快捷導(dǎo)航

基于C#檢測(cè)敏感詞功能

更新時(shí)間：2024年11月08日 15:18:11 作者：Lazy龍

這篇文章主要為大家詳細(xì)介紹了如何基于C#實(shí)現(xiàn)檢測(cè)敏感詞功能,文中的示例代碼講解詳細(xì),感興趣的小伙伴可以跟隨小編一起學(xué)習(xí)一下

讀取TXT文件數(shù)據(jù)

然后我得先對(duì)這些txt文件進(jìn)行處理轉(zhuǎn)換成我們能用的格式：一開始我直接for循環(huán)查找是否含有敏感詞，后邊找資料看到一個(gè)DFA算法。

using System;
using System.Text;
using System.Collections.Generic;
using System.IO;
 
public class Program
{
    static void Main()
    {
        //換行的txt文件
        List<string> list = LineFeed();
        //帶有逗號(hào)的txt文件
        Comma();
 
        string name = "假如這是敏感詞";
 
        //檢測(cè)昵稱中是否含有敏感詞
        CensorText(name, list);
 
        Console.Read();
    }
 
    static void CensorText(string text, List<string> list)
    {
        foreach (string line in list)
        {
            if (text.Contains(line))
            {
                Console.WriteLine("昵稱中存在無(wú)法使用的字符，請(qǐng)修改后再次確認(rèn)");
            }
        }
    }
 
    //用換行分割的txt文件
    static List<string> LineFeed() 
    {
        string filePath = "E:\\C#Project\\PBZ\\反動(dòng)詞庫(kù).txt"; // 替換為你的 txt 文件路徑
        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("讀取文件時(shí)出現(xiàn)錯(cuò)誤: " + e.Message);
        }
 
        return lines;
    }
 
    //用逗號(hào)分隔的txt文件
    static void Comma() 
    {
        string filePath = "E:\\C#Project\\PBZ\\GFW補(bǔ)充詞庫(kù).txt"; // 替換為你的 txt 文件路徑
        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("讀取文件時(shí)出現(xiàn)錯(cuò)誤: " + e.Message);
        }
 
        return elements;
    }
}

這樣處理過(guò)后的數(shù)據(jù)就是List<string>,或者可以處理成數(shù)組、集合都可以

我把處理出來(lái)的數(shù)據(jù)放在HashSet中

/// <summary>
/// 敏感詞詞庫(kù)
/// </summary>
public static HashSet<string> MaskWord = new HashSet<string>
{
   "敏感詞1","敏感詞2","敏感詞3","..."
}

C#版DFA算法

然后通過(guò)C#版的DFA算法判斷昵稱中是否含有敏感詞返回bool型放在工具類中使用：

java實(shí)現(xiàn)敏感詞過(guò)濾（DFA算法）

敏感詞管理（DFA算法實(shí)現(xiàn)）

/// <summary>
/// 檢測(cè)敏感詞
/// </summary>
/// <param name="text">要檢測(cè)的詞</param>
/// <param name="MaskWord">敏感詞詞庫(kù)</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; // 匹配到敏感詞
			}
		}
		else
		{
			currentState = stateMap.ContainsKey("0") ? stateMap["0"] : new Dictionary<string, string>();
		}
	}
	return false; // 未匹配到敏感詞
}

到此這篇關(guān)于基于C#檢測(cè)敏感詞功能的文章就介紹到這了,更多相關(guān)C#檢測(cè)敏感詞內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: