一下实现对敏感词,禁忌词的过滤.

两个个文件words.properties和KeyWordFilter.java;

1、words.properties文件是个文本文件；内容如下:

敏感词一

敏感词二

敏感词三

2、KeyWordFilter.java是个java文件内容如下:

import java.io.IOException;

import java.io.InputStream;

import java.text.SimpleDateFormat;

import java.util.Date;

import java.util.Enumeration;

import java.util.Properties;

import java.util.regex.Pattern;

import java.util.regex.Matcher;

public class KeyWordFilter

{

private static Pattern pattern = null;

// 从words.properties初始化正则表达式字符串

private static void initPattern()

{

StringBuffer patternBuf = new StringBuffer("");

try

{

InputStream in = KeyWordFilter.class.getClassLoader().getResourceAsStream("words.properties");

Properties pro = new Properties();

pro.load(in);

Enumeration enu = pro.propertyNames();

patternBuf.append("(");

while(enu.hasMoreElements())

{

patternBuf.append((String)enu.nextElement()+"|");

}

patternBuf.deleteCharAt(patternBuf.length()-1);

patternBuf.append(")");

//unix换成UTF-8

//pattern = Pattern.compile(new String(patternBuf.toString().getBytes("ISO-8859-1"), "UTF-8"));

//win下换成gb2312

pattern = Pattern.compile(new String(patternBuf.toString().getBytes("ISO-8859-1"), "gb2312"));

}

catch(IOException ioEx)

{

ioEx.printStackTrace();

}

}

private static String doFilter(String str)

{

Matcher m = pattern.matcher(str);

str = m.replaceAll("");

return str;

}

public static void main(String[] args)

{

String str = "国敏感词一院学位办就敏感词三的报道表示敏感词二";

System.out.println("str:"+str);

initPattern();

Date d1 = new Date();

SimpleDateFormat formatter = new SimpleDateFormat("EEE, d MMM yyyy HH:mm:ss:SSS Z");

System.out.println("start:"+formatter.format(d1));

System.out.println("共"+str.length()+"个字符，查到" + KeyWordFilter.doFilter(str));

Date d2 = new Date();

System.out.println("end:"+formatter.format(d2));

}

}

输出为:

__________________________________

str:国敏感词一院学位办就敏感词三的报道表示敏感词二

start:星期二, 24 三月 2009 14:50:17:171 +0800

共23个字符，查到国院学位办就的报道表示

end:星期二, 24 三月 2009 14:50:17:531 +0800