/**
     * Filter for URLs to control which URLs are processed.
     */
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    protected RuleManager ruleManager;

    /**
     * Controller for managing crawling intervals and delays.
     */
    protected IntervalController intervalController;

    /**

 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>
 *   <li>Validation</li>
 *   <li>XInclude awareness</li>
 * </ul>
 *
 * <p>
 * It also allows defining field rules using XPath expressions to extract specific data from the XML document and map it to fields in the ResultData.
 * The extracted data is then formatted into an XML structure suitable for indexing.
 * </p>
 *
 * <p>

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    @Resource
    protected RuleManager ruleManager;

    /**
     * Container for managing crawler components.
     */
    @Resource

				"application/onenote",
				"application/parityfec",
				"application/patch-ops-error+xml",
				"application/pgp-encrypted",
				"application/pgp-keys",
				"application/pgp-signature",
				"application/pics-rules",
				"application/pidf+xml",
				"application/pidf-diff+xml",
				"application/pkcs10",
				"application/pkcs7-mime",
				"application/pkcs7-signature",
				"application/pkix-cert",
				"application/pkix-crl",

      },
      "dutch_stemmer": {
        "type":       "stemmer",
        "language":   "dutch"
      },
      "dutch_override": {
        "type":       "stemmer_override",
        "rules": [
          "fiets=>fiets",
          "bromfiets=>bromfiets",
          "ei=>eier",
          "kind=>kinder"
        ]
      },
      "english_keywords": {
        "type":       "keyword_marker",

  <mime-type type="application/pgp-keys"/>

  <mime-type type="application/pgp-signature">
    <glob pattern="*.asc"/>
    <glob pattern="*.sig"/>
  </mime-type>

  <mime-type type="application/pics-rules">
    <glob pattern="*.prf"/>
  </mime-type>
  <mime-type type="application/pidf+xml"/>
  <mime-type type="application/pidf-diff+xml"/>
  <mime-type type="application/pkcs10">
    <glob pattern="*.p10"/>