Created
December 8, 2013 08:39
-
-
Save bg5sbk/7854685 to your computer and use it in GitHub Desktop.
Get UTF-8 character by Erlang.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
-module(utf8_util). | |
-export([get_utf8_char/1]). | |
get_utf8_char ([]) -> | |
{0, []}; | |
get_utf8_char ([Char1 | String]) -> | |
get_utf8_char(Char1, String). | |
get_utf8_char (Char1, String) when Char1 < 16#80 -> | |
{Char1, String}; | |
get_utf8_char (Char1, String) when Char1 < 16#E0 -> | |
[Char2 | String2] = String, | |
{{Char1, Char2}, String2}; | |
get_utf8_char (Char1, String) when Char1 < 16#F0 -> | |
[Char2, Char3 | String2] = String, | |
{{Char1, Char2, Char3}, String2}; | |
get_utf8_char (Char1, String) when Char1 < 16#F8 -> | |
[Char2, Char3, Char4 | String2] = String, | |
{{Char1, Char2, Char3, Char4}, String2}; | |
get_utf8_char (Char1, String) when Char1 < 16#FC-> | |
[Char2, Char3, Char4, Char5 | String2] = String, | |
{{Char1, Char2, Char3, Char4, Char5}, String2}; | |
get_utf8_char (Char1, String) when Char1 < 16#FE-> | |
[Char2, Char3, Char4, Char5, Char6 | String2] = String, | |
{{Char1, Char2, Char3, Char4, Char5, Char6}, String2}. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment