这期内容当中小编将会给大家带来有关如何在Java项目中利用DFA算法实现一个过滤敏感字功能,文章内容丰富且以专业的角度为大家分析和叙述,阅读完这篇文章希望大家可以有所收获。
模式图
直接上代码
public class KeywordFilter {
// private static ReentrantReadWriteLock lock = new ReentrantReadWriteLock();
public static Map<String, HashMap> currentMap = new ConcurrentHashMap<String, HashMap>();
public static Map nowhash = null;
public static Object wordMap;// map子节点
// 不建立对象
private KeywordFilter() {
}
private static String getKey(int companyId) {
return "companyId" + companyId;
}
/*
* <p>说明:清扫内容</p>
*
*
* @data:2017-8-22 上午10:13:11
*/
public static void clear() {
try {
currentMap.clear();
} catch (Exception e) {
e.printStackTrace();
} finally {
}
}
/*
* <p>说明:各个渠道的过滤字符</p>
*
*
* @data:2017-8-20 下午2:55:06
*/
public static void saveKeywords(int companyId, List<String> keywords) {
try {
Map tempAllMap = currentMap;
String key = getKey(companyId);
int l = keywords.size();
int il;
Map tempMap;
for (int i = 0; i < l; i++) {
String key2 = keywords.get(i).trim();// 去掉空白
nowhash = currentMap;
il = key2.length();
for (int j = 0; j < il; j++) {
char word = key2.charAt(j);
tempMap = (Map) nowhash.get(word);
wordMap = nowhash.get(word);
if (wordMap != null) {// 检查数据
if (!tempMap.containsKey(key)) {
nowhash.put(key, 0);
}
nowhash = (HashMap) wordMap;
} else {
HashMap<String, String> newWordHash = new HashMap<String, String>();
newWordHash.put(key, "0");
nowhash.put(word, newWordHash);
nowhash = newWordHash;
}
if (j == il - 1) {
nowhash.put(key, "1");
}
}
}
} catch (Exception e) {
e.printStackTrace();
} finally {
nowhash = null;
wordMap = null;
}
}
/*
* <p>说明:替换掉对应的渠道规定掉敏感字</p>
*
*
* @data:2017-8-20 上午11:41:47
*/
public static List<String> repword(int companyId, String txt) {
Map tempMap = currentMap;
List<String> result = new ArrayList<String>();
String key = getKey(companyId);
nowhash = currentMap;
int l = txt.length();
char word;
String keywordStr = "";
String keyStatu;
StringBuilder keyword = new StringBuilder();// 敏感字
for (int i = 0; i < l; i++) {
word = txt.charAt(i);
wordMap = nowhash.get(word);
if (wordMap != null) {// 找到类似敏感字的字体,开始查询
keyword.append(word);
Object te = nowhash = (HashMap) wordMap;
// 遍历到这一步,就符合完整的关键字模板
if (nowhash.get(key) != null
&& nowhash.get(key).toString().equals("1")) {// 确定是敏感字,开始替换
if (i < l - 1 && nowhash.get(txt.charAt(i + 1)) != null) {// 优先过滤长敏感词,去掉就槟城了优先过滤段敏感词
continue;
}
txt = txt.replaceAll(keyword.toString(), "*");
nowhash = currentMap;
keywordStr += keyword.toString() + ",";
i = i - keyword.length() + 1;
l = txt.length();// 重新获取字符长度
keyword.delete(0, keyword.length());// 清空数据
}
} else {// 这个字不是敏感字,直接排除
nowhash = currentMap;
keyword.delete(0, keyword.length());// 清空数据
continue;
}
}
// 清除内存指向
nowhash = null;
wordMap = null;
result.add(txt);
result.add(keywordStr.length() - 1 > 0 ? keywordStr.substring(0,
keywordStr.length() - 1) : keywordStr);
return result;
}
/*
* <p>说明:检查是否存在敏感字</p>
*
*
* @data:2017-8-20 下午3:00:06 专门设计成私有的,如果没有理由,别改动他
*/
private static int checkKeyWords(String txt, int companyId, int begin) {
int result = 0;
String key = getKey(companyId);
try {
nowhash = currentMap;
int l = txt.length();
char word = 0;
for (int i = begin; i < l; i++) {
word = txt.charAt(i);
wordMap = nowhash.get(word);
if (wordMap != null) {
result++;
nowhash = (HashMap) wordMap;
if (((String) nowhash.get(key)).equals("1")) {
nowhash = null;
wordMap = null;
return result;
}
} else {
result = 0;
break;
}
}
} catch (Exception e) {
e.printStackTrace();
} finally {
nowhash = null;
wordMap = null;
return result;
}
}
/*
* <p>说明:返回检查的文本中包含的敏感字</p>
*
*
* @data:2017-8-20 下午3:32:53
*/
public static String getTxtKeyWords(String txt, int companyId) {
String result = null;
StringBuilder temp = new StringBuilder();
String key;
int l = txt.length();
for (int i = 0; i < l;) {
int len = checkKeyWords(txt, companyId, i);
if (len > 0) {
key = (txt.substring(i, i + len));// 挑选出来的关键字
temp.append(key + ",");
txt = txt.replaceAll(key, "");// 挑选出来的关键字替换成空白,加快挑选速度
l = txt.length();
} else {
i++;
}
}
if (temp.length() > 0) {
result = temp.substring(0, temp.length() - 1);
}
return result;
}
/*
* <p>说明:判断文中是否包含渠道规定的敏感字</p>
*
* @data:2017-8-20 下午3:33:19
*/
public boolean isKeyWords(String txt, int companyId) {
for (int i = 0; i < txt.length(); i++) {
int len = checkKeyWords(txt, companyId, i);
if (len > 0) {
return true;
}
}
return false;
}
public static void main(String[] arg) {
List<String> keywords = new ArrayList<String>();
keywords.add("傻×");
keywords.add("汉*");
keywords.add("草");
keywords.add("草泥马");
KeywordFilter.saveKeywords(1, keywords);
String txt = "是傻×汉*傻A傻B傻C傻D汉*傻×草泥马";
List<String> list = repword(1, txt);
System.out.println("文中包含的敏感字为:" + list.get(1));
System.out.println("原文:" + txt);
System.out.println("敏感字过滤后:" + list.get(0));
}
}
上述就是小编为大家分享的如何在Java项目中利用DFA算法实现一个过滤敏感字功能了,如果刚好有类似的疑惑,不妨参照上述分析进行理解。如果想知道更多相关知识,欢迎关注亿速云行业资讯频道。
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。