Got an issue similar to https://issues.apache.org/jira/browse/SPARK-8897,
but with the Decimal datatype coming from a Postgres DB:
//Set up SparkR
>Sys.setenv(SPARK_HOME="/Users/ashkurenko/work/git_repos/spark")
>Sys.setenv(SPARKR_SUBMIT_ARGS="--driver-class-path
~/Downloads/postgresql-9.4-1201.jdbc4.jar sparkr-shell")
>.libPaths(c(file.path(Sys.getenv("SPARK_HOME"), "R", "lib"), .libPaths()))
>library(SparkR)
>sc <- sparkR.init(master="local")
// Connect to a Postgres DB via JDBC
>sqlContext <- sparkRSQL.init(sc)
>sql(sqlContext, "
CREATE TEMPORARY TABLE mytable
USING org.apache.spark.sql.jdbc
OPTIONS (url 'jdbc:postgresql://servername:5432/dbname'
,dbtable 'mydbtable'
)
")
// Try pulling a Decimal column from a table
>myDataFrame <- sql(sqlContext,("select a_decimal_column from mytable "))
// The schema shows up fine
>show(myDataFrame)
DataFrame[a_decimal_column:decimal(10,0)]
>schema(myDataFrame)
StructType
|-name = "a_decimal_column", type = "DecimalType(10,0)", nullable = TRUE
// ... but pulling data fails:
localDF <- collect(myDataFrame)
Error in as.data.frame.default(x[[i]], optional = TRUE) :
cannot coerce class ""jobj"" to a data.frame
-------
Proposed fix:
diff --git a/core/src/main/scala/org/apache/spark/api/r/SerDe.scala
b/core/src/main/scala/org/apache/spark/api/r/SerDe.scala
index d5b4260..b77ae2a 100644
--- a/core/src/main/scala/org/apache/spark/api/r/SerDe.scala
+++ b/core/src/main/scala/org/apache/spark/api/r/SerDe.scala
@@ -219,6 +219,9 @@ private[spark] object SerDe {
case "float" | "java.lang.Float" =>
writeType(dos, "double")
writeDouble(dos, value.asInstanceOf[Float].toDouble)
+ case "decimal" | "java.math.BigDecimal" =>
+ writeType(dos, "double")
+ writeDouble(dos,
scala.math.BigDecimal(value.asInstanceOf[java.math.BigDecimal]).toDouble)
case "double" | "java.lang.Double" =>
writeType(dos, "double")
writeDouble(dos, value.asInstanceOf[Double])
Thanks,
Alex