juripetersen commented on code in PR #647:
URL: https://github.com/apache/wayang/pull/647#discussion_r2671331299
##########
wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/DataQuanta.scala:
##########
@@ -1027,6 +1027,12 @@ class DataQuanta[Out: ClassTag](val operator:
ElementaryOperator, outputIndex: I
writeTextFileJava(url, toSerializableFunction(formatterUdf), udfLoad)
}
+ def writeParquet(url: String, overwrite: Boolean = false)(implicit ev: Out
=:= Record): Unit =
Review Comment:
See comment above.
##########
wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/JavaPlanBuilder.scala:
##########
@@ -72,6 +72,16 @@ class JavaPlanBuilder(wayangCtx: WayangContext, jobName:
String) {
def readParquet(url: String, projection: Array[String] = null):
UnarySourceDataQuantaBuilder[UnarySourceDataQuantaBuilder[_, Record], Record] =
createSourceBuilder(ParquetSource.create(url,
projection))(ClassTag(classOf[Record]))
+ /**
+ * Read a parquet file and provide it as a dataset of [[Record]]s backed by
Spark Datasets.
+ *
+ * @param url the URL of the Parquet file
+ * @param projection the projection, if any
+ * @return [[DataQuantaBuilder]] for the file
+ */
+ def readParquetAsDataset(url: String, projection: Array[String] = null):
UnarySourceDataQuantaBuilder[UnarySourceDataQuantaBuilder[_, Record], Record] =
Review Comment:
See comment above.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
