scala json fastjson json4s

 

最近有个spark任务涉及到scala操作json，大概流程是这样：从hbase取数据，每条数据先parse json，然后删除一个多余的key，最后在弄成json字符串，输出到hdfs。

json大概长这样，{“@type”:{"version":"1.0.2","name":"application-content","data":[]},"key-to-remove":[{"blah":"more blah"}],"@value":[]}

逻辑不复杂，读取hbase的部分在此略去，json相关代码如下，用fastjson解析json

package dev.json

import com.alibaba.fastjson.JSON

object Course1 {
 def main(args: Array[String]): Unit = {
 val key = "key-to-remove"
val s =
  """
  |{"@type":{"version":"1.0.2","name":"application-content","data":[]},"key-to-remove":[{"blah":"more blah"}],"@value":[]}
  |""".stripMargin
 val obj = JSON.parseObject(s)
 obj.remove(key)
 val out = obj.toJSONString
 println(out)
 }
}

然后就是一顿报错

Exception in thread "main" com.alibaba.fastjson.JSONException: expect ':' at 2, actual "

at com.alibaba.fastjson.parser.DefaultJSONParser.parseObject(DefaultJSONParser.java:296)

at com.alibaba.fastjson.parser.DefaultJSONParser.parse(DefaultJSONParser.java:1401)

at com.alibaba.fastjson.parser.DefaultJSONParser.parse(DefaultJSONParser.java:1367)

at com.alibaba.fastjson.JSON.parse(JSON.java:183)

at com.alibaba.fastjson.JSON.parse(JSON.java:193)

at com.alibaba.fastjson.JSON.parse(JSON.java:149)

at com.alibaba.fastjson.JSON.parseObject(JSON.java:254)

at dev.json.Course1$.main(Course1.scala:12)

at dev.json.Course1.main(Course1.scala)

以前用fastjson从来没碰到这样的问题，一顿百度，然后才知道是里面包含了@type的key，autotype is not supported，阿里出于安全考虑，@type容易注入一些不安全操作，所以抛出错误。查了一些资料，总算是修复了，需要加上一些选项，把所在包添加白名单，从而关闭对@type的解析。代码如下：

package dev.json

import com.alibaba.fastjson.JSON
import com.alibaba.fastjson.parser.{Feature, ParserConfig}

object Course1 {
 // 添加包白名单
ParserConfig.getGlobalInstance.addAccept("dev.json")

 def main(args: Array[String]): Unit = {
 val key = "key-to-remove"
val s =
  """
  |{"@type":{"version":"1.0.2","name":"application-content","data":[]},"key-to-remove":[{"blah":"more blah"}],"@value":[]}
  |""".stripMargin
 // 关闭特殊key检查
val obj = JSON.parseObject(s, Feature.DisableSpecialKeyDetect)
 obj.remove(key)
 val out = obj.toJSONString
 println(out)
 }
}

然后结果就可以正常解析，输出如下：

{"@value":[],"@type":{"data":[],"name":"application-content","version":"1.0.2"}}

 

这次报错，加上前段时间因为fastjson漏洞事件，公司要求紧急升级fastjson版本，瞬间对fastjson印象不那么好了，说不定哪天就全面禁止在项目中使用fastjson。所以顺便尝试了jackson的scala版本，json4s。json4s使用起来也不那么顺手，但也够用。上面的功能，用json4s重写了一个版本。

package dev.json

import org.json4s.DefaultFormats
import org.json4s.JsonDSL._
import org.json4s.jackson.JsonMethods._

object Course2 {

 implicit val formats = DefaultFormats

 def main(args: Array[String]): Unit = {
 val key = "key-to-remove"
val s =
  """
  |{"@type":{"version":"1.0.2","name":"application-content","data":[]},"key-to-remove":[{"blah":"more blah"}],"@value":[]}
  |""".stripMargin
 val obj = parse(s)
 if (null != obj) {
  val obj2 = obj.removeField(_._1.equals(key))
  val out = compact(render(obj2))
  println(out)
 }
 }
}

scala json fastjson json4s
文章转载：http://www.shaoqun.com/a/464614.html