rdblue commented on a change in pull request #1633: URL: https://github.com/apache/iceberg/pull/1633#discussion_r521634244
########## File path: aws/src/main/java/org/apache/iceberg/aws/glue/GlueCatalog.java ########## @@ -0,0 +1,423 @@ +/* + * 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.io.Closeable; +import java.io.IOException; +import java.util.List; +import java.util.Map; +import java.util.Set; +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.AwsClientUtil; +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.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import software.amazon.awssdk.awscore.exception.AwsServiceException; +import software.amazon.awssdk.services.glue.GlueClient; +import software.amazon.awssdk.services.glue.model.CreateDatabaseRequest; +import software.amazon.awssdk.services.glue.model.CreateTableRequest; +import software.amazon.awssdk.services.glue.model.DeleteDatabaseRequest; +import software.amazon.awssdk.services.glue.model.DeleteTableRequest; +import software.amazon.awssdk.services.glue.model.EntityNotFoundException; +import software.amazon.awssdk.services.glue.model.GetDatabaseRequest; +import software.amazon.awssdk.services.glue.model.GetDatabaseResponse; +import software.amazon.awssdk.services.glue.model.GetDatabasesRequest; +import software.amazon.awssdk.services.glue.model.GetDatabasesResponse; +import software.amazon.awssdk.services.glue.model.GetTableRequest; +import software.amazon.awssdk.services.glue.model.GetTableResponse; +import software.amazon.awssdk.services.glue.model.GetTablesRequest; +import software.amazon.awssdk.services.glue.model.GetTablesResponse; +import software.amazon.awssdk.services.glue.model.InvalidInputException; +import software.amazon.awssdk.services.glue.model.Table; +import software.amazon.awssdk.services.glue.model.TableInput; +import software.amazon.awssdk.services.glue.model.UpdateDatabaseRequest; + +public class GlueCatalog extends BaseMetastoreCatalog implements Closeable, SupportsNamespaces, Configurable { + + private static final Logger LOG = LoggerFactory.getLogger(GlueCatalog.class); + + public static final String CONFIG_GLUE_CATALOG_ID = "glue-catalog-id"; + public static final String CONFIG_SKIP_ARCHIVE = "skip-archive"; + public static final boolean CONFIG_SKIP_ARCHIVE_DEFAULT = false; + + private final GlueClient glue; + private Configuration hadoopConf; + private String catalogId; + private String catalogName; + private String warehousePath; + private boolean skipArchive; + private FileIO fileIO; + + /** + * No-arg constructor to load the catalog dynamically. + * <p> + * Only the AWS Glue client is initialized. + * Other fields must be initialized by calling {@link GlueCatalog#initialize(String, Map)} later. + */ + public GlueCatalog() { + this.glue = AwsClientUtil.defaultGlueClient(); + } + + /** + * All-arg constructor to directly initialize the catalog. + * <p> + * All the fields are directly initialized. + * There is no need to call {@link GlueCatalog#initialize(String, Map)} later. + * + * @param glue Glue client + * @param catalogName a custom name for the catalog, usually obtained from a Spark or Flink session. + * @param catalogId The ID of the Glue Data Catalog where the tables reside. + * If none is provided, the AWS account ID is used by default. + * @param warehousePath warehouse path, such as s3://my-iceberg-bucket/metadata_prod + * @param skipArchive if Glue should skip archiving an old table version when creating a new version in a commit. + * By default Glue archives all old table versions after an UpdateTable call. + * but Glue has a default max number of archived table versions (can be increased). + * So for streaming use case with lots of commits, it is recommended to set this value to true. + * @param fileIO file IO to use. + */ + public GlueCatalog(GlueClient glue, String catalogName, String catalogId, String warehousePath, Review comment: Since all this does is call `initialize`, maybe we don't even need it for tests. That method could be package-private. ---------------------------------------------------------------- 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
