[SPARK-15230][SQL] distinct() does not handle column name with dot properly
## What changes were proposed in this pull request? When table is created with column name containing dot, distinct() will fail to run. For example, ```scala val rowRDD = sparkContext.parallelize(Seq(Row(1), Row(1), Row(2))) val schema = StructType(Array(StructField("column.with.dot", IntegerType, nullable = false))) val df = spark.createDataFrame(rowRDD, schema) ``` running the following will have no problem: ```scala df.select(new Column("`column.with.dot`")) ``` but running the query with additional distinct() will cause exception: ```scala df.select(new Column("`column.with.dot`")).distinct() ``` The issue is that distinct() will try to resolve the column name, but the column name in the schema does not have backtick with it. So the solution is to add the backtick before passing the column name to resolve(). ## How was this patch tested? Added a new test case. Author: bomeng <bmeng@us.ibm.com> Closes #13140 from bomeng/SPARK-15230.
This commit is contained in:
parent
37f3be5d29
commit
925884a612
|
@ -1812,7 +1812,13 @@ class Dataset[T] private[sql](
|
|||
* @since 2.0.0
|
||||
*/
|
||||
def dropDuplicates(colNames: Seq[String]): Dataset[T] = withTypedPlan {
|
||||
val groupCols = colNames.map(resolve)
|
||||
val resolver = sparkSession.sessionState.analyzer.resolver
|
||||
val allColumns = queryExecution.analyzed.output
|
||||
val groupCols = colNames.map { colName =>
|
||||
allColumns.find(col => resolver(col.name, colName)).getOrElse(
|
||||
throw new AnalysisException(
|
||||
s"""Cannot resolve column name "$colName" among (${schema.fieldNames.mkString(", ")})"""))
|
||||
}
|
||||
val groupColExprIds = groupCols.map(_.exprId)
|
||||
val aggCols = logicalPlan.output.map { attr =>
|
||||
if (groupColExprIds.contains(attr.exprId)) {
|
||||
|
|
|
@ -1536,4 +1536,9 @@ class DataFrameSuite extends QueryTest with SharedSQLContext {
|
|||
Utils.deleteRecursively(baseDir)
|
||||
}
|
||||
}
|
||||
|
||||
test("SPARK-15230: distinct() does not handle column name with dot properly") {
|
||||
val df = Seq(1, 1, 2).toDF("column.with.dot")
|
||||
checkAnswer(df.distinct(), Row(1) :: Row(2) :: Nil)
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue