From 99386fe3989f758844de14b2c28eccfdf8163221 Mon Sep 17 00:00:00 2001 From: Kevin Yu Date: Thu, 9 Jun 2016 09:50:09 -0700 Subject: [SPARK-15804][SQL] Include metadata in the toStructType ## What changes were proposed in this pull request? The help function 'toStructType' in the AttributeSeq class doesn't include the metadata when it builds the StructField, so it causes this reported problem https://issues.apache.org/jira/browse/SPARK-15804?jql=project%20%3D%20SPARK when spark writes the the dataframe with the metadata to the parquet datasource. The code path is when spark writes the dataframe to the parquet datasource through the InsertIntoHadoopFsRelationCommand, spark will build the WriteRelation container, and it will call the help function 'toStructType' to create StructType which contains StructField, it should include the metadata there, otherwise, we will lost the user provide metadata. ## How was this patch tested? added test case in ParquetQuerySuite.scala (If this patch involves UI changes, please attach a screenshot; otherwise, remove this) Author: Kevin Yu Closes #13555 from kevinyu98/spark-15804. --- .../apache/spark/sql/catalyst/expressions/package.scala | 2 +- .../execution/datasources/parquet/ParquetQuerySuite.scala | 15 +++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala index 81f5bb4a65..a6125c61e5 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala @@ -91,7 +91,7 @@ package object expressions { implicit class AttributeSeq(val attrs: Seq[Attribute]) extends Serializable { /** Creates a StructType with a schema matching this `Seq[Attribute]`. */ def toStructType: StructType = { - StructType(attrs.map(a => StructField(a.name, a.dataType, a.nullable))) + StructType(attrs.map(a => StructField(a.name, a.dataType, a.nullable, a.metadata))) } // It's possible that `attrs` is a linked list, which can lead to bad O(n^2) loops when diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala index 78b97f6995..ea57f71c50 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala @@ -625,6 +625,21 @@ class ParquetQuerySuite extends QueryTest with ParquetTest with SharedSQLContext } } } + + test("SPARK-15804: write out the metadata to parquet file") { + val df = Seq((1, "abc"), (2, "hello")).toDF("a", "b") + val md = new MetadataBuilder().putString("key", "value").build() + val dfWithmeta = df.select('a, 'b.as("b", md)) + + withTempPath { dir => + val path = dir.getCanonicalPath + dfWithmeta.write.parquet(path) + + readParquetFile(path) { df => + assert(df.schema.last.metadata.getString("key") == "value") + } + } + } } object TestingUDT { -- cgit v1.2.3