Github user chenliang613 commented on a diff in the pull request: https://github.com/apache/carbondata/pull/1307#discussion_r137447980 --- Diff: integration/presto/src/main/java/org/apache/carbondata/presto/CarbonVectorizedRecordReader.java --- @@ -0,0 +1,264 @@ +/* + * 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.carbondata.presto; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.Map; + +import org.apache.carbondata.core.cache.dictionary.Dictionary; +import org.apache.carbondata.core.datastore.block.TableBlockInfo; +import org.apache.carbondata.core.keygenerator.directdictionary.DirectDictionaryGenerator; +import org.apache.carbondata.core.keygenerator.directdictionary.DirectDictionaryKeyGeneratorFactory; +import org.apache.carbondata.core.metadata.datatype.DataType; +import org.apache.carbondata.core.metadata.encoder.Encoding; +import org.apache.carbondata.core.scan.executor.QueryExecutor; +import org.apache.carbondata.core.scan.executor.QueryExecutorFactory; +import org.apache.carbondata.core.scan.executor.exception.QueryExecutionException; +import org.apache.carbondata.core.scan.model.QueryDimension; +import org.apache.carbondata.core.scan.model.QueryMeasure; +import org.apache.carbondata.core.scan.model.QueryModel; +import org.apache.carbondata.core.scan.result.iterator.AbstractDetailQueryResultIterator; +import org.apache.carbondata.core.scan.result.vector.CarbonColumnVector; +import org.apache.carbondata.core.scan.result.vector.CarbonColumnarBatch; +import org.apache.carbondata.core.util.CarbonUtil; +import org.apache.carbondata.hadoop.AbstractRecordReader; +import org.apache.carbondata.hadoop.CarbonInputSplit; +import org.apache.carbondata.hadoop.CarbonMultiBlockSplit; + +import org.apache.hadoop.mapreduce.InputSplit; +import org.apache.hadoop.mapreduce.TaskAttemptContext; +import org.apache.spark.memory.MemoryMode; +import org.apache.spark.sql.execution.vectorized.ColumnarBatch; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; + +/** + * A specialized RecordReader that reads into InternalRows or ColumnarBatches directly using the + * carbondata column APIs and fills the data directly into columns. + */ +class CarbonVectorizedRecordReader extends AbstractRecordReader<Object> { --- End diff -- Yes, we could consider the refactor as you suggested in 1.3.0. @bhavya411 please add comment for this class , like "TODO: abstract and consolidate VectorizedRecordReader into one , and be shared for all integration modules"
---