[ https://issues.apache.org/jira/browse/TIKA-2326?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Md updated TIKA-2326: --------------------- Fix Version/s: 1.13 > java.lang.OutOfMemoryError: Java heap space > ------------------------------------------- > > Key: TIKA-2326 > URL: https://issues.apache.org/jira/browse/TIKA-2326 > Project: Tika > Issue Type: Bug > Affects Versions: 1.8 > Environment: Ubuntu 16.04, java version "1.8.0_121" > Reporter: Md > Fix For: 1.13 > > Attachments: > 5d3e8154444263c73061d8804e15db3ammn0789_CLEAN_REVISED.docx > > > I am using RecursiveParserWrapper with AutoDetectParser() and here is the > part of my code which is doing parsing > > RecursiveParserWrapper parser = null; > ContentHandlerFactory factory = new > BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1); > > if(fileNameWithPath.toLowerCase().contains(htmlInTxtFile.toLowerCase())) { > parser = new RecursiveParserWrapper(new HtmlParser(), factory); > } else { > parser = new RecursiveParserWrapper(new AutoDetectParser(), > factory); > } > // -1 for unlimited buffer > ContentHandler handler = new BodyContentHandler(-1); > ParseContext context = new ParseContext(); > parser.parse(inputStream, handler, metadata, context); > Out of my 251000 files there is only one file where parser is unable to parse > and proving out of memory error. Here goes the error message > Caused by: java.lang.OutOfMemoryError: Java heap space > at org.apache.xmlbeans.impl.store.CharUtil.allocate(CharUtil.java:397) > at org.apache.xmlbeans.impl.store.CharUtil.saveChars(CharUtil.java:506) > at org.apache.xmlbeans.impl.store.CharUtil.saveChars(CharUtil.java:419) > at org.apache.xmlbeans.impl.store.CharUtil.saveChars(CharUtil.java:489) > at org.apache.xmlbeans.impl.store.Cur$CurLoadContext.text(Cur.java:2927) > at > org.apache.xmlbeans.impl.store.Cur$CurLoadContext.stripText(Cur.java:3130) > at org.apache.xmlbeans.impl.store.Cur$CurLoadContext.text(Cur.java:3143) > at > org.apache.xmlbeans.impl.store.Locale$SaxHandler.characters(Locale.java:3291) > at > org.apache.xmlbeans.impl.piccolo.xml.Piccolo.reportCdata(Piccolo.java:992) > at > org.apache.xmlbeans.impl.piccolo.xml.PiccoloLexer.parseXMLNS(PiccoloLexer.java:1290) > at > org.apache.xmlbeans.impl.piccolo.xml.PiccoloLexer.parseXML(PiccoloLexer.java:1261) > at > org.apache.xmlbeans.impl.piccolo.xml.PiccoloLexer.yylex(PiccoloLexer.java:4812) > at org.apache.xmlbeans.impl.piccolo.xml.Piccolo.yylex(Piccolo.java:1290) > at > org.apache.xmlbeans.impl.piccolo.xml.Piccolo.yyparse(Piccolo.java:1400) > at org.apache.xmlbeans.impl.piccolo.xml.Piccolo.parse(Piccolo.java:714) > at > org.apache.xmlbeans.impl.store.Locale$SaxLoader.load(Locale.java:3479) > at > org.apache.xmlbeans.impl.store.Locale.parseToXmlObject(Locale.java:1277) > at > org.apache.xmlbeans.impl.store.Locale.parseToXmlObject(Locale.java:1264) > at > org.apache.xmlbeans.impl.schema.SchemaTypeLoaderBase.parse(SchemaTypeLoaderBase.java:345) > at > org.openxmlformats.schemas.wordprocessingml.x2006.main.DocumentDocument$Factory.parse(Unknown > Source) > at > org.apache.poi.xwpf.usermodel.XWPFDocument.onDocumentRead(XWPFDocument.java:136) > at org.apache.poi.POIXMLDocument.load(POIXMLDocument.java:166) > at > org.apache.poi.xwpf.usermodel.XWPFDocument.<init>(XWPFDocument.java:118) > at > org.apache.poi.xwpf.extractor.XWPFWordExtractor.<init>(XWPFWordExtractor.java:59) > at > org.apache.poi.extractor.ExtractorFactory.createExtractor(ExtractorFactory.java:182) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:86) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:82) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:281) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:281) > at > org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) > at > org.apache.tika.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130) > -- This message was sent by Atlassian JIRA (v6.3.15#6346)