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.
 *

     * @param outExt the output file extension
     * @return the extracted text content
     * @throws ExtractException if an error occurs while reading the file
     */
    protected String getOutputContent(final File outputFile, final String outExt) {
        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {
            final Map<String, String> params = new HashMap<>();

            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);

    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) {

        this.userPrefix = userPrefix;
    }

    /**
     * Extracts role type information from SMB (Server Message Block) response data.
     * Processes both SMB and SMB1 protocols to extract allowed and denied SIDs.
     *
     * @param responseData the response data containing SMB metadata
     * @return a list of role type strings extracted from the SMB permissions
     */

    }

    public void test_contentGetterSetter() {
        // Test content getter/setter
        ExtractData data = new ExtractData();

        String content = "This is extracted content";
        data.setContent(content);
        assertEquals(content, data.getContent());

        String newContent = "New content";
        data.setContent(newContent);

import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

                logger.warn("Failed to close HTTP client for API extractor", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

            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) {

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content and metadata from CSV files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic delimiter detection (comma, tab, semicolon, pipe)</li>