Description
I don't think attempting to parse a DTD should throw an error.
Thanks!
$ curl -s http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd | java -jar tika-app-0.7.jar
Exception in thread "main" org.apache.tika.exception.TikaException: TIKA-237: Illegal SAXException from org.apache.tika.parser.xml.DcXMLParser@28bb0d0d
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:142)
at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:99)
at org.apache.tika.cli.TikaCLI.process(TikaCLI.java:155)
at org.apache.tika.cli.TikaCLI.main(TikaCLI.java:65)
Caused by: org.xml.sax.SAXParseException: The markup in the document preceding the root element must be well-formed.
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(ErrorHandlerWrapper.java:195)
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(ErrorHandlerWrapper.java:174)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:388)
at com.sun.org.apache.xerces.internal.impl.XMLScanner.reportFatalError(XMLScanner.java:1414)
at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl$PrologDriver.next(XMLDocumentScannerImpl.java:915)
at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:648)
at com.sun.org.apache.xerces.internal.impl.XMLNSDocumentScannerImpl.next(XMLNSDocumentScannerImpl.java:140)
at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:511)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:808)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:737)
at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:119)
at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1205)
at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:522)
at javax.xml.parsers.SAXParser.parse(SAXParser.java:395)
at javax.xml.parsers.SAXParser.parse(SAXParser.java:198)
at org.apache.tika.parser.xml.XMLParser.parse(XMLParser.java:86)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:132)
... 3 more