spark ParquetWrite 源码
spark ParquetWrite 代码
文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetWrite.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.v2.parquet
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.internal.Logging
import org.apache.spark.sql.connector.write.LogicalWriteInfo
import org.apache.spark.sql.execution.datasources.OutputWriterFactory
import org.apache.spark.sql.execution.datasources.parquet._
import org.apache.spark.sql.execution.datasources.v2.FileWrite
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._
case class ParquetWrite(
paths: Seq[String],
formatName: String,
supportsDataType: DataType => Boolean,
info: LogicalWriteInfo) extends FileWrite with Logging {
override def prepareWrite(
sqlConf: SQLConf,
job: Job,
options: Map[String, String],
dataSchema: StructType): OutputWriterFactory = {
val parquetOptions = new ParquetOptions(options, sqlConf)
ParquetUtils.prepareWrite(sqlConf, job, dataSchema, parquetOptions)
}
}
相关信息
相关文章
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
-
7、 openharmony
-
8、 golang
-
10、 Vue中input框自动聚焦