ConeyLiu commented on code in PR #1174: URL: https://github.com/apache/parquet-mr/pull/1174#discussion_r1366603099
########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/PrefetchIndexCache.java: ########## @@ -0,0 +1,156 @@ +/* + * 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.parquet.hadoop; + +import org.apache.parquet.Preconditions; +import org.apache.parquet.column.values.bloomfilter.BloomFilter; +import org.apache.parquet.hadoop.metadata.BlockMetaData; +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData; +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.internal.column.columnindex.ColumnIndex; +import org.apache.parquet.internal.column.columnindex.OffsetIndex; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; +import java.util.Set; + +/** + * This index cache will prefetch those columns' indexes when calling {@link #setBlockMetadata(BlockMetaData)}. + * <p> + * + * Note: the given index will be freed from the cache after calling the related get method. + */ +class PrefetchIndexCache implements IndexCache { + private final ParquetFileReader fileReader; + private final Set<ColumnPath> columns; + + private Map<ColumnPath, ColumnIndex> columnIndexCache; + private Map<ColumnPath, OffsetIndex> offsetIndexCache; + private Map<ColumnPath, BloomFilter> bloomIndexCache; + + PrefetchIndexCache( + ParquetFileReader fileReader, + Set<ColumnPath> columns) { + this.fileReader = fileReader; + this.columns = columns; + } + + @Override + public void setBlockMetadata(BlockMetaData currentBlockMetadata) throws IOException { + this.columnIndexCache = readAllColumnIndexes(currentBlockMetadata); + this.offsetIndexCache = readAllOffsetIndexes(currentBlockMetadata); + this.bloomIndexCache = readAllBloomFilters(currentBlockMetadata); + } + + @Override + public ColumnIndex getColumnIndex(ColumnChunkMetaData chunk) throws IOException { + ColumnPath columnPath = chunk.getPath(); + if (columns.contains(columnPath)) { + Preconditions.checkState( + columnIndexCache.containsKey(columnPath), + "Not found cached ColumnIndex for column: %s with cache strategy: %s", + columnPath.toDotString(), + CacheStrategy.PRECACHE_BLOCK); + } + + return columnIndexCache.remove(columnPath); Review Comment: I added the parameter: `freeCacheAfterGet` to enable it or not. -- 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. To unsubscribe, e-mail: dev-unsubscr...@parquet.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
