Spark处理json数据

val eventsFromJSONDF = Seq (
  (0, """{"device_id": 0, "device_type": "sensor-ipad", "ip": "68.161.225.1", "cca3": "USA", "cn": "United States", "temp": 25, "signal": 23, "battery_level": 8, "c02_level": 917, "timestamp" :1475600496 }"""),
  (1, """{"device_id": 1, "device_type": "sensor-igauge", "ip": "213.161.254.1", "cca3": "NOR", "cn": "Norway", "temp": 30, "signal": 18, "battery_level": 6, "c02_level": 1413, "timestamp" :1475600498 }"""),
  (2, """{"device_id": 2, "device_type": "sensor-ipad", "ip": "88.36.5.1", "cca3": "ITA", "cn": "Italy", "temp": 18, "signal": 25, "battery_level": 5, "c02_level": 1372, "timestamp" :1475600500 }"""),
  (3, """{"device_id": 3, "device_type": "sensor-inest", "ip": "66.39.173.154", "cca3": "USA", "cn": "United States", "temp": 47, "signal": 12, "battery_level": 1, "c02_level": 1447, "timestamp" :1475600502 }"""),
  (4, """{"device_id": 4, "device_type": "sensor-ipad", "ip": "203.82.41.9", "cca3": "PHL", "cn": "Philippines", "temp": 29, "signal": 11, "battery_level": 0, "c02_level": 983, "timestamp" :1475600504 }"""),
  (5, """{"device_id": 5, "device_type": "sensor-istick", "ip": "204.116.105.67", "cca3": "USA", "cn": "United States", "temp": 50, "signal": 16, "battery_level": 8, "c02_level": 1574, "timestamp" :1475600506 }"""),
  (6, """{"device_id": 6, "device_type": "sensor-ipad", "ip": "220.173.179.1", "cca3": "CHN", "cn": "China", "temp": 21, "signal": 18, "battery_level": 9, "c02_level": 1249, "timestamp" :1475600508 }"""),
  (7, """{"device_id": 7, "device_type": "sensor-ipad", "ip": "118.23.68.227", "cca3": "JPN", "cn": "Japan", "temp": 27, "signal": 15, "battery_level": 0, "c02_level": 1531, "timestamp" :1475600512 }"""),
  (8 ,""" {"device_id": 8, "device_type": "sensor-inest", "ip": "208.109.163.218", "cca3": "USA", "cn": "United States", "temp": 40, "signal": 16, "battery_level": 9, "c02_level": 1208, "timestamp" :1475600514 }"""),
  (9,"""{"device_id": 9, "device_type": "sensor-ipad", "ip": "88.213.191.34", "cca3": "ITA", "cn": "Italy", "temp": 19, "signal": 11, "battery_level": 0, "c02_level": 1171, "timestamp" :1475600516 }""")).toDF("id", "json")

json—>DF

get_json_object($“json”,"$.字段名")

val jsDF = eventsFromJSONDF.select($"id", get_json_object($"json","$.device_type").alias("device_type"),get_json_object($"json","$.ip").alias("ip"),get_json_object($"json", "$.cca3").alias("cca3"),get_json_object($"json","$.cn").alias("cn"),get_json_object($"json","$.temp").alias("temp"),get_json_object($"json","$.signal").alias("signal")).show

在这里插入图片描述
DS—>json

from_json($“字段名”,jsonSchema)

import org.apache.spark.sql.types._
import org.apache.spark.sql.functions._
val jsonSchema = new StructType().add("battery_level", LongType).add("c02_level",LongType).add("cca3",StringType).add("cn", StringType).add("device_id",LongType).add("device_type", StringType).add("signal", LongType).add("ip",StringType).add("temp", LongType).add("timestamp", TimestampType)

先转成DS

//case class
case class DeviceData (id: Int, device: String)
// DS
val eventsDS = Seq (
  (0, """{"device_id": 0, "device_type": "sensor-ipad", "ip": "68.161.225.1", "cca3": "USA", "cn": "United States", "temp": 25, "signal": 23, "battery_level": 8, "c02_level": 917, "timestamp" :1475600496 }"""),
  (1, """{"device_id": 1, "device_type": "sensor-igauge", "ip": "213.161.254.1", "cca3": "NOR", "cn": "Norway", "temp": 30, "signal": 18, "battery_level": 6, "c02_level": 1413, "timestamp" :1475600498 }"""),
  (2, """{"device_id": 2, "device_type": "sensor-ipad", "ip": "88.36.5.1", "cca3": "ITA", "cn": "Italy", "temp": 18, "signal": 25, "battery_level": 5, "c02_level": 1372, "timestamp" :1475600500 }"""),
  (3, """{"device_id": 3, "device_type": "sensor-inest", "ip": "66.39.173.154", "cca3": "USA", "cn": "United States", "temp": 47, "signal": 12, "battery_level": 1, "c02_level": 1447, "timestamp" :1475600502 }"""),
  (4, """{"device_id": 4, "device_type": "sensor-ipad", "ip": "203.82.41.9", "cca3": "PHL", "cn": "Philippines", "temp": 29, "signal": 11, "battery_level": 0, "c02_level": 983, "timestamp" :1475600504 }"""),
  (5, """{"device_id": 5, "device_type": "sensor-istick", "ip": "204.116.105.67", "cca3": "USA", "cn": "United States", "temp": 50, "signal": 16, "battery_level": 8, "c02_level": 1574, "timestamp" :1475600506 }"""),
  (6, """{"device_id": 6, "device_type": "sensor-ipad", "ip": "220.173.179.1", "cca3": "CHN", "cn": "China", "temp": 21, "signal": 18, "battery_level": 9, "c02_level": 1249, "timestamp" :1475600508 }"""),
  (7, """{"device_id": 7, "device_type": "sensor-ipad", "ip": "118.23.68.227", "cca3": "JPN", "cn": "Japan", "temp": 27, "signal": 15, "battery_level": 0, "c02_level": 1531, "timestamp" :1475600512 }"""),
  (8 ,""" {"device_id": 8, "device_type": "sensor-inest", "ip": "208.109.163.218", "cca3": "USA", "cn": "United States", "temp": 40, "signal": 16, "battery_level": 9, "c02_level": 1208, "timestamp" :1475600514 }"""),
  (9,"""{"device_id": 9, "device_type": "sensor-ipad", "ip": "88.213.191.34", "cca3": "ITA", "cn": "Italy", "temp": 19, "signal": 11, "battery_level": 0, "c02_level": 1171, "timestamp" :1475600516 }"""),
  (10,"""{"device_id": 10, "device_type": "sensor-igauge", "ip": "68.28.91.22", "cca3": "USA", "cn": "United States", "temp": 32, "signal": 26, "battery_level": 7, "c02_level": 886, "timestamp" :1475600518 }"""),
  (11,"""{"device_id": 11, "device_type": "sensor-ipad", "ip": "59.144.114.250", "cca3": "IND", "cn": "India", "temp": 46, "signal": 25, "battery_level": 4, "c02_level": 863, "timestamp" :1475600520 }"""),
  (12, """{"device_id": 12, "device_type": "sensor-igauge", "ip": "193.156.90.200", "cca3": "NOR", "cn": "Norway", "temp": 18, "signal": 26, "battery_level": 8, "c02_level": 1220, "timestamp" :1475600522 }"""),
  (13, """{"device_id": 13, "device_type": "sensor-ipad", "ip": "67.185.72.1", "cca3": "USA", "cn": "United States", "temp": 34, "signal": 20, "battery_level": 8, "c02_level": 1504, "timestamp" :1475600524 }"""),
  (14, """{"device_id": 14, "device_type": "sensor-inest", "ip": "68.85.85.106", "cca3": "USA", "cn": "United States", "temp": 39, "signal": 17, "battery_level": 8, "c02_level": 831, "timestamp" :1475600526 }"""),
  (15, """{"device_id": 15, "device_type": "sensor-ipad", "ip": "161.188.212.254", "cca3": "USA", "cn": "United States", "temp": 27, "signal": 26, "battery_level": 5, "c02_level": 1378, "timestamp" :1475600528 }"""),
  (16, """{"device_id": 16, "device_type": "sensor-igauge", "ip": "221.3.128.242", "cca3": "CHN", "cn": "China", "temp": 10, "signal": 24, "battery_level": 6, "c02_level": 1423, "timestamp" :1475600530 }"""),
  (17, """{"device_id": 17, "device_type": "sensor-ipad", "ip": "64.124.180.215", "cca3": "USA", "cn": "United States", "temp": 38, "signal": 17, "battery_level": 9, "c02_level": 1304, "timestamp" :1475600532 }"""),
  (18, """{"device_id": 18, "device_type": "sensor-igauge", "ip": "66.153.162.66", "cca3": "USA", "cn": "United States", "temp": 26, "signal": 10, "battery_level": 0, "c02_level": 902, "timestamp" :1475600534 }"""),
  (19, """{"device_id": 19, "device_type": "sensor-ipad", "ip": "193.200.142.254", "cca3": "AUT", "cn": "Austria", "temp": 32, "signal": 27, "battery_level": 5, "c02_level": 1282, "timestamp" :1475600536 }""")).toDF("id", "device").as[DeviceData]

使用方法

eventsDS.select(from_json($"device",jsonSchema)).as("devices").select($"devices.*").show(false)

在这里插入图片描述
在这里插入图片描述
to_json

eventsDS.select(to_json(struct($"*"))).toDF("devices").show(false)

在这里插入图片描述

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值