[SPARK-17764][SQL] Add `to_json` supporting to convert nested struct column to JSON string

## What changes were proposed in this pull request?

This PR proposes to add `to_json` function in contrast with `from_json` in Scala, Java and Python.

It'd be useful if we can convert a same column from/to json. Also, some datasources do not support nested types. If we are forced to save a dataframe into those data sources, we might be able to work around by this function.

The usage is as below:

``` scala
val df = Seq(Tuple1(Tuple1(1))).toDF("a")
df.select(to_json($"a").as("json")).show()
```

``` bash
+--------+
|    json|
+--------+
|{"_1":1}|
+--------+
```
## How was this patch tested?

Unit tests in `JsonFunctionsSuite` and `JsonExpressionsSuite`.

Author: hyukjinkwon <gurwls223@gmail.com>

Closes #15354 from HyukjinKwon/SPARK-17764.

8 files changed, 152 insertions, 14 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
index 65dbd6a4e3..244a5a34f3 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
@@ -17,16 +17,17 @@
 
 package org.apache.spark.sql.catalyst.expressions
 
-import java.io.{ByteArrayOutputStream, StringWriter}
+import java.io.{ByteArrayOutputStream, CharArrayWriter, StringWriter}
 
 import scala.util.parsing.combinator.RegexParsers
 
 import com.fasterxml.jackson.core._
 
+import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
 import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.json.{JacksonParser, JSONOptions, SparkSQLJsonProcessingException}
+import org.apache.spark.sql.catalyst.json._
 import org.apache.spark.sql.catalyst.util.ParseModes
 import org.apache.spark.sql.types._
 import org.apache.spark.unsafe.types.UTF8String
@@ -494,3 +495,46 @@ case class JsonToStruct(schema: StructType, options: Map[String, String], child:
 
   override def inputTypes: Seq[AbstractDataType] = StringType :: Nil
 }
+
+/**
+ * Converts a [[StructType]] to a json output string.
+ */
+case class StructToJson(options: Map[String, String], child: Expression)
+  extends Expression with CodegenFallback with ExpectsInputTypes {
+  override def nullable: Boolean = true
+
+  @transient
+  lazy val writer = new CharArrayWriter()
+
+  @transient
+  lazy val gen =
+    new JacksonGenerator(child.dataType.asInstanceOf[StructType], writer)
+
+  override def dataType: DataType = StringType
+  override def children: Seq[Expression] = child :: Nil
+
+  override def checkInputDataTypes(): TypeCheckResult = {
+    if (StructType.acceptsType(child.dataType)) {
+      try {
+        JacksonUtils.verifySchema(child.dataType.asInstanceOf[StructType])
+        TypeCheckResult.TypeCheckSuccess
+      } catch {
+        case e: UnsupportedOperationException =>
+          TypeCheckResult.TypeCheckFailure(e.getMessage)
+      }
+    } else {
+      TypeCheckResult.TypeCheckFailure(
+        s"$prettyName requires that the expression is a struct expression.")
+    }
+  }
+
+  override def eval(input: InternalRow): Any = {
+    gen.write(child.eval(input).asInstanceOf[InternalRow])
+    gen.flush()
+    val json = writer.toString
+    writer.reset()
+    UTF8String.fromString(json)
+  }
+
+  override def inputTypes: Seq[AbstractDataType] = StructType :: Nil
+}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonGenerator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonGenerator.scala
index 5b55b70186..4b548e0e7f 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonGenerator.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonGenerator.scala
@@ -15,15 +15,14 @@
  * limitations under the License.
  */
 
-package org.apache.spark.sql.execution.datasources.json
+package org.apache.spark.sql.catalyst.json
 
 import java.io.Writer
 
 import com.fasterxml.jackson.core._
 
-import org.apache.spark.sql.catalyst.expressions.SpecializedGetters
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.json.JSONOptions
+import org.apache.spark.sql.catalyst.expressions.SpecializedGetters
 import org.apache.spark.sql.catalyst.util.{ArrayData, DateTimeUtils, MapData}
 import org.apache.spark.sql.types._
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonUtils.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonUtils.scala
index c4d9abb2c0..3b23c6cd28 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonUtils.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonUtils.scala
@@ -19,6 +19,8 @@ package org.apache.spark.sql.catalyst.json
 
 import com.fasterxml.jackson.core.{JsonParser, JsonToken}
 
+import org.apache.spark.sql.types._
+
 object JacksonUtils {
   /**
    * Advance the parser until a null or a specific token is found
@@ -29,4 +31,28 @@ object JacksonUtils {
       case x => x != stopOn
     }
   }
+
+  /**
+   * Verify if the schema is supported in JSON parsing.
+   */
+  def verifySchema(schema: StructType): Unit = {
+    def verifyType(name: String, dataType: DataType): Unit = dataType match {
+      case NullType | BooleanType | ByteType | ShortType | IntegerType | LongType | FloatType |
+           DoubleType | StringType | TimestampType | DateType | BinaryType | _: DecimalType =>
+
+      case st: StructType => st.foreach(field => verifyType(field.name, field.dataType))
+
+      case at: ArrayType => verifyType(name, at.elementType)
+
+      case mt: MapType => verifyType(name, mt.keyType)
+
+      case udt: UserDefinedType[_] => verifyType(name, udt.sqlType)
+
+      case _ =>
+        throw new UnsupportedOperationException(
+          s"Unable to convert column $name of type ${dataType.simpleString} to JSON.")
+    }
+
+    schema.foreach(field => verifyType(field.name, field.dataType))
+  }
 }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
index 84623934d9..f9db649bc2 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
@@ -343,4 +343,13 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
       null
     )
   }
+
+  test("to_json") {
+    val schema = StructType(StructField("a", IntegerType) :: Nil)
+    val struct = Literal.create(create_row(1), schema)
+    checkEvaluation(
+      StructToJson(Map.empty, struct),
+      """{"a":1}"""
+    )
+  }
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index 6e0a2471e0..eb2b20afc3 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -37,6 +37,7 @@ import org.apache.spark.sql.catalyst.analysis._
 import org.apache.spark.sql.catalyst.encoders._
 import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.expressions.aggregate._
+import org.apache.spark.sql.catalyst.json.JacksonGenerator
 import org.apache.spark.sql.catalyst.optimizer.CombineUnions
 import org.apache.spark.sql.catalyst.plans._
 import org.apache.spark.sql.catalyst.plans.logical._
@@ -45,7 +46,6 @@ import org.apache.spark.sql.catalyst.util.usePrettyExpression
 import org.apache.spark.sql.execution.{FileRelation, LogicalRDD, QueryExecution, SQLExecution}
 import org.apache.spark.sql.execution.command.{CreateViewCommand, ExplainCommand, GlobalTempView, LocalTempView}
 import org.apache.spark.sql.execution.datasources.LogicalRelation
-import org.apache.spark.sql.execution.datasources.json.JacksonGenerator
 import org.apache.spark.sql.execution.python.EvaluatePython
 import org.apache.spark.sql.streaming.DataStreamWriter
 import org.apache.spark.sql.types._
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala
index 5a409c04c9..0e38aefecb 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala
@@ -32,7 +32,7 @@ import org.apache.spark.internal.Logging
 import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.{AnalysisException, Row, SparkSession}
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.json.{JacksonParser, JSONOptions}
+import org.apache.spark.sql.catalyst.json.{JacksonGenerator, JacksonParser, JSONOptions}
 import org.apache.spark.sql.catalyst.util.CompressionCodecs
 import org.apache.spark.sql.execution.datasources._
 import org.apache.spark.sql.execution.datasources.text.TextOutputWriter
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 5f1efd22d8..944a476114 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -2883,10 +2883,10 @@ object functions {
    * (Scala-specific) Parses a column containing a JSON string into a [[StructType]] with the
    * specified schema. Returns `null`, in the case of an unparseable string.
    *
+   * @param e a string column containing JSON data.
    * @param schema the schema to use when parsing the json string
    * @param options options to control how the json is parsed. accepts the same options and the
    *                json data source.
-   * @param e a string column containing JSON data.
    *
    * @group collection_funcs
    * @since 2.1.0
@@ -2936,6 +2936,48 @@ object functions {
   def from_json(e: Column, schema: String, options: java.util.Map[String, String]): Column =
     from_json(e, DataType.fromJson(schema).asInstanceOf[StructType], options)
 
+
+  /**
+   * (Scala-specific) Converts a column containing a [[StructType]] into a JSON string with the
+   * specified schema. Throws an exception, in the case of an unsupported type.
+   *
+   * @param e a struct column.
+   * @param options options to control how the struct column is converted into a json string.
+   *                accepts the same options and the json data source.
+   *
+   * @group collection_funcs
+   * @since 2.1.0
+   */
+  def to_json(e: Column, options: Map[String, String]): Column = withExpr {
+    StructToJson(options, e.expr)
+  }
+
+  /**
+   * (Java-specific) Converts a column containing a [[StructType]] into a JSON string with the
+   * specified schema. Throws an exception, in the case of an unsupported type.
+   *
+   * @param e a struct column.
+   * @param options options to control how the struct column is converted into a json string.
+   *                accepts the same options and the json data source.
+   *
+   * @group collection_funcs
+   * @since 2.1.0
+   */
+  def to_json(e: Column, options: java.util.Map[String, String]): Column =
+    to_json(e, options.asScala.toMap)
+
+  /**
+   * Converts a column containing a [[StructType]] into a JSON string with the
+   * specified schema. Throws an exception, in the case of an unsupported type.
+   *
+   * @param e a struct column.
+   *
+   * @group collection_funcs
+   * @since 2.1.0
+   */
+  def to_json(e: Column): Column =
+    to_json(e, Map.empty[String, String])
+
   /**
    * Returns length of array or map.
    *
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
index 518d6e92b2..59ae889cf3 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
@@ -17,9 +17,9 @@
 
 package org.apache.spark.sql
 
-import org.apache.spark.sql.functions.from_json
+import org.apache.spark.sql.functions.{from_json, struct, to_json}
 import org.apache.spark.sql.test.SharedSQLContext
-import org.apache.spark.sql.types.{IntegerType, StructType}
+import org.apache.spark.sql.types.{CalendarIntervalType, IntegerType, StructType}
 
 class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
   import testImplicits._
@@ -31,7 +31,6 @@ class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
       Row("alice", "5"))
   }
 
-
   val tuples: Seq[(String, String)] =
     ("1", """{"f1": "value1", "f2": "value2", "f3": 3, "f5": 5.23}""") ::
     ("2", """{"f1": "value12", "f3": "value3", "f2": 2, "f4": 4.01}""") ::
@@ -97,7 +96,7 @@ class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
     checkAnswer(expr, expected)
   }
 
-  test("json_parser") {
+  test("from_json") {
     val df = Seq("""{"a": 1}""").toDS()
     val schema = new StructType().add("a", IntegerType)
 
@@ -106,7 +105,7 @@ class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
       Row(Row(1)) :: Nil)
   }
 
-  test("json_parser missing columns") {
+  test("from_json missing columns") {
     val df = Seq("""{"a": 1}""").toDS()
     val schema = new StructType().add("b", IntegerType)
 
@@ -115,7 +114,7 @@ class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
       Row(Row(null)) :: Nil)
   }
 
-  test("json_parser invalid json") {
+  test("from_json invalid json") {
     val df = Seq("""{"a" 1}""").toDS()
     val schema = new StructType().add("a", IntegerType)
 
@@ -123,4 +122,23 @@ class JsonFunctionsSuite extends QueryTest with SharedSQLContext {
       df.select(from_json($"value", schema)),
       Row(null) :: Nil)
   }
+
+  test("to_json") {
+    val df = Seq(Tuple1(Tuple1(1))).toDF("a")
+
+    checkAnswer(
+      df.select(to_json($"a")),
+      Row("""{"_1":1}""") :: Nil)
+  }
+
+  test("to_json unsupported type") {
+    val df = Seq(Tuple1(Tuple1("interval -3 month 7 hours"))).toDF("a")
+      .select(struct($"a._1".cast(CalendarIntervalType).as("a")).as("c"))
+    val e = intercept[AnalysisException]{
+      // Unsupported type throws an exception
+      df.select(to_json($"c")).collect()
+    }
+    assert(e.getMessage.contains(
+      "Unable to convert column a of type calendarinterval to JSON."))
+  }
 }