Make Unicode corrections

10 files changed, 20 insertions, 24 deletions

diff --git a/lib/kernel/doc/src/file.xml b/lib/kernel/doc/src/file.xml
index 4a9b7d2ceb..a96da0fb4e 100644
--- a/lib/kernel/doc/src/file.xml
+++ b/lib/kernel/doc/src/file.xml
@@ -156,9 +156,6 @@
     <datatype>
       <name name="file_info_option"/>
     </datatype>
-    <datatype>
-      <name name="sendfile_option"/>
-    </datatype>
    </datatypes>
 
   <funcs>
@@ -1648,6 +1645,7 @@
     <func>
       <name name="sendfile" arity="5"/>
       <fsummary>send a file to a socket</fsummary>
+      <type name="sendfile_option"/>
       <desc>
         <p>Sends <c>Bytes</c> from the file
         referenced by <c>RawFile</c> beginning at <c>Offset</c> to
diff --git a/lib/kernel/src/application_controller.erl b/lib/kernel/src/application_controller.erl
index 3c860af48e..1602745669 100644
--- a/lib/kernel/src/application_controller.erl
+++ b/lib/kernel/src/application_controller.erl
@@ -1447,7 +1447,7 @@ prim_consult(FullName) ->
 	{ok, Bin, _} ->
             case file_binary_to_list(Bin) of
                 {ok, String} ->
-                    case erl_scan:string(String, 1, [unicode]) of
+                    case erl_scan:string(String) of
                         {ok, Tokens, _EndLine} ->
                             prim_parse(Tokens, []);
                         {error, Reason, _EndLine} ->
@@ -1600,7 +1600,7 @@ conv(_) -> [].
 
 %%% Fix some day: eliminate the duplicated code here
 make_term(Str) -> 
-    case erl_scan:string(Str, 1, [unicode]) of
+    case erl_scan:string(Str) of
 	{ok, Tokens, _} ->		  
 	    case erl_parse:parse_term(Tokens ++ [{dot, 1}]) of
 		{ok, Term} ->
diff --git a/lib/kernel/src/file.erl b/lib/kernel/src/file.erl
index 70c4583ad2..e7a0451011 100644
--- a/lib/kernel/src/file.erl
+++ b/lib/kernel/src/file.erl
@@ -1196,7 +1196,7 @@ change_time(Name, {{AY, AM, AD}, {AH, AMin, ASec}}=Atime,
 -spec sendfile(RawFile, Socket, Offset, Bytes, Opts) ->
    {'ok', non_neg_integer()} | {'error', inet:posix() | 
 				closed | badarg | not_owner} when
-      RawFile :: file:fd(),
+      RawFile :: fd(),
       Socket :: inet:socket(),
       Offset :: non_neg_integer(),
       Bytes :: non_neg_integer(),
@@ -1222,7 +1222,7 @@ sendfile(File, Sock, Offset, Bytes, Opts) ->
 -spec sendfile(Filename, Socket) ->
    {'ok', non_neg_integer()} | {'error', inet:posix() | 
 				closed | badarg | not_owner}
-      when Filename :: file:name(),
+      when Filename :: name(),
 	   Socket :: inet:socket().
 sendfile(Filename, Sock)  ->
     case file:open(Filename, [read, raw, binary]) of
@@ -1345,7 +1345,7 @@ eval_stream(Fd, Handling, Bs) ->
     eval_stream(Fd, Handling, 1, undefined, [], Bs).
 
 eval_stream(Fd, H, Line, Last, E, Bs) ->
-    eval_stream2(io:parse_erl_exprs(Fd, '', Line, [unicode]), Fd, H, Last, E, Bs).
+    eval_stream2(io:parse_erl_exprs(Fd, '', Line), Fd, H, Last, E, Bs).
 
 eval_stream2({ok,Form,EndLine}, Fd, H, Last, E, Bs0) ->
     try erl_eval:exprs(Form, Bs0) of
diff --git a/lib/parsetools/src/leex.erl b/lib/parsetools/src/leex.erl
index 32c513f56c..22b496258f 100644
--- a/lib/parsetools/src/leex.erl
+++ b/lib/parsetools/src/leex.erl
@@ -504,7 +504,7 @@ collect_rule(Ifile, Chars, L0) ->
 collect_action(_Ifile, {error, _}, L, _Cont0) ->
     {error, {L, leex, cannot_parse}, ignored_end_line};
 collect_action(Ifile, Chars, L0, Cont0) ->
-    case erl_scan:tokens(Cont0, Chars, L0, [unicode]) of
+    case erl_scan:tokens(Cont0, Chars, L0) of
         {done,{ok,Toks,_},_} -> {ok,Toks,L0};
         {done,{eof,_},_} -> {eof,L0};
         {done,{error,E,_},_} -> {error,E,L0};
diff --git a/lib/parsetools/src/yecc.erl b/lib/parsetools/src/yecc.erl
index 2f0f70f39b..30e0db421e 100644
--- a/lib/parsetools/src/yecc.erl
+++ b/lib/parsetools/src/yecc.erl
@@ -2561,7 +2561,7 @@ format_assoc(nonassoc) ->
 
 format_symbol(Symbol) ->
     String = concat([Symbol]),
-    case erl_scan:string(String, 1, [unicode]) of
+    case erl_scan:string(String) of
         {ok, [{atom, _, _}], _} ->
             io_lib:fwrite(<<"~w">>, [Symbol]);
         {ok, [{Word, _}], _} when Word =/= ':', Word =/= '->' ->
diff --git a/lib/parsetools/src/yeccscan.erl b/lib/parsetools/src/yeccscan.erl
index 9e0e85143a..fa3ce8c73b 100644
--- a/lib/parsetools/src/yeccscan.erl
+++ b/lib/parsetools/src/yeccscan.erl
@@ -1,7 +1,7 @@
 %%
 %% %CopyrightBegin%
 %% 
-%% Copyright Ericsson AB 1996-2012. All Rights Reserved.
+%% Copyright Ericsson AB 1996-2013. All Rights Reserved.
 %% 
 %% The contents of this file are subject to the Erlang Public License,
 %% Version 1.1, (the "License"); you may not use this file except in
@@ -24,7 +24,7 @@ scan(Inport) ->
     scan(Inport, '', 1).
 
 scan(Inport, Prompt, Line1) ->
-    case catch io:scan_erl_form(Inport, Prompt, Line1, [unicode]) of
+    case catch io:scan_erl_form(Inport, Prompt, Line1) of
 	{eof, Line2} ->
 	    {eof, Line2};
 	{ok, Tokens, Line2} ->
diff --git a/lib/stdlib/doc/src/unicode_usage.xml b/lib/stdlib/doc/src/unicode_usage.xml
index 0a75fbeec0..354ec58df3 100644
--- a/lib/stdlib/doc/src/unicode_usage.xml
+++ b/lib/stdlib/doc/src/unicode_usage.xml
@@ -69,12 +69,11 @@ strings.</p>
 <p>Character data may be combined from several sources, sometimes available in a mix of strings and binaries. Erlang has for long had the concept of <c>iodata</c> or <c>iolists</c>, where binaries and lists can be combined to represent a sequence of bytes. In the same way, the Unicode aware modules often allow for combinations of binaries and lists where the binaries have characters encoded in UTF-8 and the lists contain such binaries or numbers representing Unicode codepoints:</p>
 <code type="none">
 unicode_binary() = binary() with characters encoded in UTF-8 coding standard
-unicode_char() = integer() >= 0 representing valid Unicode codepoint
 
 chardata() = charlist() | unicode_binary()
 
-charlist() = [unicode_char() | unicode_binary() | charlist()]
-  a unicode_binary is allowed as the tail of the list</code>
+charlist() = maybe_improper_list(char() | unicode_binary() | charlist(),
+                                 unicode_binary() | nil())</code>
 <p>The module <c>unicode</c> in STDLIB even supports similar mixes with binaries containing other encodings than UTF-8, but that is a special case to allow for conversions to and from external data:</p>
     <code type="none">
 external_unicode_binary() = binary() with characters coded in
@@ -82,10 +81,10 @@ external_unicode_binary() = binary() with characters coded in
 
 external_chardata() = external_charlist() | external_unicode_binary()
 
-external_charlist() = [unicode_char() |
-                       external_unicode_binary() |
-                       external_charlist()]
-  an external_unicode_binary() is allowed as the tail of the list</code>
+external_charlist() = maybe_improper_list(char() |
+                                            external_unicode_binary() |
+                                            external_charlist(),
+                                          external_unicode_binary() | nil())</code>
 </section>
 <section>
 <title>Basic Language Support for Unicode</title>
diff --git a/lib/stdlib/src/epp.erl b/lib/stdlib/src/epp.erl
index afa39c3fb9..1bb3b95ae2 100644
--- a/lib/stdlib/src/epp.erl
+++ b/lib/stdlib/src/epp.erl
@@ -661,7 +661,7 @@ leave_file(From, St) ->
 %% scan_toks(Tokens, From, EppState)
 
 scan_toks(From, St) ->
-    case io:scan_erl_form(St#epp.file, '', St#epp.location, [unicode]) of
+    case io:scan_erl_form(St#epp.file, '', St#epp.location) of
 	{ok,Toks,Cl} ->
 	    scan_toks(Toks, From, St#epp{location=Cl});
 	{error,E,Cl} ->
@@ -1035,7 +1035,7 @@ new_location(Ln, {Le,_}, {Lf,_}) ->
 %%  nested conditionals and repeated 'else's.
 
 skip_toks(From, St, [I|Sis]) ->
-    case io:scan_erl_form(St#epp.file, '', St#epp.location, [unicode]) of
+    case io:scan_erl_form(St#epp.file, '', St#epp.location) of
 	{ok,[{'-',_Lh},{atom,_Li,ifdef}|_Toks],Cl} ->
 	    skip_toks(From, St#epp{location=Cl}, [ifdef,I|Sis]);
 	{ok,[{'-',_Lh},{atom,_Li,ifndef}|_Toks],Cl} ->
diff --git a/lib/stdlib/src/shell.erl b/lib/stdlib/src/shell.erl
index 0cd408204e..c94f052b24 100644
--- a/lib/stdlib/src/shell.erl
+++ b/lib/stdlib/src/shell.erl
@@ -950,7 +950,7 @@ local_func(rd, [{atom,_,RecName},RecDef0], Bs, _Shell, RT, _Lf, _Ef) ->
     RecDef = expand_value(RecDef0),
     RDs = lists:flatten(erl_pp:expr(RecDef)),
     Attr = lists:concat(["-record('", RecName, "',", RDs, ")."]),
-    {ok, Tokens, _} = erl_scan:string(Attr, 1, [unicode]),
+    {ok, Tokens, _} = erl_scan:string(Attr),
     case erl_parse:parse_form(Tokens) of
         {ok,AttrForm} ->
             [RN] = add_records([AttrForm], Bs, RT),
@@ -1397,7 +1397,6 @@ enc() ->
 garb(Shell) ->
     erlang:garbage_collect(Shell),
     catch erlang:garbage_collect(whereis(user)),
-    catch erlang:garbage_collect(whereis(group)),
     catch erlang:garbage_collect(group_leader()),
     erlang:garbage_collect().
 
diff --git a/lib/syntax_tools/src/epp_dodger.erl b/lib/syntax_tools/src/epp_dodger.erl
index 70395848a1..131be4e8e4 100644
--- a/lib/syntax_tools/src/epp_dodger.erl
+++ b/lib/syntax_tools/src/epp_dodger.erl
@@ -401,7 +401,7 @@ quick_parse_form(Dev, L0, Options) ->
 parse_form(Dev, L0, Parser, Options) ->
     NoFail = proplists:get_bool(no_fail, Options),
     Opt = #opt{clever = proplists:get_bool(clever, Options)},
-    case io:scan_erl_form(Dev, "", L0, [unicode]) of
+    case io:scan_erl_form(Dev, "", L0) of
         {ok, Ts, L1} ->
             case catch {ok, Parser(Ts, Opt)} of
                 {'EXIT', Term} ->