Shinsuke Sugaya <******@****.***> 1444529815 +0900

test.tar data/folder/file.html テスト data/file.txt テキスト...

        assertContentType("image/gif", null, "hoge.gif");

        assertContentType("application/pdf", "extractor/test.pdf", "hoge.pdf");

        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?

                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

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

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

import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.fess.crawler.entity.ExtractData;

            logger.info(e.getMessage());
        }
    }

    public void test_getTika_tar() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/tar/test.tar");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);

- 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

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

#### Media Files

				"application/x-shockwave-flash",
				"application/x-silverlight-app",
				"application/x-stuffit",
				"application/x-stuffitx",
				"application/x-sv4cpio",
				"application/x-sv4crc",
				"application/x-tar",
				"application/x-tex",
				"application/x-tex-tfm",
				"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",

  </mime-type>
  <mime-type type="application/x-gtar">
    <_comment>GNU tar Compressed File Archive (GNU Tape Archive)</_comment>
    <magic priority="50">
      <!-- GNU tar archive -->
      <match value="ustar  \0" type="string" offset="257" />
    </magic>
    <glob pattern="*.gtar"/>
    <sub-class-of type="application/x-tar"/>
  </mime-type>
  <mime-type type="application/x-guitar-pro">