PrintStream out) {
|
|
| 366 | 377 |
out.println("* siteScheduleID: " + siteScheduleID);
|
| 367 | 378 |
out.println("* documentListURL: " + documentListURL);
|
| 368 | 379 |
out.println("* ldapDN: " + ldapDN);
|
| ... | ... | |
| 408 | 419 |
|
| 409 | 420 |
|
| 410 | 421 |
/** |
| 422 |
* Accessor method for setting the value of the schemaLocation field. |
|
| 423 |
* |
|
| 424 |
* @param schemaLocation the new value of the schemaLocation field |
|
| 425 |
*/ |
|
| 426 |
public void setSchemaLocation(String schemaLocation) {
|
|
| 427 |
this.schemaLocation = schemaLocation; |
|
| 428 |
} |
|
| 429 |
|
|
| 430 |
|
|
| 431 |
/** |
|
| 411 | 432 |
* This inner class extends DefaultHandler. It parses the document list, |
| 412 | 433 |
* creating a new HarvestDocument object every time it finds a </Document> |
| 413 | 434 |
* end tag. |
Also available in: Unified diff
Refactored a number of methods to allow for more effective JUnit testing