* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.RequestData;

     * Gets the child URL extraction rules as a stream of tag-attribute pairs.
     *
     * @param responseData the response data
     * @param resultData the result data
     * @return a stream of tag-attribute pairs
     */
    protected Stream<Pair<String, String>> getChildUrlRules(final ResponseData responseData, final ResultData resultData) {
        return childUrlRuleMap.entrySet().stream().map(e -> new Pair<>(e.getKey(), e.getValue()));

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**
     * The maximum content size.
     */
    protected long maxContentSize = -1;

    /**

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Base64;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.stream.Stream;

import org.apache.lucene.queryparser.flexible.standard.StandardQueryParser;
import org.apache.lucene.queryparser.flexible.standard.config.StandardQueryConfigHandler;
import org.apache.lucene.search.BooleanClause;

    private static final Logger logger = LogManager.getLogger(AbstractCrawlerClient.class);

    /** The MIME type for application/octet-stream. */
    protected static final String APPLICATION_OCTET_STREAM = "application/octet-stream";

    /** The property name for access timeout. */
    public static final String ACCESS_TIMEOUT_PROPERTY = "accessTimeout";

                logger.error("Failed to close httpClient.", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

 */
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;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.SystemUtil;

import java.io.InputStreamReader;
import java.time.ZonedDateTime;
import java.time.format.DateTimeFormatter;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.ExecutorService;
import java.util.stream.Stream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.suggest.analysis.SuggestAnalyzer;

     *
     * @return The created OpenSearch client.
     */
    protected Client createClient() {
        final String[] hosts =
                split(address, ",").get(stream -> stream.map(String::trim).filter(StringUtil::isNotEmpty).toArray(n -> new String[n]));
        final Settings settings = Settings.builder().putList("http.hosts", hosts).build();
        return new HttpClient(settings, null);
    }

     * @param crawlerClientFactory The CrawlerClientFactory to register.
     */
    public synchronized void register(final CrawlerClientFactory crawlerClientFactory) {
        clientMap.entrySet().stream().forEach(e -> load(crawlerClientFactory, e.getKey(), e.getValue()));
        clientFactoryList.add(crawlerClientFactory);
        if (clientFactoryList.size() > maxClientFactorySize) {
            clientFactoryList.remove(0);