default boolean isHtmlMimetypeForCache(final String mimetype) {
        final String[] mimetypes = getCrawlerDocumentCacheHtmlMimetypes().split(",");
        if (mimetypes.length == 1 && StringUtil.isBlank(mimetypes[0])) {
            return true;
        }
        return stream(mimetypes).get(stream -> stream.anyMatch(s -> s.equalsIgnoreCase(mimetype)));
    }

    String getCrawlerDocumentCacheSupportedMimetypes();

			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel.sheet.3"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel.sheet.4"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel.workspace.3"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>

     * @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";

                }
                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 {

#!/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

index.field.created=created
# Field name for timestamp in the index.
index.field.timestamp=timestamp
# Field name for label in the index.
index.field.label=label
# Field name for MIME type in the index.
index.field.mimetype=mimetype
# Field name for parent ID in the index.
index.field.parent_id=parent_id
# Field name for important content in the index.
index.field.important_content=important_content
# Field name for content in the index.

<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<include path="crawler/robotstxt.xml" />
	<include path="crawler/contentlength.xml" />
	<include path="crawler/mimetype.xml" />

	<component name="internalHttpClient" class="org.codelibs.fess.crawler.client.http.HcHttpClient"
		instance="prototype">
		<property name="connectionTimeout">15000</property>

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

     * @return true if the content is HTML, false otherwise
     */
    protected boolean isHtml(final ResponseData responseData) {
        final String mimeType = responseData.getMimeType();
        if ("text/html".equals(mimeType) || "application/xhtml+xml".equals(mimeType)) {
            return true;
        }
        return false;
    }

    /**
     * Adds a rule for extracting child URLs from HTML tags.
     *