Merge branch 'develop' into techdebt/5710-5711-binary-formats-cleanup

Conflicts:
- include/nlohmann/detail/output/binary_writer.hpp: kept write_msgpack_unsigned() for both msgpack integer cases; it already reads the active union member, which is what develop's #5694 fixes in the old ladders
- single_include/nlohmann/json.hpp: regenerated with make amalgamate

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

include/nlohmann/detail/input/binary_reader.hpp

@@ -8,7 +8,6 @@
 
 #pragma once
 
-#include <algorithm> // generate_n
 #include <array> // array
 #include <cmath> // ldexp
 #include <cstddef> // size_t
@@ -123,7 +122,26 @@ class binary_reader
     ~binary_reader() = default;
 
     /*!
-    @param[in] format  the binary format to parse
+    @brief parse in the format the constructor was given
+
+    @param[in] sax_    a SAX event processor
+    @param[in] strict  whether to expect the input to be consumed completed
+    @param[in] tag_handler  how to treat CBOR tags
+
+    @return whether parsing was successful
+    */
+    JSON_HEDLEY_NON_NULL(2)
+    bool sax_parse(json_sax_t* sax_,
+                   const bool strict = true,
+                   const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
+    {
+        return sax_parse(input_format, sax_, strict, tag_handler);
+    }
+
+    /*!
+    @param[in] format  the binary format to parse; must equal the format the
+                        constructor was given, since that format is what
+                        every reader function below actually dispatches on
     @param[in] sax_    a SAX event processor
     @param[in] strict  whether to expect the input to be consumed completed
     @param[in] tag_handler  how to treat CBOR tags
@@ -136,6 +154,7 @@ class binary_reader
                    const bool strict = true,
                    const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
     {
+        JSON_ASSERT(format == input_format);
         sax = sax_;
         container_stack.clear();
         bon8_pushback_size = 0;
@@ -148,7 +167,7 @@ class binary_reader
                 break;
 
             case input_format_t::cbor:
-                result = parse_cbor_internal(true, tag_handler);
+                result = parse_cbor_internal(tag_handler);
                 break;
 
             case input_format_t::msgpack:
@@ -271,6 +290,22 @@ class binary_reader
         return enter_container(/*is_object*/true, len, type_marker);
     }
 
+    /*!
+    @brief close the innermost open array or object
+
+    Pops the container opened by the matching @ref enter_container call and
+    emits the SAX end event. Every format-specific driver otherwise repeated
+    the same pop-then-dispatch sequence at its own close site.
+
+    @return whether the SAX parser accepted the end event
+    */
+    bool leave_container()
+    {
+        const bool is_object = container_stack.back().is_object;
+        container_stack.pop_back();
+        return is_object ? sax->end_object() : sax->end_array();
+    }
+
     //////////
     // BSON //
     //////////
@@ -355,8 +390,8 @@ class binary_reader
             if (element_type == 0) // end of the innermost document
             {
                 // a copy, not a reference: it must stay valid across the
-                // pop_back() below, which destroys the container_stack
+                // pop_back() inside leave_container() below, which destroys
-                // element it would otherwise alias
+                // the container_stack element it would otherwise alias
                 const container_frame top = container_stack.back();
 
                 if (JSON_HEDLEY_UNLIKELY(!check_bson_document_size(top.start_position, top.declared_size)))
@@ -364,8 +399,7 @@ class binary_reader
                     return false;
                 }
 
-                container_stack.pop_back();
+                if (JSON_HEDLEY_UNLIKELY(!leave_container()))
-                if (JSON_HEDLEY_UNLIKELY(top.is_object ? !sax->end_object() : !sax->end_array()))
                 {
                     return false;
                 }
@@ -860,29 +894,13 @@ class binary_reader
                 return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
 
             case 0x98: // array (one-byte uint8_t for n follows)
-            {
-                std::uint8_t len{};
-                return get_number(input_format_t::cbor, len) && enter_array(static_cast<std::size_t>(len));
-            }
-
             case 0x99: // array (two-byte uint16_t for n follow)
-            {
-                std::uint16_t len{};
-                return get_number(input_format_t::cbor, len) && enter_array(static_cast<std::size_t>(len));
-            }
-
             case 0x9A: // array (four-byte uint32_t for n follow)
-            {
-                std::uint32_t len{};
-                std::size_t size{};
-                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && enter_array(size);
-            }
-
             case 0x9B: // array (eight-byte uint64_t for n follow)
             {
                 std::uint64_t len{};
                 std::size_t size{};
-                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && enter_array(size);
+                return get_cbor_argument(len) && get_cbor_container_size(len, size, "array") && enter_array(size);
             }
 
             case 0x9F: // array (indefinite length)
@@ -916,35 +934,19 @@ class binary_reader
                 return enter_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
 
             case 0xB8: // map (one-byte uint8_t for n follows)
-            {
-                std::uint8_t len{};
-                return get_number(input_format_t::cbor, len) && enter_object(static_cast<std::size_t>(len));
-            }
-
             case 0xB9: // map (two-byte uint16_t for n follow)
-            {
-                std::uint16_t len{};
-                return get_number(input_format_t::cbor, len) && enter_object(static_cast<std::size_t>(len));
-            }
-
             case 0xBA: // map (four-byte uint32_t for n follow)
-            {
-                std::uint32_t len{};
-                std::size_t size{};
-                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && enter_object(size);
-            }
-
             case 0xBB: // map (eight-byte uint64_t for n follow)
             {
                 std::uint64_t len{};
                 std::size_t size{};
-                return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && enter_object(size);
+                return get_cbor_argument(len) && get_cbor_container_size(len, size, "map") && enter_object(size);
             }
 
             case 0xBF: // map (indefinite length)
                 return enter_object(detail::unknown_size());
 
-            case 0xC0: // tagged item
+            case 0xC0: // tagged item (tag value 0-23, in the head itself)
             case 0xC1:
             case 0xC2:
             case 0xC3:
@@ -968,6 +970,22 @@ class binary_reader
             case 0xD5:
             case 0xD6:
             case 0xD7:
+            {
+                if (tag_handler == cbor_tag_handler_t::error)
+                {
+                    auto last_token = get_token_string();
+                    return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
+                                            exception_message(input_format_t::cbor, concat("invalid byte: 0x", last_token), "value"), nullptr));
+                }
+
+                // ignore and store: the tag value is already in the head, so
+                // there is nothing left to read here; the tagged value that
+                // follows is read by the loop in parse_cbor_internal() rather
+                // than by recursing here
+                tag_pending = true;
+                return true;
+            }
+
             case 0xD8: // tagged item (1 byte follows)
             case 0xD9: // tagged item (2 bytes follow)
             case 0xDA: // tagged item (4 bytes follow)
@@ -984,47 +1002,11 @@ class binary_reader
 
                     case cbor_tag_handler_t::ignore:
                     {
-                        // ignore binary subtype
+                        // ignore the tag's binary subtype argument
-                        switch (current)
+                        std::uint64_t subtype_to_ignore{};
+                        if (!get_cbor_argument(subtype_to_ignore))
                         {
-                            case 0xD8:
+                            return false;
-                            {
-                                std::uint8_t subtype_to_ignore{};
-                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
-                                {
-                                    return false;
-                                }
-                                break;
-                            }
-                            case 0xD9:
-                            {
-                                std::uint16_t subtype_to_ignore{};
-                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
-                                {
-                                    return false;
-                                }
-                                break;
-                            }
-                            case 0xDA:
-                            {
-                                std::uint32_t subtype_to_ignore{};
-                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
-                                {
-                                    return false;
-                                }
-                                break;
-                            }
-                            case 0xDB:
-                            {
-                                std::uint64_t subtype_to_ignore{};
-                                if (!get_number(input_format_t::cbor, subtype_to_ignore))
-                                {
-                                    return false;
-                                }
-                                break;
-                            }
-                            default:
-                                break;
                         }
                         // the tagged value follows; it is read by the loop in
                         // parse_cbor_internal() rather than by recursing here
@@ -1034,57 +1016,15 @@ class binary_reader
 
                     case cbor_tag_handler_t::store:
                     {
-                        binary_t b;
                         // use binary subtype and store in a binary container
-                        switch (current)
+                        std::uint64_t subtype{};
+                        if (!get_cbor_argument(subtype))
                         {
-                            case 0xD8:
+                            return false;
-                            {
-                                std::uint8_t subtype{};
-                                if (!get_number(input_format_t::cbor, subtype))
-                                {
-                                    return false;
-                                }
-                                b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
-                                break;
-                            }
-                            case 0xD9:
-                            {
-                                std::uint16_t subtype{};
-                                if (!get_number(input_format_t::cbor, subtype))
-                                {
-                                    return false;
-                                }
-                                b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
-                                break;
-                            }
-                            case 0xDA:
-                            {
-                                std::uint32_t subtype{};
-                                if (!get_number(input_format_t::cbor, subtype))
-                                {
-                                    return false;
-                                }
-                                b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
-                                break;
-                            }
-                            case 0xDB:
-                            {
-                                std::uint64_t subtype{};
-                                if (!get_number(input_format_t::cbor, subtype))
-                                {
-                                    return false;
-                                }
-                                b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
-                                break;
-                            }
-                            default:
-                            {
-                                // as above, the tagged value is read by the caller
-                                tag_pending = true;
-                                return true;
-                            }
                         }
+                        binary_t b;
+                        b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
+
                         get();
                         // a byte string (the heads accepted by get_cbor_binary) keeps the tag as subtype
                         if ((current >= 0x40 && current <= 0x5B) || current == 0x5F)
@@ -1115,52 +1055,7 @@ class binary_reader
                 return sax->null();
 
             case 0xF9: // Half-Precision Float (two-byte IEEE 754)
-            {
+                return get_half_float(input_format_t::cbor, false);
-                const auto byte1_raw = get();
-                if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number")))
-                {
-                    return false;
-                }
-                const auto byte2_raw = get();
-                if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number")))
-                {
-                    return false;
-                }
-
-                const auto byte1 = static_cast<unsigned char>(byte1_raw);
-                const auto byte2 = static_cast<unsigned char>(byte2_raw);
-
-                // Code from RFC 8949, Appendix D, Figure 3:
-                // As half-precision floating-point numbers were only added
-                // to IEEE 754 in 2008, today's programming platforms often
-                // still only have limited support for them. It is very
-                // easy to include at least decoding support for them even
-                // without such support. An example of a small decoder for
-                // half-precision floating-point numbers in the C language
-                // is shown in Fig. 3.
-                const auto half = static_cast<unsigned int>((byte1 << 8u) + byte2);
-                const double val = [&half]
-                {
-                    const int exp = (half >> 10u) & 0x1Fu;
-                    const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(exp <= 31);
-                    JSON_ASSERT(mant <= 1023);
-                    switch (exp)
-                    {
-                        case 0:
-                            return std::ldexp(mant, -24);
-                        case 31:
-                            return (mant == 0)
-                            ? std::numeric_limits<double>::infinity()
-                            : std::numeric_limits<double>::quiet_NaN();
-                        default:
-                            return std::ldexp(mant + 1024, exp - 25);
-                    }
-                }();
-                return sax->number_float((half & 0x8000u) != 0
-                                         ? static_cast<number_float_t>(-val)
-                                         : static_cast<number_float_t>(val), "");
-            }
 
             case 0xFA: // Single-Precision Float (four-byte IEEE 754)
             {
@@ -1539,6 +1434,73 @@ class binary_reader
         }
     }
 
+    /*!
+    @brief read a CBOR argument (additional information 24-27) of the width
+           @ref current announces
+
+    The lower 5 bits of @a current (0x18-0x1B) select a 1/2/4/8-byte
+    big-endian unsigned integer that follows the head byte; this is shared by
+    every major type that uses this encoding (unsigned/negative integers,
+    strings, arrays, maps, tags). Reading always goes through @ref get_number,
+    so EOF is reported the same way as before this helper existed.
+
+    @param[out] value  the decoded argument
+    @return whether reading succeeded
+    */
+    bool get_cbor_argument(std::uint64_t& value)
+    {
+        switch (current & 0x1F)
+        {
+            case 0x18: // 1 byte
+            {
+                std::uint8_t n{};
+                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::cbor, n)))
+                {
+                    return false;
+                }
+                value = n;
+                return true;
+            }
+
+            case 0x19: // 2 bytes
+            {
+                std::uint16_t n{};
+                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::cbor, n)))
+                {
+                    return false;
+                }
+                value = n;
+                return true;
+            }
+
+            case 0x1A: // 4 bytes
+            {
+                std::uint32_t n{};
+                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::cbor, n)))
+                {
+                    return false;
+                }
+                value = n;
+                return true;
+            }
+
+            case 0x1B: // 8 bytes
+            {
+                std::uint64_t n{};
+                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::cbor, n)))
+                {
+                    return false;
+                }
+                value = n;
+                return true;
+            }
+
+            default:                 // LCOV_EXCL_LINE
+                JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
+                return false;        // LCOV_EXCL_LINE
+        }
+    }
+
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 
@@ -1571,19 +1533,15 @@ class binary_reader
     enclosing container after each element, so that the nesting depth of the
     input costs heap rather than native stack (see #5104).
 
-    @param[in] get_char  whether a new character should be retrieved from the
-                         input (true) or whether the last read character
-                         @a current should be considered instead
     @param[in] tag_handler how CBOR tags should be treated
 
     @return whether reading the value succeeded
     */
-    bool parse_cbor_internal(const bool get_char,
+    bool parse_cbor_internal(const cbor_tag_handler_t tag_handler)
-                             const cbor_tag_handler_t tag_handler)
     {
         // whether the next value starts at a fresh byte or at the one already
         // read into `current`
-        bool fetch = get_char;
+        bool fetch = true;
 
         // the key currently being read; hoisted out of the loop so that its
         // capacity is reused across elements and across nesting levels
@@ -1626,8 +1584,7 @@ class binary_reader
 
                 if (at_end)
                 {
-                    container_stack.pop_back();
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
-                    if (JSON_HEDLEY_UNLIKELY(top.is_object ? !sax->end_object() : !sax->end_array()))
                     {
                         return false;
                     }
@@ -1676,9 +1633,6 @@ class binary_reader
     // MsgPack //
     /////////////
 
-    /*!
-    @return whether a valid MessagePack value was passed to the SAX parser
-    */
     /*!
     @brief read one MessagePack value
 
@@ -2377,8 +2331,7 @@ class binary_reader
 
                 if (container_stack.back().remaining == 0)
                 {
-                    container_stack.pop_back();
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
-                    if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
                     {
                         return false;
                     }
@@ -2423,20 +2376,16 @@ class binary_reader
     ////////////
 
     /*!
-    @param[in] get_char  whether a new character should be retrieved from the
-                         input (true, default) or whether the last read
-                         character should be considered instead
-
     @return whether a valid UBJSON value was passed to the SAX parser
     */
-    bool parse_ubjson_internal(const bool get_char = true)
+    bool parse_ubjson_internal()
     {
         // the key currently being read; hoisted out of the loop so that its
         // capacity is reused across elements and across nesting levels
         string_t key;
 
         // the type marker of the value to read next
-        char_int_type prefix = get_char ? get_ignore_noop() : current;
+        char_int_type prefix = get_ignore_noop();
 
         while (true)
         {
@@ -2511,8 +2460,7 @@ class binary_reader
                     break;
                 }
 
-                container_stack.pop_back();
+                if (JSON_HEDLEY_UNLIKELY(!leave_container()))
-                if (JSON_HEDLEY_UNLIKELY(top.is_object ? !sax->end_object() : !sax->end_array()))
                 {
                     return false;
                 }
@@ -2720,6 +2668,42 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief read a UBJSON/BJData optimized-container count of a signed marker
+           type ('i', 'I', 'l', 'L') and narrow it to std::size_t
+
+    Every signed count marker rejects a negative value the same way (error
+    113); the value_in_range_of check additionally needed for 'L' is only
+    ever live when @a SignedType is std::int64_t on a target where
+    std::size_t is narrower (e.g. 32-bit), since 'i'/'I'/'l' can never exceed
+    std::size_t there.
+
+    @tparam SignedType  std::int8_t, std::int16_t, std::int32_t or std::int64_t
+    @param[out] result  the count narrowed to std::size_t
+    @return whether reading and validating succeeded
+    */
+    template<typename SignedType>
+    bool get_ubjson_signed_count(std::size_t& result)
+    {
+        SignedType number{};
+        if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
+        {
+            return false;
+        }
+        if (JSON_HEDLEY_UNLIKELY(number < 0))
+        {
+            return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
+                                    exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
+        }
+        if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(number)))
+        {
+            return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
+                                    exception_message(input_format, "integer value overflow", "size"), nullptr));
+        }
+        result = static_cast<std::size_t>(number); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): number is not a char
+        return true;
+    }
+
     /*!
     @param[out] result  determined size
     @param[in,out] is_ndarray  for input, `true` means already inside an ndarray vector
@@ -2752,73 +2736,16 @@ class binary_reader
             }
 
             case 'i':
-            {
+                return get_ubjson_signed_count<std::int8_t>(result);
-                std::int8_t number{};
-                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
-                {
-                    return false;
-                }
-                if (number < 0)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
-                                            exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
-                }
-                result = static_cast<std::size_t>(number); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): number is not a char
-                return true;
-            }
 
             case 'I':
-            {
+                return get_ubjson_signed_count<std::int16_t>(result);
-                std::int16_t number{};
-                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
-                {
-                    return false;
-                }
-                if (number < 0)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
-                                            exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
-                }
-                result = static_cast<std::size_t>(number);
-                return true;
-            }
 
             case 'l':
-            {
+                return get_ubjson_signed_count<std::int32_t>(result);
-                std::int32_t number{};
-                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
-                {
-                    return false;
-                }
-                if (number < 0)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
-                                            exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
-                }
-                result = static_cast<std::size_t>(number);
-                return true;
-            }
 
             case 'L':
-            {
+                return get_ubjson_signed_count<std::int64_t>(result);
-                std::int64_t number{};
-                if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
-                {
-                    return false;
-                }
-                if (number < 0)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
-                                            exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
-                }
-                if (!value_in_range_of<std::size_t>(number))
-                {
-                    return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
-                                            exception_message(input_format, "integer value overflow", "size"), nullptr));
-                }
-                result = static_cast<std::size_t>(number);
-                return true;
-            }
 
             case 'u':
             {
@@ -2909,16 +2836,23 @@ class binary_reader
                     result = 1;
                     for (auto i : dim)
                     {
-                        // Pre-multiplication overflow check: if i > 0 and result > SIZE_MAX/i, then result*i would overflow.
+                        // Pre-multiplication overflow check: since the loop above
-                        // This check must happen before multiplication since overflow detection after the fact is unreliable
+                        // already rejected any zero dimension, i is always > 0
-                        // as modular arithmetic can produce any value, not just 0 or SIZE_MAX.
+                        // here, so result > SIZE_MAX/i means result*i would
-                        if (JSON_HEDLEY_UNLIKELY(i > 0 && result > (std::numeric_limits<std::size_t>::max)() / i))
+                        // overflow. This check must happen before multiplication
+                        // since overflow detection after the fact is unreliable,
+                        // as modular arithmetic can produce any value, not just 0
+                        // or SIZE_MAX.
+                        if (JSON_HEDLEY_UNLIKELY(result > (std::numeric_limits<std::size_t>::max)() / i))
                         {
                             return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message(input_format, "excessive ndarray size caused overflow", "size"), nullptr));
                         }
                         result *= i;
-                        // Additional post-multiplication check to catch any edge cases the pre-check might miss
+                        // the pre-check above already rules out result becoming 0
-                        if (result == 0 || result == npos)
+                        // by overflow; the only value it cannot rule out is an
+                        // exact match with npos, the sentinel reserved for an
+                        // unknown-size container (see get_ubjson_size_type())
+                        if (result == npos)
                         {
                             return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message(input_format, "excessive ndarray size caused overflow", "size"), nullptr));
                         }
@@ -2979,7 +2913,7 @@ class binary_reader
         {
             result.second = get();  // must not ignore 'N', because 'N' maybe the type
             if (input_format == input_format_t::bjdata
-                    && JSON_HEDLEY_UNLIKELY(std::binary_search(bjd_optimized_type_markers.begin(), bjd_optimized_type_markers.end(), result.second)))
+                    && JSON_HEDLEY_UNLIKELY(is_bjd_excluded_optimized_type(result.second)))
             {
                 auto last_token = get_token_string();
                 return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
@@ -3123,50 +3057,7 @@ class binary_reader
                 {
                     break;
                 }
-                const auto byte1_raw = get();
+                return get_half_float(input_format, true);
-                if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "number")))
-                {
-                    return false;
-                }
-                const auto byte2_raw = get();
-                if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "number")))
-                {
-                    return false;
-                }
-
-                const auto byte1 = static_cast<unsigned char>(byte1_raw);
-                const auto byte2 = static_cast<unsigned char>(byte2_raw);
-
-                // Code from RFC 8949, Appendix D, Figure 3:
-                // As half-precision floating-point numbers were only added
-                // to IEEE 754 in 2008, today's programming platforms often
-                // still only have limited support for them. It is very
-                // easy to include at least decoding support for them even
-                // without such support. An example of a small decoder for
-                // half-precision floating-point numbers in the C language
-                // is shown in Fig. 3.
-                const auto half = static_cast<unsigned int>((byte2 << 8u) + byte1);
-                const double val = [&half]
-                {
-                    const int exp = (half >> 10u) & 0x1Fu;
-                    const unsigned int mant = half & 0x3FFu;
-                    JSON_ASSERT(exp <= 31);
-                    JSON_ASSERT(mant <= 1023);
-                    switch (exp)
-                    {
-                        case 0:
-                            return std::ldexp(mant, -24);
-                        case 31:
-                            return (mant == 0)
-                            ? std::numeric_limits<double>::infinity()
-                            : std::numeric_limits<double>::quiet_NaN();
-                        default:
-                            return std::ldexp(mant + 1024, exp - 25);
-                    }
-                }();
-                return sax->number_float((half & 0x8000u) != 0
-                                         ? static_cast<number_float_t>(-val)
-                                         : static_cast<number_float_t>(val), "");
             }
 
             case 'd':
@@ -3239,19 +3130,16 @@ class binary_reader
         if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
         {
             size_and_type.second &= ~(static_cast<char_int_type>(1) << 8);  // use bit 8 to indicate ndarray, here we remove the bit to restore the type marker
-            auto it = std::lower_bound(bjd_types_map.begin(), bjd_types_map.end(), size_and_type.second, [](const bjd_type & p, char_int_type t)
+            const char* type_name = bjd_type_name(size_and_type.second);
-            {
-                return p.first < t;
-            });
             string_t key = "_ArrayType_";
-            if (JSON_HEDLEY_UNLIKELY(it == bjd_types_map.end() || it->first != size_and_type.second))
+            if (JSON_HEDLEY_UNLIKELY(type_name == nullptr))
             {
                 auto last_token = get_token_string();
                 return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
                                         exception_message(input_format, "invalid byte: 0x" + last_token, "type"), nullptr));
             }
 
-            string_t type = it->second; // sax->string() takes a reference
+            string_t type = type_name; // sax->string() takes a reference
             if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->string(type)))
             {
                 return false;
@@ -3543,8 +3431,7 @@ class binary_reader
 
                 if (at_end)
                 {
-                    container_stack.pop_back();
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
-                    if (JSON_HEDLEY_UNLIKELY(top.is_object ? !sax->end_object() : !sax->end_array()))
                     {
                         return false;
                     }
@@ -4083,6 +3970,68 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief read and decode an IEEE 754 half-precision (16-bit) float
+
+    Used by CBOR (big endian) and BJData (little endian); the two formats
+    only differ in the byte order of the two bytes that make up the half.
+
+    @param[in] format       the current format (for diagnostics)
+    @param[in] little_endian whether the two bytes are little endian (BJData)
+                             or big endian (CBOR)
+
+    @return whether reading and decoding succeeded
+    */
+    bool get_half_float(const input_format_t format, const bool little_endian)
+    {
+        const auto byte1_raw = get();
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "number")))
+        {
+            return false;
+        }
+        const auto byte2_raw = get();
+        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(format, "number")))
+        {
+            return false;
+        }
+
+        const auto byte1 = static_cast<unsigned char>(byte1_raw);
+        const auto byte2 = static_cast<unsigned char>(byte2_raw);
+
+        // Code from RFC 8949, Appendix D, Figure 3:
+        // As half-precision floating-point numbers were only added
+        // to IEEE 754 in 2008, today's programming platforms often
+        // still only have limited support for them. It is very
+        // easy to include at least decoding support for them even
+        // without such support. An example of a small decoder for
+        // half-precision floating-point numbers in the C language
+        // is shown in Fig. 3.
+        const auto half = little_endian
+                          ? static_cast<unsigned int>((byte2 << 8u) + byte1)
+                          : static_cast<unsigned int>((byte1 << 8u) + byte2);
+        const double val = [&half]
+        {
+            const int exp = (half >> 10u) & 0x1Fu;
+            const unsigned int mant = half & 0x3FFu;
+            JSON_ASSERT(exp <= 31);
+            JSON_ASSERT(mant <= 1023);
+            switch (exp)
+            {
+                case 0:
+                    return std::ldexp(mant, -24);
+                case 31:
+                    return (mant == 0)
+                    ? std::numeric_limits<double>::infinity()
+                    : std::numeric_limits<double>::quiet_NaN();
+                default:
+                    return std::ldexp(mant + 1024, exp - 25);
+            }
+        }();
+        return sax->number_float((half & 0x8000u) != 0
+                                 ? static_cast<number_float_t>(-val)
+                                 : static_cast<number_float_t>(val), "");
+    }
+
     /*!
     @brief create a string by reading characters from the input
 
@@ -4308,38 +4257,61 @@ class binary_reader
     /// BON8: number of bytes in @ref bon8_pushback
     std::size_t bon8_pushback_size = 0;
 
-    // excluded markers in bjdata optimized type
-#define JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_ \
-    make_array<char_int_type>('F', 'H', 'N', 'S', 'T', 'Z', '[', '{')
-
-#define JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_ \
-    make_array<bjd_type>(                      \
-    bjd_type{'B', "byte"},                     \
-    bjd_type{'C', "char"},                     \
-    bjd_type{'D', "double"},                   \
-    bjd_type{'I', "int16"},                    \
-    bjd_type{'L', "int64"},                    \
-    bjd_type{'M', "uint64"},                   \
-    bjd_type{'U', "uint8"},                    \
-    bjd_type{'d', "single"},                   \
-    bjd_type{'i', "int8"},                     \
-    bjd_type{'l', "int32"},                    \
-    bjd_type{'m', "uint32"},                   \
-    bjd_type{'u', "uint16"})
-
   JSON_PRIVATE_UNLESS_TESTED:
-    // lookup tables
+    /*!
-    // NOLINTNEXTLINE(cppcoreguidelines-non-private-member-variables-in-classes)
+    @brief whether @a marker is excluded from BJData's optimized ND-array types
-    const decltype(JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_) bjd_optimized_type_markers =
+    @return whether @a marker is one of 'F', 'H', 'N', 'S', 'T', 'Z', '[', '{'
-        JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_;
 
-    using bjd_type = std::pair<char_int_type, string_t>;
+    Mirrors binary_writer's @ref binary_writer::is_bjdata_excluded_type_marker
-    // NOLINTNEXTLINE(cppcoreguidelines-non-private-member-variables-in-classes)
+    "is_bjdata_excluded_type_marker()`, which encodes the same list the other
-    const decltype(JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_) bjd_types_map =
+    way; keep the two in sync.
-        JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_;
+    */
+    static constexpr bool is_bjd_excluded_optimized_type(const char_int_type marker) noexcept
+    {
+        return marker == '[' || marker == '{' || marker == 'S' || marker == 'H'
+               || marker == 'T' || marker == 'F' || marker == 'N' || marker == 'Z';
+    }
 
-#undef JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_
+    /*!
-#undef JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_
+    @brief look up the ND-array element type name for a BJData dtype marker
+    @return the type name ("uint8", "int8", ...), or nullptr if @a marker does
+            not name a known dtype
+
+    A C++11 `constexpr` function cannot contain a `switch`, so this is a
+    plain (non-constexpr) switch instead.
+    */
+    static const char* bjd_type_name(const char_int_type marker)
+    {
+        switch (marker)
+        {
+            case 'B':
+                return "byte";
+            case 'C':
+                return "char";
+            case 'D':
+                return "double";
+            case 'I':
+                return "int16";
+            case 'L':
+                return "int64";
+            case 'M':
+                return "uint64";
+            case 'U':
+                return "uint8";
+            case 'd':
+                return "single";
+            case 'i':
+                return "int8";
+            case 'l':
+                return "int32";
+            case 'm':
+                return "uint32";
+            case 'u':
+                return "uint16";
+            default:
+                return nullptr;
+        }
+    }
 };
 
 #ifndef JSON_HAS_CPP_17

include/nlohmann/detail/meta/cpp_future.hpp

@@ -9,7 +9,6 @@
 
 #pragma once
 
-#include <array> // array
 #include <cstddef> // size_t
 #include <type_traits> // conditional, enable_if, false_type, integral_constant, is_constructible, is_integral, is_same, remove_cv, remove_reference, true_type
 #include <utility> // index_sequence, make_index_sequence, index_sequence_for
@@ -161,11 +160,5 @@ struct static_const
     constexpr T static_const<T>::value;
 #endif
 
-template<typename T, typename... Args>
-constexpr std::array<T, sizeof...(Args)> make_array(Args&& ... args)
-{
-    return std::array<T, sizeof...(Args)> {{static_cast<T>(std::forward<Args>(args))...}};
-}
-
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json.hpp

@@ -5034,7 +5034,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict);
     }
 
     /// @brief generate SAX events (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -5051,7 +5051,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         return format == input_format_t::json
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict);
     }
 
     /// @brief generate SAX events
@@ -5073,7 +5073,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
                ? parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict)
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(format, sax, strict);
+               : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict);
     }
 #ifndef JSON_NO_IO
     /// @brief deserialize from stream
@@ -5371,7 +5371,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5391,7 +5391,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5420,7 +5420,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(&sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5438,7 +5438,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5457,7 +5457,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5484,7 +5484,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5502,7 +5502,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5521,7 +5521,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5548,7 +5548,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5566,7 +5566,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5585,7 +5585,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5603,7 +5603,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bon8).sax_parse(input_format_t::bon8, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bon8).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5622,7 +5622,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bon8).sax_parse(input_format_t::bon8, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bon8).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5640,7 +5640,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5659,7 +5659,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }
@@ -5686,7 +5686,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(&sdp, strict)) // cppcheck-suppress[accessMoved]
         {
             result = value_t::discarded;
         }

tests/src/unit-bjdata.cpp

@@ -210,15 +210,42 @@ TEST_CASE_TEMPLATE_INVOKE(value_in_range_of_test, \
 
 TEST_CASE("BJData")
 {
-    SECTION("binary_reader BJData LUT arrays are sorted")
+    SECTION("binary_reader BJData lookup tables")
     {
         std::vector<std::uint8_t> const data;
         auto ia = nlohmann::detail::input_adapter(data);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
         nlohmann::detail::binary_reader<json, decltype(ia)> const br{std::move(ia), json::input_format_t::bjdata};
 
-        CHECK(std::is_sorted(br.bjd_optimized_type_markers.begin(), br.bjd_optimized_type_markers.end()));
+        // the excluded optimized-type markers must match binary_writer's
-        CHECK(std::is_sorted(br.bjd_types_map.begin(), br.bjd_types_map.end()));
+        // is_bjdata_excluded_type_marker(), which encodes the same 8 markers
+        for (const char marker :
+                {'[', '{', 'S', 'H', 'T', 'F', 'N', 'Z'
+                })
+        {
+            CHECK(br.is_bjd_excluded_optimized_type(marker));
+        }
+        for (const char marker :
+                {'U', 'i', 'u', 'I', 'm', 'l', 'M', 'L', 'd', 'D', 'C', 'B', 'x'
+                })
+        {
+            CHECK(!br.is_bjd_excluded_optimized_type(marker));
+        }
+
+        // every dtype marker must round-trip to its ND-array type name
+        const std::vector<std::pair<char, std::string>> types
+        {
+            {'B', "byte"}, {'C', "char"}, {'D', "double"}, {'I', "int16"},
+            {'L', "int64"}, {'M', "uint64"}, {'U', "uint8"}, {'d', "single"},
+            {'i', "int8"}, {'l', "int32"}, {'m', "uint32"}, {'u', "uint16"}
+        };
+        for (const auto& type : types)
+        {
+            const char* name = br.bjd_type_name(type.first);
+            REQUIRE(name != nullptr);
+            CHECK(std::string(name) == type.second);
+        }
+        CHECK(br.bjd_type_name('x') == nullptr);
     }
 
     SECTION("individual values")

tests/src/unit-ubjson.cpp

@@ -3033,3 +3033,224 @@ TEST_CASE("UBJSON optimized array of unsigned integers beyond int64")
     CHECK(json::to_ubjson(j, true, true) == expected);
     CHECK(json::from_ubjson(expected) == j);
 }
+
+namespace
+{
+// the bytes that follow the marker of an integer: the value in the width of
+// the marker (big endian for UBJSON, little endian for BJData), or, for a
+// high-precision number, the length and the decimal digits
+std::vector<std::uint8_t> integer_payload(const char marker, const json& value, const bool little_endian)
+{
+    std::size_t width = 0;
+    switch (marker)
+    {
+        case 'i':
+        case 'U':
+            width = 1;
+            break;
+        case 'I':
+        case 'u':
+            width = 2;
+            break;
+        case 'l':
+        case 'm':
+            width = 4;
+            break;
+        case 'L':
+        case 'M':
+            width = 8;
+            break;
+        default:
+        {
+            const std::string digits = value.dump();
+            std::vector<std::uint8_t> result = {'i', static_cast<std::uint8_t>(digits.size())};
+            for (const char c : digits)
+            {
+                result.push_back(static_cast<std::uint8_t>(c));
+            }
+            return result;
+        }
+    }
+
+    const std::uint64_t bits = value.is_number_unsigned()
+                               ? value.get<std::uint64_t>()
+                               : static_cast<std::uint64_t>(value.get<std::int64_t>());
+    std::vector<std::uint8_t> result(width);
+    for (std::size_t i = 0; i < width; ++i)
+    {
+        result[little_endian ? i : width - 1 - i] = static_cast<std::uint8_t>(bits >> (8 * i));
+    }
+    return result;
+}
+
+json i64(const std::int64_t v)
+{
+    return v;
+}
+
+json u64(const std::uint64_t v)
+{
+    return v;
+}
+} // namespace
+
+TEST_CASE("UBJSON and BJData integer markers at every range edge")
+{
+    // An optimized container announces the marker of its values after `$` and
+    // then writes every value without a marker, so the marker the writer
+    // announces and the width it writes must match for every value. This
+    // checks both for the values around each edge of the integer types, as
+    // scalars and as the values of optimized arrays and objects.
+    struct integer_case
+    {
+        json value;
+        char ubjson; // expected UBJSON marker
+        char bjdata; // expected BJData marker
+    };
+
+    const std::int64_t int64_min = (std::numeric_limits<std::int64_t>::min)();
+    const std::int64_t int64_max = (std::numeric_limits<std::int64_t>::max)();
+    const std::uint64_t uint64_max = (std::numeric_limits<std::uint64_t>::max)();
+
+    const std::vector<integer_case> cases =
+    {
+        // int8
+        {i64(-129), 'I', 'I'},
+        {i64(-128), 'i', 'i'},
+        {i64(-127), 'i', 'i'},
+        {i64(-1), 'i', 'i'},
+        {i64(0), 'i', 'i'},
+        {u64(0), 'i', 'i'},
+        {i64(126), 'i', 'i'},
+        {i64(127), 'i', 'i'},
+        {u64(127), 'i', 'i'},
+        {i64(128), 'U', 'U'},
+        {u64(128), 'U', 'U'},
+        // uint8
+        {i64(254), 'U', 'U'},
+        {i64(255), 'U', 'U'},
+        {u64(255), 'U', 'U'},
+        {i64(256), 'I', 'I'},
+        {u64(256), 'I', 'I'},
+        // int16
+        {i64(-32769), 'l', 'l'},
+        {i64(-32768), 'I', 'I'},
+        {i64(-32767), 'I', 'I'},
+        {i64(32766), 'I', 'I'},
+        {i64(32767), 'I', 'I'},
+        {u64(32767), 'I', 'I'},
+        {i64(32768), 'l', 'u'},
+        {u64(32768), 'l', 'u'},
+        // uint16 (BJData only)
+        {i64(65534), 'l', 'u'},
+        {i64(65535), 'l', 'u'},
+        {u64(65535), 'l', 'u'},
+        {i64(65536), 'l', 'l'},
+        {u64(65536), 'l', 'l'},
+        // int32
+        {i64(-2147483649LL), 'L', 'L'},
+        {i64(-2147483648LL), 'l', 'l'},
+        {i64(-2147483647LL), 'l', 'l'},
+        {i64(2147483646LL), 'l', 'l'},
+        {i64(2147483647LL), 'l', 'l'},
+        {u64(2147483647ULL), 'l', 'l'},
+        {i64(2147483648LL), 'L', 'm'},
+        {u64(2147483648ULL), 'L', 'm'},
+        // uint32 (BJData only)
+        {i64(4294967294LL), 'L', 'm'},
+        {i64(4294967295LL), 'L', 'm'},
+        {u64(4294967295ULL), 'L', 'm'},
+        {i64(4294967296LL), 'L', 'L'},
+        {u64(4294967296ULL), 'L', 'L'},
+        // int64
+        {i64(int64_min), 'L', 'L'},
+        {i64(int64_min + 1), 'L', 'L'},
+        {i64(int64_max - 1), 'L', 'L'},
+        {i64(int64_max), 'L', 'L'},
+        {u64(static_cast<std::uint64_t>(int64_max)), 'L', 'L'},
+        // uint64 (BJData only; UBJSON writes a high-precision number)
+        {u64(static_cast<std::uint64_t>(int64_max) + 1), 'H', 'M'},
+        {u64(uint64_max - 1), 'H', 'M'},
+        {u64(uint64_max), 'H', 'M'},
+    };
+
+    for (const auto& c : cases)
+    {
+        for (const bool bjdata :
+                {
+                    false, true
+                })
+        {
+            const char marker = bjdata ? c.bjdata : c.ubjson;
+            const std::vector<std::uint8_t> payload = integer_payload(marker, c.value, bjdata);
+            const auto to_binary = [bjdata](const json & j, const bool use_size, const bool use_type)
+            {
+                return bjdata ? json::to_bjdata(j, use_size, use_type) : json::to_ubjson(j, use_size, use_type);
+            };
+            const auto from_binary = [bjdata](const std::vector<std::uint8_t>& v)
+            {
+                return bjdata ? json::from_bjdata(v) : json::from_ubjson(v);
+            };
+            INFO("value = " << c.value.dump() << (c.value.is_number_unsigned() ? " (unsigned)" : "") << ", format = " << (bjdata ? "BJData" : "UBJSON"));
+
+            // scalar
+            std::vector<std::uint8_t> expected = {static_cast<std::uint8_t>(marker)};
+            expected.insert(expected.end(), payload.begin(), payload.end());
+            for (const bool use_size :
+                    {
+                        false, true
+                    })
+            {
+                CHECK(to_binary(c.value, use_size, false) == expected);
+            }
+            CHECK(from_binary(expected) == c.value);
+
+            const json arr = {c.value, c.value, c.value};
+
+            // array without count or type: every value has its marker
+            expected = {'['};
+            for (int i = 0; i < 3; ++i)
+            {
+                expected.push_back(static_cast<std::uint8_t>(marker));
+                expected.insert(expected.end(), payload.begin(), payload.end());
+            }
+            expected.push_back(']');
+            CHECK(to_binary(arr, false, false) == expected);
+            CHECK(from_binary(expected) == arr);
+
+            // array with count: every value has its marker
+            expected = {'[', '#', 'i', 3};
+            for (int i = 0; i < 3; ++i)
+            {
+                expected.push_back(static_cast<std::uint8_t>(marker));
+                expected.insert(expected.end(), payload.begin(), payload.end());
+            }
+            CHECK(to_binary(arr, true, false) == expected);
+            CHECK(from_binary(expected) == arr);
+
+            // array with type and count: the marker once, then the payloads
+            expected = {'[', '$', static_cast<std::uint8_t>(marker), '#', 'i', 3};
+            for (int i = 0; i < 3; ++i)
+            {
+                expected.insert(expected.end(), payload.begin(), payload.end());
+            }
+            CHECK(to_binary(arr, true, true) == expected);
+            CHECK(from_binary(expected) == arr);
+
+            // object with type and count: the marker once, then key and payload
+            const json obj = {{"a", c.value}, {"b", c.value}};
+            expected = {'{', '$', static_cast<std::uint8_t>(marker), '#', 'i', 2};
+            for (const char key :
+                    {'a', 'b'
+                    })
+            {
+                expected.push_back('i');
+                expected.push_back(1);
+                expected.push_back(static_cast<std::uint8_t>(key));
+                expected.insert(expected.end(), payload.begin(), payload.end());
+            }
+            CHECK(to_binary(obj, true, true) == expected);
+            CHECK(from_binary(expected) == obj);
+        }
+    }
+}