teabot commented on a change in pull request #1103: URL: https://github.com/apache/iceberg/pull/1103#discussion_r440028833
########## File path: mr/src/main/java/org/apache/iceberg/mr/mapred/TableResolver.java ########## @@ -0,0 +1,80 @@ +/* + * 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.mr.mapred; + +import java.io.IOException; +import java.util.Properties; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.mapred.JobConf; +import org.apache.iceberg.Table; +import org.apache.iceberg.exceptions.NoSuchTableException; +import org.apache.iceberg.hadoop.HadoopTables; +import org.apache.iceberg.mr.InputFormatConfig; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; + +final class TableResolver { + + private TableResolver() { + } + + static Table resolveTableFromJob(JobConf conf) throws IOException { + Properties properties = new Properties(); + properties.setProperty(InputFormatConfig.CATALOG_NAME, + conf.get(InputFormatConfig.CATALOG_NAME, InputFormatConfig.HADOOP_TABLES)); //Default to HadoopTables + properties.setProperty(InputFormatConfig.SNAPSHOT_TABLE, + conf.get(InputFormatConfig.SNAPSHOT_TABLE, "true")); + properties.setProperty(InputFormatConfig.TABLE_LOCATION, extractProperty(conf, InputFormatConfig.TABLE_LOCATION)); + properties.setProperty(InputFormatConfig.TABLE_NAME, extractProperty(conf, InputFormatConfig.TABLE_NAME)); + return resolveTableFromConfiguration(conf, properties); + } + + static Table resolveTableFromConfiguration(Configuration conf, Properties properties) throws IOException { + String catalogName = properties.getProperty(InputFormatConfig.CATALOG_NAME, InputFormatConfig.HADOOP_TABLES); + String tableLocation = properties.getProperty(InputFormatConfig.TABLE_LOCATION); + String tableName = properties.getProperty(InputFormatConfig.TABLE_NAME); + Preconditions.checkNotNull(tableLocation, "Table location is not set."); + Preconditions.checkNotNull(tableName, "Table name is not set."); + switch (catalogName) { + case InputFormatConfig.HADOOP_TABLES: + HadoopTables tables = new HadoopTables(conf); + if (tableName.endsWith(InputFormatConfig.SNAPSHOT_TABLE_SUFFIX)) { Review comment: I definitely think we should adopt the simplification offered by points 2,3,4. My only concern with point 1, is that it can often be useful to guide users into a good convention by making it a default behaviour. That said, table naming strategies are almost certainly the responsibility of the data lake owner and not the implementation - so perhaps best to drop the reserved suffix also. Thanks for this suggestion. ---------------------------------------------------------------- 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]
