This project has retired. For details please refer to its Attic page.

Serialized Form

Package org.apache.crunch

Class org.apache.crunch.CombineFn extends DoFn<Pair<S,Iterable<T>>,Pair<S,T>> implements Serializable

Class org.apache.crunch.CrunchRuntimeException extends RuntimeException implements Serializable

Serialized Fields

logged

boolean logged

Class org.apache.crunch.DoFn extends Object implements Serializable

Class org.apache.crunch.FilterFn extends DoFn<T,T> implements Serializable

Class org.apache.crunch.GroupingOptions extends Object implements Serializable

Serialized Fields

partitionerClass

Class<T> partitionerClass

groupingComparatorClass

Class<T> groupingComparatorClass

sortComparatorClass

Class<T> sortComparatorClass

requireSortedKeys

boolean requireSortedKeys

numReducers

int numReducers

extraConf

Map<K,V> extraConf

Class org.apache.crunch.MapFn extends DoFn<S,T> implements Serializable

Class org.apache.crunch.Pair extends Object implements Serializable

Serialized Fields

first

Object first

second

Object second

Package org.apache.crunch.contrib.bloomfilter

Class org.apache.crunch.contrib.bloomfilter.BloomFilterFn extends DoFn<S,Pair<String,org.apache.hadoop.util.bloom.BloomFilter>> implements Serializable

Package org.apache.crunch.contrib.text

Class org.apache.crunch.contrib.text.AbstractCompositeExtractor extends Object implements Serializable

Serialized Fields

tokenizerFactory

TokenizerFactory tokenizerFactory

errors

int errors

errorOnLast

boolean errorOnLast

extractors

List<E> extractors

Class org.apache.crunch.contrib.text.AbstractSimpleExtractor extends Object implements Serializable

Serialized Fields

errors

int errors

errorOnLast

boolean errorOnLast

defaultValue

Object defaultValue

scannerFactory

TokenizerFactory scannerFactory

Class org.apache.crunch.contrib.text.TokenizerFactory extends Object implements Serializable

Serialized Fields

delim

String delim

skip

String skip

locale

Locale locale

indices

Set<E> indices

keep

boolean keep

Package org.apache.crunch.examples

Class org.apache.crunch.examples.AverageBytesByIP extends org.apache.hadoop.conf.Configured implements Serializable

Serialized Fields

calulateAverage

MapFn<S,T> calulateAverage

extractResponseSize

DoFn<S,T> extractResponseSize

Class org.apache.crunch.examples.SecondarySortExample extends org.apache.hadoop.conf.Configured implements Serializable

Class org.apache.crunch.examples.SortExample extends CrunchTool implements Serializable

Class org.apache.crunch.examples.TotalBytesByIP extends org.apache.hadoop.conf.Configured implements Serializable

Serialized Fields

extractIPResponseSize

DoFn<S,T> extractIPResponseSize

Class org.apache.crunch.examples.WordAggregationHBase extends org.apache.hadoop.conf.Configured implements Serializable

Serialized Fields

COLUMN_FAMILY_SOURCE

byte[] COLUMN_FAMILY_SOURCE

COLUMN_QUALIFIER_SOURCE_PLAY

byte[] COLUMN_QUALIFIER_SOURCE_PLAY

COLUMN_QUALIFIER_SOURCE_QUOTE

byte[] COLUMN_QUALIFIER_SOURCE_QUOTE

COLUMN_FAMILY_TARGET

byte[] COLUMN_FAMILY_TARGET

COLUMN_QUALIFIER_TARGET_TEXT

byte[] COLUMN_QUALIFIER_TARGET_TEXT

Class org.apache.crunch.examples.WordCount extends org.apache.hadoop.conf.Configured implements Serializable

Package org.apache.crunch.fn

Class org.apache.crunch.fn.Aggregators.SimpleAggregator extends Object implements Serializable

Class org.apache.crunch.fn.CompositeMapFn extends MapFn<R,T> implements Serializable

Serialized Fields

first

MapFn<S,T> first

second

MapFn<S,T> second

Class org.apache.crunch.fn.ExtractKeyFn extends MapFn<V,Pair<K,V>> implements Serializable

Serialized Fields

mapFn

MapFn<S,T> mapFn

Class org.apache.crunch.fn.IdentityFn extends MapFn<T,T> implements Serializable

Class org.apache.crunch.fn.PairMapFn extends MapFn<Pair<K,V>,Pair<S,T>> implements Serializable

Serialized Fields

keys

MapFn<S,T> keys

values

MapFn<S,T> values

Package org.apache.crunch.impl.mr.run

Class org.apache.crunch.impl.mr.run.RTNode extends Object implements Serializable

Serialized Fields

nodeName

String nodeName

fn

DoFn<S,T> fn

outputPType

PType<T> outputPType

children

List<E> children

inputConverter

Converter<K,V,S,T> inputConverter

outputConverter

Converter<K,V,S,T> outputConverter

outputName

String outputName

Package org.apache.crunch.impl.spark

Class org.apache.crunch.impl.spark.ByteArray extends Object implements Serializable

Serialized Fields

value

byte[] value

Class org.apache.crunch.impl.spark.CounterAccumulatorParam extends Object implements Serializable

Class org.apache.crunch.impl.spark.IntByteArray extends ByteArray implements Serializable

Serialized Fields

partition

int partition

Class org.apache.crunch.impl.spark.SparkComparator extends Object implements Serializable

Serialized Fields

cmpClass

Class<T> cmpClass

options

GroupingOptions options

ptype

PGroupedTableType<K,V> ptype

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.SparkPartitioner extends org.apache.spark.Partitioner implements Serializable

Serialized Fields

numPartitions

int numPartitions

Class org.apache.crunch.impl.spark.SparkRuntimeContext extends Object implements Serializable

Serialized Fields

broadConf

org.apache.spark.broadcast.Broadcast<T> broadConf

counters

org.apache.spark.Accumulator<T> counters

Package org.apache.crunch.impl.spark.collect

Class org.apache.crunch.impl.spark.collect.ToByteArrayFunction extends org.apache.spark.api.java.function.PairFunction<scala.Tuple2<IntByteArray,List<byte[]>>,ByteArray,List<byte[]>> implements Serializable

Package org.apache.crunch.impl.spark.fn

Class org.apache.crunch.impl.spark.fn.CombineMapsideFunction extends org.apache.spark.api.java.function.PairFlatMapFunction<Iterator<scala.Tuple2<K,V>>,K,V> implements Serializable

Serialized Fields

combineFn

CombineFn<S,T> combineFn

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.FlatMapDoFn extends org.apache.spark.api.java.function.FlatMapFunction<Iterator<S>,T> implements Serializable

Serialized Fields

fn

DoFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.FlatMapPairDoFn extends org.apache.spark.api.java.function.FlatMapFunction<Iterator<scala.Tuple2<K,V>>,T> implements Serializable

Serialized Fields

fn

DoFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.InputConverterFunction extends org.apache.spark.api.java.function.Function<scala.Tuple2<K,V>,S> implements Serializable

Serialized Fields

converter

Converter<K,V,S,T> converter

Class org.apache.crunch.impl.spark.fn.MapFunction extends org.apache.spark.api.java.function.Function<Object,Object> implements Serializable

Serialized Fields

fn

MapFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

initialized

boolean initialized

Class org.apache.crunch.impl.spark.fn.MapOutputFunction extends org.apache.spark.api.java.function.PairFunction<Pair<K,V>,ByteArray,byte[]> implements Serializable

Serialized Fields

keySerde

SerDe<T> keySerde

valueSerde

SerDe<T> valueSerde

Class org.apache.crunch.impl.spark.fn.OutputConverterFunction extends org.apache.spark.api.java.function.PairFunction<S,K,V> implements Serializable

Serialized Fields

converter

Converter<K,V,S,T> converter

Class org.apache.crunch.impl.spark.fn.PairFlatMapDoFn extends org.apache.spark.api.java.function.PairFlatMapFunction<Iterator<T>,K,V> implements Serializable

Serialized Fields

fn

DoFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.PairFlatMapPairDoFn extends org.apache.spark.api.java.function.PairFlatMapFunction<Iterator<scala.Tuple2<K,V>>,K2,V2> implements Serializable

Serialized Fields

fn

DoFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.PairMapFunction extends org.apache.spark.api.java.function.Function<scala.Tuple2<K,V>,S> implements Serializable

Serialized Fields

fn

MapFn<S,T> fn

ctxt

SparkRuntimeContext ctxt

initialized

boolean initialized

Class org.apache.crunch.impl.spark.fn.PairMapIterableFunction extends org.apache.spark.api.java.function.PairFunction<Pair<K,List<V>>,S,Iterable<T>> implements Serializable

Serialized Fields

fn

MapFn<S,T> fn

runtimeContext

SparkRuntimeContext runtimeContext

initialized

boolean initialized

Class org.apache.crunch.impl.spark.fn.PartitionedMapOutputFunction extends org.apache.spark.api.java.function.PairFunction<Pair<K,V>,IntByteArray,byte[]> implements Serializable

Serialized Fields

keySerde

SerDe<T> keySerde

valueSerde

SerDe<T> valueSerde

ptype

PGroupedTableType<K,V> ptype

partitionerClass

Class<T> partitionerClass

numPartitions

int numPartitions

runtimeContext

SparkRuntimeContext runtimeContext

Class org.apache.crunch.impl.spark.fn.ReduceGroupingFunction extends org.apache.spark.api.java.function.PairFlatMapFunction<Iterator<scala.Tuple2<ByteArray,List<byte[]>>>,ByteArray,List<byte[]>> implements Serializable

Serialized Fields

options

GroupingOptions options

ptype

PGroupedTableType<K,V> ptype

ctxt

SparkRuntimeContext ctxt

Class org.apache.crunch.impl.spark.fn.ReduceInputFunction extends org.apache.spark.api.java.function.Function<scala.Tuple2<ByteArray,List<byte[]>>,Pair<K,List<V>>> implements Serializable

Serialized Fields

keySerDe

SerDe<T> keySerDe

valueSerDe

SerDe<T> valueSerDe

Package org.apache.crunch.impl.spark.serde

Class org.apache.crunch.impl.spark.serde.AvroSerDe extends Object implements Serializable

Serialized Fields

avroType

AvroType<T> avroType

Class org.apache.crunch.impl.spark.serde.WritableSerDe extends Object implements Serializable

Serialized Fields

clazz

Class<T> clazz

Package org.apache.crunch.io

Class org.apache.crunch.io.FormatBundle extends Object implements Serializable

Serialized Fields

formatClass

Class<T> formatClass

extraConf

Map<K,V> extraConf

conf

org.apache.hadoop.conf.Configuration conf

Package org.apache.crunch.io.avro

Class org.apache.crunch.io.avro.AvroReadableData extends ReadableDataImpl<T> implements Serializable

Serialized Fields

avroType

AvroType<T> avroType

Package org.apache.crunch.io.avro.trevni

Class org.apache.crunch.io.avro.trevni.TrevniReadableData extends ReadableDataImpl<T> implements Serializable

Serialized Fields

avroType

AvroType<T> avroType

Package org.apache.crunch.io.hbase

Class org.apache.crunch.io.hbase.HBaseData extends Object implements Serializable

Serialized Fields

table

String table

scanAsString

String scanAsString

Class org.apache.crunch.io.hbase.HBaseValueConverter extends Object implements Serializable

Serialized Fields

serializationClass

Class<T> serializationClass

Class org.apache.crunch.io.hbase.HFileReadableData extends ReadableDataImpl<org.apache.hadoop.hbase.KeyValue> implements Serializable

Package org.apache.crunch.io.impl

Class org.apache.crunch.io.impl.ReadableDataImpl extends Object implements Serializable

Serialized Fields

paths

List<E> paths

Package org.apache.crunch.io.parquet

Class org.apache.crunch.io.parquet.AvroParquetReadableData extends ReadableDataImpl<T> implements Serializable

Serialized Fields

avroType

AvroType<T> avroType

Package org.apache.crunch.io.seq

Class org.apache.crunch.io.seq.SeqFileReadableData extends ReadableDataImpl implements Serializable

Serialized Fields

ptype

PType<T> ptype

Package org.apache.crunch.io.text

Class org.apache.crunch.io.text.TextReadableData extends ReadableDataImpl<T> implements Serializable

Serialized Fields

ptype

PType<T> ptype

sep

String sep

Package org.apache.crunch.lib

Class org.apache.crunch.lib.Aggregate.TopKCombineFn extends CombineFn<Integer,Pair<K,V>> implements Serializable

Serialized Fields

limit

int limit

maximize

boolean maximize

Class org.apache.crunch.lib.Aggregate.TopKFn extends DoFn<Pair<K,V>,Pair<Integer,Pair<K,V>>> implements Serializable

Serialized Fields

limit

int limit

maximize

boolean maximize

Package org.apache.crunch.lib.join

Class org.apache.crunch.lib.join.BloomFilterJoinStrategy extends Object implements Serializable

Serialized Fields

vectorSize

int vectorSize

nbHash

int nbHash

delegateJoinStrategy

JoinStrategy<K,U,V> delegateJoinStrategy

Class org.apache.crunch.lib.join.DefaultJoinStrategy extends Object implements Serializable

Serialized Fields

numReducers

int numReducers

Class org.apache.crunch.lib.join.FullOuterJoinFn extends JoinFn<K,U,V> implements Serializable

Class org.apache.crunch.lib.join.InnerJoinFn extends JoinFn<K,U,V> implements Serializable

Class org.apache.crunch.lib.join.JoinFn extends DoFn<Pair<Pair<K,Integer>,Iterable<Pair<U,V>>>,Pair<K,Pair<U,V>>> implements Serializable

Serialized Fields

keyType

PType<T> keyType

leftValueType

PType<T> leftValueType

Class org.apache.crunch.lib.join.LeftOuterJoinFn extends JoinFn<K,U,V> implements Serializable

Class org.apache.crunch.lib.join.MapsideJoinStrategy extends Object implements Serializable

Serialized Fields

materialize

boolean materialize

Class org.apache.crunch.lib.join.RightOuterJoinFn extends JoinFn<K,U,V> implements Serializable

Class org.apache.crunch.lib.join.ShardedJoinStrategy extends Object implements Serializable

Serialized Fields

wrappedJoinStrategy

JoinStrategy<K,U,V> wrappedJoinStrategy

shardingStrategy

ShardedJoinStrategy.ShardingStrategy<K> shardingStrategy

Package org.apache.crunch.lib.sort

Class org.apache.crunch.lib.sort.SortFns.AvroGenericFn extends MapFn<V extends Tuple,org.apache.avro.generic.GenericRecord> implements Serializable

Serialized Fields

indices

int[] indices

schemaJson

String schemaJson

Class org.apache.crunch.lib.sort.SortFns.SingleKeyFn extends MapFn<V extends Tuple,K> implements Serializable

Serialized Fields

index

int index

Class org.apache.crunch.lib.sort.SortFns.TupleKeyFn extends MapFn<V extends Tuple,K extends Tuple> implements Serializable

Serialized Fields

indices

int[] indices

tupleFactory

TupleFactory<T extends Tuple> tupleFactory

Package org.apache.crunch.types

Class org.apache.crunch.types.CollectionDeepCopier extends Object implements Serializable

Serialized Fields

elementType

PType<T> elementType

Class org.apache.crunch.types.DeepCopier.NoOpDeepCopier extends Object implements Serializable

Class org.apache.crunch.types.MapDeepCopier extends Object implements Serializable

Serialized Fields

ptype

PType<T> ptype

Class org.apache.crunch.types.PGroupedTableType extends Object implements Serializable

Serialized Fields

tableType

PTableType<K,V> tableType

Class org.apache.crunch.types.PGroupedTableType.PairIterableMapFn extends MapFn<Pair<Object,Iterable<Object>>,Pair<K,Iterable<V>>> implements Serializable

Serialized Fields

keys

MapFn<S,T> keys

values

MapFn<S,T> values

Class org.apache.crunch.types.TupleDeepCopier extends Object implements Serializable

Serialized Fields

tupleFactory

TupleFactory<T extends Tuple> tupleFactory

elementTypes

List<E> elementTypes

Class org.apache.crunch.types.TupleFactory extends Object implements Serializable

Package org.apache.crunch.types.avro

Class org.apache.crunch.types.avro.AvroDeepCopier.AvroGenericDeepCopier extends org.apache.crunch.types.avro.AvroDeepCopier<org.apache.avro.generic.GenericData.Record> implements Serializable

Class org.apache.crunch.types.avro.AvroDeepCopier.AvroReflectDeepCopier extends org.apache.crunch.types.avro.AvroDeepCopier<T> implements Serializable

Serialized Fields

valueClass

Class<T> valueClass

Class org.apache.crunch.types.avro.AvroDeepCopier.AvroSpecificDeepCopier extends org.apache.crunch.types.avro.AvroDeepCopier<T> implements Serializable

Serialized Fields

valueClass

Class<T> valueClass

Class org.apache.crunch.types.avro.AvroType extends Object implements Serializable

Serialized Fields

typeClass

Class<T> typeClass

schemaString

String schemaString

baseInputMapFn

MapFn<S,T> baseInputMapFn

baseOutputMapFn

MapFn<S,T> baseOutputMapFn

subTypes

List<E> subTypes

deepCopier

DeepCopier<T> deepCopier

initialized

boolean initialized

Package org.apache.crunch.types.writable

Class org.apache.crunch.types.writable.WritableDeepCopier extends Object implements Serializable

Serialized Fields

writableClass

Class<T> writableClass

Class org.apache.crunch.types.writable.WritableType extends Object implements Serializable

Serialized Fields

typeClass

Class<T> typeClass

writableClass

Class<T> writableClass

converter

Converter<K,V,S,T> converter

inputFn

MapFn<S,T> inputFn

outputFn

MapFn<S,T> outputFn

deepCopier

DeepCopier<T> deepCopier

subTypes

List<E> subTypes

initialized

boolean initialized

Package org.apache.crunch.util

Class org.apache.crunch.util.CrunchTool extends org.apache.hadoop.conf.Configured implements Serializable

Class org.apache.crunch.util.DelegatingReadableData extends Object implements Serializable

Serialized Fields

delegate

ReadableData<T> delegate

fn

DoFn<S,T> fn

Class org.apache.crunch.util.UnionReadableData extends Object implements Serializable

Serialized Fields

data

List<E> data