extensionMap.put("odt", "txt");
        extensionMap.put("ott", "txt");
        extensionMap.put("sxw", "txt");
        extensionMap.put("rtf", "txt");
        extensionMap.put("doc", "txt");
        extensionMap.put("docx", "txt");
        extensionMap.put("wpd", "txt");
        extensionMap.put("txt", "txt");
        extensionMap.put("html", "txt");
        // Spreadsheet Formats
        extensionMap.put("ods", "tsv");

        assertEquals("application/msword", extractData.getValues("Content-Type")[0]);
    }

    public void test_getTika_mswordx() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.docx");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);

            final List<Map<String, Object>> docs = new ArrayList<>(docPerReq);
            try (final DocumentReader documentReader = reader.get()) {
                Map<String, Object> doc = documentReader.read();
                while (doc != null) {
                    if (Thread.currentThread().isInterrupted()) {
                        break;
                    }
                    docs.add(doc);

        private final Node doc;

        public DefaultNamespaceContext(final Node doc) {
            this.doc = doc;
        }

        @Override
        public String getNamespaceURI(final String prefix) {
            return getNamespaceForPrefix(prefix, doc);
        }

            final PDDocument doc = document;
            final Set<Exception> exceptionSet = new HashSet<>();
            final Thread task = new Thread(() -> {
                try {
                    stripper.writeText(doc, writer);
                    extractEmbeddedDocuments(doc, writer);
                    extractAnnotations(doc, writer);
                } catch (final Exception e) {

import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {

     * Returns the result data header.
     * @return The result data header.
     */
    protected String getResultDataHeader() {
        // TODO: Support other XML header types
        return "<?xml version=\"1.0\"?>\n<doc>\n";
    }

    /**
     * Returns the result data body for a single value.
     * @param name The name of the field.
     * @param value The value of the field.
     * @return The result data body.
     */

    // public ResponseData call() throws Exception {
    // String[] urls =
    // new String[] {
    // "http://.../",
    // "http://.../test.pdf",
    // "http://.../test.doc",
    // "http://.../test.xls",
    // "http://.../test.ppt",
    // "http://.../test.txt", };
    // for (String url : urls) {
    // ResponseData responseData = httpClient.doGet(url);