/**
     *  Evaluate XPath string to an XObject.
     *  XPath namespace prefixes are resolved from the namespaceNode.
     *  The implementation of this is a little slow, since it creates
     *  a number of objects each time it is called.  This could be optimized
     *  to keep the same objects around, but then thread-safety issues would arise.
     *
     *  @param contextNode The node to start searching from.

     */
    @Override
    public int read(final byte[] b) throws IOException {
        return inputStream.read(b);
    }

    /**
     * Repositions this stream to the position at the time the mark method was last called.
     *
     * @throws IOException if this stream has not been marked or if the mark has been invalidated
     */
    @Override
    public synchronized void reset() throws IOException {

            return true;
        }
        return directive.allows(path);
    }

    /**
     * Gets the crawl delay value for the specified user agent from robots.txt.
     * The crawl delay specifies the time (in seconds) to wait between successive requests.
     *
     * @param userAgent The user agent string to match against robots.txt directives
     * @return The crawl delay value in seconds. Returns 0 if no matching directive is found

     */
    public void awaitTermination() {
        awaitTermination(0);
    }

    /**
     * Waits for the crawling process to terminate for a specified duration.
     * @param millis The maximum time to wait in milliseconds. A value of 0 means wait indefinitely.
     */
    public void awaitTermination(final long millis) {
        if (parentThread != null) {
            try {
                parentThread.join(millis);

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client.storage;

import java.io.ByteArrayInputStream;
import java.time.Duration;
import java.util.HashMap;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.InputStreamUtil;

 * It also integrates with other Fess Crawler components, such as {@link ContentLengthHelper} and
 * {@link MimeTypeHelper}, to handle content length checks and MIME type detection.
 * </p>
 *
 * <p>
 * The class uses JCIFS properties to configure the SMB connection.
 * </p>
 *
 * <p>
 * Usage example:
 * </p>
 *
 * <pre>
 * {@code

import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URI;
import java.net.URISyntaxException;
import java.time.Duration;
import java.util.HashSet;
import java.util.Queue;
import java.util.Set;
import java.util.concurrent.ConcurrentLinkedQueue;

import org.apache.commons.lang3.StringUtils;
import org.apache.commons.net.ftp.FTP;

  </mime-type>
  
  <mime-type type="application/ecmascript">
    <glob pattern="*.ecma"/>
  </mime-type>
  <mime-type type="application/edi-consent"/>
  <mime-type type="application/edi-x12"/>
  <mime-type type="application/edifact"/>
  <mime-type type="application/emma+xml">
    <glob pattern="*.emma"/>
  </mime-type>
  <mime-type type="application/envi.hdr">

    /** Map to store maximum content lengths for specific MIME types */
    protected Map<String, Long> maxLengthMap = new HashMap<>();

    /**
     * Adds a maximum content length for a specific MIME type.
     * @param mimeType The MIME type for which to set the maximum length
     * @param maxLength The maximum content length in bytes
     * @throws CrawlerSystemException if the MIME type is blank or maxLength is negative
     */

 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface
 * for configuring the extraction parameters and handling the underlying complexities of content processing,