* defined in the {@link Rule} interface to provide specific rule logic.
 * </p>
 *
 */
public abstract class AbstractRule implements Rule {

    private static final long serialVersionUID = 1L;

    /** The rule ID. */
    protected String ruleId;

    /** The response processor. */
    protected ResponseProcessor responseProcessor;

    /** The crawler container. */

 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

    private static final long serialVersionUID = 1L;

    /**
     * Constructor.
     * @param message The error message.
     */
    public UnsupportedExtractException(final String message) {
        super(message, false, false);

 * This exception can be thrown with a message, a cause, or both.
 */
public class MimeTypeException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**
     * Creates a new MimeTypeException with the specified detail message and cause.
     *
     * @param message the detail message explaining the reason for the exception

    /**
     * Default keys for suggest settings.
     */
    public static class DefaultKeys {
        /** Index key. */
        public static final String INDEX = "index";
        /** Supported fields key. */
        public static final String SUPPORTED_FIELDS = "supportedFields";
        /** Tag field name key. */
        public static final String TAG_FIELD_NAME = "tagFieldName";
        /** Role field name key. */

 */
public class BadWordSettings {
    private static final Logger logger = LogManager.getLogger(BadWordSettings.class);

    /** Key for bad word settings. */
    public static final String BAD_WORD_SETTINGD_KEY = "badword";

    /** Array settings for bad words. */
    protected ArraySettings arraySettings;

    /** Default bad words. */
    protected static String[] defaultWords = null;

    /**
     * Constructor.

 * It also provides a protected constructor that allows to specify whether or not suppression is enabled or stack trace is writable.
 */
public class CrawlerSystemException extends RuntimeException {

    private static final long serialVersionUID = 1L;

    /**
     * Constructs a new {@code CrawlerSystemException} with the specified detail message and cause.
     *

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content by executing an external command.
 */
public class CommandExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(CommandExtractor.class);

    /** The encoding for the output. */
    protected String outputEncoding = Constants.UTF_8;

    /** The extension for the output file. */

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class MsWordExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(MsWordExtractorTest.class);

    public MsWordExtractor msWordExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

     *
     * @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 == '-' //

            throw new CrawlerSystemException(e);
        } finally {
            if (tempDocRoot) {
                docRoot.delete();
            }
        }
    }

    protected static File createDocRoot(final int count) {
        try {
            final File tempDir = File.createTempFile("crawlerDocRoot", "");
            tempDir.delete();
            tempDir.mkdirs();

            // robots.txt