roffild.spark

Class MLPDataFileInputFormat

java.lang.Object

org.apache.hadoop.mapreduce.InputFormat<K,V>

org.apache.hadoop.mapreduce.lib.input.FileInputFormat<java.lang.String[],org.apache.spark.sql.Row>

roffild.spark.MLPDataFileInputFormat

Direct Known Subclasses:

MLPDataFileInputFormatVector

public class MLPDataFileInputFormat
extends org.apache.hadoop.mapreduce.lib.input.FileInputFormat<java.lang.String[],org.apache.spark.sql.Row>

Only for local files

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat

org.apache.hadoop.mapreduce.lib.input.FileInputFormat.Counter

Field Summary

Fields inherited from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat

DEFAULT_LIST_STATUS_NUM_THREADS, INPUT_DIR, INPUT_DIR_RECURSIVE, LIST_STATUS_NUM_THREADS, NUM_INPUT_FILES, PATHFILTER_CLASS, SPLIT_MAXSIZE, SPLIT_MINSIZE

Constructor Summary

Constructors

Constructor and Description
MLPDataFileInputFormat()

Method Summary

Modifier and Type	Method and Description
org.apache.hadoop.mapreduce.RecordReader<java.lang.String[],org.apache.spark.sql.Row>	createRecordReader(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext context)
java.util.List<org.apache.hadoop.mapreduce.InputSplit>	getSplits(org.apache.hadoop.mapreduce.JobContext job)
protected boolean	isSplitable(org.apache.hadoop.mapreduce.JobContext context, org.apache.hadoop.fs.Path filename)

Methods inherited from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat

addInputPath, addInputPathRecursively, addInputPaths, computeSplitSize, getBlockIndex, getFormatMinSplitSize, getInputDirRecursive, getInputPathFilter, getInputPaths, getMaxSplitSize, getMinSplitSize, listStatus, makeSplit, makeSplit, setInputDirRecursive, setInputPathFilter, setInputPaths, setInputPaths, setMaxInputSplitSize, setMinInputSplitSize

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

MLPDataFileInputFormat

public MLPDataFileInputFormat()

Method Detail

createRecordReader

public org.apache.hadoop.mapreduce.RecordReader<java.lang.String[],org.apache.spark.sql.Row> createRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
                                                                                                                org.apache.hadoop.mapreduce.TaskAttemptContext context)
                                                                                                         throws java.io.IOException,
                                                                                                                java.lang.InterruptedException

Specified by:

createRecordReader in class org.apache.hadoop.mapreduce.InputFormat<java.lang.String[],org.apache.spark.sql.Row>

Throws:

java.io.IOException

java.lang.InterruptedException

isSplitable

protected boolean isSplitable(org.apache.hadoop.mapreduce.JobContext context,
                              org.apache.hadoop.fs.Path filename)

Overrides:

isSplitable in class org.apache.hadoop.mapreduce.lib.input.FileInputFormat<java.lang.String[],org.apache.spark.sql.Row>

getSplits

public java.util.List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext job)
                                                                 throws java.io.IOException

Overrides:

getSplits in class org.apache.hadoop.mapreduce.lib.input.FileInputFormat<java.lang.String[],org.apache.spark.sql.Row>

Throws:

java.io.IOException