Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/16826#discussion_r103062718
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/internal/SessionState.scala ---
@@ -65,22 +82,118 @@ private[sql] class SessionState(sparkSession:
SparkSession) {
hadoopConf
}
- lazy val experimentalMethods = new ExperimentalMethods
-
/**
- * Internal catalog for managing functions registered by the user.
+ * Get an identical copy of the `SessionState` and associate it with the
given `SparkSession`
*/
- lazy val functionRegistry: FunctionRegistry =
FunctionRegistry.builtin.copy()
+ def clone(newSparkSession: SparkSession): SessionState = {
+ val sparkContext = newSparkSession.sparkContext
+ val confCopy = conf.clone()
+ val functionRegistryCopy = functionRegistry.clone()
+ val sqlParser: ParserInterface = new SparkSqlParser(confCopy)
+ val catalogCopy = catalog.clone(
+ confCopy,
+ SessionState.newHadoopConf(sparkContext.hadoopConfiguration,
confCopy),
+ functionRegistryCopy,
+ sqlParser)
+ val queryExecutionCreator = (plan: LogicalPlan) => new
QueryExecution(newSparkSession, plan)
+
+ SessionState.mergeSparkConf(confCopy, sparkContext.getConf)
+
+ new SessionState(
+ sparkContext,
+ newSparkSession.sharedState,
+ confCopy,
+ experimentalMethods.clone(),
+ functionRegistryCopy,
+ catalogCopy,
+ sqlParser,
+ SessionState.createAnalyzer(newSparkSession, catalogCopy, confCopy),
+ new StreamingQueryManager(newSparkSession),
+ queryExecutionCreator)
+ }
+
+ // ------------------------------------------------------
+ // Helper methods, partially leftover from pre-2.0 days
+ // ------------------------------------------------------
+
+ def executePlan(plan: LogicalPlan): QueryExecution =
queryExecutionCreator(plan)
+
+ def refreshTable(tableName: String): Unit = {
+ catalog.refreshTable(sqlParser.parseTableIdentifier(tableName))
+ }
+
+ def addJar(path: String): Unit = sharedState.addJar(path)
+}
+
+
+object SessionState {
+
+ def apply(sparkSession: SparkSession): SessionState = {
+ apply(sparkSession, None)
+ }
+
+ def apply(
+ sparkSession: SparkSession,
+ conf: Option[SQLConf]): SessionState = {
+
+ val sparkContext = sparkSession.sparkContext
+
+ // SQL-specific key-value configurations.
+ val sqlConf = conf.getOrElse(new SQLConf)
+
+ // Automatically extract all entries and put them in our SQLConf
+ mergeSparkConf(sqlConf, sparkContext.getConf)
+
+ // Internal catalog for managing functions registered by the user.
+ val functionRegistry = FunctionRegistry.builtin.clone()
+
+ // A class for loading resources specified by a function.
+ val functionResourceLoader: FunctionResourceLoader =
+ createFunctionResourceLoader(sparkContext, sparkSession.sharedState)
+
+ // Parser that extracts expressions, plans, table identifiers etc.
from SQL texts.
+ val sqlParser: ParserInterface = new SparkSqlParser(sqlConf)
+
+ // Internal catalog for managing table and database states.
+ val catalog = new SessionCatalog(
+ sparkSession.sharedState.externalCatalog,
+ sparkSession.sharedState.globalTempViewManager,
+ functionResourceLoader,
+ functionRegistry,
+ sqlConf,
+ newHadoopConf(sparkContext.hadoopConfiguration, sqlConf),
+ sqlParser)
+
+ // Logical query plan analyzer for resolving unresolved attributes and
relations.
+ val analyzer: Analyzer = createAnalyzer(sparkSession, catalog, sqlConf)
+
+ // Interface to start and stop [[StreamingQuery]]s.
+ val streamingQueryManager: StreamingQueryManager = new
StreamingQueryManager(sparkSession)
+
+ val queryExecutionCreator = (plan: LogicalPlan) => new
QueryExecution(sparkSession, plan)
+
+ new SessionState(
+ sparkContext,
+ sparkSession.sharedState,
+ sqlConf,
+ new ExperimentalMethods,
+ functionRegistry,
+ catalog,
+ sqlParser,
+ analyzer,
+ streamingQueryManager,
+ queryExecutionCreator)
+ }
+
+ def createFunctionResourceLoader(
--- End diff --
private
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
