spark HadoopFileWholeTextReader 源码
spark HadoopFileWholeTextReader 代码
文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/HadoopFileWholeTextReader.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
import java.io.Closeable
import java.net.URI
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.io.Text
import org.apache.hadoop.mapreduce._
import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit
import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl
import org.apache.spark.input.WholeTextFileRecordReader
/**
* An adaptor from a [[PartitionedFile]] to an [[Iterator]] of [[Text]], which is all of the lines
* in that file.
*/
class HadoopFileWholeTextReader(file: PartitionedFile, conf: Configuration)
extends Iterator[Text] with Closeable {
private val _iterator = {
val fileSplit = new CombineFileSplit(
Array(new Path(new URI(file.filePath))),
Array(file.start),
Array(file.length),
// The locality is decided by `getPreferredLocations` in `FileScanRDD`.
Array.empty[String])
val attemptId = new TaskAttemptID(new TaskID(new JobID(), TaskType.MAP, 0), 0)
val hadoopAttemptContext = new TaskAttemptContextImpl(conf, attemptId)
val reader = new WholeTextFileRecordReader(fileSplit, hadoopAttemptContext, 0)
reader.setConf(hadoopAttemptContext.getConfiguration)
reader.initialize(fileSplit, hadoopAttemptContext)
new RecordReaderIterator(reader)
}
override def hasNext: Boolean = _iterator.hasNext
override def next(): Text = _iterator.next()
override def close(): Unit = _iterator.close()
}
相关信息
相关文章
spark AggregatePushDownUtils 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