- **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

cd fess-suggest

# Compile the project
mvn compile

# Run tests
mvn test

# Package JAR
mvn package

# Install to local repository
mvn install
```

### Code Quality Commands

```bash
# Format code (Eclipse formatter)
mvn formatter:format

# Check/apply license headers
mvn license:check
mvn license:format

# Generate test coverage report

        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.
     */

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;

		</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 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.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.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.
 *

 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>
 *   <li>Validation</li>
 *   <li>XInclude awareness</li>
 * </ul>
 *
 * <p>