spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From yhuai <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-10301] [SQL] Fixes schema merging for n...
Date Fri, 04 Sep 2015 17:30:00 GMT
Github user yhuai commented on a diff in the pull request:

    https://github.com/apache/spark/pull/8509#discussion_r38774767
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystReadSupport.scala
---
    @@ -160,4 +101,168 @@ private[parquet] object CatalystReadSupport {
       val SPARK_ROW_REQUESTED_SCHEMA = "org.apache.spark.sql.parquet.row.requested_schema"
     
       val SPARK_METADATA_KEY = "org.apache.spark.sql.parquet.row.metadata"
    +
    +  /**
    +   * Tailors `parquetSchema` according to `catalystSchema` by removing column paths don't
exist
    +   * in `catalystSchema`, and adding those only exist in `catalystSchema`.
    +   */
    +  def clipParquetSchema(parquetSchema: MessageType, catalystSchema: StructType): MessageType
= {
    +    val clippedParquetFields = clipParquetGroupFields(parquetSchema.asGroupType(), catalystSchema)
    +    Types.buildMessage().addFields(clippedParquetFields: _*).named("root")
    +  }
    +
    +  private def clipParquetType(parquetType: Type, catalystType: DataType): Type = {
    +    catalystType match {
    +      case t: ArrayType if !isPrimitiveCatalystType(t.elementType) =>
    +        // Only clips array types with nested type as element type.
    +        clipParquetListType(parquetType.asGroupType(), t.elementType)
    +
    +      case t: MapType if !isPrimitiveCatalystType(t.valueType) =>
    +        // Only clips map types with nested type as value type.
    +        clipParquetMapType(parquetType.asGroupType(), t.keyType, t.valueType)
    +
    +      case t: StructType =>
    +        clipParquetGroup(parquetType.asGroupType(), t)
    +
    +      case _ =>
    +        parquetType
    +    }
    +  }
    +
    +  /**
    +   * Whether a Catalyst [[DataType]] is primitive.  Primitive [[DataType]] is not equivalent
to
    +   * [[AtomicType]].  For example, [[CalendarIntervalType]] is primitive, but it's not
an
    +   * [[AtomicType]].
    +   */
    +  private def isPrimitiveCatalystType(dataType: DataType): Boolean = {
    +    dataType match {
    +      case _: ArrayType | _: MapType | _: StructType => false
    --- End diff --
    
    Looks like for a UDT, we need to call `isPrimitiveCatalystType` on the `sqlType` of this
UDT?


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

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


Mime
View raw message