}
        return new URL(currentUrl);
    }

    /**
     * Gets child URL extraction rules from configuration.
     *
     * @param responseData the response data from crawling
     * @param resultData the result data
     * @return stream of tag-attribute pairs for URL extraction
     */
    @Override

        } catch (final Exception e) {
            throw new ExtractException(e);
        }
    }

    /**
     * Returns the encoding used for text extraction.
     * @return the encoding
     */
    public String getEncoding() {
        return encoding;
    }

    /**
     * Sets the encoding.
     * @param encoding The encoding to set.
     */

            throw new FessSystemException("Could not find extractorFactory.");
        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        if (logger.isDebugEnabled()) {
            logger.debug("url={}, extractor={}", responseData.getUrl(), extractor);
        }
        return extractor;
    }

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

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors

    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override

        this.propertyMap = propertyMap;
    }

    /**
     * Gets the map of child URL extraction rules.
     *
     * @return the child URL rule map
     */
    public Map<String, String> getChildUrlRuleMap() {
        return childUrlRuleMap;
    }

    /**
     * Sets the map of child URL extraction rules.
     *
     * @param childUrlRuleMap the child URL rule map to set
     */

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;

     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (logger.isDebugEnabled()) {
            logger.debug("Accessing {}", url);
        }

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.mail.Address;
import jakarta.mail.BodyPart;
import jakarta.mail.Header;
import jakarta.mail.Message;