spark sql中处理json嵌套数组的方法

Question

各位大神刚开始学spark sql想处理json数据，一般的json数据没问题，但是当json串中有json嵌套数组时，就不太清楚怎样获取这个数据里每一项的数据，请各位指点。格式如
{"name":"Yin","address":[{"city":"Columbus","state":"防守打法"},{"city":"Columbus2","state":"防守打法"}]}我想获取address中的每一个数据项，应该怎么弄比较好？谢谢！

Answer 1

别沉了，补个代码
val conf =new SparkConf().setAppName("test2").setMaster("local")
val sc =new SparkContext(conf)
var sqlContext= new SQLContext(sc)

    var anotherPeopleRDD=sc.parallelize("""{"name":"Yin","address":[{"city":"Columbus","state":"http://www.tom.com"},{"city":"Columbus2","state":"http://www.tom.com.cn"}]}"""::Nil)

sqlContext.udf.register("testaddress",(arr:Array[Row])=>{
})

val anotherPeople = sqlContext.jsonRDD(anotherPeopleRDD)
anotherPeople.printSchema
anotherPeople.registerTempTable("people")
val pairs = sqlContext.sql("select testaddress(address) from people ")
pairs.collect()

    我想用udf 但是总报错：
    java.lang.ClassCastException: scala.collection.mutable.WrappedArray$ofRef cannot be cast to [Lorg.apache.spark.sql.Row;
at com.dwnews.DMP.ETL.service.FileFilterService$$anonfun$test2$1.apply(FileFilterService.scala:100)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:75)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:74)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF.eval(ScalaUDF.scala:964)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:55)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:53)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)