Github user gengliangwang commented on a diff in the pull request:
https://github.com/apache/spark/pull/22878#discussion_r230041592
--- Diff:
external/avro/src/main/scala/org/apache/spark/sql/avro/AvroEncoder.scala ---
@@ -0,0 +1,533 @@
+/*
+ * 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.sql.avro
+
+import java.io._
+import java.util.{Map => JMap}
+
+import scala.collection.JavaConverters._
+import scala.language.existentials
+import scala.reflect.ClassTag
+
+import org.apache.avro.Schema
+import org.apache.avro.Schema.Parser
+import org.apache.avro.Schema.Type._
+import org.apache.avro.generic.{GenericData, IndexedRecord}
+import org.apache.avro.reflect.ReflectData
+import org.apache.avro.specific.SpecificRecord
+
+import org.apache.spark.sql.Encoder
+import org.apache.spark.sql.avro.SchemaConverters._
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.analysis.{GetColumnByOrdinal,
UnresolvedExtractValue}
+import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.codegen._
+import org.apache.spark.sql.catalyst.expressions.codegen.Block._
+import org.apache.spark.sql.catalyst.expressions.objects.{LambdaVariable
=> _, _}
+import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData,
GenericArrayData}
+import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
+
+/**
+ * A Spark-SQL Encoder for Avro objects
+ */
+object AvroEncoder {
+ /**
+ * Provides an Encoder for Avro objects of the given class
+ *
+ * @param avroClass the class of the Avro object for which to generate
the Encoder
+ * @tparam T the type of the Avro class, must implement SpecificRecord
+ * @return an Encoder for the given Avro class
+ */
+ def of[T <: SpecificRecord](avroClass: Class[T]): Encoder[T] = {
+ AvroExpressionEncoder.of(avroClass)
+ }
+ /**
+ * Provides an Encoder for Avro objects implementing the given schema
+ *
+ * @param avroSchema the Schema of the Avro object for which to generate
the Encoder
+ * @tparam T the type of the Avro class that implements the Schema, must
implement IndexedRecord
+ * @return an Encoder for the given Avro Schema
+ */
+ def of[T <: IndexedRecord](avroSchema: Schema): Encoder[T] = {
--- End diff --
In `from_avro`, we are using avro schema in json format string, should we
consider change to that?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
