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

package org.codelibs.fess.crawler.log;

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,

        assertFalse(urlFilter.match("https://example.com/script.js"));
        assertFalse(urlFilter.match("https://example.com/admin/login"));
        assertFalse(urlFilter.match("https://example.com/page#section"));
    }

    /**
     * Test adding invalid regex exclude pattern
     */
    public void test_addExclude_invalidRegex() {
        String sessionId = "test-session-007";

 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns
 * and optionally at specific positions in the processing order.</p>
 *
 * <p>This factory is typically initialized through dependency injection and can be

     */
    public static final String MIME_TYPE = "mimeType";

    /**
     * Field name for creation time.
     */
    public static final String CREATE_TIME = "createTime";

    /**
     * Field name for execution time.
     */
    public static final String EXECUTION_TIME = "executionTime";

    /**
     * Field name for content length.
     */
    public static final String CONTENT_LENGTH = "contentLength";

import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * The {@link CrawlerContext} class holds the context information for a crawler execution.
 * It contains various attributes related to the crawler's state, configuration, and runtime data.
 * This class provides methods to access and modify these attributes, allowing for control and monitoring

    /**
     * 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
     */

 * 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

    protected String method;

    /** The MIME type of the accessed resource. */
    protected String mimeType;

    /** The creation time of the access result. */
    protected Long createTime;

    /** The execution time of the access. */
    protected Integer executionTime;

    /** The content length of the accessed resource. */
    protected Long contentLength;

    /** The last modified time of the accessed resource. */

 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *
 * <p>
 * The {@link TikaDetectParser} inner class extends {@link CompositeParser} to provide auto-detection of the MIME type
 * of the document. It also handles zip bomb prevention and embedded document extraction.
 * </p>
 *
 * <p>