yihua commented on code in PR #12866:
URL: https://github.com/apache/hudi/pull/12866#discussion_r2105475619
##########
hudi-io/src/main/java/org/apache/hudi/io/hfile/HFileBlock.java:
##########
@@ -187,34 +162,161 @@ public int getOnDiskSizeWithHeader() {
* @throws IOException upon decoding and decompression error.
*/
public void unpack() throws IOException {
- if (!isUnpacked) {
+ if (!readAttributesOpt.get().isUnpacked) {
// Should only be called for compressed blocks
CompressionCodec compression = context.getCompressionCodec();
if (compression != CompressionCodec.NONE) {
// Copy the block header which is not compressed
System.arraycopy(
- compressedByteBuff, startOffsetInCompressedBuff, byteBuff, 0,
HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff,
+ readAttributesOpt.get().byteBuff,
+ 0,
+ HFILEBLOCK_HEADER_SIZE);
try (InputStream byteBuffInputStream = new ByteArrayInputStream(
- compressedByteBuff, startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE, onDiskSizeWithoutHeader)) {
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE,
+ readAttributesOpt.get().onDiskSizeWithoutHeader)) {
context.getDecompressor().decompress(
byteBuffInputStream,
- byteBuff,
+ readAttributesOpt.get().byteBuff,
HFILEBLOCK_HEADER_SIZE,
- byteBuff.length - HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().byteBuff.length -
HFILEBLOCK_HEADER_SIZE);
}
}
- isUnpacked = true;
+ readAttributesOpt.get().isUnpacked = true;
}
}
+ // ================ Below are for Write ================
+
/**
- * Allocates new byte buffer for the uncompressed bytes.
- *
- * @return a new byte array based on the size of uncompressed data, holding
the same header
- * bytes.
+ * Returns serialized "data" part of the block.
+ * This function should be implemented by each block type separately.
+ * By default, it does nothing.
+ */
+ public ByteBuffer getPayload() {
+ return ByteBuffer.allocate(0);
+ }
Review Comment:
```suggestion
protected ByteBuffer getUncompressedBlockDataToWrite();
```
##########
hudi-io/src/main/java/org/apache/hudi/io/hfile/HFileBlock.java:
##########
@@ -187,34 +162,161 @@ public int getOnDiskSizeWithHeader() {
* @throws IOException upon decoding and decompression error.
*/
public void unpack() throws IOException {
- if (!isUnpacked) {
+ if (!readAttributesOpt.get().isUnpacked) {
// Should only be called for compressed blocks
CompressionCodec compression = context.getCompressionCodec();
if (compression != CompressionCodec.NONE) {
// Copy the block header which is not compressed
System.arraycopy(
- compressedByteBuff, startOffsetInCompressedBuff, byteBuff, 0,
HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff,
+ readAttributesOpt.get().byteBuff,
+ 0,
+ HFILEBLOCK_HEADER_SIZE);
try (InputStream byteBuffInputStream = new ByteArrayInputStream(
- compressedByteBuff, startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE, onDiskSizeWithoutHeader)) {
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE,
+ readAttributesOpt.get().onDiskSizeWithoutHeader)) {
context.getDecompressor().decompress(
byteBuffInputStream,
- byteBuff,
+ readAttributesOpt.get().byteBuff,
HFILEBLOCK_HEADER_SIZE,
- byteBuff.length - HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().byteBuff.length -
HFILEBLOCK_HEADER_SIZE);
}
}
- isUnpacked = true;
+ readAttributesOpt.get().isUnpacked = true;
}
}
+ // ================ Below are for Write ================
+
/**
- * Allocates new byte buffer for the uncompressed bytes.
- *
- * @return a new byte array based on the size of uncompressed data, holding
the same header
- * bytes.
+ * Returns serialized "data" part of the block.
+ * This function should be implemented by each block type separately.
+ * By default, it does nothing.
+ */
+ public ByteBuffer getPayload() {
+ return ByteBuffer.allocate(0);
+ }
+
+ /**
+ * Return serialized block including header, data, checksum.
+ */
+ public ByteBuffer serialize() throws IOException {
+ // Block payload.
+ ByteBuffer payloadBuff = getPayload();
+ // Compress if specified.
+ ByteBuffer compressedPayload = compress(payloadBuff);
Review Comment:
```suggestion
ByteBuffer uncompressedBlockData = getPayload();
// Compress if specified.
ByteBuffer compressedBlockData = compress(payloadBuff);
```
##########
hudi-io/src/main/java/org/apache/hudi/io/hfile/HFileBlock.java:
##########
@@ -187,34 +162,161 @@ public int getOnDiskSizeWithHeader() {
* @throws IOException upon decoding and decompression error.
*/
public void unpack() throws IOException {
- if (!isUnpacked) {
+ if (!readAttributesOpt.get().isUnpacked) {
// Should only be called for compressed blocks
CompressionCodec compression = context.getCompressionCodec();
if (compression != CompressionCodec.NONE) {
// Copy the block header which is not compressed
System.arraycopy(
- compressedByteBuff, startOffsetInCompressedBuff, byteBuff, 0,
HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff,
+ readAttributesOpt.get().byteBuff,
+ 0,
+ HFILEBLOCK_HEADER_SIZE);
try (InputStream byteBuffInputStream = new ByteArrayInputStream(
- compressedByteBuff, startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE, onDiskSizeWithoutHeader)) {
+ readAttributesOpt.get().compressedByteBuff,
+ readAttributesOpt.get().startOffsetInCompressedBuff +
HFILEBLOCK_HEADER_SIZE,
+ readAttributesOpt.get().onDiskSizeWithoutHeader)) {
context.getDecompressor().decompress(
byteBuffInputStream,
- byteBuff,
+ readAttributesOpt.get().byteBuff,
HFILEBLOCK_HEADER_SIZE,
- byteBuff.length - HFILEBLOCK_HEADER_SIZE);
+ readAttributesOpt.get().byteBuff.length -
HFILEBLOCK_HEADER_SIZE);
}
}
- isUnpacked = true;
+ readAttributesOpt.get().isUnpacked = true;
}
}
+ // ================ Below are for Write ================
+
/**
- * Allocates new byte buffer for the uncompressed bytes.
- *
- * @return a new byte array based on the size of uncompressed data, holding
the same header
- * bytes.
+ * Returns serialized "data" part of the block.
+ * This function should be implemented by each block type separately.
+ * By default, it does nothing.
+ */
+ public ByteBuffer getPayload() {
+ return ByteBuffer.allocate(0);
+ }
Review Comment:
Can be folded into `serialize()`
##########
hudi-io/src/main/java/org/apache/hudi/io/hfile/HFileBlockWriteAttributes.java:
##########
@@ -0,0 +1,67 @@
+/*
+ * 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.hudi.io.hfile;
+
+public class HFileBlockWriteAttributes {
+ public static final int DEFAULT_BYTES_PER_CHECKSUM = 16 * 1024;
+ public static final byte[] EMPTY_BYTE_ARRAY = new byte[0];
+ public static final ChecksumType CHECKSUM_TYPE = ChecksumType.NULL;
+ protected long startOffsetInBuff = -1;
+ protected long previousBlockOffset = -1;
+ protected int blockSize;
+
+ public HFileBlockWriteAttributes(long startOffsetInBuff, long
previousBlockOffset, int blockSize) {
+ this.startOffsetInBuff = startOffsetInBuff;
+ this.previousBlockOffset = -1;
Review Comment:
```suggestion
this.previousBlockOffset = previousBlockOffset;
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
