Reputation: 31
I have a dataframe which looks like that
+--------------------+----------------+------+------+
| id | migration|number|string|
+--------------------+----------------+------+------+
|[5e5db036e0403b1a. |mig | 1| str |
+--------------------+----------------+------+------+
and I have a jsonSchema:
{
"title": "Section",
"type": "object",
"additionalProperties": false,
"required": ["migration", "id"],
"properties": {
"migration": {
"type": "string",
"additionalProperties": false
},
"string": {
"type": "string"
},
"number": {
"type": "number",
"min": 0
}
}
}
I would like to validate the schema of my dataframe with my jsonSchema. Thank you
Upvotes: 0
Views: 2258
Reputation: 4045
Please find inline code comments for the explanation
val newSchema : StructType = DataType.fromJson("""{
| "type": "struct",
| "fields": [
| {
| "name": "id",
| "type": "string",
| "nullable": true,
| "metadata": {}
| },
| {
| "name": "migration",
| "type": "string",
| "nullable": true,
| "metadata": {}
| },
| {
| "name": "number",
| "type": "integer",
| "nullable": false,
| "metadata": {}
| },
| {
| "name": "string",
| "type": "string",
| "nullable": true,
| "metadata": {}
| }
| ]
|}""".stripMargin).asInstanceOf[StructType] // Load you schema from JSON string
// println(newSchema)
val spark = Constant.getSparkSess // Create SparkSession object
//Correct data
val correctData: RDD[Row] = spark.sparkContext.parallelize(Seq(Row("5e5db036e0403b1a.","mig",1,"str")))
val dfNew = spark.createDataFrame(correctData, newSchema) // validating the data
dfNew.show()
//InCorrect data
val inCorrectData: RDD[Row] = spark.sparkContext.parallelize(Seq(Row("5e5db036e0403b1a.",1,1,"str")))
val dfInvalid = spark.createDataFrame(inCorrectData, newSchema) // validating the data which will throw RuntimeException: java.lang.Integer is not a valid external type for schema of string
dfInvalid.show()
val res = spark.sql("") // Load the SQL dataframe
val diffColumn : Seq[StructField] = res.schema.diff(newSchema) // compare SQL dataframe with JSON schema
diffColumn.foreach(_.name) // Print the Diff columns
Upvotes: 1