许久没做erlang开发了，最近有网友问到erlang的问题，就抽时间看下。问题是这样的，模块有中文，将中文直接打印出来，shell下显示会出现乱码，但如果先将中文转成binary，就可以正常显示出来。
shell中文乱码问题
这里以一个简单的例子，说明下：
-module(m).
-compile(export_all).
test() ->
io:format("~ts~n", ["中国"]),
io:format("~ts~n", [list_to_binary("中国")]).编译，然后测试下结果：Eshell V5.10.3 (abort with ^G)
1> c(m).
{ok, m}
2> m:test().
??-???
中国
ok{function, test, 0, 2}.
{label,1}.
{line,[{location,"erl.erl",4}]}.
{func_info,{atom,erl},{atom,test},0}.
{label,2}.
{allocate,0,0}.
{move,{literal,[[228,184,173,229,155,189]]},{x,1}}.
{move,{literal,"~ts~n"},{x,0}}.
{line,[{location,"erl.erl",5}]}.
{call_ext,2,{extfunc,io,format,2}}.
{move,{literal,[<<228,184,173,229,155,189>>]},{x,1}}.
{move,{literal,"~ts~n"},{x,0}}.
{line,[{location,"erl.erl",6}]}.
{call_ext_last,2,{extfunc,io,format,2},0}.实际上，erlang会做优化，list_to_binary在编译期就被优化掉了。%% io_lib.erl
format(Format, Args) ->
case catch io_lib_format:fwrite(Format, Args) of
{‘EXIT‘,_} ->
erlang:error(badarg, [Format, Args]);
Other ->
Other
end.
实现代码在 io_lib_format模块，如下：%% io_lib_format.erl
fwrite(Format, Args) when is_atom(Format) ->
fwrite(atom_to_list(Format), Args);
fwrite(Format, Args) when is_binary(Format) ->
fwrite(binary_to_list(Format), Args);
fwrite(Format, Args) ->
Cs = collect(Format, Args), %% 收集格式化信息，生成控制结构
Pc = pcount(Cs), %% 计算请求打印的数量
build(Cs, Pc, 0). %% 解析控制结构，生成数据
collect([$~|Fmt0], Args0) ->
%% 格式化参数以 ~打头，否则忽略
{C,Fmt1,Args1} = collect_cseq(Fmt0, Args0),
[C|collect(Fmt1, Args1)];
collect([C|Fmt], Args) ->
[C|collect(Fmt, Args)];
collect([], []) -> [].
collect_cseq(Fmt0, Args0) ->
{F,Ad,Fmt1,Args1} = field_width(Fmt0, Args0),
{P,Fmt2,Args2} = precision(Fmt1, Args1),
{Pad,Fmt3,Args3} = pad_char(Fmt2, Args2),
{Encoding,Fmt4,Args4} = encoding(Fmt3, Args3),
{Strings,Fmt5,Args5} = strings(Fmt4, Args4),
{C,As,Fmt6,Args6} = collect_cc(Fmt5, Args5),
{{C,As,F,Ad,P,Pad,Encoding,Strings},Fmt6,Args6}.
%% 检查format 参数含有 t， 然后打标记 unicode，其他记latin1
encoding([$t|Fmt],Args) ->
true = hd(Fmt) =/= $l, %% 确保不是传入 ~tl
{unicode,Fmt,Args};
encoding(Fmt,Args) ->
{latin1,Fmt,Args}.再看下以上build部分的代码。代码过长，做了删节：%% io_lib_format.erl
build([{C,As,F,Ad,P,Pad,Enc,Str}|Cs], Pc0, I) ->
S = control(C, As, F, Ad, P, Pad, Enc, Str, I),
%% 处理控制结构
Pc1 = decr_pc(C, Pc0),
if
Pc1 > 0 -> [S|build(Cs, Pc1, indentation(S, I))];
true -> [S|build(Cs, Pc1, I)]
end;
build([$\n|Cs], Pc, _I) -> [$\n|build(Cs, Pc, 0)];
build([$\t|Cs], Pc, I) -> [$\t|build(Cs, Pc, ((I + 8) div 8) * 8)];
build([C|Cs], Pc, I) -> [C|build(Cs, Pc, I+1)];
build([], _Pc, _I) -> [].
control($w, [A], F, Adj, P, Pad, _Enc, _Str, _I) ->
term(io_lib:write(A, -1), F, Adj, P, Pad);
control($p, [A], F, Adj, P, Pad, Enc, Str, I) ->
print(A, -1, F, Adj, P, Pad, Enc, Str, I);
control($W, [A,Depth], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(Depth) ->
term(io_lib:write(A, Depth), F, Adj, P, Pad);
control($P, [A,Depth], F, Adj, P, Pad, Enc, Str, I) when is_integer(Depth) ->
print(A, Depth, F, Adj, P, Pad, Enc, Str, I);
control($s, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_atom(A) ->
string(atom_to_list(A), F, Adj, P, Pad);
control($s, [L0], F, Adj, P, Pad, latin1, _Str, _I) ->
%% 处理 ~s，如果数据标记是 latin1
L = iolist_to_chars(L0),
string(L, F, Adj, P, Pad);
control($s, [L0], F, Adj, P, Pad, unicode, _Str, _I) ->
%% 处理 ~s，如果数据标记是 unicode
L = cdata_to_chars(L0),
uniconv(string(L, F, Adj, P, Pad));
control($e, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_float(A) ->
%% 该函数太长了，不是讨论重点，做了删节
cdata_to_chars([C|Cs]) when is_integer(C), C >= $\000 ->
[C | cdata_to_chars(Cs)];
cdata_to_chars([I|Cs]) ->
[cdata_to_chars(I) | cdata_to_chars(Cs)];
cdata_to_chars([]) ->
[];
cdata_to_chars(B) when is_binary(B) ->
%% 如果数据是binary，做一下unicode转换
case catch unicode:characters_to_list(B) of
L when is_list(L) -> L;
_ -> binary_to_list(B)
end.可想而知，如果没有不是 ~ts，或者不是binary，都不会做转换。原文：http://blog.csdn.net/mycwq/article/details/50762572