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

    /**
     * Extracts text content from an LHA archive input stream.
     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler.lasta</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler.opensearch</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.suggest</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

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.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**

import jakarta.annotation.Resource;

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

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

    /**

  <mime-type type="application/java-archive">
    <_comment>Java Archive</_comment>
    <tika:link>http://en.wikipedia.org/wiki/.jar</tika:link>
    <tika:uti>com.sun.java-archive</tika:uti>
    <sub-class-of type="application/zip"/>
    <glob pattern="*.jar"/>
  </mime-type>

  <mime-type type="application/vnd.android.package-archive">
    <sub-class-of type="application/java-archive"/>
    <glob pattern="*.apk"/>

#### 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

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files

     * <li>yearly</li>
     * <li>never</li>
     * </ul>
     * The value "always" should be used to describe documents that change each
     * time they are accessed. The value "never" should be used to describe
     * archived URLs.
     *
     * Please note that the value of this tag is considered a hint and not a
     * command. Even though search engine crawlers may consider this information