* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

			<artifactId>commons-lang3</artifactId>
			<version>${commons.lang3.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-text</artifactId>
			<version>${commons.text.version}</version>
		</dependency>
		<dependency>
			<groupId>commons-net</groupId>
			<artifactId>commons-net</artifactId>
			<version>${commons.net.version}</version>
		</dependency>

      (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.

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

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

    public void test_getTika_text() {

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

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

        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());