* when making decisions, they may crawl pages marked "hourly" less
     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**

                    || PRIORITY_ELEMENT.equals(qName)) {
                buf = new StringBuilder();
            }
        }

        @Override
        public void characters(final char[] ch, final int offset, final int length) {
            if (buf != null) {
                buf.append(new String(ch, offset, length));
            }
        }

        @Override

  <mime-type type="text/x-robots">
    <!-- robots.txt file -->
    <!-- draft: https://datatracker.ietf.org/doc/html/draft-koster-rep -->
    <!-- should have a higher priority than rfc822 - TIKA-3489 -->
    <!-- and a lower priority than pcap - TIKA-4174 -->
    <magic priority="55">
      <match minShouldMatch="2">
        <match value="user-agent:" type="stringignorecase" offset="0"/>

     *
     * @param c the character to check
     * @return {@code true} if the character is a valid URL character, {@code false} otherwise
     */
    public static boolean isUrlChar(final char c) {
        if (c >= 'a' && c <= 'z' //
                || c >= 'A' && c <= 'Z' //
                || c >= '0' && c <= '9' //
                || c == '.' //
                || c == '-' //
                || c == '*' //

    public static String stripInvalidXMLCharacters(final String in) {
        if (StringUtil.isEmpty(in)) {
            return in;
        }

        final StringBuilder buf = new StringBuilder(in.length());
        char c;
        for (int i = 0; i < in.length(); i++) {
            c = in.charAt(i);
            if (c == 0x9 || c == 0xA || c == 0xD || c >= 0x20 && c <= 0xD7FF || c >= 0xE000 && c <= 0xFFFD

# _/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/
# 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

 */
package org.codelibs.fess.crawler.util;

import java.io.IOException;
import java.io.InputStream;

/**
 * A wrapper for an {@link InputStream} that ignores the {@link #close()} method call.
 * This can be useful when you want to prevent the underlying input stream from being closed.
 *
 * <p>All other methods delegate to the wrapped input stream.</p>
 *
 */
public class IgnoreCloseInputStream extends InputStream {

 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>
 * The log level can be set to DEBUG, INFO, WARN, or ERROR, and the class provides methods to check if a specific log level is enabled.
 * </p>
 *

 *   <li>Dependency injection using {@code @Resource} annotation</li>
 *   <li>Lifecycle management using {@code @PostConstruct} and {@code @PreDestroy} annotations</li>
 * </ul>
 *
 * <p>Components can be registered in two ways:
 * <ul>
 *   <li>As singletons, where one instance is shared throughout the container's lifecycle</li>
 *   <li>As prototypes, where a new instance is created each time the component is requested</li>

     * This method delegates to {@link FileInputStream#mark(int)}.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        fileInputStream.mark(readlimit);
    }

    /**