msamirkhan commented on a change in pull request #29354: URL: https://github.com/apache/spark/pull/29354#discussion_r465989873
########## File path: external/avro/src/main/scala/org/apache/spark/sql/avro/SparkAvroDatumReader.scala ########## @@ -0,0 +1,811 @@ +/* + * 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.IOException +import java.math.BigDecimal +import java.nio.ByteBuffer + +import scala.collection.JavaConverters._ +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +import org.apache.avro.{LogicalTypes, Schema, SchemaBuilder} +import org.apache.avro.Conversions.DecimalConversion +import org.apache.avro.LogicalTypes.{TimestampMicros, TimestampMillis} +import org.apache.avro.Schema.Type._ +import org.apache.avro.generic.{GenericDatumReader, GenericFixed} +import org.apache.avro.io.ResolvingDecoder +import org.apache.avro.util.Utf8 + +import org.apache.spark.sql.catalyst.{InternalRow, NoopFilters, StructFilters} +import org.apache.spark.sql.catalyst.expressions.{MutableAny, MutableBoolean, MutableByte, + MutableDouble, MutableFloat, MutableInt, MutableLong, MutableShort, MutableValue, + SpecificInternalRow, UnsafeArrayData} +import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, ArrayData, DateTimeUtils, + GenericArrayData} +import org.apache.spark.sql.catalyst.util.DateTimeConstants.MILLIS_PER_DAY +import org.apache.spark.sql.execution.datasources.DataSourceUtils +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.internal.SQLConf.LegacyBehaviorPolicy +import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.types.UTF8String + +/** + * Reader to read data as catalyst format from avro decoders. Multiple calls + * return the same [[InternalRow]] object. If needed, caller should copy before making a new call. + * + * @param actual + * @param expected + * @param rootCatalystType + * @param datetimeRebaseMode + * @tparam T + */ +class SparkAvroDatumReader[T]( Review comment: This commit moves to using native reader for avro files. Previously we had Decoder => GenericAvroDatumReader => AvroDeserializer. Now SparkAvroDatumReader reads directly from the Decoder. Array reading performance degraded, which has been fixed in a latter commit. Moving to the native reader also allows us to "skip" reading columns that are not needed. This change is also in a latter commit. Read times can be found in the attached pdf on pg 2 under column D. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
