org.apache.nifi.processors.standard

Class DetectDuplicate

java.lang.Object

org.apache.nifi.components.AbstractConfigurableComponent

org.apache.nifi.processor.AbstractSessionFactoryProcessor

org.apache.nifi.processor.AbstractProcessor

org.apache.nifi.processors.standard.DetectDuplicate

All Implemented Interfaces:

ConfigurableComponent, Processor

@EventDriven
 @SupportsBatching(defaultDuration=TWENTY_FIVE_MILLIS)
 @Tags(value={"hash","dupe","duplicate","dedupe"})
 @InputRequirement(value=INPUT_REQUIRED)
 @CapabilityDescription(value="Caches a value, computed from FlowFile attributes, for each incoming FlowFile and determines if the cached value has already been seen. If so, routes the FlowFile to \'duplicate\' with an attribute named \'original.identifier\' that specifies the original FlowFile\'s \"description\", which is specified in the <FlowFile Description> property. If the FlowFile is not determined to be a duplicate, the Processor routes the FlowFile to \'non-duplicate\'")
 @WritesAttribute(attribute="original.flowfile.description",
                 description="All FlowFiles routed to the duplicate relationship will have an attribute added named original.flowfile.description. The value of this attribute is determined by the attributes of the original copy of the data and by the FlowFile Description property.")
 @SeeAlso(classNames={"org.apache.nifi.distributed.cache.client.DistributedMapCacheClientService","org.apache.nifi.distributed.cache.server.map.DistributedMapCacheServer"})
public class DetectDuplicate
extends AbstractProcessor

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
private static class	DetectDuplicate.CacheValue
private static class	DetectDuplicate.CacheValueDeserializer
private static class	DetectDuplicate.CacheValueSerializer
private static class	DetectDuplicate.StringSerializer

Field Summary

Fields

Modifier and Type	Field and Description
static PropertyDescriptor	AGE_OFF_DURATION
static PropertyDescriptor	CACHE_ENTRY_IDENTIFIER
static PropertyDescriptor	CACHE_IDENTIFIER
static PropertyDescriptor	DISTRIBUTED_CACHE_SERVICE
static PropertyDescriptor	FLOWFILE_DESCRIPTION
private Serializer<String>	keySerializer
static String	ORIGINAL_DESCRIPTION_ATTRIBUTE_NAME
static Relationship	REL_DUPLICATE
static Relationship	REL_FAILURE
static Relationship	REL_NON_DUPLICATE
private Set<Relationship>	relationships
private Deserializer<DetectDuplicate.CacheValue>	valueDeserializer
private Serializer<DetectDuplicate.CacheValue>	valueSerializer

Constructor Summary

Constructors

Constructor and Description
DetectDuplicate()

Method Summary

Modifier and Type	Method and Description
Set<Relationship>	getRelationships()
protected List<PropertyDescriptor>	getSupportedPropertyDescriptors()
void	onTrigger(ProcessContext context, ProcessSession session)

Methods inherited from class org.apache.nifi.processor.AbstractProcessor

onTrigger

Methods inherited from class org.apache.nifi.processor.AbstractSessionFactoryProcessor

getControllerServiceLookup, getIdentifier, getLogger, getNodeTypeProvider, init, initialize, isConfigurationRestored, isScheduled, toString, updateConfiguredRestoredTrue, updateScheduledFalse, updateScheduledTrue

Methods inherited from class org.apache.nifi.components.AbstractConfigurableComponent

customValidate, equals, getPropertyDescriptor, getPropertyDescriptors, getSupportedDynamicPropertyDescriptor, hashCode, onPropertyModified, validate

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.nifi.processor.Processor

isStateful

Methods inherited from interface org.apache.nifi.components.ConfigurableComponent

getPropertyDescriptor, getPropertyDescriptors, onPropertyModified, validate

Field Detail

ORIGINAL_DESCRIPTION_ATTRIBUTE_NAME

public static final String ORIGINAL_DESCRIPTION_ATTRIBUTE_NAME

See Also:

Constant Field Values

DISTRIBUTED_CACHE_SERVICE

public static final PropertyDescriptor DISTRIBUTED_CACHE_SERVICE

CACHE_ENTRY_IDENTIFIER

public static final PropertyDescriptor CACHE_ENTRY_IDENTIFIER

FLOWFILE_DESCRIPTION

public static final PropertyDescriptor FLOWFILE_DESCRIPTION

AGE_OFF_DURATION

public static final PropertyDescriptor AGE_OFF_DURATION

CACHE_IDENTIFIER

public static final PropertyDescriptor CACHE_IDENTIFIER

REL_DUPLICATE

public static final Relationship REL_DUPLICATE

REL_NON_DUPLICATE

public static final Relationship REL_NON_DUPLICATE

REL_FAILURE

public static final Relationship REL_FAILURE

relationships

private final Set<Relationship> relationships

keySerializer

private final Serializer<String> keySerializer

valueSerializer

private final Serializer<DetectDuplicate.CacheValue> valueSerializer

valueDeserializer

private final Deserializer<DetectDuplicate.CacheValue> valueDeserializer

Constructor Detail

DetectDuplicate

public DetectDuplicate()

Method Detail

getSupportedPropertyDescriptors

protected List<PropertyDescriptor> getSupportedPropertyDescriptors()

Overrides:

getSupportedPropertyDescriptors in class AbstractConfigurableComponent

getRelationships

public Set<Relationship> getRelationships()

Specified by:

getRelationships in interface Processor

Overrides:

getRelationships in class AbstractSessionFactoryProcessor

onTrigger

public void onTrigger(ProcessContext context,
                      ProcessSession session)
               throws ProcessException

Specified by:

onTrigger in class AbstractProcessor

Throws:

ProcessException