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 {

    /**
     * Sets the MIME type of the content to extract.
     *
     * @param mimeType the MIME type to set
     * @return this builder instance for method chaining
     */
    public ExtractorBuilder mimeType(final String mimeType) {
        this.mimeType = mimeType;
        return this;
    }

    /**
     * Sets the filename of the content to extract.
     *
     * @param filename the filename to set

    public void test_builder() {
        assertEquals("test", extractorFactory.builder(new ByteArrayInputStream("test".getBytes()), null).extract().getContent());
        assertEquals("test",
                extractorFactory.builder(new ByteArrayInputStream("test".getBytes()), null).filename("test.txt").extract().getContent());
    }

    public void test_addExtractor_weight() {
        final String key = "application/test";

            }
        } catch (final MaxLengthExceededException e) {
            throw e;
        } catch (final Exception e) {
            if (buf.length() == 0) {
                throw new ExtractException("Could not extract a content.", e);
            }
        }

        return new ExtractData(buf.toString().trim());
    }

    /**
     * Sets the maximum content size.

            }
        } catch (final MaxLengthExceededException e) {
            throw e;
        } catch (final Exception e) {
            if (buf.length() == 0) {
                throw new ExtractException("Could not extract a content.", e);
            }
        } finally {
            CloseableUtil.closeQuietly(ais);
        }

        return buf.toString().trim();
    }

    /**

        }
        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.

 * 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
     */

                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.helper.MimeTypeHelper;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *