wankunde commented on a change in pull request #561: [Griffin-315] Adding JDBC based data connector URL: https://github.com/apache/griffin/pull/561#discussion_r361972937
########## File path: measure/src/main/scala/org/apache/griffin/measure/datasource/connector/batch/JDBCBasedDataConnector.scala ########## @@ -0,0 +1,127 @@ +/* + * 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.griffin.measure.datasource.connector.batch + +import org.apache.spark.sql.{DataFrame, SparkSession} + +import org.apache.griffin.measure.Loggable +import org.apache.griffin.measure.configuration.dqdefinition.DataConnectorParam +import org.apache.griffin.measure.context.TimeRange +import org.apache.griffin.measure.datasource.TimestampStorage +import org.apache.griffin.measure.utils.ParamUtil._ + +/** + * A batch data connector for JDBC based source which allows support for various + * JDBC based data sources like Oracle. Postgres etc. + * + * Supported Configurations: + * - database : [[String]] specifying the database name. + * - tablename : [[String]] specifying the table name to be read + * - url : [[String]] specifying the URL to connect to database + * - user : [[String]] specifying the user for connection to database + * - password: [[String]] specifying the password for connection to database + * - driver : [[String]] specifying the driver for JDBC connection to database + * - where : [[String]] specifying the condition for reading data from table + * + * Some defaults assumed by this connector (if not set) are as follows: + * - `database` is default, + * - `driver` is com.mysql.jdbc.Driver, + * - `where` is None + */ +case class JDBCBasedDataConnector( + @transient sparkSession: SparkSession, + dcParam: DataConnectorParam, + timestampStorage: TimestampStorage) + extends BatchDataConnector { + + import JDBCBasedDataConnector._ + val config: Map[String, Any] = dcParam.getConfig + val database: String = config.getString(Database, DefaultDatabase) + val tableName: String = config.getString(TableName, EmptyString) + val fullTableName: String = s"$database.$tableName" + val whereString: String = config.getString(Where, EmptyString) + val url: String = config.getString(Url, EmptyString) + val user: String = config.getString(User, EmptyString) + val password: String = config.getString(Password, EmptyString) + val driver: String = config.getString(Driver, DefaultDriver) + + require(url.nonEmpty, "JDBC connection: connection url is mandatory") + require(user.nonEmpty, "JDBC connection: user name is mandatory") + require(password.nonEmpty, "JDBC connection: password is mandatory") + require(tableName.nonEmpty, "JDBC connection: table is mandatory") + assert(isJDBCDriverLoaded(driver), s"JDBC driver ${driver} not present in classpath") + + override def data(ms: Long): (Option[DataFrame], TimeRange) = { + val dfOpt = try { + val dtSql = createSqlStmt() + val prop = new java.util.Properties + prop.setProperty("user", user) + prop.setProperty("password", password) + prop.setProperty("driver", driver) + val df: DataFrame = sparkSession.read.jdbc(url, s"($dtSql) as t", prop) + val dfOpt = Some(df) + val preDfOpt = preProcess(dfOpt, ms) + preDfOpt + } catch { + case e: Throwable => + error(s"load mysql table $fullTableName fails: ${e.getMessage}", e) Review comment: `mysql` keyword should not be included in error messages. ---------------------------------------------------------------- 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] With regards, Apache Git Services
