C# 实现敏感词过滤-.Net系列-C#-我要学365体育投注人人小站_365体育投注打不开_皇冠365体育投注网址_我要学365体育投注人人小站_365体育投注打不开_皇冠365体育投注网址是一个面向开发者的知识分享网站 365体育投注人人小站_365体育投注打不开_皇冠365体育投注网址
我的位置:首页 > .Net系列>C#

C# 实现敏感词过滤

时间:2019-11-08 16:24:00 来源:互联网 作者: 神秘的大神 字体:

  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
{
    /// 
    /// 敏感词库
    /// 
    public class WordsLibrary
    {
        /// 
        /// 词库树结构类
        /// 
        public class ItemTree
        {
            public char Item { get; set; }
            public bool IsEnd { get; set; }
            public List Child { get; set; }
        }

        /// 
        /// 词库树
        /// 
        public ItemTree Library { get; private set; }

        /// 
        /// 敏感词组
        /// 
        public string[] Words { get; protected set; }

        /// 
        /// 敏感词库
        /// 
        public WordsLibrary()
        {
            LoadWords();
            Init();
        }

        /// 
        /// 敏感词库
        /// 
        /// 敏感词组
        public WordsLibrary(string[] words) : this()
        {
            Words = words;
        }

        /// 
        /// 加载 敏感词组,可被重写以自定义 如何加载 敏感词组
        /// 
        public virtual void LoadWords()
        {
        }

        /// 
        /// 词库初始化
        /// 
        private void Init()
        {
            if (Words == null)
                Words = new[] { "" };

            Library = new ItemTree() { Item = 'R', IsEnd = false, Child = CreateTree(Words) };
        }

        /// 
        /// 创建词库树
        /// 
        /// 敏感词组
        /// 
        private List CreateTree(string[] words)
        {
            List tree = null;

            if (words != null && words.Length > 0)
            {
                tree = new List();

                foreach (var item in words)
                    if (!string.IsNullOrEmpty(item))
                    {
                        char cha = item[0];

                        ItemTree node = tree.Find(e => e.Item == cha);
                        if (node != null)
                            AddChildTree(node, item);
                        else
                            tree.Add(CreateSingleTree(item));
                    }
            }

            return tree;
        }

        /// 
        /// 创建单个完整树
        /// 
        /// 单个敏感词
        /// 
        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 = 0; i < word.Length; i++)
            {
                ItemTree child = new ItemTree() { Item = word[i], IsEnd = false, Child = null };
                p.Child = new List() { child };
                p = child;
            }
            p.IsEnd = true;

            return root.Child.First();
        }

        /// 
        /// 附加分支子树
        /// 
        /// 子树
        /// 单个敏感词
        private void AddChildTree(ItemTree childTree, string word)
        {
            //移动 游标
            ItemTree p = childTree;

            for (int i = 1; i < word.Length; i++)
            {
                char cha = word[i];
                List child = p.Child;

                if (child == null)
                {
                    ItemTree node = new ItemTree() { Item = cha, IsEnd = false, Child = null };
                    p.Child = new List() { 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
{
    /// 
    /// 敏感词检测
    /// 
    public class ContentCheck
    {
        /// 
        /// 检测文本
        /// 
        public string Text { private get; set; }

        /// 
        /// 敏感词库 词树
        /// 
        public WordsLibrary.ItemTree Library { private get; set; }

        /// 
        /// 敏感词检测
        /// 
        public ContentCheck() { }

        /// 
        /// 敏感词检测
        /// 
        /// 敏感词库
        public ContentCheck(WordsLibrary library)
        {
            if (library.Library == null)
                throw new Exception("敏感词库未初始化");

            Library = library.Library;
        }

        /// 
        /// 敏感词检测
        /// 
        /// 敏感词库
        /// 检测文本
        public ContentCheck(WordsLibrary library, string text) : this(library)
        {
            if (text == null)
                throw new Exception("检测文本不能为null");

            Text = text;
        }

        /// 
        /// 检测敏感词
        /// 
        /// 检测文本
        /// 
        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 = 0, j = 0; 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 + 1;
                            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;
        }

        /// 
        /// 替换敏感词
        /// 
        /// 敏感词库
        /// 检测文本
        /// 替换字符
        /// 
        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 > 0)
            {
                char[] chars = text.ToCharArray();
                foreach (var item in dic)
                    chars[item.Key] = newChar;

                text = new string(chars);
            }

            return text;
        }

        /// 
        /// 替换敏感词
        /// 
        /// 检测文本
        /// 替换字符
        /// 
        public string SensitiveWordsReplace(string text, char newChar = '*')
        {
            Dictionary<int, char> dic = WordsCheck(text);
            if (dic != null && dic.Keys.Count > 0)
            {
                char[] chars = text.ToCharArray();
                foreach (var item in dic)
                    chars[item.Key] = newChar;

                text = new string(chars);
            }

            return text;
        }

        /// 
        /// 替换敏感词
        /// 
        /// 替换字符
        /// 
        public string SensitiveWordsReplace(char newChar = '*')
        {
            if (Text == null)
                throw new Exception("未设置检测文本");

            return SensitiveWordsReplace(Text, newChar);
        }

        /// 
        /// 查找敏感词
        /// 
        /// 敏感词库
        /// 检测文本
        /// 
        public static List<string> FindSensitiveWords(WordsLibrary library, string text)
        {
            ContentCheck check = new ContentCheck(library, text);
            return check.FindSensitiveWords();
        }

        /// 
        /// 查找敏感词
        /// 
        /// 检测文本
        /// 
        public List<string> FindSensitiveWords(string text)
        {
            Dictionary<int, char> dic = WordsCheck(text);
            if (dic != null && dic.Keys.Count > 0)
            {
                int i = -1;
                string str = "";
                List<string> list = new List<string>();
                foreach(var item in dic)
                {
                    if (i == -1 || i + 1 == 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;
        }

        /// 
        /// 查找敏感词
        /// 
        /// 
        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