* Where there's a hierarchy in the types, list it via a parent
   * Highly specific magic matches get a high priority
   * General magic matches which could trigger a false-positive need
     a low one
   * The priority for containers normally need to be higher than for
     the things they contain, so they don't accidently get detected
     as what's in them
   * For logic too complex to be expressed in a magic match, do the best

     * @param size The size.
     */
    public void setSize(final int size) {
        this.size = size;
    }

    /**
     * Sets the seed for random function.
     * @param seed The seed.
     */
    public void setSeed(final String seed) {
        this.seed = seed;
    }

    /**
     * Sets the window size for rescoring.
     * @param windowSize The window size.
     */

        request.addLanguage(lang);
        return this;
    }

    /**
     * Sets the seed for random function.
     * @param seed The seed.
     * @return This builder instance.
     */
    public PopularWordsRequestBuilder setSeed(final String seed) {
        request.setSeed(seed);
        return this;
    }

    /**
     * Sets the window size for rescoring.

     * @return true if all patterns must match, false if only one needs to match
     */
    public boolean isAllRequired() {
        return allRequired;
    }

    /**
     * Sets whether all regular expressions must match for this rule to match.
     * @param allRequired true if all patterns must match, false if only one needs to match
     */
    public void setAllRequired(final boolean allRequired) {

     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *
     * @param url URL
     */
    void processUrl(String url);

    /**
     * Clear this filter.
     */
    void clear();

     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD
     * - Any character between 0x10000 and 0x10FFFF
     *

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {
    //        final InputStream in = ResourceUtil
    //                .getResourceAsStream("extractor/test.pdf");

				"application/vnd.ezpix-album",
				"application/vnd.ezpix-package",
				"application/vnd.f-secure.mobile",
				"application/vnd.fdf",
				"application/vnd.fdsn.mseed",
				"application/vnd.fdsn.seed",
				"application/vnd.ffsns",
				"application/vnd.fints",
				"application/vnd.flographit",
				"application/vnd.fluxtime.clip",
				"application/vnd.font-fontforge-sfd",
				"application/vnd.framemaker",