检测敏感词功能

今天策划给我一个任务 ------ 检测昵称中是否含有敏感词功能，然后丢给我两个压缩包，我解压一看：

有的txt文件是一行一个词：

有的txt文件是按逗号分隔开：

不管是什么格式的总之量非常多，把我这辈子脏话都囊括了🥶

读取TXT文件数据

然后我得先对这些txt文件进行处理转换成我们能用的格式：一开始我直接for循环查找是否含有敏感词，后边找资料看到一个DFA算法。

cs 复制代码

using System;
using System.Text;
using System.Collections.Generic;
using System.IO;

public class Program
{
    static void Main()
    {
        //换行的txt文件
        List<string> list = LineFeed();
        //带有逗号的txt文件
        Comma();

        string name = "假如这是敏感词";

        //检测昵称中是否含有敏感词
        CensorText(name, list);

        Console.Read();
    }

    static void CensorText(string text, List<string> list)
    {
        foreach (string line in list)
        {
            if (text.Contains(line))
            {
                Console.WriteLine("昵称中存在无法使用的字符，请修改后再次确认");
            }
        }
    }

    //用换行分割的txt文件
    static List<string> LineFeed() 
    {
        string filePath = "E:\\C#Project\\PBZ\\反动词库.txt"; // 替换为你的 txt 文件路径
        List<string> lines = ReadTxtFile(filePath);

        string a = "";
        foreach (string line in lines)
        {
            a += "\"" + line + "\",";

        }
        Console.WriteLine(a);
        return lines;
    }

    static List<string> ReadTxtFile(string filePath)
    {
        List<string> lines = new List<string>();

        try
        {
            using (StreamReader sr = new StreamReader(filePath))
            {
                string line;
                while ((line = sr.ReadLine()) != null)
                {
                    lines.Add(line);
                }
            }
        }
        catch (Exception e)
        {
            Console.WriteLine("读取文件时出现错误: " + e.Message);
        }

        return lines;
    }

    //用逗号分隔的txt文件
    static void Comma() 
    {
        string filePath = "E:\\C#Project\\PBZ\\GFW补充词库.txt"; // 替换为你的 txt 文件路径
        List<string> elements = ReadTxtFile1(filePath);

        string a = "";
        foreach (string element in elements)
        {
            a += "\"" + element + "\",";
        }
        Console.WriteLine(a);
    }

    static List<string> ReadTxtFile1(string filePath)
    {
        List<string> elements = new List<string>();

        try
        {
            using (StreamReader sr = new StreamReader(filePath))
            {
                string line = sr.ReadLine();
                if (line != null)
                {
                    string[] splitElements = line.Split(',');
                    foreach (string element in splitElements)
                    {
                        elements.Add(element);
                    }
                }
            }
        }
        catch (Exception e)
        {
            Console.WriteLine("读取文件时出现错误: " + e.Message);
        }

        return elements;
    }
}

这样处理过后的数据就是List<string>,或者可以处理成数组、集合都可以

我把处理出来的数据放在HashSet中

cs 复制代码

/// <summary>
/// 敏感词词库
/// </summary>
public static HashSet<string> MaskWord = new HashSet<string>
{
   "敏感词1","敏感词2","敏感词3","..."
}

C#版DFA算法

然后通过C#版的DFA算法判断昵称中是否含有敏感词返回bool型放在工具类中使用：

java实现敏感词过滤（DFA算法） - AlanLee-Java - 博客园

敏感词管理（DFA算法实现）_dfa算法初始化map-CSDN博客

敏感词过滤-DFA算法-CSDN博客

cs 复制代码

/// <summary>
/// 检测敏感词
/// </summary>
/// <param name="text">要检测的词</param>
/// <param name="MaskWord">敏感词词库</param>
/// <returns></returns>
public static bool CheckSensitiveWords(string text)
{
	Dictionary<string, Dictionary<string, string>> stateMap = new Dictionary<string, Dictionary<string, string>>();
	Dictionary<string, string> currentState = new Dictionary<string, string>();
	char[] chars;

	foreach (string word in MaskWord)
	{
		currentState = stateMap.ContainsKey("0") ? stateMap["0"] : new Dictionary<string, string>();
		Dictionary<string, string> nextState;
		chars = word.ToCharArray();
		for (int i = 0; i < chars.Length; i++)
		{
			string c = chars[i].ToString();
			string nextStateKey = i == chars.Length - 1 ? "end" : (i + 1).ToString();
			if (currentState.ContainsKey(c))
			{
				nextState = stateMap[currentState[c]];
			}
			else
			{
				nextState = new Dictionary<string, string>();
				stateMap[currentState.Count.ToString()] = nextState;
				currentState[c] = currentState.Count.ToString();
			}
				currentState = nextState;
				currentState["end"] = "end";
		}
	}

	currentState = stateMap.ContainsKey("0") ? stateMap["0"] : new Dictionary<string, string>();
	chars = text.ToCharArray();
	for (int i = 0; i < chars.Length; i++)
	{
		string c = chars[i].ToString();
		if (currentState.ContainsKey(c))
		{
			currentState = stateMap[currentState[c]];
			if (currentState.ContainsKey("end"))
			{
				return true; // 匹配到敏感词
			}
		}
		else
		{
			currentState = stateMap.ContainsKey("0") ? stateMap["0"] : new Dictionary<string, string>();
		}
	}
	return false; // 未匹配到敏感词
}