skoppu22 commented on code in PR #206: URL: https://github.com/apache/cassandra-analytics/pull/206#discussion_r3776337493
########## cassandra-analytics-core/src/main/java/org/apache/cassandra/spark/data/backup/BackupReader.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.cassandra.spark.data.backup; + +import java.io.Serializable; +import java.math.BigInteger; +import java.util.List; +import java.util.Map; +import java.util.Optional; +import java.util.concurrent.CompletableFuture; +import java.util.function.LongConsumer; + +import com.google.common.collect.RangeMap; +import org.jetbrains.annotations.NotNull; + +import org.apache.cassandra.analytics.stats.Stats; +import org.apache.cassandra.spark.data.FileType; +import org.apache.cassandra.spark.data.ReplicationFactor; +import org.apache.cassandra.spark.data.S3ClientConfig; +import org.apache.cassandra.spark.data.SSTableKey; +import org.apache.cassandra.spark.data.partitioner.CassandraInstance; +import org.apache.cassandra.spark.data.partitioner.Partitioner; +import org.apache.cassandra.spark.utils.streaming.StreamConsumer; + +/** + * Pluggable backup-reader API. Implementations encapsulate the format-specific knowledge for a + * given backup implementation. Concrete factories are registered with {@link BackupReaderRegistry} on the + * driver and selected via the {@code backupReaderType} option; the data layer programs strictly + * against this interface. + * + * <p>Implementations are {@link Serializable} so the data layer can ship a configured reader to + * executors inside the Spark task closure, and {@link AutoCloseable} so the data layer can + * release reader-local resources on shutdown. + */ +public interface BackupReader extends Serializable, AutoCloseable +{ + /** + * Populates the reader's per-(cluster, keyspace, table) cache by walking the backup manifest. + * + * @param clusterName logical cluster identity (UUID or human-readable name) + * @param keyspace Cassandra keyspace + * @param table Cassandra table + * @param datacenter datacenter to read from + */ + void initializeSSTableInfoCache(String clusterName, String keyspace, String table, String datacenter) + throws IllegalArgumentException; + + /** + * Lists Cassandra instances present in the backup for the given dataset slice. + * + * @param clusterName logical cluster identity + * @param keyspace Cassandra keyspace + * @param table Cassandra table + * @param datacenter datacenter to read from + * @return Cassandra instances contributing to this slice + */ + List<CassandraInstance> instances(String clusterName, String keyspace, String table, String datacenter); + + /** + * Discovers SSTables across all nodes for the given dataset slice. + * + * @param clusterName logical cluster identity + * @param keyspace Cassandra keyspace + * @param table Cassandra table + * @param datacenter datacenter to read from + * @return map of SSTable key to per-file-type sizes + */ + Map<SSTableKey, Map<FileType, Long>> sstables(String clusterName, String keyspace, String table, String datacenter); + + /** + * Discovers SSTables for a single node. + * + * @param clusterName logical cluster identity + * @param keyspace Cassandra keyspace + * @param table Cassandra table + * @param datacenter datacenter to read from + * @param nodeId node identifier whose SSTables to enumerate + * @return map of SSTable key to per-file-type sizes for the given node + */ + Map<SSTableKey, Map<FileType, Long>> sstables(String clusterName, + String keyspace, + String table, + String datacenter, + String nodeId); + + /** + * Buffered ranged GET; completes with the full {@code [start, end]} byte range. + * + * @param clusterName logical cluster identity + * @param datacenter datacenter to read from + * @param token Cassandra token (used for path resolution by some implementations) + * @param sstableKey identifies the SSTable + * @param fileType which SSTable component to read + * @param start inclusive byte offset + * @param end inclusive byte offset + * @param stats per-task stats sink for S3 operation metrics + * @return future completing with the read bytes + */ + CompletableFuture<byte[]> readAsync(String clusterName, Review Comment: Also, would be good to have `KeyService` interface with `byte[] unwrapDek(String keyId, byte[] wrappedDek) `method. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
