[GitHub] [spark] sunchao commented on a change in pull request #35262: [SPARK-37974][SQL] Implement vectorized DELTA_BYTE_ARRAY and DELTA_LENGTH_BYTE_ARRAY encodings for Parquet V2 support

[GitBox <gi...@apache.org>]

sunchao commented on a change in pull request #35262:
URL: https://github.com/apache/spark/pull/35262#discussion_r820000445



##########
File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java
##########
@@ -16,51 +16,115 @@
  */
 package org.apache.spark.sql.execution.datasources.parquet;
 
+import static org.apache.spark.sql.types.DataTypes.BinaryType;
+import static org.apache.spark.sql.types.DataTypes.IntegerType;
+
 import org.apache.parquet.bytes.ByteBufferInputStream;
-import org.apache.parquet.column.values.deltastrings.DeltaByteArrayReader;
+import org.apache.parquet.column.values.RequiresPreviousReader;
+import org.apache.parquet.column.values.ValuesReader;
 import org.apache.parquet.io.api.Binary;
+import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector;
 import org.apache.spark.sql.execution.vectorized.WritableColumnVector;
 
 import java.io.IOException;
 import java.nio.ByteBuffer;
 
 /**
- * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized interface.
+ * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized
+ * interface.
  */
-public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase {
-  private final DeltaByteArrayReader deltaByteArrayReader = new DeltaByteArrayReader();
+public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase
+    implements VectorizedValuesReader, RequiresPreviousReader {
+
+  private final VectorizedDeltaBinaryPackedReader prefixLengthReader;
+  private final VectorizedDeltaLengthByteArrayReader suffixReader;
+  private WritableColumnVector prefixLengthVector;
+  private WritableColumnVector suffixVector;
+  private byte[] previous = new byte[0];
+  private int currentRow = 0;
+
+  // temporary variable used by getBinary
+  private final WritableColumnVector binaryValVector;
+
+  VectorizedDeltaByteArrayReader() {
+    this.prefixLengthReader = new VectorizedDeltaBinaryPackedReader();
+    this.suffixReader = new VectorizedDeltaLengthByteArrayReader();
+    binaryValVector = new OnHeapColumnVector(1, BinaryType);
+  }
 
   @Override
   public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException {
-    deltaByteArrayReader.initFromPage(valueCount, in);
+    prefixLengthVector = new OnHeapColumnVector(valueCount, IntegerType);
+    suffixVector = new OnHeapColumnVector(valueCount, BinaryType);
+    prefixLengthReader.initFromPage(valueCount, in);
+    prefixLengthReader.readIntegers(prefixLengthReader.getTotalValueCount(),
+        prefixLengthVector, 0);
+    suffixReader.initFromPage(valueCount, in);
+    suffixReader.readBinary(prefixLengthReader.getTotalValueCount(), suffixVector, 0);

Review comment:
       Instead of eagerly read the suffixes, we can have a method in `VectorizedDeltaLengthByteArrayReader` that just return the suffix at `rowId`:
   ```java
     public ByteBuffer getBytes(int rowId) {
       int length = lengthsVector.getInt(rowId);
       try {
         return in.slice(length);
       } catch (EOFException e) {
         throw new ParquetDecodingException("Failed to read " + length + " bytes");
       }
     }
   ```
   
   I tried this approach [here](https://github.com/sunchao/spark/commit/6d15a86be25d9911f9f7ee8d866afeb170cc7fa4), and it can improve the benchmark.

##########
File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java
##########
@@ -0,0 +1,86 @@
+/*
+ * 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.spark.sql.execution.datasources.parquet;
+
+import static org.apache.spark.sql.types.DataTypes.IntegerType;
+
+import java.io.EOFException;
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import org.apache.parquet.bytes.ByteBufferInputStream;
+import org.apache.parquet.io.ParquetDecodingException;
+import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector;
+import org.apache.spark.sql.execution.vectorized.WritableColumnVector;
+
+/**
+ * An implementation of the Parquet DELTA_LENGTH_BYTE_ARRAY decoder that supports the vectorized
+ * interface.
+ */
+public class VectorizedDeltaLengthByteArrayReader extends VectorizedReaderBase implements
+    VectorizedValuesReader {
+
+  private final VectorizedDeltaBinaryPackedReader lengthReader;
+  private ByteBufferInputStream in;
+  private WritableColumnVector lengthsVector;
+  private int currentRow = 0;
+
+  VectorizedDeltaLengthByteArrayReader() {
+    lengthReader = new VectorizedDeltaBinaryPackedReader();
+  }
+
+  @Override
+  public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException {
+    lengthsVector = new OnHeapColumnVector(valueCount, IntegerType);
+    lengthReader.initFromPage(valueCount, in);
+    lengthReader.readIntegers(lengthReader.getTotalValueCount(), lengthsVector, 0);
+    this.in = in.remainingStream();
+  }
+
+  @Override
+  public void readBinary(int total, WritableColumnVector c, int rowId) {
+    ByteBuffer buffer;
+    ByteBufferOutputWriter outputWriter = ByteBufferOutputWriter::writeArrayByteBuffer;
+    int length;
+    for (int i = 0; i < total; i++) {
+      length = lengthsVector.getInt(rowId + i);
+      try {
+        buffer = in.slice(length);
+      } catch (EOFException e) {
+        throw new ParquetDecodingException("Failed to read " + length + " bytes");
+      }
+      outputWriter.write(c, rowId + i, buffer, length);
+    }
+    currentRow += total;
+  }
+
+  @Override
+  public void skipBinary(int total) {
+    if (total == 0) {

Review comment:
       We can remove this too




-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org