HeartSaVioR commented on a change in pull request #29767:
URL: https://github.com/apache/spark/pull/29767#discussion_r490662104
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala
##########
@@ -300,54 +301,44 @@ final class DataStreamWriter[T] private[sql](ds:
Dataset[T]) {
"write files of Hive data source directly.")
}
- if (source == "memory") {
+ if (source == SOURCE_NAME_TABLE) {
+ assertNotPartitioned("table")
+
+ import df.sparkSession.sessionState.analyzer.CatalogAndIdentifier
+
+ import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._
+ val CatalogAndIdentifier(catalog, identifier) =
df.sparkSession.sessionState.sqlParser
+ .parseMultipartIdentifier(tableName)
+ val tableInstance = catalog.asTableCatalog.loadTable(identifier)
+
+ import
org.apache.spark.sql.execution.datasources.v2.DataSourceV2Implicits._
+ val sink = tableInstance match {
+ case t: SupportsWrite if t.supports(STREAMING_WRITE) => t
+ case t => throw new AnalysisException("Table doesn't support streaming
" +
+ s"write - $t")
+ }
+
+ startQuery(sink, extraOptions)
+ } else if (source == "memory") {
assertNotPartitioned("memory")
if (extraOptions.get("queryName").isEmpty) {
throw new AnalysisException("queryName must be specified for memory
sink")
}
val sink = new MemorySink()
val resultDf = Dataset.ofRows(df.sparkSession, new MemoryPlan(sink,
df.schema.toAttributes))
- val chkpointLoc = extraOptions.get("checkpointLocation")
val recoverFromChkpoint = outputMode == OutputMode.Complete()
- val query =
df.sparkSession.sessionState.streamingQueryManager.startQuery(
- extraOptions.get("queryName"),
- chkpointLoc,
- df,
- extraOptions.toMap,
- sink,
- outputMode,
- useTempCheckpointLocation = true,
- recoverFromCheckpointLocation = recoverFromChkpoint,
- trigger = trigger)
- resultDf.createOrReplaceTempView(query.name)
- query
+ startQuery(sink, extraOptions, Some(resultDf), recoverFromCheckpoint =
recoverFromChkpoint)
} else if (source == "foreach") {
assertNotPartitioned("foreach")
val sink = ForeachWriterTable[T](foreachWriter, ds.exprEnc)
- df.sparkSession.sessionState.streamingQueryManager.startQuery(
- extraOptions.get("queryName"),
- extraOptions.get("checkpointLocation"),
- df,
- extraOptions.toMap,
- sink,
- outputMode,
- useTempCheckpointLocation = true,
- trigger = trigger)
+ startQuery(sink, extraOptions)
} else if (source == "foreachBatch") {
Review comment:
Ah I missed after doing another approach of refactoring. I'll fix.
Thanks!
----------------------------------------------------------------
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]
