Menu

#66 Web crawler stop with Error

v1.2
open
nobody
None
1
2012-09-13
2010-02-20
No

The Web crawler stops after several crawl session with this error:

java.lang.NullPointerException
at org.apache.lucene.index.Term.compareTo(Term.java:119)
at org.apache.lucene.index.TermInfosReader.get(TermInfosReader.java:203)
at org.apache.lucene.index.TermInfosReader.get(TermInfosReader.java:179)
at org.apache.lucene.index.SegmentTermDocs.seek(SegmentTermDocs.java:57)
at org.apache.lucene.index.DocumentsWriter.applyDeletes(DocumentsWriter.java:984)
at org.apache.lucene.index.DocumentsWriter.applyDeletes(DocumentsWriter.java:956)
at org.apache.lucene.index.IndexWriter.applyDeletes(IndexWriter.java:5190)
at org.apache.lucene.index.IndexWriter.doFlushInternal(IndexWriter.java:4354)
at org.apache.lucene.index.IndexWriter.doFlush(IndexWriter.java:4192)
at org.apache.lucene.index.IndexWriter.flush(IndexWriter.java:4183)
at org.apache.lucene.index.IndexWriter.closeInternal(IndexWriter.java:2190)
at org.apache.lucene.index.IndexWriter.close(IndexWriter.java:2153)
at org.apache.lucene.index.IndexWriter.close(IndexWriter.java:2117)
at com.jaeksoft.searchlib.index.WriterLocal.close(Unknown Source)
at com.jaeksoft.searchlib.index.WriterLocal.deleteDocuments(Unknown Source)
at com.jaeksoft.searchlib.index.IndexSingle.deleteDocuments(Unknown Source)
at com.jaeksoft.searchlib.Client.deleteDocuments(Unknown Source)
at com.jaeksoft.searchlib.crawler.web.database.UrlManager.deleteUrls(Unknown Source)
at com.jaeksoft.searchlib.crawler.web.database.UrlCrawlQueue.deleteCollection(Unknown Source)
at com.jaeksoft.searchlib.crawler.web.database.UrlCrawlQueue.indexWork(Unknown Source)
at com.jaeksoft.searchlib.crawler.web.database.UrlCrawlQueue.index(Unknown Source)
at com.jaeksoft.searchlib.crawler.web.process.CrawlMaster.runner(Unknown Source)
at com.jaeksoft.searchlib.crawler.common.process.CrawlThreadAbstract.run(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:619)

Discussion


Log in to post a comment.