attilapiros commented on a change in pull request #23988: [SPARK-26509][SQL] Parquet DELTA_BYTE_ARRAY is not supported in Spark 2.x's Vectorized Reader URL: https://github.com/apache/spark/pull/23988#discussion_r269132853
########## File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java ########## @@ -0,0 +1,99 @@ +/* + * 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 org.apache.parquet.bytes.ByteBufferInputStream; +import org.apache.parquet.column.values.ValuesReader; +import org.apache.parquet.column.values.deltastrings.DeltaByteArrayReader; +import org.apache.parquet.io.api.Binary; +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. + */ +public class VectorizedDeltaByteArrayReader extends ValuesReader implements VectorizedValuesReader { + private final DeltaByteArrayReader deltaByteArrayReader = new DeltaByteArrayReader(); + + @Override + public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException { + deltaByteArrayReader.initFromPage(valueCount, in); + } + + @Override + public void skip() { + throw new UnsupportedOperationException(); + } + + @Override + public byte readByte() { + throw new UnsupportedOperationException(); + } + + @Override + public Binary readBinary(int len) { + throw new UnsupportedOperationException(); + } + + @Override + public void readBooleans(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readBytes(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readIntegers(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readLongs(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readFloats(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readDoubles(int total, WritableColumnVector c, int rowId) { + throw new UnsupportedOperationException(); + } + + @Override + public void readBinary(int total, WritableColumnVector c, int rowId) { + for (int i = 0; i < total; i++) { + Binary binary = deltaByteArrayReader.readBytes(); + ByteBuffer buffer = binary.toByteBuffer(); + if (buffer.hasArray()) { Review comment: I am a bit uncertain here but I have tried `binary.getBytes()` and it worked. I know currently the buffer is backed by a byte array. So my questions: - Can we use `binary.getBytes()` for both cases? - What would be its disadvantages? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
