SpringBoot之敏感词过滤

1. 功能描述

利用前缀树这种数据结构，设计并开发出敏感词过滤工具。

2. 构建敏感词表

resource/sensitive-words.txt

赌博
嫖娼
吸毒
开票

3. 敏感词过滤器

util/SensitiveFilter.java

• 构建前缀树
• 定义过滤方法

package com.nowcoder.community.util;

import org.apache.commons.lang3.CharUtils;
import org.apache.commons.lang3.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.stereotype.Component;

import javax.annotation.PostConstruct;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;

@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 (IOException e) {
    
    
            logger.error("加载敏感词文件失败: " + e.getMessage());
        }
    }

    // 将一个敏感词添加到前缀树中
    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) {
    
    
                // 初始化子节点
                subNode = new TrieNode();
                tempNode.addSubNode(c, subNode);
            }

            // 指向子节点,进入下一轮循环
            tempNode = subNode;

            // 设置结束标识
            if (i == keyword.length() - 1) {
    
    
                tempNode.setKeywordEnd(true);
            }
        }
    }

    /**
     * 过滤敏感词
     *
     * @param text 待过滤的文本
     * @return 过滤后的文本
     */
    public String filter(String text) {
    
    
        if (StringUtils.isBlank(text)) {
    
    
            return null;
        }

        // 指针1
        TrieNode tempNode = rootNode;
        // 指针2
        int begin = 0;
        // 指针3
        int position = 0;
        // 结果
        StringBuilder sb = new StringBuilder();

        while (position < text.length()) {
    
    
            char c = text.charAt(position);

            // 跳过符号
            if (isSymbol(c)) {
    
    
                // 若指针1处于根节点,将此符号计入结果,让指针2向下走一步
                if (tempNode == rootNode) {
    
    
                    sb.append(c);
                    begin++;
                }
                // 无论符号在开头或中间,指针3都向下走一步
                position++;
                continue;
            }

            // 检查下级节点
            tempNode = tempNode.getSubNode(c);
            if (tempNode == null) {
    
    
                // 以begin开头的字符串不是敏感词
                sb.append(text.charAt(begin));
                // 进入下一个位置
                position = ++begin;
                // 重新指向根节点
                tempNode = rootNode;
            } else if (tempNode.isKeywordEnd()) {
    
    
                // 发现敏感词,将begin~position字符串替换掉
                sb.append(REPLACEMENT);
                // 进入下一个位置
                begin = ++position;
                // 重新指向根节点
                tempNode = rootNode;
            } else {
    
    
                // 检查下一个字符
                position++;
            }
        }

        // 将最后一批字符计入结果
        sb.append(text.substring(begin));

        return sb.toString();
    }

    // 判断是否为符号
    private boolean isSymbol(Character c) {
    
    
        // 0x2E80~0x9FFF 是东亚文字范围
        return !CharUtils.isAsciiAlphanumeric(c) && (c < 0x2E80 || c > 0x9FFF);
    }

    // 前缀树
    private class TrieNode {
    
    

        // 关键词结束标识
        private boolean isKeywordEnd = false;

        // 子节点(key是下级字符,value是下级节点)
        private Map<Character, TrieNode> subNodes = new HashMap<>();

        public boolean isKeywordEnd() {
    
    
            return isKeywordEnd;
        }

        public void setKeywordEnd(boolean keywordEnd) {
    
    
            isKeywordEnd = keywordEnd;
        }

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

        // 获取子节点
        public TrieNode getSubNode(Character c) {
    
    
            return subNodes.get(c);
        }

    }

}

4. 测试过滤敏感词功能

SensitiveTests.java

package com.nowcoder.community;

import com.nowcoder.community.util.SensitiveFilter;
//import org.junit.Test;
import org.junit.jupiter.api.Test;
//import org.junit.runner.RunWith;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.context.SpringBootTest;
import org.springframework.test.context.ContextConfiguration;
import org.springframework.test.context.junit4.SpringRunner;


@SpringBootTest
@ContextConfiguration(classes = CommunityApplication.class)
public class SensitiveTests {
    
    

    @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);
    }

}

执行结果

2022-08-19 17:03:24,516 INFO [main] o.s.b.a.w.s.WelcomePageHandlerMapping [WelcomePageHandlerMapping.java:57] Adding welcome page template: index
2022-08-19 17:03:26,810 INFO [main] c.n.c.SensitiveTests [StartupInfoLogger.java:61] Started SensitiveTests in 14.678 seconds (JVM running for 21.276)
这里可以***,可以***,可以***,可以***,哈哈哈!
这里可以☆***☆,可以☆***☆,可以☆***☆,可以☆***☆,哈哈哈!