1

我正在尝试为名为Row. 行是命名Vals 的列表，其中 aVal要么是原子的，要么Bin是嵌套的Row。

这是我的代码：

package com.dtci.data.anonymize.parquet

import java.nio.charset.StandardCharsets
import org.scalacheck.Gen

object TestApp extends App {

  sealed trait Val
  case class Bin(bytes: Array[Byte]) extends Val
  object Bin {
    def from_string(str: String): Bin = Bin(str.getBytes(StandardCharsets.UTF_8))
  }
  case class Row(flds: List[(String, Val)]) extends Val

  val gen_bin = Gen.alphaStr.map(Bin.from_string)
  val gen_field_name = Gen.alphaLowerStr
  val gen_field = Gen.zip(gen_field_name, gen_val)
  val gen_row = Gen.nonEmptyListOf(gen_field).map(Row.apply)
  def gen_val: Gen[Val] = Gen.oneOf(gen_bin, gen_row)

  gen_row.sample.get.flds.foreach( fld => println(s"${fld._1} --> ${fld._2}"))
}

它因以下堆栈跟踪而崩溃：

Exception in thread "main" java.lang.NullPointerException
    at org.scalacheck.Gen.$anonfun$flatMap$2(Gen.scala:84)
    at org.scalacheck.Gen$R.flatMap(Gen.scala:243)
    at org.scalacheck.Gen$R.flatMap$(Gen.scala:240)
    at org.scalacheck.Gen$R$$anon$3.flatMap(Gen.scala:228)
    at org.scalacheck.Gen.$anonfun$flatMap$1(Gen.scala:84)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen$$anon$1.$anonfun$doApply$1(Gen.scala:110)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$1.doApply(Gen.scala:109)
    at org.scalacheck.Gen.$anonfun$map$1(Gen.scala:79)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen.$anonfun$flatMap$2(Gen.scala:84)
    at org.scalacheck.Gen$R.flatMap(Gen.scala:243)
    at org.scalacheck.Gen$R.flatMap$(Gen.scala:240)
    at org.scalacheck.Gen$R$$anon$3.flatMap(Gen.scala:228)
    at org.scalacheck.Gen.$anonfun$flatMap$1(Gen.scala:84)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen$$anon$1.$anonfun$doApply$1(Gen.scala:110)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$1.doApply(Gen.scala:109)
    at org.scalacheck.Gen$.$anonfun$sequence$2(Gen.scala:492)
    at scala.collection.LinearSeqOps.foldLeft(LinearSeq.scala:168)
    at scala.collection.LinearSeqOps.foldLeft$(LinearSeq.scala:164)
    at scala.collection.immutable.List.foldLeft(List.scala:79)
    at org.scalacheck.Gen$.$anonfun$sequence$1(Gen.scala:490)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen.$anonfun$map$1(Gen.scala:79)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen$$anon$1.$anonfun$doApply$1(Gen.scala:110)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$1.doApply(Gen.scala:109)
    at org.scalacheck.Gen.$anonfun$flatMap$2(Gen.scala:84)
    at org.scalacheck.Gen$R.flatMap(Gen.scala:243)
    at org.scalacheck.Gen$R.flatMap$(Gen.scala:240)
    at org.scalacheck.Gen$R$$anon$3.flatMap(Gen.scala:228)
    at org.scalacheck.Gen.$anonfun$flatMap$1(Gen.scala:84)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen$.$anonfun$sized$1(Gen.scala:551)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen$$anon$1.$anonfun$doApply$1(Gen.scala:110)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$1.doApply(Gen.scala:109)
    at org.scalacheck.Gen.$anonfun$map$1(Gen.scala:79)
    at org.scalacheck.Gen$Parameters.useInitialSeed(Gen.scala:318)
    at org.scalacheck.Gen$$anon$5.doApply(Gen.scala:255)
    at org.scalacheck.Gen.sample(Gen.scala:154)

我的代码有什么问题，我自己诊断它的最佳方法是什么？

作为说明，我已经看到关于Gen.oneOf严格和需要Gen.lzy递归结构的评论。但是，如果在我的代码中包装了gen_valinside of的定义，Gen.lzy(...)那么我会得到堆栈溢出而不是当前的空指针异常。

4

1 回答 1

0

首先，小心使用object Main extends App. main我发现它的字段初始化语义不如具有逐行语义的普通旧语义那么明显：

object Main {
  def main(args: Array[String]): Unit = {...}
}

这可能是NullPointerException.

通常，可以通过仔细检查字段初始化顺序并将其中一些（或全部）标记val为lazy.

这StackOverflowError是由于生成的数据结构太深而引起的。

通常，当您处理任何类型的递归时，请始终考虑递归应该停止的基本情况以及最终将达到基本情况的步骤。

在您的特定情况下，我们可以利用Gen.sized和Gen.resize负责生成元素的“大”程度（结帐文档和谷歌以获取更多信息）。

package com.dtci.data.anonymize.parquet

import java.nio.charset.StandardCharsets
import org.scalacheck.Gen

object Main extends App {

  sealed trait Val
  case class Bin(bytes: Array[Byte]) extends Val
  object Bin {
    def from_string(str: String): Bin = Bin(str.getBytes(StandardCharsets.UTF_8))
  }
  case class Row(flds: List[(String, Val)]) extends Val

  val gen_bin = Gen.alphaStr.map(Bin.from_string)
  val gen_field_name = Gen.alphaLowerStr
  val gen_field = Gen.zip(gen_field_name, gen_val)
  val gen_row = Gen.sized(size => Gen.resize(size / 2, Gen.nonEmptyListOf(gen_field).map(Row.apply)))

  def gen_val: Gen[Val] = Gen.sized { size =>
    if (size <= 0) {
      gen_bin
    } else {
      Gen.oneOf(gen_bin, gen_row)
    }
  }

  gen_row.sample.get.flds.foreach(fld => println(s"${fld._1} --> ${fld._2}"))
}
于 2020-07-14T15:57:45.007 回答