return createExtractData(content);
        } catch (final Exception e) {
            throw new ExtractException(e);
        }
    }

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

    protected String getEncoding(final BufferedInputStream bis) {
        final byte[] b = new byte[preloadSizeForCharset];
        try {

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

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

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

/**
 * @author shinsuke
 *
 */
public interface Extractor {

    ExtractData getText(InputStream in, Map<String, String> params);

        final String content = ATTR_NAME + "," + testStr;
        final Map<String, String> params = new HashMap<String, String>();
        //final ExtractData text = extractor.getText(new ByteArrayInputStream(FileUtils.readFileToByteArray(new File(filePath))), params);
        final ExtractData text = extractor.getText(new ByteArrayInputStream(testStr.getBytes()), params);
        assertEquals(content, text.getContent());
    }

import java.io.InputStream;

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;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * @author shinsuke
 *
 */

import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.extractor.impl.LhaExtractor;
import org.codelibs.fess.crawler.extractor.impl.PasswordBasedExtractor;
import org.codelibs.fess.crawler.extractor.impl.PdfExtractor;

        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        final Map<String, String> params = new HashMap<>();
        params.put(ExtractData.RESOURCE_NAME_KEY, getResourceName(responseData));
        params.put(ExtractData.CONTENT_TYPE, responseData.getMimeType());
        String content = null;
        try (final InputStream in = responseData.getResponseBody()) {

import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;

import java.util.regex.Pattern;

import javax.annotation.Resource;
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;