敏感词过滤

public static void main(String[] args) {
        Config config = new Config();
        config.useSingleServer().setAddress("redis://192.168.56.102:6379");
//        config.useSingleServer().setPassword("");
        // 构造Redisson
        RedissonClient redissonClient = Redisson.create(config);

        // 初始化布隆过滤器：预计元素为100000000L个，误差率为3%
        RBloomFilter<Object> bloomFilter = redissonClient.getBloomFilter("phoneList");
        bloomFilter.tryInit(100000000L, 0.03);

        // 将号码插入到布隆过滤器中
        bloomFilter.add("张雪");
        bloomFilter.add("张学友");
        bloomFilter.add("张雪1");
        bloomFilter.add("张三");

        // 判断下面的号码是否在布隆过滤器中
        System.out.println(bloomFilter.contains("张雪1"));
        System.out.println(bloomFilter.contains("李四"));
        System.out.println(bloomFilter.contains("张学友"));
}

public class SensitiveWordUtil {

    public static Map<String, Object> dictionaryMap = new HashMap<>();


    /**
     * 生成关键词字典库
     * @param words
     * @return
     */
    public static void initMap(Collection<String> words) {
        if (words == null) {
            System.out.println("敏感词列表不能为空");
            return ;
        }

        // map初始长度words.size()，整个字典库的入口字数(小于words.size()，因为不同的词可能会有相同的首字)
        Map<String, Object> map = new HashMap<>(words.size());
        // 遍历过程中当前层次的数据
        Map<String, Object> curMap;
        Iterator<String> iterator = words.iterator();

        while (iterator.hasNext()) {
            String word = iterator.next();
            curMap = map;
            int len = word.length();
            //DFA算法,Deterministic Finite Automaton,即确定有穷自动机。
            for (int i =0; i < len; i++) {
                // 遍历每个词的字
                String key = String.valueOf(word.charAt(i));
                // 当前字在当前层是否存在, 不存在则新建, 当前层数据指向下一个节点, 继续判断是否存在数据
                Map<String, Object> wordMap = (Map<String, Object>) curMap.get(key);
                if (wordMap == null) {
                    // 每个节点存在两个数据: 下一个节点和isEnd(是否结束标志)
                    wordMap = new HashMap<>(2);
                    wordMap.put("isEnd", "0");
                    curMap.put(key, wordMap);
                }
                curMap = wordMap;
                // 如果当前字是词的最后一个字，则将isEnd标志置1
                if (i == len -1) {
                    curMap.put("isEnd", "1");
                }
            }
        }

        dictionaryMap = map;
    }

    /**
     * 搜索文本中某个文字是否匹配关键词
     * @param text
     * @param beginIndex
     * @return
     */
    private static int checkWord(String text, int beginIndex) {
        if (dictionaryMap == null) {
            throw new RuntimeException("字典不能为空");
        }
        boolean isEnd = false;
        int wordLength = 0;
        Map<String, Object> curMap = dictionaryMap;
        int len = text.length();
        // 从文本的第beginIndex开始匹配
        for (int i = beginIndex; i < len; i++) {
            String key = String.valueOf(text.charAt(i));
            // 获取当前key的下一个节点
            curMap = (Map<String, Object>) curMap.get(key);
            if (curMap == null) {
                break;
            } else {
                wordLength ++;
                if ("1".equals(curMap.get("isEnd"))) {
                    isEnd = true;
                }
            }
        }
        if (!isEnd) {
            wordLength = 0;
        }
        return wordLength;
    }

    /**
     * 获取匹配的关键词和命中次数
     * @param text
     * @return
     */
    public static Map<String, Integer> matchWords(String text) {
        Map<String, Integer> wordMap = new HashMap<>();
        int len = text.length();
        for (int i = 0; i < len; i++) {
            int wordLength = checkWord(text, i);
            if (wordLength > 0) {
                String word = text.substring(i, i + wordLength);
                // 添加关键词匹配次数
                if (wordMap.containsKey(word)) {
                    wordMap.put(word, wordMap.get(word) + 1);
                } else {
                    wordMap.put(word, 1);
                }

                i += wordLength - 1;
            }
        }
        return wordMap;
    }

    public static void main(String[] args) {
        List<String> list = new ArrayList<>();
        list.add("张学友");
        list.add("张学良");
        list.add("叶良");
        list.add("叶良辰");
        initMap(list);
        String content="我是张学友，不是叶良， 更不是叶良辰";
        Map<String, Integer> map = matchWords(content);
        System.out.println(map);
        //{叶良=1, 张学友=1, 叶良辰=1}
    }
}