Follow these steps to run the Spark Pi example:

- Login as user **‘spark’**.
- When the job runs, the library can now use **MinIO** during intermediate processing.
- Navigate to a node with the Spark client and access the spark2-client directory:

```
cd /usr/hdp/current/spark2-client
su spark
```

import org.codelibs.core.stream.StreamUtil;
import org.codelibs.fess.exception.FessSystemException;
import org.w3c.dom.Node;

/**
 * Represents a tag configuration for pruning HTML content during document processing.
 * This class defines tag patterns that match HTML elements based on tag name, CSS class, ID, or custom attributes.
 * It is used to identify and remove unwanted HTML elements from crawled documents.
 */

        if (ComponentUtil.hasIngestFactory()) {
            ingestFactory = ComponentUtil.getIngestFactory();
        }
    }

    /**
     * Stores a document in the index after processing and validation.
     * Handles document transformation, field addition, and batched indexing.
     *
     * @param paramMap the data store parameters
     * @param dataMap the document data to store

	token := r.Form.Get(stsToken)
	if token == "" {
		token = r.Form.Get(stsWebIdentityToken)
	}

	accessToken := r.Form.Get(stsWebIdentityAccessToken)

	// RoleARN parameter processing: If a role ARN is given in the request, we
	// use that and validate the authentication request. If not, we assume this
	// is an STS request for a claim based IDP (if one is present) and set
	// roleArn = openid.DummyRoleARN.

 * <p>
 * The {@link ContentWriter} functional interface is used to abstract the process of writing content to a writer.
 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

        assertEquals(1, mockService.getRegistrationCount());
        assertTrue(mockService.hasRegistration(regId));

        // 2. Heartbeat processing
        assertTrue(mockService.processHeartbeat(regId, 1));
        assertTrue(mockService.processHeartbeat(regId, 2));
        assertTrue(mockService.processHeartbeat(regId, 3));

        // 3. Event notifications

        User user = createTestUser("testuser");
        try {
            authenticationManager.insert(user);
            fail("Should throw NullPointerException when processing null chain");
        } catch (NullPointerException e) {
            // Expected behavior when null chain is processed
            assertTrue(true);
        }
    }

    // Test chains order preservation

            // but we can verify the method signature and basic functionality
            SearchEngineUtil.scroll("test_index", hit -> {
                callbackCount.incrementAndGet();
                return true; // Continue processing
            });
        } catch (Exception e) {
            // Expected in test environment without proper SearchEngineClient
            // The important thing is that the method exists and accepts the correct parameters

                files.add(file);
            } catch (Exception e) {
                log.warn("Error creating SmbFile from cache for {}: {}", fileInfo.getName(), e.getMessage());
                // For testing purposes, continue processing other files
                // In a real scenario, you might want to handle this differently
            }
        }

        return files;
    }

    /**

import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import org.codelibs.core.lang.ClassUtil;
import org.codelibs.core.zip.ZipInputStreamUtil;

/**
 * Handler for traversing and processing classes.
 *
 * @author koichik
 * @see ClassHandler
 * @see TraversalUtil
 */
public abstract class ClassTraversalUtil {

    /**
     * Do not instantiate.
     */