}
        return new File(baseDir, filePath);
    }

    /**
     * Gets the base path for storing files.
     *
     * @return the base path
     */
    public String getPath() {
        return path;
    }

    /**
     * Sets the base path for storing files.
     *
     * @param path the base path to set
     */
    public void setPath(final String path) {
        this.path = path;

    }

    /**
     * Gets the base href from the document's BASE tag.
     *
     * @param document the document to extract base href from
     * @return the base href URL, or null if not found
     */
    protected String getBaseHref(final Document document) {
        try {
            final XPathNodes list = getXPathAPI().selectNodeList(document, "//BASE");
            if (list.size() > 0) {

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

import org.codelibs.fess.crawler.transformer.Transformer;

/**
 * An abstract base class for transformers.
 * Provides basic implementation for managing the transformer's name.
 *
 */
public abstract class AbstractTransformer implements Transformer {

    /**

        try {
            switch (type) {
            case PRE_PROCESSING:
                delayBeforeProcessing();
                break;
            case POST_PROCESSING:
                delayAfterProcessing();
                break;
            case NO_URL_IN_QUEUE:
                delayAtNoUrlInQueue();
                break;
            case WAIT_NEW_URL:
                delayForWaitingNewUrl();

import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;

/**
 * An abstract base class for implementing Extractor interfaces.
 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>

import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}

import org.codelibs.fess.crawler.entity.ExtractData;

import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;

/**
 * PasswordBasedExtractor is an abstract base class for extractors that can handle password-protected files.
 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:

     * @return The response data.
     */
    @Override
    public ResponseData execute(final RequestData request) {
        return switch (request.getMethod()) {
        case GET -> doGet(request.getUrl());
        case HEAD -> doHead(request.getUrl());
        case POST -> doPost(request.getUrl());
        default -> throw new CrawlerSystemException(request.getMethod() + " method is not supported.");
        };
    }

    /**

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */

import org.codelibs.fess.crawler.client.http.RequestHeader;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {