this.tempDir = tempDir;
    }

    /**
     * Sets the command to execute for text extraction.
     * @param command The command to set.
     */
    public void setCommand(final String command) {
        this.command = command;
    }

    /**
     * Sets the timeout for command execution.
     * @param executionTimeout The execution timeout in milliseconds.
     */

     * time they are accessed. The value "never" should be used to describe
     * archived URLs.
     *
     * Please note that the value of this tag is considered a hint and not a
     * command. Even though search engine crawlers may consider this information
     * when making decisions, they may crawl pages marked "hourly" less
     * frequently than that, and they may crawl pages marked "yearly" more

import org.apache.commons.lang3.StringUtils;
import org.apache.commons.net.ftp.FTP;
import org.apache.commons.net.ftp.FTPClient;
import org.apache.commons.net.ftp.FTPClient.NatServerResolverImpl;
import org.apache.commons.net.ftp.FTPClientConfig;
import org.apache.commons.net.ftp.FTPFile;
import org.apache.commons.net.ftp.FTPFileFilters;
import org.apache.commons.net.ftp.FTPSClient;

import java.util.regex.Pattern;

import org.apache.commons.io.ByteOrderMark;
import org.apache.commons.io.input.BOMInputStream;
import org.apache.commons.text.translate.AggregateTranslator;
import org.apache.commons.text.translate.CharSequenceTranslator;
import org.apache.commons.text.translate.EntityArrays;
import org.apache.commons.text.translate.LookupTranslator;
import org.apache.commons.text.translate.NumericEntityUnescaper;

import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ConcurrentHashMap;
import java.util.function.BiConsumer;
import java.util.stream.Collectors;

import org.apache.commons.io.output.DeferredFileOutputStream;
import org.apache.commons.lang3.SystemUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.Detector;

- **Transformers**: Data transformation and enrichment
- **Filters**: URL filtering with regex patterns
- **Rules**: Content processing rules and validation

## Building and Testing

### Build Commands

```bash
# Build all modules
mvn clean install

# Build without tests
mvn clean install -DskipTests

# Build specific module
mvn clean install -pl fess-crawler

		</dependency>
		<dependency>
			<groupId>commons-codec</groupId>
			<artifactId>commons-codec</artifactId>
			<version>${commons.codec.version}</version>
		</dependency>
		<dependency>
			<groupId>commons-io</groupId>
			<artifactId>commons-io</artifactId>
			<version>${commons.io.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-lang3</artifactId>

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

import org.apache.commons.pool2.BasePooledObjectFactory;
import org.apache.commons.pool2.PooledObject;
import org.apache.commons.pool2.impl.DefaultPooledObject;
import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**

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;

package org.codelibs.fess.crawler.extractor.impl;

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;