wangxianghu commented on a change in pull request #3488:
URL: https://github.com/apache/hudi/pull/3488#discussion_r690429555
##########
File path:
hudi-examples/src/main/scala/org/apache/hudi/examples/spark/HoodieDataSourceExample.scala
##########
@@ -129,6 +130,43 @@ object HoodieDataSourceExample {
save(tablePath)
}
+ /**
+ * Deleta data based in data information
+ */
+ def delete(spark: SparkSession, tablePath: String, tableName: String): Unit
= {
+
+ val roViewDF = spark.read.format("org.apache.hudi").load(tablePath +
"/*/*/*/*")
+ roViewDF.createOrReplaceTempView("hudi_ro_table")
+ val df = spark.sql("select uuid, partitionpath, ts from hudi_ro_table
limit 2")
+
+ df.write.format("org.apache.hudi").
+ options(getQuickstartWriteConfigs).
+ option(PRECOMBINE_FIELD.key, "ts").
+ option(RECORDKEY_FIELD.key, "uuid").
+ option(PARTITIONPATH_FIELD.key, "partitionpath").
+ option(TABLE_NAME.key, tableName).
+ option(OPERATION.key, DELETE_OPERATION_OPT_VAL).
+ mode(Append).
+ save(tablePath)
+ }
+
+ /**
+ * Delete the data of a single or multiple partitions
Review comment:
same here
--
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]
