* @return The crawl delay value in seconds. Returns 0 if no matching directive is found
     *         or no crawl delay is specified for the matching directive.
     */
    public int getCrawlDelay(final String userAgent) {
        final Directive directive = getMatchedDirective(userAgent);
        if (directive == null) {
            return 0;
        }
        return directive.getCrawlDelay();
    }

    /**

                    if (value != null) {
                        if (!currentDirectiveList.isEmpty() && value.length() > 0) {
                            for (final Directive directive : currentDirectiveList) {
                                directive.addDisallow(value);
                            }
                        }
                    } else if ((value = getValue(ALLOW_RECORD, line)) != null) {

 *   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *
 * <p>
 * The MIME type detection is based on the {@code tika-mimetypes.xml} resource, which is loaded during initialization.
 * </p>
 *
 * <p>
 * Usage:
 * </p>

    }

    /**
     * Returns the preload size for charset detection.
     * @return The preload size for charset detection.
     */
    public int getPreloadSizeForCharset() {
        return preloadSizeForCharset;
    }

    /**
     * Sets the preload size for charset detection.
     * @param preloadSizeForCharset The preload size for charset detection to set.
     */

package org.codelibs.fess.crawler.helper;

import java.io.InputStream;
import java.util.Map;

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**
     * Determines the content type of the given input stream and filename.
     * @param is the input stream to analyze

    /**
     * Checks if automatic UTF-8 encoding detection is enabled.
     *
     * @return True if auto-detection is enabled, false otherwise
     */
    public boolean isAutodetectEncoding() {
        return autodetectEncoding;
    }

    /**
     * Sets whether automatic UTF-8 encoding detection is enabled.
     *
     * @param autodetectEncoding True to enable auto-detection, false to disable
     */

                        }

                        final RobotsTxt.Directive directive = robotsTxt.getMatchedDirective(userAgent);
                        if (directive != null) {
                            if (useRobotsTxtDisallows) {
                                for (String urlPattern : directive.getDisallows()) {
                                    if (StringUtil.isNotBlank(urlPattern)) {

 * 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

 * 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,
 * such as MIME type detection, extractor selection, and content length validation.
 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {

    }

    /**
     * Gets the preload size for charset detection.
     *
     * @return the preload size in bytes
     */
    public int getPreloadSizeForCharset() {
        return preloadSizeForCharset;
    }

    /**
     * Sets the preload size for charset detection.
     *
     * @param preloadSizeForCharset the preload size in bytes to set
     */