<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();

        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();

#### 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)

      <match value="\377\037" type="string" offset="0"/>
      <match value="0145405" type="host16" offset="0"/>
    </magic>
    <glob pattern="*.bin"/>
    <glob pattern="*.dms"/>
    <glob pattern="*.lha"/>
    <glob pattern="*.lrf"/>
    <glob pattern="*.lzh"/>
    <glob pattern="*.so"/>
    <glob pattern="*.dist"/>
    <glob pattern="*.distz"/>
    <glob pattern="*.pkg"/>
    <glob pattern="*.bpk"/>

0513          ; valid                                  # 5.0  CYRILLIC SMALL LETTER EL WITH HOOK
0514          ; mapped                 ; 0515          # 5.1  CYRILLIC CAPITAL LETTER LHA
0515          ; valid                                  # 5.1  CYRILLIC SMALL LETTER LHA
0516          ; mapped                 ; 0517          # 5.1  CYRILLIC CAPITAL LETTER RHA
0517          ; valid                                  # 5.1  CYRILLIC SMALL LETTER RHA

Albert Villanova Del Moral, Aleksey Vitebskiy, Alex Hoffman, Alexander Bayandin,
Alfie Edwards, Aman Kishore, Amogh Joshi, andreABbauer, Andrew Goodbody, Andrzej
Pomirski, Artemiy Ryabinkov, Ashish Jha, ather, Ayan Moitra, Bairen Yi, Bart
Ribbers, Bas Aarts, Behzad Abghari, Ben Arnao, Ben Barsdell, Benjamin Klimczak,
bhack, Brendan Collins, Can Wang, Cheng Ren, Chris Leary, Chris Olivier, Clemens