/**
     * Default character encoding for content extraction.
     */
    protected String encoding = Constants.UTF_8;

    /**
     * The preload size for charset detection.
     */
    protected int preloadSizeForCharset = 2048;

    /**
     * Indicates whether comment tags should be ignored during extraction.
     */
    protected boolean ignoreCommentTag = false;

    /**

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.

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

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

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */

 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.

 * 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

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

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

    private static final long serialVersionUID = 1L;

        } 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.
     */

 */
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;

        return htmlTagPattern;
    }

    /**
     * Gets the pattern used for extracting charset from meta tags.
     *
     * @return the meta charset pattern
     */
    public Pattern getMetaCharsetPattern() {
        return metaCharsetPattern;
    }

    /**
     * Sets the pattern used for extracting charset from meta tags.
     *
     * @param metaCharsetPattern the meta charset pattern to set

     * If no extractor exists for the key, a new array containing the extractor is created and associated with the key.
     *
     * @param key       The key associated with the extractor. Must not be null or blank.
     * @param extractor The extractor to add. Must not be null.
     */
    public void addExtractor(final String key, final Extractor extractor) {
        if (StringUtil.isBlank(key)) {