samarthjain commented on a change in pull request #723: Arrow changes for supporting vectorized reads URL: https://github.com/apache/incubator-iceberg/pull/723#discussion_r382857980
########## File path: arrow/src/main/java/org/apache/iceberg/arrow/vectorized/VectorizedArrowReader.java ########## @@ -0,0 +1,334 @@ +/* + * 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.iceberg.arrow.vectorized; + +import com.google.common.base.Preconditions; +import java.util.Map; +import org.apache.arrow.memory.BufferAllocator; +import org.apache.arrow.vector.BigIntVector; +import org.apache.arrow.vector.BitVector; +import org.apache.arrow.vector.DateDayVector; +import org.apache.arrow.vector.DecimalVector; +import org.apache.arrow.vector.FieldVector; +import org.apache.arrow.vector.Float4Vector; +import org.apache.arrow.vector.Float8Vector; +import org.apache.arrow.vector.IntVector; +import org.apache.arrow.vector.TimeStampMicroTZVector; +import org.apache.arrow.vector.types.pojo.ArrowType; +import org.apache.arrow.vector.types.pojo.Field; +import org.apache.arrow.vector.types.pojo.FieldType; +import org.apache.iceberg.arrow.ArrowSchemaUtil; +import org.apache.iceberg.arrow.vectorized.parquet.VectorizedColumnIterator; +import org.apache.iceberg.parquet.ParquetUtil; +import org.apache.iceberg.parquet.VectorizedReader; +import org.apache.iceberg.types.Types; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.column.Dictionary; +import org.apache.parquet.column.page.PageReadStore; +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData; +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.schema.DecimalMetadata; +import org.apache.parquet.schema.PrimitiveType; + +/*** + * {@link VectorizedReader VectorReader(s)} that read in a batch of values into Arrow vectors. + * It also takes care of allocating the right kind of Arrow vectors depending on the corresponding + * Iceberg/Parquet data types. + */ +public class VectorizedArrowReader implements VectorizedReader<VectorHolder> { + public static final int DEFAULT_BATCH_SIZE = 5000; Review comment: DEFAULT_BATCH_SIZE is used in the spark module. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
