/**
     * 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) {

        try {
            final List<BasicNameValuePair> parameters =
                    StreamUtil.split(params, "&").get(stream -> stream.filter(StringUtil::isNotBlank).map(s -> {
                        final String name;
                        final String value;
                        final int pos = s.indexOf('=');

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;

     */
    protected ExtractData createExtractData(final String content) {
        return new ExtractData(extractString(content));
    }

    /**
     * Detects the encoding of the input stream.
     * @param bis The buffered input stream.
     * @return The detected encoding.
     */
    protected String getEncoding(final BufferedInputStream bis) {
        final byte[] b = new byte[preloadSizeForCharset];
        try {

     *
     * @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);
    }

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.
 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**

        assertContentType("application/xml", "extractor/test.mm", "hoge.mm");

        assertContentType("message/rfc822", "extractor/eml/sample1.eml", "sample1.eml");

        assertContentType("application/octet-stream", null, "hoge");

        assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "h&oge.ppt");
        assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "h?oge.ppt");

/**
 * 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.List;
import java.util.Map;
import java.util.Queue;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentLinkedQueue;
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.fess.crawler.Constants;

     * @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);