* It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface

 * document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>
 *   <li>Text extraction from PDF pages</li>
 *   <li>Embedded document extraction</li>
 *   <li>Annotation extraction (file attachments)</li>
 *   <li>Metadata extraction</li>
 *   <li>Password-protected PDF support</li>
 *   <li>Configurable timeout for extraction process</li>
 * </ul>
 *
 * @author shinsuke
 */

 */
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.
 */

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.

    /**
     * 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;

    /**

## Overview

**Fess Crawler** is a powerful, flexible Java-based web crawling framework designed for enterprise-scale content extraction and processing. Built with a modular architecture, it supports multiple protocols (HTTP/HTTPS, File System, FTP, SMB, Cloud Storage) and provides extensive content extraction capabilities from various document formats.

### Key Features

 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>
 *   <li>Reading content as plain text if all other methods fail</li>
 *   <li>Applying post-extraction filters</li>
 *   <li>Handling Tika exceptions, including zip bomb exceptions</li>
 * </ul>
 *

 * 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;

            // Test file name extraction
            assertEquals("file.txt", new SmbFile("smb1://server/share/file.txt").getName());
            // Test directory name extraction (should include trailing slash)
            assertEquals("dir/", new SmbFile("smb1://server/share/dir/").getName());
            // Test share name extraction
            assertEquals("share/", new SmbFile("smb1://server/share/").getName());

 *
 * <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.