org.apache.spark.sql.internal.HiveSerDe.scala Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of spark-sql_2.11 Show documentation
There is a newer version: 2.4.8
/*
 * 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.internal

case class HiveSerDe(
  inputFormat: Option[String] = None,
  outputFormat: Option[String] = None,
  serde: Option[String] = None)

object HiveSerDe {
  /**
   * Get the Hive SerDe information from the data source abbreviation string or classname.
   *
   * @param source Currently the source abbreviation can be one of the following:
   *               SequenceFile, RCFile, ORC, PARQUET, and case insensitive.
   * @param conf SQLConf
   * @return HiveSerDe associated with the specified source
   */
  def sourceToSerDe(source: String, conf: SQLConf): Option[HiveSerDe] = {
    val serdeMap = Map(
      "sequencefile" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.mapred.SequenceFileInputFormat"),
          outputFormat = Option("org.apache.hadoop.mapred.SequenceFileOutputFormat")),

      "rcfile" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.hive.ql.io.RCFileInputFormat"),
          outputFormat = Option("org.apache.hadoop.hive.ql.io.RCFileOutputFormat"),
          serde = Option(conf.getConfString("hive.default.rcfile.serde",
            "org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe"))),

      "orc" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"),
          outputFormat = Option("org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"),
          serde = Option("org.apache.hadoop.hive.ql.io.orc.OrcSerde")),

      "parquet" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat"),
          outputFormat = Option("org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat"),
          serde = Option("org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe")),

      "textfile" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.mapred.TextInputFormat"),
          outputFormat = Option("org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat")),

      "avro" ->
        HiveSerDe(
          inputFormat = Option("org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat"),
          outputFormat = Option("org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat"),
          serde = Option("org.apache.hadoop.hive.serde2.avro.AvroSerDe")))

    val key = source.toLowerCase match {
      case s if s.startsWith("org.apache.spark.sql.parquet") => "parquet"
      case s if s.startsWith("org.apache.spark.sql.orc") => "orc"
      case s if s.equals("orcfile") => "orc"
      case s if s.equals("parquetfile") => "parquet"
      case s if s.equals("avrofile") => "avro"
      case s => s
    }

    serdeMap.get(key)
  }
}