Merge branch 'siri/unicode-merge' into maint

* siri/unicode-merge: (28 commits)
  stdlib: use 'unicode' option for regexp in ets
  ct: use 'unicode' option for regexps
  syntax_tools: add 'unicode' option to re:run for matching paths
  kernel: update simple error logger to print Unicode strings
  stdlib: add Unicode translation modifier in error_logger_tty_h
  wx: add Unicode translation modifier to wx_object
  stdlib: add Unicode translation modifier in debug format funs
  sasl: set encoding of SASL report log
  stdlib: use Unicode translation modifier in error_logger_file_h
  observer: Improve handling of Unicode
  mnesia: Improve handling of Unicode
  stdlib : Improve handling of Unicode
  kernel: Improve handling of Unicode
  hipe: Improve handling of Unicode
  edoc: Improve handling of Unicode
  syntax_tools: Improve handling of Unicode
  dialyzer: Improve handling of Unicode
  et: Improve handling of Unicode
  xref: Improve handling of Unicode
  fprof: Modify handling of Unicode
  eprof: Improve handling of Unicode
  eunit: Improve handling of Unicode
  stdlib: Improve handling of Unicode in escript
  stdlib: Improve handling of Unicode in edlin_expand
  stdlib: Modify handling of Unicode in proc_lib
  sasl: Improve handling of Unicode
  edoc: Improve handling of Unicode
  debugger: Improve handling of Unicode

OTP-14462
OTP-14464

4 files changed, 19 insertions, 18 deletions

diff --git a/lib/dialyzer/src/dialyzer.erl b/lib/dialyzer/src/dialyzer.erl
index c319acb2fb..1538174d4a 100644
--- a/lib/dialyzer/src/dialyzer.erl
+++ b/lib/dialyzer/src/dialyzer.erl
@@ -498,24 +498,24 @@ call_or_apply_to_string(ArgNs, FailReason, SigArgs, SigRet,
 	true ->
 	  %% We do not know which argument(s) caused the failure
 	  io_lib:format("will never return since the success typing arguments"
-			" are ~s\n", [SigArgs]);
+			" are ~ts\n", [SigArgs]);
         false ->
 	  io_lib:format("will never return since it differs in the ~s argument"
-			" from the success typing arguments: ~s\n",
+			" from the success typing arguments: ~ts\n",
 			[PositionString, SigArgs])
       end;
     only_contract ->
       case (ArgNs =:= []) orelse IsOverloaded of
 	true ->
 	  %% We do not know which arguments caused the failure
-	  io_lib:format("breaks the contract ~s\n", [Contract]);
+	  io_lib:format("breaks the contract ~ts\n", [Contract]);
 	false ->
-	  io_lib:format("breaks the contract ~s in the ~s argument\n",
+	  io_lib:format("breaks the contract ~ts in the ~s argument\n",
 			[Contract, PositionString])
       end;
     both ->
-      io_lib:format("will never return since the success typing is ~s -> ~s"
-		    " and the contract is ~s\n", [SigArgs, SigRet, Contract])
+      io_lib:format("will never return since the success typing is ~ts -> ~ts"
+		    " and the contract is ~ts\n", [SigArgs, SigRet, Contract])
   end.
 
 form_positions(ArgNs) ->
@@ -533,9 +533,9 @@ form_positions(ArgNs) ->
 form_expected_without_opaque([{N, T, TStr}]) ->
   case erl_types:t_is_opaque(T) of
     true  ->
-      io_lib:format("an opaque term of type ~s as ", [TStr]);
+      io_lib:format("an opaque term of type ~ts as ", [TStr]);
     false ->
-      io_lib:format("a term of type ~s (with opaque subterms) as ", [TStr])
+      io_lib:format("a term of type ~ts (with opaque subterms) as ", [TStr])
   end ++ form_position_string([N]) ++ " argument";
 form_expected_without_opaque(ExpectedTriples) -> %% TODO: can do much better here
   {ArgNs, _Ts, _TStrs} = lists:unzip3(ExpectedTriples),
@@ -546,8 +546,8 @@ form_expected(ExpectedArgs) ->
     [T] ->
       TS = erl_types:t_to_string(T),
       case erl_types:t_is_opaque(T) of
-	true  -> io_lib:format("an opaque term of type ~s is expected", [TS]);
-	false -> io_lib:format("a structured term of type ~s is expected", [TS])
+	true  -> io_lib:format("an opaque term of type ~ts is expected", [TS]);
+	false -> io_lib:format("a structured term of type ~ts is expected", [TS])
       end;
     [_,_|_] -> "terms of different types are expected in these positions"
   end.
diff --git a/lib/dialyzer/src/dialyzer_cl_parse.erl b/lib/dialyzer/src/dialyzer_cl_parse.erl
index a456d38e64..80c10183cf 100644
--- a/lib/dialyzer/src/dialyzer_cl_parse.erl
+++ b/lib/dialyzer/src/dialyzer_cl_parse.erl
@@ -82,7 +82,7 @@ cl(["--get_warnings"|T]) ->
 cl(["-D"|_]) ->
   cl_error("No defines specified after -D");
 cl(["-D"++Define|T]) ->
-  Def = re:split(Define, "=", [{return, list}]),
+  Def = re:split(Define, "=", [{return, list}, unicode]),
   append_defines(Def),
   cl(T);
 cl(["-h"|_]) ->
diff --git a/lib/dialyzer/src/dialyzer_gui_wx.erl b/lib/dialyzer/src/dialyzer_gui_wx.erl
index 538327d4d1..b4b1872c12 100644
--- a/lib/dialyzer/src/dialyzer_gui_wx.erl
+++ b/lib/dialyzer/src/dialyzer_gui_wx.erl
@@ -1093,7 +1093,7 @@ macro_loop(Options, Win, Box, MacroText, TermText, Frame) ->
 	    Fun = 
 	      fun(X) ->
 		  Val = wxControlWithItems:getString(Box,X),
-		  [MacroName|_] = re:split(Val, " ", [{return, list}]),
+		  [MacroName|_] = re:split(Val, " ", [{return, list}, unicode]),
 		  list_to_atom(MacroName)
 	      end,
 	    Delete = [Fun(X) || X <- List],
diff --git a/lib/dialyzer/src/typer.erl b/lib/dialyzer/src/typer.erl
index bf5484e5f6..16b9c8a94a 100644
--- a/lib/dialyzer/src/typer.erl
+++ b/lib/dialyzer/src/typer.erl
@@ -74,7 +74,8 @@
 -spec start() -> no_return().
 
 start() ->
-_ = io:setopts(standard_error, [{encoding,unicode}]),
+  _ = io:setopts(standard_error, [{encoding,unicode}]),
+  _ = io:setopts([{encoding,unicode}]),
   {Args, Analysis} = process_cl_args(),
   %% io:format("Args: ~p\n", [Args]),
   %% io:format("Analysis: ~p\n", [Analysis]),
@@ -484,12 +485,12 @@ write_typed_file(File, Info) ->
 
 write_typed_file(File, Info, NewFileName) ->
   {ok, Binary} = file:read_file(File),
-  Chars = binary_to_list(Binary),
+  Chars = unicode:characters_to_list(Binary),
   write_typed_file(Chars, NewFileName, Info, 1, []),
   io:format("             Saved as: ~tp\n", [NewFileName]).
 
 write_typed_file(Chars, File, #info{functions = []}, _LNo, _Acc) ->
-  ok = file:write_file(File, list_to_binary(Chars), [append]);
+  ok = file:write_file(File, unicode:characters_to_binary(Chars), [append]);
 write_typed_file([Ch|Chs] = Chars, File, Info, LineNo, Acc) ->
   [{Line,F,A}|RestFuncs] = Info#info.functions,
   case Line of
@@ -519,7 +520,7 @@ write_typed_file([Ch|Chs] = Chars, File, Info, LineNo, Acc) ->
 raw_write(F, A, Info, File, Content) ->
   TypeInfo = get_type_string(F, A, Info, file),
   ContentList = lists:reverse(Content) ++ TypeInfo ++ "\n",
-  ContentBin = list_to_binary(ContentList),
+  ContentBin = unicode:characters_to_binary(ContentList),
   file:write_file(File, ContentBin, [append]).
 
 get_type_string(F, A, Info, Mode) ->
@@ -608,7 +609,7 @@ cl(["-D"++Def|Opts]) ->
   case Def of
     "" -> fatal_error("no variable name specified after -D");
     _ ->
-      DefPair = process_def_list(re:split(Def, "=", [{return, list}])),
+      DefPair = process_def_list(re:split(Def, "=", [{return, list}, unicode])),
       {{def, DefPair}, Opts}
   end;
 cl(["-I",Dir|Opts]) -> {{inc, Dir}, Opts};
@@ -697,7 +698,7 @@ get_all_files(#args{files = Fs, files_r = Ds}) ->
 test_erl_file_exclude_ann(File) ->
   case is_erl_file(File) of
     true -> %% Exclude files ending with ".ann.erl"
-      case re:run(File, "[\.]ann[\.]erl$") of
+      case re:run(File, "[\.]ann[\.]erl$", [unicode]) of
 	{match, _} -> false;
 	nomatch -> true
       end;