- **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.
     */

            return m.group(1);
        }
        return null;
    }

    /**
     * Strips comments from a line (everything after '#' character).
     * @param line the line to strip comments from
     * @return the line without comments
     */
    protected String stripComment(final String line) {
        final int commentIndex = line.indexOf('#');
        if (commentIndex != -1) {

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>

        final String content = "TEST";
        final File contentFile = createContentFile(".txt", content.getBytes());

        final CommandExtractor extractor = new CommandExtractor();
        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        final ExtractData text = extractor.getText(new FileInputStream(contentFile), params);

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;

 */
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;

import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

import org.apache.commons.fileupload.FileItem;
import org.apache.commons.fileupload.FileUploadException;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.apache.commons.fileupload.servlet.ServletFileUpload;
import org.codelibs.fess.crawler.entity.ExtractData;