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.
     */

        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);

     * 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;

				"text/vnd.iptc.anpa",
				"text/vnd.iptc.newsml",
				"text/vnd.iptc.nitf",
				"text/vnd.latex-z",
				"text/vnd.motorola.reflex",
				"text/vnd.ms-mediapackage",
				"text/vnd.net2phone.commcenter.command",
				"text/vnd.si.uricatalogue",
				"text/vnd.sun.j2me.app-descriptor",
				"text/vnd.trolltech.linguist",
				"text/vnd.wap.si",
				"text/vnd.wap.sl",
				"text/vnd.wap.wml",

    </magic>
    <!-- XML files can start with a comment but then must not contain processing instructions.
         This should be rare so we assign lower priority here. Priority is also lower than text/html magics
         for them to be preferred for HTML starting with comment.-->
    <magic priority="30">
      <match value="&lt;!--" type="string" offset="0"/>
    </magic>

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

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;