rdblue commented on a change in pull request #1633: URL: https://github.com/apache/iceberg/pull/1633#discussion_r513617498
########## File path: aws/src/main/java/org/apache/iceberg/aws/glue/GlueTableOperations.java ########## @@ -0,0 +1,228 @@ +/* + * 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.glue; + +import java.util.Locale; +import java.util.Map; +import java.util.Objects; +import java.util.Optional; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.BaseMetastoreTableOperations; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.exceptions.AlreadyExistsException; +import org.apache.iceberg.exceptions.CommitFailedException; +import org.apache.iceberg.exceptions.NoSuchTableException; +import org.apache.iceberg.hadoop.HadoopFileIO; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import software.amazon.awssdk.services.glue.GlueClient; +import software.amazon.awssdk.services.glue.model.ConcurrentModificationException; +import software.amazon.awssdk.services.glue.model.CreateTableRequest; +import software.amazon.awssdk.services.glue.model.EntityNotFoundException; +import software.amazon.awssdk.services.glue.model.GetTableRequest; +import software.amazon.awssdk.services.glue.model.GetTableResponse; +import software.amazon.awssdk.services.glue.model.OperationTimeoutException; +import software.amazon.awssdk.services.glue.model.ResourceNumberLimitExceededException; +import software.amazon.awssdk.services.glue.model.Table; +import software.amazon.awssdk.services.glue.model.TableInput; +import software.amazon.awssdk.services.glue.model.UpdateTableRequest; + +public class GlueTableOperations extends BaseMetastoreTableOperations { + + private static final Logger LOG = LoggerFactory.getLogger(GlueTableOperations.class); + + // same as org.apache.hadoop.hive.metastore.TableType.EXTERNAL_TABLE + // more details: https://docs.aws.amazon.com/glue/latest/webapi/API_TableInput.html + protected static final String GLUE_EXTERNAL_TABLE_TYPE = "EXTERNAL_TABLE"; + + private final Configuration conf; + private final GlueClient glue; + private final String catalogId; + private final boolean skipArchive; + private final String databaseName; + private final String tableName; + private final String fullName; + + private FileIO fileIO; + + /** + * All-arg constructor + * @param conf Hadoop config, passed in for users of HadoopIO + * @param glue Glue client + * @param catalogId Glue catalog ID, which is the AWS account ID. When null, it uses the account of the Glue client. Review comment: Can Glue only have one catalog per account? Saying that the catalog ID "is" the AWS account ID seems to imply that. Assuming that the account ID is a default catalog ID, I think that this should be more clear that the account ID is used by default, and that is the ID for the account's default catalog. ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
