UTF-8字符串在lua中的字长问题

UTF-8字符串在lua中每个字符的字长是不一样，中文，英文，其他字符。都有各自不同的字长，所以UTF-8也叫作变长字符。规则如下：

1. utf8字符是变长字符

2. 字符长度有规律

UTF-8字符规律

字符串的首个byte表示了该utf8字符的长度

0xxxxxxx - 1 byte

110yxxxx - 192, 2 byte

1110yyyy - 225, 3 byte

11110zzz - 240, 4 byte

所以，要想满足自己对字符串按字符数量截取的话，就要进行一下包装了，直接贴代码，如下：

local UTF8 = {}

function UTF8.chSize(char)
    if not char then
        return 0
    elseif char > 240 then
        return 4
    elseif char > 225 then
        return 3
    elseif char > 192 then
        return 2
    else
        return 1
    end
end


function UTF8.sub(str, startChar, numChars)
    if str == nil then
        return ""
    end
  local startIndex = 1
    if (startChar==nil) then
      startChar = 1;
    end
    if (numChars==nil) then
      numChars =15;
    end;

    local allChars = numChars

  while startChar > 1 do
      local char = string.byte(str, startIndex)
      startIndex = startIndex + UTF8.chSize(char)
      startChar = startChar - 1
  end

  local currentIndex = startIndex
    while currentIndex <= numChars and currentIndex <= #str do
    local char = string.byte(str, currentIndex)
    currentIndex = currentIndex + UTF8.chSize(char)
  end

    if numChars < #str then
        return str:sub(startIndex, currentIndex - 1).."..."
    else
        return str:sub(startIndex, currentIndex - 1)
    end


end

function UTF8.length(str)
local length = 0;
local currentIndex = 1;
while currentIndex <= #str do
    local char = string.byte(str, currentIndex)
    currentIndex = currentIndex + UTF8.chSize(char)
    length = length + 1
  end
  return length;
end

function UTF8.toString(str)
    if type(str)=="string" then
        return str
    end
    local char = ""
    if type(str)~="table" then
        return char
    end
    for key, var in pairs(str) do
        if var == "\0" then
            break
        end
        char = char .. var
    end
    return char
end
return UTF8;