About Dirty Dictionary filtering problems-filtering dirty data with regular expressions

Data | problems | regular

Method One: Use regular expressions

1//Dirty Dictionary data store file path
2 private static string File_name= "Zang.txt";
3//Dirty data dictionary table, such as: Dirty data One | Dirty data two | dirty data three
4 public static string Dirtystr= "";
5
6 Public Validdirty ()
7 {
8 if (httpruntime.cache["Regex"]==null)
9 {
Ten dirtystr=readdic ();
11//Regular expression for detecting dirty dictionaries
The Regex validatereg= The new regex (^ (?!) +dirtystr+ "). (? <! " +dirtystr+ ")) *$", regexoptions.compiled|regexoptions.explicitcapture);
HttpRuntime.Cache.Insert ("Regex", Validatereg,null,datetime.now.addminutes (), TimeSpan.Zero);
14}
15
16}
Readdic private String ()
18 {
file_name=environment.currentdirectory+ "\" +file_name;
20
if (! File.exists (file_name))
22 {
Console.WriteLine ("{0} does not exist.", file_name);
Return "";
25}
StreamReader sr = File.OpenText (file_name);
input= String "";
A while (Sr. Peek () >-1)
29 {
input = Sr. ReadLine ();
31}
32
Sr. Close ();
return to input;
35
36}
37
38
validbyreg bool (String str)
40 {
A regex reg= (regex) httpruntime.cache["regex"];
Return Reg. IsMatch (str);
43
44}

Feel this method of execution is not very high, simple test 1000 words of the article, Dirty Dictionary has more than 800 keywords
The formula is 1.238 seconds, we have no better way, please do not hesitate to enlighten!

Method Two: General circulation search method

public bool Validgeneral (string str)
{

if (! File.exists (file_name))
{
Console.WriteLine ("File path or file path does not have error message");
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;

}

}

The following is the test method, what is the problem please point out!

1DateTime T1 =datetime.now;
2 string str= "213";
3 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
4 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
5 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
6 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
7 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
8 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
9 str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
Ten str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
One str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love cherish the love of Crystal Crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love cherish the love of Crystal Crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish the love of crystal crystal Love Cherish Crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
Panax Notoginseng str+= "Cherish the love of crystal Crystal love to cherish the love of Crystal, Crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
Wu str+= "Cherish crystal Love cherish crystal Love cherish crystal Love";
str+= "Cherish crystal Love cherish crystal love Cherish crystal Love love";
Validdirty vd=new Validdirty ();
Console.WriteLine (VD. Validbyreg (str));
DateTime T2 =datetime.now;
TimeSpan ts=t2-t1;
Console.WriteLine (TS. TotalMilliseconds);
Console.read ();

Algorithm	Retrieving text file length/time consuming (MS)
Regular algorithm	10 Chinese Characters/980	100 Chinese Characters/999	1000 Chinese Characters/1234
Common algorithm	10 Chinese characters/234	100 Chinese Characters/234	1000 Chinese Characters/265