garyli1019 commented on a change in pull request #2613: URL: https://github.com/apache/hudi/pull/2613#discussion_r586180443
########## File path: hudi-flink/src/main/java/org/apache/hudi/source/format/cow/ParquetColumnarRowSplitReader.java ########## @@ -0,0 +1,370 @@ +/* + * 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.source.format.cow; + +import org.apache.flink.formats.parquet.vector.reader.ColumnReader; +import org.apache.flink.table.data.ColumnarRowData; +import org.apache.flink.table.data.vector.ColumnVector; +import org.apache.flink.table.data.vector.VectorizedColumnBatch; +import org.apache.flink.table.data.vector.writable.WritableColumnVector; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.table.types.logical.LogicalTypeRoot; +import org.apache.flink.util.FlinkRuntimeException; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.column.page.PageReadStore; +import org.apache.parquet.filter2.compat.FilterCompat; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.metadata.BlockMetaData; +import org.apache.parquet.hadoop.metadata.ParquetMetadata; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; +import org.apache.parquet.schema.Types; + +import java.io.Closeable; +import java.io.IOException; +import java.util.Arrays; +import java.util.HashMap; +import java.util.List; +import java.util.Locale; +import java.util.Map; + +import static org.apache.hudi.source.format.cow.ParquetSplitReaderUtil.createColumnReader; +import static org.apache.hudi.source.format.cow.ParquetSplitReaderUtil.createWritableColumnVector; +import static org.apache.parquet.filter2.compat.RowGroupFilter.filterRowGroups; +import static org.apache.parquet.format.converter.ParquetMetadataConverter.range; +import static org.apache.parquet.hadoop.ParquetFileReader.readFooter; +import static org.apache.parquet.hadoop.ParquetInputFormat.getFilter; + +/** + * This reader is used to read a {@link VectorizedColumnBatch} from input split. + * + * <p>Note: Reference Flink release 1.11.2 + * {@code org.apache.flink.formats.parquet.vector.ParquetColumnarRowSplitReader} + * because it is package scope. + */ +public class ParquetColumnarRowSplitReader implements Closeable { Review comment: wanna bring @vinothchandar into this discussion, we had this discussion before on the Spark side. Whether we should add the Engine's FileInputFormat and FileReader into Hudi's codebase. Both sides have pros and cons. @vinothchandar WDYT? ---------------------------------------------------------------- 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]
