How to convert string to json in Spark 2 Scala

Question

Is there an easy way to convert a given Row object to json?

Found this about converting a whole Dataframe to json output: Spark Row for JSON

But I just want to convert one line to json. Here is the pseudo code for what I'm trying to do.

More precisely, I read json as input in a Dataframe. I am creating a new output, which is mainly based on columns, but with one json field for all the information that does not fit into the columns.

My question is: what is the easiest way to write this function: convertRowToJson ()

def convertRowToJson(row: Row): String = ???

def transformVenueTry(row: Row): Try[Venue] = {
  Try({
    val name = row.getString(row.fieldIndex("name"))
    val metadataRow = row.getStruct(row.fieldIndex("meta"))
    val score: Double = calcScore(row)
    val combinedRow: Row = metadataRow ++ ("score" -> score)
    val jsonString: String = convertRowToJson(combinedRow)
    Venue(name = name, json = jsonString)
  })
}

Psidom Solutions:

def convertRowToJSON(row: Row): String = {
    val m = row.getValuesMap(row.schema.fieldNames)
    JSONObject(m).toString()
}

only works if the row has only one level that does not contain nested rows. This is the diagram:

StructType(
    StructField(indicator,StringType,true),   
    StructField(range,
    StructType(
        StructField(currency_code,StringType,true),
        StructField(maxrate,LongType,true), 
        StructField(minrate,LongType,true)),true))

I also tried Artem's suggestion, but this did not compile:

def row2DataFrame(row: Row, sqlContext: SQLContext): DataFrame = {
  val sparkContext = sqlContext.sparkContext
  import sparkContext._
  import sqlContext.implicits._
  import sqlContext._
  val rowRDD: RDD[Row] = sqlContext.sparkContext.makeRDD(row :: Nil)
  val dataFrame = rowRDD.toDF() //XXX does not compile
  dataFrame
}

Answer 1

json json-. , json .

Spark , . - json . json.

sub json , .

:

dataFrameWithJsonField = dataFrame.withColumn("address_json", to_json($"location.address"))

location.address - sub json json . address_json - , json.

to_json Spark 2.1.

json json4s, _json AST, json escape- address_json.

Answer 2

getValuesMap JSON:

import scala.util.parsing.json.JSONObject
import org.apache.spark.sql._

val df = Seq((1,2,3),(2,3,4)).toDF("A", "B", "C")    
val row = df.first()          // this is an example row object

def convertRowToJSON(row: Row): String = {
    val m = row.getValuesMap(row.schema.fieldNames)
    JSONObject(m).toString()
}

convertRowToJSON(row)
// res46: String = {"A" : 1, "B" : 2, "C" : 3}

Answer 3

, , . , , json.

Answer 4

JSon , Row , Row JSon. .

import org.apache.spark.sql.Row
import org.apache.spark.sql.types._

def convertRowToJson(row: Row): String = {

  val schema = StructType(
      StructField("name", StringType, true) ::
      StructField("meta", StringType, false) ::  Nil)

      return sqlContext.applySchema(row, schema).toJSON
}

Answer 5

scala class scala.util.parsing.json.JSONObject .

@deprecated ( " .", "2.11.0" )

"JSONFormat.defaultFormat

https://issues.scala-lang.org/browse/SI-5092

Answer 6

: , . , :

def row2Json(row: Row, sqlContext: SQLContext): String = {
  import sqlContext.implicits
  val rowRDD: RDD[Row] = sqlContext.sparkContext.makeRDD(row :: Nil)
  val dataframe = sqlContext.createDataFrame(rowRDD, row.schema)
  dataframe.toJSON.first
}

, .

Answer 7

, ( ), json-. , , , (Spark 2.1):

import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, Dataset, Row}
import scala.util.parsing.json.JSONFormat.ValueFormatter
import scala.util.parsing.json.{JSONArray, JSONFormat, JSONObject}

def getValuesMap[T](row: Row, schema: StructType): Map[String,Any] = {
  schema.fields.map {
    field =>
      try{
        if (field.dataType.typeName.equals("struct")){
          field.name -> getValuesMap(row.getAs[Row](field.name),   field.dataType.asInstanceOf[StructType]) 
        }else{
          field.name -> row.getAs[T](field.name)
        }
      }catch {case e : Exception =>{field.name -> null.asInstanceOf[T]}}
  }.filter(xy => xy._2 != null).toMap
}

def convertRowToJSON(row: Row, schema: StructType): JSONObject = {
  val m: Map[String, Any] = getValuesMap(row, schema)
  JSONObject(m)
}
//I guess since I am using Any and not nothing the regular ValueFormatter is not working, and I had to add case jmap : Map[String,Any] => JSONObject(jmap).toString(defaultFormatter)
val defaultFormatter : ValueFormatter = (x : Any) => x match {
  case s : String => "\"" + JSONFormat.quoteString(s) + "\""
  case jo : JSONObject => jo.toString(defaultFormatter)
  case jmap : Map[String,Any] => JSONObject(jmap).toString(defaultFormatter)
  case ja : JSONArray => ja.toString(defaultFormatter)
  case other => other.toString
}

val someFile = "s3a://bucket/file"
val df: DataFrame = sqlContext.read.load(someFile)
val schema: StructType = df.schema
val jsons: Dataset[JSONObject] = df.map(row => convertRowToJSON(row, schema))