当前位置：首页 > news >正文

Spring Boot 敏感词过滤组件实现：基于DFA算法的高效敏感词检测与替换

news 2025/8/21 16:34:34

Spring Boot 敏感词过滤组件实现

本文将介绍如何在Spring Boot项目中实现一个高效的敏感词过滤组件，包含两种实现方式：基于DFA算法的优化版本和简单直接的实现版本。

组件功能：

1. 从文件加载敏感词库
2. 敏感词检测功能
3. 敏感词替换功能
4. 支持Spring Boot自动装配

实现方案一：DFA算法优化版

这里放入第一个SensitiveWordFilter类的完整代码

package com.example.utils;import jakarta.annotation.PostConstruct;
import org.springframework.core.io.ClassPathResource;
import org.springframework.stereotype.Component;import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.*;@Component
public class SensitiveWordFilter {private static final String REPLACEMENT = "***";private Map<Object, Object> sensitiveWordMap;@PostConstructpublic void init() {try {// 读取敏感词文件Set<String> keyWordSet = new HashSet<>();ClassPathResource resource = new ClassPathResource("sensitive-words.txt");InputStream inputStream = resource.getInputStream();BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));String line;while ((line = reader.readLine()) != null) {keyWordSet.add(line.trim());}reader.close();// 构建DFA算法模型addSensitiveWordToHashMap(keyWordSet);} catch (IOException e) {e.printStackTrace();}}private void addSensitiveWordToHashMap(Set<String> keyWordSet) {sensitiveWordMap = new HashMap(keyWordSet.size());String key;Map nowMap;Map<String, String> newWorMap;for (String aKeyWordSet : keyWordSet) {key = aKeyWordSet;nowMap = sensitiveWordMap;for (int i = 0; i < key.length(); i++) {char keyChar = key.charAt(i);Object wordMap = nowMap.get(keyChar);if (wordMap != null) {nowMap = (Map) wordMap;} else {newWorMap = new HashMap<>();newWorMap.put("isEnd", "0");nowMap.put(keyChar, newWorMap);nowMap = newWorMap;}if (i == key.length() - 1) {nowMap.put("isEnd", "1");}}}}public String filter(String text) {if (text == null || text.trim().isEmpty()) {return text;}StringBuilder result = new StringBuilder();Map nowMap = sensitiveWordMap;int start = 0;int point = 0;while (point < text.length()) {char key = text.charAt(point);nowMap = (Map) nowMap.get(key);if (nowMap != null) {point++;if ("1".equals(nowMap.get("isEnd"))) {result.append(REPLACEMENT);start = point;nowMap = sensitiveWordMap;}} else {result.append(text.charAt(start));point = ++start;nowMap = sensitiveWordMap;}}result.append(text.substring(start));return result.toString();}public boolean containsSensitiveWord(String text) {if (text == null || text.trim().isEmpty()) {return false;}Map nowMap = sensitiveWordMap;int point = 0;while (point < text.length()) {char key = text.charAt(point);nowMap = (Map) nowMap.get(key);if (nowMap != null) {point++;if ("1".equals(nowMap.get("isEnd"))) {return true;}} else {point = point - (point > 0 ? 1 : 0);nowMap = sensitiveWordMap;point++;}}return false;}
}

DFA算法特点：

使用字典树(Trie)结构存储敏感词
时间复杂度接近O(n)，n为文本长度
适合大规模敏感词库
支持最长匹配原则

实现方案二：简单直接版

这里放入第二个SensitiveWordFilter类的完整代码

package com.example.utils;import org.springframework.core.io.ClassPathResource;
import org.springframework.stereotype.Component;import jakarta.annotation.PostConstruct;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.*;@Component
public class SensitiveWordFilter {private static final String REPLACEMENT = "***";private static final Set<String> sensitiveWords = new HashSet<>();// 初始化敏感词库@PostConstructpublic void init() {try {ClassPathResource resource = new ClassPathResource("sensitive-words.txt");InputStream inputStream = resource.getInputStream();BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));String line;while ((line = reader.readLine()) != null) {sensitiveWords.add(line.trim());}reader.close();} catch (IOException e) {e.printStackTrace();}}// 过滤敏感词public String filter(String text) {if (text == null || text.trim().isEmpty()) {return text;}for (String word : sensitiveWords) {if (text.contains(word)) {text = text.replaceAll(word, REPLACEMENT);}}return text;}// 检查是否包含敏感词public boolean containsSensitiveWord(String text) {if (text == null || text.trim().isEmpty()) {return false;}for (String word : sensitiveWords) {if (text.contains(word)) {return true;}}return false;}
}

简单版特点：

实现简单直观
适合小规模敏感词库
使用String.contains()方法检测
性能在词库较大时较差

使用说明

在resources目录下创建sensitive-words.txt文件
每行写入一个敏感词
在Spring Boot项目中注入组件：

//以下引入二选一// 引入
@Resource
private SensitiveWordFilter sensitiveWordFilter;// 引入
@Autowired
private SensitiveWordFilter sensitiveWordFilter;

4. 调用方法

// 引入
@Resource
private SensitiveWordFilter sensitiveWordFilter;/*** 新增*/public void add(Comment comment) {// 过滤敏感词，哪个字段需要过滤就设置哪个// comment.setTitle(sensitiveWordFilter.filter(comment.getTitle()));comment.setContent(sensitiveWordFilter.filter(comment.getContent()));commentMapper.insert(comment);}

依赖配置

<!-- 敏感词处理依赖 -->
<dependency><groupId>jakarta.annotation</groupId><artifactId>jakarta.annotation-api</artifactId><version>2.1.1</version>
</dependency>