Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1352#discussion_r138558167
--- Diff:
integration/spark2/src/main/scala/org/apache/spark/sql/CarbonSource.scala ---
@@ -205,19 +220,188 @@ class CarbonSource extends CreatableRelationProvider
with RelationProvider
* by setting the output committer class in the conf of
spark.sql.sources.outputCommitterClass.
*/
def prepareWrite(
- sparkSession: SparkSession,
- job: Job,
- options: Map[String, String],
- dataSchema: StructType): OutputWriterFactory = new
CarbonStreamingOutputWriterFactory()
+ sparkSession: SparkSession,
+ job: Job,
+ options: Map[String, String],
+ dataSchema: StructType): OutputWriterFactory = {
-/**
- * When possible, this method should return the schema of the given
`files`. When the format
- * does not support inference, or no valid files are given should return
None. In these cases
- * Spark will require that user specify the schema manually.
- */
+ // Check if table with given path exists
+ validateTable(options.get("path").get)
+
+ // Check id streaming data schema matches with carbon table schema
+ // Data from socket source does not have schema attached to it,
+ // Following check is to ignore schema validation for socket source.
+ if (!(dataSchema.size.equals(1) &&
--- End diff --
why not equal to 1?
---
