c# - 比较两个对象时有条件地更改 GetHashCode()

Question

我有两个不同的对象列表，并希望根据某些属性的权重获得它们的相似性。最快的方法似乎是实现一个 IEquatable 接口(interface)，这就是我所做的:

public class CompareEntry : IEquatable<CompareEntry>
{
    public int LeadId { get; set; }
    public int SaleId { get; set; }
    public string Email { get; set; }
    public string PhonePrivate { get; set; }
    public string PhoneMobile { get; set; }
    public string PhoneCompany { get; set; }
    public string FirstName { get; set; }
    public string Name { get; set; }
    public string City { get; set; }
    public string ZipCode { get; set; }
    public string CompanyName { get; set; }

    public bool Equals(CompareEntry other)
    {
        int weight = 0;

        //Check whether the compared object is null.
        if (Object.ReferenceEquals(other, null))
        {
            return false;
        }

        //Check whether the compared object references the same data.
        if (Object.ReferenceEquals(this, other))
        {
            return true;
        }

        if ((this.CheckProperties(this.Email, other.Email) && this.Email == other.Email)
           || (this.CheckProperties(this.PhonePrivate, other.PhonePrivate) && this.PhonePrivate == other.PhonePrivate)
           || (this.CheckProperties(this.PhoneMobile, other.PhoneMobile) && this.PhoneMobile == other.PhoneMobile)
           || (this.CheckProperties(this.PhoneCompany, other.PhoneCompany) && this.PhoneCompany == other.PhoneCompany))
        {
            weight += 100;
        }

        if ((this.CheckProperties(this.Name, other.Name) && this.Name == other.Name)
            || (this.CheckProperties(this.FirstName, other.FirstName) && this.FirstName == other.FirstName))
        {
            weight += 25;
        }

        if ((this.CheckProperties(this.City, other.City) && this.City == other.City)
            || (this.CheckProperties(this.ZipCode, other.ZipCode) && this.ZipCode == other.ZipCode))
        {
            weight += 12;
        }

        if (this.CheckProperties(this.CompanyName, other.CompanyName) && this.CompanyName == other.CompanyName)
        {
            weight += 5;
        }

        return weight > 50;
    }

    public override int GetHashCode()
    {
        unchecked
        {
            int hash = (int)2166136261;

            hash = hash * 16777619 ^ (string.IsNullOrEmpty(Email) ? 0 : Email.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(PhonePrivate) ? 0 : PhonePrivate.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(PhoneMobile) ? 0 : PhoneMobile.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(PhoneCompany) ? 0 : PhoneCompany.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(FirstName) ? 0 : FirstName.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(Name) ? 0 : Name.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(City) ? 0 : City.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(ZipCode) ? 0 : ZipCode.GetHashCode());
            //hash = hash * 16777619 ^ (string.IsNullOrEmpty(CompanyName) ? 0 : CompanyName.GetHashCode());

            return hash;
        }
    }

    private bool CheckProperties(string prop, string otherProp)
    {
        return !string.IsNullOrEmpty(prop) && !string.IsNullOrEmpty(otherProp);
    }
}

问题是，当我覆盖 GetHashCode() 方法时，我只会得到那些完全相同的人，或者在这种特殊情况下 - 只得到相同的电子邮件。

如何在 GetHashCode() 方法中有条件地检查权重，以便我可以使用更正方法 Equals？ 或者有没有一种方法可以用其他方式进行相似性检查，哪种方式性能好？

Answer 1

Equals/GetHashCode 并非旨在比较“基本相等”的事物。在这种情况下，相等只是一个 bool 属性。特别是，采用模糊的“基本相等”方法会导致传递性问题。 Object.Equals的文档包括此要求:

If (x.Equals(y) && y.Equals(z)) returns true, then x.Equals(z) returns true.

当你有模糊相等时，这根本不成立。仅仅因为 x “非常像”y 而 y “非常像”z 并不意味着x“非常像”z。

现在您可以做的是有一个只比较电话号码的相等比较器，另一个只比较名字的相等比较器，等等——但这不会真正让你模糊匹配。