import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */

    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        return new ExtractData(getTextInternal(in, mimeTypeHelper, extractorFactory));

     * @return The password.
     */
    protected String getPassword(final Map<String, String> params) {
        final String url = params != null ? params.get(ExtractData.URL) : null;
        if (!passwordMap.isEmpty()) {
            final String resourceName = params != null ? params.get(ExtractData.RESOURCE_NAME_KEY) : null;

            String value = null;
            if (StringUtil.isNotEmpty(url)) {
                value = url;

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class HtmlExtractorTest extends PlainTestCase {

```java
public class CustomExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(final InputStream inputStream, final Map<String, String> params) {
        // Custom extraction logic
        ExtractData extractData = new ExtractData();
        // ... implementation
        return extractData;
    }
}

// Register custom extractor

import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;

import javax.xml.xpath.XPathNodes;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;