jackye1995 commented on a change in pull request #1633: URL: https://github.com/apache/iceberg/pull/1633#discussion_r513692137
########## File path: aws/src/main/java/org/apache/iceberg/aws/glue/GlueCatalog.java ########## @@ -0,0 +1,398 @@ +/* + * 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.ArrayList; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.commons.collections.CollectionUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.BaseMetastoreCatalog; +import org.apache.iceberg.CatalogUtil; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.aws.IcebergAWSConfigs; +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.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 { + + private static final Logger LOG = LoggerFactory.getLogger(GlueCatalog.class); + + private final Configuration conf; + private final GlueClient glue; + private final String catalogId; + private final String catalogName; + private final String warehousePath; + private final boolean skipArchive; + + /** + * Constructor that initializes all args from Hadoop configuration, used by engines like Spark and Flink + * @param conf Hadoop config passed from engines + */ + public GlueCatalog(Configuration conf) { + this( + conf, + conf.get(IcebergAWSConfigs.ICEBERG_AWS_GLUE_CATALOG_ID), + conf.get(IcebergAWSConfigs.ICEBERG_AWS_GLUE_WAREHOUSE_PATH), + conf.getBoolean(IcebergAWSConfigs.ICEBERG_AWS_GLUE_SKIP_ARCHIVE, + IcebergAWSConfigs.ICEBERG_AWS_GLUE_SKIP_ARCHIVE_DEFAULT) + ); + } + + /** + * Constructor with default glue client + * @param conf Hadoop config, passed in for users of HadoopIO + * @param catalogId Glue catalog ID, which is the AWS account ID. When null, it uses the account of the Glue client. + * @param warehousePath warehouse path, such as s3://my-iceberg-bucket/metadata_prod + * @param skipArchive if Glue should skip 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 turn this feature off. + */ + public GlueCatalog( + Configuration conf, + String catalogId, + String warehousePath, + boolean skipArchive) { + this(conf, GlueClient.create(), catalogId, warehousePath, skipArchive); + } + + @Override + public String name() { + return catalogName; + } + + /** + * 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. + * @param warehousePath warehouse path, such as s3://my-iceberg-bucket/metadata_prod + * @param skipArchive if Glue should skip 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 turn this feature off. + */ + public GlueCatalog( + Configuration conf, + GlueClient glue, + String catalogId, + String warehousePath, + boolean skipArchive) { + this.conf = Preconditions.checkNotNull(conf, "Cannot initialize GlueCatalog because Hadoop config is null"); + this.glue = Preconditions.checkNotNull(glue, "Cannot initialize GlueCatalog because GlueClient is null"); + this.catalogId = catalogId; + this.catalogName = "glue." + catalogId; // for logging purpose + this.warehousePath = warehousePath; + this.skipArchive = skipArchive; + validateWarehousePath(); + } + + private void validateWarehousePath() { + Preconditions.checkArgument(warehousePath != null && warehousePath.length() > 0, + "Cannot initialize GlueCatalog because warehousePath must not be null"); + Preconditions.checkArgument(warehousePath.charAt(warehousePath.length() - 1) != '/', + "Cannot initialize GlueCatalog because warehousePath %s must not end with /", warehousePath); + } + + @Override + public void close() throws IOException { + glue.close(); + } + + @Override + protected TableOperations newTableOps(TableIdentifier tableIdentifier) { + return new GlueTableOperations(conf, glue, catalogId, skipArchive, tableIdentifier); + } + + /** + * This method produces the same result as using a HiveCatalog. + * If databaseUri exists for the Glue database URI, the default location is databaseUri/tableName. + * If not, the default location is warehousePath/databaseName.db/tableName + * @param tableIdentifier table id + * @return default warehouse path + */ + @Override + protected String defaultWarehouseLocation(TableIdentifier tableIdentifier) { + // check if value is set in database + GetDatabaseResponse response = glue.getDatabase(GetDatabaseRequest.builder() + .name(IcebergToGlueConverter.getDatabaseName(tableIdentifier)) + .build()); + String dbLocationUri = response.database().locationUri(); + if (dbLocationUri != null) { + return String.format("%s/%s", dbLocationUri, tableIdentifier.name()); + } + return String.format( Review comment: sure, will update ---------------------------------------------------------------- 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
