Problem parsing UTF-8 XML File with SAX Parser

Question

I am trying to parse an XML file I made and pull information out of it. I am basing off of this tutorial. The parsing is connecting to the XML file ok and evaluates the first tag but will crash afterwards as seen in the Output. Attached below are the XML File layout, Java parsing code, and the Console Output.

Any idea why it is not reading the next tag of the XML, and if so, what should I change?

XML File:

<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
<filepath>/mnt/sdcard/Audio_Recorder/anonymous22242.3gp</filepath>
<filename>anonymous22242.3gp</filename>
<annotation>
    <file>anonymous22242.3gp</file>
    <timestamp>0:06</timestamp>
    <note>test1</note>
</annotation>
<annotation>
    <file>anonymous22242.3gp</file>
    <timestamp>0:09</timestamp>
    <note>lol</note>
</annotation>
<annotation>
    <file>anonymous22242.3gp</file>
    <timestamp>0:09</timestamp>
    <note>lolol</note>
</annotation>

Java File:

private static String fileDirectory;
private final static ArrayList<String> allFileNames = new ArrayList<String>();
private final static ArrayList<String[]> allAnnotations = new ArrayList<String[]>();
private static String[] currentAnnotation = new String[3];

public static void main(String[] args) {
    // TODO Auto-generated method stub
    try {

        SAXParserFactory factory = SAXParserFactory.newInstance();
        SAXParser playbackParser = factory.newSAXParser();

        DefaultHandler handler = new DefaultHandler() {

            boolean audioFullPath = false;
            boolean audioName = false;
            boolean annotationFile = false;
            boolean annotationTimestamp = false;
            boolean annotationNote = false;

            public void startElement(String uri, String localName,
                    String qName, Attributes attributes)
                    throws SAXException {

                System.out.println("Start Element :" + qName);

                if (qName.equalsIgnoreCase("filepath")) {
                    audioFullPath = true;
                }

                if (qName.equalsIgnoreCase("filename")) {
                    audioName = true;
                }

                if (qName.equalsIgnoreCase("file")) {
                    annotationFile = true;
                }

                if (qName.equalsIgnoreCase("timestamp")) {
                    annotationTimestamp = true;
                }

                if (qName.equalsIgnoreCase("note")) {
                    annotationNote = true;
                }

            }

            public void endElement(String uri, String localName,
                    String qName) throws SAXException {

                System.out.println("End Element :" + qName);

            }

            public void characters(char ch[], int start, int length)
                    throws SAXException {

                if (audioFullPath) {
                    String filePath = new String(ch, start, length);
                    System.out.println("Full Path : " + filePath);
                    fileDirectory = filePath;
                    audioFullPath = false;
                }

                if (audioName) {
                    String fileName = new String(ch, start, length);
                    System.out.println("File Name : " + fileName);
                    allFileNames.add(fileName);
                    audioName = false;
                }

                if (annotationFile) {
                    String fileName = new String(ch, start, length);
                    currentAnnotation[0] = fileName;
                    annotationFile = false;
                }

                if (annotationTimestamp) {
                    String timestamp = new String(ch, start, length);
                    currentAnnotation[1] = timestamp;
                    annotationTimestamp = false;
                }
                if (annotationNote) {
                    String note = new String(ch, start, length);
                    currentAnnotation[2] = note;
                    annotationNote = false;
                    allAnnotations.add(currentAnnotation);
                }

            }

        };

        File file = new File(
                "c:\\Documents and Settings\\anonymous.xml");
        InputStream inputStream = new FileInputStream(file);
        Reader xmlReader = new InputStreamReader(inputStream, "UTF-8");

        InputSource xmlSource = new InputSource(xmlReader);
        xmlSource.setEncoding("UTF-8");

        playbackParser.parse(xmlSource, handler);

        System.out.println(fileDirectory);
        System.out.println(allFileNames);
        System.out.println(allAnnotations);

    } catch (Exception e) {
        e.printStackTrace();
    }
}
}

Output:

Start Element :filepath
Full Path : /mnt/sdcard/Audio_Recorder/anonymous22242.3gp
End Element :filepath
org.xml.sax.SAXParseException: The markup in the document following the root element must be well-formed.
    at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(Unknown Source)
    at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(Unknown Source)
    at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(Unknown Source)
    at com.sun.org.apache.xerces.internal.impl.XMLScanner.reportFatalError(Unknown Source)
    at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl$TrailingMiscDriver.next(Unknown Source)
    at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(Unknown Source)
    at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(Unknown Source)
    at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(Unknown Source)
    at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(Unknown Source)
    at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(Unknown Source)
    at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(Unknown Source)
    at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(Unknown Source)
    at javax.xml.parsers.SAXParser.parse(Unknown Source)
    at main.main(main.java:131)

skaffman · Accepted Answer · 2011-07-20 20:20:18Z

5

That's not XML. There must be a single root element containing all of the rest.

answered Jul 20, 2011 at 20:20

skaffman

405k96 gold badges825 silver badges775 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

dancran Over a year ago

Yup. I feel dumb. Thanks though!

adarshr · Accepted Answer · 2011-07-20 20:20:54Z

2

Quite clearly, your XML isn't well formed. It must have a base (root) element. I have added a <config> element.

<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
<config>
    <filepath>/mnt/sdcard/Audio_Recorder/anonymous22242.3gp</filepath>
    <filename>anonymous22242.3gp</filename>
    <annotation>
        <file>anonymous22242.3gp</file>
        <timestamp>0:06</timestamp>
        <note>test1</note>
    </annotation>
    <annotation>
        <file>anonymous22242.3gp</file>
        <timestamp>0:09</timestamp>
        <note>lol</note>
    </annotation>
    <annotation>
        <file>anonymous22242.3gp</file>
        <timestamp>0:09</timestamp>
        <note>lolol</note>
    </annotation>
</config>

answered Jul 20, 2011 at 20:20

adarshr

62.8k24 gold badges146 silver badges175 bronze badges

1 Comment

dancran Over a year ago

Yeah that fixed it... Whoooooooooooops.

Collectives™ on Stack Overflow

Problem parsing UTF-8 XML File with SAX Parser

2 Answers 2

1 Comment

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

1 Comment

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related