labels.facet_filetype_rtf=Texte enrichi
labels.facet_filetype_chm=Aide HTML compilée
labels.facet_filetype_zip=Archive ZIP
labels.facet_filetype_7z=Archive 7z
labels.facet_filetype_bz=Archive BZIP
labels.facet_filetype_bz2=Archive BZIP2
labels.facet_filetype_tar=Archive TAR
labels.facet_filetype_rar=Archive RAR
labels.facet_filetype_3gp=Vidéo 3gp
labels.facet_filetype_3g2=Vidéo 3g2
labels.facet_filetype_avi=Vidéo AVI

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<version>3.4.2</version>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.curl4j</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-surefire-plugin</artifactId>
				<version>3.5.3</version>
			</plugin>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler.lasta</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

labels.facet_filetype_rtf=Rich Text
labels.facet_filetype_chm=Compiled HTML Help
labels.facet_filetype_zip=ZIP Archive
labels.facet_filetype_7z=7z Archive
labels.facet_filetype_bz=BZIP Archive
labels.facet_filetype_bz2=BZIP2 Archive
labels.facet_filetype_tar=TAR Archive
labels.facet_filetype_rar=RAR Archive
labels.facet_filetype_3gp=3gp Video
labels.facet_filetype_3g2=3g2 Video
labels.facet_filetype_avi=AVI Video

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.crawler.opensearch</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>org.codelibs.fess.suggest</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>com.mycila</groupId>
				<artifactId>license-maven-plugin</artifactId>

				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-jar-plugin</artifactId>
				<version>3.4.2</version>
				<configuration>
					<archive>
						<manifestEntries>
							<Automatic-Module-Name>jcifs</Automatic-Module-Name>
						</manifestEntries>
					</archive>
				</configuration>
			</plugin>
			<plugin>
				<groupId>org.apache.felix</groupId>
				<artifactId>maven-bundle-plugin</artifactId>

	<property name="target.dir" value="${basedir}/target" />
	<property name="branch.name" value="fess-15.4" />
	<property name="mydbflute.url" value="https://github.com/lastaflute/lastaflute-example-waterfront/archive/${branch.name}.zip" />

	<target name="mydbflute.check">
		<condition property="mydbflute.exists">
			<available file="${mydbflute.dir}" type="dir" />
		</condition>
	</target>

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;

import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;

(crawler), que puede rastrear documentos en un [servidor web](https://fess.codelibs.org/15.3/admin/webconfig-guide.html), [sistema de archivos](https://fess.codelibs.org/15.3/admin/fileconfig-guide.html), o [almacenamiento de datos](https://fess.codelibs.org/15.3/admin/dataconfig-guide.html) (como un archivo CSV o base de datos). Se admiten muchos formatos de archivos, incluidos (pero no limitados a): Microsoft Office, PDF y zip.

*[Fess Site Search](https://github.com/codelibs/fess-site-search)*...