比较字典中两个列表上的键值

Question

我试着从两个列表的字典比较一个字典的内容，我有这样的数据

data1 = [
{
"name": "MoreDependentsInd",
"description": "Form 1040-SP Indicator",
"data_type": "CheckboxType",
"xpath": "",
},
{
"name": "DependentFirstNm",
"description": "Form 1040-SR Indicator",
"data_type": "PersonNameControlType",
"xpath": "",
},
]
data2 = [
{
"id": 29,
"kind": "IN",
"container": 1,
"content": "null",
"uid": "IRS 1040-DependentDetail",
"title": "DependentDetail",
"display_name": "null",
"description": "null",
"extra_info": {
"kind": "null",
"include": {
"fields": [
{
"kind": "PersonFirstNameType",
"name": "DependentFirstNm",
"annotation": {
"documentation": {
"description": "Dependent First Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonLastNameType",
"name": "DependentLastNm",
"annotation": {
"documentation": {
"description": "Dependent Last Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonNameControlType",
"name": "DependentNameControlTxt",
"annotation": {
"documentation": {
"description": "Dependent Name Control",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "null",
"name": "IdentityProtectionPIN",
"annotation": {
"documentation": {
"description": "Dependent/Qualifying Child Identity Protection PIN",
"line_number": "(2)",
}
},
"restriction": {"rule": "null"},
},
{
"kind": "null",
"name": "DependentRelationshipCd",
"annotation": {
"documentation": {
"description": "Dependent Relationship Code",
"line_number": "(3)",
}
},
"restriction": {
"rule": {
"kind": "TextType",
"enumeration": [
"SON",
"DAUGHTER",
"STEPCHILD",
"FOSTER CHILD",
"BROTHER",
"SISTER",
"STEPBROTHER",
"STEPSISTER",
"HALF BROTHER",
"HALF SISTER",
"GRANDCHILD",
"NIECE",
"NEPHEW",
"PARENT",
"GRANDPARENT",
"AUNT",
"UNCLE",
"OTHER",
"NONE",
],
}
},
},
{
"kind": "PersonFirstNameType",
"name": "DependentFirstNm",
"annotation": {
"documentation": {
"description": "Dependent First Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonLastNameType",
"name": "DependentLastNm",
"annotation": {
"documentation": {
"description": "Dependent Last Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonNameControlType",
"name": "DependentNameControlTxt",
"annotation": {
"documentation": {
"description": "Dependent Name Control",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "null",
"name": "IdentityProtectionPIN",
"annotation": {
"documentation": {
"description": "Dependent/Qualifying Child Identity Protection PIN",
"line_number": "(2)",
}
},
"restriction": {"rule": "null"},
},
{
"kind": "null",
"name": "DependentRelationshipCd",
"annotation": {
"documentation": {
"description": "Dependent Relationship Code",
"line_number": "(3)",
}
},
"restriction": {
"rule": {
"kind": "TextType",
"enumeration": [
"SON",
"DAUGHTER",
"STEPCHILD",
"FOSTER CHILD",
"BROTHER",
"SISTER",
"STEPBROTHER",
"STEPSISTER",
"HALF BROTHER",
"HALF SISTER",
"GRANDCHILD",
"NIECE",
"NEPHEW",
"PARENT",
"GRANDPARENT",
"AUNT",
"UNCLE",
"OTHER",
"NONE",
],
}
},
},
{
"kind": "PersonFirstNameType",
"name": "DependentFirstNm",
"annotation": {
"documentation": {
"description": "Dependent First Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonLastNameType",
"name": "DependentLastNm",
"annotation": {
"documentation": {
"description": "Dependent Last Name",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "PersonNameControlType",
"name": "DependentNameControlTxt",
"annotation": {
"documentation": {
"description": "Dependent Name Control",
"line_number": "(1)",
}
},
"restriction": "null",
},
{
"kind": "null",
"name": "IdentityProtectionPIN",
"annotation": {
"documentation": {
"description": "Dependent/Qualifying Child Identity Protection PIN",
"line_number": "(2)",
}
},
"restriction": {"rule": "null"},
},
{
"kind": "null",
"name": "DependentRelationshipCd",
"annotation": {
"documentation": {
"description": "Dependent Relationship Code",
"line_number": "(3)",
}
},
"restriction": {
"rule": {
"kind": "TextType",
"enumeration": [
"SON",
"DAUGHTER",
"STEPCHILD",
"FOSTER CHILD",
"BROTHER",
"SISTER",
"STEPBROTHER",
"STEPSISTER",
"HALF BROTHER",
"HALF SISTER",
"GRANDCHILD",
"NIECE",
"NEPHEW",
"PARENT",
"GRANDPARENT",
"AUNT",
"UNCLE",
"OTHER",
"NONE",
],
}
},
},
],
"reference": "null",
},
"annotation": "null",
"max_occurs": "100",
"min_occurs": "0",
"restriction": "null",
},
"instruction": "null",
"created_at": "2022-04-26T09:53:36.426118Z",
"updated_at": "2022-04-26T09:53:36.426203Z",
},
{
"id": 30,
"kind": "IN",
"container": 1,
"content": "null",
"uid": "IRS 1040-MoreDependentsInd",
"title": "MoreDependentsInd",
"display_name": "null",
"description": "null",
"extra_info": {
"kind": "CheckboxType",
"include": "null",
"annotation": {
"documentation": {
"description": "More Dependents Indicator",
"line_number": "null",
}
},
"max_occurs": "null",
"min_occurs": "0",
"restriction": "null",
},
"instruction": "null",
"created_at": "2022-04-26T09:53:36.427552Z",
"updated_at": "2022-04-26T09:53:36.427647Z",
},
]

for i in data1:
for j in data2:
if i["name"] == j["title"]:
print("success")

的结果是成功的，但在我的代码中，有一个不足，如果它处理大量的数据那么性能会感觉很慢，如何修复它?如果值(比如数据类型)在一个键中，而我们不知道它的位置，该怎么办?

例如，我从data1中搜索值data_type，并将其与CheckboxType进行比较

"extra_info": {
"kind": "CheckboxType",
"include": "null",
"annotation": {
"documentation": {
"description": "More Dependents Indicator",
"line_number": "null",
}
},

来自索引1data2[1]的data2，但值CheckboxType也存在于另一个索引data2的另一个键

谢谢!

Answer 1

你可以在O(n)而不是O(n^2)中进行测试，通过构建name和title的集合(这是O(n))，然后取它们的交集(这也是O(n)，现在它们是集合):

>>> {i["name"] for i in data1} & {i["title"] for i in data2}
{'MoreDependentsInd'}

非空集合是真值，所以如果你不关心交集是什么，你可以在条件句中使用它:

>>> if {i["name"] for i in data1} & {i["title"] for i in data2}:
...     print("success")
...
success

如果您想查看所有字符串值，而不必知道name和title是相交键，请使用另一个生成器表达式将所有字符串值放入两个集合中:

>>> {v for i in data1 for v in i.values() if isinstance(v, str)} & {v for i in data2 for v in i.values() if isinstance(v, str)}
{'MoreDependentsInd'}