Copy the tokens of json_pointer::to_string() with std::copy

clang-tidy (bugprone-not-null-terminated-result) took the memcpy into
the result string for a C string missing its terminator. std::copy is
the same memmove; to_string() instructions are unchanged (Apple clang).

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -86,7 +86,7 @@ JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 2
 /*!
 @brief deserialization of BJData, BON8, BSON, CBOR, MessagePack, and UBJSON values
 */
-template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_binary_parser<BasicJsonType, InputAdapterType>>
+template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_parser<BasicJsonType, InputAdapterType>>
 class binary_reader
 {
     using number_integer_t = typename BasicJsonType::number_integer_t;

include/nlohmann/detail/input/lexer.hpp

@@ -14,7 +14,6 @@
 #include <cstdio> // snprintf
 #include <cstring> // memcmp
 #include <initializer_list> // initializer_list
-#include <limits> // numeric_limits
 #include <string> // char_traits, string
 #include <utility> // move
 #include <vector> // vector
@@ -1817,15 +1816,6 @@ scan_number_done:
     /// significand (see scan_number_bulk_contiguous())
     bool convert_accumulated_float(const float_significand& s, std::true_type /*native*/) noexcept
     {
-        // accept() only needs to know that the value is finite (see the parser):
-        // w < 10^19, so a value below 10^max_exponent10 cannot overflow, and a
-        // value that underflows is a finite number as well. Only a token that
-        // may overflow has to be converted to find out.
-        if (JSON_HEDLEY_UNLIKELY(discard_number_values && s.exponent + 19 <= std::numeric_limits<number_float_t>::max_exponent10))
-        {
-            value_float = 0;
-            return true;
-        }
         value_float = decimal_to_float<number_float_t>(s);
         return true;
     }

include/nlohmann/detail/input/parser.hpp

@@ -250,13 +250,6 @@ class parser
         // value to avoid a goto (see comment where set to true)
         bool skip_to_state_evaluation = false;
 
-        // a document that starts with a container pushes onto the stack at
-        // once: allocate it in one step instead of growing it from 1 byte
-        if (last_token == token_type::begin_object || last_token == token_type::begin_array)
-        {
-            states.reserve(32);
-        }
-
         while (true)
         {
             if (!skip_to_state_evaluation)

include/nlohmann/detail/json_pointer.hpp

@@ -8,7 +8,7 @@
 
 #pragma once
 
-#include <algorithm> // all_of
+#include <algorithm> // all_of, copy
 #include <array> // array
 #include <cctype> // isdigit
 #include <cerrno> // errno, ERANGE
@@ -82,12 +82,34 @@ class json_pointer
     {
         // one buffer: every token adds its escaped form (at least its length) and a slash
         std::size_t length = 0;
+        bool plain = true;
         for (const auto& reference_token : reference_tokens)
         {
             length += reference_token.size() + 1;
+            const char* const data = reference_token.data();
+            for (std::size_t i = 0, size = reference_token.size(); plain && i < size; ++i)
+            {
+                plain = data[i] != '~' && data[i] != '/';
+            }
         }
 
         string_t result;
+        if (JSON_HEDLEY_LIKELY(plain))
+        {
+            // nothing to escape: the tokens are copied into the string
+            result.resize(length);
+            if (length != 0)
+            {
+                char* out = &result[0];
+                for (const auto& reference_token : reference_tokens)
+                {
+                    *out++ = '/';
+                    out = std::copy(reference_token.data(), reference_token.data() + reference_token.size(), out);
+                }
+            }
+            return result;
+        }
+
         result.reserve(length);
         for (const auto& reference_token : reference_tokens)
         {
@@ -1198,33 +1220,32 @@ class json_pointer
         }
         result.reserve(token_count);
 
-        // extract the reference tokens:
+        // extract the reference tokens: every one runs from after a slash to
-        // - slash: position of the last read slash (or end of string)
+        // the next slash or the end of the string; a token without a '~' (the
-        // - start: position after the previous slash
+        // common case) is stored as it is, others are checked and unescaped
-        for (
+        const char* const data = reference_string.data();
-            // search for the first slash after the first character
+        const char* const end = data + size;
-            std::size_t slash = reference_string.find_first_of('/', 1),
+        for (const char* start = data + 1;; ++start)
-            // set the beginning of the first reference token
-            start = 1;
-            // we can stop if start == 0 (if slash == string_t::npos)
-            start != 0;
-            // set the beginning of the next reference token
-            // (will eventually be 0 if slash == string_t::npos)
-            start = (slash == string_t::npos) ? 0 : slash + 1,
-            // find next slash
-            slash = reference_string.find_first_of('/', start))
         {
-            // use the text between the beginning of the reference token
+            const char* slash = start;
-            // (start) and the last slash (slash).
+            bool escaped = false;
-            const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
+            while (slash != end && *slash != '/')
-            auto reference_token = string_t(reference_string.data() + start, count);
+            {
+                escaped = escaped || *slash == '~';
+                ++slash;
+            }
 
-            // check reference tokens are properly escaped; a token without
+            const auto count = static_cast<std::size_t>(slash - start);
-            // a '~' (the common case) needs neither check nor unescaping
+            if (JSON_HEDLEY_LIKELY(!escaped))
-            std::size_t pos = reference_token.find_first_of('~');
-            if (pos != string_t::npos)
             {
-                for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
+                result.emplace_back(start, count);
+            }
+            else
+            {
+                auto reference_token = string_t(start, count);
+
+                // check reference tokens are properly escaped
+                for (std::size_t pos = reference_token.find_first_of('~'); pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
                 {
                     JSON_ASSERT(reference_token[pos] == '~');
 
@@ -1238,10 +1259,14 @@ class json_pointer
                 }
 
                 detail::unescape(reference_token);
+                result.push_back(std::move(reference_token));
             }
 
-            // finally, store the reference token
+            if (slash == end)
-            result.push_back(std::move(reference_token));
+            {
+                break;
+            }
+            start = slash;
         }
 
         return result;

include/nlohmann/json.hpp

@@ -161,8 +161,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     template<typename BasicJsonType, typename InputAdapterType>
     friend class ::nlohmann::detail::json_sax_dom_parser;
     template<typename BasicJsonType, typename InputAdapterType>
-    friend class ::nlohmann::detail::json_sax_dom_binary_parser;
-    template<typename BasicJsonType, typename InputAdapterType>
     friend class ::nlohmann::detail::json_sax_dom_callback_parser;
 #if JSON_DIAGNOSTIC_POSITIONS
     friend struct ::nlohmann::detail::diagnostic_positions;
@@ -6289,7 +6287,7 @@ public:
            from_ubjson/from_bjdata/from_bon8/from_bson overloads
 
     Building the @ref binary_reader as a named local, rather than as a
-    temporary that @ref detail::json_sax_dom_binary_parser::parse is called on in
+    temporary that @ref detail::json_sax_dom_parser::parse is called on in
     the same expression, avoids a false-positive cppcheck accessMoved
     warning in each of the 16 callers.
     */
@@ -6300,7 +6298,7 @@ public:
                                        const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
     {
         basic_json result;
-        detail::json_sax_dom_binary_parser<basic_json, InputAdapterType> sdp(result, allow_exceptions);
+        detail::json_sax_dom_parser<basic_json, InputAdapterType> sdp(result, allow_exceptions);
         binary_reader<InputAdapterType> reader(std::move(ia), format, error_handler);
         if (!reader.sax_parse(&sdp, strict, tag_handler))
         {

tests/src/unit-class_parser.cpp

@@ -2952,32 +2952,3 @@ TEST_CASE("diagnostic positions: value lifetime, input adapters, and SAX")
     }
 }
 #endif
-
-TEST_CASE("accept() agrees with parse() on floats around the overflow limit")
-{
-    // accept() does not convert a float that cannot overflow; the tokens
-    // around the limit (and beyond it) must still be rejected exactly as
-    // parse() rejects them
-    const char* const numbers[] =
-    {
-        "1e0", "123.456e-5", "1e-400", "-1e-400", "1e307", "1e308", "1e309", "-1e309",
-        "10e307", "100e307", "0.1e309", "0.1e310", "1E+308", "1E+309",
-        "1.7976931348623157e308", "1.7976931348623159e308", "1.8e308", "-1.7976931348623157e308",
-        "12345678901234567e291", "12345678901234567e292", "123456789012345678e290", "123456789012345678e291",
-        "1234567890123456789e289", "1234567890123456789e290", "9999999999999999999e289", "9999999999999999999e290",
-        "0.00000000000000000001e328", "0.00000000000000000001e329"
-    };
-
-    for (const char* number : numbers)
-    {
-        for (const std::string text :
-                {
-                    std::string(number), "[" + std::string(number) + "]", "{\"a\":" + std::string(number) + "}"
-                })
-        {
-            INFO(text);
-            const bool parses = !json::parse(text, nullptr, false).is_discarded();
-            CHECK(json::accept(text) == parses);
-        }
-    }
-}

tests/src/unit-ordered_json.cpp

@@ -237,274 +237,3 @@ TEST_CASE("regression test for issue #5673 - ordered_json::emplace with a non-rv
         CHECK(oj.dump() == "{\"a\":1}");
     }
 }
-
-namespace
-{
-// the sizes around which the DOM parser changes how it stores the elements of
-// an array (16) and the members of an object in a vector (32, and 64 for the
-// key index)
-const std::size_t container_sizes[] = {0, 1, 2, 3, 15, 16, 17, 18, 31, 32, 33, 34, 63, 64, 65, 66, 200};
-
-template<typename Json>
-std::string array_text(const std::size_t n, const std::size_t depth)
-{
-    std::string text = "[";
-    for (std::size_t i = 0; i < n; ++i)
-    {
-        text += (i == 0 ? "" : ",");
-        // alternate scalars, empty containers and nested containers
-        switch (i % 4)
-        {
-            case 0:
-                text += std::to_string(i);
-                break;
-            case 1:
-                text += "\"s" + std::to_string(i) + "\"";
-                break;
-            case 2:
-                text += depth == 0 ? "[]" : array_text<Json>(n / 2, depth - 1);
-                break;
-            default:
-                text += depth == 0 ? "{}" : "{\"a\":" + array_text<Json>(n / 3, depth - 1) + ",\"b\":null}";
-                break;
-        }
-    }
-    return text + "]";
-}
-
-template<typename Json>
-std::string object_text(const std::size_t n, const std::size_t depth, const bool duplicates)
-{
-    std::string text = "{";
-    for (std::size_t i = 0; i < n; ++i)
-    {
-        text += (i == 0 ? "" : ",");
-        text += "\"key" + std::to_string(i) + "\":";
-        switch (i % 4)
-        {
-            case 0:
-                text += std::to_string(i);
-                break;
-            case 1:
-                text += depth == 0 ? "[]" : array_text<Json>(n / 2, depth - 1);
-                break;
-            case 2:
-                text += depth == 0 ? "{}" : object_text<Json>(n / 2, depth - 1, duplicates);
-                break;
-            default:
-                text += "\"value\"";
-                break;
-        }
-    }
-    if (duplicates)
-    {
-        // keys that are there already, the first and the last one, with other values
-        text += n == 0 ? "" : ",";
-        text += "\"key0\":[1,2],\"key" + std::to_string(n - 1) + "\":{\"again\":true}";
-    }
-    return text + "}";
-}
-
-template<typename Json>
-void check_same_dump(const std::string& text)
-{
-    // the text is what dump() writes for the parsed value, and the value
-    // survives a second round trip: arrays keep their elements in order, an
-    // ordered_json keeps its members in order of appearance
-    const Json parsed = Json::parse(text);
-    const Json again = Json::parse(parsed.dump());
-    CHECK(parsed == again);
-    CHECK(parsed.dump() == again.dump());
-    CHECK(Json::accept(text));
-}
-} // namespace
-
-TEST_CASE("parsing containers of sizes around the limits of the DOM parser")
-{
-    SECTION("arrays")
-    {
-        for (const std::size_t n : container_sizes)
-        {
-            const std::string text = array_text<json>(n, 2);
-            INFO("size ", n);
-
-            const json parsed = json::parse(text);
-            CHECK(parsed.is_array());
-            CHECK(parsed.size() == n);
-            for (std::size_t i = 0; i < n; i += 4)
-            {
-                CHECK(parsed[i] == i);
-            }
-            check_same_dump<json>(text);
-            check_same_dump<ordered_json>(text);
-            CHECK(ordered_json::parse(text).dump() == parsed.dump());
-        }
-    }
-
-    SECTION("objects")
-    {
-        for (const bool duplicates :
-                {
-                    false, true
-                })
-        {
-            for (const std::size_t n : container_sizes)
-            {
-                const std::string text = object_text<json>(n, 2, duplicates);
-                INFO("size ", n, " duplicates ", duplicates);
-
-                const json parsed = json::parse(text);
-                const ordered_json ordered = ordered_json::parse(text);
-                CHECK(parsed.is_object());
-                CHECK(ordered.is_object());
-                CHECK(parsed.size() == ordered.size());
-                // the same members, in the order of their first appearance
-                std::size_t i = 0;
-                for (auto it = ordered.begin(); it != ordered.end(); ++it, ++i)
-                {
-                    if (i < n)
-                    {
-                        CHECK(it.key() == "key" + std::to_string(i));
-                    }
-                    CHECK(parsed.at(it.key()) == json(it.value()));
-                }
-                if (duplicates && n > 1)
-                {
-                    // the later value replaced the earlier one in its place
-                    CHECK(ordered.at("key0") == ordered_json::parse("[1,2]"));
-                    CHECK(ordered.at("key" + std::to_string(n - 1)) == ordered_json::parse("{\"again\":true}"));
-                    CHECK(ordered.begin().key() == "key0");
-                    CHECK(ordered.size() == n);
-                }
-                check_same_dump<json>(text);
-                check_same_dump<ordered_json>(text);
-            }
-        }
-    }
-
-    SECTION("objects with many different and repeated keys")
-    {
-        // 300 members of which a third repeat an earlier key
-        std::string text = "{";
-        for (std::size_t i = 0; i < 300; ++i)
-        {
-            text += (i == 0 ? "" : ",");
-            text += "\"k" + std::to_string(i % 200) + "\":" + std::to_string(i);
-        }
-        text += "}";
-
-        const ordered_json ordered = ordered_json::parse(text);
-        const json parsed = json::parse(text);
-        CHECK(ordered.size() == 200);
-        CHECK(parsed.size() == 200);
-        std::size_t i = 0;
-        for (auto it = ordered.begin(); it != ordered.end(); ++it, ++i)
-        {
-            CHECK(it.key() == "k" + std::to_string(i));
-            // the last value written
-            CHECK(it.value() == (i < 100 ? i + 200 : i));
-            CHECK(parsed.at(it.key()) == json(it.value()));
-        }
-    }
-}
-
-namespace
-{
-// a deterministic source of structure for parsing tests: builds a JSON text
-// and, at the same time, the value it has to parse to
-class tree_generator
-{
-  public:
-    explicit tree_generator(std::uint32_t seed) : state(seed) {}
-
-    template<typename Json>
-    Json make(std::string& text, const std::size_t depth)
-    {
-        switch (next(depth == 0 ? 5 : 9))
-        {
-            case 0:
-                text += "null";
-                return Json(nullptr);
-            case 1:
-                text += "true";
-                return Json(true);
-            case 2:
-            {
-                const int n = static_cast<int>(next(2000)) - 1000;
-                text += std::to_string(n);
-                return Json(n);
-            }
-            case 3:
-                text += "\"text\"";
-                return Json("text");
-            case 4:
-                text += "2.5";
-                return Json(2.5);
-            case 5:
-            case 6:
-            case 7:
-            {
-                Json array = Json::array();
-                text += "[";
-                const std::size_t n = size();
-                for (std::size_t i = 0; i < n; ++i)
-                {
-                    text += (i == 0 ? "" : ",");
-                    array.push_back(make<Json>(text, depth - 1));
-                }
-                text += "]";
-                return array;
-            }
-            default:
-            {
-                Json object = Json::object();
-                text += "{";
-                const std::size_t n = size();
-                for (std::size_t i = 0; i < n; ++i)
-                {
-                    const std::string key = "k" + std::to_string(i);
-                    text += (i == 0 ? "\"" : ",\"") + key + "\":";
-                    object[key] = make<Json>(text, depth - 1);
-                }
-                text += "}";
-                return object;
-            }
-        }
-    }
-
-  private:
-    std::uint32_t next(const std::uint32_t bound)
-    {
-        state = state * 1664525U + 1013904223U;
-        return (state >> 8) % bound;
-    }
-
-    std::size_t size()
-    {
-        return container_sizes[next(sizeof(container_sizes) / sizeof(*container_sizes))];
-    }
-
-    std::uint32_t state;
-};
-} // namespace
-
-TEST_CASE("parsing random trees of arrays and objects")
-{
-    for (std::uint32_t seed = 1; seed <= 150; ++seed)
-    {
-        INFO("seed ", seed);
-
-        std::string text;
-        std::string ordered_text;
-        const json expected = tree_generator(seed).make<json>(text, 3);
-        const ordered_json ordered_expected = tree_generator(seed).make<ordered_json>(ordered_text, 3);
-        CHECK(text == ordered_text);
-
-        CHECK(json::parse(text) == expected);
-        CHECK(json::accept(text));
-        const ordered_json ordered = ordered_json::parse(text);
-        CHECK(ordered == ordered_expected);
-        CHECK(ordered.dump() == ordered_expected.dump());
-        CHECK(json::parse(text).dump() == expected.dump());
-    }
-}