import org.codelibs.fess.crawler.exception.ChildUrlsException;
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>

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.processor.impl;

import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;

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

import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *

import org.opensearch.index.query.QueryBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Query processor component that handles query filters and commands.
 * This class provides a pipeline for processing Lucene queries by applying
 * a chain of filters and executing registered query commands.
 *
 * <p>The processor maintains a map of query commands indexed by query class names

Tener otro gestor de procesos dentro del contenedor (como sería con múltiples workers) solo añadiría **complejidad innecesaria** que probablemente ya estés manejando con tu sistema de cluster.

### Contenedores con Múltiples Procesos y Casos Especiales { #containers-with-multiple-processes-and-special-cases }

Guillaume Nodet <******@****.***> 1725988727 +0200

Apenas um processo no servidor pode se conectar a uma porta em um endereço IP. Poderiam existir outros processos conectados em outras portas desse mesmo endereço IP, mas apenas um para cada combinação de endereço IP e porta.

TLS (HTTPS) usa a porta `443` por padrão. Então essa é a porta que precisamos.

Como apenas um único processo pode se comunicar com essa porta, o processo que faria isso seria o Proxy de Terminação TLS.

import java.io.Writer;
import java.util.HashSet;
import java.util.Set;
import java.util.TreeSet;

import org.apache.maven.api.di.Named;

/**
 * Annotation processor that generates an index file for classes annotated with {@link Named}.
 * This processor scans for classes with the {@code @Named} annotation and creates a file
 * at {@code META-INF/maven/org.apache.maven.api.di.Inject} containing the fully qualified
 * names of these classes.

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;
import org.codelibs.fess.crawler.serializer.DataSerializer;

    }

    @Override
    public ResponseProcessor getResponseProcessor() {
        return responseProcessor;
    }

    /**
     * Sets the response processor for this rule.
     *
     * @param responseProcessor the response processor to set
     */
    public void setResponseProcessor(final ResponseProcessor responseProcessor) {
        this.responseProcessor = responseProcessor;
    }