Report BON8 input that ends after a UTF-8 lead byte as truncated

A lead byte (0xC2..0xF7) inside a string begins either another character
(if a continuation byte follows) or an integer (otherwise). When the input
ended right after the lead byte, the reader took the missing byte as "not
a continuation byte", ended the string before the lead byte, and treated
the lead byte as the start of the next value. With strict=false, a message
cut off there was therefore read as a shorter value: the 11 bytes of
"😀😀é" cut after 9 bytes gave "😀😀", and ["aé"] cut after 3 of its 5
bytes gave ["a"]. With strict=true, the input was rejected with a
misleading message ("expected end of input"), or, for a key, with
parse_error.112 instead of 110.

Either reading of the lead byte leaves the message incomplete: a string at
the end of a message must be terminated by 0xFF, so the lead byte cannot
belong to a following message. Report parse_error.110 (unexpected end of
input) for strings and keys, as the comment on get_bon8_string() already
requires and as the reference decoder (HikoGUI) does.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/conversions/from_json.hpp

@@ -167,13 +167,9 @@ template<typename BasicJsonType, typename EnumType,
          enable_if_t<std::is_enum<EnumType>::value, int> = 0>
 inline void from_json(const BasicJsonType& j, EnumType& e)
 {
-    using underlying_type = typename std::underlying_type<EnumType>::type;
-    // get_arithmetic_value() does not accept boolean_t; read the number that to_json() wrote instead
-    using value_type = typename std::conditional<std::is_same<underlying_type, typename BasicJsonType::boolean_t>::value,
-          typename BasicJsonType::number_unsigned_t, underlying_type>::type;
-    value_type val;
+    typename std::underlying_type<EnumType>::type val;
     get_arithmetic_value(j, val);
-    e = static_cast<EnumType>(static_cast<underlying_type>(val));
+    e = static_cast<EnumType>(val);
 }
 #endif  // JSON_DISABLE_ENUM_SERIALIZATION
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -3821,6 +3821,11 @@ class binary_reader
         if (0xC2 <= byte && byte <= 0xF7)
         {
             const auto second = get_bon8();
+            if (second == char_traits<char_type>::eof())
+            {
+                // the input ends inside a character or an integer
+                return unexpect_eof(input_format_t::bon8, "key");
+            }
             unget_bon8(second);
             if (is_bon8_continuation(second))
             {
@@ -3919,6 +3924,12 @@ class binary_reader
             // a lead byte ends the string if no continuation byte follows: it
             // is then the first byte of an integer
             const auto second = get_bon8();
+            if (second == char_traits<char_type>::eof())
+            {
+                // the input ends inside a character or an integer: either
+                // way, the message is incomplete
+                return unexpect_eof(input_format_t::bon8, "string");
+            }
             if (!is_bon8_continuation(second))
             {
                 unget_bon8(second);

single_include/nlohmann/json.hpp

@@ -5664,13 +5664,9 @@ template<typename BasicJsonType, typename EnumType,
          enable_if_t<std::is_enum<EnumType>::value, int> = 0>
 inline void from_json(const BasicJsonType& j, EnumType& e)
 {
-    using underlying_type = typename std::underlying_type<EnumType>::type;
-    // get_arithmetic_value() does not accept boolean_t; read the number that to_json() wrote instead
-    using value_type = typename std::conditional<std::is_same<underlying_type, typename BasicJsonType::boolean_t>::value,
-          typename BasicJsonType::number_unsigned_t, underlying_type>::type;
-    value_type val;
+    typename std::underlying_type<EnumType>::type val;
     get_arithmetic_value(j, val);
-    e = static_cast<EnumType>(static_cast<underlying_type>(val));
+    e = static_cast<EnumType>(val);
 }
 #endif  // JSON_DISABLE_ENUM_SERIALIZATION
 
@@ -16592,6 +16588,11 @@ class binary_reader
         if (0xC2 <= byte && byte <= 0xF7)
         {
             const auto second = get_bon8();
+            if (second == char_traits<char_type>::eof())
+            {
+                // the input ends inside a character or an integer
+                return unexpect_eof(input_format_t::bon8, "key");
+            }
             unget_bon8(second);
             if (is_bon8_continuation(second))
             {
@@ -16690,6 +16691,12 @@ class binary_reader
             // a lead byte ends the string if no continuation byte follows: it
             // is then the first byte of an integer
             const auto second = get_bon8();
+            if (second == char_traits<char_type>::eof())
+            {
+                // the input ends inside a character or an integer: either
+                // way, the message is incomplete
+                return unexpect_eof(input_format_t::bon8, "string");
+            }
             if (!is_bon8_continuation(second))
             {
                 unget_bon8(second);

tests/src/unit-bon8.cpp

@@ -531,6 +531,47 @@ TEST_CASE("BON8")
             CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x87, 'a'}), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
         }
 
+        SECTION("input that ends after a UTF-8 lead byte")
+        {
+            // the lead byte begins either a character or an integer; both are
+            // incomplete, so the lead byte must not end the string before it
+            for (const bool strict :
+                    {
+                        true, false
+                    })
+            {
+                CAPTURE(strict)
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{'a', 0xC3}, strict), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x81, 'a', 0xC3}, strict), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x81, 'a', 0xE2}, strict), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x81, 'a', 0xF0}, strict), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x81, 0xC3, 0xA9, 0xC3}, strict), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x87, 'a', 0xC3}, strict), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing BON8 string: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x87, 0xC3}, strict), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing BON8 key: unexpected end of input", json::parse_error&);
+                CHECK_THROWS_WITH_AS(_ = json::from_bon8(bytes{0x88, 'a', 0x91, 0xE2}, strict), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing BON8 key: unexpected end of input", json::parse_error&);
+            }
+        }
+
+        SECTION("a message that is cut off is not read as a shorter value")
+        {
+            const json values = {"\xC3\xA9", "a\xE2\x82\xAC", "\xF0\x9F\x98\x80\xC3\xA9", {"a\xC3\xA9"}, {{"\xC3\xA9", "\xE2\x82\xAC"}}, {{"a", {"b\xC3\xA9", 1}}}};
+            for (const auto& j : values)
+            {
+                const bytes message = json::to_bon8(j);
+                for (std::size_t length = 0; length < message.size(); ++length)
+                {
+                    CAPTURE(j)
+                    CAPTURE(length)
+                    bytes prefix = message;
+                    prefix.resize(length);
+                    CHECK(json::from_bon8(prefix, false, false).is_discarded());
+                    // a stream is read byte by byte rather than in bulk
+                    std::istringstream stream(str(prefix));
+                    CHECK(json::from_bon8(stream, false, false).is_discarded());
+                }
+            }
+        }
+
         SECTION("invalid UTF-8")
         {
             // overlong

tests/src/unit-conversions.cpp

@@ -1358,14 +1358,6 @@ TEST_CASE("value conversion")
         CHECK(json(value_1).get<c_enum>() == value_1);
         CHECK(json(cpp_enum::value_1).get<cpp_enum>() == cpp_enum::value_1);
     }
-
-    SECTION("get an enum with underlying type bool (#5671)")
-    {
-        enum class bool_enum : bool { off, on };
-
-        CHECK(json(bool_enum::off).get<bool_enum>() == bool_enum::off);
-        CHECK(json(bool_enum::on).get<bool_enum>() == bool_enum::on);
-    }
 #endif
 
     SECTION("more involved conversions")