C# 實現敏感詞過濾

時間 2019-11-08

標籤 c# 實現敏感過濾欄目 C# 简体版

原文原文鏈接

　　實現該敏感詞過濾採用的是 DFA算法，參考文章：https://blog.csdn.net/chenssy/article/details/26961957node

　　具體實現步驟以下：算法

　　第一步，構建敏感詞庫（WordsLibrary）類：測試

using System.Collections.Generic;
using System.Linq;
using System;

namespace ContentSafe.SensitiveWord
{
    /// <summary>
    /// 敏感詞庫
    /// </summary>
    public class WordsLibrary
    {
        /// <summary>
        /// 詞庫樹結構類
        /// </summary>
        public class ItemTree
        {
            public char Item { get; set; }
            public bool IsEnd { get; set; }
            public List<ItemTree> Child { get; set; }
        }

        /// <summary>
        /// 詞庫樹
        /// </summary>
        public ItemTree Library { get; private set; }

        /// <summary>
        /// 敏感詞組
        /// </summary>
        public string[] Words { get; protected set; }

        /// <summary>
        /// 敏感詞庫
        /// </summary>
        public WordsLibrary()
        {
            LoadWords();
            Init();
        }

        /// <summary>
        /// 敏感詞庫
        /// </summary>
        /// <param name="words">敏感詞組</param>
        public WordsLibrary(string[] words) : this()
        {
            Words = words;
        }

        /// <summary>
        /// 加載 敏感詞組，可被重寫以自定義 如何加載 敏感詞組
        /// </summary>
        public virtual void LoadWords()
        {
        }

        /// <summary>
        /// 詞庫初始化
        /// </summary>
        private void Init()
        {
            if (Words == null)
                Words = new[] { "" };

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

        /// <summary>
        /// 建立詞庫樹
        /// </summary>
        /// <param name="words">敏感詞組</param>
        /// <returns></returns>
        private List<ItemTree> CreateTree(string[] words)
        {
            List<ItemTree> tree = null;

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

                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;
        }

        /// <summary>
        /// 建立單個完整樹
        /// </summary>
        /// <param name="word">單個敏感詞</param>
        /// <returns></returns>
        private ItemTree CreateSingleTree(string word)
        {
            //根節點，此節點 值爲空
            ItemTree root = new ItemTree();
            //移動 遊標
            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<ItemTree>() { child };
                p = child;
            }
            p.IsEnd = true;

            return root.Child.First();
        }

        /// <summary>
        /// 附加分支子樹
        /// </summary>
        /// <param name="childTree">子樹</param>
        /// <param name="word">單個敏感詞</param>
        private void AddChildTree(ItemTree childTree, string word)
        {
            //移動 遊標
            ItemTree p = childTree;

            for (int i = 1; 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，構建敏感詞檢測（ContentCheck）類：this

using System.Collections.Generic;
using System.Linq;
using System;

namespace ContentSafe.SensitiveWord
{
    /// <summary>
    /// 敏感詞檢測
    /// </summary>
    public class ContentCheck
    {
        /// <summary>
        /// 檢測文本
        /// </summary>
        public string Text { private get; set; }

        /// <summary>
        /// 敏感詞庫 詞樹
        /// </summary>
        public WordsLibrary.ItemTree Library { private get; set; }

        /// <summary>
        /// 敏感詞檢測
        /// </summary>
        public ContentCheck() { }

        /// <summary>
        /// 敏感詞檢測
        /// </summary>
        /// <param name="library">敏感詞庫</param>
        public ContentCheck(WordsLibrary library)
        {
            if (library.Library == null)
                throw new Exception("敏感詞庫未初始化");

            Library = library.Library;
        }

        /// <summary>
        /// 敏感詞檢測
        /// </summary>
        /// <param name="library">敏感詞庫</param>
        /// <param name="text">檢測文本</param>
        public ContentCheck(WordsLibrary library, string text) : this(library)
        {
            if (text == null)
                throw new Exception("檢測文本不能爲null");

            Text = text;
        }

        /// <summary>
        /// 檢測敏感詞
        /// </summary>
        /// <param name="text">檢測文本</param>
        /// <returns></returns>
        private Dictionary<int, char> WordsCheck(string text)
        {
            if (Library == null)
                throw new Exception("未設置敏感詞庫 詞樹");

            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;
        }

        /// <summary>
        /// 替換敏感詞
        /// </summary>
        /// <param name="library">敏感詞庫</param>
        /// <param name="text">檢測文本</param>
        /// <param name="newChar">替換字符</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 > 0)
            {
                char[] chars = text.ToCharArray();
                foreach (var item in dic)
                    chars[item.Key] = newChar;

                text = new string(chars);
            }

            return text;
        }

        /// <summary>
        /// 替換敏感詞
        /// </summary>
        /// <param name="text">檢測文本</param>
        /// <param name="newChar">替換字符</param>
        /// <returns></returns>
        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;
        }

        /// <summary>
        /// 替換敏感詞
        /// </summary>
        /// <param name="newChar">替換字符</param>
        /// <returns></returns>
        public string SensitiveWordsReplace(char newChar = '*')
        {
            if (Text == null)
                throw new Exception("未設置檢測文本");

            return SensitiveWordsReplace(Text, newChar);
        }

        /// <summary>
        /// 查找敏感詞
        /// </summary>
        /// <param name="library">敏感詞庫</param>
        /// <param name="text">檢測文本</param>
        /// <returns></returns>
        public static List<string> FindSensitiveWords(WordsLibrary library, string text)
        {
            ContentCheck check = new ContentCheck(library, text);
            return check.FindSensitiveWords();
        }

        /// <summary>
        /// 查找敏感詞
        /// </summary>
        /// <param name="text">檢測文本</param>
        /// <returns></returns>
        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;
        }

        /// <summary>
        /// 查找敏感詞
        /// </summary>
        /// <returns></returns>
        public List<string> FindSensitiveWords()
        {
            if (Text == null)
                throw new Exception("未設置檢測文本");

            return FindSensitiveWords(Text);
        }
    }
}

　　第三步，測試與使用方法：spa

string[] words = new[] { "敏感詞1", "敏感詞2", "含有", "垃圾" }; //敏感詞組 可自行在網上 搜索下載

//敏感詞庫 類可被繼承，若是想實現自定義 敏感詞導入方法 能夠 對 LoadWords 方法進行 重寫
var library = new WordsLibrary(words); //實例化 敏感詞庫

string text = "在任意一個文本中均可能包含敏感詞一、二、3等等，只要含有敏感詞都會被找出來，好比：垃圾";
ContentCheck check = new ContentCheck(library, text);  //實例化 內容檢測類
var list = check.FindSensitiveWords();    //調用 查找敏感詞方法 返回敏感詞列表
var str = check.SensitiveWordsReplace();  //調用 敏感詞替換方法 返回處理過的字符串

　　該實現方案不止這個使用方法，更多使用方法可自行研究.net

相關標籤/搜索

每日一句

每一个你不满意的现在，都有一个你没有努力的曾经。