</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>

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.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;

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.util.Map;

import org.apache.commons.io.output.DeferredFileOutputStream;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.lang.StringUtil;

import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;

import org.apache.commons.pool2.PooledObject;
import org.apache.commons.pool2.impl.DefaultPooledObject;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.pool.CrawlerPooledObjectFactory.OnDestroyListener;

 */
package org.codelibs.fess.crawler.util;

import java.io.IOException;
import java.io.Reader;
import java.util.HashSet;
import java.util.Set;

import org.apache.commons.lang3.StringUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *

import org.opensearch.action.update.UpdateRequest;
import org.opensearch.action.update.UpdateRequestBuilder;
import org.opensearch.action.update.UpdateResponse;
import org.opensearch.common.action.ActionFuture;
import org.opensearch.common.settings.Settings;
import org.opensearch.common.unit.TimeValue;
import org.opensearch.core.action.ActionListener;
import org.opensearch.core.action.ActionResponse;
import org.opensearch.index.IndexNotFoundException;

container.singleton("fileTransformer", FileTransformer.class, transformer -> {
    transformer.setMaxContentSize(10 * 1024 * 1024); // 10MB limit
});
```

## Troubleshooting

### Common Issues

#### Connection Timeouts
```java
// Increase timeout values
client.setConnectionTimeout(60000);  // 60 seconds
client.setSocketTimeout(120000);     // 120 seconds
```

#### Memory Issues

import org.codelibs.fess.crawler.util.XmlUtil;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * <p>

        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.
     */