Fix -Weffc++ in the BSON recorder test and a clang-tidy use-auto hit

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

docs/mkdocs/docs/api/basic_json/from_bson.md

@@ -80,7 +80,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 - Throws [`parse_error.110`](../../home/exceptions.md#jsonexceptionparse_error110) if the given input ends prematurely or
   the end of the input was not reached when `strict` was set to true
 - Throws [`parse_error.112`](../../home/exceptions.md#jsonexceptionparse_error112) if a parse error occurs (e.g., an
-  invalid string or byte array length)
+  invalid string or byte array length, an invalid inner length of a binary value with subtype `0x02`, or a document size
+  that does not match the content; `strict` does not affect the document size checks)
 - Throws [`parse_error.114`](../../home/exceptions.md#jsonexceptionparse_error114) if an unsupported BSON record type is
   encountered
 - Throws [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) if a string value or object key is

docs/mkdocs/docs/api/basic_json/from_ubjson.md

@@ -79,11 +79,18 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 - Throws [parse_error.110](../../home/exceptions.md#jsonexceptionparse_error110) if the given input ends prematurely or
   the end of the file was not reached when `strict` was set to true
-- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if a parse error occurs
+- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if an invalid type marker is read
+  (including a type marker after `$` of an optimized container, even if its count is 0), or if `$` is not followed by `#`
 - Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a string could not be parsed
-  successfully, or if a string value or object key is not valid UTF-8 and `error_handler` is `strict`
-- Throws [out_of_range.408](../../home/exceptions.md#jsonexceptionout_of_range408) if the size of an optimized container
-  or n-dimensional array cannot be represented by `std::size_t`
+  successfully (negative or non-integer length, `C` followed by a byte above 0x7F), if the count of an optimized
+  container is negative, or if a string value or object key is not valid UTF-8 and `error_handler` is `strict`
+- Throws [parse_error.115](../../home/exceptions.md#jsonexceptionparse_error115) if the text of a high-precision number
+  (`H`) is not a valid JSON number
+- Throws [out_of_range.406](../../home/exceptions.md#jsonexceptionout_of_range406) if a high-precision number, or a
+  float64 when `number_float_t` is `float`, does not fit into `number_float_t`
+- Throws [out_of_range.408](../../home/exceptions.md#jsonexceptionout_of_range408) if the count of an optimized
+  container exceeds the capacity of the container (or of `std::size_t`), or if an optimized array of `Z`, `T`, or `F` has
+  more than 1,048,576 elements
 
 ## Complexity
 

docs/mkdocs/docs/api/basic_json/to_bson.md

@@ -13,7 +13,7 @@ static void to_bson(const basic_json& j, detail::output_adapter<char> o,
 ```
 
 BSON (Binary JSON) is a binary format in which zero or more ordered key/value pairs are stored as a single entity (a
-so-called document).
+so-called document). The members of an object are written in the order in which iteration visits them.
 
 1. Returns a byte vector containing the BSON serialization.
 2. Writes the BSON serialization to an output adapter.

docs/mkdocs/docs/api/byte_container_with_subtype/index.md

@@ -6,7 +6,7 @@ class byte_container_with_subtype : public BinaryType;
 ```
 
 This type extends the template parameter `BinaryType` provided to [`basic_json`](../basic_json/index.md) with a subtype
-used by BSON and MessagePack. This type exists so that the user does not have to specify a type themselves with a
+used by BSON, CBOR, and MessagePack. This type exists so that the user does not have to specify a type themselves with a
 specific naming scheme in order to override the binary type.
 
 ## Template parameters

docs/mkdocs/docs/features/binary_formats/bson.md

@@ -66,7 +66,12 @@ The library uses the following mapping from JSON values types to BSON types:
 !!! warning "Incomplete mapping"
 
     The mapping is **incomplete**, since only JSON-objects (and things contained therein) can be serialized to BSON.
-    Also, keys may not contain U+0000, since they are serialized a zero-terminated c-strings.
+    Also, keys may not contain U+0000, since they are serialized as zero-terminated C strings.
+
+!!! info "Order of object members"
+
+    The members of an object are written in the order in which iteration visits them: sorted by key for
+    [`json`](../../api/json.md), in insertion order for [`ordered_json`](../../api/ordered_json.md).
 
 !!! warning "BSON type 0x11 interoperability"
 
@@ -81,6 +86,19 @@ The library uses the following mapping from JSON values types to BSON types:
     As a result, serializing and deserializing a JSON object containing such a value produces a different JSON object,
     even though the binary data is unchanged.
 
+!!! info "Binary subtype 0x02 (old binary)"
+
+    The BSON specification defines the payload of the "binary (old)" subtype `0x02` as an int32 followed by that many
+    bytes, so the value is preceded by two lengths: the length of the binary element and, as the first four bytes of
+    the payload, the number of bytes that follow. A binary value with subtype `2` is therefore written with the outer
+    length 4 bytes larger than its size and the size as inner length: `binary({1, 2, 3}, 2)` becomes
+    `07 00 00 00 02 03 00 00 00 01 02 03`. When reading, the inner length is checked and removed, so the value
+    contains only the bytes that follow it. `from_bson()` throws
+    [`parse_error.112`](../../home/exceptions.md#jsonexceptionparse_error112) if the outer length is less than 4 or the
+    inner length is not the outer length minus 4. Versions before 3.13.0 did not write the inner length and returned
+    it as part of the payload; BSON data written by those versions with subtype 2 is not readable any more and must be
+    written again.
+
 ??? example "Example: serialize a JSON value to BSON"
 
     ```cpp
@@ -135,12 +153,29 @@ The library maps BSON record types to JSON value types as follows:
     The BSON reader is lenient in a few areas where the BSON specification is more restrictive:
 
     - array element keys are not checked against the required decimal sequence (`0`, `1`, `2`, ...),
-    - any non-zero byte is accepted as `true` for the boolean type, and
-    - the payload for binary subtype `0x02` is returned as-is, including its inner length prefix.
+    - any non-zero byte is accepted as `true` for the boolean type,
+    - the payloads of the binary subtypes `0x03` (UUID, old), `0x04` (UUID), and `0x05` (MD5) are not checked to have
+      16 bytes,
+    - duplicate keys within a document are accepted; the last value wins (`{"a": 1, "a": 2}` is read as `{"a": 2}`),
+      while a SAX handler receives every occurrence,
+    - a `string` value may contain embedded `0x00` bytes, and
+    - with `strict` set to `false`, bytes after the end of the document are ignored.
 
     If BSON input must be validated for strict specification compliance, validate it separately before passing it to
     `from_bson()`.
 
+!!! note "Document size"
+
+    Every document starts with its size. `from_bson()` rejects a document with
+    [`parse_error.112`](../../home/exceptions.md#jsonexceptionparse_error112) if the size is less than 5 (the size prefix and the terminator), if an embedded document does not end before the
+    end of the document that contains it, if the elements do not fit into the declared size, or if the size does not
+    match the number of bytes read when the terminating `0x00` byte is reached. A size that is too small is detected
+    before an element is read whose type byte and name no longer fit; an element that starts inside the declared size
+    but extends past it is read, and reported to a SAX handler, before the mismatch is found at the terminator. A size
+    that is too large is likewise found only at the terminator. Passing `strict` as `false` skips only the check for bytes after
+    the end of the document ([`parse_error.110`](../../home/exceptions.md#jsonexceptionparse_error110)), not the
+    document size checks.
+
 !!! warning "Ill-formed UTF-8 in string values"
 
     The BSON specification requires `string` values (type `0x02`) to be valid UTF-8, but this is not required of a
@@ -154,8 +189,9 @@ The library maps BSON record types to JSON value types as follows:
     ill-formed bytes. `to_bson()`'s own `error_handler` parameter defaults to `keep`, so such a string value or element
     (key) name is written unchanged; with `strict` (the default if
     [`JSON_STRICT_BINARY_UTF8`](../../api/macros/json_strict_binary_utf8.md) is enabled), it throws the same exception
-    instead. Element (key) names are never validated on read, since they are read byte-by-byte as a C string. `binary`
-    values (type `0x05`) are unaffected, since they are not required to hold text.
+    instead. Element (key) names are treated like string values: with `keep` they are read unchanged, with `strict`,
+    `replace`, or `ignore` they are checked and handled in the same way. `binary` values (type `0x05`) are unaffected,
+    since they are not required to hold text.
 
 ??? example "Example: deserialize a JSON value from BSON"
 

docs/mkdocs/docs/features/binary_formats/ubjson.md

@@ -5,11 +5,11 @@ achieve the generality of JSON, combined with being much easier to process than
 
 !!! abstract "References"
 
-    - [UBJSON Website](http://ubjson.org)
+    - [UBJSON Website](https://ubjson.org)
 
 ## Byte layout
 
-UBJSON is built from just a one-byte, human-readable ASCII *type marker* (for example, `i` for int8, `S` for string, `[` for array) followed by the payload of that type. Strings and the like are prefixed with their length, which is itself a UBJSON integer value including its marker. Numbers are stored in big-endian byte order. Containers can be written in two ways: as an *unoptimized* container that is opened with `[` or `{` and closed with `]` or `}`, or as an *optimized* container that declares an element type (`$`) and/or a count (`#`) after the opening marker, which saves per-element markers and (for a count) the closing marker.
+UBJSON is built from just a one-byte, human-readable ASCII *type marker* (for example, `i` for int8, `S` for string, `[` for array) followed by the payload of that type. Strings and the like are prefixed with their length, which is itself a UBJSON integer value including its marker. Numbers are stored in big-endian byte order. Containers can be written in two ways: as an *unoptimized* container that is opened with `[` or `{` and closed with `]` or `}`, or as an *optimized* container that declares a count (`#`) after the opening marker, optionally preceded by an element type (`$`); an element type is only allowed together with a count. An optimized container saves the closing marker and, with a type, the per-element markers.
 
 Consider the following JSON value (shown formatted for readability):
 
@@ -45,7 +45,7 @@ Consider the following JSON value (shown formatted for readability):
 The library uses the following mapping from JSON values types to UBJSON types according to the UBJSON specification:
 
 | JSON value type | value/range                               | UBJSON type                                      | marker    |
-|-----------------|-------------------------------------------|----------------|--------|
+|-----------------|-------------------------------------------|--------------------------------------------------|-----------|
 | null            | `null`                                    | null                                             | `Z`       |
 | boolean         | `true`                                    | true                                             | `T`       |
 | boolean         | `false`                                   | false                                            | `F`       |
@@ -63,10 +63,10 @@ The library uses the following mapping from JSON values types to UBJSON types ac
 | number_unsigned | 32768..2147483647                         | int32                                            | `l`       |
 | number_unsigned | 2147483648..9223372036854775807           | int64                                            | `L`       |
 | number_unsigned | 9223372036854775808..18446744073709551615 | high-precision                                   | `H`       |
-| number_float    | *any value*                               | float64        | `D`    |
+| number_float    | *any value*                               | float64 (float32 if `number_float_t` is `float`) | `D` (`d`) |
 | string          | *with shortest length indicator*          | string                                           | `S`       |
 | array           | *see notes on optimized format*           | array                                            | `[`       |
-| object          | *see notes on optimized format*           | map            | `{`    |
+| object          | *see notes on optimized format*           | object                                           | `{`       |
 
 !!! success "Complete mapping"
 
@@ -93,20 +93,27 @@ The library uses the following mapping from JSON values types to UBJSON types ac
 
     The following markers are not used in the conversion:
     
-    - `Z`: no-op values are not created.
+    - `N`: no-op values are never written (they are skipped when reading).
     - `C`: single-byte strings are serialized with `S` markers.
 
 !!! info "NaN/infinity handling"
 
-    If NaN or Infinity are stored inside a JSON number, they are serialized properly. This behavior differs from the
-    [`dump()`](../../api/basic_json/dump.md) function which serializes NaN or Infinity to `null`.
+    NaN and infinity are written as IEEE 754 float64 values (`D`) and read back unchanged. This differs from
+    [`dump()`](../../api/basic_json/dump.md), which serializes them to `null`, and from the UBJSON specification, which
+    encodes infinity as `null` (it does not mention NaN); other UBJSON readers may therefore not accept these values.
 
 !!! info "Optimized formats"
 
     The optimized formats for containers are supported: Parameter `use_size` adds size information to the beginning of a
     container and removes the closing marker. Parameter `use_type` further checks whether all elements of a container
     have the same type and adds the type marker to the beginning of the container. The `use_type` parameter must only be
-    used together with `use_size = true`.
+    used together with `use_size = true`: combining `use_type` with `use_size = false` throws
+    [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if the value contains a non-empty array,
+    object, or binary value.
+
+    Two elements have the same type if they are written with the same type marker. For example, `[1, 2]` is written with
+    the type `i`, but `[1, 200]` (`i`, `U`), `[true, false]` (`T`, `F`), and `[1, 2.5]` (`i`, `D`) are not; an empty
+    container is never given a `$` annotation of its own (an array of empty arrays is still typed `[`).
 
     Note that `use_size = true` alone may result in larger representations - the benefit of this parameter is that the
     receiving side is immediately informed on the number of elements of the container.
@@ -115,8 +122,9 @@ The library uses the following mapping from JSON values types to UBJSON types ac
     already is the value. Its declared count is therefore the only thing that decides how much memory the receiving side
     allocates, and a handful of bytes can describe billions of elements. `from_ubjson` rejects such an array with
     [`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408) when the count exceeds 1,048,576
-    (`1 << 20`), and `to_ubjson` writes longer arrays of these types without the annotation, so any value it produces
-    can be read back.
+    (`1 << 20`), and `to_ubjson` writes longer arrays of these types in the counted but untyped form: the `$` type marker is
+    dropped, the `#` count is kept, and every element is written with its own marker (`[#l 1048577 Z Z ...`), so any value
+    it produces can be read back. Objects and untyped counted arrays are not subject to this limit.
 
 !!! info "Binary values"
 
@@ -141,7 +149,7 @@ The library uses the following mapping from JSON values types to UBJSON types ac
 The library maps UBJSON types to JSON value types as follows:
 
 | UBJSON type    | JSON value type                                  | marker |
-|-------------|-----------------------------------------|--------|
+|----------------|--------------------------------------------------|--------|
 | no-op          | *no value, next value is read*                   | `N`    |
 | null           | `null`                                           | `Z`    |
 | false          | `false`                                          | `F`    |
@@ -155,12 +163,39 @@ The library maps UBJSON types to JSON value types as follows:
 | int64          | number_integer                                   | `L`    |
 | string         | string                                           | `S`    |
 | char           | string                                           | `C`    |
+| high-precision | number_unsigned, number_integer, or number_float | `H`    |
 | array          | array (optimized values are supported)           | `[`    |
 | object         | object (optimized values are supported)          | `{`    |
 
+!!! info "High-precision numbers"
+
+    The payload of `H` is a length-prefixed string that is parsed as a JSON number (surrounding whitespace is ignored).
+    Integer text in the range of `number_unsigned_t` (non-negative) or `number_integer_t` (negative) is stored as such;
+    any other valid number text (larger or smaller integers, fractions, and exponents such as `1e2`) is stored as
+    `number_float`, so precision may be lost. Text that is not a valid JSON number raises
+    [`parse_error.115`](../../home/exceptions.md#jsonexceptionparse_error115), a number outside the range of
+    `number_float_t` (`1e999`) raises [`out_of_range.406`](../../home/exceptions.md#jsonexceptionout_of_range406).
+
 !!! success "Complete mapping"
 
-    The mapping is **complete** in the sense that any UBJSON value can be converted to a JSON value.
+    Every well-formed UBJSON value can be converted to a JSON value, with these exceptions: a high-precision number
+    outside the range of `number_float_t` ([`out_of_range.406`](../../home/exceptions.md#jsonexceptionout_of_range406)),
+    an optimized array of `Z`, `T`, or `F` with more than 1,048,576 elements, and a count that exceeds the capacity of the
+    container ([`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408)). High-precision numbers that
+    do not fit an integer type are stored as floating-point numbers and may lose precision. Ill-formed input is rejected
+    with a parse error.
+
+!!! info "Duplicate object keys"
+
+    If an object contains the same key more than once, the last value is kept (the UBJSON specification does not
+    address duplicate keys).
+
+!!! info "Type marker of optimized containers"
+
+    The type marker after `$` must be one of `Z`, `N`, `T`, `F`, `i`, `U`, `I`, `l`, `L`, `d`, `D`, `H`, `C`, `S`, `[`, or
+    `{`. It is checked even if the count is 0; any other marker raises
+    [`parse_error.112`](../../home/exceptions.md#jsonexceptionparse_error112). A counted object typed `N` (`{$N#i1 ...`)
+    is not supported.
 
 !!! warning "Ill-formed UTF-8 in string values and object keys"
 

docs/mkdocs/docs/features/binary_values.md

@@ -227,7 +227,10 @@ array of integers.
 ### BSON
 
 [BSON](binary_formats/bson.md) supports binary values and subtypes. If a subtype is given, it is used and added as an
-unsigned 8-bit integer. If no subtype is given, the generic binary subtype 0x00 is used.
+unsigned 8-bit integer; a subtype above 255 throws
+[`out_of_range.415`](../home/exceptions.md#jsonexceptionout_of_range415). If no subtype is given, the generic binary
+subtype 0x00 is used. The payload of the "old binary" subtype 0x02 is preceded by a second length, which the library
+writes and removes again when reading; it is not part of the payload.
 
 ??? example "Example: serialize a binary value to BSON"
 

docs/mkdocs/docs/home/exceptions.md

@@ -330,7 +330,7 @@ where they cannot be resolved.
 ### json.exception.parse_error.110
 
 When parsing a [binary format](../features/binary_formats/index.md), the byte vector ends before the complete value has
-been read.
+been read, or (with `strict = true`) further bytes follow the value.
 
 !!! failure "Example messages"
 
@@ -1045,8 +1045,8 @@ or the encoded length for [CBOR](../features/binary_formats/cbor.md).
 The exception is also thrown for a [UBJSON](../features/binary_formats/ubjson.md) array of a type that is encoded by its
 marker alone (`Z`, `T` or `F`) whose declared count exceeds 1,048,576 (`1 << 20`). Such an array has no payload, so its
 count alone decides how much memory is allocated, and a handful of bytes would otherwise describe billions of values.
-[`to_ubjson`](../api/basic_json/to_ubjson.md) writes longer arrays of these types without the size and type annotation,
-so any value it produces can still be read back.
+[`to_ubjson`](../api/basic_json/to_ubjson.md) writes longer arrays of these types without the `$` type annotation (the `#`
+count and one marker per element are kept), so any value it produces can still be read back.
 
 !!! failure "Example messages"
 
@@ -1155,12 +1155,16 @@ A JSON Patch `move` operation's `"from"` location is a proper prefix of its `"pa
 MessagePack's ext type and BSON's binary subtype are each stored in a single byte. This exception is thrown when serializing a
 [`byte_container_with_subtype`](../api/byte_container_with_subtype/index.md) whose subtype exceeds 255, the largest value the library can store in that byte.
 
-!!! failure "Example message"
+!!! failure "Example messages"
 
     ```
     [json.exception.out_of_range.415] subtype 70000 is too large for the MessagePack ext type (max 255)
     ```
 
+    ```
+    [json.exception.out_of_range.415] subtype 70000 is too large for the BSON binary subtype (max 255)
+    ```
+
 !!! note
 
     This exception was added in version 3.13.0. Before that, subtypes above 255 were silently truncated modulo 256 instead of raising an error.
@@ -1229,7 +1233,8 @@ A JSON Patch operation 'test' failed. The unsuccessful operation is also printed
 ### json.exception.other_error.502
 
 [`to_ubjson`](../api/basic_json/to_ubjson.md) and [`to_bjdata`](../api/basic_json/to_bjdata.md) were called with
-`use_type = true` but `use_size = false`. UBJSON requires a size marker (`#`) after a type marker (`$`).
+`use_type = true` but `use_size = false` for a value that contains a non-empty array, object, or binary value. UBJSON
+requires a size marker (`#`) after a type marker (`$`); scalars and empty containers do not throw.
 
 !!! failure "Example message"
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -235,6 +235,9 @@ class binary_reader
         /// UBJSON/BJData: the type marker of an optimized container, so that
         /// its elements are read without one of their own; 0 otherwise
         char_int_type type_marker;
+        /// BSON: the position right after this document, according to the
+        /// size it declares
+        std::size_t end_position = 0;
         /// BSON: the size this document declares, in bytes
         std::int32_t declared_size = 0;
         /// whether to close this container with end_object() or end_array()
@@ -371,6 +374,23 @@ class binary_reader
             return false;
         }
 
+        // the smallest document is the size prefix and the terminator
+        if (JSON_HEDLEY_UNLIKELY(document_size < 5))
+        {
+            return bson_document_size_error("document size ", document_size, " is less than 5");
+        }
+
+        // the declared size bounds where the document ends: an embedded
+        // document must end before the terminator of the document that contains it
+        const auto unsigned_size = static_cast<std::size_t>(document_size);
+        const std::size_t document_end = unsigned_size > (std::numeric_limits<std::size_t>::max)() - document_start
+                                         ? (std::numeric_limits<std::size_t>::max)()
+                                         : document_start + unsigned_size;
+        if (JSON_HEDLEY_UNLIKELY(!container_stack.empty() && document_end >= container_stack.back().end_position))
+        {
+            return bson_document_size_error("document size ", document_size, " exceeds the size of the enclosing document");
+        }
+
         if (JSON_HEDLEY_UNLIKELY(!enter_container(is_object, detail::unknown_size())))
         {
             return false;
@@ -378,6 +398,7 @@ class binary_reader
 
         container_frame& frame = container_stack.back();
         frame.start_position = document_start;
+        frame.end_position = document_end;
         frame.declared_size = document_size;
         return true;
     }
@@ -436,6 +457,13 @@ class binary_reader
                 return false;
             }
 
+            // an element needs at least its name's terminator, and the
+            // document its own terminator, within the declared size
+            if (JSON_HEDLEY_UNLIKELY(chars_read + 2 > container_stack.back().end_position))
+            {
+                return bson_document_size_error("document size ", container_stack.back().declared_size, " is too small for its content");
+            }
+
             const std::size_t element_type_parse_position = chars_read;
             key.clear();
             if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
@@ -584,9 +612,46 @@ class binary_reader
         }
         result.set_subtype(subtype);
 
+        // the "old binary" subtype 0x02 starts with an int32 that repeats the
+        // size of the payload following it; the payload does not include it
+        if (subtype == 0x02)
+        {
+            return get_bson_old_binary(len, result);
+        }
+
         return get_binary(len, result);
     }
 
+    /*!
+    @brief Parses the payload of a BSON binary value with subtype 0x02.
+    @param[in] len  The length of the binary value, including the inner int32.
+    @param[in,out] result  A reference to the binary variable where the payload
+                           (without the inner int32) is to be stored.
+    @pre len >= 0
+    @return `true` if the inner length was present and matches @a len
+    */
+    template<typename NumberType>
+    bool get_bson_old_binary(const NumberType len, binary_t& result)
+    {
+        if (JSON_HEDLEY_UNLIKELY(len < 4))
+        {
+            return bson_length_error("length of binary subtype 0x02 must be at least 4, is ", len, "binary");
+        }
+
+        std::int32_t inner_length{};
+        if (JSON_HEDLEY_UNLIKELY((!get_number<std::int32_t, true>(inner_length))))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(static_cast<std::int64_t>(inner_length) != static_cast<std::int64_t>(len) - 4))
+        {
+            return bson_length_error("inner length of binary subtype 0x02 does not match the payload size; inner length is ", inner_length, "binary");
+        }
+
+        return get_binary(inner_length, result);
+    }
+
     /*!
     @brief Read a BSON document element of the given @a element_type.
     @param[in] element_type The BSON element type, c.f. http://bsonspec.org/spec.html
@@ -3000,6 +3065,14 @@ class binary_reader
                 return false;
             }
 
+            // validate the type marker up front: otherwise it would only be
+            // checked when an element is read, and a container with count 0
+            // would accept any marker
+            if (JSON_HEDLEY_UNLIKELY(!is_valid_optimized_type(result.second)))
+            {
+                return optimized_type_error();
+            }
+
             get_ignore_noop();
             if (JSON_HEDLEY_UNLIKELY(current != '#'))
             {
@@ -4391,6 +4464,12 @@ class binary_reader
         return last_byte_error(exception_id::unexpected_byte, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(bytes_read), ")"), "document");
     }
 
+    JSON_HEDLEY_NEVER_INLINE
+    bool bson_document_size_error(const char* prefix, const std::int32_t document_size, const char* suffix) const
+    {
+        return last_byte_error(exception_id::unexpected_byte, concat(prefix, std::to_string(document_size), suffix), "document");
+    }
+
     JSON_HEDLEY_NEVER_INLINE
     bool bson_unsupported_type_error(const std::size_t position, const char_int_type element_type) const
     {
@@ -4496,6 +4575,44 @@ class binary_reader
     std::size_t bon8_pushback_size = 0;
 
   JSON_PRIVATE_UNLESS_TESTED:
+    /*!
+    @brief check whether @a marker is a type marker that may follow '$'
+    UBJSON: Z N T F i U I l L d D H C S [ {; BJData: the numeric markers and C
+    (BJData's excluded markers are rejected separately).
+    */
+    bool is_valid_optimized_type(const char_int_type marker) const noexcept
+    {
+        switch (marker)
+        {
+            case 'i':
+            case 'U':
+            case 'I':
+            case 'l':
+            case 'L':
+            case 'd':
+            case 'D':
+            case 'C':
+                return true;
+            case 'Z':
+            case 'N':
+            case 'T':
+            case 'F':
+            case 'H':
+            case 'S':
+            case '[':
+            case '{':
+                return input_format != input_format_t::bjdata;
+            case 'B':
+            case 'u':
+            case 'm':
+            case 'M':
+            case 'h':
+                return input_format == input_format_t::bjdata;
+            default:
+                return false;
+        }
+    }
+
     /*!
     @brief whether @a marker is excluded from BJData's optimized ND-array types
     @return whether @a marker is one of 'F', 'H', 'N', 'S', 'T', 'Z', '[', '{'

include/nlohmann/detail/output/binary_writer.hpp

@@ -1684,7 +1684,15 @@ class binary_writer
             throw_subtype_out_of_range(value.subtype(), "the BSON binary subtype", j);
         }
 
-        return sizeof(std::int32_t) + value.size() + 1ul;
+        // the "old binary" subtype 0x02 repeats the payload size in an inner
+        // int32 in front of the payload
+        return sizeof(std::int32_t) + (is_bson_old_binary(value) ? sizeof(std::int32_t) : 0ul) + value.size() + 1ul;
+    }
+
+    /// @return whether @a value has the BSON subtype 0x02 ("binary (old)")
+    static bool is_bson_old_binary(const binary_t& value) noexcept
+    {
+        return value.has_subtype() && value.subtype() == 0x02;
     }
 
     /*!
@@ -1697,10 +1705,18 @@ class binary_writer
     {
         write_bson_entry_header(name, 0x05);
 
-        write_number<std::int32_t>(to_bson_length(value.size()), true);
+        const bool old_binary = is_bson_old_binary(value);
+
+        // the length field counts the inner int32 of the old binary subtype
+        write_number<std::int32_t>(to_bson_length(value.size() + (old_binary ? sizeof(std::int32_t) : 0ul)), true);
 
         write_number(value.has_subtype() ? static_cast<std::uint8_t>(value.subtype()) : static_cast<std::uint8_t>(0x00));
 
+        if (old_binary)
+        {
+            write_number<std::int32_t>(to_bson_length(value.size()), true);
+        }
+
         write_bytes(value.data(), value.size());
     }
 
@@ -1860,7 +1876,8 @@ class binary_writer
            (or the header of a string or binary value) in one reservation
     @return whether the entry was written; false for a discarded value, a
             string or binary value whose length does not fit the length
-            field, in which case nothing was written
+            field, or a binary value with subtype 0x02, in which case nothing
+            was written
     @pre    @a name is at most bson_scalar_max_name_size characters long and is
             not changed by the error handler
     */
@@ -1921,7 +1938,9 @@ class binary_writer
         if (j.is_binary())
         {
             const binary_t& value = *j.m_data.m_value.binary;
-            if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size())))
+            // the old binary subtype 0x02 has an inner length that the single
+            // reservation has no room for; write_bson_binary writes it
+            if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size()) || is_bson_old_binary(value)))
             {
                 return false;
             }

single_include/nlohmann/json.hpp

@@ -17702,6 +17702,9 @@ class binary_reader
         /// UBJSON/BJData: the type marker of an optimized container, so that
         /// its elements are read without one of their own; 0 otherwise
         char_int_type type_marker;
+        /// BSON: the position right after this document, according to the
+        /// size it declares
+        std::size_t end_position = 0;
         /// BSON: the size this document declares, in bytes
         std::int32_t declared_size = 0;
         /// whether to close this container with end_object() or end_array()
@@ -17838,6 +17841,23 @@ class binary_reader
             return false;
         }
 
+        // the smallest document is the size prefix and the terminator
+        if (JSON_HEDLEY_UNLIKELY(document_size < 5))
+        {
+            return bson_document_size_error("document size ", document_size, " is less than 5");
+        }
+
+        // the declared size bounds where the document ends: an embedded
+        // document must end before the terminator of the document that contains it
+        const auto unsigned_size = static_cast<std::size_t>(document_size);
+        const std::size_t document_end = unsigned_size > (std::numeric_limits<std::size_t>::max)() - document_start
+                                         ? (std::numeric_limits<std::size_t>::max)()
+                                         : document_start + unsigned_size;
+        if (JSON_HEDLEY_UNLIKELY(!container_stack.empty() && document_end >= container_stack.back().end_position))
+        {
+            return bson_document_size_error("document size ", document_size, " exceeds the size of the enclosing document");
+        }
+
         if (JSON_HEDLEY_UNLIKELY(!enter_container(is_object, detail::unknown_size())))
         {
             return false;
@@ -17845,6 +17865,7 @@ class binary_reader
 
         container_frame& frame = container_stack.back();
         frame.start_position = document_start;
+        frame.end_position = document_end;
         frame.declared_size = document_size;
         return true;
     }
@@ -17903,6 +17924,13 @@ class binary_reader
                 return false;
             }
 
+            // an element needs at least its name's terminator, and the
+            // document its own terminator, within the declared size
+            if (JSON_HEDLEY_UNLIKELY(chars_read + 2 > container_stack.back().end_position))
+            {
+                return bson_document_size_error("document size ", container_stack.back().declared_size, " is too small for its content");
+            }
+
             const std::size_t element_type_parse_position = chars_read;
             key.clear();
             if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
@@ -18051,9 +18079,46 @@ class binary_reader
         }
         result.set_subtype(subtype);
 
+        // the "old binary" subtype 0x02 starts with an int32 that repeats the
+        // size of the payload following it; the payload does not include it
+        if (subtype == 0x02)
+        {
+            return get_bson_old_binary(len, result);
+        }
+
         return get_binary(len, result);
     }
 
+    /*!
+    @brief Parses the payload of a BSON binary value with subtype 0x02.
+    @param[in] len  The length of the binary value, including the inner int32.
+    @param[in,out] result  A reference to the binary variable where the payload
+                           (without the inner int32) is to be stored.
+    @pre len >= 0
+    @return `true` if the inner length was present and matches @a len
+    */
+    template<typename NumberType>
+    bool get_bson_old_binary(const NumberType len, binary_t& result)
+    {
+        if (JSON_HEDLEY_UNLIKELY(len < 4))
+        {
+            return bson_length_error("length of binary subtype 0x02 must be at least 4, is ", len, "binary");
+        }
+
+        std::int32_t inner_length{};
+        if (JSON_HEDLEY_UNLIKELY((!get_number<std::int32_t, true>(inner_length))))
+        {
+            return false;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(static_cast<std::int64_t>(inner_length) != static_cast<std::int64_t>(len) - 4))
+        {
+            return bson_length_error("inner length of binary subtype 0x02 does not match the payload size; inner length is ", inner_length, "binary");
+        }
+
+        return get_binary(inner_length, result);
+    }
+
     /*!
     @brief Read a BSON document element of the given @a element_type.
     @param[in] element_type The BSON element type, c.f. http://bsonspec.org/spec.html
@@ -20467,6 +20532,14 @@ class binary_reader
                 return false;
             }
 
+            // validate the type marker up front: otherwise it would only be
+            // checked when an element is read, and a container with count 0
+            // would accept any marker
+            if (JSON_HEDLEY_UNLIKELY(!is_valid_optimized_type(result.second)))
+            {
+                return optimized_type_error();
+            }
+
             get_ignore_noop();
             if (JSON_HEDLEY_UNLIKELY(current != '#'))
             {
@@ -21858,6 +21931,12 @@ class binary_reader
         return last_byte_error(exception_id::unexpected_byte, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(bytes_read), ")"), "document");
     }
 
+    JSON_HEDLEY_NEVER_INLINE
+    bool bson_document_size_error(const char* prefix, const std::int32_t document_size, const char* suffix) const
+    {
+        return last_byte_error(exception_id::unexpected_byte, concat(prefix, std::to_string(document_size), suffix), "document");
+    }
+
     JSON_HEDLEY_NEVER_INLINE
     bool bson_unsupported_type_error(const std::size_t position, const char_int_type element_type) const
     {
@@ -21963,6 +22042,44 @@ class binary_reader
     std::size_t bon8_pushback_size = 0;
 
   JSON_PRIVATE_UNLESS_TESTED:
+    /*!
+    @brief check whether @a marker is a type marker that may follow '$'
+    UBJSON: Z N T F i U I l L d D H C S [ {; BJData: the numeric markers and C
+    (BJData's excluded markers are rejected separately).
+    */
+    bool is_valid_optimized_type(const char_int_type marker) const noexcept
+    {
+        switch (marker)
+        {
+            case 'i':
+            case 'U':
+            case 'I':
+            case 'l':
+            case 'L':
+            case 'd':
+            case 'D':
+            case 'C':
+                return true;
+            case 'Z':
+            case 'N':
+            case 'T':
+            case 'F':
+            case 'H':
+            case 'S':
+            case '[':
+            case '{':
+                return input_format != input_format_t::bjdata;
+            case 'B':
+            case 'u':
+            case 'm':
+            case 'M':
+            case 'h':
+                return input_format == input_format_t::bjdata;
+            default:
+                return false;
+        }
+    }
+
     /*!
     @brief whether @a marker is excluded from BJData's optimized ND-array types
     @return whether @a marker is one of 'F', 'H', 'N', 'S', 'T', 'Z', '[', '{'
@@ -27995,7 +28112,15 @@ class binary_writer
             throw_subtype_out_of_range(value.subtype(), "the BSON binary subtype", j);
         }
 
-        return sizeof(std::int32_t) + value.size() + 1ul;
+        // the "old binary" subtype 0x02 repeats the payload size in an inner
+        // int32 in front of the payload
+        return sizeof(std::int32_t) + (is_bson_old_binary(value) ? sizeof(std::int32_t) : 0ul) + value.size() + 1ul;
+    }
+
+    /// @return whether @a value has the BSON subtype 0x02 ("binary (old)")
+    static bool is_bson_old_binary(const binary_t& value) noexcept
+    {
+        return value.has_subtype() && value.subtype() == 0x02;
     }
 
     /*!
@@ -28008,10 +28133,18 @@ class binary_writer
     {
         write_bson_entry_header(name, 0x05);
 
-        write_number<std::int32_t>(to_bson_length(value.size()), true);
+        const bool old_binary = is_bson_old_binary(value);
+
+        // the length field counts the inner int32 of the old binary subtype
+        write_number<std::int32_t>(to_bson_length(value.size() + (old_binary ? sizeof(std::int32_t) : 0ul)), true);
 
         write_number(value.has_subtype() ? static_cast<std::uint8_t>(value.subtype()) : static_cast<std::uint8_t>(0x00));
 
+        if (old_binary)
+        {
+            write_number<std::int32_t>(to_bson_length(value.size()), true);
+        }
+
         write_bytes(value.data(), value.size());
     }
 
@@ -28171,7 +28304,8 @@ class binary_writer
            (or the header of a string or binary value) in one reservation
     @return whether the entry was written; false for a discarded value, a
             string or binary value whose length does not fit the length
-            field, in which case nothing was written
+            field, or a binary value with subtype 0x02, in which case nothing
+            was written
     @pre    @a name is at most bson_scalar_max_name_size characters long and is
             not changed by the error handler
     */
@@ -28232,7 +28366,9 @@ class binary_writer
         if (j.is_binary())
         {
             const binary_t& value = *j.m_data.m_value.binary;
-            if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size())))
+            // the old binary subtype 0x02 has an inner length that the single
+            // reservation has no room for; write_bson_binary writes it
+            if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size()) || is_bson_old_binary(value)))
             {
                 return false;
             }

tests/src/unit-bjdata.cpp

@@ -3134,7 +3134,7 @@ TEST_CASE("BJData")
                 std::vector<uint8_t> const v1 = {'[', '#', 'i', 0xF1};
                 std::vector<uint8_t> const v2 = {'[', '$', 'I', '#', 'i', 0xF2};
                 std::vector<uint8_t> const v3 = {'[', '$', 'I', '#', '[', 'i', 0xF4, 'i', 0x02, ']'};
-                std::vector<uint8_t> const v4 = {'[', '$', 0xF6, '#', 'i', 0xF7};
+                std::vector<uint8_t> const v4 = {'[', '$', 'l', '#', 'i', 0xF7};
                 std::vector<uint8_t> const v5 = {'[', '$', 'I', '#', '[', 'i', 0xF5, 'i', 0xF1, ']'};
                 std::vector<uint8_t> const v6 = {'[', '#', '[', 'i', 0xF3, 'i', 0x02, ']'};
 
@@ -3455,7 +3455,7 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(v0, true, false).is_discarded());
 
             std::vector<uint8_t> const vi = {'[', '$', '#'};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vi), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing BJData value: unexpected end of input", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vi), "[json.exception.parse_error.112] parse error at byte 3: syntax error while parsing BJData type: marker 0x23 is not a permitted optimized array type", json::parse_error&);
             CHECK(json::from_bjdata(vi, true, false).is_discarded());
 
             std::vector<uint8_t> const vU = {'[', '$', 'U'};
@@ -4622,3 +4622,60 @@ TEST_CASE("BJData large strings and binaries (chunked reader)")
         }
     }
 }
+
+TEST_CASE("BJData optimized container type marker is validated for count 0")
+{
+    // the '$' type marker must be a legal marker even if no element follows
+    SECTION("invalid marker")
+    {
+        // 'Z', 'T', 'F', 'N', 'S', 'H', '[' and '{' are excluded in BJData
+        for (const char marker :
+                {'x', 'E', 'Z', 'T', 'F', 'N', 'S', 'H', '[', '{'
+                })
+        {
+            for (const char open :
+                    {'[', '{'
+                    })
+            {
+                for (const int count :
+                        {
+                            0, 1
+                        })
+                {
+                    CAPTURE(marker)
+                    CAPTURE(open)
+                    CAPTURE(count)
+                    const std::vector<std::uint8_t> v = {static_cast<std::uint8_t>(open), '$', static_cast<std::uint8_t>(marker), '#', 'i', static_cast<std::uint8_t>(count)};
+                    json _;
+                    CHECK_THROWS_AS(_ = json::from_bjdata(v), json::parse_error&);
+                    CHECK(json::from_bjdata(v, true, false).is_discarded());
+                }
+            }
+        }
+    }
+
+    SECTION("error message")
+    {
+        const std::vector<std::uint8_t> v = {'[', '$', 'x', '#', 'i', 0};
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_bjdata(v), "[json.exception.parse_error.112] parse error at byte 3: syntax error while parsing BJData type: marker 0x78 is not a permitted optimized array type", json::parse_error&);
+    }
+
+    SECTION("valid marker")
+    {
+        for (const char marker :
+                {'i', 'U', 'I', 'u', 'l', 'm', 'L', 'M', 'h', 'd', 'D', 'C'
+                })
+        {
+            CAPTURE(marker)
+            const std::vector<std::uint8_t> va = {'[', '$', static_cast<std::uint8_t>(marker), '#', 'i', 0};
+            const std::vector<std::uint8_t> vo = {'{', '$', static_cast<std::uint8_t>(marker), '#', 'i', 0};
+            CHECK(json::from_bjdata(va) == json::array());
+            CHECK(json::from_bjdata(vo) == json::object());
+        }
+
+        // an optimized array of bytes is read as a binary value
+        const std::vector<std::uint8_t> vb = {'[', '$', 'B', '#', 'i', 0};
+        CHECK(json::from_bjdata(vb) == json::binary({}));
+    }
+}

tests/src/unit-bson.cpp

@@ -802,12 +802,11 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
-        SECTION("binary member with subtype 0x02 (old binary) keeps its inner length prefix (lenient parsing)")
+        SECTION("binary member with subtype 0x02 (old binary) carries an inner length")
         {
-            // documented lenient behavior (see gh-5333): the payload for
-            // binary subtype 0x02 ("old binary") is returned as-is,
-            // including its own inner 4-byte length prefix; it is not
-            // stripped or reinterpreted
+            // the payload of binary subtype 0x02 ("old binary") starts with an
+            // int32 that repeats the payload size; the bytes below are what
+            // pymongo and the bson-corpus (binary.json) use
             std::vector<std::uint8_t> const input =
             {
                 0x17, 0x00, 0x00, 0x00, // size (little endian)
@@ -815,16 +814,87 @@ TEST_CASE("BSON")
 
                 0x06, 0x00, 0x00, 0x00, // size of binary (little endian)
                 0x02, // "old binary" subtype
-                0x02, 0x00, 0x00, 0x00, // inner length prefix (part of the old-binary payload)
+                0x02, 0x00, 0x00, 0x00, // inner length
                 0x68, 0x69, // payload ('h', 'i')
 
                 0x00 // end marker
             };
 
-            // the inner length prefix is part of the (unmodified) payload
-            const std::vector<std::uint8_t> expected_payload = {0x02, 0x00, 0x00, 0x00, 0x68, 0x69};
-            const json expected = { { "entry", json::binary(expected_payload, 0x02) } };
+            // the inner length is not part of the payload
+            const json expected = { { "entry", json::binary({0x68, 0x69}, 0x02) } };
             CHECK(json::from_bson(input) == expected);
+            CHECK(json::to_bson(expected) == input);
+            CHECK(json::from_bson(json::to_bson(expected)) == expected);
+        }
+
+        SECTION("binary member with subtype 0x02 (old binary) and empty payload")
+        {
+            std::vector<std::uint8_t> const input =
+            {
+                0x15, 0x00, 0x00, 0x00, // size (little endian)
+                0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
+                0x04, 0x00, 0x00, 0x00, // size of binary (little endian)
+                0x02, // "old binary" subtype
+                0x00, 0x00, 0x00, 0x00, // inner length
+                0x00 // end marker
+            };
+
+            const json expected = { { "entry", json::binary({}, 0x02) } };
+            CHECK(json::from_bson(input) == expected);
+            CHECK(json::to_bson(expected) == input);
+        }
+
+        SECTION("binary member with subtype 0x02 (old binary) with an invalid inner length")
+        {
+            std::vector<std::uint8_t> input =
+            {
+                0x17, 0x00, 0x00, 0x00, // size (little endian)
+                0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
+                0x06, 0x00, 0x00, 0x00, // size of binary (little endian)
+                0x02, // "old binary" subtype
+                0x02, 0x00, 0x00, 0x00, // inner length
+                0x68, 0x69, // payload ('h', 'i')
+                0x00 // end marker
+            };
+
+            SECTION("inner length too long")
+            {
+                input[19] = 0x03;
+            }
+
+            SECTION("inner length too short")
+            {
+                input[19] = 0x01;
+            }
+
+            SECTION("inner length negative")
+            {
+                input[19] = 0xFF;
+                input[20] = 0xFF;
+                input[21] = 0xFF;
+                input[22] = 0xFF;
+            }
+
+            CAPTURE(input)
+            json _;
+            CHECK_THROWS_AS(_ = json::from_bson(input), json::parse_error&);
+        }
+
+        SECTION("binary member with subtype 0x02 (old binary) without an inner length")
+        {
+            // the payload is shorter than the inner length field
+            std::vector<std::uint8_t> const input =
+            {
+                0x14, 0x00, 0x00, 0x00, // size (little endian)
+                0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
+                0x03, 0x00, 0x00, 0x00, // size of binary (little endian)
+                0x02, // "old binary" subtype
+                0x01, 0x02, 0x03, // payload without an inner length
+                0x00 // end marker
+            };
+
+            json _;
+            CHECK_THROWS_AS(_ = json::from_bson(input), json::parse_error&);
         }
 
         SECTION("Some more complex document")
@@ -1178,7 +1248,7 @@ TEST_CASE("BSON document size mismatch")
     SECTION("top-level document with a negative size")
     {
         std::vector<std::uint8_t> const input = {0xFF, 0xFF, 0xFF, 0xFF, 0x00};
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size -1 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 4: syntax error while parsing BSON document: document size -1 is less than 5", json::parse_error&);
         CHECK(json::from_bson(input, true, false).is_discarded());
     }
 
@@ -1190,7 +1260,7 @@ TEST_CASE("BSON document size mismatch")
         // enclosing document instead of "d"
         std::vector<std::uint8_t> const input =
         {
-            0x00, 0x00, 0x00, 0x00, // outer size
+            0x14, 0x00, 0x00, 0x00, // outer size
             0x03, 'd', 0x00,        // entry: embedded document "d"
             0xFF, 0xFF, 0xFF, 0x7F, //   embedded size 0x7FFFFFFF
             0x0A, 'a', 0x00,        //   entry: null "a"
@@ -1198,7 +1268,24 @@ TEST_CASE("BSON document size mismatch")
             0x08, 'h', 0x00, 0x01,  // entry: bool "h" = true
             0x00                    // outer end marker
         };
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 15: syntax error while parsing BSON document: document size 2147483647 does not match the number of bytes read (8)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 11: syntax error while parsing BSON document: document size 2147483647 exceeds the size of the enclosing document", json::parse_error&);
+        CHECK(json::from_bson(input, true, false).is_discarded());
+    }
+
+    SECTION("embedded document whose size is smaller than its content")
+    {
+        // {"a":null} is 8 bytes, but the length prefix claims 7
+        std::vector<std::uint8_t> const input =
+        {
+            0x14, 0x00, 0x00, 0x00, // outer size
+            0x03, 'd', 0x00,        // entry: embedded document "d"
+            0x07, 0x00, 0x00, 0x00, //   embedded size 7 (real is 8)
+            0x0A, 'a', 0x00,        //   entry: null "a"
+            0x00,                   //   embedded end marker
+            0x08, 'h', 0x00, 0x01,  // entry: bool "h" = true
+            0x00                    // outer end marker
+        };
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 15: syntax error while parsing BSON document: document size 7 does not match the number of bytes read (8)", json::parse_error&);
         CHECK(json::from_bson(input, true, false).is_discarded());
     }
 
@@ -1207,18 +1294,163 @@ TEST_CASE("BSON document size mismatch")
         // array [42] is 12 bytes, but the length prefix claims 13
         std::vector<std::uint8_t> const input =
         {
-            0x00, 0x00, 0x00, 0x00, // outer size
+            0x14, 0x00, 0x00, 0x00, // outer size
             0x04, 'a', 0x00,        // entry: array "a"
             0x0D, 0x00, 0x00, 0x00, //   array size 13 (real is 12)
             0x10, '0', 0x00, 0x2A, 0x00, 0x00, 0x00, //   entry: int32 "0" = 42
             0x00,                   //   array end marker
             0x00                    // outer end marker
         };
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 19: syntax error while parsing BSON document: document size 13 does not match the number of bytes read (12)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 11: syntax error while parsing BSON document: document size 13 exceeds the size of the enclosing document", json::parse_error&);
         CHECK(json::from_bson(input, true, false).is_discarded());
     }
 }
 
+TEST_CASE("BSON declared document size bounds the content")
+{
+    // records the events that a SAX parser receives
+    struct recorder : nlohmann::json_sax<json>
+    {
+        std::string events {};
+
+        bool null() override
+        {
+            events += "null ";
+            return true;
+        }
+        bool boolean(bool /*val*/) override
+        {
+            events += "boolean ";
+            return true;
+        }
+        bool number_integer(json::number_integer_t /*val*/) override
+        {
+            events += "integer ";
+            return true;
+        }
+        bool number_unsigned(json::number_unsigned_t /*val*/) override
+        {
+            events += "unsigned ";
+            return true;
+        }
+        bool number_float(json::number_float_t /*val*/, const std::string& /*s*/) override
+        {
+            events += "float ";
+            return true;
+        }
+        bool string(std::string& /*val*/) override
+        {
+            events += "string ";
+            return true;
+        }
+        bool binary(json::binary_t& /*val*/) override
+        {
+            events += "binary ";
+            return true;
+        }
+        bool start_object(std::size_t /*elements*/) override
+        {
+            events += "{ ";
+            return true;
+        }
+        bool key(std::string& /*val*/) override
+        {
+            events += "key ";
+            return true;
+        }
+        bool end_object() override
+        {
+            events += "} ";
+            return true;
+        }
+        bool start_array(std::size_t /*elements*/) override
+        {
+            events += "[ ";
+            return true;
+        }
+        bool end_array() override
+        {
+            events += "] ";
+            return true;
+        }
+        bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& /*ex*/) override
+        {
+            events += "error ";
+            return false;
+        }
+    };
+
+    SECTION("the content of a too small document is not reported")
+    {
+        // {"a":1} is 12 bytes; the length prefix claims 5, so the element
+        // does not fit
+        std::vector<std::uint8_t> const input =
+        {
+            0x05, 0x00, 0x00, 0x00,
+            0x10, 'a', 0x00, 0x01, 0x00, 0x00, 0x00,
+            0x00
+        };
+        recorder rec;
+        CHECK(!json::sax_parse(input, &rec, json::input_format_t::bson));
+        CHECK(rec.events == "{ error ");
+
+        // also without strict mode
+        recorder rec2;
+        CHECK(!json::sax_parse(input, &rec2, json::input_format_t::bson, false));
+        CHECK(rec2.events == "{ error ");
+    }
+
+    SECTION("an embedded document that does not fit its parent is not opened")
+    {
+        // the embedded document ends where the enclosing one does, so there
+        // is no room for the terminator of the enclosing document
+        std::vector<std::uint8_t> const input =
+        {
+            0x0C, 0x00, 0x00, 0x00,
+            0x03, 'd', 0x00,
+            0x05, 0x00, 0x00, 0x00, 0x00,
+            0x00
+        };
+        recorder rec;
+        CHECK(!json::sax_parse(input, &rec, json::input_format_t::bson));
+        CHECK(rec.events == "{ key error ");
+    }
+
+    SECTION("an embedded document that fits exactly")
+    {
+        std::vector<std::uint8_t> const input =
+        {
+            0x0D, 0x00, 0x00, 0x00,
+            0x03, 'd', 0x00,
+            0x05, 0x00, 0x00, 0x00, 0x00,
+            0x00
+        };
+        CHECK(json::from_bson(input) == json({{"d", json::object()}}));
+    }
+
+    SECTION("a document size that is less than 5")
+    {
+        for (const std::int32_t size :
+                {
+                    0, 1, 4, -1, (std::numeric_limits<std::int32_t>::min)()
+                })
+        {
+            CAPTURE(size)
+            std::vector<std::uint8_t> input =
+            {
+                0x00, 0x00, 0x00, 0x00, 0x00
+            };
+            input[0] = static_cast<std::uint8_t>(size & 0xFF);
+            input[1] = static_cast<std::uint8_t>((size >> 8) & 0xFF);
+            input[2] = static_cast<std::uint8_t>((size >> 16) & 0xFF);
+            input[3] = static_cast<std::uint8_t>((size >> 24) & 0xFF);
+            json _;
+            CHECK_THROWS_AS(_ = json::from_bson(input), json::parse_error&);
+            CHECK(json::from_bson(input, true, false).is_discarded());
+        }
+    }
+}
+
 TEST_CASE("BSON nesting does not consume the call stack")
 {
     // An embedded document or array used to be read by calling back into the
@@ -1923,7 +2155,7 @@ TEST_CASE("Invalid document size handling")
     {
         std::vector<std::uint8_t> const v = {0x04, 0x00, 0x00, 0x00, 0x00};
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 4 does not match the number of bytes read (5)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 4: syntax error while parsing BSON document: document size 4 is less than 5", json::parse_error&);
         CHECK(json::from_bson(v, true, false).is_discarded());
     }
 
@@ -1938,7 +2170,7 @@ TEST_CASE("Invalid document size handling")
             0x00
         };
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 16: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (16)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 5 is too small for its content", json::parse_error&);
         CHECK(json::from_bson(v, true, false).is_discarded());
     }
 
@@ -1969,7 +2201,7 @@ TEST_CASE("Invalid document size handling")
             0x00                                            // object terminator
         };
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 19: syntax error while parsing BSON document: document size 5 does not match the number of bytes read (12)", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 12: syntax error while parsing BSON document: document size 5 is too small for its content", json::parse_error&);
         CHECK(json::from_bson(v, true, false).is_discarded());
     }
 

tests/src/unit-ubjson.cpp

@@ -2023,7 +2023,7 @@ TEST_CASE("UBJSON")
             CHECK(json::from_ubjson(v0, true, false).is_discarded());
 
             std::vector<uint8_t> const vi = {'[', '$', '#'};
-            CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vi), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing UBJSON value: unexpected end of input", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vi), "[json.exception.parse_error.112] parse error at byte 3: syntax error while parsing UBJSON type: marker 0x23 is not a permitted optimized array type", json::parse_error&);
             CHECK(json::from_ubjson(vi, true, false).is_discarded());
 
             std::vector<uint8_t> const vT = {'[', '$', 'T'};
@@ -3348,3 +3348,55 @@ TEST_CASE("UBJSON large strings (chunked reader)")
         }
     }
 }
+
+TEST_CASE("UBJSON optimized container type marker is validated for count 0")
+{
+    // the '$' type marker must be a legal marker even if no element follows
+    SECTION("invalid marker")
+    {
+        for (const char marker :
+                {'x', 'E', 'B', 'u', 'm', 'M', 'h'
+                })
+        {
+            for (const char open :
+                    {'[', '{'
+                    })
+            {
+                for (const int count :
+                        {
+                            0, 1
+                        })
+                {
+                    CAPTURE(marker)
+                    CAPTURE(open)
+                    CAPTURE(count)
+                    const std::vector<std::uint8_t> v = {static_cast<std::uint8_t>(open), '$', static_cast<std::uint8_t>(marker), '#', 'i', static_cast<std::uint8_t>(count)};
+                    json _;
+                    CHECK_THROWS_AS(_ = json::from_ubjson(v), json::parse_error&);
+                    CHECK(json::from_ubjson(v, true, false).is_discarded());
+                }
+            }
+        }
+    }
+
+    SECTION("error message")
+    {
+        const std::vector<std::uint8_t> v = {'[', '$', 'x', '#', 'i', 0};
+        json _;
+        CHECK_THROWS_WITH_AS(_ = json::from_ubjson(v), "[json.exception.parse_error.112] parse error at byte 3: syntax error while parsing UBJSON type: marker 0x78 is not a permitted optimized array type", json::parse_error&);
+    }
+
+    SECTION("valid marker")
+    {
+        for (const char marker :
+                {'Z', 'N', 'T', 'F', 'i', 'U', 'I', 'l', 'L', 'd', 'D', 'H', 'C', 'S', '[', '{'
+                })
+        {
+            CAPTURE(marker)
+            const std::vector<std::uint8_t> va = {'[', '$', static_cast<std::uint8_t>(marker), '#', 'i', 0};
+            const std::vector<std::uint8_t> vo = {'{', '$', static_cast<std::uint8_t>(marker), '#', 'i', 0};
+            CHECK(json::from_ubjson(va) == json::array());
+            CHECK(json::from_ubjson(vo) == json::object());
+        }
+    }
+}