leetcode 日经贴，Cpp code -Repeated DNA Sequences

原创于 2015-08-10 14:46:17 发布 · 314 阅读

0 ·

CC 4.0 BY-SA版权

算法同时被 3 个专栏收录

183 篇文章

订阅专栏

leetcode

173 篇文章

订阅专栏

Cpp

152 篇文章

订阅专栏

本文介绍了一种算法，用于在给定的DNA序列中查找重复出现的长度为10的序列片段。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Repeated DNA Sequences

class Solution {
public:
    int getnum(char ch) {
        int ret = 0;
        switch(ch) {
            case 'A': ret = 0; break;
            case 'C': ret = 1; break;
            case 'G': ret = 2; break;
            case 'T': ret = 3; break;
            default: ret = 0;
        }
        return ret;
    }
    vector<string> findRepeatedDnaSequences(string s) {
        vector<string> ans;
        int n = s.length(); 
        if (n <= 10) {
            return ans;
        }
        int base = 4, m = 0, highbase = (1 << 18);
        for (int i = 0; i < 10; ++i) {
            m = m * base + getnum(s[i]);
        }
        unordered_map<int, int> mp;
        mp[m] = 1;
        for (int i = 10; i < n; ++i) {
            m -= highbase * getnum(s[i - 10]);
            m = m * base + getnum(s[i]);
            if (mp.find(m) != mp.end()) {
                if (mp[m] == 1) {
                    mp[m] = -1;
                    ans.push_back(s.substr(i - 9, 10));
                }
            } else {
                mp[m] = 1;
            }
        }
        return ans;
    }
};