Example usage for org.xml.sax.helpers DefaultHandler DefaultHandler

Introduction

In this page you can find the example usage for org.xml.sax.helpers DefaultHandler DefaultHandler.

Prototype

DefaultHandler

Source Link

Usage

From source file:org.apache.tika.server.MetadataEP.java

/**
 * Get a specific metadata field. If the input stream cannot be parsed, but a
 * value was found for the given metadata field, then the value of the field
 * is returned as part of a 200 OK response; otherwise a
 * {@link Status#BAD_REQUEST} is generated. If the stream was successfully
 * parsed but the specific metadata field was not found, then a
 * {@link Status#NOT_FOUND} is returned.
 * <p>//from   w w  w .j a v  a 2  s  . c o m
 * Note that this method handles multivalue fields and returns possibly more
 * metadata than requested.
 * 
 * @param field
 *          the tika metadata field name
 * @param is
 *          the document stream
 * @return one of {@link Status#OK}, {@link Status#NOT_FOUND}, or
 *         {@link Status#BAD_REQUEST}
 * @throws Exception
 */
@POST
@Path("{field}")
public Response getMetadataField(@PathParam("field") String field, InputStream is) throws Exception {

    // use BAD request to indicate that we may not have had enough data to
    // process the request
    Status defaultErrorResponse = Status.BAD_REQUEST;
    try {
        parser.parse(is, new DefaultHandler(), metadata);
        // once we've parsed the document successfully, we should use NOT_FOUND
        // if we did not see the field
        defaultErrorResponse = Status.NOT_FOUND;
    } catch (Exception e) {
        logger.info("Failed to process field " + field, e);
    }
    String[] values = metadata.getValues(field);
    if (values.length == 0) {
        return Response.status(defaultErrorResponse).entity("Failed to get metadata field " + field).build();
    }
    // remove fields we don't care about for the response
    for (String name : metadata.names()) {
        if (!field.equals(name)) {
            metadata.remove(name);
        }
    }
    return Response.ok(metadata).build();
}

---

From source file:org.apache.tika.server.MetadataResource.java

@PUT
@Produces("text/csv")
public StreamingOutput getMetadata(InputStream is, @Context HttpHeaders httpHeaders, @Context UriInfo info)
        throws Exception {
    final Metadata metadata = new Metadata();
    AutoDetectParser parser = TikaResource.createParser();
    TikaResource.fillMetadata(parser, metadata, httpHeaders);
    TikaResource.logRequest(logger, info, metadata);

    parser.parse(is, new DefaultHandler(), metadata);

    return new StreamingOutput() {
        public void write(OutputStream outputStream) throws IOException, WebApplicationException {
            CSVWriter writer = new CSVWriter(new OutputStreamWriter(outputStream));
            for (String name : metadata.names()) {
                String[] values = metadata.getValues(name);
                ArrayList<String> list = new ArrayList<String>(values.length + 1);
                list.add(name);//from  ww  w .j  av  a  2 s. co m
                list.addAll(Arrays.asList(values));
                writer.writeNext(list.toArray(values));
            }
            writer.close();
        }
    };
}

---

From source file:org.apache.tika.server.RecursiveMetadataResource.java

private MetadataList parseMetadata(InputStream is, MultivaluedMap<String, String> httpHeaders, UriInfo info)
        throws Exception {
    final Metadata metadata = new Metadata();
    final ParseContext context = new ParseContext();
    AutoDetectParser parser = TikaResource.createParser(tikaConfig);
    //TODO: parameterize choice of handler and max chars?
    BasicContentHandlerFactory.HANDLER_TYPE type = BasicContentHandlerFactory.HANDLER_TYPE.TEXT;
    RecursiveParserWrapper wrapper = new RecursiveParserWrapper(parser,
            new BasicContentHandlerFactory(type, -1));
    TikaResource.fillMetadata(parser, metadata, context, httpHeaders);
    TikaResource.fillParseContext(context, httpHeaders);
    TikaResource.logRequest(logger, info, metadata);

    wrapper.parse(is, new DefaultHandler(), metadata, context);
    return new MetadataList(wrapper.getMetadata());
}

---

From source file:org.apache.tika.server.resource.UnpackerResource.java

private Map<String, byte[]> process(InputStream is, @Context HttpHeaders httpHeaders, @Context UriInfo info,
        boolean saveAll) throws Exception {
    Metadata metadata = new Metadata();
    ParseContext pc = new ParseContext();

    Parser parser = TikaResource.createParser();
    if (parser instanceof DigestingParser) {
        //no need to digest for unwrapping
        parser = ((DigestingParser) parser).getWrappedParser();
    }//from  w w  w. j  a  v a  2s . c  o m

    TikaResource.fillMetadata(parser, metadata, pc, httpHeaders.getRequestHeaders());
    TikaResource.logRequest(LOG, info, metadata);

    ContentHandler ch;
    ByteArrayOutputStream text = new ByteArrayOutputStream();

    if (saveAll) {
        ch = new BodyContentHandler(new RichTextContentHandler(new OutputStreamWriter(text, UTF_8)));
    } else {
        ch = new DefaultHandler();
    }

    Map<String, byte[]> files = new HashMap<>();
    MutableInt count = new MutableInt();

    pc.set(EmbeddedDocumentExtractor.class, new MyEmbeddedDocumentExtractor(count, files));
    TikaResource.parse(parser, LOG, info.getPath(), is, ch, metadata, pc);

    if (count.intValue() == 0 && !saveAll) {
        throw new WebApplicationException(Response.Status.NO_CONTENT);
    }

    if (saveAll) {
        files.put(TEXT_FILENAME, text.toByteArray());

        ByteArrayOutputStream metaStream = new ByteArrayOutputStream();
        metadataToCsv(metadata, metaStream);

        files.put(META_FILENAME, metaStream.toByteArray());
    }

    return files;
}

---

From source file:org.apache.tika.server.UnpackerResource.java

@PUT
@Produces("application/zip")
public StreamingOutput getText(InputStream is, @Context HttpHeaders httpHeaders, @Context UriInfo info)
        throws Exception {
    Metadata metadata = new Metadata();

    AutoDetectParser parser = TikaResource.createParser();

    TikaResource.fillMetadata(parser, metadata, httpHeaders);
    TikaResource.logRequest(logger, info, metadata);

    ContentHandler ch = new DefaultHandler();

    ParseContext pc = new ParseContext();

    ZipOutput zout = new ZipOutput();
    MutableInt count = new MutableInt();

    pc.set(EmbeddedDocumentExtractor.class, new MyEmbeddedDocumentExtractor(count, zout));

    try {//from   ww  w  . j a v a2  s.  c om
        parser.parse(is, ch, metadata, pc);
    } catch (TikaException ex) {
        logger.warn(String.format("%s: Unpacker failed", info.getPath()), ex);
    }

    if (count.intValue() == 0) {
        throw new WebApplicationException(Response.Status.NO_CONTENT);
    }

    return zout;
}

---

From source file:org.datacleaner.cli.MainTest.java

public void testWriteHtmlToFile() throws Throwable {
    String filename = "target/test_write_html_to_file.html";
    Main.main(/*  w ww . j  a  v  a 2  s .c  o m*/
            ("-conf src/test/resources/cli-examples/conf.xml -job src/test/resources/cli-examples/employees_job.xml -of "
                    + filename + " -ot HTML").split(" "));

    File file = new File(filename);
    assertTrue(file.exists());

    {
        String result = FileHelper.readFileAsString(file);
        String[] lines = result.split("\n");

        assertEquals("<html>", lines[1]);
    }

    InputStream in = FileHelper.getInputStream(file);
    try {
        // parse it with validator.nu for HTML correctness
        final HtmlParser htmlParser = new HtmlParser(XmlViolationPolicy.FATAL);
        final AtomicInteger elementCounter = new AtomicInteger();
        htmlParser.setContentHandler(new DefaultHandler() {
            @Override
            public void startElement(String uri, String localName, String qName, Attributes attributes)
                    throws SAXException {
                elementCounter.incrementAndGet();
            }
        });
        final List<Exception> warningsAndErrors = new ArrayList<Exception>();
        htmlParser.setErrorHandler(new ErrorHandler() {
            @Override
            public void warning(SAXParseException exception) throws SAXException {
                System.err.println("Warning: " + exception.getMessage());
                warningsAndErrors.add(exception);
            }

            @Override
            public void fatalError(SAXParseException exception) throws SAXException {
                System.out.println("Fatal error: " + exception.getMessage());
                throw exception;
            }

            @Override
            public void error(SAXParseException exception) throws SAXException {
                System.err.println("Error: " + exception.getMessage());
                warningsAndErrors.add(exception);
            }
        });

        htmlParser.parse(new InputSource(in));

        // the output has approx 3600 XML elements
        int elementCount = elementCounter.get();
        assertTrue("Element count: " + elementCount, elementCount > 3000);
        assertTrue("Element count: " + elementCount, elementCount < 5000);

        if (!warningsAndErrors.isEmpty()) {
            for (Exception error : warningsAndErrors) {
                String message = error.getMessage();
                if (message.startsWith("No explicit character encoding declaration has been seen yet")
                        || message.startsWith("The character encoding of the document was not declared.")) {
                    // ignore/accept this one
                    continue;
                }
                error.printStackTrace();
                fail("Got " + warningsAndErrors.size() + " warnings and errors, see log for details");
            }
        }
    } finally {
        in.close();
    }
}

---

From source file:org.dita.dost.module.GenMapAndTopicListModule.java

/**
 * Initialize reusable filters.//  ww  w .  j a  va2s.  c  o m
 */
private void initFilters() {
    listFilter = new GenListModuleReader();
    listFilter.setLogger(logger);
    listFilter.setPrimaryDitamap(rootFile);
    listFilter.setJob(job);

    if (profilingEnabled) {
        filterUtils = parseFilterFile();
    }

    exportAnchorsFilter = new ExportAnchorsFilter();
    exportAnchorsFilter.setInputFile(rootFile);

    keydefFilter = new KeydefFilter();
    keydefFilter.setLogger(logger);
    keydefFilter.setCurrentFile(rootFile);
    keydefFilter.setJob(job);

    nullHandler = new DefaultHandler();
}

---

From source file:org.dita.dost.module.reader.AbstractReaderModule.java

/**
 * Initialize reusable filters./*from  w ww.j  a v a2  s .  c  om*/
 */
void initFilters() {
    tempFileNameScheme.setBaseDir(job.getInputDir());

    listFilter = new GenListModuleReader();
    listFilter.setLogger(logger);
    listFilter.setPrimaryDitamap(rootFile);
    listFilter.setJob(job);
    listFilter.setFormatFilter(formatFilter);

    if (profilingEnabled) {
        filterUtils = parseFilterFile();
    }

    if (INDEX_TYPE_ECLIPSEHELP.equals(transtype)) {
        exportAnchorsFilter = new ExportAnchorsFilter();
        exportAnchorsFilter.setInputFile(rootFile);
    }

    keydefFilter = new KeydefFilter();
    keydefFilter.setLogger(logger);
    keydefFilter.setCurrentFile(rootFile);
    keydefFilter.setJob(job);

    nullHandler = new DefaultHandler();

    ditaWriterFilter = new DitaWriterFilter();
    ditaWriterFilter.setTempFileNameScheme(tempFileNameScheme);
    ditaWriterFilter.setLogger(logger);
    ditaWriterFilter.setJob(job);
    ditaWriterFilter.setEntityResolver(reader.getEntityResolver());

    topicFragmentFilter = new TopicFragmentFilter(ATTRIBUTE_NAME_CONREF, ATTRIBUTE_NAME_CONREFEND);

}

---

From source file:org.dita.dost.reader.TestGenListModuleReader.java

private void run(final File rootFile) throws Exception {
    final File ditaDir = new File("src" + File.separator + "main").getAbsoluteFile();

    final boolean validate = false;
    reader = new GenListModuleReader();
    reader.setLogger(new TestUtils.TestLogger());
    reader.setCurrentFile(rootFile.toURI());
    reader.setPrimaryDitamap(rootFile.toURI());
    reader.setJob(new Job(tempDir));

    reader.setContentHandler(new DefaultHandler());

    final XMLReader parser = initXMLReader(ditaDir, validate, new File(rootFile.getPath()).getCanonicalFile());
    parser.setContentHandler(reader);/*  w  w  w . j a v a2  s .  c  o m*/

    parser.parse(rootFile.toURI().toString());
}

---

From source file:org.eclim.plugin.core.util.XmlUtils.java

/**
 * Gets an aggregate handler which delegates accordingly to the supplied
 * handlers.//  ww w. j  a  v  a2s  .  c o  m
 *
 * @param handler Main DefaultHandler to delegate to (may be null).
 * @param errorHandler DefaultHandler to delegate errors to (may be null).
 * @param entityResolver EntityResolver to delegate to (may be null).
 * @return
 */
private static DefaultHandler getHandler(DefaultHandler handler, DefaultHandler errorHandler,
        EntityResolver entityResolver) {
    DefaultHandler hdlr = handler != null ? handler : new DefaultHandler();
    return new AggregateHandler(hdlr, errorHandler, entityResolver);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• »