<artifactId>servlet-api</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>jp.gr.java_conf.dangan</groupId>
			<artifactId>jlha</artifactId>
			<version>${jlha.version}</version>
		</dependency>
		<dependency>
			<groupId>org.jodconverter</groupId>
			<artifactId>jodconverter-local</artifactId>
			<version>${jodconverter.version}</version>
		</dependency>

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

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */

                requireNonNull(getStackTraceElementMethod), requireNonNull(jla), t, n);
      }

      @Override
      public int size() {
        return (Integer)
            invokeAccessibleNonThrowingMethod(
                requireNonNull(getStackTraceDepthMethod), requireNonNull(jla), t);
      }
    };
  }

  @J2ktIncompatible
  @GwtIncompatible // java.lang.reflect

                    factory.addExtractor("application/x-lha", lhaExtractor);

                })//
        ;

        lhaExtractor = container.getComponent("lhaExtractor");

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/lha/test.lzh");
        final String content = lhaExtractor.getText(in, null).getContent();

			<!-- Supported MIME type -->
			<arg>
  "(application/xml"
+ "|application/xhtml+xml"
+ "|application/rdf+xml"
+ "|application/pdf"
+ "|application/x-freemind"
+ "|application/lha"
+ "|application/x-lha"
+ "|application/x-lha-compressed"
+ "|text/xml"
+ "|text/xml-external-parsed-entity"
+ "|text/html)"
			</arg>
		</postConstruct>
	</component>

        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");

        assertContentType("message/rfc822", "extractor/eml/sample1.eml", "sample1.eml");

        extractorFactory.addExtractor("application/vnd.visio", tikaExtractor);
        extractorFactory.addExtractor("application/pdf", pdfExtractor);
        extractorFactory.addExtractor("application/x-lha", lhaExtractor);
        extractorFactory.addExtractor("application/x-lharc", lhaExtractor);

    }

    public void test_addExtractor() {
        final ExtractorFactory extractorFactory = new ExtractorFactory();

	PLFD 1234(R1), $0, F3                   // 06000000c86104d2
	PLFS 1234567890(R4), $0, F3             // 06004996c06402d2
	PLFS 1234567890(R0), $1, F3             // 06104996c06002d2
	PLHA 1234(R1), $0, R3                   // 06000000a86104d2
	PLHZ 1234(R1), $0, R3                   // 06000000a06104d2
	PLQ 1234(R1), $0, R4                    // 04000000e08104d2

### Resumo { #summary }

Eu costumava dizer que não gostava tanto de história... e olha eu aqui agora dando aulas de "história tech". 😅

#### 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
- Audio formats (MP3, WAV, FLAC)