Copy a pair-shaped array value under JSON_BRACE_INIT_COPY_SEMANTICS

With JSON_BRACE_INIT_COPY_SEMANTICS enabled, single-element brace
initialization from a JSON value decided whether to copy the value or
build an object by inspecting the value's runtime shape: a two-element
array whose first element is a string, such as ["key", 42], was turned
into an object instead of being copied. This made the behavior depend
on the element's content, and it did not distinguish an existing value
of this shape from a nested braced pair written in the source, such as
the inner {"key", "value"} of {{"key", "value"}}.

json_ref now records whether it was constructed from a braced list
(true only for the std::initializer_list<json_ref> constructor used
for nested braced lists) or from a value. The initializer-list
constructor uses this to copy or move a single non-braced-list element
before deciding whether the list describes an object, so a JSON value
is always copied regardless of its shape, while a braced pair written
in the source still creates an object.

Fixes #5662.

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

docs/mkdocs/docs/api/macros/json_brace_init_copy_semantics.md

@@ -50,9 +50,11 @@ The default value is `0` (disabled — existing behavior is preserved).
     ```
 
     Code that relies on these producing arrays must use `json::array()` instead (see below). Lists with more than one
-    element, and a single `[string, value]` pair such as `{{"key", "value"}}`, which still creates an object, are not
-    affected. The library's own conversions are not affected either: for example, `std::tuple<int>{5}` still becomes
-    `[5]`.
+    element, and a single `[string, value]` pair *written as a braced list*, such as `{{"key", "value"}}`, which still
+    creates an object, are not affected. This exception is based on how the pair is written, not on the shape of its
+    value: an existing JSON value that happens to be a two-element array with a string as its first element, such as
+    `json arr = {"key", 42};`, is still copied by `json j{arr};` rather than turned into an object. The library's own
+    conversions are not affected either: for example, `std::tuple<int>{5}` still becomes `[5]`.
 
 !!! note "ABI compatibility"
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -3821,11 +3821,6 @@ 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))
             {
@@ -3924,12 +3919,6 @@ 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);

include/nlohmann/detail/json_ref.hpp

@@ -34,6 +34,7 @@ class json_ref
 
     json_ref(std::initializer_list<json_ref> init)
         : owned_value(init)
+        , braced_list(true)
     {}
 
     template <
@@ -69,9 +70,17 @@ class json_ref
         return &** this;
     }
 
+    /// whether the value was written as a braced list, such as {"key", 1},
+    /// rather than given as a value
+    bool is_braced_list() const noexcept
+    {
+        return braced_list;
+    }
+
   private:
     mutable value_type owned_value = nullptr;
     value_type const* value_ref = nullptr;
+    bool braced_list = false;
 };
 
 }  // namespace detail

include/nlohmann/json.hpp

@@ -1672,6 +1672,18 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                bool type_deduction = true,
                value_t manual_type = value_t::array)
     {
+#if JSON_BRACE_INIT_COPY_SEMANTICS
+        // a single element that is a value rather than a braced list is
+        // copied or moved as is, whatever its content looks like
+        if (type_deduction && init.size() == 1 && !init.begin()->is_braced_list())
+        {
+            *this = init.begin()->moved_or_copied();
+            set_parents();
+            assert_invariant();
+            return;
+        }
+#endif
+
         // check if each element is an array with two elements whose first
         // element is a string
         bool is_an_object = std::all_of(init.begin(), init.end(),

single_include/nlohmann/json.hpp

@@ -16588,11 +16588,6 @@ 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))
             {
@@ -16691,12 +16686,6 @@ 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);
@@ -20058,6 +20047,7 @@ class json_ref
 
     json_ref(std::initializer_list<json_ref> init)
         : owned_value(init)
+        , braced_list(true)
     {}
 
     template <
@@ -20093,9 +20083,17 @@ class json_ref
         return &** this;
     }
 
+    /// whether the value was written as a braced list, such as {"key", 1},
+    /// rather than given as a value
+    bool is_braced_list() const noexcept
+    {
+        return braced_list;
+    }
+
   private:
     mutable value_type owned_value = nullptr;
     value_type const* value_ref = nullptr;
+    bool braced_list = false;
 };
 
 }  // namespace detail
@@ -27764,6 +27762,18 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                bool type_deduction = true,
                value_t manual_type = value_t::array)
     {
+#if JSON_BRACE_INIT_COPY_SEMANTICS
+        // a single element that is a value rather than a braced list is
+        // copied or moved as is, whatever its content looks like
+        if (type_deduction && init.size() == 1 && !init.begin()->is_braced_list())
+        {
+            *this = init.begin()->moved_or_copied();
+            set_parents();
+            assert_invariant();
+            return;
+        }
+#endif
+
         // check if each element is an array with two elements whose first
         // element is a string
         bool is_an_object = std::all_of(init.begin(), init.end(),

tests/src/unit-bon8.cpp

@@ -531,47 +531,6 @@ 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-brace-init-copy-semantics.cpp

@@ -72,6 +72,28 @@ TEST_CASE("JSON_BRACE_INIT_COPY_SEMANTICS")
         CHECK(j7 == json::array({1, 2}));
     }
 
+    SECTION("single-element brace initialization copies a pair-shaped array value (#5662)")
+    {
+        // a JSON value that happens to be a 2-element array whose first
+        // element is a string must still be copied, not turned into an
+        // object; only a braced list written in the source, such as the
+        // inner {"key", "value"} of {{"key", "value"}}, describes an object
+        json const pair_shaped = json::array({"key", 42});
+
+        json const j1{pair_shaped};
+        CHECK(j1.is_array());
+        CHECK(j1 == pair_shaped);
+
+        json const j2 = {pair_shaped};
+        CHECK(j2.is_array());
+        CHECK(j2 == pair_shaped);
+
+        // the same holds for an rvalue of the same shape
+        json const j3{json::array({"key", 42})};
+        CHECK(j3.is_array());
+        CHECK(j3 == pair_shaped);
+    }
+
     SECTION("what the macro does not change")
     {
         // lists with more than one element are unaffected