[SPARK-9154][SQL] codegen string format

Author: tarekbecker

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala

@@ -501,6 +501,30 @@ case class StringFormat(children: Expression*) extends Expression with CodegenFa
     }
   }
 
+  override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode): String = {
+    val pattern = children.head.gen(ctx)
+    val argListGen = children.tail.map(x => (x.dataType, x.gen(ctx)))
+    val argListCode = argListGen.map(_._2.code + "\n")
+    val argListString = argListGen.foldLeft("")((s, x) => s + s", ${x._2.primitive}" + (if (!ctx.isPrimitiveType(x._1)) ".toString()" else ""))
+    val form = ctx.freshName("formatter")
+    val formatter = classOf[java.util.Formatter].getName
+    val sb = ctx.freshName("sb")
+    val stringBuffer = classOf[StringBuffer].getName
+
+    s"""
+      ${pattern.code}
+      boolean ${ev.isNull} = ${pattern.isNull};
+      ${ctx.javaType(dataType)} ${ev.primitive} = ${ctx.defaultValue(dataType)};
+      if (!${ev.isNull}) {
+        ${argListCode.mkString}
+        $stringBuffer $sb = new $stringBuffer();
+        $formatter $form = new $formatter($sb, ${classOf[Locale].getName}.US);
+        $form.format(${pattern.primitive}.toString() $argListString);
+        ${ev.primitive} = UTF8String.fromString($sb.toString());
+      }
+     """
+  }
+
   override def prettyName: String = "printf"
 }
 

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala

@@ -361,6 +361,7 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkEvaluation(StringFormat(Literal("aa")), "aa", create_row(null))
     checkEvaluation(StringFormat(Literal("aa%d%s"), Literal(123), Literal("a")), "aa123a", row1)
 
+    println(StringFormat(f, d1, s1).eval(row1))
     checkEvaluation(StringFormat(f, d1, s1), "aa12cc", row1)
     checkEvaluation(StringFormat(f, d1, s1), null, row2)
   }