// Process URL should handle different URL formats
        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");
        urlFilter.processUrl("ftp://files.server.com/documents/");
        urlFilter.processUrl("file:///local/path/file.txt");

        // Should complete without errors
        assertNotNull(urlFilter);
    }

    /**

import org.codelibs.jcifs.smb1.SmbFileInputStream;
import org.codelibs.jcifs.smb1.util.LogStream;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

    private static final Logger logger = LogManager.getLogger(ApiExtractor.class);

    /** The URL of the API endpoint. */
    protected String url;

 * This client supports operations on object storage systems compatible with S3 protocol.
 *
 * <p>This client requires the following initialization parameters:
 * <ul>
 *   <li>endpoint - The URL of the MinIO server</li>
 *   <li>accessKey - The access key for authentication</li>
 *   <li>secretKey - The secret key for authentication</li>
 *   <li>connectTimeout - Connection timeout in milliseconds (default: 10000)</li>

import org.codelibs.jcifs.smb.impl.SmbFile;
import org.codelibs.jcifs.smb.impl.SmbFileInputStream;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

-->
<!--
  Description: This xml file defines the valid mime types used by Tika.
  The mime type data within this file is based on information from various
  sources like Apache Nutch, Apache HTTP Server, the file(1) command, etc.

  Notes:
   * Tika supports a wider range of match types than Freedesktop does
   * Glob patterns must be unique, if there's a clash assign to the most
     popular format