You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@nutch.apache.org by Rafael Pappert <rp...@fwpsystems.com> on 2011/12/14 12:14:15 UTC

Solr Indexing

Hello List,

at indexing got errors like this:

Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
SEVERE: java.lang.RuntimeException: [was class java.io.IOException] Invalid CRLF
        at com.ctc.wstx.util.ExceptionUtil.throwRuntimeException(ExceptionUtil.java:18)
        at com.ctc.wstx.sr.StreamScanner.throwLazyError(StreamScanner.java:731)
        at com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3657)
        at com.ctc.wstx.sr.BasicStreamReader.getText(BasicStreamReader.java:809)
        at org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:301)
        at org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157)
        at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79)
        at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:58)
        at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:129)
        at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372)
        at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:356)
        at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:252)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:243)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:210)
        at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:224)
        at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:169)
        at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:472)
        at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:168)
        at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:98)
        at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
        at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:118)
        at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407)
        at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:987)
        at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:539)
        at org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.java:1815)
        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:662)
Caused by: java.io.IOException: Invalid CRLF
        at org.apache.coyote.http11.filters.ChunkedInputFilter.parseCRLF(ChunkedInputFilter.java:356)
        at org.apache.coyote.http11.filters.ChunkedInputFilter.doRead(ChunkedInputFilter.java:147)
        at org.apache.coyote.http11.InternalAprInputBuffer.doRead(InternalAprInputBuffer.java:548)
        at org.apache.coyote.Request.doRead(Request.java:422)
        at org.apache.catalina.connector.InputBuffer.realReadBytes(InputBuffer.java:290)
        at org.apache.tomcat.util.buf.ByteChunk.substract(ByteChunk.java:429)
        at org.apache.catalina.connector.InputBuffer.read(InputBuffer.java:315)
        at org.apache.catalina.connector.CoyoteInputStream.read(CoyoteInputStream.java:167)
        at com.ctc.wstx.io.UTF8Reader.loadMore(UTF8Reader.java:365)
        at com.ctc.wstx.io.UTF8Reader.read(UTF8Reader.java:110)
        at com.ctc.wstx.io.MergedReader.read(MergedReader.java:101)
        at com.ctc.wstx.io.ReaderSource.readInto(ReaderSource.java:84)
        at com.ctc.wstx.io.BranchingReaderSource.readInto(BranchingReaderSource.java:57)
        at com.ctc.wstx.sr.StreamScanner.loadMore(StreamScanner.java:992)
        at com.ctc.wstx.sr.BasicStreamReader.readTextSecondary(BasicStreamReader.java:4628)
        at com.ctc.wstx.sr.BasicStreamReader.readCoalescedText(BasicStreamReader.java:4126)
        at com.ctc.wstx.sr.BasicStreamReader.finishToken(BasicStreamReader.java:3701)
        at com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3649)
        ... 25 more

and this:

Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
SEVERE: org.apache.solr.common.SolrException: Unexpected EOF; was expecting a close tag for element <field>
 at [row,col {unknown-source}]: [1,2708390]
        at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:81)
        at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:58)
        at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:129)
        at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372)
        at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:356)
        at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:252)
        at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:243)
        at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:210)
        at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:224)
        at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:169)
        at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:472)
        at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:168)
        at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:98)
        at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
        at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:118)
        at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407)
        at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:987)
        at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:539)
        at org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.java:1815)
        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:662)
Caused by: com.ctc.wstx.exc.WstxEOFException: Unexpected EOF; was expecting a close tag for element <field>
 at [row,col {unknown-source}]: [1,2708390]
        at com.ctc.wstx.sr.StreamScanner.throwUnexpectedEOF(StreamScanner.java:686)
        at com.ctc.wstx.sr.BasicStreamReader.nextFromTree(BasicStreamReader.java:2730)
        at com.ctc.wstx.sr.BasicStreamReader.next(BasicStreamReader.java:1019)
        at org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:295)
        at org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157)
        at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79)
        ... 21 more

fetching, parsing, etc works without any problems. Any ideas?

Thanks in advance,
Rafael. 





Re: Solr Indexing

Posted by .
nutch 1.4

greetz,
Rafael.



what nutch version are you using?

On 14/Dec/ 2011, at 12:29 , Rafael Pappert wrote:

> Hey Markus,
> 
> Nutch' log contains loads of errors like this:
> 
> org.apache.solr.common.SolrException: Bad Request
> 
> Bad Request
> 
> request: http://hadoop0:8080/apache-solr-3.5.0/update?wt=javabin&version=2
> 	at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:430)
> 	at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:244)
> 	at org.apache.solr.client.solrj.request.AbstractUpdateRequest.process(AbstractUpdateRequest.java:105)
> 	at org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:49)
> 	at org.apache.nutch.indexer.solr.SolrWriter.write(SolrWriter.java:81)
> 	at org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.java:54)
> 	at org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.java:44)
> 	at org.apache.hadoop.mapred.ReduceTask$OldTrackingRecordWriter.write(ReduceTask.java:456)
> 	at org.apache.hadoop.mapred.ReduceTask$3.collect(ReduceTask.java:496)
> 	at org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:166)
> 	at org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:51)
> 	at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:518)
> 	at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:419)
> 	at org.apache.hadoop.mapred.Child$4.run(Child.java:259)
> 	at java.security.AccessController.doPrivileged(Native Method)
> 	at javax.security.auth.Subject.doAs(Subject.java:396)
> 	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1059)
> 	at org.apache.hadoop.mapred.Child.main(Child.java:253)
> 
> 
> 
> 
> 
> 
> On 14/Dec/ 2011, at 12:25 , Markus Jelsma wrote:
> 
>> We also need Nutch' log
>> 
>> On Wednesday 14 December 2011 12:14:15 Rafael Pappert wrote:
>>> Hello List,
>>> 
>>> at indexing got errors like this:
>>> 
>>> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
>>> SEVERE: java.lang.RuntimeException: [was class java.io.IOException] Invalid
>>> CRLF at
>>> com.ctc.wstx.util.ExceptionUtil.throwRuntimeException(ExceptionUtil.java:1
>>> 8) at com.ctc.wstx.sr.StreamScanner.throwLazyError(StreamScanner.java:731)
>>> at
>>> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
>>> 657) at
>>> com.ctc.wstx.sr.BasicStreamReader.getText(BasicStreamReader.java:809) at
>>> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:301) at
>>> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
>>> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) at
>>> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
>>> StreamHandlerBase.java:58) at
>>> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
>>> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
>>> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
>>> :356) at
>>> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
>>> a:252) at
>>> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
>>> onFilterChain.java:243) at
>>> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
>>> Chain.java:210) at
>>> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
>>> java:224) at
>>> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
>>> java:169) at
>>> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
>>> se.java:472) at
>>> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
>>> 68) at
>>> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
>>> 8) at
>>> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
>>> at
>>> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
>>> va:118) at
>>> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
>>> ) at
>>> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
>>> cessor.java:987) at
>>> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
>>> actProtocol.java:539) at
>>> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
>>> a:1815) at
>>> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.
>>> java:886) at
>>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java
>>> :908) at java.lang.Thread.run(Thread.java:662)
>>> Caused by: java.io.IOException: Invalid CRLF
>>>       at
>>> org.apache.coyote.http11.filters.ChunkedInputFilter.parseCRLF(ChunkedInput
>>> Filter.java:356) at
>>> org.apache.coyote.http11.filters.ChunkedInputFilter.doRead(ChunkedInputFil
>>> ter.java:147) at
>>> org.apache.coyote.http11.InternalAprInputBuffer.doRead(InternalAprInputBuf
>>> fer.java:548) at org.apache.coyote.Request.doRead(Request.java:422)
>>>       at
>>> org.apache.catalina.connector.InputBuffer.realReadBytes(InputBuffer.java:2
>>> 90) at org.apache.tomcat.util.buf.ByteChunk.substract(ByteChunk.java:429)
>>> at org.apache.catalina.connector.InputBuffer.read(InputBuffer.java:315) at
>>> org.apache.catalina.connector.CoyoteInputStream.read(CoyoteInputStream.jav
>>> a:167) at com.ctc.wstx.io.UTF8Reader.loadMore(UTF8Reader.java:365) at
>>> com.ctc.wstx.io.UTF8Reader.read(UTF8Reader.java:110)
>>>       at com.ctc.wstx.io.MergedReader.read(MergedReader.java:101)
>>>       at com.ctc.wstx.io.ReaderSource.readInto(ReaderSource.java:84)
>>>       at
>>> com.ctc.wstx.io.BranchingReaderSource.readInto(BranchingReaderSource.java:
>>> 57) at com.ctc.wstx.sr.StreamScanner.loadMore(StreamScanner.java:992) at
>>> com.ctc.wstx.sr.BasicStreamReader.readTextSecondary(BasicStreamReader.java
>>> :4628) at
>>> com.ctc.wstx.sr.BasicStreamReader.readCoalescedText(BasicStreamReader.java
>>> :4126) at
>>> com.ctc.wstx.sr.BasicStreamReader.finishToken(BasicStreamReader.java:3701)
>>> at
>>> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
>>> 649) ... 25 more
>>> 
>>> and this:
>>> 
>>> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
>>> SEVERE: org.apache.solr.common.SolrException: Unexpected EOF; was expecting
>>> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>>>       at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:81)
>>>       at
>>> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
>>> StreamHandlerBase.java:58) at
>>> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
>>> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
>>> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
>>> :356) at
>>> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
>>> a:252) at
>>> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
>>> onFilterChain.java:243) at
>>> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
>>> Chain.java:210) at
>>> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
>>> java:224) at
>>> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
>>> java:169) at
>>> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
>>> se.java:472) at
>>> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
>>> 68) at
>>> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
>>> 8) at
>>> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
>>> at
>>> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
>>> va:118) at
>>> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
>>> ) at
>>> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
>>> cessor.java:987) at
>>> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
>>> actProtocol.java:539) at
>>> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
>>> a:1815) at
>>> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.
>>> java:886) at
>>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java
>>> :908) at java.lang.Thread.run(Thread.java:662)
>>> Caused by: com.ctc.wstx.exc.WstxEOFException: Unexpected EOF; was expecting
>>> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>>>       at
>>> com.ctc.wstx.sr.StreamScanner.throwUnexpectedEOF(StreamScanner.java:686)
>>> at
>>> com.ctc.wstx.sr.BasicStreamReader.nextFromTree(BasicStreamReader.java:2730
>>> ) at com.ctc.wstx.sr.BasicStreamReader.next(BasicStreamReader.java:1019) at
>>> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:295) at
>>> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
>>> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) ... 21 more
>>> 
>>> fetching, parsing, etc works without any problems. Any ideas?
>>> 
>>> Thanks in advance,
>>> Rafael.
>> 
>> -- 
>> Markus Jelsma - CTO - Openindex
> 


Re: Solr Indexing

Posted by Markus Jelsma <ma...@openindex.io>.
what nutch version are you using?

On Wednesday 14 December 2011 12:29:48 Rafael Pappert wrote:
> Hey Markus,
> 
> Nutch' log contains loads of errors like this:
> 
> org.apache.solr.common.SolrException: Bad Request
> 
> Bad Request
> 
> request: http://hadoop0:8080/apache-solr-3.5.0/update?wt=javabin&version=2
> 	at
> org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHtt
> pSolrServer.java:430) at
> org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHtt
> pSolrServer.java:244) at
> org.apache.solr.client.solrj.request.AbstractUpdateRequest.process(Abstrac
> tUpdateRequest.java:105) at
> org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:49) at
> org.apache.nutch.indexer.solr.SolrWriter.write(SolrWriter.java:81) at
> org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.j
> ava:54) at
> org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.j
> ava:44) at
> org.apache.hadoop.mapred.ReduceTask$OldTrackingRecordWriter.write(ReduceTa
> sk.java:456) at
> org.apache.hadoop.mapred.ReduceTask$3.collect(ReduceTask.java:496) at
> org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:166
> ) at
> org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:51)
> at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:518)
> at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:419)
> 	at org.apache.hadoop.mapred.Child$4.run(Child.java:259)
> 	at java.security.AccessController.doPrivileged(Native Method)
> 	at javax.security.auth.Subject.doAs(Subject.java:396)
> 	at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.
> java:1059) at org.apache.hadoop.mapred.Child.main(Child.java:253)
> 
> On 14/Dec/ 2011, at 12:25 , Markus Jelsma wrote:
> > We also need Nutch' log
> > 
> > On Wednesday 14 December 2011 12:14:15 Rafael Pappert wrote:
> >> Hello List,
> >> 
> >> at indexing got errors like this:
> >> 
> >> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
> >> SEVERE: java.lang.RuntimeException: [was class java.io.IOException]
> >> Invalid CRLF at
> >> com.ctc.wstx.util.ExceptionUtil.throwRuntimeException(ExceptionUtil.java
> >> :1 8) at
> >> com.ctc.wstx.sr.StreamScanner.throwLazyError(StreamScanner.java:731) at
> >> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java
> >> :3 657) at
> >> com.ctc.wstx.sr.BasicStreamReader.getText(BasicStreamReader.java:809) at
> >> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:301) at
> >> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
> >> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) at
> >> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Conte
> >> nt StreamHandlerBase.java:58) at
> >> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerB
> >> as e.java:129) at
> >> org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
> >> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.j
> >> ava
> >> 
> >> :356) at
> >> 
> >> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.j
> >> av a:252) at
> >> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applica
> >> ti onFilterChain.java:243) at
> >> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilt
> >> er Chain.java:210) at
> >> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValv
> >> e. java:224) at
> >> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValv
> >> e. java:169) at
> >> org.apache.catalina.authenticator.AuthenticatorBase.invoke(Authenticator
> >> Ba se.java:472) at
> >> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java
> >> :1 68) at
> >> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java
> >> :9 8) at
> >> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928
> >> ) at
> >> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.
> >> ja va:118) at
> >> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:4
> >> 07 ) at
> >> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11P
> >> ro cessor.java:987) at
> >> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abs
> >> tr actProtocol.java:539) at
> >> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.j
> >> av a:1815) at
> >> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecuto
> >> r. java:886) at
> >> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.ja
> >> va
> >> 
> >> :908) at java.lang.Thread.run(Thread.java:662)
> >> 
> >> Caused by: java.io.IOException: Invalid CRLF
> >> 
> >>        at
> >> 
> >> org.apache.coyote.http11.filters.ChunkedInputFilter.parseCRLF(ChunkedInp
> >> ut Filter.java:356) at
> >> org.apache.coyote.http11.filters.ChunkedInputFilter.doRead(ChunkedInputF
> >> il ter.java:147) at
> >> org.apache.coyote.http11.InternalAprInputBuffer.doRead(InternalAprInputB
> >> uf fer.java:548) at org.apache.coyote.Request.doRead(Request.java:422)
> >> 
> >>        at
> >> 
> >> org.apache.catalina.connector.InputBuffer.realReadBytes(InputBuffer.java
> >> :2 90) at
> >> org.apache.tomcat.util.buf.ByteChunk.substract(ByteChunk.java:429) at
> >> org.apache.catalina.connector.InputBuffer.read(InputBuffer.java:315) at
> >> org.apache.catalina.connector.CoyoteInputStream.read(CoyoteInputStream.
> >> jav a:167) at com.ctc.wstx.io.UTF8Reader.loadMore(UTF8Reader.java:365)
> >> at com.ctc.wstx.io.UTF8Reader.read(UTF8Reader.java:110)
> >> 
> >>        at com.ctc.wstx.io.MergedReader.read(MergedReader.java:101)
> >>        at com.ctc.wstx.io.ReaderSource.readInto(ReaderSource.java:84)
> >>        at
> >> 
> >> com.ctc.wstx.io.BranchingReaderSource.readInto(BranchingReaderSource.jav
> >> a: 57) at com.ctc.wstx.sr.StreamScanner.loadMore(StreamScanner.java:992)
> >> at
> >> com.ctc.wstx.sr.BasicStreamReader.readTextSecondary(BasicStreamReader.j
> >> ava
> >> 
> >> :4628) at
> >> 
> >> com.ctc.wstx.sr.BasicStreamReader.readCoalescedText(BasicStreamReader.ja
> >> va
> >> 
> >> :4126) at
> >> 
> >> com.ctc.wstx.sr.BasicStreamReader.finishToken(BasicStreamReader.java:370
> >> 1) at
> >> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java
> >> :3 649) ... 25 more
> >> 
> >> and this:
> >> 
> >> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
> >> SEVERE: org.apache.solr.common.SolrException: Unexpected EOF; was
> >> expecting a close tag for element <field> at [row,col
> >> {unknown-source}]: [1,2708390]
> >> 
> >>        at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:81)
> >>        at
> >> 
> >> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Conte
> >> nt StreamHandlerBase.java:58) at
> >> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerB
> >> as e.java:129) at
> >> org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
> >> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.j
> >> ava
> >> 
> >> :356) at
> >> 
> >> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.j
> >> av a:252) at
> >> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applica
> >> ti onFilterChain.java:243) at
> >> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilt
> >> er Chain.java:210) at
> >> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValv
> >> e. java:224) at
> >> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValv
> >> e. java:169) at
> >> org.apache.catalina.authenticator.AuthenticatorBase.invoke(Authenticator
> >> Ba se.java:472) at
> >> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java
> >> :1 68) at
> >> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java
> >> :9 8) at
> >> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928
> >> ) at
> >> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.
> >> ja va:118) at
> >> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:4
> >> 07 ) at
> >> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11P
> >> ro cessor.java:987) at
> >> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abs
> >> tr actProtocol.java:539) at
> >> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.j
> >> av a:1815) at
> >> java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecuto
> >> r. java:886) at
> >> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.ja
> >> va
> >> 
> >> :908) at java.lang.Thread.run(Thread.java:662)
> >> 
> >> Caused by: com.ctc.wstx.exc.WstxEOFException: Unexpected EOF; was
> >> expecting a close tag for element <field> at [row,col
> >> {unknown-source}]: [1,2708390]
> >> 
> >>        at
> >> 
> >> com.ctc.wstx.sr.StreamScanner.throwUnexpectedEOF(StreamScanner.java:686)
> >> at
> >> com.ctc.wstx.sr.BasicStreamReader.nextFromTree(BasicStreamReader.java:27
> >> 30 ) at
> >> com.ctc.wstx.sr.BasicStreamReader.next(BasicStreamReader.java:1019) at
> >> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:295) at
> >> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
> >> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) ... 21 more
> >> 
> >> fetching, parsing, etc works without any problems. Any ideas?
> >> 
> >> Thanks in advance,
> >> Rafael.

-- 
Markus Jelsma - CTO - Openindex

Re: Solr Indexing

Posted by Rafael Pappert <rp...@fwpsystems.com>.
Hey Markus,

Nutch' log contains loads of errors like this:

org.apache.solr.common.SolrException: Bad Request

Bad Request

request: http://hadoop0:8080/apache-solr-3.5.0/update?wt=javabin&version=2
	at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:430)
	at org.apache.solr.client.solrj.impl.CommonsHttpSolrServer.request(CommonsHttpSolrServer.java:244)
	at org.apache.solr.client.solrj.request.AbstractUpdateRequest.process(AbstractUpdateRequest.java:105)
	at org.apache.solr.client.solrj.SolrServer.add(SolrServer.java:49)
	at org.apache.nutch.indexer.solr.SolrWriter.write(SolrWriter.java:81)
	at org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.java:54)
	at org.apache.nutch.indexer.IndexerOutputFormat$1.write(IndexerOutputFormat.java:44)
	at org.apache.hadoop.mapred.ReduceTask$OldTrackingRecordWriter.write(ReduceTask.java:456)
	at org.apache.hadoop.mapred.ReduceTask$3.collect(ReduceTask.java:496)
	at org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:166)
	at org.apache.nutch.indexer.IndexerMapReduce.reduce(IndexerMapReduce.java:51)
	at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:518)
	at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:419)
	at org.apache.hadoop.mapred.Child$4.run(Child.java:259)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:396)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1059)
	at org.apache.hadoop.mapred.Child.main(Child.java:253)






On 14/Dec/ 2011, at 12:25 , Markus Jelsma wrote:

> We also need Nutch' log
> 
> On Wednesday 14 December 2011 12:14:15 Rafael Pappert wrote:
>> Hello List,
>> 
>> at indexing got errors like this:
>> 
>> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
>> SEVERE: java.lang.RuntimeException: [was class java.io.IOException] Invalid
>> CRLF at
>> com.ctc.wstx.util.ExceptionUtil.throwRuntimeException(ExceptionUtil.java:1
>> 8) at com.ctc.wstx.sr.StreamScanner.throwLazyError(StreamScanner.java:731)
>> at
>> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
>> 657) at
>> com.ctc.wstx.sr.BasicStreamReader.getText(BasicStreamReader.java:809) at
>> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:301) at
>> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
>> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) at
>> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
>> StreamHandlerBase.java:58) at
>> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
>> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
>> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
>> :356) at
>> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
>> a:252) at
>> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
>> onFilterChain.java:243) at
>> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
>> Chain.java:210) at
>> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
>> java:224) at
>> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
>> java:169) at
>> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
>> se.java:472) at
>> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
>> 68) at
>> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
>> 8) at
>> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
>> at
>> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
>> va:118) at
>> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
>> ) at
>> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
>> cessor.java:987) at
>> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
>> actProtocol.java:539) at
>> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
>> a:1815) 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:662)
>> Caused by: java.io.IOException: Invalid CRLF
>>        at
>> org.apache.coyote.http11.filters.ChunkedInputFilter.parseCRLF(ChunkedInput
>> Filter.java:356) at
>> org.apache.coyote.http11.filters.ChunkedInputFilter.doRead(ChunkedInputFil
>> ter.java:147) at
>> org.apache.coyote.http11.InternalAprInputBuffer.doRead(InternalAprInputBuf
>> fer.java:548) at org.apache.coyote.Request.doRead(Request.java:422)
>>        at
>> org.apache.catalina.connector.InputBuffer.realReadBytes(InputBuffer.java:2
>> 90) at org.apache.tomcat.util.buf.ByteChunk.substract(ByteChunk.java:429)
>> at org.apache.catalina.connector.InputBuffer.read(InputBuffer.java:315) at
>> org.apache.catalina.connector.CoyoteInputStream.read(CoyoteInputStream.jav
>> a:167) at com.ctc.wstx.io.UTF8Reader.loadMore(UTF8Reader.java:365) at
>> com.ctc.wstx.io.UTF8Reader.read(UTF8Reader.java:110)
>>        at com.ctc.wstx.io.MergedReader.read(MergedReader.java:101)
>>        at com.ctc.wstx.io.ReaderSource.readInto(ReaderSource.java:84)
>>        at
>> com.ctc.wstx.io.BranchingReaderSource.readInto(BranchingReaderSource.java:
>> 57) at com.ctc.wstx.sr.StreamScanner.loadMore(StreamScanner.java:992) at
>> com.ctc.wstx.sr.BasicStreamReader.readTextSecondary(BasicStreamReader.java
>> :4628) at
>> com.ctc.wstx.sr.BasicStreamReader.readCoalescedText(BasicStreamReader.java
>> :4126) at
>> com.ctc.wstx.sr.BasicStreamReader.finishToken(BasicStreamReader.java:3701)
>> at
>> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
>> 649) ... 25 more
>> 
>> and this:
>> 
>> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
>> SEVERE: org.apache.solr.common.SolrException: Unexpected EOF; was expecting
>> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>>        at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:81)
>>        at
>> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
>> StreamHandlerBase.java:58) at
>> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
>> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
>> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
>> :356) at
>> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
>> a:252) at
>> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
>> onFilterChain.java:243) at
>> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
>> Chain.java:210) at
>> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
>> java:224) at
>> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
>> java:169) at
>> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
>> se.java:472) at
>> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
>> 68) at
>> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
>> 8) at
>> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
>> at
>> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
>> va:118) at
>> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
>> ) at
>> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
>> cessor.java:987) at
>> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
>> actProtocol.java:539) at
>> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
>> a:1815) 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:662)
>> Caused by: com.ctc.wstx.exc.WstxEOFException: Unexpected EOF; was expecting
>> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>>        at
>> com.ctc.wstx.sr.StreamScanner.throwUnexpectedEOF(StreamScanner.java:686)
>> at
>> com.ctc.wstx.sr.BasicStreamReader.nextFromTree(BasicStreamReader.java:2730
>> ) at com.ctc.wstx.sr.BasicStreamReader.next(BasicStreamReader.java:1019) at
>> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:295) at
>> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
>> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) ... 21 more
>> 
>> fetching, parsing, etc works without any problems. Any ideas?
>> 
>> Thanks in advance,
>> Rafael.
> 
> -- 
> Markus Jelsma - CTO - Openindex


Re: Solr Indexing

Posted by Markus Jelsma <ma...@openindex.io>.
We also need Nutch' log

On Wednesday 14 December 2011 12:14:15 Rafael Pappert wrote:
> Hello List,
> 
> at indexing got errors like this:
> 
> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
> SEVERE: java.lang.RuntimeException: [was class java.io.IOException] Invalid
> CRLF at
> com.ctc.wstx.util.ExceptionUtil.throwRuntimeException(ExceptionUtil.java:1
> 8) at com.ctc.wstx.sr.StreamScanner.throwLazyError(StreamScanner.java:731)
> at
> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
> 657) at
> com.ctc.wstx.sr.BasicStreamReader.getText(BasicStreamReader.java:809) at
> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:301) at
> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) at
> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
> StreamHandlerBase.java:58) at
> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
> :356) at
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
> a:252) at
> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
> onFilterChain.java:243) at
> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
> Chain.java:210) at
> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
> java:224) at
> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
> java:169) at
> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
> se.java:472) at
> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
> 68) at
> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
> 8) at
> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
> at
> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
> va:118) at
> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
> ) at
> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
> cessor.java:987) at
> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
> actProtocol.java:539) at
> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
> a:1815) 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:662)
> Caused by: java.io.IOException: Invalid CRLF
>         at
> org.apache.coyote.http11.filters.ChunkedInputFilter.parseCRLF(ChunkedInput
> Filter.java:356) at
> org.apache.coyote.http11.filters.ChunkedInputFilter.doRead(ChunkedInputFil
> ter.java:147) at
> org.apache.coyote.http11.InternalAprInputBuffer.doRead(InternalAprInputBuf
> fer.java:548) at org.apache.coyote.Request.doRead(Request.java:422)
>         at
> org.apache.catalina.connector.InputBuffer.realReadBytes(InputBuffer.java:2
> 90) at org.apache.tomcat.util.buf.ByteChunk.substract(ByteChunk.java:429)
> at org.apache.catalina.connector.InputBuffer.read(InputBuffer.java:315) at
> org.apache.catalina.connector.CoyoteInputStream.read(CoyoteInputStream.jav
> a:167) at com.ctc.wstx.io.UTF8Reader.loadMore(UTF8Reader.java:365) at
> com.ctc.wstx.io.UTF8Reader.read(UTF8Reader.java:110)
>         at com.ctc.wstx.io.MergedReader.read(MergedReader.java:101)
>         at com.ctc.wstx.io.ReaderSource.readInto(ReaderSource.java:84)
>         at
> com.ctc.wstx.io.BranchingReaderSource.readInto(BranchingReaderSource.java:
> 57) at com.ctc.wstx.sr.StreamScanner.loadMore(StreamScanner.java:992) at
> com.ctc.wstx.sr.BasicStreamReader.readTextSecondary(BasicStreamReader.java
> :4628) at
> com.ctc.wstx.sr.BasicStreamReader.readCoalescedText(BasicStreamReader.java
> :4126) at
> com.ctc.wstx.sr.BasicStreamReader.finishToken(BasicStreamReader.java:3701)
> at
> com.ctc.wstx.sr.BasicStreamReader.safeFinishToken(BasicStreamReader.java:3
> 649) ... 25 more
> 
> and this:
> 
> Dec 14, 2011 5:00:11 AM org.apache.solr.common.SolrException log
> SEVERE: org.apache.solr.common.SolrException: Unexpected EOF; was expecting
> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>         at org.apache.solr.handler.XMLLoader.load(XMLLoader.java:81)
>         at
> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Content
> StreamHandlerBase.java:58) at
> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBas
> e.java:129) at org.apache.solr.core.SolrCore.execute(SolrCore.java:1372) at
> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java
> :356) at
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.jav
> a:252) at
> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(Applicati
> onFilterChain.java:243) at
> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilter
> Chain.java:210) at
> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.
> java:224) at
> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.
> java:169) at
> org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBa
> se.java:472) at
> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:1
> 68) at
> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:9
> 8) at
> org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
> at
> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.ja
> va:118) at
> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407
> ) at
> org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Pro
> cessor.java:987) at
> org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(Abstr
> actProtocol.java:539) at
> org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.jav
> a:1815) 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:662)
> Caused by: com.ctc.wstx.exc.WstxEOFException: Unexpected EOF; was expecting
> a close tag for element <field> at [row,col {unknown-source}]: [1,2708390]
>         at
> com.ctc.wstx.sr.StreamScanner.throwUnexpectedEOF(StreamScanner.java:686)
> at
> com.ctc.wstx.sr.BasicStreamReader.nextFromTree(BasicStreamReader.java:2730
> ) at com.ctc.wstx.sr.BasicStreamReader.next(BasicStreamReader.java:1019) at
> org.apache.solr.handler.XMLLoader.readDoc(XMLLoader.java:295) at
> org.apache.solr.handler.XMLLoader.processUpdate(XMLLoader.java:157) at
> org.apache.solr.handler.XMLLoader.load(XMLLoader.java:79) ... 21 more
> 
> fetching, parsing, etc works without any problems. Any ideas?
> 
> Thanks in advance,
> Rafael.

-- 
Markus Jelsma - CTO - Openindex