jackye1995 commented on a change in pull request #2688: URL: https://github.com/apache/iceberg/pull/2688#discussion_r654833389
########## File path: aws/src/main/java/org/apache/iceberg/aws/dynamodb/DynamoDbCatalog.java ########## @@ -0,0 +1,613 @@ +/* + * 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.iceberg.aws.dynamodb; + +import java.io.Closeable; +import java.io.IOException; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.hadoop.conf.Configurable; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.BaseMetastoreCatalog; +import org.apache.iceberg.CatalogProperties; +import org.apache.iceberg.CatalogUtil; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.aws.AwsClientFactories; +import org.apache.iceberg.aws.AwsProperties; +import org.apache.iceberg.aws.s3.S3FileIO; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.SupportsNamespaces; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.exceptions.AlreadyExistsException; +import org.apache.iceberg.exceptions.NamespaceNotEmptyException; +import org.apache.iceberg.exceptions.NoSuchNamespaceException; +import org.apache.iceberg.exceptions.NoSuchTableException; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Joiner; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.Tasks; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import software.amazon.awssdk.services.dynamodb.DynamoDbClient; +import software.amazon.awssdk.services.dynamodb.model.AttributeDefinition; +import software.amazon.awssdk.services.dynamodb.model.AttributeValue; +import software.amazon.awssdk.services.dynamodb.model.BillingMode; +import software.amazon.awssdk.services.dynamodb.model.ConditionalCheckFailedException; +import software.amazon.awssdk.services.dynamodb.model.CreateTableRequest; +import software.amazon.awssdk.services.dynamodb.model.Delete; +import software.amazon.awssdk.services.dynamodb.model.DeleteItemRequest; +import software.amazon.awssdk.services.dynamodb.model.DescribeTableRequest; +import software.amazon.awssdk.services.dynamodb.model.DescribeTableResponse; +import software.amazon.awssdk.services.dynamodb.model.GetItemRequest; +import software.amazon.awssdk.services.dynamodb.model.GetItemResponse; +import software.amazon.awssdk.services.dynamodb.model.GlobalSecondaryIndex; +import software.amazon.awssdk.services.dynamodb.model.KeySchemaElement; +import software.amazon.awssdk.services.dynamodb.model.KeyType; +import software.amazon.awssdk.services.dynamodb.model.Projection; +import software.amazon.awssdk.services.dynamodb.model.ProjectionType; +import software.amazon.awssdk.services.dynamodb.model.Put; +import software.amazon.awssdk.services.dynamodb.model.PutItemRequest; +import software.amazon.awssdk.services.dynamodb.model.QueryRequest; +import software.amazon.awssdk.services.dynamodb.model.QueryResponse; +import software.amazon.awssdk.services.dynamodb.model.ResourceNotFoundException; +import software.amazon.awssdk.services.dynamodb.model.ScalarAttributeType; +import software.amazon.awssdk.services.dynamodb.model.TableStatus; +import software.amazon.awssdk.services.dynamodb.model.TransactWriteItem; +import software.amazon.awssdk.services.dynamodb.model.TransactWriteItemsRequest; +import software.amazon.awssdk.services.dynamodb.model.UpdateItemRequest; + +/** + * DynamoDB implementation of Iceberg catalog + */ +public class DynamoDbCatalog extends BaseMetastoreCatalog implements Closeable, SupportsNamespaces, Configurable { + + private static final Logger LOG = LoggerFactory.getLogger(DynamoDbCatalog.class); + private static final int CATALOG_TABLE_CREATION_WAIT_ATTEMPTS_MAX = 5; + static final Joiner COMMA = Joiner.on(','); + + private static final String GSI_NAMESPACE_IDENTIFIER = "namespace-identifier"; + private static final String COL_IDENTIFIER = "identifier"; + private static final String COL_IDENTIFIER_NAMESPACE = "NAMESPACE"; + private static final String COL_NAMESPACE = "namespace"; + private static final String PROPERTY_COL_PREFIX = "p."; Review comment: > The main concern here is that table properties can get rather messy in that anyone can add values and there's really no limitation of name. This would in turn make the catalog table schema rather messy since it would be the union of all of the table property key names. DynamoDB is a noSQL database. Similar to HBase and Cassandra, the table schema only defines the primary key (in DynamoDB case is the hash key and range key, which are the `identifier` and `namespace` columns), and all the other columns are not a part of the schema. There is no such a concept that the table schema has to be a union of all column values. > I feel like since we don't have any use cases specifically called out for secondary indexes, we should use a map to reflect the table properties. I have listed one use case that we encounter a customer request about regarding ownership. The goal is to avoid the need to keep iterating the implementation with those feature requests. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
