All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.deeplearning4j.aws.s3.uploader.S3Uploader Maven / Gradle / Ivy

There is a newer version: 1.0.0-beta_spark_2
Show newest version
/*******************************************************************************
 * 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.deeplearning4j.aws.s3.uploader;

import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.AmazonS3Client;
import com.amazonaws.services.s3.model.*;
import com.amazonaws.services.s3.transfer.MultipleFileUpload;
import com.amazonaws.services.s3.transfer.TransferManager;
import org.deeplearning4j.aws.s3.BaseS3;

import java.io.File;
import java.util.ArrayList;
import java.util.List;

/**
 * Uploads files to S3
 * 
 * @see {@link BaseS3}
 * @author Adam Gibson
 *
 */
public class S3Uploader extends BaseS3 {


    /**
     * Multi part upload for big files
     * @param file the file to upload
     * @param bucketName the bucket name to upload
     */
    public void multiPartUpload(File file, String bucketName) {
        AmazonS3 client = new AmazonS3Client(creds);
        bucketName = ensureValidBucketName(bucketName);

        List buckets = client.listBuckets();
        for (Bucket b : buckets)
            if (b.getName().equals(bucketName)) {
                doMultiPart(client, bucketName, file);
                return;
            }

        //bucket didn't exist: create it
        client.createBucket(bucketName);
        doMultiPart(client, bucketName, file);
    }

    /**
     * Upload the file to the bucket.
     * Will create the bucket if it hasn't already been created
     * @param file the file to upload
     * @param bucketName the name of the bucket
     */
    public void upload(File file, String bucketName) {
        AmazonS3 client = new AmazonS3Client(creds);
        bucketName = ensureValidBucketName(bucketName);

        List buckets = client.listBuckets();
        for (Bucket b : buckets)
            if (b.getName().equals(bucketName)) {
                client.putObject(bucketName, file.getName(), file);
                return;
            }

        //bucket didn't exist: create it
        client.createBucket(bucketName);
        client.putObject(bucketName, file.getName(), file);

    }

    private void doMultiPart(AmazonS3 s3Client, String bucketName, File file) {
        // Create a list of UploadPartResponse objects. You get one of these
        // for each part upload.
        List partETags = new ArrayList<>();

        // Step 1: Initialize.
        InitiateMultipartUploadRequest initRequest = new InitiateMultipartUploadRequest(bucketName, file.getName());
        InitiateMultipartUploadResult initResponse = s3Client.initiateMultipartUpload(initRequest);

        long contentLength = file.length();
        long partSize = 5242880; // Set part size to 5 MB.

        try {
            // Step 2: Upload parts.
            long filePosition = 0;
            for (int i = 1; filePosition < contentLength; i++) {
                // Last part can be less than 5 MB. Adjust part size.
                partSize = Math.min(partSize, (contentLength - filePosition));

                // Create request to upload a part.
                UploadPartRequest uploadRequest = new UploadPartRequest().withBucketName(bucketName)
                                .withKey(file.getName()).withUploadId(initResponse.getUploadId()).withPartNumber(i)
                                .withFileOffset(filePosition).withFile(file).withPartSize(partSize);

                // Upload part and add response to our list.
                partETags.add(s3Client.uploadPart(uploadRequest).getPartETag());

                filePosition += partSize;
            }

            // Step 3: Complete.
            CompleteMultipartUploadRequest compRequest = new CompleteMultipartUploadRequest(bucketName, file.getName(),
                            initResponse.getUploadId(), partETags);

            s3Client.completeMultipartUpload(compRequest);
        } catch (Exception e) {
            s3Client.abortMultipartUpload(
                            new AbortMultipartUploadRequest(bucketName, file.getName(), initResponse.getUploadId()));
        }
    }

    private String ensureValidBucketName(String bucketName) {
        String formatted = bucketName.replaceAll("\\s+", "_");
        int length = bucketName.length();
        if (length >= 62)
            length = 62;
        formatted = formatted.substring(0, length);
        formatted = formatted.replace(".", "d");
        formatted = formatted.toLowerCase();
        if (formatted.endsWith("-"))
            formatted = formatted.substring(0, length - 1);

        return formatted;
    }

    public void upload(File file, String name, String bucketName) {
        AmazonS3 client = getClient();
        bucketName = ensureValidBucketName(bucketName);
        List buckets = client.listBuckets();
        //	ObjectMetadata med = new ObjectMetadata();
        //		med.setContentLength(fileLength);
        for (Bucket b : buckets)
            if (b.getName().equals(bucketName)) {
                //client.putObject(bucketName, name, is, med);
                client.putObject(new PutObjectRequest(bucketName, name, file));
                return;
            }

        //bucket didn't exist: createComplex it
        client.createBucket(bucketName);
        //client.putObject(bucketName, name, is, med);
        client.putObject(new PutObjectRequest(bucketName, name, file));
    }


    public MultipleFileUpload uploadFolder(String bucketName, String keyPrefix, File folderPath,
                    boolean includeSubDir) {
        TransferManager transfer = new TransferManager(getClient());
        return transfer.uploadDirectory(bucketName, keyPrefix, folderPath, includeSubDir);
    }

    public MultipleFileUpload uploadFileList(String bucketName, File folderPath, List fileList,
                    String keyPrefix) {
        TransferManager transfer = new TransferManager(getClient());
        return transfer.uploadFileList(bucketName, keyPrefix, folderPath, fileList);
    }


}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy