[GitHub] [spark] gengliangwang commented on a change in pull request #25017: [SPARK-28218][SQL] Migrate Avro to File Data Source V2

[GitBox <gi...@apache.org>]

gengliangwang commented on a change in pull request #25017: [SPARK-28218][SQL] Migrate Avro to File Data Source V2
URL: https://github.com/apache/spark/pull/25017#discussion_r300553712
 
 

 ##########
 File path: external/avro/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala
 ##########
 @@ -0,0 +1,163 @@
+/*
+ * 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.{FileNotFoundException, IOException}
+
+import org.apache.avro.Schema
+import org.apache.avro.file.DataFileConstants.{BZIP2_CODEC, DEFLATE_CODEC, SNAPPY_CODEC, XZ_CODEC}
+import org.apache.avro.file.DataFileReader
+import org.apache.avro.generic.{GenericDatumReader, GenericRecord}
+import org.apache.avro.mapred.{AvroOutputFormat, FsInput}
+import org.apache.avro.mapreduce.AvroJob
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.FileStatus
+import org.apache.hadoop.mapreduce.Job
+
+import org.apache.spark.SparkException
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.execution.datasources.OutputWriterFactory
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types._
+import org.apache.spark.util.Utils
+
+object AvroUtils extends Logging {
+  def inferSchema(
+      spark: SparkSession,
+      options: Map[String, String],
+      files: Seq[FileStatus]): Option[StructType] = {
+    val conf = spark.sessionState.newHadoopConf()
+    if (options.contains("ignoreExtension")) {
+      logWarning(s"Option ${AvroOptions.ignoreExtensionKey} is deprecated. Please use the " +
+        "general data source option pathGlobFilter for filtering file names.")
+    }
+    val parsedOptions = new AvroOptions(options, conf)
+
+    // User can specify an optional avro json schema.
+    val avroSchema = parsedOptions.schema
+      .map(new Schema.Parser().parse)
+      .getOrElse {
+        inferAvroSchemaFromFiles(files, conf, parsedOptions.ignoreExtension,
+          spark.sessionState.conf.ignoreCorruptFiles)
+      }
+
+    SchemaConverters.toSqlType(avroSchema).dataType match {
+      case t: StructType => Some(t)
+      case _ => throw new RuntimeException(
+        s"""Avro schema cannot be converted to a Spark SQL StructType:
+           |
+           |${avroSchema.toString(true)}
+           |""".stripMargin)
+    }
+  }
+
+  def supportsDataType(dataType: DataType): Boolean = dataType match {
+    case _: AtomicType => true
+
+    case st: StructType => st.forall { f => supportsDataType(f.dataType) }
+
+    case ArrayType(elementType, _) => supportsDataType(elementType)
+
+    case MapType(keyType, valueType, _) =>
+      supportsDataType(keyType) && supportsDataType(valueType)
+
+    case udt: UserDefinedType[_] => supportsDataType(udt.sqlType)
+
+    case _: NullType => true
+
+    case _ => false
+  }
+
+  def prepareWrite(
+      sqlConf: SQLConf,
+      job: Job,
+      options: Map[String, String],
+      dataSchema: StructType): OutputWriterFactory = {
+    val parsedOptions = new AvroOptions(options, job.getConfiguration)
 
 Review comment:
   Yes, it is enough. Orc/Parquet also use the configuration from `job`.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

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