HeartSaVioR commented on a change in pull request #27637: [SPARK-30874][SQL] Support Postgres Kerberos login in JDBC connector URL: https://github.com/apache/spark/pull/27637#discussion_r382573139
########## File path: external/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/PostgresKrbIntegrationSuite.scala ########## @@ -0,0 +1,117 @@ +/* + * 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.spark.sql.jdbc + +import java.io.{File, FileInputStream, FileOutputStream} +import java.sql.Connection +import java.util.Properties + +import scala.io.Source + +import com.spotify.docker.client.messages.{ContainerConfig, HostConfig} +import javax.security.auth.login.Configuration + +import org.apache.spark.sql.Row +import org.apache.spark.sql.types.StringType +import org.apache.spark.tags.DockerTest + +@DockerTest +class PostgresKrbIntegrationSuite extends DockerKrbJDBCIntegrationSuite { + override protected val userName = s"postgres/$dockerIp" + override protected val keytabFileName = "postgres.keytab" + + override val db = new DatabaseOnDocker { + override val imageName = "postgres:12.0" + override val env = Map( + "POSTGRES_PASSWORD" -> "rootpass" + ) + override val usesIpc = false + override val jdbcPort = 5432 + + override def getJdbcUrl(ip: String, port: Int): String = + s"jdbc:postgresql://$ip:$port/postgres?user=$principal&gsslib=gssapi" + + override def getStartupProcessName: Option[String] = None + + override def beforeContainerStart(hostConfigBuilder: HostConfig.Builder, + containerConfigBuilder: ContainerConfig.Builder): Unit = { + def replaceIp(s: String): String = s.replace("__IP_ADDRESS_REPLACE_ME__", dockerIp) + copyExecutableResource("postgres_krb_setup.sh", workDir, replaceIp) + + hostConfigBuilder.appendBinds( + HostConfig.Bind.from(workDir.getAbsolutePath) + .to("/docker-entrypoint-initdb.d").readOnly(true).build() + ) + } + } + + override def dataPreparation(conn: Connection): Unit = { + conn.prepareStatement("CREATE DATABASE foo").executeUpdate() + conn.setCatalog("foo") + conn.prepareStatement("CREATE TABLE bar (c0 text)").executeUpdate() + conn.prepareStatement("INSERT INTO bar VALUES ('hello')").executeUpdate() + } + + test("Basic read test") { + // This makes sure Spark must do authentication + Configuration.setConfiguration(null) + + val expectedResult = Set("hello").map(Row(_)) + + val query = "SELECT c0 FROM bar" + // query option to pass on the query string. + val df = spark.read.format("jdbc") + .option("url", jdbcUrl) + .option("keytab", keytabFile.getAbsolutePath) + .option("principal", principal) + .option("query", query) + .load() + assert(df.collect().toSet === expectedResult) + + // query option in the create table path. + sql( + s""" + |CREATE OR REPLACE TEMPORARY VIEW queryOption + |USING org.apache.spark.sql.jdbc + |OPTIONS (url '$jdbcUrl', query '$query') + """.stripMargin.replaceAll("\n", " ")) + assert(sql("select c0 from queryOption").collect().toSet === expectedResult) + } + + test("Basic write test") { + // This makes sure Spark must do authentication + Configuration.setConfiguration(null) + + val props = new Properties + props.setProperty("keytab", keytabFile.getAbsolutePath) + props.setProperty("principal", principal) + + val tableName = "write_test" + sqlContext.createDataFrame(Seq(("foo", "bar"))) + .write.jdbc(jdbcUrl, tableName, props) + val df = sqlContext.read.jdbc(jdbcUrl, tableName, props) + + val schema = df.schema + assert(schema.head.dataType == StringType) Review comment: If below line works then it would check the same + column count as well in one-liner. `assert(schema.map(_.dataType).toSeq === Seq(StringType, StringType))` ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
