}

    /**
     * Returns the value of the request header.
     * @return The value of the request header.
     */
    public String getValue() {
        return value;
    }

    /**
     * Sets the value of the request header.
     * @param value The value of the request header.
     */
    public void setValue(final String value) {
        this.value = value;
    }

    /**

    }

    /**
     * Checks if the given input stream contains valid sitemap data.
     * @param in the input stream to validate
     * @return true if the stream contains valid sitemap data, false otherwise
     */
    public boolean isValid(final InputStream in) {
        return isValid(in, true);
    }

    /**
     * Checks if the given input stream contains valid sitemap data.
     * @param in the input stream to validate

     * Additionally, it strips invalid XML characters from the input string.
     *
     * @param value the input string to be escaped
     * @return the escaped XML string with invalid characters removed
     */
    public static String escapeXml(final String value) {
        return stripInvalidXMLCharacters(//
                value//
                        .replace("&", "&") //
                        .replace("<", "&lt;")//

     * information to search engines and may not correlate exactly to how often
     * they crawl the page. Valid values are:
     * <ul>
     * <li>always</li>
     * <li>hourly</li>
     * <li>daily</li>
     * <li>weekly</li>
     * <li>monthly</li>
     * <li>yearly</li>
     * <li>never</li>
     * </ul>

    /**
     * Checks if the given character is a valid URL character.
     *
     * Valid URL characters include:
     * - Lowercase letters (a-z)
     * - Uppercase letters (A-Z)
     * - Digits (0-9)
     * - Special characters: . - * _ : / + % = & ? # [ ] @ ~ ! $ ' ( ) , ;
     *
     * @param c the character to check
     * @return {@code true} if the character is a valid URL character, {@code false} otherwise
     */

        <match value="0x5" type="big32" offset="4"/>
        <match value="0x6" type="big32" offset="4"/>
        <match value="0x7" type="big32" offset="4"/>
        <match value="0x8" type="big32" offset="4"/>
        <match value="0x9" type="big32" offset="4"/>
        <match value="0xA" type="big32" offset="4"/>
        <match value="0xB" type="big32" offset="4"/>

import org.codelibs.fess.crawler.helper.SitemapsHelper;

/**
 * SitemapsRule is a rule implementation that extends RegexRule to determine if a given response data
 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.

     * @param key the feature key
     * @param value the feature value
     * @throws CrawlerSystemException if key or value is null
     */
    public void addFeature(final String key, final String value) {
        if (StringUtil.isBlank(key) || StringUtil.isBlank(value)) {
            throw new CrawlerSystemException("key or value is null.");
        }

        featureMap.put(key, value);
    }

    /**

        // Invalid regex pattern should be handled gracefully
        urlFilter.addInclude(".*[invalid");
        urlFilter.addInclude("https://valid.com/.*");

        // Valid pattern should still work
        assertTrue(urlFilter.match("https://valid.com/page"));
    }

    /**
     * Test adding a single exclude pattern
     */
    public void test_addExclude_singlePattern() {

    /**
     * Trims space characters from the value.
     * @param value The value to trim.
     * @return The trimmed value.
     */
    protected String trimSpace(final String value) {
        if (trimSpaceEnabled) {
            final Matcher matcher = SPACE_PATTERN.matcher(value);
            return matcher.replaceAll(" ").trim();
        }
        return value;
    }

    /**