Examples of org.xml.sax.ContentHandler

org.xml.sax.ContentHandler
axproject.org'>http://www.saxproject.org for further information.
This is the main interface that most SAX applications implement: if the application needs to be informed of basic parsing events, it implements this interface and registers an instance with the SAX parser using the {@link org.xml.sax.XMLReader#setContentHandler setContentHandler} method. The parser uses the instance to report basic document-related events like the start and end of elements and character data.

The order of events in this interface is very important, and mirrors the order of information in the document itself. For example, all of an element's content (character data, processing instructions, and/or subelements) will appear, in order, between the startElement event and the corresponding endElement event.

This interface is similar to the now-deprecated SAX 1.0 DocumentHandler interface, but it adds support for Namespaces and for reporting skipped entities (in non-validating XML processors).

Implementors should note that there is also a ContentHandler class in the java.net package; that means that it's probably a bad idea to do
```
import java.net.*; import org.xml.sax.*; 
```
In fact, "import ...*" is usually a sign of sloppy programming anyway, so the user should consider this a feature rather than a bug.
@since SAX 2.0 @author David Megginson @version 2.0.1+ (sax2r3pre1) @see org.xml.sax.XMLReader @see org.xml.sax.DTDHandler @see org.xml.sax.ErrorHandler


        assertTrue(handler.toString().contains(text));
    }


    public void testEmptyText() throws Exception {
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        parser.parse(
                new ByteArrayInputStream(new byte[0]), handler, metadata, new ParseContext());
        assertEquals("text/plain", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("\n", handler.toString());
    }

View Full Code Here

        assertEquals("ISO-8859-1", metadata.get(Metadata.CONTENT_ENCODING));
    }


    private void assertExtractText(String msg, String expected, byte[] input)
            throws Exception {
        ContentHandler handler = new BodyContentHandler() {
            public void ignorableWhitespace(char[] ch, int off, int len) {
                // Ignore the whitespace added by XHTMLContentHandler
            }
        };
        Metadata metadata = new Metadata();
        parser.parse(new ByteArrayInputStream(input), handler, metadata, new ParseContext());
        assertEquals("text/plain", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals(msg, expected, handler.toString());
    }

View Full Code Here


        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testEXCEL.xlsx");
        ContentHandler handler = new BodyContentHandler();


        try {
            parser.parse(input, handler, metadata);


            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            assertTrue(content.contains("Sample Excel Worksheet"));
            assertTrue(content.contains("Numbers and their Squares"));
            assertTrue(content.contains("9"));
            assertFalse(content.contains("9.0"));
            assertTrue(content.contains("196"));

View Full Code Here


        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testEXCEL-formats.xlsx");
        ContentHandler handler = new BodyContentHandler();


        try {
            parser.parse(input, handler, metadata);


            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));


            String content = handler.toString();


            // Number #,##0.00
            assertTrue(content.contains("1,599.99"));
            assertTrue(content.contains("-1,599.99"));

View Full Code Here


        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testPPT.pptx");
        ContentHandler handler = new BodyContentHandler();


        try {
            parser.parse(input, handler, metadata);


            assertEquals(
                    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            assertTrue(content.contains("Sample Powerpoint Slide"));
            assertTrue(content.contains("Powerpoint X for Mac"));
        } finally {
            input.close();
        }

View Full Code Here


        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testWORD.docx");
        ContentHandler handler = new BodyContentHandler();


        try {
            parser.parse(input, handler, metadata);


            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            assertTrue(handler.toString().contains("Sample Word Document"));
        } finally {
            input.close();
        }
    }

View Full Code Here


    public void testParseAscii() throws Exception {
        String path = "/test-documents/testHTML.html";
        final StringWriter href = new StringWriter();
        final StringWriter name = new StringWriter();
        ContentHandler body = new BodyContentHandler();
        Metadata metadata = new Metadata();
        InputStream stream = HtmlParserTest.class.getResourceAsStream(path);
        try {
            ContentHandler link = new DefaultHandler() {
                @Override
                public void startElement(
                        String u, String l, String n, Attributes a)
                        throws SAXException {
                    if ("a".equals(l)) {

View Full Code Here

        assertTrue(content.contains("extract content"));
        assertTrue(content.contains("an XHTML document"));
    }


    public void testParseEmpty() throws Exception {
        ContentHandler handler = new BodyContentHandler();
        new HtmlParser().parse(
                new ByteArrayInputStream(new byte[0]),
                handler,  new Metadata(), new ParseContext());
        assertEquals("", handler.toString());
    }

View Full Code Here

                    throw new SAXException(e);
                }
            }
            DOMSource source = new DOMSource(node);


            ContentHandler handler;
            if (node.getNodeType() == Node.DOCUMENT_NODE) {
                // Pass all SAX events
            handler = contentHandler;
            } else {
                // Strip start/endDocument

View Full Code Here

        try {
            Metadata metadata = new Metadata();
            metadata.set(Metadata.RESOURCE_NAME_KEY, tp.resourceStatedName);
            metadata.set(Metadata.CONTENT_TYPE, tp.statedType);
            StringWriter writer = new StringWriter();
            ContentHandler handler = new WriteOutContentHandler(writer);
            new AutoDetectParser().parse(input, handler, metadata);


            assertEquals("Bad content type: " + tp,
                    tp.realType, metadata.get(Metadata.CONTENT_TYPE));

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.xml.sax.ContentHandler

com.alibaba.citrus.asm.xml.Processor

com.nidhinova.tika.server.TikaService

com.sun.tools.internal.ws.wsdl.parser.DOMForest

com.sun.tools.internal.xjc.reader.internalizer.DOMForest

com.tamingtext.tika.TikaTest

cx.fbn.nevernote.threads.IndexRunner

net.bnubot.vercheck.XMLElementDecorator

net.javacrumbs.json2xml.JsonSaxAdapterTest

nu.validator.messages.MessageEmitterAdapter

nu.validator.servlet.VerifierServletTransaction

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.