How to remove square parentheses from a scala array

Question

I have an array of dates [2014-11-08 06:27:00.0], and would like to remove the square brackets 2014-11-08 06:27:00.0.

val conf = new SparkConf(true)
   .set("spark.cassandra.connection.host", "127.0.0.1").setAppName("CasteDate").setMaster("local[*]")
   .set("spark.cassandra.connection.port", "9042")
   .set("spark.driver.allowMultipleContexts", "true")
   .set("spark.streaming.receiver.writeAheadLog.enable", "true")

val sc = new SparkContext(conf)

val ssc = new StreamingContext(sc, Seconds(1))
val csc=new CassandraSQLContext(sc)

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

var input: SimpleDateFormat   = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.S")
input.setTimeZone(TimeZone.getTimeZone("GMT"))
var dia: SimpleDateFormat  = new SimpleDateFormat("dd")
var mes: SimpleDateFormat = new SimpleDateFormat("MM")
var ano: SimpleDateFormat = new SimpleDateFormat("yyyy")
var horas: SimpleDateFormat = new SimpleDateFormat("HH")
var minutos: SimpleDateFormat  = new SimpleDateFormat("mm")

val data=csc.sql("SELECT timecol from smartgrids.analyzer_temp").collect()

import sqlContext.implicits._

val result = data.map(row => {
                         val day = dia.format(input.parse(row.toString()))
                         val month = mes.format(input.parse(row.toString()))
                         val year = ano.format(input.parse(row.toString()))
                         val hour = horas.format(input.parse(row.toString()))
                         val minute = minutos.format(input.parse(row.toString()))
                             })

val collection = sc.parallelize(Seq(("day", 2), ("month", 2), ("year", 4), ("hour", 2), ("minute", 2)))
collection.saveToCassandra("features", "datepart", SomeColumns("day", "month", "year", "hour", "minute"))
sc.stop()         

After executing the code I get the error:

   java.text.ParseException: Unparseable date: "[2015-08-20 21:01:00.0]" 
   at java.text.DateFormat.parse(DateFormat.java:366)

I think I’m wrong because I’m mapping the date with the square brackets, so I wanted to remove it. Can someone please help me?

Answer 1

To resolve I made the following change to the code

val result = data.map(row => {
    val day = dia.format(input.parse(row.toString().replace("[", "").replace("]", "").replace("(", "").replace(")", "")))  
    val month = mes.format(input.parse(row.toString().replace("[", "").replace("]", "").replace("(", "").replace(")", "")))                                       
    val year = ano.format(input.parse(row.toString().replace("[", "").replace("]", "").replace("(", "").replace(")", "")))                                        
    val hour = horas.format(input.parse(row.toString().replace("[", "").replace("]", "").replace("(", "").replace(")", "")))                                     
    val minute = minutos.format(input.parse(row.toString().replace("[", "").replace("]", "").replace("(", "").replace(")", "")))
})

I tested and it works.

Answer 2

Try this:

  def removerChaves(s: String) = s.map(c => if(c == '[') ' ' else c).map(c => if(c == ']') ' ' else c).trim

val conf = new SparkConf(true)
   .set("spark.cassandra.connection.host", "127.0.0.1").setAppName("CasteDate").setMaster("local[*]")
   .set("spark.cassandra.connection.port", "9042")
   .set("spark.driver.allowMultipleContexts", "true")
   .set("spark.streaming.receiver.writeAheadLog.enable", "true")

val sc = new SparkContext(conf)

val ssc = new StreamingContext(sc, Seconds(1))
val csc=new CassandraSQLContext(sc)

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

var input: SimpleDateFormat   = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.S")
input.setTimeZone(TimeZone.getTimeZone("GMT"))
var dia: SimpleDateFormat  = new SimpleDateFormat("dd")
var mes: SimpleDateFormat = new SimpleDateFormat("MM")
var ano: SimpleDateFormat = new SimpleDateFormat("yyyy")
var horas: SimpleDateFormat = new SimpleDateFormat("HH")
var minutos: SimpleDateFormat  = new SimpleDateFormat("mm")

val data=csc.sql("SELECT timecol from smartgrids.analyzer_temp").collect().map(c => removerChaves(c))


import sqlContext.implicits._

val result = data.map(row => {
                         val day = dia.format(input.parse(row.toString()))
                         val month = mes.format(input.parse(row.toString()))
                         val year = ano.format(input.parse(row.toString()))
                         val hour = horas.format(input.parse(row.toString()))
                         val minute = minutos.format(input.parse(row.toString()))
                             })

val collection = sc.parallelize(Seq(("day", 2), ("month", 2), ("year", 4), ("hour", 2), ("minute", 2)))
collection.saveToCassandra("features", "datepart", SomeColumns("day", "month", "year", "hour", "minute"))
sc.stop()   

I created an expression to remove Brackets removerChaves and use it on the date.