LuaString

function string.widthSingle(inputstr)
    -- 计算字符串宽度
    -- 可以计算出字符宽度，用于显示使用
    local lenInByte = #inputstr
    local width = 0
    local i = 1
    while (i<=lenInByte)
    do
        local curByte = string.byte(inputstr, i)
        local byteCount = 1;
        if curByte>0 and curByte<=127 then
            byteCount = 1                                           --1字节字符
        elseif curByte>=192 and curByte<223 then
            byteCount = 2                                           --双字节字符
        elseif curByte>=224 and curByte<239 then
            byteCount = 3                                           --汉字
        elseif curByte>=240 and curByte<=247 then
            byteCount = 4                                           --4字节字符
        end

        --local char = string.sub(inputstr, i, i+byteCount-1)
        --print(char)

        i = i + byteCount                                 -- 重置下一字节的索引
        width = width + 1                                 -- 字符的个数（长度）
    end
    return width
end

function string.ToTable(s)
    local tb = {}

    --[[
    UTF8的编码规则：
    1. 字符的第一个字节范围： 0x00—0x7F(0-127),或者 0xC2—0xF4(194-244); UTF8 是兼容 ascii 的，所以 0~127 就和 ascii 完全一致
    2. 0xC0, 0xC1,0xF5—0xFF(192, 193 和 245-255)不会出现在UTF8编码中
    3. 0x80—0xBF(128-191)只会出现在第二个及随后的编码中(针对多字节编码，如汉字)
    ]]
    for utfChar in string.gmatch(s, "[%z\1-\127\194-\244][\128-\191]*") do
        table.insert(tb, utfChar)
    end

    return tb
end

--获取中英混合UTF8字符串的真实字符数量
function string.SubStringGetTotalIndex(str)
    local curIndex = 0;
    local i = 1;
    local lastCount = 1;
    repeat
        lastCount = string.SubStringGetByteCount(str, i)
        i = i + lastCount;
        curIndex = curIndex + 1;
    until(lastCount == 0);
    return curIndex - 1;
end

function string.SubStringGetTrueIndex(str, index)
    local curIndex = 0;
    local i = 1;
    local lastCount = 1;
    repeat
        lastCount = string.SubStringGetByteCount(str, i)
        i = i + lastCount;
        curIndex = curIndex + 1;
    until(curIndex >= index);
    return i - lastCount;
end

--返回当前字符实际占用的字符数
function string.SubStringGetByteCount(str, index)
    local curByte = string.byte(str, index)
    local byteCount = 1;
    if curByte == nil then
        byteCount = 0
    elseif curByte > 0 and curByte <= 127 then
        byteCount = 1
    elseif curByte>=192 and curByte<=223 then
        byteCount = 2
    elseif curByte>=224 and curByte<=239 then
        byteCount = 3
    elseif curByte>=240 and curByte<=247 then
        byteCount = 4
    end
    return byteCount;
end

--截取中英混合的UTF8字符串，endIndex可缺省
function string.SubStringUTF8(str, startIndex, endIndex)
    if startIndex < 0 then
        startIndex = string.SubStringGetTotalIndex(str) + startIndex + 1;
    end

    if endIndex ~= nil and endIndex < 0 then
        endIndex = string.SubStringGetTotalIndex(str) + endIndex + 1;
    end

    if endIndex == nil then
        return string.sub(str, string.SubStringGetTrueIndex(str, startIndex));
    else
        return string.sub(str, string.SubStringGetTrueIndex(str, startIndex), string.SubStringGetTrueIndex(str, endIndex + 1) - 1);
    end
end

function string.utf8len(input)
    local len  = string.len(input)
    local left = len
    local cnt  = 0
    local arr  = {0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}
    while left ~= 0 do
        local tmp = string.byte(input, -left)
        local i   = #arr
        while arr[i] do
            if tmp >= arr[i] then
                left = left - i
                break
            end
            i = i - 1
        end
        cnt = cnt + 1
    end

    return cnt
end