META-INF/MANIFEST.MF Manifest-Version: 1.0 Archiver-Version: Plexus Archiver Created-By: Apache Maven Built-By: BEBE Build-Jdk: 1.6.0_07 META-INF/maven/org.apache.maven.its/b/pom.xml 4.0.0 org.apache.maven.its b 0.1 jar Maven Integration Test :: Dummy Artifact maven-core-it file:///${basedir}/repo org.apache.maven.its a 0.1 META-INF/maven/org.apache.maven.its/b/pom.properties #Generated by Maven #Sat Oct 24 00:28:17 CEST 2009 version=0.1 groupId=org.apache.maven.its artifactId=b...

META-INF/MANIFEST.MF Manifest-Version: 1.0 Archiver-Version: Plexus Archiver Created-By: Apache Maven Built-By: BEBE Build-Jdk: 1.6.0_07 META-INF/maven/org.apache.maven.its/a/pom.xml 4.0.0 org.apache.maven.its a 0.1 jar Maven Integration Test :: Dummy Artifact maven-core-it file:///${basedir}/repo META-INF/maven/org.apache.maven.its/a/pom.properties #Generated by Maven #Sat Oct 24 00:27:56 CEST 2009 version=0.1 groupId=org.apache.maven.its artifactId=a...

import java.io.BufferedInputStream;
import java.io.InputStream;
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.zip.ZipArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ExtractData;

import java.io.InputStream;
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;

## How to access to files inside a ZIP archive

Accessing to contents inside an archive can be done using regular S3 API with a modified request path. You just need to append the path of the content inside the archive to the path of the archive itself.

e.g.:

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
 */
public class LhaExtractor extends AbstractExtractor {

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

// license that can be found in the LICENSE file.

package tar_test

import (
	"archive/tar"
	"bytes"
	"fmt"
	"io"
	"log"
	"os"
)

func Example_minimal() {
	// Create and add some files to the archive.
	var buf bytes.Buffer
	tw := tar.NewWriter(&buf)
	var files = []struct {
		Name, Body string
	}{
		{"readme.txt", "This archive contains some text files."},
		{"gopher.txt", "Gopher names:\nGeorge\nGeoffrey\nGonzo"},

	})
	if err != nil {
		f.Fatalf("failed to create writer: %s", err)
	}
	_, err = w.Write(inp)
	if err != nil {
		f.Fatalf("failed to write file to archive: %s", err)
	}
	if err := w.Close(); err != nil {
		f.Fatalf("failed to write archive: %s", err)
	}
	f.Add(b.Bytes())

	f.Fuzz(func(t *testing.T, b []byte) {
		r := NewReader(bytes.NewReader(b))
		type file struct {
			header  *Header