欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

关键字过滤实现

程序员文章站 2022-03-03 10:21:35
...

高效过滤,有兴趣的可以看看《Java系统性能优化》性能优化这本书,以下是书中部分代码,做个笔记

package com.golconda.tree;

import java.util.HashMap;
import java.util.Map;

public class Node {

	private Map<Character, Node> nextNodes = new HashMap<>();

	public void addNextNode(Character key, Node node) {
		nextNodes.put(key, node);
	}

	public Node getNextNode(Character key) {
		return nextNodes.get(key);
	}

	public boolean isLastCharacter() {
		return nextNodes.isEmpty();
	}

	public Map<Character, Node> getNextNodes() {
		return nextNodes;
	}

	public void setNextNodes(Map<Character, Node> nextNodes) {
		this.nextNodes = nextNodes;
	}

	@Override
	public int hashCode() {
		final int prime = 31;
		int result = 1;
		result = prime * result + ((nextNodes == null) ? 0 : nextNodes.hashCode());
		return result;
	}

	@Override
	public boolean equals(Object obj) {
		if (this == obj)
			return true;
		if (obj == null)
			return false;
		if (getClass() != obj.getClass())
			return false;
		Node other = (Node) obj;
		if (nextNodes == null) {
			if (other.nextNodes != null)
				return false;
		} else if (!nextNodes.equals(other.nextNodes))
			return false;
		return true;
	}
}

package com.golconda.tree;

import com.alibaba.fastjson.JSON;

public class KeywordSearch {
	static Node root = new Node();
	String sensitiveWords = "***";

	public void addWord(String word) {

		Node tempNode = root;
		for (int i = 0; i < word.length(); i++) {
			Character c = word.charAt(i);
			Node node = tempNode.getNextNode(c);
			if (node == null) {
				node = new Node();
				tempNode.addNextNode(c, node);
			}
			// 移动到下一个字
			tempNode = node;


		}
	}

	public String filter(String text) {
		StringBuilder result = new StringBuilder(text.length());
		Node tempNode = root;
		int begin = 0;
		int position = 0;
		while (position < text.length()) {

			Character c = text.charAt(position);
			tempNode = tempNode.getNextNode(c);

			if (tempNode == null) {
				如果匹配失败,合法
				result.append(text.charAt(begin));
				begin = begin + 1;
				position = begin;
				//从新匹配
				tempNode = root;
				continue;
			} else if (tempNode.isLastCharacter()) {
				//匹配结束,替换敏感词
				result.append(sensitiveWords);
				position++;
				begin = position;
				tempNode = root;
			} else {
				position++;
			}

		}
		//添加剩下的内容
		result.append(text.substring(begin));
		return result.toString();
	}

	public static void main(String[] args) {
		KeywordSearch ts = new KeywordSearch();
		ts.addWord("猪狗");
		ts.addWord("小猫");
		ts.addWord("天气预报");
		
		System.out.println(JSON.toJSONString(root.getNextNodes()));
		String ret = ts.filter("你好,小猫");
		System.out.println(ret);

	}
}