--- max 截取的长度
--- hasEnding 是否需要添加省略号
local function GetUTFLen(s)
local sTable = StringToTable(s)
local len = 0
local charLen = 0
for i = 1, #sTable do
local utfCharLen = string.len(sTable[i])
if utfCharLen > 1 then
-- 长度大于1的就认为是中文
charLen = 2
else
charLen = 1
end
len = len + charLen
end
return len
end
local function StringToTable(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
local function GetUTFLenWithCount(strText, length)
local sTable = StringToTable(strText)
local len = 0
local charLen = 1
local isLimited =(length >= 0)
for i = 1, #sTable do
local utfCharLen = string.len(sTable[i])
if utfCharLen > 1 then
-- 长度大于1的就认为是中文
charLen = 2
else
charLen = 1
end
len = len + utfCharLen
if isLimited then
length = length - charLen
if length <= 0 then
break
end
end
end
return len
end
function GetMaxLenString(s, maxLen, hasEnding)
local len = GetUTFLen(s)
local dstString = s-- 超长,裁剪,加...
if len > maxLen then
dstString = string.sub(s, 1, GetUTFLenWithCount(s, maxLen))
if hasEnding then
dstString = dstString .. "..."
end
end
return dstString
end