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.

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);

 * 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
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**

        final Extractor extractor = new Extractor() {
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                return null;
            }
        };

        assertNull(extractorFactory.getExtractor("test"));
        extractorFactory.addExtractor("test", extractor);
        assertEquals(extractor, extractorFactory.getExtractor("test"));
    }

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
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 jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {

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

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
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 jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {

        }
        return null;
    }

    /**
     * Extracts URLs from HTML tag attributes using XPath.
     *
     * @param url the base URL for resolving relative URLs
     * @param document the document to extract URLs from
     * @param xpath the XPath expression to select elements
     * @param attr the attribute name to extract URLs from
     * @param encoding the character encoding to use

            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.

    public void setMailProperties(final Properties mailProperties) {
        this.mailProperties = mailProperties;
    }

    /**
     * Extracts the body text from a MIME message.
     *
     * @param message the MIME message to extract text from
     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {