ismailsimsek commented on a change in pull request #1870: URL: https://github.com/apache/iceberg/pull/1870#discussion_r641541908
########## File path: core/src/main/java/org/apache/iceberg/jdbc/JdbcCatalog.java ########## @@ -0,0 +1,388 @@ +/* + * 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.jdbc; + +import java.io.Closeable; +import java.sql.DatabaseMetaData; +import java.sql.PreparedStatement; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.sql.SQLIntegrityConstraintViolationException; +import java.sql.SQLNonTransientConnectionException; +import java.sql.SQLTimeoutException; +import java.sql.SQLTransientConnectionException; +import java.util.Arrays; +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.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.hadoop.HadoopFileIO; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.base.Joiner; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class JdbcCatalog extends BaseMetastoreCatalog implements Configurable, SupportsNamespaces, Closeable { + + public static final String PROPERTY_PREFIX = "connection.parameter."; + private static final Logger LOG = LoggerFactory.getLogger(JdbcCatalog.class); + private static final Joiner SLASH = Joiner.on("/"); + + private FileIO io; + private String catalogName = "jdbc"; + private String warehouseLocation; + private Configuration conf; + private JdbcClientPool connections; + + public JdbcCatalog() { + } + + @Override + public void initialize(String name, Map<String, String> properties) { + String uri = properties.get(CatalogProperties.URI); + Preconditions.checkNotNull(uri, "JDBC connection URI is required"); + + String warehouse = properties.get(CatalogProperties.WAREHOUSE_LOCATION); + Preconditions.checkNotNull(warehouse, "JDBC warehouse location is required"); + this.warehouseLocation = warehouse.replaceAll("/$", ""); + + if (name != null) { + this.catalogName = name; + } + + String fileIOImpl = properties.get(CatalogProperties.FILE_IO_IMPL); + this.io = fileIOImpl == null ? new HadoopFileIO(conf) : CatalogUtil.loadFileIO(fileIOImpl, properties, conf); + + try { + LOG.debug("Connecting to Jdbc database {}", properties.get(CatalogProperties.URI)); + connections = new JdbcClientPool(uri, properties); + initializeCatalogTables(); + } catch (SQLTimeoutException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog: Query timed out"); + } catch (SQLTransientConnectionException | SQLNonTransientConnectionException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog: Connection failed"); + } catch (SQLException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog"); + } catch (InterruptedException e) { + Thread.currentThread().interrupt(); + throw new RuntimeException("Interrupted in call to initialize", e); + } + } + + private void initializeCatalogTables() throws InterruptedException, SQLException { + LOG.trace("Creating database tables (if missing) to store iceberg catalog"); + connections.run(conn -> { + DatabaseMetaData dbMeta = conn.getMetaData(); + ResultSet tableExists = dbMeta.getTables(null, null, JdbcUtil.CATALOG_TABLE_NAME, null); + + if (tableExists.next()) { + return true; + } + + LOG.debug("Creating table {} to store iceberg catalog!", JdbcUtil.CATALOG_TABLE_NAME); + return conn.prepareStatement(JdbcUtil.CREATE_CATALOG_TABLE).execute(); + }); + } + + @Override + protected TableOperations newTableOps(TableIdentifier tableIdentifier) { + return new JdbcTableOperations(connections, io, catalogName, tableIdentifier); + } + + @Override + protected String defaultWarehouseLocation(TableIdentifier table) { + return SLASH.join(defaultNamespaceLocation(table.namespace()), table.name()); + } + + @Override + public boolean dropTable(TableIdentifier identifier, boolean purge) { + + int deletedRecords; + try { + deletedRecords = connections.run(conn -> { + try (PreparedStatement sql = conn.prepareStatement(JdbcUtil.DROP_TABLE_SQL)) { + sql.setString(1, catalogName); + sql.setString(2, JdbcUtil.namespaceToString(identifier.namespace())); + sql.setString(3, identifier.name()); + return sql.executeUpdate(); + } + }); + } catch (SQLException e) { + throw new UncheckedSQLException(e, "Failed to drop %s", identifier); + } catch (InterruptedException e) { + Thread.currentThread().interrupt(); + throw new RuntimeException("Interrupted in call to dropTable", e); + } + + if (deletedRecords > 0) { + LOG.info("Successfully dropped table {}.", identifier); + } else { + LOG.info("Cannot drop table: {}! table not found in the catalog.", identifier); + return false; + } + + TableOperations ops = newTableOps(identifier); Review comment: moved it to begining and aligned with hive ########## File path: core/src/main/java/org/apache/iceberg/jdbc/JdbcCatalog.java ########## @@ -0,0 +1,388 @@ +/* + * 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.jdbc; + +import java.io.Closeable; +import java.sql.DatabaseMetaData; +import java.sql.PreparedStatement; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.sql.SQLIntegrityConstraintViolationException; +import java.sql.SQLNonTransientConnectionException; +import java.sql.SQLTimeoutException; +import java.sql.SQLTransientConnectionException; +import java.util.Arrays; +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.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.hadoop.HadoopFileIO; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.base.Joiner; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class JdbcCatalog extends BaseMetastoreCatalog implements Configurable, SupportsNamespaces, Closeable { + + public static final String PROPERTY_PREFIX = "connection.parameter."; + private static final Logger LOG = LoggerFactory.getLogger(JdbcCatalog.class); + private static final Joiner SLASH = Joiner.on("/"); + + private FileIO io; + private String catalogName = "jdbc"; + private String warehouseLocation; + private Configuration conf; + private JdbcClientPool connections; + + public JdbcCatalog() { + } + + @Override + public void initialize(String name, Map<String, String> properties) { + String uri = properties.get(CatalogProperties.URI); + Preconditions.checkNotNull(uri, "JDBC connection URI is required"); + + String warehouse = properties.get(CatalogProperties.WAREHOUSE_LOCATION); + Preconditions.checkNotNull(warehouse, "JDBC warehouse location is required"); + this.warehouseLocation = warehouse.replaceAll("/$", ""); + + if (name != null) { + this.catalogName = name; + } + + String fileIOImpl = properties.get(CatalogProperties.FILE_IO_IMPL); + this.io = fileIOImpl == null ? new HadoopFileIO(conf) : CatalogUtil.loadFileIO(fileIOImpl, properties, conf); + + try { + LOG.debug("Connecting to Jdbc database {}", properties.get(CatalogProperties.URI)); + connections = new JdbcClientPool(uri, properties); + initializeCatalogTables(); + } catch (SQLTimeoutException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog: Query timed out"); + } catch (SQLTransientConnectionException | SQLNonTransientConnectionException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog: Connection failed"); + } catch (SQLException e) { + throw new UncheckedSQLException(e, "Cannot initialize jdbc catalog"); + } catch (InterruptedException e) { + Thread.currentThread().interrupt(); + throw new RuntimeException("Interrupted in call to initialize", e); + } + } + + private void initializeCatalogTables() throws InterruptedException, SQLException { + LOG.trace("Creating database tables (if missing) to store iceberg catalog"); + connections.run(conn -> { + DatabaseMetaData dbMeta = conn.getMetaData(); + ResultSet tableExists = dbMeta.getTables(null, null, JdbcUtil.CATALOG_TABLE_NAME, null); + + if (tableExists.next()) { + return true; + } + + LOG.debug("Creating table {} to store iceberg catalog!", JdbcUtil.CATALOG_TABLE_NAME); + return conn.prepareStatement(JdbcUtil.CREATE_CATALOG_TABLE).execute(); + }); + } + + @Override + protected TableOperations newTableOps(TableIdentifier tableIdentifier) { + return new JdbcTableOperations(connections, io, catalogName, tableIdentifier); + } + + @Override + protected String defaultWarehouseLocation(TableIdentifier table) { + return SLASH.join(defaultNamespaceLocation(table.namespace()), table.name()); + } + + @Override + public boolean dropTable(TableIdentifier identifier, boolean purge) { + + int deletedRecords; + try { + deletedRecords = connections.run(conn -> { + try (PreparedStatement sql = conn.prepareStatement(JdbcUtil.DROP_TABLE_SQL)) { + sql.setString(1, catalogName); + sql.setString(2, JdbcUtil.namespaceToString(identifier.namespace())); + sql.setString(3, identifier.name()); + return sql.executeUpdate(); + } + }); + } catch (SQLException e) { + throw new UncheckedSQLException(e, "Failed to drop %s", identifier); + } catch (InterruptedException e) { + Thread.currentThread().interrupt(); + throw new RuntimeException("Interrupted in call to dropTable", e); + } + + if (deletedRecords > 0) { + LOG.info("Successfully dropped table {}.", identifier); + } else { + LOG.info("Cannot drop table: {}! table not found in the catalog.", identifier); + return false; + } + + TableOperations ops = newTableOps(identifier); Review comment: moved it to beginning and aligned with hive -- 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]
