akashrn5 commented on a change in pull request #3770: URL: https://github.com/apache/carbondata/pull/3770#discussion_r434515732
########## File path: sdk/sdk/src/main/java/org/apache/carbondata/sdk/file/PaginationCarbonReader.java ########## @@ -0,0 +1,302 @@ +/* + * 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.sdk.file; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.List; + +import org.apache.carbondata.common.annotations.InterfaceAudience; +import org.apache.carbondata.common.annotations.InterfaceStability; +import org.apache.carbondata.core.cache.CarbonLRUCache; +import org.apache.carbondata.core.constants.CarbonCommonConstants; +import org.apache.carbondata.core.indexstore.BlockletDetailInfo; +import org.apache.carbondata.hadoop.CarbonInputSplit; +import org.apache.carbondata.sdk.file.cache.BlockletRows; + +import org.apache.hadoop.mapreduce.InputSplit; + +/** + * CarbonData SDK reader with pagination support + */ +@InterfaceAudience.User +@InterfaceStability.Evolving +public class PaginationCarbonReader<T> extends CarbonReader<T> { + // Splits based the file present in the reader path when the reader is built. + private List<InputSplit> allBlockletSplits; + + // Rows till the current splits stored as list. + private List<Long> rowCountInSplits; + + // Reader builder used to create the pagination reader, used for building split level readers. + private CarbonReaderBuilder readerBuilder; + + private boolean isClosed; + + // to store the rows of each blocklet in memory based LRU cache. + // key: unique blocklet id + // value: BlockletRows + private CarbonLRUCache cache = + new CarbonLRUCache(CarbonCommonConstants.CARBON_MAX_PAGINATION_LRU_CACHE_SIZE_IN_MB, + CarbonCommonConstants.CARBON_MAX_PAGINATION_LRU_CACHE_SIZE_IN_MB_DEFAULT); + + /** + * Call {@link #builder(String)} to construct an instance + */ + + PaginationCarbonReader(List<InputSplit> splits, CarbonReaderBuilder readerBuilder) { + // Initialize super class with no readers. + // Based on the splits identified for pagination query, readers will be built for the query. + super(null); + this.allBlockletSplits = splits; + this.readerBuilder = readerBuilder; + // prepare the mapping. + rowCountInSplits = new ArrayList<>(splits.size()); + long sum = ((CarbonInputSplit) splits.get(0)).getDetailInfo().getRowCount(); + rowCountInSplits.add(sum); + for (int i = 1; i < splits.size(); i++) { + // prepare a summation array of row counts in each blocklet, + // this is used for pruning with pagination vales. + // At current index, it contains sum of rows of all the blocklet from previous + current. + sum += ((CarbonInputSplit) splits.get(i)).getDetailInfo().getRowCount(); + rowCountInSplits.add(sum); + } + } + + /** + * Pagination query with from and to range. + * + * @param fromRowNumber must be greater 0 (as row id starts from 1) + * and less than equal to toRowNumber + * @param toRowNumber must be greater than 0 (as row id starts from 1) + * and greater than equals to fromRowNumber and not outside the total rows + * @return array of rows between fromRowNumber and toRowNumber (inclusive) + * @throws Exception + */ + public Object[] read(long fromRowNumber, long toRowNumber) + throws IOException, InterruptedException { + if (isClosed) { + throw new RuntimeException("Pagination Reader is closed. please build again"); + } + if (fromRowNumber < 1) { + throw new IllegalArgumentException("from row id:" + fromRowNumber + " is less than 1"); + } + if (fromRowNumber > toRowNumber) { + throw new IllegalArgumentException( Review comment: same as above ---------------------------------------------------------------- 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
