DFA有穷自动机敏感词过滤算法

1.EndType

package com.example.utils.wordfilter;

/**
 * 结束类型定义
 */
public enum EndType {

    /**
     * 有下一个,结束
     */
    HAS_NEXT, IS_END
}

2.WordType

package com.example.utils.wordfilter;

/**
 * 词汇类型
 */
public enum WordType {

    /**
     * 黑名单/白名单
     */
    BLACK, WHITE
}

3.FlagIndex

package com.example.utils.wordfilter;

import java.util.List;

/**
 * 敏感词标记
 */
public class FlagIndex {

    /**
     * 标记结果
     */
    private boolean flag;
    /**
     * 是否黑名单词汇
     */
    private boolean isWhiteWord;
    /**
     * 标记索引
     */
    private List<Integer> index;

    public boolean isFlag() {
        return flag;
    }

    public void setFlag(boolean flag) {
        this.flag = flag;
    }

    public List<Integer> getIndex() {
        return index;
    }

    public void setIndex(List<Integer> index) {
        this.index = index;
    }

    public boolean isWhiteWord() {
        return isWhiteWord;
    }

    public void setWhiteWord(boolean whiteWord) {
        isWhiteWord = whiteWord;
    }
}

4.WordContext

package com.example.utils.wordfilter;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.*;

/**
 * 词库上下文环境
 * 初始化敏感词库,将敏感词加入到HashMap中,构建DFA算法模型
 */
@SuppressWarnings({"rawtypes", "unchecked"})
public class WordContext {

    /**
     * 敏感词字典
     */
    private final Map wordMap = new HashMap();

    /**
     * 是否已初始化
     */
    private boolean init;
    /**
     * 黑名单列表
     */
    private final String blackList;
    /**
     * 白名单列表
     */
    private final String whiteList;

    public WordContext() {
        this.blackList = "/blacklist.txt";
        this.whiteList = "/whitelist.txt";
        initKeyWord();
    }

    public WordContext(String blackList, String whiteList) {
        this.blackList = blackList;
        this.whiteList = whiteList;
        initKeyWord();
    }

    /**
     * 获取初始化的敏感词列表
     *
     * @return 敏感词列表
     */
    public Map getWordMap() {
        return wordMap;
    }

    /**
     * 初始化
     */
    private synchronized void initKeyWord() {
        try {
            if (!init) {
                // 将敏感词库加入到HashMap中
                addWord(readWordFile(blackList), WordType.BLACK);
                // 将非敏感词库也加入到HashMap中
                addWord(readWordFile(whiteList), WordType.WHITE);
            }
            init = true;
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }

    /**
     * 读取敏感词库,将敏感词放入HashSet中,构建一个DFA算法模型:<br>
     * 中 = { isEnd = 0 国 = {<br>
     * isEnd = 1 人 = {isEnd = 0 民 = {isEnd = 1} } 男 = { isEnd = 0 人 = { isEnd = 1 }
     * } } } 五 = { isEnd = 0 星 = { isEnd = 0 红 = { isEnd = 0 旗 = { isEnd = 1 } } } }
     */
    public void addWord(Iterable<String> wordList, WordType wordType) {
        Map nowMap;
        Map<String, String> newWorMap;
        // 迭代keyWordSet
        for (String key : wordList) {
            nowMap = wordMap;
            for (int i = 0; i < key.length(); i++) {
                // 转换成char型
                char keyChar = key.charAt(i);
                // 获取
                Object wordMap = nowMap.get(keyChar);
                // 如果存在该key,直接赋值
                if (wordMap != null) {
                    nowMap = (Map) wordMap;
                } else {
                    // 不存在则构建一个map,同时将isEnd设置为0,因为他不是最后一个
                    newWorMap = new HashMap<>(4);
                    // 不是最后一个
                    newWorMap.put("isEnd", String.valueOf(EndType.HAS_NEXT.ordinal()));
                    nowMap.put(keyChar, newWorMap);
                    nowMap = newWorMap;
                }

                if (i == key.length() - 1) {
                    // 最后一个
                    nowMap.put("isEnd", String.valueOf(EndType.IS_END.ordinal()));
                    nowMap.put("isWhiteWord", String.valueOf(wordType.ordinal()));
                }
            }
        }
    }

    /**
     * 在线删除敏感词
     *
     * @param wordList 敏感词列表
     * @param wordType 黑名单 BLACk,白名单WHITE
     */
    public void removeWord(Iterable<String> wordList, WordType wordType) {
        Map nowMap;
        for (String key : wordList) {
            List<Map> cacheList = new ArrayList<>();
            nowMap = wordMap;
            for (int i = 0; i < key.length(); i++) {
                char keyChar = key.charAt(i);

                Object map = nowMap.get(keyChar);
                if (map != null) {
                    nowMap = (Map) map;
                    cacheList.add(nowMap);
                } else {
                    return;
                }

                if (i == key.length() - 1) {
                    char[] keys = key.toCharArray();
                    boolean cleanable = false;
                    char lastChar = 0;
                    for (int j = cacheList.size() - 1; j >= 0; j--) {
                        Map cacheMap = cacheList.get(j);
                        if (j == cacheList.size() - 1) {
                            if (String.valueOf(WordType.BLACK.ordinal()).equals(cacheMap.get("isWhiteWord"))) {
                                if (wordType == WordType.WHITE) {
                                    return;
                                }
                            }
                            if (String.valueOf(WordType.WHITE.ordinal()).equals(cacheMap.get("isWhiteWord"))) {
                                if (wordType == WordType.BLACK) {
                                    return;
                                }
                            }
                            cacheMap.remove("isWhiteWord");
                            cacheMap.remove("isEnd");
                            if (cacheMap.size() == 0) {
                                cleanable = true;
                                continue;
                            }
                        }
                        if (cleanable) {
                            Object isEnd = cacheMap.get("isEnd");
                            if (String.valueOf(EndType.IS_END.ordinal()).equals(isEnd)) {
                                cleanable = false;
                            }
                            cacheMap.remove(lastChar);
                        }
                        lastChar = keys[j];
                    }

                    if (cleanable) {
                        wordMap.remove(lastChar);
                    }
                }
            }
        }
    }

    /**
     * 读取敏感词库中的内容,将内容添加到set集合中
     */
    private Set<String> readWordFile(String file) throws Exception {
        Set<String> set;
        // 字符编码
        String encoding = "UTF-8";
        try (InputStreamReader read = new InputStreamReader(
                this.getClass().getResourceAsStream(file), encoding)) {
            set = new HashSet<>();
            BufferedReader bufferedReader = new BufferedReader(read);
            String txt;
            // 读取文件,将文件内容放入到set中
            while ((txt = bufferedReader.readLine()) != null) {
                set.add(txt);
            }
        }
        // 关闭文件流
        return set;
    }
}

5.WordFilter

package com.example.utils.wordfilter;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.Objects;

/**
 * 敏感词过滤器
 */
@SuppressWarnings("rawtypes")
public class WordFilter {

    /**
     * 敏感词表
     */
    private final Map wordMap;

    /**
     * 构造函数
     */
    public WordFilter(WordContext context) {
        this.wordMap = context.getWordMap();
    }

    /**
     * 替换敏感词
     *
     * @param text 输入文本
     */
    public String replace(final String text) {
        return replace(text, 0, '*');
    }

    /**
     * 替换敏感词
     *
     * @param text   输入文本
     * @param symbol 替换符号
     */
    public String replace(final String text, final char symbol) {
        return replace(text, 0, symbol);
    }

    /**
     * 替换敏感词
     *
     * @param text   输入文本
     * @param skip   文本距离
     * @param symbol 替换符号
     */
    public String replace(final String text, final int skip, final char symbol) {
        char[] charset = text.toCharArray();
        for (int i = 0; i < charset.length; i++) {
            FlagIndex fi = getFlagIndex(charset, i, skip);
            if (fi.isFlag()) {
                if (!fi.isWhiteWord()) {
                    for (int j : fi.getIndex()) {
                        charset[j] = symbol;
                    }
                } else {
                    i += fi.getIndex().size() - 1;
                }
            }
        }
        return new String(charset);
    }

    /**
     * 是否包含敏感词
     *
     * @param text 输入文本
     */
    public boolean include(final String text) {
        return include(text, 0);
    }

    /**
     * 是否包含敏感词
     *
     * @param text 输入文本
     * @param skip 文本距离
     */
    public boolean include(final String text, final int skip) {
        boolean include = false;
        char[] charset = text.toCharArray();
        for (int i = 0; i < charset.length; i++) {
            FlagIndex fi = getFlagIndex(charset, i, skip);
            if(fi.isFlag()) {
                if (fi.isWhiteWord()) {
                    i += fi.getIndex().size() - 1;
                } else {
                    include = true;
                    break;
                }
            }
        }
        return include;
    }

    /**
     * 获取敏感词数量
     *
     * @param text 输入文本
     */
    public int wordCount(final String text) {
        return wordCount(text, 0);
    }

    /**
     * 获取敏感词数量
     *
     * @param text 输入文本
     * @param skip 文本距离
     */
    public int wordCount(final String text, final int skip) {
        int count = 0;
        char[] charset = text.toCharArray();
        for (int i = 0; i < charset.length; i++) {
            FlagIndex fi = getFlagIndex(charset, i, skip);
            if (fi.isFlag()) {
                if(fi.isWhiteWord()) {
                    i += fi.getIndex().size() - 1;
                } else {
                    count++;
                }
            }
        }
        return count;
    }

    /**
     * 获取敏感词列表
     *
     * @param text 输入文本
     */
    public List<String> wordList(final String text) {
        return wordList(text, 0);
    }

    /**
     * 获取敏感词列表
     *
     * @param text 输入文本
     * @param skip 文本距离
     */
    public List<String> wordList(final String text, final int skip) {
        List<String> wordList = new ArrayList<>();
        char[] charset = text.toCharArray();
        for (int i = 0; i < charset.length; i++) {
            FlagIndex fi = getFlagIndex(charset, i, skip);
            if (fi.isFlag()) {
                if(fi.isWhiteWord()) {
                    i += fi.getIndex().size() - 1;
                } else {
                    StringBuilder builder = new StringBuilder();
                    for (int j : fi.getIndex()) {
                        char word = text.charAt(j);
                        builder.append(word);
                    }
                    wordList.add(builder.toString());
                }
            }
        }
        return wordList;
    }

    /**
     * 获取标记索引
     *
     * @param charset 输入文本
     * @param begin   检测起始
     * @param skip    文本距离
     */
    private FlagIndex getFlagIndex(final char[] charset, final int begin, final int skip) {
        FlagIndex fi = new FlagIndex();

        Map current = wordMap;
        boolean flag = false;
        int count = 0;
        List<Integer> index = new ArrayList<>();
        for (int i = begin; i < charset.length; i++) {
            char word = charset[i];
            Map mapTree = (Map) current.get(word);
            if (count > skip || (i == begin && Objects.isNull(mapTree))) {
                break;
            }
            if (Objects.nonNull(mapTree)) {
                current = mapTree;
                count = 0;
                index.add(i);
            } else {
                count++;
                if (flag && count > skip) {
                    break;
                }
            }
            if ("1".equals(current.get("isEnd"))) {
                flag = true;
            }
            if ("1".equals(current.get("isWhiteWord"))) {
                fi.setWhiteWord(true);
                break;
            }
        }

        fi.setFlag(flag);
        fi.setIndex(index);

        return fi;
    }
}

注:Skip距离

程序会跳过不同的距离,查找敏感词,距离越长,过滤越严格,效率越低,开发者可以根据具体需求设置,这里以“紧急”为敏感词举例,以此类推

  • 0 匹配紧急

  • 1 匹配不紧不急,紧x急

  • 2 匹配紧急,紧x急,紧xx急

6.功能测试

package com.example.wordfilter;

import com.example.utils.wordfilter.WordContext;
import com.example.utils.wordfilter.WordFilter;
import com.example.utils.wordfilter.WordType;
import org.junit.Test;
import org.springframework.boot.test.context.SpringBootTest;

import java.util.Collections;

/**
 * DFA敏感词单元测试用例
 */
@SpringBootTest
public class DFATest {

    /**
     * 词库上下文环境
     */
    private final WordContext context = new WordContext();
    private final WordFilter filter = new WordFilter(context);

    /**
     * 测试替换敏感词
     */
    @Test
    public void replace() {
        String text = "利于上游行业发展的政策逐渐发布";
        System.out.println(filter.replace(text));   //利于上游行业发展的政策逐渐发布
        context.removeWord(Collections.singletonList("上游行业"), WordType.WHITE);
        System.out.println(filter.replace(text));   //利于上**业发展的政策逐渐发布
    }

    /**
     * 测试是否包含敏感词
     */
    @Test
    public void include() {
        String text = "利于上游行业发展的政策逐渐发布";
        System.out.println(filter.include(text));   //false
        context.removeWord(Collections.singletonList("上游行业"), WordType.WHITE);
        System.out.println(filter.include(text));   //true
    }

    /**
     * 获取敏感词数
     */
    @Test
    public void wordCount() {
        String text = "利于上游行业发展的政策逐渐发布";
        System.out.println(filter.wordCount(text));   //0
        context.removeWord(Collections.singletonList("上游行业"), WordType.WHITE);
        System.out.println(filter.wordCount(text));   //1
    }

    /**
     * 获取敏感词列表
     */
    @Test
    public void wordList() {
        String text = "利于上游1行业发展的政策逐渐发布";
        System.out.println(filter.wordList(text));   //[]]
        context.removeWord(Collections.singletonList("上游行业"), WordType.WHITE);
        System.out.println(filter.wordList(text));   //[游行]
    }

    /**
     * 测试替换敏感词
     */
    @Test
    public void replace2() {
        String text = "你是个笨蛋吧";
        System.out.println(filter.replace(text));
    }

    /**
     * 测试替换敏感词
     */
    @Test
    public void replace3() {
        String text = "你是个日本鬼子吧";
        System.out.println(filter.replace(text));
    }

}

7.工程目录


可以点个免费的赞吗!!!   

  • 12
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值