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;

            });

            // Keep only the specified number of versions
            for (int i = keepVersions; i < archives.size(); i++) {
                removeSessionKey(archives.get(i));
                removed++;
            }
        }

        if (removed > 0) {
            log.info("Cleaned up {} archived key versions", removed);
        }
    }

    private int extractVersion(String archivedKey) {

        String sessionId = "remove-with-archives";
        keyManager.storeSessionKey(sessionId, testKey, "AES");

        // Create archived versions
        for (int i = 0; i < 3; i++) {
            keyManager.rotateSessionKey(sessionId);
        }

        // Verify archives exist
        assertTrue(keyManager.hasSessionKey(sessionId + ".v0"), "Version 0 should exist");

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 {

  <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"/>

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

#### 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