spark ParquetOutputWriter 源码
spark ParquetOutputWriter 代码
文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetOutputWriter.scala
/*
* 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.execution.datasources.parquet
import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapreduce._
import org.apache.parquet.hadoop.ParquetOutputFormat
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.execution.datasources.OutputWriter
// NOTE: This class is instantiated and used on executor side only, no need to be serializable.
class ParquetOutputWriter(val path: String, context: TaskAttemptContext)
extends OutputWriter {
private val recordWriter: RecordWriter[Void, InternalRow] = {
new ParquetOutputFormat[InternalRow]() {
override def getDefaultWorkFile(context: TaskAttemptContext, extension: String): Path = {
new Path(path)
}
}.getRecordWriter(context)
}
override def write(row: InternalRow): Unit = recordWriter.write(null, row)
override def close(): Unit = recordWriter.close(context)
}
相关信息
相关文章
spark ParquetRecordMaterializer 源码
0
赞
- 所属分类： 前端技术
- 本文标签：
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
8、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦