日日操夜夜添-日日操影院-日日草夜夜操-日日干干-精品一区二区三区波多野结衣-精品一区二区三区高清免费不卡

DFA，全稱 Deterministic Finite Automaton， 即確定有窮自動機(jī)。

黑馬頭條項(xiàng)目的敏感詞過濾工具類，基于DFA算法思想。

package com.heima.utils.common;
import JAVA.util.*;
public class SensitivewordUtil {
    public static Map<String, Object> dictionaryMap = new HashMap<>();
    /**
     * 生成關(guān)鍵詞字典庫
     * @param words
     * @return
     */
    public static void initMap(Collection<String> words) {
        if (words == null) {
            System.out.println("敏感詞列表不能為空");
            return ;
        }
        // map初始長度words.size()，整個字典庫的入口字?jǐn)?shù)(小于words.size()，因?yàn)椴煌脑~可能會有相同的首字)
        Map<String, Object> map = new HashMap<>(words.size());
        // 遍歷過程中當(dāng)前層次的數(shù)據(jù)
        Map<String, Object> curMap = null;
        Iterator<String> iterator = words.iterator();

        while (iterator.hasNext()) {
            String word = iterator.next();
            curMap = map;
            int len = word.length();
            for (int i =0; i < len; i++) {
                // 遍歷每個詞的字
                String key = String.valueOf(word.charAt(i));
                // 當(dāng)前字在當(dāng)前層是否存在, 不存在則新建, 當(dāng)前層數(shù)據(jù)指向下一個節(jié)點(diǎn), 繼續(xù)判斷是否存在數(shù)據(jù)
                Map<String, Object> wordMap = (Map<String, Object>) curMap.get(key);
                if (wordMap == null) {
                    // 每個節(jié)點(diǎn)存在兩個數(shù)據(jù): 下一個節(jié)點(diǎn)和isEnd(是否結(jié)束標(biāo)志)
                    wordMap = new HashMap<>(2);
                    wordMap.put("isEnd", "0");
                    curMap.put(key, wordMap);
                }
                curMap = wordMap;
                // 如果當(dāng)前字是詞的最后一個字，則將isEnd標(biāo)志置1
                if (i == len -1) {
                    curMap.put("isEnd", "1");
                }
            }
        }

        dictionaryMap = map;
    }

    /**
     * 搜索文本中某個文字是否匹配關(guān)鍵詞
     * @param text
     * @param beginIndex
     * @return
     */
    private static int checkWord(String text, int beginIndex) {
        if (dictionaryMap == null) {
            throw new RuntimeException("字典不能為空");
        }
        boolean isEnd = false;
        int wordLength = 0;
        Map<String, Object> curMap = dictionaryMap;
        int len = text.length();
        // 從文本的第beginIndex開始匹配
        for (int i = beginIndex; i < len; i++) {
            String key = String.valueOf(text.charAt(i));
            // 獲取當(dāng)前key的下一個節(jié)點(diǎn)
            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;
    }

    /**
     * 獲取匹配的關(guān)鍵詞和命中次數(shù)
     * @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);
                // 添加關(guān)鍵詞匹配次數(shù)
                if (wordMap.contAInsKey(word)) {
                    wordMap.put(word, wordMap.get(word) + 1);
                } else {
                    wordMap.put(word, 1);
                }
                i += wordLength - 1;
            }
        }
        return wordMap;
    }
}