import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

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

import jakarta.annotation.Resource;

/**

        this.maxContentLength = maxContentLength;
        return this;
    }

    /**
     * Sets the cache file size threshold in bytes.
     *
     * @param cacheFileSize the cache file size to set
     * @return this builder instance for method chaining
     */
    public ExtractorBuilder cacheFileSize(final int cacheFileSize) {

import org.codelibs.fess.crawler.util.XmlUtil;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;

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

import jakarta.annotation.Resource;

/**
 * <p>

    public void setCredentialsProvider(final CredentialsProvider credentialsProvider) {
        this.credentialsProvider = credentialsProvider;
    }

    /**
     * Sets the authentication cache.
     * @param authCache The authentication cache.
     */
    public void setAuthCache(final AuthCache authCache) {
        this.authCache = authCache;
    }

    /**
     * Sets the HTTP client context.

    /**
     * Data service for checking access results.
     */
    @Resource
    protected OpenSearchDataService dataService;

    /**
     * Cache for session queues.
     */
    protected Map<String, QueueHolder> sessionCache = new ConcurrentHashMap<>();

    /**
     * The number of URLs to fetch when polling.
     */
    protected int pollingFetchSize = 1000;

			<artifactId>httpmime</artifactId>
			<version>${httpcomponents.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.httpcomponents</groupId>
			<artifactId>httpclient-cache</artifactId>
			<version>${httpcomponents.version}</version>
		</dependency>
		<dependency>
			<groupId>jakarta.annotation</groupId>
			<artifactId>jakarta.annotation-api</artifactId>

            }
            return url;
        }

        /**
         * Gets a cache key for this FTP connection based on host and port.
         * This key can be used to cache FTP client connections.
         *
         * @return The cache key in format "host:port"
         */
        public String getCacheKey() {
            return getHost() + ":" + getPort();
        }