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

		</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" >

#!/bin/bash

cmd_type=$1
url=$2
output_file=$3
mimetype=${4:-}
image_size=100x100
target_file=$(echo "$url" | sed -e "s#^file:/*#/#g")

check_command() {
  cmd=$1
  cmd_path=$(command -v "${cmd}")
  if [[ ! -e "${cmd_path}" ]] ; then
    echo "${cmd} does not exist."
    exit 1
  fi
}

# Get ImageMagick command (magick for v7, convert for v6)
get_imagemagick_cmd() {
  if command -v magick >/dev/null 2>&1; then

     */
    protected boolean isImageMimeType(final ResponseData responseData) {
        final String mimeType = responseData.getMimeType();
        if (mimeType == null) {
            return true;
        }

        return switch (mimeType) {
        case "image/png", "image/gif", "image/jpeg", "image/bmp" -> true;
        default -> false;
        };
    }

    /**

    echo -e "${GREEN}PASSED${NC}"
    ((TESTS_PASSED++))
else
    echo -e "${RED}FAILED${NC}"
    ((TESTS_FAILED++))
fi

echo ""
echo "--- Mimetype argument tests ---"

echo -n "Testing: mimetype is 4th argument... "
if grep -q 'mimetype=\${4:-}' "${GENERATE_THUMBNAIL}"; then
    echo -e "${GREEN}PASSED${NC}"
    ((TESTS_PASSED++))
else
    echo -e "${RED}FAILED${NC}"
    ((TESTS_FAILED++))
fi

        # Transform to Fess format
        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

    /**
     * Get file type icon based on URL or mimetype
     */
    function getFileTypeIcon(url, mimetype) {
        if (mimetype) {
            if (mimetype.indexOf('pdf') !== -1) return 'fa-file-pdf-o';
            if (mimetype.indexOf('word') !== -1 || mimetype.indexOf('document') !== -1) return 'fa-file-word-o';
            if (mimetype.indexOf('excel') !== -1 || mimetype.indexOf('spreadsheet') !== -1) return 'fa-file-excel-o';

        // Default constructor
    }

    /**
     * Initializes the extension override map by loading configuration from FessConfig.
     * The mappings are loaded from the crawler.document.mimetype.extension.overrides property,
     * where each line contains a mapping in the format ".ext=mime/type".
     */
    @PostConstruct
    public void init() {

        putResultDataBody(dataMap, fessConfig.getIndexFieldAnchor(), StringUtil.EMPTY);
        // mimetype
        putResultDataBody(dataMap, fessConfig.getIndexFieldMimetype(), mimeType);
        if (fileTypeHelper != null) {
            // filetype
            putResultDataBody(dataMap, fessConfig.getIndexFieldFiletype(), fileTypeHelper.get(mimeType));
        }
        // content_length

        }
        return buf.toString();
    }

    /**
     * Sets the MIME type.
     * @param mimeType The MIME type.
     */
    public void setMimeType(final String mimeType) {
        this.mimeType = mimeType;
    }