diff options
Diffstat (limited to 'sql/core')
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRDD.scala | 23 |
1 files changed, 19 insertions, 4 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRDD.scala index 95935ba874..4189dfcf95 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRDD.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRDD.scala @@ -300,7 +300,7 @@ private[sql] class JDBCRDD( abstract class JDBCConversion case object BooleanConversion extends JDBCConversion case object DateConversion extends JDBCConversion - case object DecimalConversion extends JDBCConversion + case class DecimalConversion(precisionInfo: Option[(Int, Int)]) extends JDBCConversion case object DoubleConversion extends JDBCConversion case object FloatConversion extends JDBCConversion case object IntegerConversion extends JDBCConversion @@ -317,8 +317,8 @@ private[sql] class JDBCRDD( schema.fields.map(sf => sf.dataType match { case BooleanType => BooleanConversion case DateType => DateConversion - case DecimalType.Unlimited => DecimalConversion - case DecimalType.Fixed(d) => DecimalConversion + case DecimalType.Unlimited => DecimalConversion(None) + case DecimalType.Fixed(d) => DecimalConversion(Some(d)) case DoubleType => DoubleConversion case FloatType => FloatConversion case IntegerType => IntegerConversion @@ -375,7 +375,22 @@ private[sql] class JDBCRDD( } else { mutableRow.update(i, null) } - case DecimalConversion => + // When connecting with Oracle DB through JDBC, the precision and scale of BigDecimal + // object returned by ResultSet.getBigDecimal is not correctly matched to the table + // schema reported by ResultSetMetaData.getPrecision and ResultSetMetaData.getScale. + // If inserting values like 19999 into a column with NUMBER(12, 2) type, you get through + // a BigDecimal object with scale as 0. But the dataframe schema has correct type as + // DecimalType(12, 2). Thus, after saving the dataframe into parquet file and then + // retrieve it, you will get wrong result 199.99. + // So it is needed to set precision and scale for Decimal based on JDBC metadata. + case DecimalConversion(Some((p, s))) => + val decimalVal = rs.getBigDecimal(pos) + if (decimalVal == null) { + mutableRow.update(i, null) + } else { + mutableRow.update(i, Decimal(decimalVal, p, s)) + } + case DecimalConversion(None) => val decimalVal = rs.getBigDecimal(pos) if (decimalVal == null) { mutableRow.update(i, null) |