import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

/**
 * @author shinsuke
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    public HtmlXpathExtractor htmlXpathExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("htmlXpathExtractor", HtmlXpathExtractor.class);
        htmlXpathExtractor = container.getComponent("htmlXpathExtractor");
        htmlXpathExtractor.init();
    }

			<arg>"//TITLE"</arg>
		</postConstruct>
	</component>
	<component name="xmlExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.XmlExtractor" />
	<component name="htmlXpathExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.HtmlXpathExtractor">
		<postConstruct name="addFeature">
			<arg>"http://xml.org/sax/features/namespaces"</arg>
			<arg>"false"</arg>
		</postConstruct>
	</component>