- DFA 方法
private CSLogger logger = Loggers.getLogger(SensitiveWordDAFService.class);
private static Map sensitiveWordMap=new HashMap();
public static int minMatchTYpe = 1; //最小匹配规则
public static int maxMatchType = 2; //最大匹配规则
public SensitiveWordDAFService() {
//添加敏感词
long start = System.currentTimeMillis();
SensitiveWordUtil sensitiveWordUtil=new SensitiveWordUtil();
addSensitiveWordToHashMap(sensitiveWordUtil.getSensitiveWordSet());
logger.info("敏感词加载时间:"+(System.currentTimeMillis()-start)+"ms");
}
/**
* DFA 算法
* @param keyWordSet 敏感词库
*/
public static void addSensitiveWordToHashMap(Set<String> keyWordSet) {
if(keyWordSet==null){
return;
}
sensitiveWordMap = new HashMap(keyWordSet.size()); //初始化敏感词容器，减少扩容操作
String key = null;
Map nowMap = null;
Map<String, String> newWorMap = null;
//迭代keyWordSet
Iterator<String> iterator = keyWordSet.iterator();
while(iterator.hasNext()){
key = iterator.next(); //关键字
nowMap = sensitiveWordMap;
for(int i = 0 ; i < key.length() ; i++){
char keyChar = key.charAt(i); //转换成char型
Object wordMap = nowMap.get(keyChar); //获取
if(wordMap != null){ //如果存在该key，直接赋值
nowMap = (Map) wordMap;
}
else{ //不存在则，则构建一个map，同时将isEnd设置为0，因为他不是最后一个
newWorMap = new HashMap<String,String>();
newWorMap.put("isEnd", "0"); //不是最后一个
nowMap.put(keyChar, newWorMap);
nowMap = newWorMap;
}
if(i == key.length() - 1){
nowMap.put("isEnd", "1"); //最后一个
}
}
}
}
/**
* 检查文字中是否包含敏感字符，检查规则如下：
* @param txt
* @param beginIndex
* @param matchType
* @return，如果存在，则返回敏感词字符的长度，不存在返回0
* @version 1.0
*/
public int CheckSensitiveWord(String txt,int beginIndex,int matchType){
boolean flag = false; //敏感词结束标识位：用于敏感词只有1位的情况
int matchFlag = 0; //匹配标识数默认为0
char word = 0;
Map nowMap = sensitiveWordMap;
for(int i = beginIndex; i < txt.length() ; i++){
word = txt.charAt(i);
nowMap = (Map) nowMap.get(word); //获取指定key
if(nowMap != null){ //存在，则判断是否为最后一个
matchFlag++; //找到相应key，匹配标识+1
if("1".equals(nowMap.get("isEnd"))){ //如果为最后一个匹配规则,结束循环，返回匹配标识数
flag = true; //结束标志位为true
if(minMatchTYpe == matchType){ //最小规则，直接返回,最大规则还需继续查找
break;
}
}
}
else{ //不存在，直接返回
break;
}
}
if(matchFlag < 2 || !flag){
matchFlag = 0;
}
return matchFlag;
}
/**
* 判断文字是否包含敏感字符
* @author chenming
* @date 2014年4月20日 下午4:28:30
* @param txt 文字
* @param matchType 匹配规则 1：最小匹配规则，2：最大匹配规则
* @return 若包含返回true，否则返回false
* @version 1.0
*/
public boolean isContaintSensitiveWord(String txt,int matchType){
boolean flag = false;
for(int i = 0 ; i < txt.length() ; i++){
int matchFlag = this.CheckSensitiveWord(txt, i, matchType); //判断是否包含敏感字符
if(matchFlag > 0){ //大于0存在，返回true
flag = true;
}
}
return flag;
}
/**
* 获取文字中的敏感词
* @param txt 文字
* @param matchType 匹配规则 1：最小匹配规则，2：最大匹配规则
* @return
* @version 1.0
*/
public Set<String> getSensitiveWord(String txt , int matchType){
Set<String> sensitiveWordList = new HashSet<String>();
for(int i = 0 ; i < txt.length() ; i++){
int length = CheckSensitiveWord(txt, i, matchType); //判断是否包含敏感字符
if(length > 0){ //存在,加入list中
sensitiveWordList.add(txt.substring(i, i+length));
i = i + length - 1; //减1的原因，是因为for会自增
}
}
return sensitiveWordList;
}
/**
* 替换敏感字字符
* @param txt
* @param matchType
* @param replaceChar 替换字符，默认*
* @version 1.0
*/
public String replaceSensitiveWord(String txt,int matchType,String replaceChar){
String resultTxt = txt;
Set<String> set = getSensitiveWord(txt, matchType); //获取所有的敏感词
Iterator<String> iterator = set.iterator();
String word = null;
String replaceString = null;
while (iterator.hasNext()) {
word = iterator.next();
replaceString = getReplaceChars(replaceChar, word.length());
resultTxt = resultTxt.replaceAll(word, replaceString);
}
return resultTxt;
}
/**
* 获取替换字符串
* @param replaceChar
* @param length
* @return
* @version 1.0
*/
private String getReplaceChars(String replaceChar,int length){
String resultReplace = replaceChar;
for(int i = 1 ; i < length ; i++){
resultReplace += replaceChar;
}
return resultReplace;
}
public static void main(String[] args) {
SensitiveWordDAFService sensitiveWordService = new SensitiveWordDAFService();
System.out.println("敏感词数量:"+sensitiveWordMap.size());
String query="阿宾白黄牙签java hadoop 开发 option";
System.out.println("待检测语句字数：" + query.length());
long beginTime = System.currentTimeMillis();
long endTime = System.currentTimeMillis();
Set<String> set = sensitiveWordService.getSensitiveWord(query, 1);
System.out.println("语句中包含敏感词的个数为：" + set.size() + "。包含：" + set);
System.out.println("总共消耗时间为：" + (endTime - beginTime));
}
原理参考博客 https://blog.csdn.net/cdj0311/article/details/79789480
- 双层for 循环去除敏感词
private List<String> wordDicList=new ArrayList<String>();
private List<String> sensitiveWordList=new ArrayList<String>();
public SensitiveWordBaseService() {
wordDicList = SensitiveWordUtil.getSensitiveWordList();
System.out.println("敏感词加载完成,长度:"+wordDicList.size());
}
public String filterInfo(String str){
sensitiveWordList= new ArrayList<String>();
StringBuilder query = new StringBuilder(str);
HashMap<Integer, Integer> hash = new HashMap<Integer, Integer>(wordDicList.size());
String temp;
for(int x = 0; x < wordDicList.size();x++)
{
temp = wordDicList.get(x);
int findIndexSize = 0;
for(int start = -1;(start=query.indexOf(temp,findIndexSize)) > -1;)
{
//System.out.println("###replace="+temp);
findIndexSize = start+temp.length();//从已找到的后面开始找
Integer mapStart = hash.get(start);//起始位置
if(mapStart == null || (mapStart != null && findIndexSize > mapStart))//满足1个，即可更新map
{
hash.put(start, findIndexSize);
//System.out.println("###敏感词："+buffer.substring(start, findIndexSize));
}
}
}
Collection<Integer> values = hash.keySet();
for(Integer startIndex : values)
{
Integer endIndex = hash.get(startIndex);
//获取敏感词，并加入列表，用来统计数量
String sensitive = query.substring(startIndex, endIndex);
//System.out.println("###敏感词："+sensitive);
if (!sensitive.contains("*")) {//添加敏感词到集合
wordDicList.add(sensitive);
sensitiveWordList.add(sensitive);
}
query.replace(startIndex, endIndex, "**");
}
hash.clear();
return query.toString();
}
public static void main(String[] args) {
long start = System.currentTimeMillis();
String string="java 阿宾 阿宾 hadoop 开发 大保健 option";
SensitiveWordBaseService sensitiveWordBaseService=new SensitiveWordBaseService();
String s = sensitiveWordBaseService.filterInfo(string);
System.out.println(s);
System.out.println("用时："+(System.currentTimeMillis()-start)+"ms");
}
- 通过IK分词器去除敏感词，缺点是有的敏感词会被切分，识别不出来
3.1 添加依赖
<!-- https://mvnrepository.com/artifact/com.janeluo/ikanalyzer -->
<dependency>
<groupId>com.janeluo</groupId>
<artifactId>ikanalyzer</artifactId>
<version>2012_u6</version>
</dependency>
3.2 代码
/**
* 敏感词集合
*/
public static HashMap sensitiveWordMap=new HashMap();
/**
* 初始化敏感词库
*
* @param sensitiveWordSet 敏感词库
*/
public static synchronized void init(Set<String> sensitiveWordSet) {
//初始化敏感词容器，减少扩容操作
sensitiveWordMap = new HashMap(sensitiveWordSet.size());
for (String sensitiveWord : sensitiveWordSet) {
sensitiveWordMap.put(sensitiveWord, sensitiveWord);
}
}
/**
* 判断文字是否包含敏感字符
*
* @param txt 文字
* @return 若包含返回true，否则返回false
*/
public static boolean contains(String txt) throws Exception {
boolean flag = false;
List<String> wordList = segment(txt);
for (String word : wordList) {
if (sensitiveWordMap.get(word) != null) {
return true;
}
}
return flag;
}
/**
* 获取文字中的敏感词
*
* @param txt 文字
* @return
*/
public static Set<String> getSensitiveWord(String txt) throws IOException {
Set<String> sensitiveWordList = new HashSet<String>();
List<String> wordList = segment(txt);
for (String word : wordList) {
if (sensitiveWordMap.get(word) != null) {
sensitiveWordList.add(word);
}
}
return sensitiveWordList;
}
/**
* 替换敏感字字符
*
* @param txt 文本
* @param replaceChar 替换的字符，匹配的敏感词以字符逐个替换，如 语句：我爱中国人 敏感词：中国人，替换字符：*， 替换结果：我爱***
* @return
*/
public static String replaceSensitiveWord(String txt, char replaceChar) throws IOException {
String resultTxt = txt;
//获取所有的敏感词
Set<String> sensitiveWordList = getSensitiveWord(txt);
String replaceString;
for (String sensitiveWord : sensitiveWordList) {
replaceString = getReplaceChars(replaceChar, sensitiveWord.length());
resultTxt = resultTxt.replaceAll(sensitiveWord, replaceString);
}
return resultTxt;
}
/**
* 替换敏感字字符
*
* @param txt 文本
* @param replaceStr 替换的字符串，匹配的敏感词以字符逐个替换，如 语句：我爱中国人 敏感词：中国人，替换字符串：[屏蔽]，替换结果：我爱[屏蔽]
* @return
*/
public static String replaceSensitiveWord(String txt, String replaceStr) throws IOException {
String resultTxt = txt;
//获取所有的敏感词
Set<String> sensitiveWordList = getSensitiveWord(txt);
for (String sensitiveWord : sensitiveWordList) {
resultTxt = resultTxt.replaceAll(sensitiveWord, replaceStr);
}
return resultTxt;
}
/**
* 获取替换字符串
*
* @param replaceChar
* @param length
* @return
*/
private static String getReplaceChars(char replaceChar, int length) {
String resultReplace = String.valueOf(replaceChar);
for (int i = 1; i < length; i++) {
resultReplace += replaceChar;
}
return resultReplace;
}
/**
* 对语句进行分词
*
* @param text 语句
* @return 分词后的集合
* @throws IOException
*/
private static List segment(String text) throws IOException {
List<String> list = new ArrayList<String>();
StringReader re = new StringReader(text);
IKSegmenter ik = new IKSegmenter(re, true);
Lexeme lex;
while ((lex = ik.next()) != null) {
list.add(lex.getLexemeText());
}
return list;
}
public static void main(String[] args) throws IOException {
SensitiveWordUtil sensitiveWordUtil=new SensitiveWordUtil();
Set<String> sensitiveWordSet = sensitiveWordUtil.getSensitiveWordSet();
sensitiveWordSet.add("太多");
sensitiveWordSet.add("爱恋");
sensitiveWordSet.add("静静");
sensitiveWordSet.add("哈哈");
sensitiveWordSet.add("啦啦");
sensitiveWordSet.add("感动");
sensitiveWordSet.add("发呆");
//初始化敏感词库
init(sensitiveWordSet);
/**
* 需要进行处理的目标字符串
*/
System.out.println("敏感词的数量：" + sensitiveWordMap.size());
String string = "太多的伤感情怀也许只局限于饲养基地 荧幕中的情节。"
+ "然后 我们的扮演的角色就是跟随着主人公的喜红客联盟 怒哀乐而过于牵强的把自己的情感也附加于银幕情节中，然后感动就流泪，"
+ "难过就躺在某一个人的怀里尽情的阐述心扉或者手机卡复制器一个贱人一杯红酒一部电影在夜 深人静的晚上，关上电话静静的发呆着。";
String string="阿宾白黄牙签java hadoop 开发 option";
System.out.println("待检测语句字数：" + string.length());
/**
* 是否含有关键字
*/
try {
boolean result = contains(string);
System.out.println(result);
} catch (Exception e) {
e.printStackTrace();
}
/**
* 获取语句中的敏感词
*/
Set<String> set = getSensitiveWord(string);
System.out.println("语句中包含敏感词的个数为：" + set.size() + "。包含：" + set);
/**
* 替换语句中的敏感词
*/
String filterStr = replaceSensitiveWord(string, '*');
System.out.println(filterStr);
String filterStr2 = replaceSensitiveWord(string, "[*敏感词*]");
System.out.println(filterStr2);
}
980
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
