* Service for managing URL queues during crawling.
     */
    @Resource
    protected UrlQueueService<UrlQueue<?>> urlQueueService;

    /**
     * Service for managing access result data.
     */
    @Resource
    protected DataService<AccessResult<?>> dataService;

    /**
     * Container for managing crawler components.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**

/**
 * Interface representing a client for a web crawler.
 * This client is responsible for executing requests and handling responses.
 * It extends {@link AutoCloseable} to allow for resource management.
 */
public interface CrawlerClient extends AutoCloseable {

    /**
     * Sets the initialization parameters for the crawler client.
     *

 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations
 * should also handle resource cleanup when the {@link #close()} method is called.</p>
 */
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *

            final BeanDesc beanDesc = BeanDescFactory.getBeanDesc(component.getClass());
            for (final FieldDesc fieldDesc : beanDesc.getFieldDescs()) {
                final Resource annotation = fieldDesc.getField().getAnnotation(Resource.class);
                if (annotation != null) {
                    final Object injected = container.getComponent(fieldDesc.getFieldName());
                    if (injected != null) {

import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.util.AccessResultCallback;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link DataService} interface for managing access result data.
 * This class provides methods to store, retrieve, update, and delete access results,

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final VisioTextExtractor visioTextExtractor = new VisioTextExtractor(in);
            return new ExtractData(visioTextExtractor.getText());
        } catch (final IOException e) {

 * It extends the AbstractTransformer class.
 *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>

import io.minio.Result;
import io.minio.StatObjectArgs;
import io.minio.StatObjectResponse;
import io.minio.errors.ErrorResponseException;
import io.minio.messages.Item;
import io.minio.messages.Tags;
import jakarta.annotation.Resource;

/**
 * A crawler client implementation for accessing and retrieving content from storage systems using MinIO.
 * This client supports operations on object storage systems compatible with S3 protocol.
 *

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(in);
            return new ExtractData(wordExtractor.getText());

 */
package org.codelibs.fess.crawler.exception;

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors
 * to handle different scenarios such as wrapping another exception or providing a specific error message.
 */