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

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.

/**
 * An abstract base class for implementing Extractor interfaces.
 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the
 * {@link CrawlerContainer}. It also provides a convenient method for

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>

/**
 * The HankakuKanaToZenkakuKana class implements the Normalizer interface to convert
 * half-width Katakana characters (Hankaku Kana) to full-width Katakana characters (Zenkaku Kana).
 * It also handles the conversion of voiced and semi-voiced sound marks.
 *
 * <p>This class provides the following functionalities:</p>
 * <ul>
 *   <li>Normalization of a string containing Hankaku Kana to Zenkaku Kana.</li>

 * idleConnectionTimeout the timeout duration (in milliseconds) for idle connections
 *
 * <p>Methods:</p>
 * <ul>
 *   <li>{@link #expired()}: Handles the expiration of connections by closing expired and idle connections.</li>
 * </ul>
 *
 * <p>Logging:</p>
 * <ul>
 *   <li>Logs a warning if the clientConnectionManager is null.</li>

import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.
 * This class handles the registration and loading of crawler client factories and their associated clients.
 * <p>
 * The class maintains a mapping between regular expressions and component names, and manages a list

 *     .method("GET")
 *     .url("https://example.com")
 *     .weight(1.0f)
 *     .build();
 * </pre>
 *
 * <p>The builder is implemented using an inner class {@link RequestDataContext} that handles
 * the actual construction of the RequestData object.</p>
 *
 */
public final class RequestDataBuilder {
    private RequestDataBuilder() {
    }

    /**

 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>

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

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */

import org.dbflute.utflute.core.PlainTestCase;
import org.mortbay.jetty.Handler;
import org.mortbay.jetty.HttpConnection;
import org.mortbay.jetty.HttpMethods;
import org.mortbay.jetty.Server;
import org.mortbay.jetty.handler.AbstractHandler;
import org.mortbay.jetty.handler.DefaultHandler;
import org.mortbay.jetty.handler.HandlerList;

/**
 * @author shinsuke
 *
 */