Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/12601#discussion_r80641407
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcRelationProvider.scala
---
@@ -19,37 +19,102 @@ package org.apache.spark.sql.execution.datasources.jdbc
import java.util.Properties
-import org.apache.spark.sql.SQLContext
-import org.apache.spark.sql.sources.{BaseRelation, DataSourceRegister,
RelationProvider}
+import scala.collection.JavaConverters.mapAsJavaMapConverter
-class JdbcRelationProvider extends RelationProvider with
DataSourceRegister {
+import org.apache.spark.sql.{AnalysisException, DataFrame, SaveMode,
SQLContext}
+import org.apache.spark.sql.sources.{BaseRelation,
CreatableRelationProvider, DataSourceRegister, RelationProvider}
+
+class JdbcRelationProvider extends CreatableRelationProvider
+ with RelationProvider with DataSourceRegister {
override def shortName(): String = "jdbc"
- /** Returns a new base relation with the given parameters. */
override def createRelation(
sqlContext: SQLContext,
parameters: Map[String, String]): BaseRelation = {
val jdbcOptions = new JDBCOptions(parameters)
- if (jdbcOptions.partitionColumn != null
- && (jdbcOptions.lowerBound == null
- || jdbcOptions.upperBound == null
- || jdbcOptions.numPartitions == null)) {
- sys.error("Partitioning incompletely specified")
- }
+ val partitionColumn = jdbcOptions.partitionColumn
+ val lowerBound = jdbcOptions.lowerBound
+ val upperBound = jdbcOptions.upperBound
+ val numPartitions = jdbcOptions.numPartitions
- val partitionInfo = if (jdbcOptions.partitionColumn == null) {
+ val partitionInfo = if (partitionColumn == null) {
null
} else {
JDBCPartitioningInfo(
- jdbcOptions.partitionColumn,
- jdbcOptions.lowerBound.toLong,
- jdbcOptions.upperBound.toLong,
- jdbcOptions.numPartitions.toInt)
+ partitionColumn, lowerBound.toLong, upperBound.toLong,
numPartitions.toInt)
}
val parts = JDBCRelation.columnPartition(partitionInfo)
val properties = new Properties() // Additional properties that we
will pass to getConnection
parameters.foreach(kv => properties.setProperty(kv._1, kv._2))
JDBCRelation(jdbcOptions.url, jdbcOptions.table, parts,
properties)(sqlContext.sparkSession)
}
+
+ /*
+ * The following structure applies to this code:
--- End diff --
I also took a look at @gatorsmile 's approach, I think it's easier to
understand, why it's rejected? We can also get rid of the `return`:
```
if (tableExists) {
mode match {
case SaveMode.Ignore =>
......
}
} else {
......
}
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
