final String xpath = xpathConfigMap.get(XPath.DEFAULT_LANG);
        if (StringUtil.isNotBlank(xpath)) {
            return xpath;
        }
        return fessConfig.getCrawlerDocumentHtmlLangXpath();
    }

    /**
     * Gets the XPath expression for extracting content.
     *
     * @param fessConfig the Fess configuration
     * @param xpathConfigMap the XPath configuration map

    }

    /**
     * Checks if a path is valid for crawling (not a JavaScript, mailto, or other invalid URL).
     *
     * @param path the path to validate
     * @return true if the path is valid, false otherwise
     */
    protected boolean isValidPath(final String path) {
        if (StringUtil.isBlank(path)) {
            return false;
        }

dc:title=title:string\n\

# html

# XPath to extract main content from HTML documents.
crawler.document.html.content.xpath=//BODY
# XPath to extract language attribute from HTML documents.
crawler.document.html.lang.xpath=//HTML/@lang
# XPath to extract digest (description) from HTML documents.
crawler.document.html.digest.xpath=//META[@name='description']/@content
# XPath to extract canonical URL from HTML documents.

    /** The key of the configuration. e.g. //HTML/@lang */
    String CRAWLER_DOCUMENT_HTML_LANG_XPATH = "crawler.document.html.lang.xpath";

    /** The key of the configuration. e.g. //META[@name='description']/@content */
    String CRAWLER_DOCUMENT_HTML_DIGEST_XPATH = "crawler.document.html.digest.xpath";

    /**
     * Reads text from a file using the default encoding.
     *
     * @param path
     *            The file path. Must not be {@literal null} or empty.
     * @return The text read from the file.
     */
    public static String readText(final String path) {
        assertArgumentNotEmpty("path", path);
        return readText(path, Charset.defaultCharset().name());
    }

    /**

    }

    /**
     * Parses an S3 path into bucket name and object path components.
     * @param path the S3 path to parse (format: bucket/object/path)
     * @return an array containing the bucket name and object path
     * @throws CrawlingAccessException if the path format is invalid
     */
    protected String[] parsePath(final String path) {
        if (StringUtil.isNotEmpty(path)) {

    }

    /**
     * Test isPathSafe with path outside base directory
     *
     * @throws Exception
     */
    @Test
    public void testIsPathSafe_PathOutsideBase() throws Exception {
        final Path baseDir = tempFolder.getRoot().toPath();
        final Path outsidePath = Paths.get("/tmp/outside.txt");

    }

    /**
     * Creates a path prefix with trailing slash if path is not empty.
     *
     * @param path the base path
     * @return path with trailing slash or empty string
     */
    protected static String getPathPrefix(final String path) {
        return StringUtil.isEmpty(path) ? StringUtil.EMPTY : path + "/";
    }

    /**
     * Combines path and name to create a full object name.
     *

    /**
     * Creates a GET request for the specified path.
     * @param path the request path
     * @return the configured CurlRequest
     */
    public CurlRequest get(final String path) {
        return request(Method.GET, path).header("Content-Type", "application/json");
    }

    /**
     * Creates a POST request for the specified path.
     * @param path the request path
     * @return the configured CurlRequest
     */

        }

        if (path.startsWith("www.")) {
            return "http://" + path;
        }

        if (path.startsWith("//")) {
            return "file://" + path;
        }
        if (path.startsWith("/")) {
            return "file:" + path;
        }
        if (!path.startsWith("file:")) {
            return "file:/" + path.replace('\\', '/');
        }
        return path;
    }