Github user vanzin commented on a diff in the pull request: https://github.com/apache/spark/pull/5876#discussion_r29906552 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala --- @@ -93,9 +100,113 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { protected[sql] def convertCTAS: Boolean = getConf("spark.sql.hive.convertCTAS", "false").toBoolean + /** + * The version of the hive client that will be used to communicate with the metastore. Note that + * this does not necessarily need to be the same version of Hive that is used internally by + * Spark SQL for execution. + */ + protected[hive] def hiveMetastoreVersion: String = + getConf(HIVE_METASTORE_VERSION, hiveExecutionVersion) + + /** + * The location of the jars that should be used to instantiate the HiveMetastoreClient. This + * property can be one of three options: + * - a classpath in the standard format for both hive and hadoop. + * - builtin - attempt to discover the jars that were used to load Spark SQL and use those. This + * option is only valid when using the execution version of Hive. + * - maven - download the correct version of hive on demand from maven. + */ + protected[hive] def hiveMetastoreJars: String = + getConf(HIVE_METASTORE_JARS, "builtin") + @transient protected[sql] lazy val substitutor = new VariableSubstitution() + /** + * The copy of the hive client that is used for execution. Currently this must always be + * Hive 13 as this is the version of Hive that is packaged with Spark SQL. This copy of the + * client is used for execution related tasks like registering temporary functions or ensuring + * that the ThreadLocal SessionState is correctly populated. This copy of Hive is *not* used + * for storing peristent metadata, and only point to a dummy metastore in a temporary directory. + */ + @transient + protected[hive] lazy val executionHive: ClientWrapper = { + logInfo(s"Initilizing execution hive, version $hiveExecutionVersion") + new ClientWrapper( + version = IsolatedClientLoader.hiveVersion(hiveExecutionVersion), + config = newTemporaryConfiguration()) + } + SessionState.setCurrentSessionState(executionHive.state) + + /** + * The copy of the Hive client that is used to retrieve metadata from the Hive MetaStore. + * The version of the Hive client that is used here must match the metastore that is configured + * in the hive-site.xml file. + */ + @transient + protected[hive] lazy val metadataHive: ClientInterface = { + val metaVersion = IsolatedClientLoader.hiveVersion(hiveMetastoreVersion) + + // We instantiate a HiveConf here to read in the hive-site.xml file and then pass the options + // into the isolated client loader + val metadataConf = new HiveConf() + // `configure` goes second to override other settings. + val allConfig = metadataConf.iterator.map(e => e.getKey -> e.getValue).toMap ++ configure + + val isolatedLoader = if (hiveMetastoreJars == "builtin") { + if (hiveExecutionVersion != hiveMetastoreVersion) { + throw new IllegalArgumentException( + "Builtin jars can only be used when hive execution version == hive metastore version. " + + s"Execution: ${hiveExecutionVersion} != Metastore: ${hiveMetastoreVersion}. " + + "Specify a vaild path to the correct hive jars using $HIVE_METASTORE_JARS " + + s"or change $HIVE_METASTORE_VERSION to $hiveExecutionVersion.") + } + val jars = getClass.getClassLoader match { + case urlClassLoader: java.net.URLClassLoader => urlClassLoader.getURLs + case other => + throw new IllegalArgumentException( + "Unable to locate hive jars to connect to metastore " + + s"using classloader ${other.getClass.getName}. " + + "Please set spark.sql.hive.metastore.jars") + } + + logInfo( + s"Initializing HiveMetastoreConnection version $hiveMetastoreVersion using Spark classes.") + new IsolatedClientLoader( + version = metaVersion, + execJars = jars.toSeq, + config = allConfig, + isolationOn = true) + } else if (hiveMetastoreJars == "maven") { + // TODO: Support for loading the jars from an already downloaded location. + logInfo( + s"Initializing HiveMetastoreConnection version $hiveMetastoreVersion using maven.") + IsolatedClientLoader.forVersion(hiveMetastoreVersion, allConfig ) + } else { + // Convert to files and expand any directories. + val jars = + hiveMetastoreJars + .split(File.pathSeparator) + .flatMap { + case path if path.endsWith("*") => --- End diff -- If you want to be really, really correct here, probably should be: case path if new File(path).getName() == "*" => new File(path).getParentFile().listFiles().filter(_.getName().toLower().endsWith(".jar")) Also, should probably check whether the parent directory actually exists, otherwise you'll get an NPE since `listFiles()` will return `null`.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org