throw exceptionSet.iterator().next();
            }
            writer.flush();
            final ExtractData extractData = new ExtractData(writer.toString());
            extractMetadata(document, extractData);
            return extractData;
        } catch (final Exception e) {
            throw new ExtractException(e);
        }
    }

    /**

        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        for (final String key : extractData.getKeySet()) {
            logger.info("{}={}", key, String.join("|", extractData.getValues(key)));
        }

    }

    public void test_usingPredefinedConstants() {
        // Test using predefined constants
        ExtractData data = new ExtractData();

        data.putValue(ExtractData.RESOURCE_NAME_KEY, "test.pdf");
        data.putValue(ExtractData.URL, "https://example.com/test.pdf");
        data.putValues(ExtractData.FILE_PASSWORDS, new String[] { "pass1", "pass2" });

            if (getLogger().isDebugEnabled()) {
                getLogger().debug("ExtractData: {}", extractData);
            }
            // meta
            extractData.getKeySet().stream().filter(k -> extractData.getValues(k) != null).forEach(key -> {
                final String[] values = extractData.getValues(key);
                metaDataMap.put(key, values);

                // meta -> content

            executeCommand(inputFile, outputFile);

            final ExtractData extractData = new ExtractData(new String(FileUtil.readBytes(outputFile), outputEncoding));
            if (StringUtil.isNotBlank(resourceName)) {
                extractData.putValues("resourceName", new String[] { resourceName });
            }

            return extractData;
        } catch (final IOException e) {

            }
        }

        final ExtractData extractData = new ExtractData(textBuilder.toString().trim());

        // Add column metadata
        if (extractColumnMetadata && headers != null) {
            extractData.putValues("columns", headers);
            extractData.putValue("column_count", String.valueOf(headers.length));
        }

        extractData.putValue("row_count", String.valueOf(rows.size()));

            final ExtractData extractData = new ExtractData(getOutputContent(outputFile, outExt));
            if (StringUtil.isNotBlank(resourceName)) {
                extractData.putValues("resourceName", new String[] { resourceName });
            }

            return extractData;
        } catch (final OfficeException e) {

 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {
 *     ExtractData extractData = new ExtractorBuilder(crawlerContainer, in, new HashMap<>())
 *         .mimeType("application/pdf")
 *         .filename("example.pdf")
 *         .maxContentLength(1024 * 1024)
 *         .extract();
 *
 *     String content = extractData.getContent();
 *     // Process the extracted content
 * } catch (IOException e) {

                }
                final ExtractData extractData = new ExtractData(content);
                final long contentLength;
                if (isByteStream) {
                    contentLength = ((ByteArrayInputStream) inputStream).available();
                } else {
                    contentLength = tempFile != null ? tempFile.length() : 0;
                }

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;