json_view: no byte range in exceptions about a removed value

#5990 dropped the found flag from diagnostics(), reasoning that a value
value_path() does not find leaves no tokens, like the root. But the node
of a value that is no longer part of the document still holds the bytes
it had in the source, so with JSON_DIAGNOSTICS and
JSON_DIAGNOSTIC_POSITIONS its exceptions gained "(bytes 1-4)" for text
that is no longer there. The test #5997 added for exactly this case
(unit-json_view_positions.cpp, "views of values that are no longer part
of the document") has failed on develop since both were merged.

Restore the flag: a value that is not found gets no context, the root
keeps its byte range.

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

include/nlohmann/detail/view/builder.hpp

@@ -1168,20 +1168,20 @@ indent_done:
             if (negative)
             {
                 ++p;
-                if (NLOHMANN_VIEW_UNLIKELY(cur() < '0' || cur() > '9'))
-                {
-                    return fail(error_code::number_after_minus);
-                }
             }
             const unsigned char* const int_start = p;
             if (cur() == '0')
             {
                 ++p;
             }
+            else if (!negative || NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            {
+                // (without a sign, the dispatch saw a digit)
+                p = skip_digits(p + 1, e);
+            }
             else
             {
-                // (a digit: the dispatch or the check after the sign saw it)
-                p = skip_digits(p + 1, e);
+                return fail(error_code::number_after_minus);
             }
             const auto int_digits = static_cast<std::size_t>(p - int_start);
             std::size_t frac_digits = 0;

include/nlohmann/detail/view/errors.hpp

@@ -230,7 +230,8 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root); with
+/// JSON_DIAGNOSTICS, nothing for a value that is no longer part of the document
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -251,10 +252,12 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
+    // a value that is no longer part of the document has no path, and its
+    // node still holds the bytes it had in the source: no context at all
     const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
     if (!found)
     {
-        // a value that is not found has no path, and with it no bytes
+        // context is still empty; returning it keeps the copy elided (-Wnrvo)
         return context;
     }
     if (!tokens.empty())

single_include/nlohmann/json_view.hpp

@@ -2473,20 +2473,20 @@ indent_done:
             if (negative)
             {
                 ++p;
-                if (NLOHMANN_VIEW_UNLIKELY(cur() < '0' || cur() > '9'))
-                {
-                    return fail(error_code::number_after_minus);
-                }
             }
             const unsigned char* const int_start = p;
             if (cur() == '0')
             {
                 ++p;
             }
+            else if (!negative || NLOHMANN_VIEW_LIKELY(cur() >= '1' && cur() <= '9'))
+            {
+                // (without a sign, the dispatch saw a digit)
+                p = skip_digits(p + 1, e);
+            }
             else
             {
-                // (a digit: the dispatch or the check after the sign saw it)
-                p = skip_digits(p + 1, e);
+                return fail(error_code::number_after_minus);
             }
             const auto int_digits = static_cast<std::size_t>(p - int_start);
             std::size_t frac_digits = 0;
@@ -5059,7 +5059,8 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root); with
+/// JSON_DIAGNOSTICS, nothing for a value that is no longer part of the document
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -5080,10 +5081,12 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
+    // a value that is no longer part of the document has no path, and its
+    // node still holds the bytes it had in the source: no context at all
     const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
     if (!found)
     {
-        // a value that is not found has no path, and with it no bytes
+        // context is still empty; returning it keeps the copy elided (-Wnrvo)
         return context;
     }
     if (!tokens.empty())

tests/src/unit-allocator.cpp

@@ -1038,14 +1038,6 @@ template<class T>
 struct sweep_allocator
 {
     using value_type = T;
-    // GCC 4.8's std::map takes these from the allocator instead of from
-    // std::allocator_traits
-    using pointer = T*;
-    using const_pointer = const T*;
-    using reference = T&;
-    using const_reference = const T&;
-    using size_type = std::size_t;
-    using difference_type = std::ptrdiff_t;
 
     sweep_allocator() = default;
     template<class U> sweep_allocator(const sweep_allocator<U>& /*unused*/) noexcept {}
@@ -1163,14 +1155,9 @@ TEST_CASE("parse() survives a failing allocation at every point (#5985)")
 
     // With iterator debugging (MSVC STL debug builds, also used by clang-cl),
     // containers allocate a debug proxy through the allocator inside their
-    // noexcept default and move constructors, so failing that allocation
-    // terminates the program instead of throwing std::bad_alloc. Nothing to
-    // check there.
+    // noexcept move constructors, so failing that allocation terminates the
+    // program instead of throwing std::bad_alloc. Nothing to check there.
 #if !(defined(_ITERATOR_DEBUG_LEVEL) && _ITERATOR_DEBUG_LEVEL > 0)
-    // Clang 3.4 and 3.5 leak memory when an element constructor throws
-    // inside libstdc++'s containers (a std::map copy, a std::vector
-    // reallocation), without any json value involved.
-#if !(defined(__clang__) && !defined(__apple_build_version__) && __clang_major__ == 3 && __clang_minor__ < 6)
     SECTION("parser callback")
     {
         const auto keep_all = [](int /*depth*/, sweep_json::parse_event_t /*event*/, sweep_json& /*parsed*/) noexcept
@@ -1191,6 +1178,7 @@ TEST_CASE("parse() survives a failing allocation at every point (#5985)")
             return sweep_json::parse(text, drop_d);
         });
     }
+#endif
 
     SECTION("sax_parse into an existing value")
     {
@@ -1204,7 +1192,5 @@ TEST_CASE("parse() survives a failing allocation at every point (#5985)")
             return value;
         });
     }
-#endif
-#endif
 }
 #endif

tests/src/unit-class_lexer.cpp

@@ -2222,10 +2222,9 @@ TEST_CASE("serialization of short strings")
     {
         CAPTURE(s)
         const json j = s;
-        const std::string quoted = "\"" + s + "\""; // NOLINT(performance-inefficient-string-concatenation)
-        CHECK(j.dump() == quoted);
-        CHECK(j.dump(-1, ' ', true) == quoted);
-        CHECK(json({{s, s}}).dump() == "{" + quoted + ":" + quoted + "}"); // NOLINT(performance-inefficient-string-concatenation)
+        CHECK(j.dump() == "\"" + s + "\"");
+        CHECK(j.dump(-1, ' ', true) == "\"" + s + "\"");
+        CHECK(json({{s, s}}).dump() == "{\"" + s + "\":\"" + s + "\"}");
     }
 
     // a character that needs an escape

tests/src/unit-custom-object-key-type.cpp

@@ -160,12 +160,12 @@ class strict_key
     }
 
   private:
-    std::string m_value;
+    std::string m_value{};
 };
 
 strict_key make_strict_key(const std::string& key)
 {
-    return {key.c_str()};
+    return strict_key(key.c_str());
 }
 
 template<class Key, class Value, class Compare, class Allocator>
@@ -224,9 +224,7 @@ TEST_CASE("converting a value with keys that cannot be made from a std::string n
         }
     }
 
-    // direct-initialization: a copy-initialization makes GCC 4.8 instantiate the
-    // copy constructor, which needs a range constructor strict_object lacks
-    const strict_json converted(value);
+    const strict_json converted = value;
 
     // at() needs to make a std::string of a key for its error message
     const auto member = [](const strict_json & object, const char* name) -> const strict_json &

tests/src/unit-json_view.cpp

@@ -105,53 +105,19 @@ template<typename T>
 struct failing_allocator
 {
     using value_type = T;
-    // GCC 4.8's std::map takes these from the allocator instead of from
-    // std::allocator_traits
-    using pointer = T*;
-    using const_pointer = const T*;
-    using reference = T&;
-    using const_reference = const T&;
-    using size_type = std::size_t;
-    using difference_type = std::ptrdiff_t;
-
-    template<typename U>
-    struct rebind
-    {
-        using other = failing_allocator<U>;
-    };
 
     failing_allocator() = default;
 
     template<typename U>
     explicit failing_allocator(const failing_allocator<U>& /*other*/) noexcept {}
 
-    [[noreturn]] T* allocate(std::size_t /*n*/) // NOLINT(readability-convert-member-functions-to-static)
+    T* allocate(std::size_t /*n*/) // NOLINT(readability-convert-member-functions-to-static)
     {
         throw std::bad_alloc();
     }
 
     void deallocate(T* /*p*/, std::size_t /*n*/) noexcept {} // NOLINT(readability-convert-member-functions-to-static)
 
-    // GCC 4.8's std::map calls these on the allocator directly instead of
-    // going through std::allocator_traits
-    std::size_t max_size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return (std::numeric_limits<std::size_t>::max)() / sizeof(T);
-    }
-
-    template<typename U, typename... Args>
-    void construct(U* p, Args&& ... args) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        ::new (static_cast<void*>(p)) U(std::forward<Args>(args)...);
-    }
-
-    template<typename U>
-    void destroy(U* p) noexcept // NOLINT(readability-convert-member-functions-to-static)
-    {
-        static_cast<void>(p); // unused for trivially destructible types
-        p->~U();
-    }
-
     template<typename U>
     bool operator==(const failing_allocator<U>& /*other*/) const noexcept
     {
@@ -304,7 +270,7 @@ TEST_CASE("json_view")
                     "\"", "\"abc", "\"\\x\"", "\"\\u12\"", "\"\\ud800\"", "\"\\udc00\"", "\"\x01\"", "\"\xff\"", "\"\xc3\"", "[1]x", "/", "/*", "[\n  1,\n  x\n]", // NOLINT(modernize-raw-string-literal)
                     "1e400", "-1e400", "[1.7976931348623159e308]", "{\"a\":\n{\"b\": [1, 2,\n 3 x]}}",
                     // (an error after every kind of value: the error is found by replaying the parser)
-                    R"([null, true, -1, 1, 1.5, "s", {"a": 1} 2])", R"({"a": null, "b": -1, "c": 1.5, "d": "s", "e": {}, 1})"
+                    "[null, true, -1, 1, 1.5, \"s\", {\"a\": 1} 2]", "{\"a\": null, \"b\": -1, \"c\": 1.5, \"d\": \"s\", \"e\": {}, 1}"
                 })
         {
             CAPTURE(text)
@@ -1590,7 +1556,7 @@ TEST_CASE("json_view values")
         CHECK_THROWS_WITH_AS(not_an_object.root().get<view_map>(), json_view_test::message("type_error.302", "", 0, 5, "type must be object, but is array").c_str(), json::type_error&);
 #if !defined(JSON_NOEXCEPTION)
         // (and one that cannot allocate its nodes)
-        using failing_map = std::map<std::string, json_view, std::less<std::string>, failing_allocator<std::pair<const std::string, json_view>>>; // NOLINT(modernize-use-transparent-functors)
+        using failing_map = std::map<std::string, json_view, std::less<std::string>, failing_allocator<std::pair<const std::string, json_view>>>;
         const json_document one_member = json_document::parse(R"({"a":1})");
         CHECK_THROWS_AS(one_member.root().get<failing_map>(), std::bad_alloc&);
 #endif

tests/src/unit-locale-cpp.cpp

@@ -505,8 +505,8 @@ struct locale_switching_token
 {
     using value_type = char;
 
-    locale_switching_token(std::string text_, std::string switch_to_)
-        : text(std::move(text_)), switch_to(std::move(switch_to_))
+    locale_switching_token(std::string text_, const char* switch_to_)
+        : text(std::move(text_)), switch_to(switch_to_)
     {}
 
     std::size_t size() const
@@ -523,13 +523,13 @@ struct locale_switching_token
     {
         if (!switched)
         {
-            switched = std::setlocale(LC_NUMERIC, switch_to.c_str()) != nullptr;
+            switched = std::setlocale(LC_NUMERIC, switch_to) != nullptr;
         }
-        return &text[0]; // NOLINT(readability-container-data-pointer): std::string::data() is const before C++17
+        return &text[0];
     }
 
     std::string text;
-    std::string switch_to;
+    const char* switch_to;
     bool switched = false;
 };
 
@@ -647,7 +647,7 @@ TEST_CASE("convert_float_locale_aware")
 
             // "C" -> comma locale: strtod stops at the '.', so the conversion is repeated
             {
-                locale_switching_token token("1.5", comma_locale);
+                locale_switching_token token("1.5", comma_locale.c_str());
                 double value = 0;
                 nlohmann::detail::convert_float_locale_aware(token, 1, value);
                 if (token.switched)
@@ -660,7 +660,7 @@ TEST_CASE("convert_float_locale_aware")
             // the same for the other floating-point types
             REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
             {
-                locale_switching_token token("2.25", comma_locale);
+                locale_switching_token token("2.25", comma_locale.c_str());
                 float value = 0;
                 nlohmann::detail::convert_float_locale_aware(token, 1, value);
                 if (token.switched)
@@ -670,7 +670,7 @@ TEST_CASE("convert_float_locale_aware")
             }
             REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
             {
-                locale_switching_token token("2.25", comma_locale);
+                locale_switching_token token("2.25", comma_locale.c_str());
                 long double value = 0;
                 nlohmann::detail::convert_float_locale_aware(token, 1, value);
                 if (token.switched)

tests/src/unit-msgpack-cpp17.cpp

@@ -122,8 +122,7 @@ TEST_CASE("JSON text with std::byte")
     SECTION("invalid text")
     {
         CHECK_FALSE(json::accept(to_bytes("[1,\n2,")));
-        json _;
-        CHECK_THROWS_WITH_AS(_ = json::parse(to_bytes("[1,\n2,")),
+        CHECK_THROWS_WITH_AS(json::parse(to_bytes("[1,\n2,")),
                              "[json.exception.parse_error.101] parse error at line 2, column 3: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal", json::parse_error&);
     }
 }

tests/src/unit-ordered_json.cpp

@@ -541,7 +541,6 @@ TEST_CASE("object_key_index")
         };
 
         std::vector<std::size_t> hashes;
-        hashes.reserve(initial);
         for (std::size_t i = 0; i < initial; ++i)
         {
             hashes.push_back(hash_of(i));

tests/src/unit-regression1.cpp

@@ -1533,7 +1533,7 @@ TEST_CASE("regression tests 1")
         {
             my_json::object_t top = orig.get_ref<const my_json::object_t&>();
             top.at("x") = my_json::parse(R"({"a":{"b":1},"n":null,"arr":[10,20],"objs":[{"m":5},{"m":6}]})");
-            return my_json(std::move(top)); // NOLINT(modernize-return-braced-init-list): {top} would be an array
+            return my_json(std::move(top));
         };
 
         SECTION("existing members")

tests/src/unit-stream-bulk-scan.cpp

@@ -120,7 +120,6 @@ class oversized_get_area_streambuf : public std::streambuf
   private:
     std::array<char, 8> m_data{{'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'}};
 };
-
 #endif
 
 // how a test reads from the stream
@@ -464,18 +463,15 @@ TEST_CASE("parsing from a std::istream scans the get area in bulk")
         CHECK(token.empty());
     }
 
-#if SIZE_MAX > UINT32_MAX
-    // a get area larger than an int needs a 64-bit std::size_t (checked by the
-    // preprocessor, as a constant condition triggers MSVC's C4127)
     SECTION("skipping more characters than gbump() takes at once")
     {
         // gbump() takes an int, but a get area can be larger
-        const std::size_t claimed = std::size_t{3} << 30u;
+        const std::size_t claimed = sizeof(std::size_t) < 8 ? 0 : std::size_t{3} << 30u;
         oversized_get_area_streambuf buf(claimed);
-        if (static_cast<std::size_t>(buf.in_avail()) != claimed)
+        if (claimed == 0 || static_cast<std::size_t>(buf.in_avail()) != claimed)
         {
-            // a standard library whose streambuf stores the size of the get
-            // area in an int (MSVC)
+            // a 32-bit size_t, or a standard library whose streambuf stores
+            // the size of the get area in an int (MSVC)
             MESSAGE("a get area larger than an int is not supported");
         }
         else
@@ -495,7 +491,6 @@ TEST_CASE("parsing from a std::istream scans the get area in bulk")
             buf.restore_get_area();
         }
     }
-#endif
 #endif
 
     SECTION("SAX parsing from a stream")