org.apache.nifi.processors.standard

Class JoinEnrichment

java.lang.Object

org.apache.nifi.components.AbstractConfigurableComponent

org.apache.nifi.processor.AbstractSessionFactoryProcessor

org.apache.nifi.processor.util.bin.BinFiles

org.apache.nifi.processors.standard.JoinEnrichment

All Implemented Interfaces:

ConfigurableComponent, Processor

@TriggerWhenEmpty
 @SideEffectFree
 @Tags(value={"fork","join","enrichment","record","sql","wrap","recordpath","merge","combine","streams"})
 @CapabilityDescription(value="Joins together Records from two different FlowFiles where one FlowFile, the \'original\' contains arbitrary records and the second FlowFile, the \'enrichment\' contains additional data that should be used to enrich the first. See Additional Details for more information on how to configure this processor and the different use cases that it aims to accomplish.")
 @SeeAlso(value=ForkEnrichment.class)
 @WritesAttribute(attribute="mime.type",description="Sets the mime.type attribute to the MIME Type specified by the Record Writer") @WritesAttribute(attribute="record.count",description="The number of records in the FlowFile")
 @InputRequirement(value=INPUT_REQUIRED)
 @SystemResourceConsideration(resource=MEMORY,
                             description="This Processor will load into heap all FlowFiles that are on its incoming queues. While it loads the FlowFiles themselves, and not their content, the FlowFile attributes can be very memory intensive. Additionally, if the Join Strategy is set to SQL, the SQL engine may require buffering the entire contents of the enrichment FlowFile for each concurrent task. See Processor\'s Additional Details for more details and for steps on how to mitigate these concerns.")
public class JoinEnrichment
extends BinFiles

Field Summary

Fields

Modifier and Type	Field and Description
(package private) static PropertyDescriptor	DEFAULT_PRECISION
(package private) static PropertyDescriptor	DEFAULT_SCALE
(package private) static PropertyDescriptor	ENRICHMENT_RECORD_READER
(package private) static String	ENRICHMENT_ROLE_ATTRIBUTE
(package private) static String	GROUP_ID_ATTRIBUTE
(package private) static PropertyDescriptor	INSERTION_RECORD_PATH
(package private) static AllowableValue	JOIN_INSERT_ENRICHMENT_FIELDS
(package private) static AllowableValue	JOIN_SQL
(package private) static PropertyDescriptor	JOIN_STRATEGY
(package private) static AllowableValue	JOIN_WRAPPER
(package private) static PropertyDescriptor	MAX_BIN_COUNT
(package private) static PropertyDescriptor	ORIGINAL_RECORD_READER
private static List<PropertyDescriptor>	properties
(package private) static String	RECORD_COUNT_ATTRIBUTE
(package private) static PropertyDescriptor	RECORD_WRITER
(package private) static Relationship	REL_FAILURE
(package private) static Relationship	REL_JOINED
(package private) static Relationship	REL_ORIGINAL
(package private) static Relationship	REL_TIMEOUT
private static Set<Relationship>	relationships
(package private) static PropertyDescriptor	SQL
private SqlJoinCache	sqlJoinCache
(package private) static PropertyDescriptor	TIMEOUT

Fields inherited from class org.apache.nifi.processor.util.bin.BinFiles

MAX_BIN_AGE, MAX_ENTRIES, MAX_SIZE, MIN_ENTRIES, MIN_SIZE

Constructor Summary

Constructors

Constructor and Description
JoinEnrichment()

Method Summary

Modifier and Type	Method and Description
void	cleanup()
private EnrichmentRole	getEnrichmentRole(FlowFile flowFile)
private FlowFile	getFlowFileWithRole(Collection<FlowFile> flowFiles, EnrichmentRole desiredRole)
protected String	getGroupId(ProcessContext context, FlowFile flowFile, ProcessSession session)
private RecordJoinStrategy	getJoinStrategy(ProcessContext context, Map<String,String> attributes)
protected int	getMaxBinAgeSeconds(PropertyContext context)
protected long	getMaxBytes(PropertyContext context)
protected int	getMaxEntries(PropertyContext context)
protected long	getMinBytes(PropertyContext context)
protected int	getMinEntries(PropertyContext context)
private EnrichmentRole	getOtherEnrichmentRole(EnrichmentRole role)
private RecordSchema	getReaderSchema(RecordReaderFactory recordReaderFactory, FlowFile flowFile, ProcessSession session)
Set<Relationship>	getRelationships()
protected List<PropertyDescriptor>	getSupportedPropertyDescriptors()
protected FlowFile	preprocessFlowFile(ProcessContext context, ProcessSession session, FlowFile flowFile)
protected BinProcessingResult	processBin(Bin unmodifiableBin, ProcessContext context)
protected int	processBins(ProcessContext context, ProcessSessionFactory sessionFactory)
void	registerCalciteDriver()
protected void	setUpBinManager(BinManager binManager, ProcessContext context)
private BinProcessingResult	transferFailure(List<FlowFile> flowFiles, ProcessSession session)

Methods inherited from class org.apache.nifi.processor.util.bin.BinFiles

additionalCustomValidation, customValidate, getReadyBins, onScheduled, onTrigger, resetState

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

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

GROUP_ID_ATTRIBUTE

static final String GROUP_ID_ATTRIBUTE

See Also:

Constant Field Values

ENRICHMENT_ROLE_ATTRIBUTE

static final String ENRICHMENT_ROLE_ATTRIBUTE

See Also:

Constant Field Values

RECORD_COUNT_ATTRIBUTE

static final String RECORD_COUNT_ATTRIBUTE

See Also:

Constant Field Values

JOIN_WRAPPER

static final AllowableValue JOIN_WRAPPER

JOIN_SQL

static final AllowableValue JOIN_SQL

JOIN_INSERT_ENRICHMENT_FIELDS

static final AllowableValue JOIN_INSERT_ENRICHMENT_FIELDS

ORIGINAL_RECORD_READER

static final PropertyDescriptor ORIGINAL_RECORD_READER

ENRICHMENT_RECORD_READER

static final PropertyDescriptor ENRICHMENT_RECORD_READER

RECORD_WRITER

static final PropertyDescriptor RECORD_WRITER

JOIN_STRATEGY

static final PropertyDescriptor JOIN_STRATEGY

SQL

static final PropertyDescriptor SQL

DEFAULT_PRECISION

static final PropertyDescriptor DEFAULT_PRECISION

DEFAULT_SCALE

static final PropertyDescriptor DEFAULT_SCALE

INSERTION_RECORD_PATH

static final PropertyDescriptor INSERTION_RECORD_PATH

TIMEOUT

static final PropertyDescriptor TIMEOUT

MAX_BIN_COUNT

static final PropertyDescriptor MAX_BIN_COUNT

properties

private static final List<PropertyDescriptor> properties

REL_JOINED

static final Relationship REL_JOINED

REL_ORIGINAL

static final Relationship REL_ORIGINAL

REL_TIMEOUT

static final Relationship REL_TIMEOUT

REL_FAILURE

static final Relationship REL_FAILURE

relationships

private static final Set<Relationship> relationships

sqlJoinCache

private final SqlJoinCache sqlJoinCache

Constructor Detail

JoinEnrichment

public JoinEnrichment()

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

registerCalciteDriver

@OnScheduled
public void registerCalciteDriver()

cleanup

@OnStopped
public void cleanup()
                        throws Exception

Throws:

Exception

preprocessFlowFile

protected FlowFile preprocessFlowFile(ProcessContext context,
                                      ProcessSession session,
                                      FlowFile flowFile)

Specified by:

preprocessFlowFile in class BinFiles

getGroupId

protected String getGroupId(ProcessContext context,
                            FlowFile flowFile,
                            ProcessSession session)

Specified by:

getGroupId in class BinFiles

setUpBinManager

protected void setUpBinManager(BinManager binManager,
                               ProcessContext context)

Specified by:

setUpBinManager in class BinFiles

getMinEntries

protected int getMinEntries(PropertyContext context)

Overrides:

getMinEntries in class BinFiles

getMaxEntries

protected int getMaxEntries(PropertyContext context)

Overrides:

getMaxEntries in class BinFiles

getMinBytes

protected long getMinBytes(PropertyContext context)

Overrides:

getMinBytes in class BinFiles

getMaxBytes

protected long getMaxBytes(PropertyContext context)

Overrides:

getMaxBytes in class BinFiles

getMaxBinAgeSeconds

protected int getMaxBinAgeSeconds(PropertyContext context)

Overrides:

getMaxBinAgeSeconds in class BinFiles

processBin

protected BinProcessingResult processBin(Bin unmodifiableBin,
                                         ProcessContext context)
                                  throws ProcessException

Specified by:

processBin in class BinFiles

Throws:

ProcessException

getReaderSchema

private RecordSchema getReaderSchema(RecordReaderFactory recordReaderFactory,
                                     FlowFile flowFile,
                                     ProcessSession session)
                              throws IOException,
                                     MalformedRecordException,
                                     SchemaNotFoundException

Throws:

IOException

MalformedRecordException

SchemaNotFoundException

transferFailure

private BinProcessingResult transferFailure(List<FlowFile> flowFiles,
                                            ProcessSession session)

getJoinStrategy

private RecordJoinStrategy getJoinStrategy(ProcessContext context,
                                           Map<String,String> attributes)

getFlowFileWithRole

private FlowFile getFlowFileWithRole(Collection<FlowFile> flowFiles,
                                     EnrichmentRole desiredRole)

getEnrichmentRole

private EnrichmentRole getEnrichmentRole(FlowFile flowFile)

getOtherEnrichmentRole

private EnrichmentRole getOtherEnrichmentRole(EnrichmentRole role)

processBins

protected int processBins(ProcessContext context,
                          ProcessSessionFactory sessionFactory)

Overrides:

processBins in class BinFiles