bugfix (null pointer exception in assortments)

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@404 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
orbiter 20 years ago
parent 1d2155675b
commit 159f795f65

@ -932,13 +932,13 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser
}
if (noIndexReason == null) {
// strip out words
log.logDebug("(Profile) Condensing for '" + entry.normalizedURLString() + "'");
log.logDebug("Condensing for '" + entry.normalizedURLString() + "'");
plasmaCondenser condenser = new plasmaCondenser(new ByteArrayInputStream(document.getText()));
//log.logInfo("INDEXING HEADLINE:" + descr);
try {
log.logDebug("(Profile) Create LURL-Entry for '" + entry.normalizedURLString() + "', " +
"responseHeader=" + entry.responseHeader().toString());
//log.logDebug("Create LURL-Entry for '" + entry.normalizedURLString() + "', " +
// "responseHeader=" + entry.responseHeader().toString());
Date lastModified = entry.responseHeader().lastModified();
if (lastModified == null) lastModified = entry.responseHeader().date();
if (lastModified == null) lastModified = new Date();
@ -957,20 +957,18 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser
);
String urlHash = newEntry.hash();
log.logDebug("(Profile) Remove NURL for '" + entry.normalizedURLString() + "'");
//log.logDebug("Remove NURL for '" + entry.normalizedURLString() + "'");
urlPool.noticeURL.remove(urlHash); // worked-off
if (((processCase == 4) || (processCase == 5) || (processCase == 6)) &&
(entry.profile().localIndexing())) {
// remove stopwords
log.logDebug("(Profile) Exclude Stopwords for '" + entry.normalizedURLString() + "'");
log.logInfo("Excluded " + condenser.excludeWords(stopwords) + " words in URL " + entry.url());
//System.out.println("DEBUG: words left to be indexed: " + condenser.getWords());
// do indexing
log.logDebug("(Profile) Create Index for '" + entry.normalizedURLString() + "'");
//log.logDebug("Create Index for '" + entry.normalizedURLString() + "'");
int words = searchManager.addPageIndex(entry.url(), urlHash, loadDate, condenser, plasmaWordIndexEntry.language(entry.url()), plasmaWordIndexEntry.docType(entry.responseHeader().mime()));
log.logInfo("Indexed " + words + " words in URL " + entry.url() + " (" + descr + ")");
log.logInfo("*Indexed " + words + " words in URL " + entry.url() + " (" + descr + ")");
// if this was performed for a remote crawl request, notify requester
if ((processCase == 6) && (initiator != null)) {
@ -978,7 +976,7 @@ public final class plasmaSwitchboard extends serverAbstractSwitch implements ser
yacyClient.crawlReceipt(initiator, "crawl", "fill", "indexed", newEntry, "");
}
} else {
log.logDebug("Resource '" + entry.normalizedURLString() + "' not indexed (indexing is off)");
log.logDebug("Not Indexed Resource '" + entry.normalizedURLString() + "': process case=" + processCase);
}
} catch (Exception ee) {
log.logError("Could not index URL " + entry.url() + ": " + ee.getMessage());

@ -318,9 +318,13 @@ public final class plasmaWordIndexCache implements plasmaWordIndexInterface {
if (cache.size() == 0) return;
flushThread.pause();
try {
int count = hashScore.getMaxScore();
String hash = (String) hashScore.getMaxObject();
long time = (hash == null) ? System.currentTimeMillis() : longTime(hashDate.getScore(hash));
if (hash == null) {
flushThread.proceed();
return;
}
int count = hashScore.getMaxScore();
long time = longTime(hashDate.getScore(hash));
if ((count > ramcacheLimit) && (System.currentTimeMillis() - time > 10000)) {
// flush high-score entries
flushFromMem(hash, true);
@ -364,7 +368,7 @@ public final class plasmaWordIndexCache implements plasmaWordIndexInterface {
plasmaWordIndexEntryContainer feedback = assortmentCluster.storeTry(key, container);
if (feedback == null) {
return container.size();
} else if (reintegrate) {
} else if ((container.size() != feedback.size()) && (reintegrate)) {
// put assortmentRecord together with container back to ram
synchronized (cache) {
cache.put(key, feedback);

Loading…
Cancel
Save