* Constructs a new FilenameExtractor.
     */
    public FilenameExtractor() {
        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.
     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.
     * @return An ExtractData object containing the filename as content.
     */
    @Override

        super();
    }

    /**
     * Extracts text content from an LHA archive input stream.
     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null
     * @throws ExtractException if an error occurs during extraction

            final Stream<QueryLog> stream = Stream.of(queryLogs);
            if (parallel) {
                stream.parallel();
            }
            final SuggestItem[] array = stream.flatMap(queryLog -> contentsParser
                    .parseQueryLog(queryLog, supportedFields, tagFieldNames, roleFieldName, readingConverter, normalizer)
                    .stream()).toArray(n -> new SuggestItem[n]);

 */
package org.codelibs.fess.crawler.filter.impl;

import java.util.LinkedHashSet;
import java.util.List;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

        if (keyList == null || keyList.isEmpty()) {
            throw new CrawlerSystemException("The key list is empty.");
        }
        keyList.stream().distinct().forEach(key -> addExtractor(key, extractor));
    }

    /**
     * Retrieves an extractor for the specified key.
     * If multiple extractors are associated with the key, returns a composite extractor

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {
        super();
    }

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import java.util.regex.Pattern;
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.misc.Pair;

import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import org.codelibs.fess.crawler.entity.OpenSearchUrlFilter;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.service.UrlFilterService;

     * 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()));

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {
        super();
    }

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {