rdblue commented on a change in pull request #1587: URL: https://github.com/apache/iceberg/pull/1587#discussion_r521614936
########## File path: nessie/src/main/java/org/apache/iceberg/nessie/NessieCatalog.java ########## @@ -0,0 +1,431 @@ +/* + * 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.nessie; + +import com.dremio.nessie.api.TreeApi; +import com.dremio.nessie.client.NessieClient; +import com.dremio.nessie.error.NessieConflictException; +import com.dremio.nessie.error.NessieNotFoundException; +import com.dremio.nessie.model.Contents; +import com.dremio.nessie.model.ContentsKey; +import com.dremio.nessie.model.EntriesResponse; +import com.dremio.nessie.model.IcebergTable; +import com.dremio.nessie.model.ImmutableDelete; +import com.dremio.nessie.model.ImmutableOperations; +import com.dremio.nessie.model.ImmutablePut; +import com.dremio.nessie.model.Operations; +import com.dremio.nessie.model.Reference; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.function.Predicate; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.hadoop.conf.Configurable; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.BaseMetastoreCatalog; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableOperations; +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.CommitFailedException; +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.Joiner; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; + +/** + * Nessie implementation of Iceberg Catalog. + * + * <p> + * A note on namespaces: Nessie namespaces are implicit and do not need to be explicitly created or deleted. + * The create and delete namespace methods are no-ops for the NessieCatalog. One can still list namespaces that have + * objects stored in them to assist with namespace-centric catalog exploration. + * </p> + */ +public class NessieCatalog extends BaseMetastoreCatalog implements AutoCloseable, SupportsNamespaces, Configurable { + + private static final Joiner SLASH = Joiner.on("/"); + public static final String NESSIE_WAREHOUSE_DIR = "nessie.warehouse.dir"; + private NessieClient client; + private String warehouseLocation; + private Configuration config; + private UpdateableReference reference; + private String name; + + /** + * Try to avoid passing parameters via hadoop config. Dynamic catalog expects Map instead + * + * todo replace with #1640 style constructor Review comment: > Is the intention to add the new catalogs to the Iceberg shaded jar? I think it depends. If a catalog pulls in a ton of dependencies and requires updating a lot of the shaded Jar's documentation, then it comes at a high cost. On the other hand, if it uses existing bundled libraries or libraries that can be pulled from the Spark runtime, then it would be easier. > I believe we still need to update the IcebergSource to handle custom (Iceberg) catalogs right? Yes, we will need to come up with a way for IcebergSource to work with custom catalogs. Spark has a way for the source to return a catalog and identifier that is used instead of the source directly. That's a much better model, but the problem is that we don't necessarily know what the catalog should be. And, if we redirect to a catalog, we will need to also have a catalog that can load Hadoop tables from a URI. I think this is more of a follow-up. ---------------------------------------------------------------- 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]
