j3d1/json
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Fix character skipping after a surrogate pair

Browse source 
In a string the first character following a surrogate pair is skipped by the
lexer, but the rest of the string is parsed as usual.
This commit is contained in:
Robert Marki 2015-11-13 12:49:26 +01:00
parent 3948630374
commit ec7a1d8347
3 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/json.hpp
View file

@ -6856,8 +6856,8 @@ basic_json_parser_59:
auto codepoint2 = std::strtoul(std::string(reinterpret_cast<typename string_t::const_pointer>
(i + 7), 4).c_str(), nullptr, 16);
result += to_unicode(codepoint, codepoint2);
// skip the next 11 characters (xxxx\uyyyy)
i += 11;
// skip the next 10 characters (xxxx\uyyyy)
i += 10;
}
else
{

4
src/json.hpp.re2c
View file

@ -6162,8 +6162,8 @@ class basic_json
auto codepoint2 = std::strtoul(std::string(reinterpret_cast<typename string_t::const_pointer>
(i + 7), 4).c_str(), nullptr, 16);
result += to_unicode(codepoint, codepoint2);
// skip the next 11 characters (xxxx\uyyyy)
i += 11;
// skip the next 10 characters (xxxx\uyyyy)
i += 10;
}
else
{

5
test/unit.cpp
View file

@ -10205,4 +10205,9 @@ TEST_CASE("regression tests")
j["string"] = bytes;
CHECK(j["string"] == "\u0007\u0007");
}
SECTION("character following a surrogate pair is skipped")
{
CHECK(json::parse("\"\\ud80c\\udc60abc\"").get<json::string_t>() == u8"\U00013060abc");
}
}