# Lasta Di properties, you can set container's options
# _/_/_/_/_/_/_/_/_/_/

# location of smart-deploy mode e.g. maihama_env.properties: lasta_di.smart.deploy.mode
#smart.deploy.mode.location = maihama_env.properties: lasta_di.smart.deploy.mode

# package for smart deploy target e.g. org.docksidestage.app
smart.package1 = org.codelibs.fess.crawler

        return stripInvalidXMLCharacters(//
                value//
                        .replace("&", "&") //
                        .replace("<", "&lt;")//
                        .replace(">", "&gt;")//
                        .replace("\"", "&quot;")//
                        .replace("\'", "&apos;")//
        );
    }

    /**
     * Strips invalid XML characters from the input string.

    int NO_URL_IN_QUEUE = 4;

    /** Constant indicating that the crawler is waiting for new URLs. */
    int WAIT_NEW_URL = 8;

    /**
     * Introduces a delay based on the specified type.
     *
     * @param type the type of delay to be introduced
     */
    void delay(int type);

    /** Delay in milliseconds after processing a URL */
    protected long delayMillisAfterProcessing = 0L;

    /** Delay in milliseconds when no URL is in the queue */
    protected long delayMillisAtNoUrlInQueue = 500L;

    /** Delay in milliseconds before processing a URL */
    protected long delayMillisBeforeProcessing = 0L;

    /** Delay in milliseconds for waiting for new URLs */

User-agent: FessCrawler
Disallow:           # allows all 

User-agent: BruteBot
Disallow: /
Allow: /foo/bar/
Crawl-delay: 1314000

# welcome!
User-agent: Googlebot
Crawl-delay: 1

User-agent: *
Disallow: /private/
Disallow: /help        # disallows /help.html, /help/index.html, etc.
Allow: /help/faq.html
Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

 *
 * <p>
 * Subclasses are responsible for implementing the abstract methods to define the actual delay
 * mechanism for each of these stages.
 * </p>
 *
 * <p>
 * The class also provides a mechanism to ignore exceptions that may occur during the delay process.
 * If {@link #ignoreException} is set to true, any exceptions thrown during the delay will be caught
 * and ignored. Otherwise, they will be re-thrown as {@link CrawlerSystemException}.

 * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
 * ensuring that requests to the same host are not made too frequently.
 * The delay is calculated based on the configured delayMillisBeforeProcessing parameter.
 * If the time since the last request to the host is less than the configured delay,
 * the thread waits until the delay has elapsed.
 * This class is thread-safe.
 */

    }

    public void test_doGet_dir() {
        final File file = ResourceUtil.getResourceAsFile("test");
        String path = file.getAbsolutePath();
        if (!path.startsWith("/")) {
            path = "/" + path.replace('\\', '/');
        }
        try {
            fsClient.doGet("file://" + path);
            fail();
        } catch (final ChildUrlsException e) {
            final Set<RequestData> urlSet = e.getChildUrlList();

        String input = content.replaceAll("[\\r\\n]", " ");
        if (ignoreCommentTag) {
            input = input.replaceAll("<!--[^>]+-->", "");
        } else {
            input = input.replace("<!--", "").replace("-->", "");
        }
        final Matcher matcher = getTagPattern().matcher(input);
        final StringBuffer sb = new StringBuffer();
        final Pattern attrPattern = Pattern.compile("\\s[^ ]+=\"([^\"]*)\"");

    protected static final Pattern ALLOW_RECORD = Pattern.compile("^allow:\\s*([^\\s]*)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing crawl-delay records. */
    protected static final Pattern CRAWL_DELAY_RECORD = Pattern.compile("^crawl-delay:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for Sitemap record.
     */