[SPARK-10170] [SQL] Add DB2 JDBC dialect support.

Data frame write to DB2 database is failing because by default JDBC data source implementation is generating a table schema with DB2 unsupported data types TEXT for String, and BIT1(1) for Boolean.

This patch registers DB2 JDBC Dialect that maps String, Boolean to valid DB2 data types.

Author: sureshthalamati <suresh.thalamati@gmail.com>

Closes #8393 from sureshthalamati/db2_dialect_spark-10170.

2 files changed, 25 insertions, 0 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
index 8849fc2f1f..c6d05c9b83 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
@@ -125,6 +125,7 @@ object JdbcDialects {
 
   registerDialect(MySQLDialect)
   registerDialect(PostgresDialect)
+  registerDialect(DB2Dialect)
 
   /**
    * Fetch the JdbcDialect class corresponding to a given database url.
@@ -222,3 +223,20 @@ case object MySQLDialect extends JdbcDialect {
     s"`$colName`"
   }
 }
+
+/**
+ * :: DeveloperApi ::
+ * Default DB2 dialect, mapping string/boolean on write to valid DB2 types.
+ * By default string, and boolean gets mapped to db2 invalid types TEXT, and BIT(1).
+ */
+@DeveloperApi
+case object DB2Dialect extends JdbcDialect {
+
+  override def canHandle(url: String): Boolean = url.startsWith("jdbc:db2")
+
+  override def getJDBCType(dt: DataType): Option[JdbcType] = dt match {
+    case StringType => Some(JdbcType("CLOB", java.sql.Types.CLOB))
+    case BooleanType => Some(JdbcType("CHAR(1)", java.sql.Types.CHAR))
+    case _ => None
+  }
+}
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
index 0edac0848c..d8c9a08d84 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
@@ -407,6 +407,7 @@ class JDBCSuite extends SparkFunSuite with BeforeAndAfter with SharedSQLContext
   test("Default jdbc dialect registration") {
     assert(JdbcDialects.get("jdbc:mysql://127.0.0.1/db") == MySQLDialect)
     assert(JdbcDialects.get("jdbc:postgresql://127.0.0.1/db") == PostgresDialect)
+    assert(JdbcDialects.get("jdbc:db2://127.0.0.1/db") == DB2Dialect)
     assert(JdbcDialects.get("test.invalid") == NoopDialect)
   }
 
@@ -443,4 +444,10 @@ class JDBCSuite extends SparkFunSuite with BeforeAndAfter with SharedSQLContext
     assert(agg.getCatalystType(0, "", 1, null) === Some(LongType))
     assert(agg.getCatalystType(1, "", 1, null) === Some(StringType))
   }
+
+  test("DB2Dialect type mapping") {
+    val db2Dialect = JdbcDialects.get("jdbc:db2://127.0.0.1/db")
+    assert(db2Dialect.getJDBCType(StringType).map(_.databaseTypeDefinition).get == "CLOB")
+    assert(db2Dialect.getJDBCType(BooleanType).map(_.databaseTypeDefinition).get == "CHAR(1)")
+  }
 }