elastic / stream2es

Stream data into ES (Wikipedia, Twitter, stdin, or other ESes)
355 stars 62 forks source link

java.lang.ArrayIndexOutOfBoundsException: 900000 #70

Open ourdark opened 7 years ago

ourdark commented 7 years ago

nohup java -DentityExpansionLimit=2147480000 -DtotalEntitySizeLimit=2147480000 -Djdk.xml.totalEntitySizeLimit=2147480000 -Xmx2g -jar stream2es wiki --target http://es2:9200/en-wiki --source /mirror/enwiki-latest-pages-articles.xml.bz2 --log debug &

java.lang.ArrayIndexOutOfBoundsException: 900000 at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.getAndMoveToFrontDecode(CBZip2InputStream.java:647) at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.initBlock(CBZip2InputStream.java:282) at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.setupNoRandPartA(CBZip2InputStream.java:839) at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.setupNoRandPartB(CBZip2InputStream.java:888) at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.read0(CBZip2InputStream.java:205) at org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream.read(CBZip2InputStream.java:173) at sun.nio.cs.StreamDecoder.readBytes(StreamDecoder.java:284) at sun.nio.cs.StreamDecoder.implRead(StreamDecoder.java:326) at sun.nio.cs.StreamDecoder.read(StreamDecoder.java:178) at java.io.InputStreamReader.read(InputStreamReader.java:184) at java.io.BufferedReader.read1(BufferedReader.java:210) at java.io.BufferedReader.read(BufferedReader.java:286) at com.sun.org.apache.xerces.internal.impl.XMLEntityScanner.load(XMLEntityScanner.java:1896) at com.sun.org.apache.xerces.internal.impl.XMLEntityScanner.skipChar(XMLEntityScanner.java:1551) at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl$FragmentContentDriver.next(XMLDocumentFragmentScannerImpl.java:2821) at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:602) at com.sun.org.apache.xerces.internal.impl.XMLNSDocumentScannerImpl.next(XMLNSDocumentScannerImpl.java:112) at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:505) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:841) at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:770) at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:141) at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1213) at org.elasticsearch.river.wikipedia.support.WikiXMLSAXParser.parse(WikiXMLSAXParser.java:68) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at clojure.lang.Reflector.invokeMatchingMethod(Reflector.java:93) at clojure.lang.Reflector.invokeNoArgInstanceMember(Reflector.java:313) at stream2es.stream.wiki$fn__7115$fn__7116.invoke(wiki.clj:45) at stream2es.main$stream_BANG_.invokeStatic(main.clj:245) at stream2es.main$stream_BANG_.invoke(main.clj:241) at stream2es.main$main.invokeStatic(main.clj:333) at stream2es.main$main.invoke(main.clj:317) at stream2es.main$_main.invokeStatic(main.clj:339) at stream2es.main$_main.doInvoke(main.clj:337) at clojure.lang.RestFn.applyTo(RestFn.java:137) at stream2es.main.main(Unknown Source) 2017-02-06T10:56:16.458+0000 ERROR unexpected exception: see above