Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[HUDI-8298] refactor SparkDatasetTestUtils#serializeRow #12620

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[HUDI-8298] refactor SparkDatasetTestUtils#serializeRow #12620

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 7 additions & 11 deletions ...urce/hudi-spark-common/src/test/java/org/apache/hudi/testutils/SparkDatasetTestUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
import org.apache.hudi.config.HoodieWriteConfig;
import org.apache.hudi.index.HoodieIndex;

import org.apache.spark.package$;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SQLContext;
Expand Down Expand Up @@ -237,17 +236,14 @@ public static HoodieWriteConfig.Builder getConfigBuilder(String basePath, int ti
.withBulkInsertParallelism(2);
}

private static InternalRow serializeRow(ExpressionEncoder encoder, Row row)
public static InternalRow serializeRow(ExpressionEncoder encoder, Row row)
throws InvocationTargetException, IllegalAccessException, NoSuchMethodException, ClassNotFoundException {
// TODO [HUDI-8298] only spark 3 needed
if (package$.MODULE$.SPARK_VERSION().startsWith("2.")) {
Method spark2method = encoder.getClass().getMethod("toRow", Object.class);
return (InternalRow) spark2method.invoke(encoder, row);
} else {
Class<?> serializerClass = Class.forName("org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$Serializer");
Object serializer = encoder.getClass().getMethod("createSerializer").invoke(encoder);
Method aboveSpark2method = serializerClass.getMethod("apply", Object.class);
return (InternalRow) aboveSpark2method.invoke(serializer, row);
Object serializer = encoder.createSerializer();
try {
Method applyMethod = serializer.getClass().getMethod("apply", Object.class);
return (InternalRow) applyMethod.invoke(serializer, row);
} catch (Exception e) {
throw new RuntimeException("Failed to serialize row", e);
}
}
}
21 changes: 2 additions & 19 deletions ...asource/hudi-spark/src/test/java/org/apache/hudi/testutils/KeyGeneratorTestUtilities.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,13 @@
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericRecord;
import org.apache.spark.package$;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder;
import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema;
import org.apache.spark.sql.types.StructType;

import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;

import scala.Function1;

Expand Down Expand Up @@ -101,21 +99,6 @@ private static ExpressionEncoder getEncoder(StructType schema) {
}

public static InternalRow getInternalRow(Row row, ExpressionEncoder<Row> encoder) throws ClassNotFoundException, InvocationTargetException, IllegalAccessException, NoSuchMethodException {
return serializeRow(encoder, row);
return SparkDatasetTestUtils.serializeRow(encoder, row);
}

private static InternalRow serializeRow(ExpressionEncoder encoder, Row row)
throws InvocationTargetException, IllegalAccessException, NoSuchMethodException, ClassNotFoundException {
// TODO [HUDI-8298] only spark 3 needed
if (package$.MODULE$.SPARK_VERSION().startsWith("2.")) {
Method spark2method = encoder.getClass().getMethod("toRow", Object.class);
return (InternalRow) spark2method.invoke(encoder, row);
} else {
Class<?> serializerClass = Class.forName("org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$Serializer");
Object serializer = encoder.getClass().getMethod("createSerializer").invoke(encoder);
Method aboveSpark2method = serializerClass.getMethod("apply", Object.class);
return (InternalRow) aboveSpark2method.invoke(serializer, row);
}
}

}
}