如果你只想遍历这些令牌，这是非常简洁的:

line = "one, two and 3!"

for token in string.gmatch(line, "[^%s]+") do
   print(token)
end

输出:

一个, 两个 而且 3！

简单解释:“[^%s]+”模式匹配空格字符之间的每个非空字符串。

我使用上面的例子来创建我自己的函数。但对我来说，缺失的部分是自动逃脱魔法角色。

以下是我的观点:

function split(text, delim)
    -- returns an array of fields based on text and delimiter (one character only)
    local result = {}
    local magic = "().%+-*?[]^$"

    if delim == nil then
        delim = "%s"
    elseif string.find(delim, magic, 1, true) then
        -- escape magic
        delim = "%"..delim
    end

    local pattern = "[^"..delim.."]+"
    for w in string.gmatch(text, pattern) do
        table.insert(result, w)
    end
    return result
end

因为剥猫皮的方法不止一种，下面是我的方法:

代码:

#!/usr/bin/env lua

local content = [=[
Lorem ipsum dolor sit amet, consectetur adipisicing elit,
sed do eiusmod tempor incididunt ut labore et dolore magna 
aliqua. Ut enim ad minim veniam, quis nostrud exercitation 
ullamco laboris nisi ut aliquip ex ea commodo consequat.
]=]

local function split(str, sep)
   local result = {}
   local regex = ("([^%s]+)"):format(sep)
   for each in str:gmatch(regex) do
      table.insert(result, each)
   end
   return result
end

local lines = split(content, "\n")
for _,line in ipairs(lines) do
   print(line)
end

输出: 圣洁圣洁的人， sed做eiusmod时间incididunt ut并dolore麦格纳 aliqua。Ut enim ad minivenim, quis nostrud practice 这一切都是徒劳的结果。

解释:

gmatch函数作为一个迭代器，它获取所有与regex匹配的字符串。正则表达式接受所有字符，直到找到分隔符为止。

很多答案只接受单字符分隔符，或者不能很好地处理边缘情况(例如空分隔符)，所以我认为我将提供一个更明确的解决方案。

这里有两个函数，gsplit和split，改编自Scribunto MediaWiki扩展中的代码，用于维基百科等维基。该代码在GPL v2下获得许可。我已经更改了变量名，并添加了注释，使代码更容易理解，我还更改了代码，使用常规的Lua字符串模式，而不是Scribunto的Unicode字符串模式。原始代码在这里有测试用例。

-- gsplit: iterate over substrings in a string separated by a pattern
-- 
-- Parameters:
-- text (string)    - the string to iterate over
-- pattern (string) - the separator pattern
-- plain (boolean)  - if true (or truthy), pattern is interpreted as a plain
--                    string, not a Lua pattern
-- 
-- Returns: iterator
--
-- Usage:
-- for substr in gsplit(text, pattern, plain) do
--   doSomething(substr)
-- end
local function gsplit(text, pattern, plain)
  local splitStart, length = 1, #text
  return function ()
    if splitStart then
      local sepStart, sepEnd = string.find(text, pattern, splitStart, plain)
      local ret
      if not sepStart then
        ret = string.sub(text, splitStart)
        splitStart = nil
      elseif sepEnd < sepStart then
        -- Empty separator!
        ret = string.sub(text, splitStart, sepStart)
        if sepStart < length then
          splitStart = sepStart + 1
        else
          splitStart = nil
        end
      else
        ret = sepStart > splitStart and string.sub(text, splitStart, sepStart - 1) or ''
        splitStart = sepEnd + 1
      end
      return ret
    end
  end
end

-- split: split a string into substrings separated by a pattern.
-- 
-- Parameters:
-- text (string)    - the string to iterate over
-- pattern (string) - the separator pattern
-- plain (boolean)  - if true (or truthy), pattern is interpreted as a plain
--                    string, not a Lua pattern
-- 
-- Returns: table (a sequence table containing the substrings)
local function split(text, pattern, plain)
  local ret = {}
  for match in gsplit(text, pattern, plain) do
    table.insert(ret, match)
  end
  return ret
end

split函数的一些例子:

local function printSequence(t)
  print(unpack(t))
end

printSequence(split('foo, bar,baz', ',%s*'))       -- foo     bar     baz
printSequence(split('foo, bar,baz', ',%s*', true)) -- foo, bar,baz
printSequence(split('foo', ''))                    -- f       o       o

下面是一个在Lua 4.0中工作的例程，返回inputstr中由sep分隔的子字符串的表t:

function string_split(inputstr, sep)
    local inputstr = inputstr .. sep
    local idx, inc, t = 0, 1, {}
    local idx_prev, substr
    repeat 
        idx_prev = idx
        inputstr = strsub(inputstr, idx + 1, -1)    -- chop off the beginning of the string containing the match last found by strfind (or initially, nothing); keep the rest (or initially, all)
        idx = strfind(inputstr, sep)                -- find the 0-based r_index of the first occurrence of separator 
        if idx == nil then break end                -- quit if nothing's found
        substr = strsub(inputstr, 0, idx)           -- extract the substring occurring before the separator (i.e., data field before the next delimiter)
        substr = gsub(substr, "[%c" .. sep .. " ]", "") -- eliminate control characters, separator and spaces
        t[inc] = substr             -- store the substring (i.e., data field)
        inc = inc + 1               -- iterate to next
    until idx == nil
    return t
end

这个简单的测试

inputstr = "the brown lazy fox jumped over the fat grey hen ... or something."
sep = " " 
t = {}
t = string_split(inputstr,sep)
for i=1,15 do
    print(i, t[i])
end

收益率:

--> t[1]=the
--> t[2]=brown
--> t[3]=lazy
--> t[4]=fox
--> t[5]=jumped
--> t[6]=over
--> t[7]=the
--> t[8]=fat
--> t[9]=grey
--> t[10]=hen
--> t[11]=...
--> t[12]=or
--> t[13]=something.

一种别人没有的方式

function str_split(str, sep)
    if sep == nil then
        sep = '%s'
    end 

    local res = {}
    local func = function(w)
        table.insert(res, w)
    end 

    string.gsub(str, '[^'..sep..']+', func)
    return res 
end