45 lines
1.6 KiB
Java
45 lines
1.6 KiB
Java
|
/*******************************************************************************
|
||
|
|
* Copyright (c) 2015-2018 Skymind, Inc.
|
||
|
|
*
|
||
|
|
* This program and the accompanying materials are made available under the
|
||
|
|
* terms of the Apache License, Version 2.0 which is available at
|
||
|
|
* https://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.
|
||
|
|
*
|
||
|
|
* SPDX-License-Identifier: Apache-2.0
|
||
|
|
******************************************************************************/
|
||
|
|
|
||
|
|
package org.datavec.spark.functions;
|
||
|
|
|
||
|
|
import org.apache.spark.api.java.function.Function;
|
||
|
|
import org.datavec.api.records.reader.RecordReader;
|
||
|
|
import org.datavec.api.split.StringSplit;
|
||
|
|
import org.datavec.api.writable.Writable;
|
||
|
|
|
||
|
|
import java.util.List;
|
||
|
|
|
||
|
|
/**
|
||
|
|
* LineRecordReaderFunction: Used to map a {@code JavaRDD<String>} to a {@code JavaRDD<Collection<Writable>>}
|
||
|
|
* Note that this is most useful with LineRecordReader instances (CSVRecordReader, SVMLightRecordReader, etc)
|
||
|
|
*
|
||
|
|
* @author Alex Black
|
||
|
|
*/
|
||
|
|
public class LineRecordReaderFunction implements Function<String, List<Writable>> {
|
||
|
|
private final RecordReader recordReader;
|
||
|
|
|
||
|
|
public LineRecordReaderFunction(RecordReader recordReader) {
|
||
|
|
this.recordReader = recordReader;
|
||
|
|
}
|
||
|
|
|
||
|
|
@Override
|
||
|
|
public List<Writable> call(String s) throws Exception {
|
||
|
|
recordReader.initialize(new StringSplit(s));
|
||
|
|
return recordReader.next();
|
||
|
|
}
|
||
|
|
}
|