* <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

        logger.info(content);
        assertTrue(content.contains("テスト"));
        for (final String key : extractData.getKeySet()) {
            logger.info("{}={}", key, String.join("|", extractData.getValues(key)));
        }
        assertEquals("4", extractData.getValues("cp:revision")[0]);
        assertEquals("こめんと", extractData.getValues("w:Comments")[0]);

                        .forPath("/minio/health/ready")//
                        .forPort(port)//
                        .withStartupTimeout(Duration.ofSeconds(30)));
        logger.info("Starting {}", IMAGE_NAME);
        minioServer.start();
        logger.info("Started {}", IMAGE_NAME);

        String bucketName = "fess";
        Integer mappedPort = minioServer.getFirstMappedPort();
        Testcontainers.exposeHostPorts(mappedPort);

            final int exitValue = currentProcess.exitValue();

            if (logger.isInfoEnabled()) {
                if (standardOutput) {
                    logger.info("Exit Code: {}", exitValue);
                } else {
                    logger.info("Exit Code: {} - Process Output:\n{}", exitValue, it.getOutput());
                }
            }
            if (exitValue == 143 && mt.isTeminated()) {

        if (e.isDebugEnabled()) {
            logger.debug("Crawling Access Exception at {}", urlQueue.getUrl(), e);
        } else if (e.isInfoEnabled()) {
            logger.info(e.getMessage());
        } else if (e.isWarnEnabled()) {
            logger.warn("Crawling Access Exception at " + urlQueue.getUrl(), e);
        } else if (e.isErrorEnabled()) {

import org.w3c.dom.Node;
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>

                final String settingsSource = getDefaultIndexSettings();
                final String indexName = createIndexName(index);
                if (logger.isInfoEnabled()) {
                    logger.info("Create suggest index: {}", indexName);
                }

                client.admin()
                        .indices()
                        .prepareCreate(indexName)

import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * <p>
 * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.
 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>

    protected void extractMetadata(final PDDocument document, final ExtractData extractData) {
        final PDDocumentInformation info = document.getDocumentInformation();
        if (info == null) {
            return;
        }

        for (final String key : info.getMetadataKeys()) {
            final String value = info.getCustomMetadataValue(key);
            addMetadata(extractData, key, value);
        }
    }

    /**

                }
                return c.admin().indices().prepareCreate(index).setSource(source, XContentType.JSON).execute();
            });
            if (indexResponse.isAcknowledged()) {
                logger.info("Created {} index.", index);
            } else if (logger.isDebugEnabled()) {
                logger.debug("Failed to create {} index.", index);
            }
        }