import java.net.URI;
import java.net.URISyntaxException;
import java.net.URLEncoder;
import java.nio.file.Files;
import java.nio.file.attribute.AclFileAttributeView;
import java.nio.file.attribute.FileOwnerAttributeView;
import java.nio.file.attribute.PosixFileAttributeView;
import java.nio.file.attribute.UserPrincipal;
import java.util.Date;
import java.util.HashSet;
import java.util.Set;
import java.util.concurrent.atomic.AtomicBoolean;

        }
    }

    /**
     * Gets the child URL extraction rules as a stream of tag-attribute pairs.
     *
     * @param responseData the response data
     * @param resultData the result data
     * @return a stream of tag-attribute pairs
     */
    protected Stream<Pair<String, String>> getChildUrlRules(final ResponseData responseData, final ResultData resultData) {

 * and processing of Sitemap data.
 * </p>
 *
 * <p>
 * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
 * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers
 * to incrementally fetch sitemaps that have been updated since a certain date.
 * </p>
 *
 * <p>

         * return null; }
         */
    }

    /**
     * Gets the reading from the attribute.
     * @param stream The token stream.
     * @return The reading from the attribute.
     */
    protected String getReadingFromAttribute(final TokenStream stream) {
        return null;
        /*

 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**
     * Regular expression pattern to match the charset attribute in the meta tag of HTML documents.
     * The pattern captures the charset value specified in the content attribute of the meta tag.

            return matcher.replaceAll(" ").trim();
        }
        return value;
    }

    /**
     * Adds an attribute to the factory.
     * @param name The name of the attribute.
     * @param value The value of the attribute.
     */
    public void addAttribute(final String name, final Object value) {
        attributeMap.put(name, value);
    }

    /**

  <!-- can't tell from the root element whether this is fodt, fodp, etc.
     This is a made up general mime to cover the open office flat formats.
      Subtype detection can be done with the document:mime attribute in the root
      element and/or file extensions fodt...-->
  <mime-type type="application/vnd.oasis.opendocument.tika.flat.document">
    <_comment>OpenDocument v1.0: Flat Text document</_comment>