在.NET中，GetHashCode方法在整个.NET基类库的许多地方都使用。正确执行它对于在集合中或确定相等时快速查找项目尤为重要。
对于如何为自定义类实现GetHashCode，是否有标准算法或最佳实践，以便不会降低性能？
当前回答
这是一个很好的例子：
/// <summary>
/// Helper class for generating hash codes suitable
/// for use in hashing algorithms and data structures like a hash table.
/// </summary>
public static class HashCodeHelper
{
private static int GetHashCodeInternal(int key1, int key2)
{
unchecked
{
var num = 0x7e53a269;
num = (-1521134295 * num) + key1;
num += (num << 10);
num ^= (num >> 6);
num = ((-1521134295 * num) + key2);
num += (num << 10);
num ^= (num >> 6);
return num;
}
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="arr">An array of objects used for generating the
/// hash code.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode(params object[] arr)
{
int hash = 0;
foreach (var item in arr)
hash = GetHashCodeInternal(hash, item.GetHashCode());
return hash;
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <param name="obj3">The third object.</param>
/// <param name="obj4">The fourth object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and
/// data structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2, T3, T4>(T1 obj1, T2 obj2, T3 obj3,
T4 obj4)
{
return GetHashCode(obj1, GetHashCode(obj2, obj3, obj4));
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <param name="obj3">The third object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2, T3>(T1 obj1, T2 obj2, T3 obj3)
{
return GetHashCode(obj1, GetHashCode(obj2, obj3));
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2>(T1 obj1, T2 obj2)
{
return GetHashCodeInternal(obj1.GetHashCode(), obj2.GetHashCode());
}
}
下面是如何使用它：
private struct Key
{
private Type _type;
private string _field;
public Type Type { get { return _type; } }
public string Field { get { return _field; } }
public Key(Type type, string field)
{
_type = type;
_field = field;
}
public override int GetHashCode()
{
return HashCodeHelper.GetHashCode(_field, _type);
}
public override bool Equals(object obj)
{
if (!(obj is Key))
return false;
var tf = (Key)obj;
return tf._field.Equals(_field) && tf._type.Equals(_type);
}
}
其他回答
这是一个很好的例子：
/// <summary>
/// Helper class for generating hash codes suitable
/// for use in hashing algorithms and data structures like a hash table.
/// </summary>
public static class HashCodeHelper
{
private static int GetHashCodeInternal(int key1, int key2)
{
unchecked
{
var num = 0x7e53a269;
num = (-1521134295 * num) + key1;
num += (num << 10);
num ^= (num >> 6);
num = ((-1521134295 * num) + key2);
num += (num << 10);
num ^= (num >> 6);
return num;
}
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="arr">An array of objects used for generating the
/// hash code.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode(params object[] arr)
{
int hash = 0;
foreach (var item in arr)
hash = GetHashCodeInternal(hash, item.GetHashCode());
return hash;
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <param name="obj3">The third object.</param>
/// <param name="obj4">The fourth object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and
/// data structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2, T3, T4>(T1 obj1, T2 obj2, T3 obj3,
T4 obj4)
{
return GetHashCode(obj1, GetHashCode(obj2, obj3, obj4));
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <param name="obj3">The third object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2, T3>(T1 obj1, T2 obj2, T3 obj3)
{
return GetHashCode(obj1, GetHashCode(obj2, obj3));
}
/// <summary>
/// Returns a hash code for the specified objects
/// </summary>
/// <param name="obj1">The first object.</param>
/// <param name="obj2">The second object.</param>
/// <returns>
/// A hash code, suitable for use in hashing algorithms and data
/// structures like a hash table.
/// </returns>
public static int GetHashCode<T1, T2>(T1 obj1, T2 obj2)
{
return GetHashCodeInternal(obj1.GetHashCode(), obj2.GetHashCode());
}
}
下面是如何使用它：
private struct Key
{
private Type _type;
private string _field;
public Type Type { get { return _type; } }
public string Field { get { return _field; } }
public Key(Type type, string field)
{
_type = type;
_field = field;
}
public override int GetHashCode()
{
return HashCodeHelper.GetHashCode(_field, _type);
}
public override bool Equals(object obj)
{
if (!(obj is Key))
return false;
var tf = (Key)obj;
return tf._field.Equals(_field) && tf._type.Equals(_type);
}
}
与夜编码器的解决方案非常相似，只是如果你想提高素数更容易。
PS：这是你嘴里吐出一点东西的时候之一，因为你知道这可以用9个默认值重构成一个方法，但它会更慢，所以你闭上眼睛，试着忘掉它。
/// <summary>
/// Try not to look at the source code. It works. Just rely on it.
/// </summary>
public static class HashHelper
{
private const int PrimeOne = 17;
private const int PrimeTwo = 23;
public static int GetHashCode<T1, T2, T3, T4, T5, T6, T7, T8, T9, T10>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6, T7 arg7, T8 arg8, T9 arg9, T10 arg10)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
hash = hash * PrimeTwo + arg6.GetHashCode();
hash = hash * PrimeTwo + arg7.GetHashCode();
hash = hash * PrimeTwo + arg8.GetHashCode();
hash = hash * PrimeTwo + arg9.GetHashCode();
hash = hash * PrimeTwo + arg10.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4, T5, T6, T7, T8, T9>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6, T7 arg7, T8 arg8, T9 arg9)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
hash = hash * PrimeTwo + arg6.GetHashCode();
hash = hash * PrimeTwo + arg7.GetHashCode();
hash = hash * PrimeTwo + arg8.GetHashCode();
hash = hash * PrimeTwo + arg9.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4, T5, T6, T7, T8>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6, T7 arg7, T8 arg8)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
hash = hash * PrimeTwo + arg6.GetHashCode();
hash = hash * PrimeTwo + arg7.GetHashCode();
hash = hash * PrimeTwo + arg8.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4, T5, T6, T7>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6, T7 arg7)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
hash = hash * PrimeTwo + arg6.GetHashCode();
hash = hash * PrimeTwo + arg7.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4, T5, T6>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
hash = hash * PrimeTwo + arg6.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4, T5>(T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
hash = hash * PrimeTwo + arg5.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3, T4>(T1 arg1, T2 arg2, T3 arg3, T4 arg4)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
hash = hash * PrimeTwo + arg4.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2, T3>(T1 arg1, T2 arg2, T3 arg3)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
hash = hash * PrimeTwo + arg3.GetHashCode();
return hash;
}
}
public static int GetHashCode<T1, T2>(T1 arg1, T2 arg2)
{
unchecked
{
int hash = PrimeOne;
hash = hash * PrimeTwo + arg1.GetHashCode();
hash = hash * PrimeTwo + arg2.GetHashCode();
return hash;
}
}
}
这是我的哈希码助手。它的优点是它使用泛型类型参数，因此不会导致装箱：
public static class HashHelper
{
public static int GetHashCode<T1, T2>(T1 arg1, T2 arg2)
{
unchecked
{
return 31 * arg1.GetHashCode() + arg2.GetHashCode();
}
}
public static int GetHashCode<T1, T2, T3>(T1 arg1, T2 arg2, T3 arg3)
{
unchecked
{
int hash = arg1.GetHashCode();
hash = 31 * hash + arg2.GetHashCode();
return 31 * hash + arg3.GetHashCode();
}
}
public static int GetHashCode<T1, T2, T3, T4>(T1 arg1, T2 arg2, T3 arg3,
T4 arg4)
{
unchecked
{
int hash = arg1.GetHashCode();
hash = 31 * hash + arg2.GetHashCode();
hash = 31 * hash + arg3.GetHashCode();
return 31 * hash + arg4.GetHashCode();
}
}
public static int GetHashCode<T>(T[] list)
{
unchecked
{
int hash = 0;
foreach (var item in list)
{
hash = 31 * hash + item.GetHashCode();
}
return hash;
}
}
public static int GetHashCode<T>(IEnumerable<T> list)
{
unchecked
{
int hash = 0;
foreach (var item in list)
{
hash = 31 * hash + item.GetHashCode();
}
return hash;
}
}
/// <summary>
/// Gets a hashcode for a collection for that the order of items
/// does not matter.
/// So {1, 2, 3} and {3, 2, 1} will get same hash code.
/// </summary>
public static int GetHashCodeForOrderNoMatterCollection<T>(
IEnumerable<T> list)
{
unchecked
{
int hash = 0;
int count = 0;
foreach (var item in list)
{
hash += item.GetHashCode();
count++;
}
return 31 * hash + count.GetHashCode();
}
}
/// <summary>
/// Alternative way to get a hashcode is to use a fluent
/// interface like this:<br />
/// return 0.CombineHashCode(field1).CombineHashCode(field2).
/// CombineHashCode(field3);
/// </summary>
public static int CombineHashCode<T>(this int hashCode, T arg)
{
unchecked
{
return 31 * hashCode + arg.GetHashCode();
}
}
此外，它还具有扩展方法来提供流畅的界面，因此您可以这样使用它：
public override int GetHashCode()
{
return HashHelper.GetHashCode(Manufacturer, PartN, Quantity);
}
或者像这样：
public override int GetHashCode()
{
return 0.CombineHashCode(Manufacturer)
.CombineHashCode(PartN)
.CombineHashCode(Quantity);
}
如果我们的财产不超过8处（希望如此），这里还有另一种选择。
ValueTuple是一个结构，似乎有一个可靠的GetHashCode实现。
这意味着我们可以简单地这样做：
// Yay, no allocations and no custom implementations!
public override int GetHashCode() => (this.PropA, this.PropB).GetHashCode();
让我们来看看.NETCore当前对ValueTuple的GetHashCode的实现。
这来自ValueTuple：
internal static int CombineHashCodes(int h1, int h2)
{
return HashHelpers.Combine(HashHelpers.Combine(HashHelpers.RandomSeed, h1), h2);
}
internal static int CombineHashCodes(int h1, int h2, int h3)
{
return HashHelpers.Combine(CombineHashCodes(h1, h2), h3);
}
这来自HashHelper：
public static readonly int RandomSeed = Guid.NewGuid().GetHashCode();
public static int Combine(int h1, int h2)
{
unchecked
{
// RyuJIT optimizes this to use the ROL instruction
// Related GitHub pull request: dotnet/coreclr#1830
uint rol5 = ((uint)h1 << 5) | ((uint)h1 >> 27);
return ((int)rol5 + h1) ^ h2;
}
}
英语：
向左旋转（循环移位）h1 5个位置。将结果和h1相加。将结果与h2进行异或运算。首先对{static random seed，h1}执行上述操作。对于每个其他项目，对上一个结果和下一个项目（例如h2）执行操作。
如果能更多地了解这个ROL-5散列代码算法的财产，那就太好了。
遗憾的是，为我们自己的GetHashCode延迟ValueTuple可能不像我们希望的那样快。相关讨论中的这条评论说明了直接调用HashHelpers.Combine更具性能。另一方面，这是内部的，所以我们必须复制代码，牺牲了我们在这里获得的大部分。此外，我们将负责记住首先与随机种子结合。我不知道如果我们跳过这一步会有什么后果。
使用System.HashCode
如果使用的是.NET Standard 2.1或更高版本，则可以使用System.HashCode结构。在早期的框架中，它可以从Microsoft.Bcl.HashCode包中获得。有两种使用方法：
HashCode.Combine
Combine方法可用于创建哈希代码，最多可提供八个对象。
public override int GetHashCode() => HashCode.Combine(this.object1, this.object2);
HashCode.添加
Add方法帮助您处理集合：
public override int GetHashCode()
{
var hashCode = new HashCode();
hashCode.Add(this.object1);
foreach (var item in this.collection)
{
hashCode.Add(item);
}
return hashCode.ToHashCode();
}
GetHashCode变得简单
System.HashCode的替代品，超级容易使用，但速度仍然很快。您可以阅读完整的博客文章“GetHashCode Made Easy”以了解更多详细信息和评论。
用法示例
public class SuperHero
{
public int Age { get; set; }
public string Name { get; set; }
public List<string> Powers { get; set; }
public override int GetHashCode() =>
HashCode.Of(this.Name).And(this.Age).AndEach(this.Powers);
}
实施
public struct HashCode : IEquatable<HashCode>
{
private const int EmptyCollectionPrimeNumber = 19;
private readonly int value;
private HashCode(int value) => this.value = value;
public static implicit operator int(HashCode hashCode) => hashCode.value;
public static bool operator ==(HashCode left, HashCode right) => left.Equals(right);
public static bool operator !=(HashCode left, HashCode right) => !(left == right);
public static HashCode Of<T>(T item) => new HashCode(GetHashCode(item));
public static HashCode OfEach<T>(IEnumerable<T> items) =>
items == null ? new HashCode(0) : new HashCode(GetHashCode(items, 0));
public HashCode And<T>(T item) =>
new HashCode(CombineHashCodes(this.value, GetHashCode(item)));
public HashCode AndEach<T>(IEnumerable<T> items)
{
if (items == null)
{
return new HashCode(this.value);
}
return new HashCode(GetHashCode(items, this.value));
}
public bool Equals(HashCode other) => this.value.Equals(other.value);
public override bool Equals(object obj)
{
if (obj is HashCode)
{
return this.Equals((HashCode)obj);
}
return false;
}
public override int GetHashCode() => this.value.GetHashCode();
private static int CombineHashCodes(int h1, int h2)
{
unchecked
{
// Code copied from System.Tuple a good way to combine hashes.
return ((h1 << 5) + h1) ^ h2;
}
}
private static int GetHashCode<T>(T item) => item?.GetHashCode() ?? 0;
private static int GetHashCode<T>(IEnumerable<T> items, int startHashCode)
{
var temp = startHashCode;
var enumerator = items.GetEnumerator();
if (enumerator.MoveNext())
{
temp = CombineHashCodes(temp, GetHashCode(enumerator.Current));
while (enumerator.MoveNext())
{
temp = CombineHashCodes(temp, GetHashCode(enumerator.Current));
}
}
else
{
temp = CombineHashCodes(temp, EmptyCollectionPrimeNumber);
}
return temp;
}
}
什么是好算法？
表演
计算哈希码的算法需要很快。简单的算法通常会更快。不分配额外内存的内存也会减少垃圾收集的需求，这反过来也会提高性能。
具体来说，在C#哈希函数中，您经常使用unchecked关键字来停止溢出检查以提高性能。
确定性
哈希算法需要是确定性的，即给定相同的输入，它必须始终产生相同的输出。
减少碰撞
计算哈希代码的算法需要将哈希冲突保持在最小值。哈希冲突是在两个不同对象上对GetHashCode的两次调用产生相同哈希代码时发生的情况。请注意，碰撞是允许的（有些人认为不允许），但应将其保持在最低限度。
许多哈希函数包含像17或23这样的幻数。这些是特殊的素数，与使用非素数相比，由于其数学财产有助于减少散列冲突。
哈希一致性
一个好的哈希函数应该在其输出范围内尽可能均匀地映射期望的输入，即，它应该基于均匀分布的输入输出广泛的哈希。它应该具有哈希一致性。
阻止的DoS
在.NETCore中，每次重新启动应用程序时，都会得到不同的哈希代码。这是防止拒绝服务攻击（DoS）的安全功能。对于.NET Framework，应通过添加以下App.config文件来启用此功能：
<?xml version ="1.0"?>
<configuration>
<runtime>
<UseRandomizedStringHashAlgorithm enabled="1" />
</runtime>
</configuration>
由于此特性，哈希代码不应在创建它们的应用程序域之外使用，也不应将其用作集合中的关键字段，也不应该持久化。
请在此处阅读更多信息。
加密安全？
算法不必是加密哈希函数。这意味着它不必满足以下条件：
生成生成给定哈希值的消息是不可行的。找到具有相同哈希值的两个不同消息是不可行的。对消息进行一次小的更改应该会对哈希值进行广泛的更改，以使新的哈希值看起来与旧的哈希值不相关（雪崩效应）。
推荐文章
- 如何为构造函数定制Visual Studio的私有字段生成快捷方式?
- 为什么Visual Studio 2015/2017/2019测试运行器没有发现我的xUnit v2测试
- AppSettings从.config文件中获取值
- 如何检查IEnumerable是否为空或空?
- 没有ListBox。SelectionMode="None"，是否有其他方法禁用列表框中的选择?
- 在c#代码中设置WPF文本框的背景颜色
- HyperLogLog算法是如何工作的?
- 如何在iis7应用程序池中设置。net Framework 4.5版本
- 如何分裂()一个分隔字符串到一个列表<字符串>
- 如何指定最小值，但没有使用范围数据注释属性的最大小数?
- 递归执行广度优先搜索
- 如何在PowerShell中获得本地主机名?
- 为什么在Java和。net中不能修改字符串?
- 四舍五入到一个数字的最接近倍数
- 'throw'和'throw new Exception()'的区别
