lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-1040] Make Hudi support Spark 3 (#2208)

Browse Source 
* Fix flaky MOR unit test

* Update Spark APIs to make it be compatible with both spark2 & spark3

* Refactor bulk insert v2 part to make Hudi be able to compile with Spark3

* Add spark3 profile to handle fasterxml & spark version

* Create hudi-spark-common module & refactor hudi-spark related modules

Co-authored-by: Wenning Ding <wenningd@amazon.com>
This commit is contained in:
wenningd
2020-12-09 15:52:23 -08:00
committed by GitHub
parent 3a91d26d62
commit fce1453fa6
79 changed files with 1040 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
hudi-integ-test/src/main/java/org/apache/hudi/integ/testsuite/reader/SparkBasedReader.java
View File

@@ -20,7 +20,7 @@ package org.apache.hudi.integ.testsuite.reader;
import java.util.List;
import org.apache.avro.generic.GenericRecord;
import org.apache.hudi.AvroConversionUtils;
import org.apache.hudi.HoodieSparkUtils;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.utilities.schema.RowBasedSchemaProvider;
import org.apache.spark.api.java.JavaRDD;
@@ -49,7 +49,7 @@ public class SparkBasedReader {
.option(AVRO_SCHEMA_OPTION_KEY, schemaStr)
.load(JavaConverters.asScalaIteratorConverter(listOfPaths.iterator()).asScala().toSeq());
return AvroConversionUtils
return HoodieSparkUtils
.createRdd(dataSet.toDF(), structName.orElse(RowBasedSchemaProvider.HOODIE_RECORD_STRUCT_NAME),
nameSpace.orElse(RowBasedSchemaProvider.HOODIE_RECORD_NAMESPACE))
.toJavaRDD();
@@ -61,7 +61,7 @@ public class SparkBasedReader {
Dataset<Row> dataSet = sparkSession.read()
.parquet((JavaConverters.asScalaIteratorConverter(listOfPaths.iterator()).asScala().toSeq()));
return AvroConversionUtils
return HoodieSparkUtils
.createRdd(dataSet.toDF(), structName.orElse(RowBasedSchemaProvider.HOODIE_RECORD_STRUCT_NAME),
RowBasedSchemaProvider.HOODIE_RECORD_NAMESPACE)
.toJavaRDD();