PR comments

Author: anmolanmol1234

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/contracts/services/AppendRequestParameters.java

@@ -81,7 +81,7 @@ public AppendRequestParameters(final long position,
    * @param leaseId leaseId of the blob to be appended
    * @param isExpectHeaderEnabled true if the expect header is enabled
    * @param blobParams parameters specific to append operation on Blob Endpoint.
-   *  @param md5  The Base64-encoded MD5 hash of the block for data integrity validation.
+   * @param md5  The Base64-encoded MD5 hash of the block for data integrity validation.
    */
   public AppendRequestParameters(final long position,
       final int offset,

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsBlobBlock.java

@@ -46,6 +46,8 @@ public class AbfsBlobBlock extends AbfsBlock {
    *
    * @param outputStream AbfsOutputStream Instance.
    * @param offset       Used to generate blockId based on offset.
+   * @param blockIdLength  the expected length of the generated block ID.
+   * @param blockIndex     the index of the block; used in block ID generation.
    * @throws IOException exception is thrown.
    */
   AbfsBlobBlock(AbfsOutputStream outputStream, long offset, int blockIdLength, long blockIndex) throws IOException {
@@ -57,16 +59,15 @@ public class AbfsBlobBlock extends AbfsBlock {
   }
 
   /**
-   * Generates a Base64-encoded block ID string based on the given position, stream ID, and desired raw length.
-   * The block ID is composed using the stream UUID and the block index, which is derived from
-   * the given position divided by the output stream's buffer size. The resulting string is
-   * optionally adjusted to match the specified raw length, padded or trimmed as needed, and
-   * then Base64-encoded.
+   * Generates a Base64-encoded block ID string using the given stream UUID and block index.
+   * The block ID is first created as a raw string using a format with the stream ID and block index.
+   * If a non-zero rawLength is provided, the raw block ID is padded or trimmed to match the length.
+   * The final string is then Base64-encoded and returned.
    *
-   * @param streamId   The UUID representing the stream, used as a prefix in the block ID.
-   * @param rawLength  The desired length of the raw block ID string before Base64 encoding.
-   *                   If 0, no length adjustment is made.
-   * @return A Base64-encoded block ID string suitable for use in block-based storage APIs.
+   * @param streamId   the UUID of the stream used to generate the block ID.
+   * @param rawLength  the desired length of the raw block ID string before encoding.
+   *                   If 0, no length adjustment is done.
+   * @return the Base64-encoded block ID string.
    */
   private String generateBlockId(UUID streamId, int rawLength) {
     String rawBlockId = String.format(BLOCK_ID_FORMAT, streamId, blockIndex);

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsBlobClient.java

@@ -984,7 +984,7 @@ public AbfsRestOperation appendBlock(final String path,
       requestHeaders.add(new AbfsHttpHeader(X_MS_LEASE_ID, requestParameters.getLeaseId()));
     }
     if (isChecksumValidationEnabled()) {
-    addCheckSumHeaderForWrite(requestHeaders, requestParameters);
+      addCheckSumHeaderForWrite(requestHeaders, requestParameters);
     }
     final AbfsUriQueryBuilder abfsUriQueryBuilder = createDefaultUriQueryBuilder();
     abfsUriQueryBuilder.addQuery(QUERY_PARAM_COMP, APPEND_BLOCK);
@@ -1025,6 +1025,7 @@ public AbfsRestOperation appendBlock(final String path,
    * @param leaseId if there is an active lease on the path.
    * @param contextEncryptionAdapter to provide encryption context.
    * @param tracingContext for tracing the server calls.
+   * @param blobMd5 the MD5 hash of the blob for integrity verification.
    * @return exception as this operation is not supported on Blob Endpoint.
    * @throws UnsupportedOperationException always.
    */
@@ -1053,6 +1054,7 @@ public AbfsRestOperation flush(final String path,
    * @param eTag The etag of the blob.
    * @param contextEncryptionAdapter to provide encryption context.
    * @param tracingContext for tracing the service call.
+   * @param blobMd5 the MD5 hash of the blob for integrity verification.
    * @return executed rest operation containing response from server.
    * @throws AzureBlobFileSystemException if rest operation fails.
    */

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsClient.java

@@ -890,16 +890,18 @@ public abstract AbfsRestOperation flush(String path, long position,
 
   /**
    * Flushes previously uploaded data to the specified path.
-   * @param buffer                The buffer containing block IDs to be flushed.
-   * @param path                  The file path to which data should be flushed.
-   * @param isClose               True if this is the final flush (i.e., the file is being closed).
-   * @param cachedSasToken        SAS token used for authentication (if applicable).
-   * @param leaseId               Lease ID, if a lease is active on the file.
-   * @param eTag                  ETag used for conditional request headers (e.g., If-Match).
+   *
+   * @param buffer The buffer containing block IDs to be flushed.
+   * @param path The file path to which data should be flushed.
+   * @param isClose True if this is the final flush (i.e., the file is being closed).
+   * @param cachedSasToken SAS token used for authentication (if applicable).
+   * @param leaseId Lease ID, if a lease is active on the file.
+   * @param eTag ETag used for conditional request headers (e.g., If-Match).
    * @param contextEncryptionAdapter Adapter to provide encryption context, if encryption is enabled.
-   * @param tracingContext        Context for tracing the server calls.
-   * @param blobMd5               The Base64-encoded MD5 hash of the blob for data integrity validation.
-   * @return                      The executed {@link AbfsRestOperation} containing the server response.
+   * @param tracingContext Context for tracing the server calls.
+   * @param blobMd5 The Base64-encoded MD5 hash of the blob for data integrity validation.
+   * @return The executed {@link AbfsRestOperation} containing the server response.
+   *
    * @throws AzureBlobFileSystemException if the flush operation fails.
    */
   public abstract AbfsRestOperation flush(byte[] buffer,

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsDfsClient.java

@@ -846,6 +846,7 @@ && appendSuccessCheckOp(op, path,
    * @param leaseId if there is an active lease on the path.
    * @param contextEncryptionAdapter to provide encryption context.
    * @param tracingContext for tracing the server calls.
+   * @param blobMd5 the MD5 hash of the blob for integrity verification.
    * @return executed rest operation containing response from server.
    * @throws AzureBlobFileSystemException if rest operation fails.
    */
@@ -891,6 +892,21 @@ public AbfsRestOperation flush(final String path,
     return op;
   }
 
+  /**
+   * Flushes data to a file at the specified path, using the provided buffer and other parameters.
+   * This operation is not supported on the DFS endpoint and will throw an {@link UnsupportedOperationException}.
+   *
+   * @param buffer the byte array containing the data to be flushed to the file.
+   * @param path the path where the data has to be flushed.
+   * @param isClose whether this is the last flush operation to the file.
+   * @param cachedSasToken the SAS token to authenticate the operation.
+   * @param leaseId the lease ID, if an active lease exists on the path.
+   * @param eTag the ETag for concurrency control to ensure the flush is applied to the correct file version.
+   * @param contextEncryptionAdapter the adapter providing the encryption context.
+   * @param tracingContext the tracing context for tracking server calls.
+   * @param blobMd5 the MD5 hash of the blob for integrity verification.
+   * @throws UnsupportedOperationException if flush with blockIds is called on a DFS endpoint.
+   */
   @Override
   public AbfsRestOperation flush(byte[] buffer,
       final String path,

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AzureBlobIngressHandler.java

@@ -20,8 +20,6 @@
 
 import java.io.IOException;
 import java.nio.charset.StandardCharsets;
-import java.security.MessageDigest;
-import java.util.Base64;
 
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AzureDFSIngressHandler.java

@@ -19,8 +19,6 @@
 package org.apache.hadoop.fs.azurebfs.services;
 
 import java.io.IOException;
-import java.security.MessageDigest;
-import java.util.Base64;
 
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;