map.put(ExtractData.RESOURCE_NAME_KEY, filename);
                    final String content = extractor.getText(is, map).getContent();
                    writer.write(content);
                    writer.write('\n');
                } catch (final Exception e) {
                    if (logger.isDebugEnabled()) {
                        logger.debug("Exception in an internal extractor.", e);

    protected interface ContentWriter {
        /**
         * Accepts a writer.
         * @param writer A writer.
         * @throws IOException if an I/O error occurs.
         * @throws TikaException if a Tika exception occurs.
         * @throws SAXException if a SAX exception occurs.
         */
        void accept(Writer writer) throws IOException, TikaException, SAXException;
    }

    /**

            private static final int MAX_LEN = 1000;

            private final ByteArrayOutputStream buf = new ByteArrayOutputStream(MAX_LEN);

            @Override
            public void write(final int b) throws IOException {
                if (b == '\n' || b == '\r' || buf.size() >= MAX_LEN) {
                    try {
                        final String msg = buf.toString(Constants.UTF_8);

            }
        }
    }

    /**
     * Converts this access result data to XContent format for OpenSearch indexing.
     *
     * @param builder The XContentBuilder to write to.
     * @param params Additional parameters for the conversion.
     * @return The XContentBuilder with the access result data.
     * @throws IOException if the conversion fails.
     */
    @Override

     */
    public static final String WEIGHT = "weight";

    /**
     * Converts this URL queue entry to XContent format for OpenSearch indexing.
     *
     * @param builder The XContentBuilder to write to.
     * @param params Additional parameters for the conversion.
     * @return The XContentBuilder with the URL queue data.
     * @throws IOException if the conversion fails.
     */
    @Override

    public void setUrl(final String url) {
        this.url = url;
    }

    /**
     * Converts this URL filter to XContent format for OpenSearch indexing.
     *
     * @param builder The XContentBuilder to write to.
     * @param params Additional parameters for the conversion.
     * @return The XContentBuilder with the URL filter data.
     * @throws IOException if the conversion fails.
     */
    @Override

				"application/vnd.sun.xml.impress",
				"application/vnd.sun.xml.impress.template",
				"application/vnd.sun.xml.math",
				"application/vnd.sun.xml.writer",
				"application/vnd.sun.xml.writer.global",
				"application/vnd.sun.xml.writer.template",
				"application/vnd.sun.wadl+xml",
				"application/vnd.sus-calendar",
				"application/vnd.svd",
				"application/vnd.swiftview-ics",

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertEquals("Writer", extractData.getValues("Creator")[0]);
        assertEquals("OpenOffice.org 3.0", extractData.getValues("Producer")[0]);
        assertEquals("D:20090627222631+09'00'", extractData.getValues("CreationDate")[0]);
    }

     * crawler may only retrieve Sitemaps that were modified since a certain
     * date. This incremental Sitemap fetching mechanism allows for the rapid
     * discovery of new URLs on very large sites.
     */
    private String lastmod;

    /**
     * Creates a new SitemapFile instance.
     */
    public SitemapFile() {
        // Default constructor
    }

    /*
     * (non-Javadoc)

 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.
 * The extractor first tries to match against the URL, then falls back to the resource name if available.
 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */