diff options
| author | Björn Gustavsson <[email protected]> | 2011-08-30 11:51:11 +0200 |
|---|---|---|
| committer | Björn Gustavsson <[email protected]> | 2011-10-13 14:16:00 +0200 |
| commit | 34db76765561487e526fe66d3d19ecf3b3fb9dc8 (patch) | |
| tree | 9141e3c5729e46d03c8b27b14da3b29b1e54abca /erts/emulator/test | |
| parent | 6ca6dd3c670fb8185ebb9a20c2a731a7375c1cac (diff) | |
| download | otp-34db76765561487e526fe66d3d19ecf3b3fb9dc8.tar.gz otp-34db76765561487e526fe66d3d19ecf3b3fb9dc8.tar.bz2 otp-34db76765561487e526fe66d3d19ecf3b3fb9dc8.zip | |
Allow noncharacter code points in unicode encoding and decoding
The two noncharacter code points 16#FFFE and 16#FFFF were not
allowed to be encoded or decoded using the unicode module or
bit syntax. That causes an inconsistency, since the noncharacters
16#FDD0 to 16#FDEF could be encoded/decoded.
There is two ways to fix that inconsistency.
We have chosen to allow 16#FFFE and 16#FFFF to be encoded and
decoded, because the noncharacters could be useful internally
within an application and it will make encoding and decoding
slightly faster.
Reported-by: Alisdair Sullivan
Diffstat (limited to 'erts/emulator/test')
| -rw-r--r-- | erts/emulator/test/bs_utf_SUITE.erl | 12 |
1 files changed, 3 insertions, 9 deletions
diff --git a/erts/emulator/test/bs_utf_SUITE.erl b/erts/emulator/test/bs_utf_SUITE.erl index 72c656c400..4ab7d674a6 100644 --- a/erts/emulator/test/bs_utf_SUITE.erl +++ b/erts/emulator/test/bs_utf_SUITE.erl @@ -64,8 +64,7 @@ end_per_group(_GroupName, Config) -> utf8_roundtrip(Config) when is_list(Config) -> ?line utf8_roundtrip(0, 16#D7FF), - ?line utf8_roundtrip(16#E000, 16#FFFD), - ?line utf8_roundtrip(16#10000, 16#10FFFF), + ?line utf8_roundtrip(16#E000, 16#10FFFF), ok. utf8_roundtrip(First, Last) when First =< Last -> @@ -91,8 +90,7 @@ utf16_roundtrip(Config) when is_list(Config) -> do_utf16_roundtrip(Fun) -> do_utf16_roundtrip(0, 16#D7FF, Fun), - do_utf16_roundtrip(16#E000, 16#FFFD, Fun), - do_utf16_roundtrip(16#10000, 16#10FFFF, Fun). + do_utf16_roundtrip(16#E000, 16#10FFFF, Fun). do_utf16_roundtrip(First, Last, Fun) when First =< Last -> Fun(First), @@ -129,8 +127,7 @@ utf32_roundtrip(Config) when is_list(Config) -> do_utf32_roundtrip(Fun) -> do_utf32_roundtrip(0, 16#D7FF, Fun), - do_utf32_roundtrip(16#E000, 16#FFFD, Fun), - do_utf32_roundtrip(16#10000, 16#10FFFF, Fun). + do_utf32_roundtrip(16#E000, 16#10FFFF, Fun). do_utf32_roundtrip(First, Last, Fun) when First =< Last -> Fun(First), @@ -158,7 +155,6 @@ utf32_little_roundtrip(Char) -> utf8_illegal_sequences(Config) when is_list(Config) -> ?line fail_range(16#10FFFF+1, 16#10FFFF+512), %Too large. ?line fail_range(16#D800, 16#DFFF), %Reserved for UTF-16. - ?line fail_range(16#FFFE, 16#FFFF), %Non-characters. %% Illegal first character. ?line [fail(<<I,16#8F,16#8F,16#8F>>) || I <- lists:seq(16#80, 16#BF)], @@ -251,7 +247,6 @@ fail_1(_) -> ok. utf16_illegal_sequences(Config) when is_list(Config) -> ?line utf16_fail_range(16#10FFFF+1, 16#10FFFF+512), %Too large. ?line utf16_fail_range(16#D800, 16#DFFF), %Reserved for UTF-16. - ?line utf16_fail_range(16#FFFE, 16#FFFF), %Non-characters. ?line lonely_hi_surrogate(16#D800, 16#DFFF), ?line leading_lo_surrogate(16#DC00, 16#DFFF), @@ -300,7 +295,6 @@ leading_lo_surrogate(_, _, _) -> ok. utf32_illegal_sequences(Config) when is_list(Config) -> ?line utf32_fail_range(16#10FFFF+1, 16#10FFFF+512), %Too large. ?line utf32_fail_range(16#D800, 16#DFFF), %Reserved for UTF-16. - ?line utf32_fail_range(16#FFFE, 16#FFFF), %Non-characters. ?line utf32_fail_range(-100, -1), ok. |