</property>
		<property name="allRequired">true</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>"http[s]?:.*"</arg>
		</postConstruct>
		<postConstruct name="addRule">
			<arg>"mimeType"</arg>
			<!-- Supported MIME type -->
			<arg>"text/html"</arg>
		</postConstruct>
	</component>

	<component name="webFileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >

        try {
            final String filename = getDecodeText(bodyPart.getFileName());
            final String mimeType = mimeTypeHelper.getContentType(null, filename);
            if (mimeType != null) {
                final Extractor extractor = extractorFactory.getExtractor(mimeType);
                if (extractor != null) {
                    try (final InputStream in = bodyPart.getInputStream()) {

        assertArgumentNotEmpty("path", path);

        final InputStream is = ResourceUtil.getResourceAsStream(path);
        try {
            final String mimetype = URLConnection.guessContentTypeFromStream(is);
            if (mimetype != null) {
                return mimetype;
            }
            return URLConnection.guessContentTypeFromName(path);
        } catch (final IOException e) {
            throw new IORuntimeException(e);

     * @param mimeType The MIME type of the content.
     * @return The file extension including the dot (e.g., ".gif"), or empty string if unknown.
     */
    protected String getExtensionFromMimeType(final String mimeType) {
        if (mimeType == null) {
            return "";
        }
        return switch (mimeType) {
        case "image/gif" -> ".gif";

{
    "properties": {
      "parentUrl": {
        "type": "keyword"
      },
      "method": {
        "type": "keyword"
      },
      "mimeType": {
        "type": "keyword"
      },
      "sessionId": {
        "type": "keyword"
      },
      "url": {
        "type": "keyword"
      },
      "executionTime": {
        "type": "long"
      },
      "createTime": {
        "type": "long"
      },

        stream(config.getPermissions()).of(stream -> stream.forEach(p -> roleTypeList.add(p)));
        defaultDataMap.put(fessConfig.getIndexFieldRole(), roleTypeList);
        // mimetype
        defaultDataMap.put(fessConfig.getIndexFieldMimetype(), mimeType);
        // title
        // content
        // cache
        // digest
        // host
        // site
        // url
        // anchor

                }
                final String filename = entry.getName();
                final String mimeType = mimeTypeHelper.getContentType(null, filename);
                if (mimeType != null) {
                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {

                }
                final String filename = entry.getName();
                final String mimeType = mimeTypeHelper.getContentType(null, filename);
                if (mimeType != null) {
                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {

                }
                final String filename = head.getPath();
                final String mimeType = mimeTypeHelper.getContentType(null, filename);
                if (mimeType != null) {
                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        InputStream is = null;
                        try {

        fess_doc = {
            "url": doc.get("url", ""),
            "title": doc.get("title", ""),
            "content": doc.get("content", ""),
            "mimetype": doc.get("mimetype", "text/html"),
            "filetype": doc.get("filetype", "html"),
            "created": doc.get("@timestamp", ""),
            "timestamp": doc.get("@timestamp", ""),
            # Add custom fields as needed
        }