aboutsummaryrefslogtreecommitdiffstats
path: root/lib/compiler
diff options
context:
space:
mode:
authorBjörn Gustavsson <[email protected]>2011-08-30 11:51:11 +0200
committerBjörn Gustavsson <[email protected]>2011-10-13 14:16:00 +0200
commit34db76765561487e526fe66d3d19ecf3b3fb9dc8 (patch)
tree9141e3c5729e46d03c8b27b14da3b29b1e54abca /lib/compiler
parent6ca6dd3c670fb8185ebb9a20c2a731a7375c1cac (diff)
downloadotp-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 'lib/compiler')
-rw-r--r--lib/compiler/test/bs_utf_SUITE.erl21
1 files changed, 0 insertions, 21 deletions
diff --git a/lib/compiler/test/bs_utf_SUITE.erl b/lib/compiler/test/bs_utf_SUITE.erl
index f30a4d3fef..94549ad0d3 100644
--- a/lib/compiler/test/bs_utf_SUITE.erl
+++ b/lib/compiler/test/bs_utf_SUITE.erl
@@ -264,18 +264,10 @@ literals(Config) when is_list(Config) ->
?line {'EXIT',{badarg,_}} = (catch <<(-1)/utf32,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<(-1)/little-utf32,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf8,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf8,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/utf8,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf16,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<16#D800/little-utf16,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf16,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/little-utf16,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/utf16,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/little-utf16,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf32,I/utf8>>),
?line {'EXIT',{badarg,_}} = (catch <<16#D800/little-utf32,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf32,I/utf8>>),
- ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/little-utf32,I/utf8>>),
B = 16#10FFFF+1,
?line {'EXIT',{badarg,_}} = (catch <<B/utf8>>),
@@ -286,20 +278,11 @@ literals(Config) when is_list(Config) ->
%% Matching of bad literals.
?line error = bad_literal_match(<<237,160,128>>), %16#D800 in UTF-8
- ?line error = bad_literal_match(<<239,191,190>>), %16#FFFE in UTF-8
- ?line error = bad_literal_match(<<239,191,191>>), %16#FFFF in UTF-8
?line error = bad_literal_match(<<244,144,128,128>>), %16#110000 in UTF-8
- ?line error = bad_literal_match(<<255,254>>), %16#FFFE in UTF-16
- ?line error = bad_literal_match(<<255,255>>), %16#FFFF in UTF-16
-
?line error = bad_literal_match(<<16#D800:32>>),
- ?line error = bad_literal_match(<<16#FFFE:32>>),
- ?line error = bad_literal_match(<<16#FFFF:32>>),
?line error = bad_literal_match(<<16#110000:32>>),
?line error = bad_literal_match(<<16#D800:32/little>>),
- ?line error = bad_literal_match(<<16#FFFE:32/little>>),
- ?line error = bad_literal_match(<<16#FFFF:32/little>>),
?line error = bad_literal_match(<<16#110000:32/little>>),
ok.
@@ -314,11 +297,7 @@ match_literal(<<"bj\366rn"/big-utf16>>) -> bjorn_utf16be;
match_literal(<<"bj\366rn"/little-utf16>>) -> bjorn_utf16le.
bad_literal_match(<<16#D800/utf8>>) -> ok;
-bad_literal_match(<<16#FFFE/utf8>>) -> ok;
-bad_literal_match(<<16#FFFF/utf8>>) -> ok;
bad_literal_match(<<16#110000/utf8>>) -> ok;
-bad_literal_match(<<16#FFFE/utf16>>) -> ok;
-bad_literal_match(<<16#FFFF/utf16>>) -> ok;
bad_literal_match(<<16#D800/utf32>>) -> ok;
bad_literal_match(<<16#110000/utf32>>) -> ok;
bad_literal_match(<<16#D800/little-utf32>>) -> ok;