com.amazonaws.services.s3.iterable.S3Objects Maven / Gradle / Ivy
Show all versions of aws-java-sdk Show documentation
/*
* Copyright 2012-2014 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License").
* You may not use this file except in compliance with the License.
* A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file 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 com.amazonaws.services.s3.iterable;
import java.util.Iterator;
import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.model.ListObjectsRequest;
import com.amazonaws.services.s3.model.ObjectListing;
import com.amazonaws.services.s3.model.S3ObjectSummary;
/**
* Provides an easy way to iterate Amazon S3 objects in a "foreach" statement.
* For example:
*
*
* for ( S3ObjectSummary summary : S3Objects.withPrefix(s3, "my-bucket", "photos/") ) {
* System.out.printf("Object with key '%s'\n", summary.getKey());
* }
*
*
* The list of {@link S3ObjectSummary}s will be fetched lazily, a page at a
* time, as they are needed. The size of the page can be controlled with the
* {@link S3Objects#withBatchSize(int)} method.
*/
public class S3Objects implements Iterable {
private AmazonS3 s3;
private String prefix = null;
private String bucketName;
private Integer batchSize = null;
private S3Objects(AmazonS3 s3, String bucketName) {
this.s3 = s3;
this.bucketName = bucketName;
}
/**
* Constructs an iterable that covers all the objects in an Amazon S3
* bucket.
*
* @param s3
* The Amazon S3 client.
* @param bucketName
* The bucket name.
* @return An iterator for object summaries.
*/
public static S3Objects inBucket(AmazonS3 s3, String bucketName) {
return new S3Objects(s3, bucketName);
}
/**
* Constructs an iterable that covers the objects in an Amazon S3 bucket
* where the key begins with the given prefix.
*
* @param s3
* The Amazon S3 client.
* @param bucketName
* The bucket name.
* @param prefix
* The prefix.
* @return An iterator for object summaries.
*/
public static S3Objects withPrefix(AmazonS3 s3, String bucketName, String prefix) {
S3Objects objects = new S3Objects(s3, bucketName);
objects.prefix = prefix;
return objects;
}
/**
* Sets the batch size, i.e., how many {@link S3ObjectSummary}s will be
* fetched at once.
*
* @param batchSize
* How many object summaries to fetch at once.
*/
public S3Objects withBatchSize(int batchSize) {
this.batchSize = batchSize;
return this;
}
public Integer getBatchSize() {
return batchSize;
}
public String getPrefix() {
return prefix;
}
public String getBucketName() {
return bucketName;
}
public AmazonS3 getS3() {
return s3;
}
private class S3ObjectIterator implements Iterator {
private ObjectListing currentListing = null;
private Iterator currentIterator = null;
@Override
public boolean hasNext() {
prepareCurrentListing();
return currentIterator.hasNext();
}
@Override
public S3ObjectSummary next() {
prepareCurrentListing();
return currentIterator.next();
}
@Override
public void remove() {
throw new UnsupportedOperationException();
}
private void prepareCurrentListing() {
while ( currentListing == null || (!currentIterator.hasNext() && currentListing.isTruncated()) ) {
if ( currentListing == null ) {
ListObjectsRequest req = new ListObjectsRequest();
req.setBucketName(getBucketName());
req.setPrefix(getPrefix());
req.setMaxKeys(getBatchSize());
currentListing = getS3().listObjects(req);
} else {
currentListing = getS3().listNextBatchOfObjects(currentListing);
}
currentIterator = currentListing.getObjectSummaries().iterator();
}
}
}
@Override
public Iterator iterator() {
return new S3ObjectIterator();
}
}