Handle UTF-8 in character literals

Also handle `\x{hhh..}` in strings... Character literals has to be a single character, not composite.

+ tests (and the corresponding fix to the char literal pretty printer)
This commit is contained in:
Hans Svensson
2020-02-24 15:35:54 +01:00
parent 2bad76314f
commit e98edd4eef
4 changed files with 63 additions and 30 deletions
+3 -2
View File
@@ -63,7 +63,8 @@ simple_contracts_test_() ->
%% Parse tests of example contracts
[ {lists:concat(["Parse the ", Contract, " contract."]),
fun() -> roundtrip_contract(Contract) end}
|| Contract <- [counter, voting, all_syntax, '05_greeter', aeproof, multi_sig, simple_storage, fundme, dutch_auction] ]
|| Contract <- [counter, voting, all_syntax, '05_greeter', aeproof,
multi_sig, simple_storage, fundme, dutch_auction, utf8] ]
}.
parse_contract(Name) ->
@@ -85,7 +86,7 @@ parse_expr(Text) ->
round_trip(Text) ->
Contract = parse_string(Text),
Text1 = prettypr:format(aeso_pretty:decls(strip_stdlib(Contract))),
Contract1 = parse_string(Text1),
Contract1 = parse_string(aeso_scan:utf8_encode(Text1)),
NoSrcLoc = remove_line_numbers(Contract),
NoSrcLoc1 = remove_line_numbers(Contract1),
?assertMatch(NoSrcLoc, diff(NoSrcLoc, NoSrcLoc1)).
+21
View File
@@ -0,0 +1,21 @@
contract UTF8 =
entrypoint f1() : char = '1'
entrypoint f2() : char = '+'
entrypoint f3() : char = 'd'
entrypoint f4() : char = 'X'
entrypoint f5() : char = 'å'
entrypoint f6() : char = 'Ä'
entrypoint f7() : char = 'æ'
entrypoint f8() : char = 'ë'
entrypoint f9() : char = 'ẻ'
entrypoint f10() : char = '\x27'
entrypoint f11() : char = '\x{2200}'
entrypoint f12() : char = '💩'
entrypoint f13() : char = '\n'
// entrypoint f13() : char = 'e̊'
// entrypoint f14() : char = '\Ì'
// '💩' vs. map('a,'b)