public class HoodieJavaEngineContext
extends org.apache.hudi.common.engine.HoodieEngineContext
| Constructor and Description |
|---|
HoodieJavaEngineContext(org.apache.hadoop.conf.Configuration conf) |
HoodieJavaEngineContext(org.apache.hadoop.conf.Configuration conf,
org.apache.hudi.common.engine.TaskContextSupplier taskContextSupplier) |
| Modifier and Type | Method and Description |
|---|---|
<T> org.apache.hudi.common.data.HoodieData<T> |
emptyHoodieData() |
<I,O> List<O> |
flatMap(List<I> data,
org.apache.hudi.common.function.SerializableFunction<I,Stream<O>> func,
int parallelism) |
<I> void |
foreach(List<I> data,
org.apache.hudi.common.function.SerializableConsumer<I> consumer,
int parallelism) |
org.apache.hudi.common.util.Option<String> |
getProperty(org.apache.hudi.common.engine.EngineProperty key) |
<I,O> List<O> |
map(List<I> data,
org.apache.hudi.common.function.SerializableFunction<I,O> func,
int parallelism) |
<I,K,V> Stream<org.apache.hudi.common.util.collection.ImmutablePair<K,V>> |
mapPartitionsToPairAndReduceByKey(Stream<I> data,
org.apache.hudi.common.function.SerializablePairFlatMapFunction<Iterator<I>,K,V> flatMapToPairFunc,
org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc,
int parallelism) |
<I,K,V> Map<K,V> |
mapToPair(List<I> data,
org.apache.hudi.common.function.SerializablePairFunction<I,K,V> func,
Integer parallelism) |
<I,K,V> List<V> |
mapToPairAndReduceByKey(List<I> data,
org.apache.hudi.common.function.SerializablePairFunction<I,K,V> mapToPairFunc,
org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc,
int parallelism) |
org.apache.hudi.common.data.HoodieAccumulator |
newAccumulator() |
<T> org.apache.hudi.common.data.HoodieData<T> |
parallelize(List<T> data,
int parallelism) |
<I,K,V> List<V> |
reduceByKey(List<org.apache.hudi.common.util.collection.Pair<K,V>> data,
org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc,
int parallelism) |
void |
setJobStatus(String activeModule,
String activityDescription) |
void |
setProperty(org.apache.hudi.common.engine.EngineProperty key,
String value) |
public HoodieJavaEngineContext(org.apache.hadoop.conf.Configuration conf)
public HoodieJavaEngineContext(org.apache.hadoop.conf.Configuration conf,
org.apache.hudi.common.engine.TaskContextSupplier taskContextSupplier)
public org.apache.hudi.common.data.HoodieAccumulator newAccumulator()
newAccumulator in class org.apache.hudi.common.engine.HoodieEngineContextpublic <T> org.apache.hudi.common.data.HoodieData<T> emptyHoodieData()
emptyHoodieData in class org.apache.hudi.common.engine.HoodieEngineContextpublic <T> org.apache.hudi.common.data.HoodieData<T> parallelize(List<T> data, int parallelism)
parallelize in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,O> List<O> map(List<I> data, org.apache.hudi.common.function.SerializableFunction<I,O> func, int parallelism)
map in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,K,V> List<V> mapToPairAndReduceByKey(List<I> data, org.apache.hudi.common.function.SerializablePairFunction<I,K,V> mapToPairFunc, org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc, int parallelism)
mapToPairAndReduceByKey in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,K,V> Stream<org.apache.hudi.common.util.collection.ImmutablePair<K,V>> mapPartitionsToPairAndReduceByKey(Stream<I> data, org.apache.hudi.common.function.SerializablePairFlatMapFunction<Iterator<I>,K,V> flatMapToPairFunc, org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc, int parallelism)
mapPartitionsToPairAndReduceByKey in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,K,V> List<V> reduceByKey(List<org.apache.hudi.common.util.collection.Pair<K,V>> data, org.apache.hudi.common.function.SerializableBiFunction<V,V,V> reduceFunc, int parallelism)
reduceByKey in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,O> List<O> flatMap(List<I> data, org.apache.hudi.common.function.SerializableFunction<I,Stream<O>> func, int parallelism)
flatMap in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I> void foreach(List<I> data, org.apache.hudi.common.function.SerializableConsumer<I> consumer, int parallelism)
foreach in class org.apache.hudi.common.engine.HoodieEngineContextpublic <I,K,V> Map<K,V> mapToPair(List<I> data, org.apache.hudi.common.function.SerializablePairFunction<I,K,V> func, Integer parallelism)
mapToPair in class org.apache.hudi.common.engine.HoodieEngineContextpublic void setProperty(org.apache.hudi.common.engine.EngineProperty key,
String value)
setProperty in class org.apache.hudi.common.engine.HoodieEngineContextpublic org.apache.hudi.common.util.Option<String> getProperty(org.apache.hudi.common.engine.EngineProperty key)
getProperty in class org.apache.hudi.common.engine.HoodieEngineContextCopyright © 2023 The Apache Software Foundation. All rights reserved.