import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.transformer.Transformer;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

import jakarta.annotation.Resource;

/**
 * <p>
 * {@link DefaultResponseProcessor} is a default implementation of {@link ResponseProcessor}.
 * It processes the response data based on the HTTP status code and configured transformer.
 * </p>
 *

    protected String getEncoding(final BufferedInputStream bis) {
        final byte[] b = new byte[preloadSizeForCharset];
        try {
            bis.mark(preloadSizeForCharset);
            @SuppressWarnings("resource")
            final BOMInputStream bomIn = new BOMInputStream(bis, false, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE,
                    ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE, BOM_UTF_7);

    /** Helper for processing robots.txt files */
    @Resource
    protected RobotsTxtHelper robotsTxtHelper;

    /** Helper for managing content length limits */
    @Resource
    protected ContentLengthHelper contentLengthHelper;

    /** Helper for determining MIME types */
    @Resource
    protected MimeTypeHelper mimeTypeHelper;

    /** The HTTP client instance */

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>
 * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.

import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import jakarta.annotation.Resource;

/**
 * The {@code HtmlTransformer} class is responsible for transforming HTML responses
 * during the crawling process. It extracts data, identifies child URLs, and handles
 * character set encoding.
 * <p>

        // Verify
        assertEquals("serializeRule", deserializedRule.getRuleId());
        assertNotNull(deserializedRule.getResponseProcessor());

        // Note: crawlerContainer is transient (marked with @Resource)
        // so it won't be serialized
        assertNull(deserializedRule.crawlerContainer);
    }

    /**
     * Test with null CrawlerContainer
     */
    public void test_nullCrawlerContainer() {

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;

/**
 * FtpClient is a crawler client implementation for accessing resources via the FTP protocol.
 * It extends {@link AbstractCrawlerClient} and provides methods to retrieve content and metadata

        tuples.add(new Tuple<>(DefaultKeys.SUPPORTED_FIELDS, "content"));
        return tuples;
    }

    /**
     * Loads the index settings from a resource file.
     * @return The index settings as a string.
     * @throws IOException If an I/O error occurs.
     */
    protected String loadIndexSettings() throws IOException {