org.apache.spark.sql.ForeachWriter.scala Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql
import org.apache.spark.annotation.InterfaceStability
/**
* A class to consume data generated by a `StreamingQuery`. Typically this is used to send the
* generated data to external systems. Each partition will use a new deserialized instance, so you
* usually should do all the initialization (e.g. opening a connection or initiating a transaction)
* in the `open` method.
*
* Scala example:
* {{{
* datasetOfString.writeStream.foreach(new ForeachWriter[String] {
*
* def open(partitionId: Long, version: Long): Boolean = {
* // open connection
* }
*
* def process(record: String) = {
* // write string to connection
* }
*
* def close(errorOrNull: Throwable): Unit = {
* // close the connection
* }
* })
* }}}
*
* Java example:
* {{{
* datasetOfString.writeStream().foreach(new ForeachWriter() {
*
* @Override
* public boolean open(long partitionId, long version) {
* // open connection
* }
*
* @Override
* public void process(String value) {
* // write string to connection
* }
*
* @Override
* public void close(Throwable errorOrNull) {
* // close the connection
* }
* });
* }}}
* @since 2.0.0
*/
@InterfaceStability.Evolving
abstract class ForeachWriter[T] extends Serializable {
// TODO: Move this to org.apache.spark.sql.util or consolidate this with batch API.
/**
* Called when starting to process one partition of new data in the executor. The `version` is
* for data deduplication when there are failures. When recovering from a failure, some data may
* be generated multiple times but they will always have the same version.
*
* If this method finds using the `partitionId` and `version` that this partition has already been
* processed, it can return `false` to skip the further data processing. However, `close` still
* will be called for cleaning up resources.
*
* @param partitionId the partition id.
* @param version a unique id for data deduplication.
* @return `true` if the corresponding partition and version id should be processed. `false`
* indicates the partition should be skipped.
*/
def open(partitionId: Long, version: Long): Boolean
/**
* Called to process the data in the executor side. This method will be called only when `open`
* returns `true`.
*/
def process(value: T): Unit
/**
* Called when stopping to process one partition of new data in the executor side. This is
* guaranteed to be called either `open` returns `true` or `false`. However,
* `close` won't be called in the following cases:
* - JVM crashes without throwing a `Throwable`
* - `open` throws a `Throwable`.
*
* @param errorOrNull the error thrown during processing data or null if there was no error.
*/
def close(errorOrNull: Throwable): Unit
}