Question

JSON1：

{ “测试”：{ “名称”： “测试”， “桶”：{ “名称”： “ ”}，“ 格式 ”：{“ JSON ”：{“ 路径 ”：“”}}， “状态”：{ “ID”： “01658204657296583104”， “模式”：{ “InputSchema”：{ “RecordColumns”：[{ “映射”： “0”， “名称”： “column0”， “SQLTYPE”：” STRING “}，{” 映射 “：” 1" ， “名称”： “列1”， “SQLTYPE”： “STRING”}，{ “映射”： “2”， “名称”： “列2”， “SQLTYPE” ： “STRING”}，{ “映射”： “3”， “名称”： “栏3”， “SQLTYPE”： “STRING”}，{ “映射”： “4”， “名称”： “column4”，” SQLTYPE “：” STRING “}，{” 映射 “：” 5" ， “名称”： “column5”， “SQLTYPE”： “STRING”}，{ “映射”： “6”， “名称”： “column6” “SQLTYPE”： “STRING”}，{ “映射”： “7”， “名称”： “time_column7”， “SQLTYPE”： “PERIOD”}，{ “映射”： “8”， “名称”：” column8" ， “SQLTYPE”： “STRING”}，{ “映射”： “9”， “名称”： “column9”， “SQLTYPE”： “STRING”}，{ “映射”： “10”， “名称” ： “column10”， “SQLTYPE”： “NUMBER”}，{ “映射”： “11”， “名称”： “column11”， “SQLTYPE”： “STRING”}，{ “映射”： “12”，”名称 “：” column12" ， “SQLTYPE”： “STRING”}，{ “映射”： “13”， “名称”： “column13”， “SQLTYPE”： “STRING”}，{ “映射”： “14” ， “名称”： “column14”， “SQLTYPE”： “NUMBER”}，{ “映射”： “15”， “名称”： “time_column15”， “SQLTYPE” ： “期间”}，{ “映射”： “16”， “名称”： “column16”， “SQLTYPE”： “NUMBER”}，{ “映射”： “17”， “名称”： “column17”，” SQLTYPE “：” STRING “}，{” 映射 “：” 18" ， “名称”： “column18”， “SQLTYPE”： “STRING”}]， “RecordEncoding”： “UTF-8”， “RecordFormat”：{ “MappingParameters”：{ “JSONMappingParameters”：{ “RecordRowPath”： “$”}}， “RecordFormatType”： “JSON”}}}， “进度”：[637637]， “源”：{” ./ allure.json “：{” LOC “：” ./ allure.json”， “ETAG”： “无”， “ID”： “”}}， “事件”：[]}}}

JSON2：

{ “测试”：{ “名称”： “测试”， “桶”：{ “名称”： “ ”}，“ 格式 ”：{“ JSON ”：{“ 路径 ”：“”}}， “状态”：{ “ID”： “01658204657296583104”， “模式”：{ “InputSchema”：{ “RecordColumns”：[{ “映射”： “0”， “名称”： “column0”， “SQLTYPE”：” STRING “}，{” 映射 “：” 1" ， “名称”： “列1”， “SQLTYPE”： “STRING”}，{ “映射”： “2”， “名称”： “列2”， “SQLTYPE” ： “STRING”}，{ “映射”： “3”， “名称”： “栏3”， “SQLTYPE”： “STRING”}，{ “映射”： “4”， “名称”： “column4”，” SQLTYPE “：” STRING “}，{” 映射 “：” 5" ， “名称”： “column5”， “SQLTYPE”： “STRING”}，{ “映射”： “6”， “名称”： “column6” “SQLTYPE”： “STRING”}，{ “映射”： “7”， “名称”： “time_column7”， “SQLTYPE”： “PERIOD”}，{ “映射”： “8”， “名称”：” column8" ， “SQLTYPE”： “STRING”}，{ “映射”： “9”， “名称”： “column9”， “SQLTYPE”： “STRING”}，{ “映射”： “10”， “名称” ： “column10”， “SQLTYPE”： “STRING”}，{ “映射”： “11”， “名称”： “column11”， “SQLTYPE”： “STRING”}，{ “映射”： “12”，”名称 “：” column12" ， “SQLTYPE”： “STRING”}，{ “映射”： “13”， “名称”： “column13”， “SQLTYPE”： “STRING”}，{ “映射”： “14” ， “名称”： “column14”， “SQLTYPE”： “NUMBER”}，{ “映射”： “15”， “名称”： “time_column15”， “SQLTYPE” ： “期间”}，{ “映射”： “16”， “名称”： “column16”， “SQLTYPE”： “NUMBER”}，{ “映射”： “17”， “名称”： “column17”，” SQLTYPE “：” STRING “}，{” 映射 “：” 18" ， “名称”： “column18”， “SQLTYPE”： “STRING”}]， “RecordEncoding”： “UTF-8”， “RecordFormat”：{ “MappingParameters”：{ “JSONMappingParameters”：{ “RecordRowPath”： “$”}}， “RecordFormatType”： “JSON”}}}， “进度”：[637637]， “源”：{” ./ allure.json “：{” LOC “：” ./ allure.json”， “ETAG”： “无”， “ID”： “01658204657296583104”}}， “事件”：[]}}}

任何人都可以帮我解决这个问题吗？我想要一个python脚本，它将比较两个JSON文件并仅返回不同的键值。

Answer 1

这个简单的代码使用递归函数来提取所有嵌入式列表/字典中的所有值。然后，它比较通过解析json1和json2获得的两个列表，并检测类似列表索引处的所有不同值：

json1 = {"test":{"name":"test","bucket":{"name":"."},"format":{"JSON":{"path":""}},"state":{"id":"01658204657296583104","schema":{"InputSchema":{"RecordColumns":[{"Mapping":"0","Name":"column0","SqlType":"STRING"},{"Mapping":"1","Name":"column1","SqlType":"STRING"},{"Mapping":"2","Name":"column2","SqlType":"STRING"},{"Mapping":"3","Name":"column3","SqlType":"STRING"},{"Mapping":"4","Name":"column4","SqlType":"STRING"},{"Mapping":"5","Name":"column5","SqlType":"STRING"},{"Mapping":"6","Name":"column6","SqlType":"STRING"},{"Mapping":"7","Name":"time_column7","SqlType":"PERIOD"},{"Mapping":"8","Name":"column8","SqlType":"STRING"},{"Mapping":"9","Name":"column9","SqlType":"STRING"},{"Mapping":"10","Name":"column10","SqlType":"NUMBER"},{"Mapping":"11","Name":"column11","SqlType":"STRING"},{"Mapping":"12","Name":"column12","SqlType":"STRING"},{"Mapping":"13","Name":"column13","SqlType":"STRING"},{"Mapping":"14","Name":"column14","SqlType":"NUMBER"},{"Mapping":"15","Name":"time_column15","SqlType":"PERIOD"},{"Mapping":"16","Name":"column16","SqlType":"NUMBER"},{"Mapping":"17","Name":"column17","SqlType":"STRING"},{"Mapping":"18","Name":"column18","SqlType":"STRING"}],"RecordEncoding":"UTF-8","RecordFormat":{"MappingParameters":{"JSONMappingParameters":{"RecordRowPath":"$"}},"RecordFormatType":"JSON"}}},"progress":[637,637],"sources":{"./allure.json":{"loc":"./allure.json","etag":"None","id":""}},"events":[]}}}
json2 = {"test":{"name":"test","bucket":{"name":"."},"format":{"JSON":{"path":""}},"state":{"id":"01658204657296583104","schema":{"InputSchema":{"RecordColumns":[{"Mapping":"0","Name":"column0","SqlType":"STRING"},{"Mapping":"1","Name":"column1","SqlType":"STRING"},{"Mapping":"2","Name":"column2","SqlType":"STRING"},{"Mapping":"3","Name":"column3","SqlType":"STRING"},{"Mapping":"4","Name":"column4","SqlType":"STRING"},{"Mapping":"5","Name":"column5","SqlType":"STRING"},{"Mapping":"6","Name":"column6","SqlType":"STRING"},{"Mapping":"7","Name":"time_column7","SqlType":"PERIOD"},{"Mapping":"8","Name":"column8","SqlType":"STRING"},{"Mapping":"9","Name":"column9","SqlType":"STRING"},{"Mapping":"10","Name":"column10","SqlType":"STRING"},{"Mapping":"11","Name":"column11","SqlType":"STRING"},{"Mapping":"12","Name":"column12","SqlType":"STRING"},{"Mapping":"13","Name":"column13","SqlType":"STRING"},{"Mapping":"14","Name":"column14","SqlType":"NUMBER"},{"Mapping":"15","Name":"time_column15","SqlType":"PERIOD"},{"Mapping":"16","Name":"column16","SqlType":"NUMBER"},{"Mapping":"17","Name":"column17","SqlType":"STRING"},{"Mapping":"18","Name":"column18","SqlType":"STRING"}],"RecordEncoding":"UTF-8","RecordFormat":{"MappingParameters":{"JSONMappingParameters":{"RecordRowPath":"$"}},"RecordFormatType":"JSON"}}},"progress":[637,637],"sources":{"./allure.json":{"loc":"./allure.json","etag":"None","id":"01658204657296583104"}},"events":[]}}}

def get_values(json, lst):
  if isinstance(json, list):
    for item in json: get_values(item, lst)
  elif isinstance(json, dict):
    for item in json.values(): get_values(item, lst)
  else: lst.append(json)

list1 = []; get_values(json1, list1)
list2 = []; get_values(json2, list2)

diff = [(n, x, y) for n,(x,y) in enumerate(zip(list1, list2)) if x != y]
print(diff)

结果：

[(36, 'NUMBER', 'STRING'), (68, '', '01658204657296583104')]

按键比较2个JSON文件，并使用python

1 个答案: