[spark] branch master updated: [SPARK-26499][SQL] JdbcUtils.makeGetter does not handle ByteType

[gu...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new 5f0ddd2  [SPARK-26499][SQL] JdbcUtils.makeGetter does not handle ByteType
5f0ddd2 is described below

commit 5f0ddd2d6e2fdebf549207bbc4b13ca709eee3c4
Author: Thomas D'Silva <td...@apache.org>
AuthorDate: Tue Jan 1 14:11:14 2019 +0800

    [SPARK-26499][SQL] JdbcUtils.makeGetter does not handle ByteType
    
    …Type
    
    ## What changes were proposed in this pull request?
    Modifed JdbcUtils.makeGetter to handle ByteType.
    
    ## How was this patch tested?
    
    Added a new test to JDBCSuite that maps ```TINYINT``` to ```ByteType```.
    
    Closes #23400 from twdsilva/tiny_int_support.
    
    Authored-by: Thomas D'Silva <td...@apache.org>
    Signed-off-by: Hyukjin Kwon <gu...@apache.org>
---
 .../sql/execution/datasources/jdbc/JdbcUtils.scala |  4 ++++
 .../org/apache/spark/sql/jdbc/JDBCSuite.scala      | 25 ++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala
index edea549..922bef2 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala
@@ -438,6 +438,10 @@ object JdbcUtils extends Logging {
       (rs: ResultSet, row: InternalRow, pos: Int) =>
         row.setShort(pos, rs.getShort(pos + 1))
 
+    case ByteType =>
+      (rs: ResultSet, row: InternalRow, pos: Int) =>
+        row.update(pos, rs.getByte(pos + 1))
+
     case StringType =>
       (rs: ResultSet, row: InternalRow, pos: Int) =>
         // TODO(davies): use getBytes for better performance, if the encoding is UTF-8
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 71e8376..e464163 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
@@ -56,6 +56,20 @@ class JDBCSuite extends QueryTest
       Some(StringType)
   }
 
+  val testH2DialectTinyInt = new JdbcDialect {
+    override def canHandle(url: String): Boolean = url.startsWith("jdbc:h2")
+    override def getCatalystType(
+        sqlType: Int,
+        typeName: String,
+        size: Int,
+        md: MetadataBuilder): Option[DataType] = {
+      sqlType match {
+        case java.sql.Types.TINYINT => Some(ByteType)
+        case _ => None
+      }
+    }
+  }
+
   before {
     Utils.classForName("org.h2.Driver")
     // Extra properties that will be specified for our database. We need these to test
@@ -693,6 +707,17 @@ class JDBCSuite extends QueryTest
     JdbcDialects.unregisterDialect(testH2Dialect)
   }
 
+  test("Map TINYINT to ByteType via JdbcDialects") {
+    JdbcDialects.registerDialect(testH2DialectTinyInt)
+    val df = spark.read.jdbc(urlWithUserAndPass, "test.inttypes", new Properties())
+    val rows = df.collect()
+    assert(rows.length === 2)
+    assert(rows(0).get(2).isInstanceOf[Byte])
+    assert(rows(0).getByte(2) === 3)
+    assert(rows(1).isNullAt(2))
+    JdbcDialects.unregisterDialect(testH2DialectTinyInt)
+  }
+
   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)


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org