SpringBoot项目实现过滤敏感词的功能(基于前缀树)

package cn.edu.njtech.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);
    /**
     * 过滤敏感词
     * @param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 tmpNode = root;
        // 指针2
        int begin = 0;
        // 指针3
        int pos = 0;
        // 结果
        StringBuilder stringBuilder = new StringBuilder();
        while (pos < text.length()){
            char c = text.charAt(pos);
            // 跳过符号
            if(isSymbol(c)){
                // 若指针1指向根节点,将此符号计入结果,让指针2向下走一步
                if(tmpNode == root){
                    stringBuilder.append(c);
                    begin++;
                }
                // 指针3肯定走
                pos++;
                continue;
            }
            // 检查下级节点
            tmpNode = tmpNode.getSubNode(c);
            if (tmpNode == null){
                // 以begin开头的词不是敏感词
                stringBuilder.append(text.charAt(begin));
                // 进入下一个位置
                pos = ++begin;
                // 重新指向根节点
                tmpNode = root;
            }else if (tmpNode.isKeyWordEnd()){
                // 发现敏感词 将begin~pos字符串替换掉
                stringBuilder.append(REPLACEMENT);
                begin = ++pos;
                tmpNode = root;
            }else{
                // 继续检查下一个字符
                pos++;
            }
        }
        // 将最后一批字符计入结果
        stringBuilder.append(text.substring(begin));
        return stringBuilder.toString();
    }

    private boolean isSymbol(Character s){
        // 0x2E80~0x9FFF 是东亚文字范围
        return !CharUtils.isAsciiAlphanumeric(s) && (s < 0x2E80 || s > 0x9FFF);
    }

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

    // 根节点初始化
    private TrieNode root = new TrieNode();

    @PostConstruct
    public void init(){
        try(
                InputStream is = this.getClass().getClassLoader().getResourceAsStream("sensitive-word.txt");
                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(is));
                ){
            String keyword;
            while ((keyword = bufferedReader.readLine()) != null){
                // 添加到前缀树
                this.addKeyword(keyword);
            }
        }catch (IOException e){
            logger.error("加载敏感词失败:"+e.getMessage());
        }

    }

    // 将一个敏感词添加到前缀树中
    private void addKeyword(String keyword){
        TrieNode tmpNode = root;
        for(int i= 0;i< keyword.length();i++){
            char c = keyword.charAt(i);
            TrieNode subNode = tmpNode.getSubNode(c);
            if(subNode == null){
                // 初始化子节点
                subNode = new TrieNode();
                tmpNode.addSubNode(c,subNode);
            }
            // 指向子节点,进行下一轮循环
            tmpNode = subNode;
            // 设置结束的标识
            if (i == keyword.length() - 1){
                tmpNode.setKeyWordEnd(true);
            }
        }
    }

    // 前缀树
    private class TrieNode{
        // 描述关键词结束的标识
        private boolean isKeyWordEnd = false;

        // 当前节点的子节点(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;
        }

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

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

}

标签：SpringBoot,TrieNode,pos,private,过滤,import,tmpNode,节点,前缀
来源： https://blog.csdn.net/jdq8576/article/details/110292312