From eae496a72e270fd7af411714738e99a7fadfd19b Mon Sep 17 00:00:00 2001
From: Rickard Green <rickard@erlang.org>
Date: Wed, 6 Sep 2017 17:00:14 +0200
Subject: Don't allow null in filenames

---
 lib/stdlib/src/filename.erl | 70 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

(limited to 'lib/stdlib/src/filename.erl')

diff --git a/lib/stdlib/src/filename.erl b/lib/stdlib/src/filename.erl
index 9bf4290916..1c3ab6d274 100644
--- a/lib/stdlib/src/filename.erl
+++ b/lib/stdlib/src/filename.erl
@@ -41,6 +41,7 @@
          safe_relative_path/1]).
 -export([find_src/1, find_src/2]). % deprecated
 -export([basedir/2, basedir/3]).
+-export([validate/1]).
 
 %% Undocumented and unsupported exports.
 -export([append/2]).
@@ -1135,3 +1136,72 @@ basedir_os_type() ->
         {win32,_}     -> windows;
         _             -> linux
     end.
+
+%%
+%% validate/1
+%%
+
+-spec validate(FileName) -> boolean() when
+      FileName :: file:name_all().
+
+validate(FileName) when is_binary(FileName) ->
+    %% Raw filename...
+    validate_bin(FileName);
+validate(FileName) when is_list(FileName);
+                        is_atom(FileName) ->
+    validate_list(FileName,
+                  file:native_name_encoding(),
+                  os:type()).
+
+validate_list(FileName, Enc, Os) ->
+    try
+        true = validate_list(FileName, Enc, Os, 0) > 0
+    catch
+        _ : _ -> false
+    end.
+
+validate_list([], _Enc, _Os, Chars) ->
+    Chars;
+validate_list(C, Enc, Os, Chars) when is_integer(C) ->
+    validate_char(C, Enc, Os),
+    Chars+1;
+validate_list(A, Enc, Os, Chars) when is_atom(A) ->
+    validate_list(atom_to_list(A), Enc, Os, Chars);
+validate_list([H|T], Enc, Os, Chars) ->
+    NewChars = validate_list(H, Enc, Os, Chars),
+    validate_list(T, Enc, Os, NewChars).
+
+%% C is always an integer...
+% validate_char(C, _, _) when not is_integer(C) ->
+%     throw(invalid);
+validate_char(C, _, _) when C < 1 ->
+    throw(invalid); %% No negative or null characters...
+validate_char(C, latin1, _) when C > 255 ->
+    throw(invalid);
+validate_char(C, utf8, _) when C >= 16#110000 ->
+    throw(invalid);
+validate_char(C, utf8, {win32, _}) when C > 16#ffff ->
+    throw(invalid); %% invalid win wchar...
+validate_char(_C, utf8, {win32, _}) ->
+    ok; %% Range below is accepted on windows...
+validate_char(C, utf8, _) when 16#D800 =< C, C =< 16#DFFF ->
+    throw(invalid); %% invalid unicode range...
+validate_char(_, _, _) ->
+    ok.
+
+validate_bin(Bin) ->
+    %% Raw filename. That is, we do not interpret
+    %% the encoding, but we still do not accept
+    %% null characters...
+    try
+        true = validate_bin(Bin, 0) > 0
+    catch
+        _ : _ -> false
+    end.
+
+validate_bin(<<>>, Bs) ->
+    Bs;
+validate_bin(<<0, _Rest/binary>>, _Bs) ->
+    throw(invalid); %% No null characters allowed...
+validate_bin(<<_B, Rest/binary>>, Bs) ->
+    validate_bin(Rest, Bs+1).
-- 
cgit v1.2.3