使用Jolt将含嵌套元素的对象数组转换为独立对象列表

问题描述 #

我们需要处理包含嵌套子对象的复杂对象数组，目标是拆解该结构，生成由嵌套结构中独立元素组成的新数组，以简化数据处理、提升数据分析与操作效率。当前使用给定的Jolt规则转换后，实际输出不符合预期，需调整规则，使输出为每个partyContact包含自身关联的postalAddress数组的对象列表。

输入数据（Input.json） #

{
  "link": [],
  "record": 1,
  "pageSize": 10,
  "matchedEntities": [
    {
      "busEntity": {
        "ContactView": {
          "idObject": "6940205       ",
          "ApplicationId": "CNT01",
          "clnsdNm": "Jhon cena",
          "certifiedContact": {
            "id": "2",
            "CertifiedContactDesc": "Uncertified"
          },
          "PtPostalAdd": {
            "item": [
              {
                "id": "3149850       ",
                "label": " Postal Address",
                "mainAddrCd": {
                  "id": "3             ",
                  "label": "Lookup Postal Address Type",
                  "addrTypDesc": "Primary",
                  "addrTyp": "P"
                },
                "mdmOpsAddrInd": {
                  "rowidObject": "2",
                  "label": "Lookup Postal Address Type",
                  "addrTypDesc": "Not Appliacble",
                  "addrTyp": "N"
                },
                "PostalAddress_rowidObject": "3209850",
                "PostalAddress": {
                  "rowidObject": "237",
                  "srcAddrln1": "BERNARDELLI",
                  "srcCity": "PORTO",
                  "srcState": "RJ",
                  "srcPstlCd": "5600re",
                  "srcCountryCd": {
                    "rowidObject": "32            ",
                    "label": "Lookup Source Country",
                    "cntryCd": "BR",
                    "cntryDesc": "Brazil"
                  },
                  "addrLn1": "2000 RUA FERNANDO BERNARDELLI",
                  "city": "PORTO REAL",
                  "state": "RJ",
                  "pstlCd": "27570000",
                  "countryCd": {
                    "cntryDesc": "Brazil",
                    "cntryCd": "BR"
                  }
                }
              },
              {
                "id": "43",
                "label": " Postal Address 2",
                "mainAddrCd": {
                  "id": "3             ",
                  "label": "Lookup Postal Address Type",
                  "addrTypDesc": "Primary",
                  "addrTyp": "P"
                },
                "mdmOpsAddrInd": {
                  "addrTypDesc": "Not Appliacble",
                  "addrTyp": "N"
                },
                "PostalAddress_id": "23",
                "PostalAddress": {
                  "srcAddrln1": "test",
                  "srcCity": "test",
                  "srcState": "test",
                  "srcPstlCd": "5600re",
                  "srcCountryCd": {
                    "rowidObject": "32            ",
                    "label": "Lookup Source Country",
                    "cntryCd": "BR",
                    "cntryDesc": "Brazil"
                  },
                  "addrLn1": "2000 RUA FERNANDO BERNARDELLI",
                  "city": "PORTO REAL",
                  "state": "RJ",
                  "pstlCd": "27570000",
                  "countryCd": {
                    "cntryDesc": "Brazil",
                    "cntryCd": "BR"
                  }
                }
              }
            ]
          }
        }
      },
      "matchRule": "MRS Contact Search Match|1",
      "matchScore": "100"
    },
    {
      "busEntity": {
        "ContactView": {
          "id": "6940205       ",
          "ApplicationId": "CNT02",
          "clnsdNm": "Alexis Vieira",
          "certifiedContact": {
            "CertifiedContactDesc": "Uncertified"
          },
          "PtPostalAdd": {
            "item": [
              {
                "id": "3149850       ",
                "label": " Postal Address",
                "mainAddrCd": {
                  "id": "3             ",
                  "label": "Lookup Postal Address Type",
                  "addrTypDesc": "Primary",
                  "addrTyp": "P"
                },
                "mdmOpsAddrInd": {
                  "addrTypDesc": "Not Appliacble",
                  "addrTyp": "N"
                },
                "PostalAddress_rowidObject": "3209850",
                "PostalAddress": {
                  "srcAddrln1": "BERNARDELLI",
                  "srcCity": "PORTO",
                  "srcState": "RJ",
                  "srcPstlCd": "5600re",
                  "srcCountryCd": {
                    "rowidObject": "32            ",
                    "label": "Lookup Source Country",
                    "cntryCd": "BR",
                    "cntryDesc": "Brazil"
                  },
                  "addrLn1": "2000 RUA FERNANDO BERNARDELLI",
                  "city": "PORTO REAL",
                  "state": "RJ",
                  "pstlCd": "27570000",
                  "countryCd": {
                    "cntryDesc": "Brazil",
                    "cntryCd": "BR"
                  }
                }
              }
            ]
          }
        }
      }
    }
  ],
  "facet": []
}

当前实际输出 #

{
  "partyContact" : {
    "cntId" : [ "CNT01", "CNT02" ],
    "cntName" : [ "Jhon cena", "Alexis Vieira" ],
    "certifiedContact" : [ "Uncertified", "Uncertified" ]
  },
  "postalAddress" : [ {
    "mainAddrCd" : [ "Primary", "Primary" ],
    "addressType" : [ "Not Appliacble", "Not Appliacble" ],
    "srcAddrLn1" : [ "BERNARDELLI", "BERNARDELLI" ],
    "srcCity" : [ "PORTO", "PORTO" ],
    "srcState" : [ "RJ", "RJ" ],
    "srcPstlCd" : [ "5600re", "5600re" ],
    "addressLine1" : [ "2000 RUA FERNANDO BERNARDELLI", "2000 RUA FERNANDO BERNARDELLI" ],
    "city" : [ "PORTO REAL", "PORTO REAL" ],
    "state" : [ "RJ", "RJ" ],
    "postal_Code" : [ "27570000", "27570000" ],
    "srcCountryCd" : [ "BR", "BR" ]
  }, {
    "mainAddrCd" : "Primary",
    "addressType" : "Not Appliacble",
    "srcAddrLn1" : "test",
    "srcCity" : "test",
    "srcState" : "test",
    "srcPstlCd" : "5600re",
    "addressLine1" : "2000 RUA FERNANDO BERNARDELLI",
    "city" : "PORTO REAL",
    "state" : "RJ",
    "postal_Code" : "27570000",
    "srcCountryCd" : "BR"
  } ]
}

当前使用的Jolt规则 #

[
  {
    "operation": "shift",
    "spec": {
      "matchedEntities": {
        "*": {
          "busEntity": {
            "ContactView": {
              "ApplicationId": "partyContact.cntId",
              "clnsdNm": "partyContact.cntName",
              "certifiedContact": {
                "CertifiedContactDesc": "partyContact.certifiedContact"
              },
              "PartyAlternateId": {
                "item": {
                  "*": {
                    "altIdType": {
                      "idTyp": {
                        "0002": {
                          "@(3,altIdVal)": "partyContact.partyUid"
                        },
                        "0008": {
                          "@(3,altIdVal)": "partyContact.metalPortalUserId"
                        },
                        "0011": {
                          "@(3,altIdVal)": "partyContact.ecpPortalUserId"
                        }
                      }
                    }
                  }
                }
              },
              "PtPostalAdd": {
                "item": {
                  "*": {
                    "mainAddrCd": {
                      "addrTypDesc": "postalAddress[&2].mainAddrCd"
                    },
                    "mdmOpsAddrInd": {
                      "addrTypDesc": "postalAddress[&2].addressType"
                    },
                    "PostalAddress": {
                      "srcAddrln1": "postalAddress[&2].srcAddrLn1",
                      "srcAddrln2": "postalAddress[&2].srcAddrLn2",
                      "srcAddrln3": "postalAddress[&2].srcAddrLn3",
                      "SrcAddrln4": "postalAddress[&2].srcAddrLn4",
                      "srcCity": "postalAddress[&2].srcCity",
                      "srcState": "postalAddress[&2].srcState",
                      "srcPstlCd": "postalAddress[&2].srcPstlCd",
                      "srcSystem": "postalAddress[&2][&2].srcSystem",
                      "srcDoNotStd": "postalAddress[&2].srcDoNotStd",
                      "addrId": "postalAddress[&2].addressId",
                      "addrLn1": "postalAddress[&2].addressLine1",
                      "addrLn2": "postalAddress[&2].addressLine2",
                      "addrLn3": "postalAddress[&2].addressLine3",
                      "addrLn4": "postalAddress[&2].adddressLine4",
                      "city": "postalAddress[&2].city",
                      "county": "postalAddress[&2].county",
                      "state": "postalAddress[&2].state",
                      "pstlCd": "postalAddress[&2].postal_Code",
                      "countryCd": {
                        "cntryCd": "postalAddress[&3].srcCountryCd"
                      },
                      "vldtnStsCd": "postalAddress[&2].validation_Status_Code",
                      "enrchdInd": "postalAddress[&2].enrichedIndicator"
                    }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
]

预期输出 #

[
  {
    "partyContact": {
      "cntId": "CNT01",
      "cntName": "Jhon cena",
      "certifiedContact": "Uncertified",
      "postalAddress": [
        {
          "mainAddrCd": "Primary",
          "addressType": "Not Appliacble",
          "srcAddrLn1": "BERNARDELLI",
          "srcCity": "PORTO",
          "srcState": "RJ",
          "srcPstlCd": "5600re",
          "addressLine1": "2000 RUA FERNANDO BERNARDELLI",
          "city": "PORTO REAL",
          "state": "RJ",
          "postal_Code": "27570000",
          "srcCountryCd": "BR"
        },
        {
          "mainAddrCd": "Primary",
          "addressType": "Not Appliacble",
          "srcAddrLn1": "test",
          "srcCity": "test",
          "srcState": "test",
          "srcPstlCd": "5600re",
          "addressLine1": "2000 RUA FERNANDO BERNARDELLI",
          "city": "PORTO REAL",
          "state": "RJ",
          "postal_Code": "27570000",
          "srcCountryCd": "BR"
        }
      ]
    }
  },
  {
    "partyContact": {
      "cntId": "CNT02",
      "cntName": "Alexis Vieira",
      "certifiedContact": "Uncertified",
      "postalAddress": [
        {
          "mainAddrCd": "Primary",
          "addressType": "Not Appliacble",
          "srcAddrLn1": "BERNARDELLI",
          "srcCity": "PORTO",
          "srcState": "RJ",
          "srcPstlCd": "5600re",
          "addressLine1": "2000 RUA FERNANDO BERNARDELLI",
          "city": "PORTO REAL",
          "state": "RJ",
          "postal_Code": "27570000",
          "srcCountryCd": "BR"
        }
      ]
    }
  }
]

（注：修正了原预期输出中CNT01联系人姓名的错误，应为Jhon cena）

调整后的Jolt规则 #

[
  {
    "operation": "shift",
    "spec": {
      "matchedEntities": {
        "*": {
          "busEntity": {
            "ContactView": {
              "ApplicationId": "[&1].partyContact.cntId",
              "clnsdNm": "[&1].partyContact.cntName",
              "certifiedContact": {
                "CertifiedContactDesc": "[&2].partyContact.certifiedContact"
              },
              "PtPostalAdd": {
                "item": {
                  "*": {
                    "mainAddrCd": {
                      "addrTypDesc": "[&4].partyContact.postalAddress[&1].mainAddrCd"
                    },
                    "mdmOpsAddrInd": {
                      "addrTypDesc": "[&4].partyContact.postalAddress[&1].addressType"
                    },
                    "PostalAddress": {
                      "srcAddrln1": "[&4].partyContact.postalAddress[&1].srcAddrLn1",
                      "srcCity": "[&4].partyContact.postalAddress[&1].srcCity",
                      "srcState": "[&4].partyContact.postalAddress[&1].srcState",
                      "srcPstlCd": "[&4].partyContact.postalAddress[&1].srcPstlCd",
                      "addrLn1": "[&4].partyContact.postalAddress[&1].addressLine1",
                      "city": "[&4].partyContact.postalAddress[&1].city",
                      "state": "[&4].partyContact.postalAddress[&1].state",
                      "pstlCd": "[&4].partyContact.postalAddress[&1].postal_Code",
                      "srcCountryCd": {
                        "cntryCd": "[&5].partyContact.postalAddress[&2].srcCountryCd"
                      },
                      "countryCd": {
                        "cntryCd": "[&5].partyContact.postalAddress[&2].srcCountryCd"
                      }
                    }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
]

关键修改说明 #

1. 根节点映射：使用[&1]对应matchedEntities数组的每个元素索引，将每个联系人转换为输出数组的一个独立对象。
2. 联系人字段映射：将ApplicationId、clnsdNm等字段映射到[&1].partyContact下，确保每个联系人的属性独立存在，不会合并为数组。
3. 地址关联映射：将地址字段映射到[&4].partyContact.postalAddress[&1]，其中&4对应外层matchedEntities的索引，&1对应当前PtPostalAdd.item的索引，实现每个联系人的地址数组与自身关联。

内容的提问来源于stack exchange，提问作者Rakesh GR