LintCode-499: Word Count (Map Reduce) (System Design题)

这题其实就是简单模拟字符串分块统计个数和归并的过程。
我用的stringstream来split字符串。

/**
 * Definition of Input:
 * template<class T>
 * class Input {
 * public:
 *     bool done(); 
 *         // Returns true if the iteration has elements or false.
 *     void next();
 *         // Move to the next element in the iteration
 *         // Runtime error if the iteration has no more elements
 *     T value();
 *        // Get the current element, Runtime error if
 *        // the iteration has no more elements
 * }
 */
class WordCountMapper: public Mapper {
public:
    void Map(Input<string>* input) {
        // Please directly use func 'output' to 
        // output the results into output buffer.
        // void output(string &key, int value);

        while(!input->done()) {
            stringstream ss;
            string word;
            ss << input->value();
            while(ss >> word) output(word, 1);
            input->next();
        }
    }
};


class WordCountReducer: public Reducer {
public:
    void Reduce(string &key, Input<int>* input) {
        // Please directly use func 'output' to 
        // output the results into output buffer.
        // void output(string &key, int value);

        int count = 0;
        while(!input->done()) {
            count += input->value();
            input->next();
        }

        output(key, count);
    }
};

jiuzhang给的答案是用split()函数，我觉得也不错。

void Map(Input<string>* input) {
        // Write your code here
        // Please directly use func 'output' to 
        // output the results into output buffer.
        // void output(string &key, int value);
        while (!input->done()) {
            vector<string> words = split(input->value(), " ");
            for (string word : words) {
                output(word, 1);
            }
            input->next();
        }
    }

    vector<string> split(const string &str, string delim) {
        vector<string> results;
        int lastIndex = 0, index;
        while ((index = str.find(delim, lastIndex)) != string::npos) {
            results.push_back(str.substr(lastIndex, index - lastIndex));
            lastIndex = index + delim.length();
        }
        if (lastIndex != str.length()) {
            results.push_back(str.substr(lastIndex, str.length() - lastIndex));
        }
        return results;
    }