.NET脏字过滤算法

方法一：使用正则表达式

 1 // 脏字典数据存放文件路径
 2          private   static   string  FILE_NAME = " zang.txt " ;
 3          // 脏数据字典表，如：脏数据一|脏数据二|脏数据三
 4          public   static   string  dirtyStr = "" ;
 5         
 6          public  ValidDirty()
 7          {
 8            if (HttpRuntime.Cache["Regex"]==null)
 9            {
10                dirtyStr=ReadDic();
11                //用于检测脏字典的正则表达式
12                Regex validateReg= new Regex("^((?!"+dirtyStr+").(?<!"+dirtyStr+"))*$",RegexOptions.Compiled|RegexOptions.ExplicitCapture);    
13                HttpRuntime.Cache.Insert("Regex" ,validateReg,null,DateTime.Now.AddMinutes(20) ,TimeSpan.Zero);
14            }
15            
16        }
17          private   string  ReadDic()
18          {
19            FILE_NAME=Environment.CurrentDirectory+"//"+FILE_NAME;
20
21            if (!File.Exists(FILE_NAME)) 
22            {
23                Console.WriteLine("{0} does not exist.", FILE_NAME);
24                return "";
25            }
26            StreamReader sr = File.OpenText(FILE_NAME);
27            String input="";
28            while (sr.Peek() > -1) 
29            {
30                input += sr.ReadLine() ;
31            }
32            
33            sr.Close();
34            return input;
35
36        }
37
38         
39          public   bool  ValidByReg( string  str)
40          {
41            Regex reg=(Regex)HttpRuntime.Cache["Regex"];
42            return reg.IsMatch(str) ;
43            
44        }

感觉这种方法的执行效率不是很高，简单的测试了一下 1000字的文章，脏字典有800多个关键字
式了一下是 1.238秒，大家有没有更好的方法，请不吝赐教！

方法二：普通循环查找方法

     public   bool  ValidGeneral( string  str)
         {
            
            if(!File.Exists(FILE_NAME))
            {
                Console.WriteLine("文件路径或者文件路径不存在错误信息") ;
                return false;
            }
            else
            {
                StreamReader objReader = new StreamReader(FILE_NAME,System.Text.Encoding.GetEncoding("gb2312"));
                string sLine="";
                ArrayList arrText = new ArrayList();

                while (sLine != null)
                {
                    sLine = objReader.ReadLine();
                    if (sLine != null)
                        arrText.Add(sLine);
                    
                }
                objReader.Close();


                foreach (string sOutput in arrText)
                {
                    string[] strArr=sOutput.Split('|');
                    
                    for (int i = 0; i < strArr.Length; i++)
                    {
                        if (str.IndexOf(strArr[i])!=-1)
                        {
                            return false;    
                        }
                        
                    }
                    
                }
                return true;

            }

        }

以下是测试的方法，有什么问题还大家请指出！

 1 DateTime t1  = DateTime.Now;
 2              string  str = " 213 " ;
 3             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 4             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 5             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 6             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 7             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 8             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
 9             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
10             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
11             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
12             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;    
13             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
14             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
15             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
16             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
17             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
18             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
19             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
20             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
21             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
22             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
23             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
24             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
25             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
26             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
27             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
28             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
29             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
30             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
31             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
32             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
33             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
34             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
35             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
36             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
37             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
38             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
39             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
40             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
41             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
42             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
43             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
44             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
45             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
46             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
47             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
48             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
49             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
50             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
51             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
52             str += " 珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋珍惜水晶之恋 " ;
53             ValidDirty vd = new  ValidDirty() ;
54             Console.WriteLine(vd.ValidByReg(str))  ;
55             DateTime t2  = DateTime.Now;
56             TimeSpan ts = t2 - t1;
57             Console.WriteLine(ts.TotalMilliseconds) ; 
58             Console.Read() ;

算法	检索文本文件长度 / 耗费时间（ms）
正则算法	10个汉字/ 980	100个汉字/999	1000个汉字/1234
普通算法	10个汉字/ 234	100个汉字/234	1000个汉字/265

脏字典下载