Keep a NUL byte ending a // comment as the end of input

With the default NUL handling (JSON_STRICT_NUL_HANDLING not set), a NUL
byte in the input is treated as the real end of input everywhere -
except when it immediately ends a `//` comment: scan_comment() matched
'\0' as a comment terminator like '\n', so the NUL was consumed as
part of the comment and scan() never saw it as end of input; the next
get() then kept reading past it. Multi-line comments and
JSON_STRICT_NUL_HANDLING=1 were unaffected, since there the NUL is
just part of the comment text.

Fix scan_comment() to leave the NUL unconsumed (unget()) instead of
returning it as part of the comment, so the following scan() reports
it as end of input, exactly as for a NUL anywhere else.

Fixes #5659.

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

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

@@ -50,11 +50,9 @@ 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 *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]`.
+    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]`.
 
 !!! note "ABI compatibility"
 

include/nlohmann/detail/input/lexer.hpp

@@ -975,10 +975,15 @@ class lexer : public lexer_base<BasicJsonType>
                         case '\n':
                         case '\r':
                         case char_traits<char_type>::eof():
+                            return true;
+
 #if !JSON_STRICT_NUL_HANDLING
                         case '\0':
-#endif
+                            // a NUL byte is the end of the input (see scan()),
+                            // so leave it for scan() to see
+                            unget();
                             return true;
+#endif
 
                         default:
                             break;

include/nlohmann/detail/json_ref.hpp

@@ -34,7 +34,6 @@ class json_ref
 
     json_ref(std::initializer_list<json_ref> init)
         : owned_value(init)
-        , braced_list(true)
     {}
 
     template <
@@ -70,17 +69,9 @@ 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

@@ -1672,18 +1672,6 @@ 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

@@ -10067,10 +10067,15 @@ class lexer : public lexer_base<BasicJsonType>
                         case '\n':
                         case '\r':
                         case char_traits<char_type>::eof():
+                            return true;
+
 #if !JSON_STRICT_NUL_HANDLING
                         case '\0':
-#endif
+                            // a NUL byte is the end of the input (see scan()),
+                            // so leave it for scan() to see
+                            unget();
                             return true;
+#endif
 
                         default:
                             break;
@@ -20047,7 +20052,6 @@ class json_ref
 
     json_ref(std::initializer_list<json_ref> init)
         : owned_value(init)
-        , braced_list(true)
     {}
 
     template <
@@ -20083,17 +20087,9 @@ 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
@@ -27762,18 +27758,6 @@ 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-brace-init-copy-semantics.cpp

@@ -72,28 +72,6 @@ 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

tests/src/unit-class_parser.cpp

@@ -592,6 +592,45 @@ TEST_CASE("parser class")
 
                 // parsing from a string literal is unaffected either way
                 CHECK(json::parse("123") == json(123));
+
+                // a NUL byte that ends a // comment ends the input just
+                // like a NUL byte anywhere else (issue #5659); before the
+                // fix, the NUL was consumed as part of the comment, and
+                // scanning continued with whatever followed it
+                {
+                    // same as "//c" alone (real end of input after the
+                    // comment), rather than continuing with "[1]"
+                    std::string s1 = "//c";
+                    s1.push_back('\0');
+                    s1 += "[1]";
+                    json _; // NOLINT(readability-identifier-naming)
+                    CHECK_THROWS_WITH_AS(_ = json::parse(s1, nullptr, true, true),
+                                         "[json.exception.parse_error.101] parse error at line 1, column 4: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal",
+                                         json::parse_error&);
+                    CHECK_FALSE(json::accept(s1, true, true));
+                }
+
+                {
+                    // same as "[1, //c" alone, rather than continuing with " 2]"
+                    std::string s2 = "[1, //c";
+                    s2.push_back('\0');
+                    s2 += " 2]";
+                    json _; // NOLINT(readability-identifier-naming)
+                    CHECK_THROWS_WITH_AS(_ = json::parse(s2, nullptr, true, true),
+                                         "[json.exception.parse_error.101] parse error at line 1, column 8: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal",
+                                         json::parse_error&);
+                    CHECK_FALSE(json::accept(s2, true, true));
+                }
+
+                {
+                    // same as "1 //c" alone: the comment (and the NUL that
+                    // ends it) is ignored, and "x" is never reached
+                    std::string s3 = "1 //c";
+                    s3.push_back('\0');
+                    s3 += "x";
+                    CHECK(json::parse(s3, nullptr, true, true) == json(1));
+                    CHECK(json::accept(s3, true, true));
+                }
             }
 #endif