io.druid.segment.incremental

Class IncrementalIndex<AggregatorType>

java.lang.Object

io.druid.segment.incremental.IncrementalIndex<AggregatorType>

All Implemented Interfaces:

Closeable, AutoCloseable, Iterable<Row>

Direct Known Subclasses:

OffheapIncrementalIndex, OnheapIncrementalIndex

public abstract class IncrementalIndex<AggregatorType>
extends Object
implements Iterable<Row>, Closeable

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	IncrementalIndex.DimensionDesc
static class	IncrementalIndex.FactsEntry
static class	IncrementalIndex.MetricDesc
static class	IncrementalIndex.TimeAndDims

Constructor Summary

Constructors

Constructor and Description
IncrementalIndex(IncrementalIndexSchema incrementalIndexSchema, boolean deserializeComplexMetrics, boolean reportParseExceptions) Setting deserializeComplexMetrics to false is necessary for intermediate aggregation such as groupBy that should not deserialize input columns using ComplexMetricSerde for aggregators that return complex metrics.

Method Summary

Modifier and Type	Method and Description
int	add(InputRow row) Adds a new row.
protected abstract Integer	addToFacts(AggregatorFactory[] metrics, boolean deserializeComplexMetrics, boolean reportParseExceptions, InputRow row, AtomicInteger numEntries, IncrementalIndex.TimeAndDims key, ThreadLocal<InputRow> rowContainer, com.google.common.base.Supplier<InputRow> rowSupplier)
abstract boolean	canAppendRow()
void	close()
protected Comparator<IncrementalIndex.TimeAndDims>	dimsComparator()
InputRow	formatRow(InputRow row)
AggregatorType[]	getAggs()
protected abstract AggregatorType[]	getAggsForRow(int rowOffset)
protected abstract Object	getAggVal(AggregatorType agg, int rowOffset, int aggPosition)
ColumnCapabilities	getCapabilities(String column)
Map<String,ColumnCapabilitiesImpl>	getColumnCapabilities()
IncrementalIndex.DimensionDesc	getDimension(String dimension)
Map<String,DimensionHandler>	getDimensionHandlers()
Integer	getDimensionIndex(String dimension)
List<String>	getDimensionNames()
List<String>	getDimensionOrder()
List<IncrementalIndex.DimensionDesc>	getDimensions()
abstract io.druid.segment.incremental.IncrementalIndex.FactsHolder	getFacts()
org.joda.time.Interval	getInterval()
org.joda.time.DateTime	getMaxIngestedEventTime()
org.joda.time.DateTime	getMaxTime()
Metadata	getMetadata()
AggregatorFactory[]	getMetricAggs()
Class	getMetricClass(String metric)
protected abstract float	getMetricFloatValue(int rowOffset, int aggOffset)
Integer	getMetricIndex(String metricName)
protected abstract long	getMetricLongValue(int rowOffset, int aggOffset)
List<String>	getMetricNames()
protected abstract Object	getMetricObjectValue(int rowOffset, int aggOffset)
List<IncrementalIndex.MetricDesc>	getMetrics()
String	getMetricType(String metric)
org.joda.time.DateTime	getMinTime()
abstract String	getOutOfRowsReason()
protected abstract AggregatorType[]	initAggs(AggregatorFactory[] metrics, com.google.common.base.Supplier<InputRow> rowSupplier, boolean deserializeComplexMetrics)
boolean	isEmpty()
boolean	isRollup()
Iterable<Row>	iterableWithPostAggregations(List<PostAggregator> postAggs, boolean descending)
Iterator<Row>	iterator()
void	loadDimensionIterable(Iterable<String> oldDimensionOrder, Map<String,ColumnCapabilitiesImpl> oldColumnCapabilities)
protected ColumnSelectorFactory	makeColumnSelectorFactory(AggregatorFactory agg, com.google.common.base.Supplier<InputRow> in, boolean deserializeComplexMetrics)
static ColumnSelectorFactory	makeColumnSelectorFactory(VirtualColumns virtualColumns, AggregatorFactory agg, com.google.common.base.Supplier<InputRow> in, boolean deserializeComplexMetrics) Column selector used at ingestion time for inputs to aggregators.
int	size()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.lang.Iterable

forEach, spliterator

Constructor Detail

IncrementalIndex

public IncrementalIndex(IncrementalIndexSchema incrementalIndexSchema,
                        boolean deserializeComplexMetrics,
                        boolean reportParseExceptions)

Setting deserializeComplexMetrics to false is necessary for intermediate aggregation such as groupBy that should not deserialize input columns using ComplexMetricSerde for aggregators that return complex metrics.

Parameters:

incrementalIndexSchema - the schema to use for incremental index

deserializeComplexMetrics - flag whether or not to call ComplexMetricExtractor.extractValue() on the input value for aggregators that return metrics other than float.

reportParseExceptions - flag whether or not to report ParseExceptions that occur while extracting values from input rows

Method Detail

makeColumnSelectorFactory

public static ColumnSelectorFactory makeColumnSelectorFactory(VirtualColumns virtualColumns,
                                                              AggregatorFactory agg,
                                                              com.google.common.base.Supplier<InputRow> in,
                                                              boolean deserializeComplexMetrics)

Column selector used at ingestion time for inputs to aggregators.

Parameters:

agg - the aggregator

in - ingestion-time input row supplier

deserializeComplexMetrics - whether complex objects should be deserialized by a ComplexMetricExtractor

Returns:

column selector factory

isRollup

public boolean isRollup()

getFacts

public abstract io.druid.segment.incremental.IncrementalIndex.FactsHolder getFacts()

canAppendRow

public abstract boolean canAppendRow()

getOutOfRowsReason

public abstract String getOutOfRowsReason()

initAggs

protected abstract AggregatorType[] initAggs(AggregatorFactory[] metrics,
                                             com.google.common.base.Supplier<InputRow> rowSupplier,
                                             boolean deserializeComplexMetrics)

addToFacts

protected abstract Integer addToFacts(AggregatorFactory[] metrics,
                                      boolean deserializeComplexMetrics,
                                      boolean reportParseExceptions,
                                      InputRow row,
                                      AtomicInteger numEntries,
                                      IncrementalIndex.TimeAndDims key,
                                      ThreadLocal<InputRow> rowContainer,
                                      com.google.common.base.Supplier<InputRow> rowSupplier)
                               throws IndexSizeExceededException

Throws:

IndexSizeExceededException

getAggsForRow

protected abstract AggregatorType[] getAggsForRow(int rowOffset)

getAggVal

protected abstract Object getAggVal(AggregatorType agg,
                                    int rowOffset,
                                    int aggPosition)

getMetricFloatValue

protected abstract float getMetricFloatValue(int rowOffset,
                                             int aggOffset)

getMetricLongValue

protected abstract long getMetricLongValue(int rowOffset,
                                           int aggOffset)

getMetricObjectValue

protected abstract Object getMetricObjectValue(int rowOffset,
                                               int aggOffset)

close

public void close()

Specified by:

close in interface Closeable

Specified by:

close in interface AutoCloseable

formatRow

public InputRow formatRow(InputRow row)

getColumnCapabilities

public Map<String,ColumnCapabilitiesImpl> getColumnCapabilities()

add

public int add(InputRow row)
        throws IndexSizeExceededException

Adds a new row. The row might correspond with another row that already exists, in which case this will update that row instead of inserting a new one.

Calls to add() are thread safe.

Parameters:

row - the row of data to add

Returns:

the number of rows in the data set after adding the InputRow

Throws:

IndexSizeExceededException

isEmpty

public boolean isEmpty()

size

public int size()

getAggs

public AggregatorType[] getAggs()

getMetricAggs

public AggregatorFactory[] getMetricAggs()

getDimensionNames

public List<String> getDimensionNames()

getDimensions

public List<IncrementalIndex.DimensionDesc> getDimensions()

getDimension

public IncrementalIndex.DimensionDesc getDimension(String dimension)

getMetricType

public String getMetricType(String metric)

getMetricClass

public Class getMetricClass(String metric)

getInterval

public org.joda.time.Interval getInterval()

getMinTime

public org.joda.time.DateTime getMinTime()

getMaxTime

public org.joda.time.DateTime getMaxTime()

getDimensionIndex

public Integer getDimensionIndex(String dimension)

getDimensionOrder

public List<String> getDimensionOrder()

loadDimensionIterable

public void loadDimensionIterable(Iterable<String> oldDimensionOrder,
                                  Map<String,ColumnCapabilitiesImpl> oldColumnCapabilities)

getMetricNames

public List<String> getMetricNames()

getMetrics

public List<IncrementalIndex.MetricDesc> getMetrics()

getMetricIndex

public Integer getMetricIndex(String metricName)

getCapabilities

public ColumnCapabilities getCapabilities(String column)

getMetadata

public Metadata getMetadata()

getDimensionHandlers

public Map<String,DimensionHandler> getDimensionHandlers()

iterator

public Iterator<Row> iterator()

Specified by:

iterator in interface Iterable<Row>

iterableWithPostAggregations

public Iterable<Row> iterableWithPostAggregations(List<PostAggregator> postAggs,
                                                  boolean descending)

getMaxIngestedEventTime

public org.joda.time.DateTime getMaxIngestedEventTime()

makeColumnSelectorFactory

protected ColumnSelectorFactory makeColumnSelectorFactory(AggregatorFactory agg,
                                                          com.google.common.base.Supplier<InputRow> in,
                                                          boolean deserializeComplexMetrics)

dimsComparator

protected final Comparator<IncrementalIndex.TimeAndDims> dimsComparator()