Updated how the files are handled
All checks were successful
Locusworks Team/aws-s3-sync/pipeline/head This commit looks good

This commit is contained in:
2020-11-03 22:32:58 -06:00
parent 572c067b9d
commit 70f54ea2ee
3 changed files with 148 additions and 30 deletions

View File

@ -35,14 +35,11 @@ public class Entry {
logger.info("Starting S3 Sync");
try {
S3Client client = new S3Client(ConfigurationManager.getInstance());
try (S3Client client = new S3Client(ConfigurationManager.getInstance())) {
client.syncFolder();
} catch (Exception | Error e) {
logger.error(e);
System.exit(-1);
}
}
}

View File

@ -9,28 +9,42 @@ import java.nio.file.Paths;
import java.util.LinkedHashMap;
import java.util.Map;
import org.apache.commons.codec.digest.DigestUtils;
import org.apache.commons.lang3.StringUtils;
import com.amazonaws.services.s3.model.S3Object;
import net.locusworks.logger.ApplicationLogger;
import net.locusworks.logger.ApplicationLoggerFactory;
public class FileManager implements AutoCloseable {
private ApplicationLogger logger = ApplicationLoggerFactory.getLogger(FileManager.class);
public static final String FILE_CSV = "upload.csv";
private Map<String, FileDetail> detailMap;
private S3Client client;
private String bucket;
private static FileManager instance;
private FileManager() throws IOException {
private FileManager(S3Client client) throws IOException {
detailMap = new LinkedHashMap<String, FileDetail>();
this.client = client;
this.bucket = client.getBucket();
readFile();
}
private void readFile() throws IOException {
S3Object hashFile = client.getObject(bucket, FILE_CSV);
if (hashFile == null) return;
Path file = Paths.get(FILE_CSV);
if (Files.notExists(file)) return;
client.downloadFile(FILE_CSV, file);
if (Files.notExists(file)) return;
try(BufferedReader reader = Files.newBufferedReader(file)) {
String line = null;
while((line = reader.readLine()) != null) {
@ -39,13 +53,13 @@ public class FileManager implements AutoCloseable {
logger.warn("Invalid entry detected: " + line);
continue;
}
FileDetail fd = new FileDetail(values[0], values[1], Boolean.valueOf(values[2]));
detailMap.put(values[0], fd);
}
}
}
private void saveFile() throws IOException {
try(BufferedWriter writer = Files.newBufferedWriter(Paths.get(FILE_CSV))) {
writer.write("FILE_NAME,HASH,STATUS\n");
@ -54,16 +68,16 @@ public class FileManager implements AutoCloseable {
};
}
}
public boolean addEntry(String file, String hash, boolean uploaded) {
return addEntry(new FileDetail(file, hash, uploaded));
}
public boolean addEntry(FileDetail fd) {
return detailMap.put(fd.getFile(), fd) != null;
}
public FileDetail uploadFile(Path path) throws IOException {
public FileDetail getFileDetail(Path path) throws IOException {
boolean newFile = false;
String file = path.toString();
FileDetail fd = null;
@ -73,26 +87,33 @@ public class FileManager implements AutoCloseable {
newFile = true;
fd = new FileDetail(file, DigestUtils.sha1Hex(Files.newInputStream(path)), false);
}
String sha1 = newFile ? fd.getHash() : DigestUtils.sha1Hex(Files.newInputStream(path));
if (!sha1.equals(fd.getHash())) {
fd.setUploaded(false);
}
return fd;
}
@Override
public void close() throws Exception {
saveFile();
client.uploadFile(Paths.get(FILE_CSV));
Files.deleteIfExists(Paths.get(FILE_CSV));
}
public static FileManager newInstance(S3Client client) throws IOException {
instance = new FileManager(client);
return instance;
}
public static FileManager getInstance() throws IOException {
if (instance == null) {
instance = new FileManager();
if (instance == null || instance.client == null || StringUtils.isBlank(instance.bucket)) {
throw new IOException("a call to newInstance() was not made. Please call newInstance first");
}
return instance;
}
}

View File

@ -4,10 +4,16 @@ import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import com.amazonaws.AmazonClientException;
import com.amazonaws.AmazonServiceException;
import com.amazonaws.SdkClientException;
import com.amazonaws.regions.Regions;
import com.amazonaws.services.s3.AmazonS3;
import com.amazonaws.services.s3.AmazonS3ClientBuilder;
import com.amazonaws.services.s3.model.Bucket;
import com.amazonaws.services.s3.model.GetObjectRequest;
import com.amazonaws.services.s3.model.Permission;
import com.amazonaws.services.s3.model.S3Object;
import com.amazonaws.services.s3.transfer.Download;
import com.amazonaws.services.s3.transfer.TransferManager;
import com.amazonaws.services.s3.transfer.TransferManagerBuilder;
import com.amazonaws.services.s3.transfer.Upload;
@ -15,7 +21,7 @@ import net.locusworks.logger.ApplicationLogger;
import net.locusworks.logger.ApplicationLoggerFactory;
import net.locusworks.s3sync.conf.ConfigurationManager;
public class S3Client {
public class S3Client implements AutoCloseable {
private ApplicationLogger logger = ApplicationLoggerFactory.getLogger(S3Client.class);
@ -37,11 +43,15 @@ public class S3Client {
this.bucket = conf.getBucketName();
this.syncFolder = conf.getSyncFolder();
}
public String getBucket() {
return this.bucket;
}
public void uploadFile(Path file) {
TransferManager xferMgr = TransferManagerBuilder.standard().withS3Client(s3Client).build();
uploadFile(xferMgr, file);
xferMgr.shutdownNow();
xferMgr.shutdownNow(false);
}
public void uploadFile(TransferManager xferMgr, Path file) {
@ -49,7 +59,7 @@ public class S3Client {
xferMgr = !xferMgrNull ? xferMgr : TransferManagerBuilder.standard().withS3Client(s3Client).build();
FileDetail fd = null;
try {
fd = FileManager.getInstance().uploadFile(file);
fd = FileManager.getInstance().getFileDetail(file);
if (fd.isUploaded()) return;
logger.info("Uploading file: %s", file);
Upload xfer = xferMgr.upload(bucket, getPath(file), file.toFile());
@ -69,14 +79,37 @@ public class S3Client {
logger.error(e.getMessage());
} finally {
if (xferMgrNull) {
xferMgr.shutdownNow();
xferMgr.shutdownNow(false);
}
}
}
public void downloadFile(String key, Path file) {
TransferManager xferMgr = TransferManagerBuilder.standard().withS3Client(s3Client).build();
downloadFile(xferMgr, key, file);
xferMgr.shutdownNow(false);
}
public void downloadFile(TransferManager xferMgr, String key, Path file) {
boolean xferMgrNull = xferMgr == null;
xferMgr = !xferMgrNull ? xferMgr : TransferManagerBuilder.standard().withS3Client(s3Client).build();
try {
logger.info("Downloading file: %s", file);
Download xfer = xferMgr.download(bucket, key, file.toFile());
xfer.waitForCompletion();
logger.info("Done downloading %s", file);
} catch (AmazonClientException | InterruptedException e) {
logger.error(e.getMessage());
} finally {
if (xferMgrNull) {
xferMgr.shutdownNow(false);
}
}
}
public void syncFolder() throws IOException {
TransferManager xferMgr = TransferManagerBuilder.standard().withS3Client(s3Client).build();
try (FileManager manager = FileManager.getInstance()) {
try (FileManager manager = FileManager.newInstance(this)) {
Files.walk(syncFolder)
.filter(f -> Files.isRegularFile(f))
.forEach(f -> uploadFile(xferMgr, syncFolder.resolve(f)));
@ -84,7 +117,67 @@ public class S3Client {
logger.error("Unable to load file Manager: " + e.getMessage());
}
xferMgr.shutdownNow();
xferMgr.shutdownNow(false);
}
/**
* <p>
* Gets the object stored in Amazon S3 under the specified bucket and key.
* </p>
* <p>
* Be extremely careful when using this method; the returned Amazon S3
* object contains a direct stream of data from the HTTP connection. The
* underlying HTTP connection cannot be reused until the user finishes
* reading the data and closes the stream. Also note that if not all data
* is read from the stream then the SDK will abort the underlying connection,
* this may have a negative impact on performance. Therefore:
* </p>
* <ul>
* <li>Use the data from the input stream in Amazon S3 object as soon as possible</li>
* <li>Read all data from the stream (use {@link GetObjectRequest#setRange(long, long)} to request only the bytes you need)</li>
* <li>Close the input stream in Amazon S3 object as soon as possible</li>
* </ul>
* If these rules are not followed, the client can run out of resources by
* allocating too many open, but unused, HTTP connections. </p>
* <p>
* To get an object from Amazon S3, the caller must have
* {@link Permission#Read} access to the object.
* </p>
* <p>
* If the object fetched is publicly readable, it can also read it by
* pasting its URL into a browser.
* </p>
* <p>
* For more advanced options (such as downloading only a range of an
* object's content, or placing constraints on when the object should be
* downloaded) callers can use {@link #getObject(GetObjectRequest)}.
* </p>
* <p>
* If you are accessing <a href="http://aws.amazon.com/kms/">AWS
* KMS</a>-encrypted objects, you need to specify the correct region of the
* bucket on your client and configure AWS Signature Version 4 for added
* security. For more information on how to do this, see
* http://docs.aws.amazon.com/AmazonS3/latest/dev/UsingAWSSDK.html#
* specify-signature-version
* </p>
*
* @param bucketName
* The name of the bucket containing the desired object.
* @param key
* The key under which the desired object is stored.
*
* @return The object stored in Amazon S3 in the specified bucket and key.
*
* @throws SdkClientException
* If any errors are encountered in the client while making the
* request or handling the response.
*
*/
public S3Object getObject(String bucketName, String key) {
try {
return s3Client.getObject(bucketName, key);
} catch (AmazonServiceException ex) {}
return null;
}
private String getPath(Path file) {
@ -92,5 +185,12 @@ public class S3Client {
Path relative = syncFolder.relativize(file);
return relative.toString().replace("\\", "/");
}
@Override
public void close() throws Exception {
if (s3Client != null) {
s3Client.shutdown();
}
}
}