[
https://issues.apache.org/jira/browse/BEAM-2500?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16270075#comment-16270075
]
ASF GitHub Bot commented on BEAM-2500:
--------------------------------------
jacobmarble commented on a change in pull request #4080: [BEAM-2500] Add S3
FileSystem to Java SDK
URL: https://github.com/apache/beam/pull/4080#discussion_r153687348
##########
File path:
sdks/java/io/amazon-web-services/src/main/java/org/apache/beam/sdk/io/aws/s3/S3FileSystem.java
##########
@@ -0,0 +1,599 @@
+/*
+ * 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.beam.sdk.io.aws.s3;
+
+import static com.google.common.base.Preconditions.checkArgument;
+import static com.google.common.base.Preconditions.checkNotNull;
+import static com.google.common.base.Preconditions.checkState;
+
+import com.amazonaws.AmazonClientException;
+import com.amazonaws.auth.AWSStaticCredentialsProvider;
+import com.amazonaws.auth.BasicAWSCredentials;
+import com.amazonaws.services.s3.AmazonS3;
+import com.amazonaws.services.s3.AmazonS3ClientBuilder;
+import com.amazonaws.services.s3.model.AmazonS3Exception;
+import com.amazonaws.services.s3.model.CompleteMultipartUploadRequest;
+import com.amazonaws.services.s3.model.CopyPartRequest;
+import com.amazonaws.services.s3.model.CopyPartResult;
+import com.amazonaws.services.s3.model.DeleteObjectsRequest;
+import com.amazonaws.services.s3.model.DeleteObjectsRequest.KeyVersion;
+import com.amazonaws.services.s3.model.InitiateMultipartUploadRequest;
+import com.amazonaws.services.s3.model.InitiateMultipartUploadResult;
+import com.amazonaws.services.s3.model.ListObjectsV2Request;
+import com.amazonaws.services.s3.model.ListObjectsV2Result;
+import com.amazonaws.services.s3.model.ObjectMetadata;
+import com.amazonaws.services.s3.model.PartETag;
+import com.amazonaws.services.s3.model.S3ObjectSummary;
+import com.google.common.annotations.VisibleForTesting;
+import com.google.common.base.Function;
+import com.google.common.base.Predicate;
+import com.google.common.base.Strings;
+import com.google.common.collect.ArrayListMultimap;
+import com.google.common.collect.FluentIterable;
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.Iterables;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Multimap;
+import com.google.common.util.concurrent.Futures;
+import com.google.common.util.concurrent.ListenableFuture;
+import com.google.common.util.concurrent.ListeningExecutorService;
+import com.google.common.util.concurrent.MoreExecutors;
+import java.io.FileNotFoundException;
+import java.io.IOException;
+import java.nio.channels.ReadableByteChannel;
+import java.nio.channels.WritableByteChannel;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Iterator;
+import java.util.List;
+import java.util.concurrent.Callable;
+import java.util.concurrent.ExecutionException;
+import java.util.concurrent.ExecutorService;
+import java.util.concurrent.Executors;
+import java.util.concurrent.Future;
+import java.util.regex.Pattern;
+import org.apache.beam.sdk.io.FileSystem;
+import org.apache.beam.sdk.io.aws.options.S3Options;
+import org.apache.beam.sdk.io.fs.CreateOptions;
+import org.apache.beam.sdk.io.fs.MatchResult;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+class S3FileSystem extends FileSystem<S3ResourceId> {
+
+ private static final Logger LOG =
LoggerFactory.getLogger(S3FileSystem.class);
+
+ // Amazon S3 API docs: Each part must be at least 5 MB in size, except the
last part.
+ private static final int MINIMUM_UPLOAD_BUFFER_SIZE_BYTES = 5 * 1024 * 1024;
+ private static final int DEFAULT_UPLOAD_BUFFER_SIZE_BYTES =
+ Runtime.getRuntime().maxMemory() < 512 * 1024 * 1024
+ ? MINIMUM_UPLOAD_BUFFER_SIZE_BYTES
+ : 64 * 1024 * 1024;
Review comment:
Done
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> Add support for S3 as a Apache Beam FileSystem
> ----------------------------------------------
>
> Key: BEAM-2500
> URL: https://issues.apache.org/jira/browse/BEAM-2500
> Project: Beam
> Issue Type: Improvement
> Components: sdk-java-extensions
> Reporter: Luke Cwik
> Assignee: Jacob Marble
> Priority: Minor
> Attachments: hadoop_fs_patch.patch
>
>
> Note that this is for providing direct integration with S3 as an Apache Beam
> FileSystem.
> There is already support for using the Hadoop S3 connector by depending on
> the Hadoop File System module[1], configuring HadoopFileSystemOptions[2] with
> a S3 configuration[3].
> 1: https://github.com/apache/beam/tree/master/sdks/java/io/hadoop-file-system
> 2:
> https://github.com/apache/beam/blob/master/sdks/java/io/hadoop-file-system/src/main/java/org/apache/beam/sdk/io/hdfs/HadoopFileSystemOptions.java#L53
> 3: https://wiki.apache.org/hadoop/AmazonS3
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
