Github user squito commented on a diff in the pull request:
https://github.com/apache/spark/pull/7004#discussion_r34585666
--- Diff:
core/src/test/scala/org/apache/spark/serializer/GenericAvroSerializerSuite.scala
---
@@ -0,0 +1,83 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.serializer
+
+import java.io.{ByteArrayInputStream, ByteArrayOutputStream, OutputStream}
+import java.nio.ByteBuffer
+
+import com.esotericsoftware.kryo.io.{Output, Input}
+import org.apache.avro.generic.GenericData.Record
+import org.apache.avro.{SchemaBuilder, Schema}
+import org.apache.spark.{SparkFunSuite, SharedSparkContext}
+
+class GenericAvroSerializerSuite extends SparkFunSuite with
SharedSparkContext {
+ conf.set("spark.serializer",
"org.apache.spark.serializer.KryoSerializer")
+
+ val schema : Schema = SchemaBuilder
+ .record("testRecord").fields()
+ .requiredString("data")
+ .endRecord()
+ val record = new Record(schema)
+ record.put("data", "test data")
+
+ test("schema compression and decompression") {
+ val genericSer = new GenericAvroSerializer(conf.getAvroSchema)
+ assert(schema ===
genericSer.decompress(ByteBuffer.wrap(genericSer.compress(schema))))
+ }
+
+ test("record serialization and deserialization") {
+ val genericSer = new GenericAvroSerializer(conf.getAvroSchema)
+
+ val outputStream = new ByteArrayOutputStream()
+ val output = new Output(outputStream)
+ genericSer.serializeDatum(record, output)
+ output.flush()
+ output.close()
+
+ val input = new Input(new
ByteArrayInputStream(outputStream.toByteArray))
+ assert(genericSer.deserializeDatum(input) === record)
+ }
+
+ test("uses schema fingerprint to decrease message size") {
+ val genericSerFull = new GenericAvroSerializer(conf.getAvroSchema)
+
+ val output = new Output(new ByteArrayOutputStream())
+
+ val beginningNormalPosition = output.total()
+ genericSerFull.serializeDatum(record, output)
+ output.flush()
+ val normalLength = output.total - beginningNormalPosition
+
+ conf.registerAvroSchema(Array(schema))
--- End diff --
if you switch to varargs this could just be
`conf.registerAvroSchema(schema)`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
