import java.io.File;
import java.util.jar.JarEntry;
import java.util.jar.JarFile;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import org.codelibs.core.lang.ClassUtil;
import org.codelibs.core.zip.ZipInputStreamUtil;

/**
 * クラスを横断して処理するためのハンドラです。
 *
 * @author koichik
 * @see ClassHandler
 * @see TraversalUtil
 */

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

        assertContentType("application/gzip", "extractor/gz/test.tar.gz", "hoge.tar.gz");
        assertContentType("application/zip", "extractor/zip/test.zip", "hoge.zip");
        assertContentType("application/x-lharc", "extractor/lha/test.lzh", "hoge.lzh"); // TODO is it correct?

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

import java.nio.file.Paths;
import java.text.SimpleDateFormat;
import java.util.Arrays;
import java.util.Date;
import java.util.Properties;
import java.util.stream.Stream;
import java.util.zip.ZipEntry;
import java.util.zip.ZipOutputStream;

import javax.annotation.Resource;

import org.apache.commons.text.StringEscapeUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

import java.util.jar.JarFile;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import org.codelibs.core.jar.JarFileUtil;
import org.codelibs.core.lang.ClassLoaderUtil;
import org.codelibs.core.lang.ClassUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.log.Logger;
import org.codelibs.core.net.URLUtil;
import org.codelibs.core.zip.ZipFileUtil;
import org.codelibs.core.zip.ZipInputStreamUtil;

import java.io.IOException;
import java.io.InputStream;
import java.util.jar.JarEntry;
import java.util.jar.JarFile;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import org.codelibs.core.jar.JarFileUtil;
import org.codelibs.core.zip.ZipInputStreamUtil;

/**
 * リソースをトラバースするためのクラスです。
 *
 * @author taedium
 * @see ResourceHandler
 * @see TraversalUtil
 */

import java.io.InputStreamReader;
import java.io.Reader;
import java.io.StringReader;
import java.util.Base64;
import java.util.HashSet;
import java.util.Map;
import java.util.Set;
import java.util.zip.GZIPInputStream;
import java.util.zip.GZIPOutputStream;

import javax.annotation.PostConstruct;

import org.apache.commons.lang3.StringUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

                final MediaType type = detector.detect(tis, metadata);
                metadata.set(ExtractData.CONTENT_TYPE, type.toString());

                // TIKA-216: Zip bomb prevention
                final SecureContentHandler sch = new SecureContentHandler(handler, tis);

                sch.setMaximumCompressionRatio(maxCompressionRatio);

import java.util.List;
import java.util.concurrent.ForkJoinPool;
import java.util.function.BiConsumer;
import java.util.function.Consumer;
import java.util.function.Supplier;
import java.util.logging.Logger;
import java.util.zip.GZIPInputStream;

import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLSocketFactory;

import org.apache.commons.io.IOUtils;
import org.codelibs.curl.Curl.Method;
import org.codelibs.curl.io.ContentCache;

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

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.zip.GZIPInputStream;

import javax.xml.XMLConstants;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;

        assertEquals("かいしゃ", extractData.getValues("dc:publisher")[0]);
    }

    public void test_getTika_zip() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/zip/test.zip");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);