实现 该 敏感词过滤 采用的是 DFA算法，参考文章：https://blog.csdn.net/chenssy/article/details/26961957
具体 实现 步骤 如下：
第一步，构建 敏感词库（WordsLibrary） 类：
using System.Collections.Generic;
using System.Linq;
using System; namespace ContentSafe.SensitiveWord
{
/// <summary>
/// 敏感词库
/// </summary>
public class WordsLibrary
{
/// <summary>
/// 词库树结构类
/// </summary>
public class ItemTree
{
public char Item { get; set; }
public bool IsEnd { get; set; }
public List<ItemTree> Child { get; set; }
} /// <summary>
/// 词库树
/// </summary>
public ItemTree Library { get; private set; } /// <summary>
/// 敏感词组
/// </summary>
public string[] Words { get; protected set; } /// <summary>
/// 敏感词库
/// </summary>
public WordsLibrary()
{
LoadWords();
Init();
} /// <summary>
/// 敏感词库
/// </summary>
/// <param name="words">敏感词组</param>
public WordsLibrary(string[] words) : this()
{
Words = words;
} /// <summary>
/// 加载 敏感词组，可被重写以自定义 如何加载 敏感词组
/// </summary>
public virtual void LoadWords()
{
} /// <summary>
/// 词库初始化
/// </summary>
private void Init()
{
if (Words == null)
Words = new[] { "" }; Library = new ItemTree() { Item = 'R', IsEnd = false, Child = CreateTree(Words) };
} /// <summary>
/// 创建词库树
/// </summary>
/// <param name="words">敏感词组</param>
/// <returns></returns>
private List<ItemTree> CreateTree(string[] words)
{
List<ItemTree> tree = null; if (words != null && words.Length > )
{
tree = new List<ItemTree>(); foreach (var item in words)
if (!string.IsNullOrEmpty(item))
{
char cha = item[]; ItemTree node = tree.Find(e => e.Item == cha);
if (node != null)
AddChildTree(node, item);
else
tree.Add(CreateSingleTree(item));
}
} return tree;
} /// <summary>
/// 创建单个完整树
/// </summary>
/// <param name="word">单个敏感词</param>
/// <returns></returns>
private ItemTree CreateSingleTree(string word)
{
//根节点，此节点 值为空
ItemTree root = new ItemTree();
//移动 游标
ItemTree p = root; for (int i = ; i < word.Length; i++)
{
ItemTree child = new ItemTree() { Item = word[i], IsEnd = false, Child = null };
p.Child = new List<ItemTree>() { child };
p = child;
}
p.IsEnd = true; return root.Child.First();
} /// <summary>
/// 附加分支子树
/// </summary>
/// <param name="childTree">子树</param>
/// <param name="word">单个敏感词</param>
private void AddChildTree(ItemTree childTree, string word)
{
//移动 游标
ItemTree p = childTree; for (int i = ; i < word.Length; i++)
{
char cha = word[i];
List<ItemTree> child = p.Child; if (child == null)
{
ItemTree node = new ItemTree() { Item = cha, IsEnd = false, Child = null };
p.Child = new List<ItemTree>() { node };
p = node;
}
else
{
ItemTree node = child.Find(e => e.Item == cha);
if (node == null)
{
node = new ItemTree() { Item = cha, IsEnd = false, Child = null };
child.Add(node);
p = node;
}
else
p = node;
}
}
p.IsEnd = true;
}
}
}
第二步，构建 敏感词检测（ContentCheck） 类：
using System.Collections.Generic;
using System.Linq;
using System; namespace ContentSafe.SensitiveWord
{
/// <summary>
/// 敏感词检测
/// </summary>
public class ContentCheck
{
/// <summary>
/// 检测文本
/// </summary>
public string Text { private get; set; } /// <summary>
/// 敏感词库 词树
/// </summary>
public WordsLibrary.ItemTree Library { private get; set; } /// <summary>
/// 敏感词检测
/// </summary>
public ContentCheck() { } /// <summary>
/// 敏感词检测
/// </summary>
/// <param name="library">敏感词库</param>
public ContentCheck(WordsLibrary library)
{
if (library.Library == null)
throw new Exception("敏感词库未初始化"); Library = library.Library;
} /// <summary>
/// 敏感词检测
/// </summary>
/// <param name="library">敏感词库</param>
/// <param name="text">检测文本</param>
public ContentCheck(WordsLibrary library, string text) : this(library)
{
if (text == null)
throw new Exception("检测文本不能为null"); Text = text;
} /// <summary>
/// 检测敏感词
/// </summary>
/// <param name="text">检测文本</param>
/// <returns></returns>
private Dictionary<int, char> WordsCheck(string text)
{
if (Library == null)
throw new Exception("未设置敏感词库 词树"); Dictionary<int, char> dic = new Dictionary<int, char>();
WordsLibrary.ItemTree p = Library;
List<int> indexs = new List<int>(); for (int i = , j = ; j < text.Length; j++)
{
char cha = text[j];
var child = p.Child; var node = child.Find(e => e.Item == cha);
if (node != null)
{
indexs.Add(j);
if (node.IsEnd || node.Child == null)
{
if (node.Child != null)
{
int k = j + ;
if (k < text.Length && node.Child.Exists(e => e.Item == text[k]))
{
p = node;
continue;
}
} foreach (var item in indexs)
dic.Add(item, text[item]); indexs.Clear();
p = Library;
i = j;
++i;
}
else
p = node;
}
else
{
indexs.Clear();
if (p.GetHashCode() != Library.GetHashCode())
{
++i;
j = i;
p = Library;
}
else
i = j;
}
} return dic;
} /// <summary>
/// 替换敏感词
/// </summary>
/// <param name="library">敏感词库</param>
/// <param name="text">检测文本</param>
/// <param name="newChar">替换字符</param>
/// <returns></returns>
public static string SensitiveWordsReplace(WordsLibrary library, string text, char newChar = '*')
{
Dictionary<int, char> dic = new ContentCheck(library).WordsCheck(text);
if (dic != null && dic.Keys.Count > )
{
char[] chars = text.ToCharArray();
foreach (var item in dic)
chars[item.Key] = newChar; text = new string(chars);
} return text;
} /// <summary>
/// 替换敏感词
/// </summary>
/// <param name="text">检测文本</param>
/// <param name="newChar">替换字符</param>
/// <returns></returns>
public string SensitiveWordsReplace(string text, char newChar = '*')
{
Dictionary<int, char> dic = WordsCheck(text);
if (dic != null && dic.Keys.Count > )
{
char[] chars = text.ToCharArray();
foreach (var item in dic)
chars[item.Key] = newChar; text = new string(chars);
} return text;
} /// <summary>
/// 替换敏感词
/// </summary>
/// <param name="newChar">替换字符</param>
/// <returns></returns>
public string SensitiveWordsReplace(char newChar = '*')
{
if (Text == null)
throw new Exception("未设置检测文本"); return SensitiveWordsReplace(Text, newChar);
} /// <summary>
/// 查找敏感词
/// </summary>
/// <param name="library">敏感词库</param>
/// <param name="text">检测文本</param>
/// <returns></returns>
public static List<string> FindSensitiveWords(WordsLibrary library, string text)
{
ContentCheck check = new ContentCheck(library, text);
return check.FindSensitiveWords();
} /// <summary>
/// 查找敏感词
/// </summary>
/// <param name="text">检测文本</param>
/// <returns></returns>
public List<string> FindSensitiveWords(string text)
{
Dictionary<int, char> dic = WordsCheck(text);
if (dic != null && dic.Keys.Count > )
{
int i = -;
string str = "";
List<string> list = new List<string>();
foreach(var item in dic)
{
if (i == - || i + == item.Key)
str += item.Value;
else
{
list.Add(str);
str = "" + item.Value;
} i = item.Key;
}
list.Add(str); return list.Distinct().ToList();
}
else
return null;
} /// <summary>
/// 查找敏感词
/// </summary>
/// <returns></returns>
public List<string> FindSensitiveWords()
{
if (Text == null)
throw new Exception("未设置检测文本"); return FindSensitiveWords(Text);
}
}
}
第三步，测试与使用方法：
string[] words = new[] { "敏感词1", "敏感词2", "含有", "垃圾" }; //敏感词组 可自行在网上 搜索下载
//敏感词库 类可被继承，如果想实现自定义 敏感词导入方法 可以 对 LoadWords 方法进行 重写
var library = new WordsLibrary(words); //实例化 敏感词库
string text = "在任意一个文本中都可能包含敏感词1、2、3等等，只要含有敏感词都会被找出来，比如：垃圾";
ContentCheck check = new ContentCheck(library, text); //实例化 内容检测类
var list = check.FindSensitiveWords(); //调用 查找敏感词方法 返回敏感词列表
var str = check.SensitiveWordsReplace(); //调用 敏感词替换方法 返回处理过的字符串该 实现方案 不止 这个 使用方法，更多使用方法 可自行 研究