diff options
author | Yash Datta <Yash.Datta@guavus.com> | 2015-03-26 21:13:38 +0800 |
---|---|---|
committer | Cheng Lian <lian@databricks.com> | 2015-03-26 21:13:38 +0800 |
commit | 1c05027a143d1b0bf3df192984e6cac752b1e926 (patch) | |
tree | f9ac6606175278fa2ef3896613f1fcbf654c97a1 | |
parent | 0c88ce5416d7687bc806a7655e17009ad5823d30 (diff) | |
download | spark-1c05027a143d1b0bf3df192984e6cac752b1e926.tar.gz spark-1c05027a143d1b0bf3df192984e6cac752b1e926.tar.bz2 spark-1c05027a143d1b0bf3df192984e6cac752b1e926.zip |
[SQL][SPARK-6471]: Metastore schema should only be a subset of parquet schema to support dropping of columns using replace columns
Currently in the parquet relation 2 implementation, error is thrown in case merged schema is not exactly the same as metastore schema.
But to support cases like deletion of column using replace column command, we can relax the restriction so that even if metastore schema is a subset of merged parquet schema, the query will work.
Author: Yash Datta <Yash.Datta@guavus.com>
Closes #5141 from saucam/replace_col and squashes the following commits:
e858d5b [Yash Datta] SPARK-6471: Fix test cases, add a new test case for metastore schema to be subset of parquet schema
5f2f467 [Yash Datta] SPARK-6471: Metastore schema should only be a subset of parquet schema to support dropping of columns using replace columns
-rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala | 5 | ||||
-rw-r--r-- | sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala | 18 |
2 files changed, 19 insertions, 4 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala index 410600b052..3516cfe680 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala @@ -758,12 +758,13 @@ private[sql] object ParquetRelation2 extends Logging { |${parquetSchema.prettyJson} """.stripMargin - assert(metastoreSchema.size == parquetSchema.size, schemaConflictMessage) + assert(metastoreSchema.size <= parquetSchema.size, schemaConflictMessage) val ordinalMap = metastoreSchema.zipWithIndex.map { case (field, index) => field.name.toLowerCase -> index }.toMap - val reorderedParquetSchema = parquetSchema.sortBy(f => ordinalMap(f.name.toLowerCase)) + val reorderedParquetSchema = parquetSchema.sortBy(f => + ordinalMap.getOrElse(f.name.toLowerCase, metastoreSchema.size + 1)) StructType(metastoreSchema.zip(reorderedParquetSchema).map { // Uses Parquet field names but retains Metastore data types. diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala index 321832cd43..8462f9bb2d 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala @@ -212,8 +212,11 @@ class ParquetSchemaSuite extends FunSuite with ParquetTest { StructField("UPPERCase", IntegerType, nullable = true)))) } - // Conflicting field count - assert(intercept[Throwable] { + // MetaStore schema is subset of parquet schema + assertResult( + StructType(Seq( + StructField("UPPERCase", DoubleType, nullable = false)))) { + ParquetRelation2.mergeMetastoreParquetSchema( StructType(Seq( StructField("uppercase", DoubleType, nullable = false))), @@ -221,6 +224,17 @@ class ParquetSchemaSuite extends FunSuite with ParquetTest { StructType(Seq( StructField("lowerCase", BinaryType), StructField("UPPERCase", IntegerType, nullable = true)))) + } + + // Conflicting field count + assert(intercept[Throwable] { + ParquetRelation2.mergeMetastoreParquetSchema( + StructType(Seq( + StructField("uppercase", DoubleType, nullable = false), + StructField("lowerCase", BinaryType))), + + StructType(Seq( + StructField("UPPERCase", IntegerType, nullable = true)))) }.getMessage.contains("detected conflicting schemas")) // Conflicting field names |