From 98cb178fe80be7ee560c16e02dc31bf3df7700c8 Mon Sep 17 00:00:00 2001 From: Rory Byrne Date: Sat, 16 Jan 2010 11:18:39 +0000 Subject: Fix re:replace/4 to handle binary unicode output when nothing replaced A bug with re:replace/4 causes an exception when: (a) it's given a unicode charlist as input; (b) it's set to {return,binary}; and (c) it finds nothing to replace. The problem is: when re:replace/4 does not find anything to replace in its Subject input, it calls iolist_to_binary on this data. This fails if the original input is a charlist with non-ascii codepoints. --- lib/stdlib/src/re.erl | 7 ++++++- lib/stdlib/test/re_SUITE.erl | 4 ++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/lib/stdlib/src/re.erl b/lib/stdlib/src/re.erl index 5417ac02e5..f934fdcba1 100644 --- a/lib/stdlib/src/re.erl +++ b/lib/stdlib/src/re.erl @@ -237,7 +237,12 @@ replace(Subject,RE,Replacement,Options) -> iodata -> IoList; binary -> - iolist_to_binary(IoList); + case Unicode of + false -> + iolist_to_binary(IoList); + true -> + unicode:characters_to_binary(IoList,unicode) + end; list -> case Unicode of false -> diff --git a/lib/stdlib/test/re_SUITE.erl b/lib/stdlib/test/re_SUITE.erl index 98eb66d1fb..a9c9afea94 100644 --- a/lib/stdlib/test/re_SUITE.erl +++ b/lib/stdlib/test/re_SUITE.erl @@ -289,6 +289,10 @@ 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. -- cgit v1.2.3