1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
|
/*
* 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.input
import scala.collection.JavaConversions._
import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapreduce.InputSplit
import org.apache.hadoop.mapreduce.JobContext
import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat
import org.apache.hadoop.mapreduce.RecordReader
import org.apache.hadoop.mapreduce.TaskAttemptContext
/**
* A [[org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat CombineFileInputFormat]] for
* reading whole text files. Each file is read as key-value pair, where the key is the file path and
* the value is the entire content of file.
*/
private[spark] class WholeTextFileInputFormat
extends CombineFileInputFormat[String, String] with Configurable {
override protected def isSplitable(context: JobContext, file: Path): Boolean = false
override def createRecordReader(
split: InputSplit,
context: TaskAttemptContext): RecordReader[String, String] = {
val reader =
new ConfigurableCombineFileRecordReader(split, context, classOf[WholeTextFileRecordReader])
reader.setConf(getConf)
reader
}
/**
* Allow minPartitions set by end-user in order to keep compatibility with old Hadoop API,
* which is set through setMaxSplitSize
*/
def setMinPartitions(context: JobContext, minPartitions: Int) {
val files = listStatus(context)
val totalLen = files.map { file =>
if (file.isDir) 0L else file.getLen
}.sum
val maxSplitSize = Math.ceil(totalLen * 1.0 /
(if (minPartitions == 0) 1 else minPartitions)).toLong
super.setMaxSplitSize(maxSplitSize)
}
}
|