Github user vdiravka commented on a diff in the pull request: https://github.com/apache/drill/pull/1214#discussion_r183633688 --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/AbstractParquetScanBatchCreator.java --- @@ -0,0 +1,195 @@ +/* + * 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.drill.exec.store.parquet; + +import com.google.common.base.Functions; +import com.google.common.collect.Maps; +import org.apache.drill.common.Stopwatch; +import org.apache.drill.common.exceptions.ExecutionSetupException; +import org.apache.drill.exec.ExecConstants; +import org.apache.drill.exec.ops.ExecutorFragmentContext; +import org.apache.drill.exec.ops.OperatorContext; +import org.apache.drill.exec.physical.impl.ScanBatch; +import org.apache.drill.exec.store.ColumnExplorer; +import org.apache.drill.exec.store.RecordReader; +import org.apache.drill.exec.store.dfs.DrillFileSystem; +import org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader; +import org.apache.drill.exec.store.parquet2.DrillParquetReader; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.format.converter.ParquetMetadataConverter; +import org.apache.parquet.hadoop.CodecFactory; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.metadata.ParquetMetadata; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.LinkedList; +import java.util.List; +import java.util.Map; +import java.util.concurrent.TimeUnit; + +public abstract class AbstractParquetScanBatchCreator { + + private static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(AbstractParquetScanBatchCreator.class); + + private static final String ENABLE_BYTES_READ_COUNTER = "parquet.benchmark.bytes.read"; + private static final String ENABLE_BYTES_TOTAL_COUNTER = "parquet.benchmark.bytes.total"; + private static final String ENABLE_TIME_READ_COUNTER = "parquet.benchmark.time.read"; + + protected ScanBatch getBatch(ExecutorFragmentContext context, AbstractParquetRowGroupScan rowGroupScan, OperatorContext oContext) throws ExecutionSetupException { + final ColumnExplorer columnExplorer = new ColumnExplorer(context.getOptions(), rowGroupScan.getColumns()); + + if (!columnExplorer.isStarQuery()) { + rowGroupScan = rowGroupScan.copy(columnExplorer.getTableColumns()); + rowGroupScan.setOperatorId(rowGroupScan.getOperatorId()); + } + + boolean useAsyncPageReader = + context.getOptions().getOption(ExecConstants.PARQUET_PAGEREADER_ASYNC).bool_val; + + AbstractDrillFileSystemManager fsManager = getDrillFileSystemCreator(oContext, useAsyncPageReader); + + // keep footers in a map to avoid re-reading them + Map<String, ParquetMetadata> footers = new HashMap<>(); + List<RecordReader> readers = new LinkedList<>(); + List<Map<String, String>> implicitColumns = new ArrayList<>(); + Map<String, String> mapWithMaxColumns = new LinkedHashMap<>(); + for(RowGroupReadEntry rowGroup : rowGroupScan.getRowGroupReadEntries()) { --- End diff -- `for (`
---