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

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

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.
 * 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 {

        extra.put("reloadable_ja_stop", JapaneseStopTokenFilterFactory::new);
        extra.put("kanji_number", KanjiNumberFilterFactory::new);
        extra.put("kuromoji_pos_concat", PosConcatenationFilterFactory::new);
        extra.put("char_type", CharTypeFilterFactory::new);
        extra.put("number_concat", NumberConcatenationFilterFactory::new);

 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */

            });
            return extractData;
        } finally {
            xpathAPI.remove();
        }
    }

    /**
     * Extracts strings from a document using the specified XPath expression.
     *
     * @param document the DOM document to extract strings from
     * @param path the XPath expression to evaluate
     * @return an array of strings extracted from the document
     */

            ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *
     * @param document The document to parse, represented as a map of field names to values.
     * @param fields The fields to extract from the document.
     * @param tagFieldNames The names of the fields that contain tags.

            throw new RobotsTxtException("Failed to parse robots.txt.", e);
        }
    }

    /**
     * Extracts the value from a line using the given pattern.
     * @param pattern the pattern to match against
     * @param line the line to extract the value from
     * @return the extracted value, or null if no match
     */
    protected String getValue(final Pattern pattern, final String line) {

                throw new ExtractException(e);
            }
        }

        return encoding;
    }

    /**
     * Extracts text content from the given content by removing tags and processing attributes.
     * @param content The content to extract from.
     * @return The extracted text.
     */
    protected String extractString(final String content) {

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {
        super();
    }

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.