Github user cloud-fan commented on a diff in the pull request:

    https://github.com/apache/spark/pull/21762#discussion_r202502456
  
    --- Diff: 
external/avro/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala 
---
    @@ -0,0 +1,348 @@
    +/*
    + * 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.nio.ByteBuffer
    +
    +import scala.collection.JavaConverters._
    +import scala.collection.mutable.ArrayBuffer
    +
    +import org.apache.avro.{Schema, SchemaBuilder}
    +import org.apache.avro.Schema.Type._
    +import org.apache.avro.generic._
    +import org.apache.avro.util.Utf8
    +
    +import org.apache.spark.sql.catalyst.InternalRow
    +import org.apache.spark.sql.catalyst.expressions.{SpecificInternalRow, 
UnsafeArrayData}
    +import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData, 
DateTimeUtils, GenericArrayData}
    +import org.apache.spark.sql.types._
    +import org.apache.spark.unsafe.types.UTF8String
    +
    +/**
    + * A deserializer to deserialize data in avro format to data in catalyst 
format.
    + */
    +class AvroDeserializer(rootAvroType: Schema, rootCatalystType: DataType) {
    +  private val converter: Any => Any = rootCatalystType match {
    +    // A shortcut for empty schema.
    +    case st: StructType if st.isEmpty =>
    +      (data: Any) => InternalRow.empty
    +
    +    case st: StructType =>
    +      val resultRow = new SpecificInternalRow(st.map(_.dataType))
    +      val fieldUpdater = new RowUpdater(resultRow)
    +      val writer = getRecordWriter(rootAvroType, st, Nil)
    +      (data: Any) => {
    +        val record = data.asInstanceOf[GenericRecord]
    +        writer(fieldUpdater, record)
    +        resultRow
    +      }
    +
    +    case _ =>
    +      val tmpRow = new SpecificInternalRow(Seq(rootCatalystType))
    +      val fieldUpdater = new RowUpdater(tmpRow)
    +      val writer = newWriter(rootAvroType, rootCatalystType, Nil)
    +      (data: Any) => {
    +        writer(fieldUpdater, 0, data)
    +        tmpRow.get(0, rootCatalystType)
    +      }
    +  }
    +
    +  def deserialize(data: Any): Any = converter(data)
    +
    +  /**
    +   * Creates a writer to writer avro values to Catalyst values at the 
given ordinal with the given
    --- End diff --
    
    nit `a writer to write`


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to