c++ 11 utf8 subst…

改编自：http://www.zedwood.com/article/cpp-utf-8-mb_substr-function

这个也有问题，我基础这个改了个完善的另外写了个文字个数统计

uint64_t pinyin::utf8_len(const std::string &str) {

    uint64_t i = 0;

    uint64_t count = 0;

    uint64_t c;

    for (i = 0; i < str.length(); i++) {

        count++;

        c = (unsigned char) str[i];

        if (c >= 0 && c <= 127) i += 0;

        else if ((c & 0xE0) == 0xC0) i += 1;

        else if ((c & 0xF0) == 0xE0) i += 2;

        else if ((c & 0xF8) == 0xF0) i += 3;

            //else if (($c & 0xFC) == 0xF8) i+=4; // 111110bb //byte 5, unnecessary in 4 byte UTF-8

            //else if (($c & 0xFE) == 0xFC) i+=5; // 1111110b //byte 6, unnecessary in 4 byte UTF-8

        else return 0;//invalid utf8

    }

    return count;

}

std::string pinyin::utf8_substr(const std::string &str, uint64_t start, uint64_t leng) {

    if (leng == 0) { return ""; }

    uint64_t c, i, ix, q, min = std::string::npos, max = std::string::npos;

    for (q = 0, i = 0, ix = str.length(); i < ix; i++, q++) {

        if (q == start) { min = i; }

        if (q <= start + leng || leng == std::string::npos) { max = i; }

        c = (unsigned char) str[i];

        if (c >= 0 && c <= 127) i += 0;

        else if ((c & 0xE0) == 0xC0) i += 1;

        else if ((c & 0xF0) == 0xE0) i += 2;

        else if ((c & 0xF8) == 0xF0) i += 3;

            //else if (($c & 0xFC) == 0xF8) i+=4; // 111110bb //byte 5, unnecessary in 4 byte UTF-8

            //else if (($c & 0xFE) == 0xFC) i+=5; // 1111110b //byte 6, unnecessary in 4 byte UTF-8

        else return "";//invalid utf8

    }

    if (q <= start + leng || leng == std::string::npos) { max = i; }

    if (min == std::string::npos || max == std::string::npos) { return ""; }

    return str.substr(min, max - min);

}