rdblue commented on a change in pull request #529: Add hadoop table catalog (WIP) URL: https://github.com/apache/incubator-iceberg/pull/529#discussion_r344528836
########## File path: core/src/main/java/org/apache/iceberg/hadoop/HadoopCatalog.java ########## @@ -0,0 +1,170 @@ +/* + * 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.hadoop; + +import com.google.common.base.Joiner; +import com.google.common.base.Preconditions; +import java.io.Closeable; +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.Map; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.iceberg.BaseMetastoreCatalog; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.exceptions.AlreadyExistsException; +import org.apache.iceberg.exceptions.RuntimeIOException; + +/** + * The HadoopCatalog provides a way to manage the path-based table just like catalog. It uses + * a specified directory under a specified filesystem as the warehouse directory, and organizes + * two levels directories that mapped to the database and the table respectively. The HadoopCatalog + * takes a URI as its root directory, and creates a child directory "iceberg/warehouse" as the + * warehouse directory. When creating a table such as $db.$tbl, it creates $db.db/$tbl under + * iceberg/warehouse, and put the table metadata into the directory. + * + * The HadoopCatalog now supports createtable, droptable, the renametable is not supported yet. + * + * Note: The HadoopCatalog requires the rename operation of the filesystem is an atomic operation. + */ +public class HadoopCatalog extends BaseMetastoreCatalog implements Closeable { + private static final String ICEBERG_HADOOP_WAREHOUSE_BASE = "iceberg/warehouse"; + private final Configuration conf; + private String warehouseUri; + + public HadoopCatalog(Configuration conf, String warehouseUri) { + this.conf = conf; + + if (warehouseUri != null) { + this.warehouseUri = warehouseUri; + } else { + String fsRoot = conf.get("fs.defaultFS"); + Path warehousePath = new Path(fsRoot, ICEBERG_HADOOP_WAREHOUSE_BASE); + try { + FileSystem fs = Util.getFs(warehousePath, conf); + if (!fs.isDirectory(warehousePath)) { + if (!fs.mkdirs(warehousePath)) { + throw new IOException("failed to create warehouse for hadoop catalog"); + } + } + this.warehouseUri = fsRoot + "/" + ICEBERG_HADOOP_WAREHOUSE_BASE; + } catch (IOException e) { + throw new RuntimeIOException("failed to create directory for warehouse", e); + } + } + } + + public HadoopCatalog(Configuration conf) { + this(conf, null); + } + + @Override + public org.apache.iceberg.Table createTable( + TableIdentifier identifier, Schema schema, PartitionSpec spec, Map<String, String> properties) { Review comment: I think this catalog should implement the `createTable` variant with `location` and then validate that the location is `null` with a `Precondition`: ```java Preconditions.checkArgument(location == null, "Cannot set a custom location for a path-based table"); ``` ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
