- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

## Architecture

### Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core framework

      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.

      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.

      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.

      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright {yyyy} {name of copyright owner}

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.

            "48, 16, true", // DIRECTORY | ARCHIVE vs DIRECTORY
            "48, 32, true", // DIRECTORY | ARCHIVE vs ARCHIVE
            "21, 5, true", // READONLY | SYSTEM | DIRECTORY vs READONLY | SYSTEM

            // Negative cases (should be rejected)
            "1, 2, false", // READONLY vs HIDDEN
            "2, 1, false", // HIDDEN vs READONLY
            "16, 32, false", // DIRECTORY vs ARCHIVE

 * 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;

labels.pathmap_list=Lista de mapeo de rutas
labels.log_file_list=Lista de archivos de registro
labels.labeltype_list=Lista de tipos de etiquetas
labels.key_match_list=Lista de coincidencias de claves
labels.job_log_list=Lista de registros de trabajos
labels.group_list=Lista de grupos
labels.file_config_list=Lista de configuración de archivos
labels.file_auth_list=Lista de autenticación de archivos
labels.failure_url_list=Lista de URL fallidas

			<param name="jar.version" value="2.1.1" />
			<param name="file.version" value="2.1.1" />
		</antcall>
		<!-- kopf -->
		<get dest="${target.dir}/kopf.zip">
			<url url="https://github.com/codelibs/fess-kopf/archive/${kopf.branch}.zip" />
		</get>
		<delete dir="${site.dir}/kopf" />
		<unzip dest="${site.dir}/kopf" src="${target.dir}/kopf.zip">
			<patternset>
				<include name="fess-kopf-${kopf.branch}/_site/**" />
			</patternset>

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