Merge branch 'rb/stdlib_re_unicode_fixes' into ccase/r13b04_dev

* rb/stdlib_re_unicode_fixes:
  Fix lost unicode option in re:compile()
  Refactor out repeated block in re module
  Fix re:replace/4 to handle unicode charlist Replacement argument
  Fix re:replace/4 to handle unicode charlist RE argument
  Fix re:replace/4 to handle binary unicode output when nothing replaced

OTP-8394  A number of bugs concerning re and unicode are corrected:
          - re:compile no longer loses unicode option, which also fixes bug
            in re:split.
          - re:replace now handles unicode charlist replacement argument
          - re:replace now handles unicode RE charlist argument correctly
          - re:replace now handles binary unicode output correctly when
          nothing is replaced.

          Most code, testcases and error isolation done by Rory Byrne.

1 files changed, 22 insertions, 8 deletions

diff --git a/lib/stdlib/test/re_SUITE.erl b/lib/stdlib/test/re_SUITE.erl
index 98eb66d1fb..fa50ba3b7a 100644
--- a/lib/stdlib/test/re_SUITE.erl
+++ b/lib/stdlib/test/re_SUITE.erl
@@ -1,29 +1,29 @@
 %%
 %% %CopyrightBegin%
-%% 
-%% Copyright Ericsson AB 2008-2009. All Rights Reserved.
-%% 
+%%
+%% Copyright Ericsson AB 2008-2010. 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
 %% compliance with the License. You should have received a copy of the
 %% Erlang Public License along with this software. If not, it can be
 %% retrieved online at http://www.erlang.org/.
-%% 
+%%
 %% Software distributed under the License is distributed on an "AS IS"
 %% basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
 %% the License for the specific language governing rights and limitations
 %% under the License.
-%% 
+%%
 %% %CopyrightEnd%
 %%
 -module(re_SUITE).
 
--export([all/1, pcre/1,compile_options/1,run_options/1,combined_options/1,replace_autogen/1,global_capture/1,replace_return/1,split_autogen/1,split_options/1,split_specials/1,error_handling/1]).
+-export([all/1, pcre/1,compile_options/1,run_options/1,combined_options/1,replace_autogen/1,global_capture/1,replace_input_types/1,replace_return/1,split_autogen/1,split_options/1,split_specials/1,error_handling/1]).
 
 -include("test_server.hrl").
 -include_lib("kernel/include/file.hrl").
 
-all(suite) -> [pcre,compile_options,run_options,combined_options,replace_autogen,global_capture,replace_return,split_autogen,split_options,split_specials,error_handling].
+all(suite) -> [pcre,compile_options,run_options,combined_options,replace_autogen,global_capture,replace_input_types,replace_return,split_autogen,split_options,split_specials,error_handling].
 
 pcre(doc) ->
     ["Run all applicable tests from the PCRE testsuites."];
@@ -268,7 +268,17 @@ global_capture(Config) when is_list(Config) ->
     ?line {match,[[{3,5},{5,3}],[{11,4},{12,3}]]} = re:run("ABC�bcdABCabcdA",".(?<FOO>bcd)",[global,{capture,all,index},unicode]),
     ?t:timetrap_cancel(Dog),
     ok.
-    
+
+replace_input_types(doc) ->
+    ["Tests replace with different input types"];
+replace_input_types(Config) when is_list(Config) ->
+    Dog = ?t:timetrap(?t:minutes(3)),
+    ?line <<"abcd">> = re:replace("abcd","Z","X",[{return,binary},unicode]),
+    ?line <<"abcd">> = re:replace("abcd","\x{400}","X",[{return,binary},unicode]),
+    ?line <<"a",208,128,"cd">> = re:replace(<<"abcd">>,"b","\x{400}",[{return,binary},unicode]),
+    ?t:timetrap_cancel(Dog),
+    ok.
+
 replace_return(doc) ->    
     ["Tests return options of replace together with global searching"];
 replace_return(Config) when is_list(Config) ->
@@ -289,6 +299,10 @@ replace_return(Config) when is_list(Config) ->
     ?line <<"iXk">> = re:replace("abcdefghijk","(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)","\\9X",[{return,binary}]),
     ?line <<"jXk">> = re:replace("abcdefghijk","(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)","\\10X",[{return,binary}]),
     ?line <<"Xk">> = re:replace("abcdefghijk","(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)","\\11X",[{return,binary}]),
+    ?line "a\x{400}bcX" = re:replace("a\x{400}bcd","d","X",[global,{return,list},unicode]),
+    ?line <<"a",208,128,"bcX">> = re:replace("a\x{400}bcd","d","X",[global,{return,binary},unicode]),
+    ?line "a\x{400}bcd" = re:replace("a\x{400}bcd","Z","X",[global,{return,list},unicode]),
+    ?line <<"a",208,128,"bcd">> = re:replace("a\x{400}bcd","Z","X",[global,{return,binary},unicode]),
     ?t:timetrap_cancel(Dog),
     ok.