org.deeplearning4j.spark.data.loader.RemoteFileSource Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of dl4j-spark3_2.12 Show documentation

The newest version!

/*
 *  ******************************************************************************
 *  *
 *  *
 *  * 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.
 *  *
 *  *  See the NOTICE file distributed with this work for additional
 *  *  information regarding copyright ownership.
 *  * 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.deeplearning4j.spark.data.loader;

import lombok.AllArgsConstructor;
import lombok.Getter;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.nd4j.common.loader.Source;

import java.io.IOException;
import java.io.InputStream;

@AllArgsConstructor
public class RemoteFileSource implements Source {
    public static final int DEFAULT_BUFFER_SIZE = 4*1024*2014;
    @Getter
    private String path;
    private final FileSystem fileSystem;
    private final int bufferSize;

    public RemoteFileSource(String path, FileSystem fileSystem){
        this(path, fileSystem, DEFAULT_BUFFER_SIZE);
    }

    @Override
    public InputStream getInputStream() throws IOException {
        return fileSystem.open(new Path(path), bufferSize);
    }
}