前缀树
- 名称:Trie、字典树、查找树
- 特点:查找效率高、内存消耗大
- 应用:字符串检索、词频统计、字符串排序等
敏感词过滤器
- 定义前缀树
- 根据敏感词汇初始,初始化前缀树
- 编写过滤敏感词汇方法
![在这里插入图片描述](https://img-blog.csdnimg.cn/e74b968fd1644b9fbd5e07901ee32909.png)
实现敏感词过滤类
- 定义内部类 TrieNode(前缀树节点)
- 属性: private boolean isKeywordEnd
- 节点容器:private Map<Character, TrieNode> subNodes = new HashMap<>();
- 判断是否为结束节点方法:public boolean isKeywordEnd()
- 添加子节点方法
- 获取子节点方法
- 定义替换符号:private static final String REPLACEMENT = “***”;
- 定义初始根节点:private TrieNode rootNode = new TrieNode();
- 添加敏感词到前缀树中方法:private void addKeyword(String keyword)
- 判断是否为特殊字符:private boolean isSymbol(Character c)
- 初始化敏感词前缀树方法:public void init()
- 过滤方法(过滤算法):public String filter(String text)-
@Component
public class SensitiveFilter {
private static final Logger logger = LoggerFactory.getLogger(SensitiveFilter.class);
private static final String REPLACEMENT = "***";
private TrieNode rootNode = new TrieNode();
@PostConstruct
public void init() {
try(
InputStream is = this.getClass().getClassLoader().getResourceAsStream("sensitive-words.txt");
BufferedReader reader = new BufferedReader(new InputStreamReader(is));
) {
String keyword;
while ((keyword = reader.readLine()) != null) {
addKeyword(keyword);
}
} catch (IOException e) {
logger.error("加载敏感词文件失败: " + e.getMessage());
}
}
private void addKeyword(String keyword) {
TrieNode tempNode = rootNode;
for (int i = 0; i < keyword.length(); i++) {
char c = keyword.charAt(i);
TrieNode subNode = tempNode.getSubNode(c);
if (subNode == null) {
subNode = new TrieNode();
tempNode.addSubNode(c, subNode);
}
tempNode = subNode;
if (i == keyword.length() - 1) {
tempNode.setKeywordEnd(true);
}
}
}
public String filter(String text) {
if (StringUtils.isBlank(text)) {
return null;
}
TrieNode tempNode = rootNode;
int begin = 0;
int position = 0;
StringBuilder sb = new StringBuilder();
while (begin < text.length()) {
if (position < text.length()) {
char c = text.charAt(position);
if (isSymbol(c)) {
if (tempNode == rootNode) {
sb.append(c);
begin++;
}
position++;
continue;
}
tempNode = tempNode.getSubNode(c);
if (tempNode == null) {
sb.append(text.charAt(begin));
position = ++begin;
tempNode = rootNode;
} else if (tempNode.isKeywordEnd()) {
sb.append(REPLACEMENT);
begin = ++position;
tempNode = rootNode;
} else {
position++;
}
}
else {
sb.append(text.charAt(begin));
position = ++begin;
tempNode = rootNode;
}
}
return sb.toString();
}
private boolean isSymbol(Character c) {
return !CharUtils.isAsciiAlphanumeric(c) && (c < 0x2E80 || c > 0x9FFF);
}
private class TrieNode {
private boolean isKeywordEnd = false;
private Map<Character, TrieNode> subNodes = new HashMap<>();
public boolean isKeywordEnd() {
return isKeywordEnd;
}
public void setKeywordEnd(boolean keywordEnd) {
isKeywordEnd = keywordEnd;
}
public void addSubNode(Character c, TrieNode node) {
subNodes.put(c, node);
}
public TrieNode getSubNode(Character c) {
return subNodes.get(c);
}
}
}