Skip to content

fix: process unicode escape sequences #317

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
keynslug wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: process unicode escape sequences #317

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e30badc
fix: process unicode escape sequences
keynslug Jul 31, 2026
77a8700
test: verify triple-quoted strings do no unescaping
keynslug Jul 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 47 additions & 0 deletions src/hocon_scanner.xrl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,8 +232,55 @@ unesc([$\\, $t | T]) -> {$\t, T};
unesc([$\\, $r | T]) -> {$\r, T};
unesc([$\\, $b | T]) -> {$\b, T};
unesc([$\\, $f | T]) -> {$\f, T};
unesc([$\\, $u | T]) -> unescapeu(T);

@zmstone zmstone Jul 31, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this only unescapes double quote strings.
for """ strings, maybe add a test case to cover that it's intentionally not unescaped

unesc([H | T]) -> {H, T}.

-define(unescapeu_invalid(ESC), ?unescapeu_invalid(invalid_uescape, ESC)).
-define(unescapeu_invalid(R, ESC),
throw({scan_error, #{reason => R, escape => ESC}})
).

unescapeu([E1, E2, E3, E4 | T]) ->
try hex_to_int(E1, E2, E3, E4) of
CP when CP >= 16#D800, CP =< 16#DBFF ->
unescape_surrogate(T, CP);
CP ->
try <<CP/utf8>> of
_ -> {CP, T}
catch
_:_ -> ?unescapeu_invalid([$u, E1, E2, E3, E4])
end
catch
_:_ ->
?unescapeu_invalid([$u, E1, E2, E3, E4])
end;
unescapeu(Esc) ->
?unescapeu_invalid([$u | Esc]).

unescape_surrogate([$\\, $u, E1, E2, E3, E4 | T], Hi) ->
try hex_to_int(E1, E2, E3, E4) of
Lo when Lo >= 16#DC00, Lo =< 16#DFFF ->
CP = 16#10000 + ((Hi band 16#3FF) bsl 10) + (Lo band 16#3FF),
try <<CP/utf8>> of
_ -> {CP, T}
catch
_:_ -> ?unescapeu_invalid(invalid_uescape_surrogate, [$u, E1, E2, E3, E4])
end;
_ ->
?unescapeu_invalid(invalid_uescape_surrogate, [$u, E1, E2, E3, E4])
catch
_:_ -> ?unescapeu_invalid([$u, E1, E2, E3, E4])
end;
unescape_surrogate(Esc, _Hi) ->
?unescapeu_invalid([$u | Esc]).

hex_to_int(H1, H2, H3, H4) ->
hex_digit(H4) + 16 * (hex_digit(H3) + 16 * (hex_digit(H2) + 16 * hex_digit(H1))).

hex_digit(C) when C >= $a, C =< $f -> C - $a + 10;
hex_digit(C) when C >= $A, C =< $F -> C - $A + 10;
hex_digit(C) when C >= $0, C =< $9 -> C - $0.

maybe_var_ref_name("${?" ++ Name_CR) ->
[$} | NameRev] = lists:reverse(Name_CR),
unicode:characters_to_binary(string:trim(lists:reverse(NameRev)), utf8).
Expand Down
73 changes: 73 additions & 0 deletions test/hocon_tests.erl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,79 @@ escape_test_() ->
)
].

unicode_escape_test_() ->
[
{"ASCII code point",
?_assertEqual(
#{<<"k">> => <<"A">>},
binary(<<"k = \"\\u0041\"">>)
)},
{"mixed-case hexadecimal BMP code points",
?_assertEqual(
#{<<"k">> => <<"å你"/utf8>>},
binary(<<"k = \"\\u00e5\\u4F60\"">>)
)},
{"unicode escape in a quoted key",
?_assertEqual(
#{<<"key">> => 1},
binary(<<"\"\\u006bey\" = 1">>)
)},
{"surrogate pair",
?_assertEqual(
#{<<"k">> => <<"😀"/utf8>>},
binary(<<"k = \"\\uD83D\\uDE00\"">>)
)},
{"lowest surrogate pair",
?_assertEqual(
#{<<"k">> => <<16#10000/utf8>>},
binary(<<"k = \"\\uD800\\uDC00\"">>)
)},
{"highest surrogate pair",
?_assertEqual(
#{<<"k">> => <<16#10FFFF/utf8>>},
binary(<<"k = \"\\uDBFF\\uDFFF\"">>)
)},
{"lone low surrogate",
?_assertMatch(
{error, {scan_error, #{reason := invalid_uescape}}},
hocon:binary(<<"k = \"\\uDC00\"">>)
)},
{"lone high surrogate",
?_assertMatch(
{error, {scan_error, #{reason := invalid_uescape}}},
hocon:binary(<<"k = \"\\uD800\"">>)
)},
{"high surrogate followed by a BMP code point",
?_assertMatch(
{error, {scan_error, #{reason := invalid_uescape_surrogate}}},
hocon:binary(<<"k = \"\\uD800\\u0041\"">>)
)},
{"malformed unicode escape",
?_assertMatch(
{error, {scan_error, _}},
hocon:binary(<<"k = \"\\u123x\"">>)
)},
{"short unicode escape",
?_assertMatch(
{error, {scan_error, _}},
hocon:binary(<<"k = \"\\u123\"">>)
)},
{"triple-quoted strings preserve quoting verbatim",
?_assertEqual(
#{<<"k">> => <<"\\u00e5\\u4F60\\t">>},
binary(<<"k = \"\"\"\\u00e5\\u4F60\\t\"\"\"">>)
)},
{"triple-quoted indented strings preserve quoting verbatim",
?_assertEqual(
#{<<"k">> => <<"\\u00e5\\u4F60\\t\n">>},
binary(<<
"k = \"\"\"~\n"
" \\u00e5\\u4F60\\t\n"
"~\"\"\""
>>)
)}
].

triple_quote_string_test_() ->
Parse = fun(Str) -> maps:get(<<"a">>, binary(<<"a = \"\"\"", Str/binary, "\"\"\"">>)) end,
[
Expand Down
Loading