* This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LhaExtractor.class);

    /** Maximum content size for extraction. -1 means no limit. */

**Strategy**: `CrawlerClient`, `Extractor`, `Transformer` - pluggable implementations
**Builder**: `RequestDataBuilder`, `ExtractorBuilder` - fluent construction
**Template Method**: `AbstractCrawlerClient`, `AbstractExtractor` - common logic with overrides
**DI**: LastaFlute container with `@Resource` and XML config

### Core Principles

**Thread Safety**:
- `AtomicLong` for counters (`CrawlerContext.accessCount`)

import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(TarExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

 *   <li>Link URL extraction</li>
 *   <li>Code block content extraction</li>
 *   <li>Clean text conversion from Markdown</li>
 *   <li>Configurable encoding</li>
 * </ul>
 */
public class MarkdownExtractor extends AbstractExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(MarkdownExtractor.class);

    /** Default encoding for Markdown files. */

 * The extractor first tries to match against the URL, then falls back to the resource name if available.
 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

    /** Map of regex patterns to passwords for static password configuration. */

 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */

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 {

    private static final Logger logger = LogManager.getLogger(ApiExtractor.class);

    /** The URL of the API endpoint. */
    protected String url;

    /** The access timeout in seconds. */

 *   <li>Nested structure flattening with configurable depth</li>
 *   <li>Array element extraction</li>
 *   <li>Configurable field separator and array formatting</li>
 * </ul>
 */
public class JsonExtractor extends AbstractExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(JsonExtractor.class);

    /** Jackson ObjectMapper for JSON parsing. */

 *   <li>Quoted field handling</li>
 *   <li>Column names as metadata</li>
 *   <li>Configurable encoding and row limits</li>
 * </ul>
 */
public class CsvExtractor extends AbstractExtractor {
    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(CsvExtractor.class);

    /** Default encoding for CSV files. */
    protected String encoding = Constants.UTF_8;