LintCode 1369: Most Common Word

1369. Most Common Word
      Given a paragraph and a list of banned words, return the most frequent word that is not in the list of banned words. It is guaranteed there is at least one word that isn’t banned, and that the answer is unique.

Words in the list of banned words are given in lowercase, and free of punctuation. Words in the paragraph are not case sensitive. The answer is in lowercase.

Example
Input:
paragraph = “Bob hit a ball, the hit BALL flew far after it was hit.”
banned = [“hit”]

Output:“ball”

Explanation:
“hit” occurs 3 times, but it is a banned word.
“ball” occurs twice (and no other word does), so it is the most frequent non-banned word in the paragraph.
Note that words in the paragraph are not case sensitive,
that punctuation is ignored (even if adjacent to words, such as “ball,”),
and that “hit” isn’t the answer even though it occurs more because it is banned.
Notice
1 <= paragraph.length <= 1000.
1 <= banned.length <= 100.
1 <= banned[i].length <= 10.
The answer is unique, and written in lowercase (even if its occurrences in paragraph may have uppercase symbols, and even if it is a proper noun.)
paragraph only consists of letters, spaces, or the punctuation symbols !?’,;.
Different words in paragraph are always separated by a space.
There are no hyphens or hyphenated words.
Words only consist of letters, never apostrophes or other punctuation symbols.

“Bob”
[]

代码如下：
解法1：tokenize。

class Solution {
public:
    /**
     * @param paragraph: 
     * @param banned: 
     * @return: nothing
     */
    string mostCommonWord(string &paragraph, vector<string> &banned) {
        int len = paragraph.size();
        int bannedCount = banned.size();
        map<string, int> mp; //word, count;
        set<string> s(banned.begin(), banned.end()); //banned set
    
        to_lower_letter(paragraph);
        for (int i = 0; i < bannedCount; ++i) {
            to_lower_letter(banned[i]);
        }
        
        int begPos = 0, endPos = 0;
        int boundary = len - 1;
        for (int i = 0; i < boundary; ++i) {
            string word;
            if (is_lower_letter((char)paragraph[i])) {
                if (!is_lower_letter((char)paragraph[i + 1])) {
                    endPos = i;
                    word = paragraph.substr(begPos, endPos - begPos + 1);
                } else if (i == len - 2) {
                    endPos = boundary;
                    word = paragraph.substr(begPos, endPos - begPos + 1);
                }

                if (word.size() > 0) {
                    if (s.find(word) == s.end()) {
                        if (mp.find(word) == mp.end()) {
                            mp[word] = 1;     
                        } else {
                            mp[word]++;
                        }
                    }
                }
            } else if (!is_lower_letter((char)paragraph[i]) && is_lower_letter((char)paragraph[i + 1])) {
                begPos = i + 1;
            } else {
                continue;
            }
        }
        
        int maxCount = INT_MIN;
        string result;
        for (auto m : mp) {
            if (m.second > maxCount) {
                result = m.first;
                maxCount = m.second;
            }
        }
        
        return result;
    }

private:
    inline bool is_lower_letter(char c) {
        return (c >= 'a') && (c <= 'z');
    }

    inline void to_lower_letter(string &s) {
        int len = s.size();
        for (int i = 0; i < len; ++i) {
            if ((s[i] >= 'A') && (s[i] <= 'Z'))
                s[i] = s[i] - 'A' + 'a'; 
        }
    }     
};

解法2：基于stringstream

class Solution {
public:
    /**
     * @param paragraph: 
     * @param banned: 
     * @return: nothing
     */
    string mostCommonWord(string &paragraph, vector<string> &banned) {
        int len = paragraph.size();
        int bannedCount = banned.size();
        map<string, int> mp; //word, count;
        set<string> s(banned.begin(), banned.end()); //banned set
    
        to_lower_letter(paragraph);
        for (int i = 0; i < bannedCount; ++i) {
            to_lower_letter(banned[i]);
        }
        
        stringstream ss(paragraph);
        string buf;
        //vector<string> words;
        while(ss >> buf) {
            if (!is_lower_letter(buf.back())) buf.pop_back();
            
            if (s.find(buf) == s.end()) {
                if (mp.find(buf) == mp.end()) {
                    mp[buf] = 1;     
                } else {
                    mp[buf]++;
                }
            }
        }
        
        int maxCount = INT_MIN;
        string result;
        for (auto m : mp) {
            if (m.second > maxCount) {
                result = m.first;
                maxCount = m.second;
            }
        }
        
        return result;
    }

private:
    inline bool is_lower_letter(char c) {
        return (c >= 'a') && (c <= 'z');
    }

    inline void to_lower_letter(string &s) {
        int len = s.size();
        for (int i = 0; i < len; ++i) {
            if ((s[i] >= 'A') && (s[i] <= 'Z'))
                s[i] = s[i] - 'A' + 'a'; 
        }
    }     
};