敏感词过滤


1.敏感词过滤工具类

SensitiveFilter.java

/**
 * 敏感词过滤工具类
 * @Author: ANTIA1
 * @Date: 2021/2/13 14:43
 */
@Component
public class SensitiveFilter {

    private static final Logger LOGGER = LoggerFactory.getLogger(SensitiveFilter.class);

    //替换符
    private static final String REPLACEMENT = "***";

    //根节点
    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){
                // 添加到前缀树
                this.addKeyword(keyword);
            }
        } catch (Exception e) {
            LOGGER.error("加载敏感词文件失败:"+e.getMessage());
        }
    }

    /**
     * 把敏感词添加到前缀树中
     * @param keyword
     */
    private void addKeyword(String keyword){
        TrieNode tempNode = rootNode;
        for (int i=0;i 0x9FFF)
        return !CharUtils.isAsciiAlphanumeric(c) && (c<0x2E80 || c > 0x9FFF);
    }

    /**
     * 前缀树
     */
    @Data
    private class TrieNode{
        // 关键词结束标识
        private boolean isKeywordEnd = false;

        //子节点
        private Map subNods = new HashMap<>();


        // 添加子节点
        public void addSubNode(Character c,TrieNode node){
            subNods.put(c,node);
        }

        // 获得子节点
        public TrieNode getSubNode(Character c){
            return subNods.get(c);
        }
    }

}

2.敏感词文件

sensitive-words.txt 一词一行

3.测试结果

Test.java

/**
 * 敏感词测试
 */
@Autowired
private SensitiveFilter sensitiveFilter;

@Test
public void testSensitiveFilter(){
    String text = "这里可以赌博,可以嫖娼,可以吸毒,可以开票,哈哈哈!";
    text = sensitiveFilter.filter(text);
    System.out.println(text);

    text = "这里可以▲赌▲博▲,可以▲嫖▲娼▲,可以▲吸▲毒▲,可以▲开▲票▲,哈哈哈!";
    text = sensitiveFilter.filter(text);
    System.out.println(text);

}

结果: