Refactor out string.gsplit to util.gsplit

This commit is contained in:
chrox
2015-04-22 14:17:06 +08:00
parent 98515a2210
commit 932df2a2f9
3 changed files with 79 additions and 44 deletions

View File

@@ -8,4 +8,43 @@ function util.stripePunctuations(word)
return word:gsub("\226[\128-\131][\128-\191]",''):gsub("^%p+",''):gsub("%p+$",'')
end
--[[
Lua doesn't have a string.split() function and most of the time
you don't really need it because string.gmatch() is enough.
However string.gmatch() has one significant disadvantage for me:
You can't split a string while matching both the delimited
strings and the delimiters themselves without tracking positions
and substrings. The gsplit function below takes care of
this problem.
Author: Peter Odding
License: MIT/X11
Source: http://snippets.luacode.org/snippets/String_splitting_130
--]]
function util.gsplit(str, pattern, capture)
pattern = pattern and tostring(pattern) or '%s+'
if (''):find(pattern) then
error('pattern matches empty string!', 2)
end
return coroutine.wrap(function()
local index = 1
repeat
local first, last = str:find(pattern, index)
if first and last then
if index < first then
coroutine.yield(str:sub(index, first - 1))
end
if capture then
coroutine.yield(str:sub(first, last))
end
index = last + 1
else
if index <= #str then
coroutine.yield(str:sub(index))
end
break
end
until index > #str
end)
end
return util