面试题 17.13. 恢复空格

哦，不！你不小心把一个长篇文章中的空格、标点都删掉了，并且大写也弄成了小写。像句子"I reset the computer. It still didn’t boot!“已经变成了"iresetthecomputeritstilldidntboot”。在处理标点符号和大小写之前，你得先把它断成词语。当然了，你有一本厚厚的词典dictionary，不过，有些词没在词典里。假设文章用sentence表示，设计一个算法，把文章断开，要求未识别的字符最少，返回未识别的字符数。

注意：本题相对原题稍作改动，只需返回未识别的字符数

示例：
输入：
dictionary = [“looked”,“just”,“like”,“her”,“brother”]
sentence = “jesslookedjustliketimherbrother”
输出： 7
解释： 断句后为"jess looked just like tim her brother"，共7个未识别字符。

来源：力扣（LeetCode）添加链接描述

暴力动态规划：

class Solution {
public:
    int respace(vector<string>& dictionary, string sentence) {
        int n = sentence.size();
        int dp[n+1];
        dp[0] = 0;
        for(int i = 1; i <= n; i++){
            dp[i] = dp[i-1] + 1;
            for(auto &word : dictionary) {
                if(word.size() <= i) {
                    if(word == sentence.substr(i-word.size(), word.size())) {
                        dp[i] = min(dp[i], dp[i-word.size()]);
                    }
                }
            }
        }
        return dp[n];
    }
};

字典树：

class Trie {
    public:
    Trie *next[26] = { NULL };
    bool isEnd;

    Trie(){
        isEnd = false;
    }
    void insert(string w) {
        int n = w.size();
        Trie *cur = this;

        for(int i = n-1; i >= 0; i--) {
            int j = w[i] - 'a';
            if(cur->next[j] == NULL) {
                cur->next[j] = new Trie();
            }
            cur = cur->next[j];
        }
        cur->isEnd = true;
    }
};

class Solution {
public:
    int respace(vector<string>& dictionary, string sentence) {
        Trie *root = new Trie();
        for(auto &word : dictionary) {
            root->insert(word);
        }

        int n = sentence.size();
        int dp[n+1];

        dp[0] = 0;

        for(int i = 1; i <= n; i++) {
            dp[i] = dp[i-1] + 1;
            Trie *cur = root;
            for(int j = i; j >= 1; j--) {
                int t = sentence[j-1] - 'a';
                if(cur->next[t] == NULL) break;
                else if(cur->next[t]->isEnd){
                    dp[i] = min(dp[i], dp[j-1]);
                }
                cur = cur->next[t];
            }

        }
        return dp[n];
    }
};