Lua实现特殊字符过滤

[lmc994464212qq]

function filter_spec_chars(s,charTypes)
local ss = {}
local k = 1
while true do
if k > #s then break end
local c = string.byte(s,k)
if not c then break end
if c<192 then
if (c>=48 and c<=57) then
if charTypes.num then
table.insert(ss, string.char(c))
end
elseif (c>= 65 and c<=90) or (c>=97 and c<=122) then
if charTypes.char then
table.insert(ss, string.char(c))
end
end
k = k + 1
elseif c<224 then
k = k + 2
elseif c<240 then
if c>=228 and c<=233 then
local c1 = string.byte(s,k+1)
local c2 = string.byte(s,k+2)
if c1 and c2 then
local a1,a2,a3,a4 = 128,191,128,191
if c == 228 then a1 = 184
elseif c == 233 then a2,a4 = 190,c1 ~= 190 and 191 or 165
end
if c1>=a1 and c1<=a2 and c2>=a3 and c2<=a4 then
if charTypes.chs then
table.insert(ss, string.char(c,c1,c2))
end
end
end
end
k = k + 3
elseif c<248 then
k = k + 4
elseif c<252 then
k = k + 5
elseif c<254 then
k = k + 6
end
end
return table.concat(ss)
end

local function main()
print(filter_spec_chars("123你好OI+)*&^#@163.com", {num="数字",char="字母",chs="中文"}))
end
main()

[勤奋的小游侠]

你这种东西不实用，几个M文件的过滤会卡死

[zerozerg2006]

引用 1 楼 lovesmiles 的回复:

你这种东西不实用，几个M文件的过滤会卡死

其实也不能这么说，让lua使用扫描的方法去处理几M的文件本身就不合理。一个脚本语言不应该期望和C一样强大。 我猜楼主是想处理几十个字符的字符串吧

[miniBirds]

-- RuneLen returns the number of bytes required to encode the rune. -- It returns -1 if the rune is not a valid value to encode in UTF-8. local surrogateMin = 55296 --0xD800 local surrogateMax =57343 -- 0xDFFF local rune1Max = 127 --1<<7 - 1 local rune2Max = 2047 -- 1<<11 - 1 local rune3Max =65535 -- 1<<16 - 1 local MaxRune = 1114111-- "\U0010FFFF" -- Maximum valid Unicode code point. function RuneLen(r) if r < 0 then return -1 elseif r <= rune1Max then return 1 elseif r <= rune2Max then return 2 elseif surrogateMin <= r and r <= surrogateMax then return -1 elseif r <= rune3Max then return 3 elseif r <= MaxRune then return 4 else return -1 end end local str="a你😊b好3😊c" for p, c in utf8.codes(str) do print("#############################################") print(p .."=".. c .."("..RuneLen(c)..")") end