(d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed

    public static final String FILE_PASSWORDS = "file.passwords";

    /** Map containing metadata key-value pairs */
    protected Map<String, String[]> metadata = new HashMap<>();

    /** The extracted content text */
    protected String content;

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

    /**

essData:!0,async:!0,contentType:"application/x-www-form-urlencoded; charset=UTF-8",accepts:{"*":pc,text:"text/plain",html:"text/html",xml:"application/xml, text/xml",json:"application/json, text/javascript"},contents:{xml:/xml/,html:/html/,json:/json/},responseFields:{xml:"responseXML",text:"responseText",json:"responseJSON"},converters:{"* text":String,"text html":!0,"text json":n.parseJSON,"text xml":n.parseXML},flatOptions:{url:!0,context:!0}},ajaxSetup:function(a,b){return b?tc(tc(a,n.ajaxSe...

import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.

public class SitemapFile implements Sitemap {

    private static final long serialVersionUID = 1L;

    /**
     * Identifies the location of the Sitemap. This location can be a Sitemap,
     * an Atom file, RSS file or a simple text file.
     */
    private String loc;

    /**
     * Identifies the time that the corresponding Sitemap file was modified. It
     * does not correspond to the time that any of the pages listed in that

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                })//
        ;

        tikaExtractor = container.getComponent("tikaExtractor");
    }

    public void test_getTika_text() {

        responseData.setUrl("http://hoge/test.html");
        responseData.setResponseBody(data);
        responseData.setCharSet("ISO-8859-1");
        responseData.setMimeType("text/html");
        final ResultData resultData = htmlTransformer.transform(responseData);
        assertEquals(content, new String(resultData.getData()));
        assertEquals(1, resultData.getChildUrlSet().size());

 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

 * <pre>
 * XmlTransformer transformer = new XmlTransformer();
 * transformer.setNamespaceAware(true);
 * transformer.setCacheDuration(30);
 * transformer.addFieldRule("title", "/book/title/text()");
 * transformer.addFieldRule("author", "/book/author/name/text()");
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setResponseBody(new ByteArrayInputStream(xmlContent.getBytes(StandardCharsets.UTF_8)));

     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *
     * @return true if this stream instance supports the mark and reset methods; false otherwise
     */
    @Override
    public boolean markSupported() {