mirror of
https://github.com/nlohmann/json.git
synced 2026-09-07 08:47:57 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
450fc8dce7 | ||
|
|
3a186c4570 | ||
|
|
d82ab21724 | ||
|
|
3bb551f46f |
@@ -69,12 +69,6 @@ The library uses the following mapping from JSON values types to UBJSON types ac
|
||||
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.
|
||||
|
||||
An array whose type marker is `Z` (null), `T` (true) or `F` (false) stores no payload at all, because the marker
|
||||
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, and
|
||||
`to_ubjson` writes longer arrays of these types without the annotation, so any value it produces can be read back.
|
||||
|
||||
!!! info "Binary values"
|
||||
|
||||
If the JSON data contains the binary type, the value stored is a list of integers, as suggested by the UBJSON
|
||||
|
||||
@@ -868,12 +868,6 @@ The size of an array or object in a [binary format](../features/binary_formats/i
|
||||
the size following `#` for [UBJSON](../features/binary_formats/ubjson.md)/[BJData](../features/binary_formats/bjdata.md),
|
||||
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. 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.
|
||||
|
||||
!!! failure "Example messages"
|
||||
|
||||
```
|
||||
@@ -885,9 +879,6 @@ so any value it produces can still be read back.
|
||||
```
|
||||
[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size
|
||||
```
|
||||
```
|
||||
[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size
|
||||
```
|
||||
|
||||
### json.exception.out_of_range.409
|
||||
|
||||
|
||||
@@ -58,26 +58,6 @@ inline bool little_endianness(int num = 1) noexcept
|
||||
return *reinterpret_cast<char*>(&num) == 1;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief largest element count accepted for a UBJSON container of a valueless type
|
||||
|
||||
An element of type 'Z' (null), 'T' (true) or 'F' (false) is encoded by its
|
||||
type marker alone, so an optimized container of one of those types has no
|
||||
payload at all and its declared count is the only thing that decides how much
|
||||
is allocated: `[$Z#L` followed by a large count turns some ten bytes of input
|
||||
into that many values (see #2793, which reports 35 GB and 150 seconds). Every
|
||||
other type costs at least one byte per element and is bounded by the end of
|
||||
the input.
|
||||
|
||||
This is a sanity bound rather than a security boundary, and it is far above
|
||||
any container met in practice. @ref binary_writer falls back to the
|
||||
unoptimized encoding for longer containers, so that a value serialized by
|
||||
this library can always be read back.
|
||||
|
||||
@sa https://github.com/nlohmann/json/issues/2793
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 20;
|
||||
|
||||
///////////////////
|
||||
// binary reader //
|
||||
///////////////////
|
||||
@@ -130,7 +110,6 @@ class binary_reader
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
|
||||
{
|
||||
sax = sax_;
|
||||
container_stack.clear();
|
||||
bool result = false;
|
||||
|
||||
switch (format)
|
||||
@@ -180,69 +159,6 @@ class binary_reader
|
||||
}
|
||||
|
||||
private:
|
||||
////////////////////////
|
||||
// nested containers //
|
||||
////////////////////////
|
||||
|
||||
/*!
|
||||
@brief a container that has been opened and not closed yet
|
||||
|
||||
The binary readers do not call themselves once per nesting level. Like
|
||||
@ref parser::sax_parse_internal, which does the same for JSON text, they
|
||||
keep the containers they are inside of on a heap-allocated stack, so that
|
||||
the native call stack does not grow with the nesting depth of the input
|
||||
and a deeply nested value is bounded by memory rather than by the stack
|
||||
(see #5104).
|
||||
|
||||
The members are ordered by decreasing alignment, which is the ordering that
|
||||
keeps a struct from growing as members are added to it.
|
||||
*/
|
||||
struct container_frame
|
||||
{
|
||||
container_frame(const std::size_t remaining_, const bool is_object_) noexcept
|
||||
: remaining(remaining_), is_object(is_object_) {}
|
||||
|
||||
/// number of elements that have not been read yet
|
||||
std::size_t remaining;
|
||||
/// whether to close this container with end_object() or end_array()
|
||||
bool is_object;
|
||||
};
|
||||
|
||||
/*!
|
||||
@brief open a nested array or object
|
||||
|
||||
Emits the SAX start event and records the container. This is the only
|
||||
place the binary readers start a container, so a check that rejects one
|
||||
can be made here and is then guaranteed to run before the start event.
|
||||
|
||||
@param[in] is_object whether an object (true) or an array (false) begins
|
||||
@param[in] len number of elements the container declares
|
||||
|
||||
@return whether the SAX parser accepted the start event
|
||||
*/
|
||||
bool enter_container(const bool is_object, const std::size_t len)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->start_object(len) : !sax->start_array(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
container_stack.emplace_back(len, is_object);
|
||||
return true;
|
||||
}
|
||||
|
||||
/// @copydoc enter_container
|
||||
bool enter_array(const std::size_t len)
|
||||
{
|
||||
return enter_container(/*is_object*/false, len);
|
||||
}
|
||||
|
||||
/// @copydoc enter_container
|
||||
bool enter_object(const std::size_t len)
|
||||
{
|
||||
return enter_container(/*is_object*/true, len);
|
||||
}
|
||||
|
||||
//////////
|
||||
// BSON //
|
||||
//////////
|
||||
@@ -1080,21 +996,23 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a definite-length CBOR string
|
||||
@brief reads a CBOR string
|
||||
|
||||
Reads everything @ref get_cbor_string accepts except the indefinite-length
|
||||
form, which that function handles itself. The bytes are appended to @a
|
||||
result, so consecutive chunks of an indefinite-length string can be read
|
||||
into the same string.
|
||||
This function first reads starting bytes to determine the expected
|
||||
string length and then copies this number of bytes into a string.
|
||||
Additionally, CBOR's strings with indefinite lengths are supported.
|
||||
|
||||
@param[out] result string the bytes are appended to
|
||||
@param[out] result created string
|
||||
|
||||
@return whether string creation completed
|
||||
|
||||
@pre @a current is not EOF
|
||||
*/
|
||||
bool get_cbor_string_chunk(string_t& result)
|
||||
bool get_cbor_string(string_t& result)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
switch (current)
|
||||
{
|
||||
// UTF-8 string (0x00..0x17 bytes follow)
|
||||
@@ -1150,6 +1068,20 @@ class binary_reader
|
||||
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
|
||||
}
|
||||
|
||||
case 0x7F: // UTF-8 string (indefinite length)
|
||||
{
|
||||
while (get() != 0xFF)
|
||||
{
|
||||
string_t chunk;
|
||||
if (!get_cbor_string(chunk))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
result.append(chunk);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
default:
|
||||
{
|
||||
auto last_token = get_token_string();
|
||||
@@ -1160,82 +1092,23 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a CBOR string
|
||||
@brief reads a CBOR byte array
|
||||
|
||||
This function first reads starting bytes to determine the expected
|
||||
string length and then copies this number of bytes into a string.
|
||||
Additionally, CBOR's strings with indefinite lengths are supported.
|
||||
byte array length and then copies this number of bytes into the byte array.
|
||||
Additionally, CBOR's byte arrays with indefinite lengths are supported.
|
||||
|
||||
@param[out] result created string
|
||||
|
||||
@return whether string creation completed
|
||||
*/
|
||||
bool get_cbor_string(string_t& result)
|
||||
{
|
||||
// number of indefinite-length strings that have been opened and not
|
||||
// closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
|
||||
// but this reader has always accepted it, so the open levels are
|
||||
// counted instead of recursed through, which overflowed the stack for
|
||||
// an input of repeated 0x7F bytes (see #5104). Every chunk is appended
|
||||
// to the same result, so no per-level state is needed.
|
||||
std::size_t open = 0;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (current == 0x7F) // UTF-8 string (indefinite length)
|
||||
{
|
||||
++open;
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
// a break marker closes the innermost indefinite-length string;
|
||||
// outside of one it is not a string and falls through to the error
|
||||
if (open != 0 && current == 0xFF)
|
||||
{
|
||||
if (--open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
get();
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a definite-length CBOR byte array
|
||||
|
||||
Reads everything @ref get_cbor_binary accepts except the indefinite-length
|
||||
form, which that function handles itself. The bytes are appended to @a
|
||||
result, so consecutive chunks of an indefinite-length byte array can be
|
||||
read into the same byte array.
|
||||
|
||||
@param[out] result byte array the bytes are appended to
|
||||
@param[out] result created byte array
|
||||
|
||||
@return whether byte array creation completed
|
||||
|
||||
@pre @a current is not EOF
|
||||
*/
|
||||
bool get_cbor_binary_chunk(binary_t& result)
|
||||
bool get_cbor_binary(binary_t& result)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
switch (current)
|
||||
{
|
||||
// Binary data (0x00..0x17 bytes follow)
|
||||
@@ -1295,6 +1168,20 @@ class binary_reader
|
||||
get_binary(input_format_t::cbor, len, result);
|
||||
}
|
||||
|
||||
case 0x5F: // Binary data (indefinite length)
|
||||
{
|
||||
while (get() != 0xFF)
|
||||
{
|
||||
binary_t chunk;
|
||||
if (!get_cbor_binary(chunk))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
result.insert(result.end(), chunk.begin(), chunk.end());
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
default:
|
||||
{
|
||||
auto last_token = get_token_string();
|
||||
@@ -1304,63 +1191,6 @@ class binary_reader
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a CBOR byte array
|
||||
|
||||
This function first reads starting bytes to determine the expected
|
||||
byte array length and then copies this number of bytes into the byte array.
|
||||
Additionally, CBOR's byte arrays with indefinite lengths are supported.
|
||||
|
||||
@param[out] result created byte array
|
||||
|
||||
@return whether byte array creation completed
|
||||
*/
|
||||
bool get_cbor_binary(binary_t& result)
|
||||
{
|
||||
// the open indefinite-length byte arrays are counted rather than
|
||||
// recursed through, for the reason given in @ref get_cbor_string
|
||||
std::size_t open = 0;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (current == 0x5F) // Binary data (indefinite length)
|
||||
{
|
||||
++open;
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
// a break marker closes the innermost indefinite-length byte
|
||||
// array; outside of one it falls through to the error below
|
||||
if (open != 0 && current == 0xFF)
|
||||
{
|
||||
if (--open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
get();
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief narrow a definite CBOR array/map length to std::size_t
|
||||
|
||||
@@ -1486,17 +1316,7 @@ class binary_reader
|
||||
/*!
|
||||
@return whether a valid MessagePack value was passed to the SAX parser
|
||||
*/
|
||||
/*!
|
||||
@brief read one MessagePack value
|
||||
|
||||
Reads a single value and passes it to the SAX parser. A value that begins
|
||||
a container is not read to its end: the container is opened with
|
||||
@ref enter_container and its elements are read by
|
||||
@ref parse_msgpack_internal, so that nesting does not consume native stack.
|
||||
|
||||
@return whether reading the value succeeded
|
||||
*/
|
||||
bool parse_msgpack_value()
|
||||
bool parse_msgpack_internal()
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
@@ -1652,7 +1472,7 @@ class binary_reader
|
||||
case 0x8D:
|
||||
case 0x8E:
|
||||
case 0x8F:
|
||||
return enter_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
return get_msgpack_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
|
||||
// fixarray
|
||||
case 0x90:
|
||||
@@ -1671,7 +1491,7 @@ class binary_reader
|
||||
case 0x9D:
|
||||
case 0x9E:
|
||||
case 0x9F:
|
||||
return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
return get_msgpack_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
|
||||
// fixstr
|
||||
case 0xA0:
|
||||
@@ -1802,25 +1622,25 @@ class binary_reader
|
||||
case 0xDC: // array 16
|
||||
{
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_array(static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDD: // array 32
|
||||
{
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_array(conditional_static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_array(conditional_static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDE: // map 16
|
||||
{
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_object(static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDF: // map 32
|
||||
{
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_object(conditional_static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_object(conditional_static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
// negative fixint
|
||||
@@ -2068,69 +1888,55 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief read a MessagePack value and everything nested inside it
|
||||
|
||||
Reads values until the one that was begun here is complete, resuming the
|
||||
enclosing container each time an element ends, so that the nesting depth
|
||||
of the input costs heap rather than native stack (see #5104).
|
||||
|
||||
@return whether reading the value succeeded
|
||||
@param[in] len the length of the array
|
||||
@return whether array creation completed
|
||||
*/
|
||||
bool parse_msgpack_internal()
|
||||
bool get_msgpack_array(const std::size_t len)
|
||||
{
|
||||
// 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;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (!container_stack.empty())
|
||||
{
|
||||
// copied out before anything can push onto the stack and
|
||||
// invalidate a reference into it
|
||||
const bool is_object = container_stack.back().is_object;
|
||||
|
||||
if (container_stack.back().remaining == 0)
|
||||
{
|
||||
container_stack.pop_back();
|
||||
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
// the value begun here is complete once its container is
|
||||
if (container_stack.empty())
|
||||
|
||||
for (std::size_t i = 0; i < len; ++i)
|
||||
{
|
||||
return true;
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// claim the element about to be read
|
||||
--container_stack.back().remaining;
|
||||
return sax->end_array();
|
||||
}
|
||||
|
||||
if (is_object)
|
||||
/*!
|
||||
@param[in] len the length of the object
|
||||
@return whether object creation completed
|
||||
*/
|
||||
bool get_msgpack_object(const std::size_t len)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
string_t key;
|
||||
for (std::size_t i = 0; i < len; ++i)
|
||||
{
|
||||
get();
|
||||
key.clear();
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_value()))
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
key.clear();
|
||||
}
|
||||
|
||||
// a value that opened a container left it on the stack; one that
|
||||
// did not, and that was not inside a container, was the whole value
|
||||
if (container_stack.empty())
|
||||
{
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return sax->end_object();
|
||||
}
|
||||
|
||||
////////////
|
||||
@@ -2585,12 +2391,7 @@ class binary_reader
|
||||
{
|
||||
result.first = npos; // size
|
||||
result.second = 0; // type
|
||||
// seed the flag with the caller's context: inside an ndarray dimension
|
||||
// vector another ndarray is not allowed, and get_ubjson_size_value()
|
||||
// rejects it up front instead of reading it and reporting afterwards.
|
||||
// Seeding it with `false` made every '#' of a "[#[#[..." chain descend
|
||||
// another level, which overflowed the stack (see #5104).
|
||||
bool is_ndarray = inside_ndarray;
|
||||
bool is_ndarray = false;
|
||||
|
||||
get_ignore_noop();
|
||||
|
||||
@@ -2623,11 +2424,13 @@ class binary_reader
|
||||
}
|
||||
|
||||
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
|
||||
// an ndarray was read here only if the flag flipped; when it was
|
||||
// seeded true, get_ubjson_size_value() already rejected the nested
|
||||
// dimension vector
|
||||
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
|
||||
if (input_format == input_format_t::bjdata && is_ndarray)
|
||||
{
|
||||
if (inside_ndarray)
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
|
||||
exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
|
||||
}
|
||||
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
|
||||
}
|
||||
return is_error;
|
||||
@@ -2636,7 +2439,7 @@ class binary_reader
|
||||
if (current == '#')
|
||||
{
|
||||
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
|
||||
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
|
||||
if (input_format == input_format_t::bjdata && is_ndarray)
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
|
||||
exception_message(input_format, "ndarray requires both type and size", "size"), nullptr));
|
||||
@@ -2907,17 +2710,6 @@ class binary_reader
|
||||
|
||||
if (size_and_type.first != npos)
|
||||
{
|
||||
// reading an element of a valueless type consumes no input, so the
|
||||
// declared count alone decides how much is allocated; the check is
|
||||
// made before the start event so that no container is opened that
|
||||
// is then abandoned. See @ref max_valueless_container_size.
|
||||
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
|
||||
&& size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
|
||||
exception_message(input_format, "excessive array size", "size"), nullptr));
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_array(size_and_type.first)))
|
||||
{
|
||||
return false;
|
||||
@@ -3435,9 +3227,6 @@ class binary_reader
|
||||
/// the SAX parser
|
||||
json_sax_t* sax = nullptr;
|
||||
|
||||
/// the containers that have been opened and not closed yet; see @ref container_frame
|
||||
std::vector<container_frame> container_stack{};
|
||||
|
||||
// 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', '[', '{')
|
||||
|
||||
@@ -826,17 +826,7 @@ class binary_writer
|
||||
|
||||
std::vector<CharType> bjdx = {'[', '{', 'S', 'H', 'T', 'F', 'N', 'Z'}; // excluded markers in bjdata optimized type
|
||||
|
||||
// an optimized array of a valueless type carries no payload, so a
|
||||
// reader has nothing but the declared count to bound the allocation
|
||||
// by and refuses an excessive one. Write the unoptimized form for
|
||||
// those, at one byte per element, so the result can be read back.
|
||||
// Objects are not affected: every element is preceded by its key.
|
||||
const bool valueless_type = (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
const bool excessive_valueless = valueless_type
|
||||
&& j.m_data.m_value.array->size() > detail::max_valueless_container_size;
|
||||
|
||||
if (same_prefix && !excessive_valueless
|
||||
&& !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
|
||||
if (same_prefix && !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
|
||||
{
|
||||
prefix_required = false;
|
||||
oa->write_character(to_char_type('$'));
|
||||
|
||||
+147
-82
@@ -3573,6 +3573,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
{
|
||||
using std::swap;
|
||||
swap(*(m_data.m_value.array), other);
|
||||
set_parents();
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -3589,6 +3590,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
{
|
||||
using std::swap;
|
||||
swap(*(m_data.m_value.object), other);
|
||||
set_parents();
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -4473,11 +4475,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -4493,11 +4492,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -4522,11 +4518,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in MessagePack format
|
||||
@@ -4540,11 +4533,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -4559,11 +4549,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -4586,11 +4573,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in UBJSON format
|
||||
@@ -4604,11 +4588,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -4623,11 +4604,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -4650,11 +4628,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BJData format
|
||||
@@ -4668,11 +4643,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -4687,11 +4659,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BSON format
|
||||
@@ -4705,11 +4674,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -4724,11 +4690,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -4751,11 +4714,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
/// @}
|
||||
|
||||
@@ -5199,21 +5159,96 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
|
||||
case value_t::object:
|
||||
{
|
||||
// first pass: traverse this object's elements
|
||||
// first pass: record, for every source key, whether it is
|
||||
// common to both objects (in source's iteration order) or
|
||||
// was deleted (i.e., in source but not in target) -- this is
|
||||
// a by-product of the target.find() call already needed to
|
||||
// tell the two cases apart, so it adds no extra lookups. The
|
||||
// "remove" ops themselves are emitted later, interleaved
|
||||
// with the recursive per-key diffs in the fast path below,
|
||||
// to match source's original iteration order (as the
|
||||
// original, pre-reordering-aware implementation did) instead
|
||||
// of grouping all removes before all recursive diffs.
|
||||
std::vector<typename object_t::key_type> common_keys_source_order;
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
// escape the key name to be used in a JSON patch
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
|
||||
if (target.find(it.key()) != target.end())
|
||||
{
|
||||
// recursive call to compare object values at key it
|
||||
auto temp_diff = diff(it.value(), target[it.key()], path_key);
|
||||
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
|
||||
common_keys_source_order.push_back(it.key());
|
||||
}
|
||||
}
|
||||
|
||||
// second pass: find keys that were added (i.e., in target but
|
||||
// not in source), and record the keys common to both, in
|
||||
// target's iteration order -- again a by-product of the
|
||||
// source.find() call already needed to detect added keys. At
|
||||
// the same time, determine whether every added key comes
|
||||
// after every common key in target's order (a precondition
|
||||
// for the fast path below, which only ever appends new keys
|
||||
// at the very end): for an object_t whose iteration order is
|
||||
// a pure function of the key set (e.g. the default std::map,
|
||||
// which always iterates in sorted key order), the order
|
||||
// check further below is always true and this whole
|
||||
// mechanism is effectively a no-op; it only matters for a
|
||||
// reorderable object_t such as the one backing `ordered_json`.
|
||||
// patch ops for keys that were added (i.e., in target but not
|
||||
// in source); built here so the fast path below can reuse
|
||||
// them without a second source.find() per target key. Only
|
||||
// used by the fast path -- the slow (reordering) path
|
||||
// rebuilds "add" ops for every key itself.
|
||||
std::vector<typename object_t::key_type> common_keys_target_order;
|
||||
basic_json added_ops(value_t::array);
|
||||
bool new_keys_form_suffix = true;
|
||||
bool seen_new_key = false;
|
||||
for (auto it = target.cbegin(); it != target.cend(); ++it)
|
||||
{
|
||||
if (source.find(it.key()) == source.end())
|
||||
{
|
||||
seen_new_key = true;
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
added_ops.push_back(
|
||||
{
|
||||
{"op", "add"}, {"path", path_key},
|
||||
{"value", it.value()}
|
||||
});
|
||||
}
|
||||
else
|
||||
{
|
||||
// found a key that is not in o -> remove it
|
||||
common_keys_target_order.push_back(it.key());
|
||||
if (seen_new_key)
|
||||
{
|
||||
new_keys_form_suffix = false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
|
||||
{
|
||||
// fast path: order of common keys already matches (or the
|
||||
// object_t's iteration order does not depend on
|
||||
// insertion history), so a plain per-key recursive diff
|
||||
// is correct and minimal, as before. common_keys_source_order
|
||||
// is, by construction, the subsequence of source's keys
|
||||
// that are common to both objects, in source's iteration
|
||||
// order -- so it can be walked in lockstep with `source`
|
||||
// using a cheap key comparison instead of another lookup.
|
||||
// Deleted keys (those source keys not in common_keys_source_order)
|
||||
// are interleaved here too, in source's original order, to
|
||||
// match the historical (pre-reordering-aware) output order.
|
||||
auto common_it = common_keys_source_order.cbegin();
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
|
||||
{
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
auto temp_diff = diff(it.value(), target[it.key()], path_key);
|
||||
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
|
||||
++common_it;
|
||||
}
|
||||
else
|
||||
{
|
||||
// found a key that is not in target -> remove it
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(object(
|
||||
{
|
||||
{"op", "remove"}, {"path", path_key}
|
||||
@@ -5221,12 +5256,42 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
}
|
||||
}
|
||||
|
||||
// second pass: traverse other object's elements
|
||||
// append the "add" ops for brand-new keys collected above
|
||||
// during the pass over target -- no second source.find()
|
||||
// per target key needed
|
||||
result.insert(result.end(), added_ops.begin(), added_ops.end());
|
||||
}
|
||||
else
|
||||
{
|
||||
// slow path: the common keys are in a different relative
|
||||
// order in source and target (only possible for a
|
||||
// reorderable object_t like ordered_map). Building a
|
||||
// minimal reordering patch is a nontrivial (LCS-like)
|
||||
// problem; instead, remove every source key -- both
|
||||
// deleted keys (which must be removed regardless) and
|
||||
// common keys (removed so they can be re-added in
|
||||
// target's order) -- and re-add every key that should
|
||||
// remain, with its final target value, in target's
|
||||
// order. basic_json::patch()'s "add" operation on an
|
||||
// object uses operator[], which appends at the end for a
|
||||
// vector-backed insertion-ordered map when the key does
|
||||
// not already exist -- so removing a key and then adding
|
||||
// it moves it to the end, fixing its position.
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(object(
|
||||
{
|
||||
{"op", "remove"}, {"path", path_key}
|
||||
}));
|
||||
}
|
||||
|
||||
// add every key that is either common (just removed
|
||||
// above) or brand new, in target's iteration order, so
|
||||
// that the final order after applying the patch matches
|
||||
// target exactly
|
||||
for (auto it = target.cbegin(); it != target.cend(); ++it)
|
||||
{
|
||||
if (source.find(it.key()) == source.end())
|
||||
{
|
||||
// found a key that is not in this -> add it
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(
|
||||
{
|
||||
|
||||
+240
-396
@@ -10745,26 +10745,6 @@ inline bool little_endianness(int num = 1) noexcept
|
||||
return *reinterpret_cast<char*>(&num) == 1;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief largest element count accepted for a UBJSON container of a valueless type
|
||||
|
||||
An element of type 'Z' (null), 'T' (true) or 'F' (false) is encoded by its
|
||||
type marker alone, so an optimized container of one of those types has no
|
||||
payload at all and its declared count is the only thing that decides how much
|
||||
is allocated: `[$Z#L` followed by a large count turns some ten bytes of input
|
||||
into that many values (see #2793, which reports 35 GB and 150 seconds). Every
|
||||
other type costs at least one byte per element and is bounded by the end of
|
||||
the input.
|
||||
|
||||
This is a sanity bound rather than a security boundary, and it is far above
|
||||
any container met in practice. @ref binary_writer falls back to the
|
||||
unoptimized encoding for longer containers, so that a value serialized by
|
||||
this library can always be read back.
|
||||
|
||||
@sa https://github.com/nlohmann/json/issues/2793
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 20;
|
||||
|
||||
///////////////////
|
||||
// binary reader //
|
||||
///////////////////
|
||||
@@ -10817,7 +10797,6 @@ class binary_reader
|
||||
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
|
||||
{
|
||||
sax = sax_;
|
||||
container_stack.clear();
|
||||
bool result = false;
|
||||
|
||||
switch (format)
|
||||
@@ -10867,69 +10846,6 @@ class binary_reader
|
||||
}
|
||||
|
||||
private:
|
||||
////////////////////////
|
||||
// nested containers //
|
||||
////////////////////////
|
||||
|
||||
/*!
|
||||
@brief a container that has been opened and not closed yet
|
||||
|
||||
The binary readers do not call themselves once per nesting level. Like
|
||||
@ref parser::sax_parse_internal, which does the same for JSON text, they
|
||||
keep the containers they are inside of on a heap-allocated stack, so that
|
||||
the native call stack does not grow with the nesting depth of the input
|
||||
and a deeply nested value is bounded by memory rather than by the stack
|
||||
(see #5104).
|
||||
|
||||
The members are ordered by decreasing alignment, which is the ordering that
|
||||
keeps a struct from growing as members are added to it.
|
||||
*/
|
||||
struct container_frame
|
||||
{
|
||||
container_frame(const std::size_t remaining_, const bool is_object_) noexcept
|
||||
: remaining(remaining_), is_object(is_object_) {}
|
||||
|
||||
/// number of elements that have not been read yet
|
||||
std::size_t remaining;
|
||||
/// whether to close this container with end_object() or end_array()
|
||||
bool is_object;
|
||||
};
|
||||
|
||||
/*!
|
||||
@brief open a nested array or object
|
||||
|
||||
Emits the SAX start event and records the container. This is the only
|
||||
place the binary readers start a container, so a check that rejects one
|
||||
can be made here and is then guaranteed to run before the start event.
|
||||
|
||||
@param[in] is_object whether an object (true) or an array (false) begins
|
||||
@param[in] len number of elements the container declares
|
||||
|
||||
@return whether the SAX parser accepted the start event
|
||||
*/
|
||||
bool enter_container(const bool is_object, const std::size_t len)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->start_object(len) : !sax->start_array(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
container_stack.emplace_back(len, is_object);
|
||||
return true;
|
||||
}
|
||||
|
||||
/// @copydoc enter_container
|
||||
bool enter_array(const std::size_t len)
|
||||
{
|
||||
return enter_container(/*is_object*/false, len);
|
||||
}
|
||||
|
||||
/// @copydoc enter_container
|
||||
bool enter_object(const std::size_t len)
|
||||
{
|
||||
return enter_container(/*is_object*/true, len);
|
||||
}
|
||||
|
||||
//////////
|
||||
// BSON //
|
||||
//////////
|
||||
@@ -11767,21 +11683,23 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a definite-length CBOR string
|
||||
@brief reads a CBOR string
|
||||
|
||||
Reads everything @ref get_cbor_string accepts except the indefinite-length
|
||||
form, which that function handles itself. The bytes are appended to @a
|
||||
result, so consecutive chunks of an indefinite-length string can be read
|
||||
into the same string.
|
||||
This function first reads starting bytes to determine the expected
|
||||
string length and then copies this number of bytes into a string.
|
||||
Additionally, CBOR's strings with indefinite lengths are supported.
|
||||
|
||||
@param[out] result string the bytes are appended to
|
||||
@param[out] result created string
|
||||
|
||||
@return whether string creation completed
|
||||
|
||||
@pre @a current is not EOF
|
||||
*/
|
||||
bool get_cbor_string_chunk(string_t& result)
|
||||
bool get_cbor_string(string_t& result)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
switch (current)
|
||||
{
|
||||
// UTF-8 string (0x00..0x17 bytes follow)
|
||||
@@ -11837,6 +11755,20 @@ class binary_reader
|
||||
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
|
||||
}
|
||||
|
||||
case 0x7F: // UTF-8 string (indefinite length)
|
||||
{
|
||||
while (get() != 0xFF)
|
||||
{
|
||||
string_t chunk;
|
||||
if (!get_cbor_string(chunk))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
result.append(chunk);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
default:
|
||||
{
|
||||
auto last_token = get_token_string();
|
||||
@@ -11847,82 +11779,23 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a CBOR string
|
||||
@brief reads a CBOR byte array
|
||||
|
||||
This function first reads starting bytes to determine the expected
|
||||
string length and then copies this number of bytes into a string.
|
||||
Additionally, CBOR's strings with indefinite lengths are supported.
|
||||
byte array length and then copies this number of bytes into the byte array.
|
||||
Additionally, CBOR's byte arrays with indefinite lengths are supported.
|
||||
|
||||
@param[out] result created string
|
||||
|
||||
@return whether string creation completed
|
||||
*/
|
||||
bool get_cbor_string(string_t& result)
|
||||
{
|
||||
// number of indefinite-length strings that have been opened and not
|
||||
// closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
|
||||
// but this reader has always accepted it, so the open levels are
|
||||
// counted instead of recursed through, which overflowed the stack for
|
||||
// an input of repeated 0x7F bytes (see #5104). Every chunk is appended
|
||||
// to the same result, so no per-level state is needed.
|
||||
std::size_t open = 0;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (current == 0x7F) // UTF-8 string (indefinite length)
|
||||
{
|
||||
++open;
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
// a break marker closes the innermost indefinite-length string;
|
||||
// outside of one it is not a string and falls through to the error
|
||||
if (open != 0 && current == 0xFF)
|
||||
{
|
||||
if (--open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
get();
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a definite-length CBOR byte array
|
||||
|
||||
Reads everything @ref get_cbor_binary accepts except the indefinite-length
|
||||
form, which that function handles itself. The bytes are appended to @a
|
||||
result, so consecutive chunks of an indefinite-length byte array can be
|
||||
read into the same byte array.
|
||||
|
||||
@param[out] result byte array the bytes are appended to
|
||||
@param[out] result created byte array
|
||||
|
||||
@return whether byte array creation completed
|
||||
|
||||
@pre @a current is not EOF
|
||||
*/
|
||||
bool get_cbor_binary_chunk(binary_t& result)
|
||||
bool get_cbor_binary(binary_t& result)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
switch (current)
|
||||
{
|
||||
// Binary data (0x00..0x17 bytes follow)
|
||||
@@ -11982,6 +11855,20 @@ class binary_reader
|
||||
get_binary(input_format_t::cbor, len, result);
|
||||
}
|
||||
|
||||
case 0x5F: // Binary data (indefinite length)
|
||||
{
|
||||
while (get() != 0xFF)
|
||||
{
|
||||
binary_t chunk;
|
||||
if (!get_cbor_binary(chunk))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
result.insert(result.end(), chunk.begin(), chunk.end());
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
default:
|
||||
{
|
||||
auto last_token = get_token_string();
|
||||
@@ -11991,63 +11878,6 @@ class binary_reader
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief reads a CBOR byte array
|
||||
|
||||
This function first reads starting bytes to determine the expected
|
||||
byte array length and then copies this number of bytes into the byte array.
|
||||
Additionally, CBOR's byte arrays with indefinite lengths are supported.
|
||||
|
||||
@param[out] result created byte array
|
||||
|
||||
@return whether byte array creation completed
|
||||
*/
|
||||
bool get_cbor_binary(binary_t& result)
|
||||
{
|
||||
// the open indefinite-length byte arrays are counted rather than
|
||||
// recursed through, for the reason given in @ref get_cbor_string
|
||||
std::size_t open = 0;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (current == 0x5F) // Binary data (indefinite length)
|
||||
{
|
||||
++open;
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
// a break marker closes the innermost indefinite-length byte
|
||||
// array; outside of one it falls through to the error below
|
||||
if (open != 0 && current == 0xFF)
|
||||
{
|
||||
if (--open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
get();
|
||||
continue;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (open == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
get();
|
||||
}
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief narrow a definite CBOR array/map length to std::size_t
|
||||
|
||||
@@ -12173,17 +12003,7 @@ class binary_reader
|
||||
/*!
|
||||
@return whether a valid MessagePack value was passed to the SAX parser
|
||||
*/
|
||||
/*!
|
||||
@brief read one MessagePack value
|
||||
|
||||
Reads a single value and passes it to the SAX parser. A value that begins
|
||||
a container is not read to its end: the container is opened with
|
||||
@ref enter_container and its elements are read by
|
||||
@ref parse_msgpack_internal, so that nesting does not consume native stack.
|
||||
|
||||
@return whether reading the value succeeded
|
||||
*/
|
||||
bool parse_msgpack_value()
|
||||
bool parse_msgpack_internal()
|
||||
{
|
||||
switch (get())
|
||||
{
|
||||
@@ -12339,7 +12159,7 @@ class binary_reader
|
||||
case 0x8D:
|
||||
case 0x8E:
|
||||
case 0x8F:
|
||||
return enter_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
return get_msgpack_object(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
|
||||
// fixarray
|
||||
case 0x90:
|
||||
@@ -12358,7 +12178,7 @@ class binary_reader
|
||||
case 0x9D:
|
||||
case 0x9E:
|
||||
case 0x9F:
|
||||
return enter_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
return get_msgpack_array(conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
|
||||
|
||||
// fixstr
|
||||
case 0xA0:
|
||||
@@ -12489,25 +12309,25 @@ class binary_reader
|
||||
case 0xDC: // array 16
|
||||
{
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_array(static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_array(static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDD: // array 32
|
||||
{
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_array(conditional_static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_array(conditional_static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDE: // map 16
|
||||
{
|
||||
std::uint16_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_object(static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_object(static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
case 0xDF: // map 32
|
||||
{
|
||||
std::uint32_t len{};
|
||||
return get_number(input_format_t::msgpack, len) && enter_object(conditional_static_cast<std::size_t>(len));
|
||||
return get_number(input_format_t::msgpack, len) && get_msgpack_object(conditional_static_cast<std::size_t>(len));
|
||||
}
|
||||
|
||||
// negative fixint
|
||||
@@ -12755,69 +12575,55 @@ class binary_reader
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief read a MessagePack value and everything nested inside it
|
||||
|
||||
Reads values until the one that was begun here is complete, resuming the
|
||||
enclosing container each time an element ends, so that the nesting depth
|
||||
of the input costs heap rather than native stack (see #5104).
|
||||
|
||||
@return whether reading the value succeeded
|
||||
@param[in] len the length of the array
|
||||
@return whether array creation completed
|
||||
*/
|
||||
bool parse_msgpack_internal()
|
||||
bool get_msgpack_array(const std::size_t len)
|
||||
{
|
||||
// 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;
|
||||
|
||||
while (true)
|
||||
{
|
||||
if (!container_stack.empty())
|
||||
{
|
||||
// copied out before anything can push onto the stack and
|
||||
// invalidate a reference into it
|
||||
const bool is_object = container_stack.back().is_object;
|
||||
|
||||
if (container_stack.back().remaining == 0)
|
||||
{
|
||||
container_stack.pop_back();
|
||||
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_array(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
// the value begun here is complete once its container is
|
||||
if (container_stack.empty())
|
||||
|
||||
for (std::size_t i = 0; i < len; ++i)
|
||||
{
|
||||
return true;
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// claim the element about to be read
|
||||
--container_stack.back().remaining;
|
||||
return sax->end_array();
|
||||
}
|
||||
|
||||
if (is_object)
|
||||
/*!
|
||||
@param[in] len the length of the object
|
||||
@return whether object creation completed
|
||||
*/
|
||||
bool get_msgpack_object(const std::size_t len)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_object(len)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
string_t key;
|
||||
for (std::size_t i = 0; i < len; ++i)
|
||||
{
|
||||
get();
|
||||
key.clear();
|
||||
if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_value()))
|
||||
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_internal()))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
key.clear();
|
||||
}
|
||||
|
||||
// a value that opened a container left it on the stack; one that
|
||||
// did not, and that was not inside a container, was the whole value
|
||||
if (container_stack.empty())
|
||||
{
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return sax->end_object();
|
||||
}
|
||||
|
||||
////////////
|
||||
@@ -13272,12 +13078,7 @@ class binary_reader
|
||||
{
|
||||
result.first = npos; // size
|
||||
result.second = 0; // type
|
||||
// seed the flag with the caller's context: inside an ndarray dimension
|
||||
// vector another ndarray is not allowed, and get_ubjson_size_value()
|
||||
// rejects it up front instead of reading it and reporting afterwards.
|
||||
// Seeding it with `false` made every '#' of a "[#[#[..." chain descend
|
||||
// another level, which overflowed the stack (see #5104).
|
||||
bool is_ndarray = inside_ndarray;
|
||||
bool is_ndarray = false;
|
||||
|
||||
get_ignore_noop();
|
||||
|
||||
@@ -13310,11 +13111,13 @@ class binary_reader
|
||||
}
|
||||
|
||||
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
|
||||
// an ndarray was read here only if the flag flipped; when it was
|
||||
// seeded true, get_ubjson_size_value() already rejected the nested
|
||||
// dimension vector
|
||||
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
|
||||
if (input_format == input_format_t::bjdata && is_ndarray)
|
||||
{
|
||||
if (inside_ndarray)
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
|
||||
exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
|
||||
}
|
||||
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
|
||||
}
|
||||
return is_error;
|
||||
@@ -13323,7 +13126,7 @@ class binary_reader
|
||||
if (current == '#')
|
||||
{
|
||||
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
|
||||
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
|
||||
if (input_format == input_format_t::bjdata && is_ndarray)
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
|
||||
exception_message(input_format, "ndarray requires both type and size", "size"), nullptr));
|
||||
@@ -13594,17 +13397,6 @@ class binary_reader
|
||||
|
||||
if (size_and_type.first != npos)
|
||||
{
|
||||
// reading an element of a valueless type consumes no input, so the
|
||||
// declared count alone decides how much is allocated; the check is
|
||||
// made before the start event so that no container is opened that
|
||||
// is then abandoned. See @ref max_valueless_container_size.
|
||||
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
|
||||
&& size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
|
||||
exception_message(input_format, "excessive array size", "size"), nullptr));
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!sax->start_array(size_and_type.first)))
|
||||
{
|
||||
return false;
|
||||
@@ -14122,9 +13914,6 @@ class binary_reader
|
||||
/// the SAX parser
|
||||
json_sax_t* sax = nullptr;
|
||||
|
||||
/// the containers that have been opened and not closed yet; see @ref container_frame
|
||||
std::vector<container_frame> container_stack{};
|
||||
|
||||
// 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', '[', '{')
|
||||
@@ -18045,17 +17834,7 @@ class binary_writer
|
||||
|
||||
std::vector<CharType> bjdx = {'[', '{', 'S', 'H', 'T', 'F', 'N', 'Z'}; // excluded markers in bjdata optimized type
|
||||
|
||||
// an optimized array of a valueless type carries no payload, so a
|
||||
// reader has nothing but the declared count to bound the allocation
|
||||
// by and refuses an excessive one. Write the unoptimized form for
|
||||
// those, at one byte per element, so the result can be read back.
|
||||
// Objects are not affected: every element is preceded by its key.
|
||||
const bool valueless_type = (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
const bool excessive_valueless = valueless_type
|
||||
&& j.m_data.m_value.array->size() > detail::max_valueless_container_size;
|
||||
|
||||
if (same_prefix && !excessive_valueless
|
||||
&& !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
|
||||
if (same_prefix && !(use_bjdata && std::find(bjdx.begin(), bjdx.end(), first_prefix) != bjdx.end()))
|
||||
{
|
||||
prefix_required = false;
|
||||
oa->write_character(to_char_type('$'));
|
||||
@@ -25222,6 +25001,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
{
|
||||
using std::swap;
|
||||
swap(*(m_data.m_value.array), other);
|
||||
set_parents();
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -25238,6 +25018,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
{
|
||||
using std::swap;
|
||||
swap(*(m_data.m_value.object), other);
|
||||
set_parents();
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -26122,11 +25903,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -26142,11 +25920,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -26171,11 +25946,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in MessagePack format
|
||||
@@ -26189,11 +25961,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -26208,11 +25977,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -26235,11 +26001,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in UBJSON format
|
||||
@@ -26253,11 +26016,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -26272,11 +26032,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -26299,11 +26056,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BJData format
|
||||
@@ -26317,11 +26071,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -26336,11 +26087,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BSON format
|
||||
@@ -26354,11 +26102,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
/// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
|
||||
@@ -26373,11 +26118,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
@@ -26400,11 +26142,8 @@ 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]
|
||||
{
|
||||
result = value_t::discarded;
|
||||
}
|
||||
return result;
|
||||
const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
|
||||
return res ? result : basic_json(value_t::discarded);
|
||||
}
|
||||
/// @}
|
||||
|
||||
@@ -26848,21 +26587,96 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
|
||||
case value_t::object:
|
||||
{
|
||||
// first pass: traverse this object's elements
|
||||
// first pass: record, for every source key, whether it is
|
||||
// common to both objects (in source's iteration order) or
|
||||
// was deleted (i.e., in source but not in target) -- this is
|
||||
// a by-product of the target.find() call already needed to
|
||||
// tell the two cases apart, so it adds no extra lookups. The
|
||||
// "remove" ops themselves are emitted later, interleaved
|
||||
// with the recursive per-key diffs in the fast path below,
|
||||
// to match source's original iteration order (as the
|
||||
// original, pre-reordering-aware implementation did) instead
|
||||
// of grouping all removes before all recursive diffs.
|
||||
std::vector<typename object_t::key_type> common_keys_source_order;
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
// escape the key name to be used in a JSON patch
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
|
||||
if (target.find(it.key()) != target.end())
|
||||
{
|
||||
// recursive call to compare object values at key it
|
||||
auto temp_diff = diff(it.value(), target[it.key()], path_key);
|
||||
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
|
||||
common_keys_source_order.push_back(it.key());
|
||||
}
|
||||
}
|
||||
|
||||
// second pass: find keys that were added (i.e., in target but
|
||||
// not in source), and record the keys common to both, in
|
||||
// target's iteration order -- again a by-product of the
|
||||
// source.find() call already needed to detect added keys. At
|
||||
// the same time, determine whether every added key comes
|
||||
// after every common key in target's order (a precondition
|
||||
// for the fast path below, which only ever appends new keys
|
||||
// at the very end): for an object_t whose iteration order is
|
||||
// a pure function of the key set (e.g. the default std::map,
|
||||
// which always iterates in sorted key order), the order
|
||||
// check further below is always true and this whole
|
||||
// mechanism is effectively a no-op; it only matters for a
|
||||
// reorderable object_t such as the one backing `ordered_json`.
|
||||
// patch ops for keys that were added (i.e., in target but not
|
||||
// in source); built here so the fast path below can reuse
|
||||
// them without a second source.find() per target key. Only
|
||||
// used by the fast path -- the slow (reordering) path
|
||||
// rebuilds "add" ops for every key itself.
|
||||
std::vector<typename object_t::key_type> common_keys_target_order;
|
||||
basic_json added_ops(value_t::array);
|
||||
bool new_keys_form_suffix = true;
|
||||
bool seen_new_key = false;
|
||||
for (auto it = target.cbegin(); it != target.cend(); ++it)
|
||||
{
|
||||
if (source.find(it.key()) == source.end())
|
||||
{
|
||||
seen_new_key = true;
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
added_ops.push_back(
|
||||
{
|
||||
{"op", "add"}, {"path", path_key},
|
||||
{"value", it.value()}
|
||||
});
|
||||
}
|
||||
else
|
||||
{
|
||||
// found a key that is not in o -> remove it
|
||||
common_keys_target_order.push_back(it.key());
|
||||
if (seen_new_key)
|
||||
{
|
||||
new_keys_form_suffix = false;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
|
||||
{
|
||||
// fast path: order of common keys already matches (or the
|
||||
// object_t's iteration order does not depend on
|
||||
// insertion history), so a plain per-key recursive diff
|
||||
// is correct and minimal, as before. common_keys_source_order
|
||||
// is, by construction, the subsequence of source's keys
|
||||
// that are common to both objects, in source's iteration
|
||||
// order -- so it can be walked in lockstep with `source`
|
||||
// using a cheap key comparison instead of another lookup.
|
||||
// Deleted keys (those source keys not in common_keys_source_order)
|
||||
// are interleaved here too, in source's original order, to
|
||||
// match the historical (pre-reordering-aware) output order.
|
||||
auto common_it = common_keys_source_order.cbegin();
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
|
||||
{
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
auto temp_diff = diff(it.value(), target[it.key()], path_key);
|
||||
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
|
||||
++common_it;
|
||||
}
|
||||
else
|
||||
{
|
||||
// found a key that is not in target -> remove it
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(object(
|
||||
{
|
||||
{"op", "remove"}, {"path", path_key}
|
||||
@@ -26870,12 +26684,42 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
|
||||
}
|
||||
}
|
||||
|
||||
// second pass: traverse other object's elements
|
||||
// append the "add" ops for brand-new keys collected above
|
||||
// during the pass over target -- no second source.find()
|
||||
// per target key needed
|
||||
result.insert(result.end(), added_ops.begin(), added_ops.end());
|
||||
}
|
||||
else
|
||||
{
|
||||
// slow path: the common keys are in a different relative
|
||||
// order in source and target (only possible for a
|
||||
// reorderable object_t like ordered_map). Building a
|
||||
// minimal reordering patch is a nontrivial (LCS-like)
|
||||
// problem; instead, remove every source key -- both
|
||||
// deleted keys (which must be removed regardless) and
|
||||
// common keys (removed so they can be re-added in
|
||||
// target's order) -- and re-add every key that should
|
||||
// remain, with its final target value, in target's
|
||||
// order. basic_json::patch()'s "add" operation on an
|
||||
// object uses operator[], which appends at the end for a
|
||||
// vector-backed insertion-ordered map when the key does
|
||||
// not already exist -- so removing a key and then adding
|
||||
// it moves it to the end, fixing its position.
|
||||
for (auto it = source.cbegin(); it != source.cend(); ++it)
|
||||
{
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(object(
|
||||
{
|
||||
{"op", "remove"}, {"path", path_key}
|
||||
}));
|
||||
}
|
||||
|
||||
// add every key that is either common (just removed
|
||||
// above) or brand new, in target's iteration order, so
|
||||
// that the final order after applying the patch matches
|
||||
// target exactly
|
||||
for (auto it = target.cbegin(); it != target.cend(); ++it)
|
||||
{
|
||||
if (source.find(it.key()) == source.end())
|
||||
{
|
||||
// found a key that is not in this -> add it
|
||||
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
|
||||
result.push_back(
|
||||
{
|
||||
|
||||
@@ -3288,10 +3288,8 @@ TEST_CASE("BJData")
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR1), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vR1, true, false).is_discarded());
|
||||
|
||||
// a dimension vector that opens another one is rejected where the
|
||||
// nested '[' is read, rather than after it has been descended into
|
||||
std::vector<uint8_t> const vR2 = {'[', '$', 'i', '#', '[', '#', '[', 'i', 1, ']', ']', 1};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 11: syntax error while parsing BJData size: expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x5D", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vR2, true, false).is_discarded());
|
||||
|
||||
std::vector<uint8_t> const vR3 = {'[', '#', '[', 'i', '2', 'i', 2, ']'};
|
||||
@@ -3299,7 +3297,7 @@ TEST_CASE("BJData")
|
||||
CHECK(json::from_bjdata(vR3, true, false).is_discarded());
|
||||
|
||||
std::vector<uint8_t> const vR4 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', 1, ']', 1};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BJData number: unexpected end of input", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vR4, true, false).is_discarded());
|
||||
|
||||
std::vector<uint8_t> const vR5 = {'[', '$', 'i', '#', '[', '[', '[', ']', ']', ']'};
|
||||
@@ -3307,25 +3305,12 @@ TEST_CASE("BJData")
|
||||
CHECK(json::from_bjdata(vR5, true, false).is_discarded());
|
||||
|
||||
std::vector<uint8_t> const vR6 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.112] parse error at byte 14: syntax error while parsing BJData size: ndarray can not be recursive", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vR6, true, false).is_discarded());
|
||||
|
||||
std::vector<uint8_t> const vH = {'[', 'H', '[', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vH), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vH, true, false).is_discarded());
|
||||
|
||||
// Every "#[" of this chain used to open another dimension vector
|
||||
// and cost several stack frames before anything was rejected, so a
|
||||
// long enough chain crashed the process (see #5104). The nested
|
||||
// vector is refused where it is read, so the length is irrelevant.
|
||||
std::vector<uint8_t> vRdeep = {'['};
|
||||
for (std::size_t i = 0; i < 100000; ++i)
|
||||
{
|
||||
vRdeep.push_back('#');
|
||||
vRdeep.push_back('[');
|
||||
}
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vRdeep), "[json.exception.parse_error.113] parse error at byte 5: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
|
||||
CHECK(json::from_bjdata(vRdeep, true, false).is_discarded());
|
||||
}
|
||||
|
||||
SECTION("objects")
|
||||
|
||||
@@ -2035,58 +2035,6 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
|
||||
{
|
||||
// Reading an indefinite-length string or byte array used to call itself
|
||||
// once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
|
||||
// the call stack before any of the input was rejected. The open levels are
|
||||
// counted now, and the levels below prove the reader still reads the same
|
||||
// values and reports the same errors at the same byte offsets.
|
||||
json _;
|
||||
|
||||
SECTION("many open levels are reported, not crashed on")
|
||||
{
|
||||
const std::vector<uint8_t> input(200000, 0x7F);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
|
||||
CHECK(json::from_cbor(input, true, false).is_discarded());
|
||||
}
|
||||
|
||||
SECTION("many open levels are reported, not crashed on (binary)")
|
||||
{
|
||||
const std::vector<uint8_t> input(200000, 0x5F);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
|
||||
CHECK(json::from_cbor(input, true, false).is_discarded());
|
||||
}
|
||||
|
||||
SECTION("chunks are still concatenated")
|
||||
{
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
|
||||
// nested indefinite-length strings are concatenated across levels
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
|
||||
}
|
||||
|
||||
SECTION("chunks are still concatenated (binary)")
|
||||
{
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
|
||||
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
|
||||
}
|
||||
|
||||
SECTION("a chunk that is not a string is still rejected")
|
||||
{
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
|
||||
}
|
||||
|
||||
SECTION("a break marker outside an indefinite-length string is not a string")
|
||||
{
|
||||
// 0xFF only closes a string that was opened; on its own it is not one
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("CBOR roundtrips" * doctest::skip())
|
||||
{
|
||||
SECTION("input from flynn")
|
||||
|
||||
@@ -273,5 +273,36 @@ TEST_CASE("Regression tests for extended diagnostics")
|
||||
CHECK(j1["numbers"]["two"] == 2);
|
||||
CHECK(j1["string"] == "t");
|
||||
}
|
||||
|
||||
SECTION("Regression test - swap(array_t&)/swap(object_t&) must update JSON_DIAGNOSTICS parent pointers")
|
||||
{
|
||||
// swap(array_t&)
|
||||
{
|
||||
json j = json::array();
|
||||
json::array_t arr = {json::array({1})};
|
||||
j.swap(arr);
|
||||
|
||||
// parent pointers of the moved-in elements must point into j, not
|
||||
// into the now-defunct free-standing array_t
|
||||
CHECK_THROWS_WITH_AS(j[0][0].get<std::string>(), "[json.exception.type_error.302] (/0/0) type must be string, but is number", json::type_error);
|
||||
|
||||
// must not trigger assert_invariant() in a debug/assert-enabled build
|
||||
json const k = j;
|
||||
CHECK(k == j);
|
||||
}
|
||||
|
||||
// swap(object_t&)
|
||||
{
|
||||
json o = json::object();
|
||||
json::object_t obj = {{"a", json::array({1})}};
|
||||
o.swap(obj);
|
||||
|
||||
CHECK_THROWS_WITH_AS(o["a"][0].get<std::string>(), "[json.exception.type_error.302] (/a/0) type must be string, but is number", json::type_error);
|
||||
|
||||
// must not trigger assert_invariant() in a debug/assert-enabled build
|
||||
json const p = o;
|
||||
CHECK(p == o);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1598,67 +1598,6 @@ TEST_CASE("MessagePack")
|
||||
}
|
||||
|
||||
// use this testcase outside [hide] to run it with Valgrind
|
||||
TEST_CASE("MessagePack nesting does not consume the call stack")
|
||||
{
|
||||
// Reading a container used to call back into the value reader once per
|
||||
// element, so the native call stack grew with the nesting depth of the
|
||||
// input: one frame per byte for repeated 0x91 (a one-element array), which
|
||||
// crashes the process long before the input is exhausted (#5104). The
|
||||
// containers are kept on a heap stack now.
|
||||
//
|
||||
// Note that deeply nested values must not be compared, copied or dumped
|
||||
// here: those operations are still recursive, and would reintroduce the
|
||||
// very crash this checks for. Depth is measured by descending instead.
|
||||
|
||||
SECTION("an unterminated chain is reported, not crashed on")
|
||||
{
|
||||
json _;
|
||||
const std::vector<uint8_t> input(300000, 0x91);
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_msgpack(input), "[json.exception.parse_error.110] parse error at byte 300001: syntax error while parsing MessagePack value: unexpected end of input", json::parse_error&);
|
||||
CHECK(json::from_msgpack(input, true, false).is_discarded());
|
||||
}
|
||||
|
||||
SECTION("a well-formed deep value is read through the SAX interface")
|
||||
{
|
||||
std::vector<uint8_t> input(300000, 0x91);
|
||||
input.push_back(0x01); // innermost value
|
||||
|
||||
SaxCountdown accept_all(600001);
|
||||
CHECK(json::sax_parse(input, &accept_all, json::input_format_t::msgpack));
|
||||
}
|
||||
|
||||
SECTION("a well-formed deep value is read into a value")
|
||||
{
|
||||
const std::size_t depth = 10000;
|
||||
std::vector<uint8_t> input(depth, 0x91);
|
||||
input.push_back(0x01);
|
||||
|
||||
json j = json::from_msgpack(input);
|
||||
|
||||
std::size_t measured = 0;
|
||||
const json* p = &j;
|
||||
while (p->is_array() && !p->empty())
|
||||
{
|
||||
p = &p->front();
|
||||
++measured;
|
||||
}
|
||||
CHECK(measured == depth);
|
||||
CHECK(p->is_number());
|
||||
}
|
||||
|
||||
SECTION("containers are still read the same way")
|
||||
{
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0x90})) == json::array());
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0x80})) == json::object());
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0x92, 0x90, 0x80})) == json({json::array(), json::object()}));
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0x91, 0x91, 0x91, 0x90})) == json({{{json::array()}}}));
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0x81, 0xA1, 'a', 0x81, 0xA1, 'b', 0x92, 0x01, 0x02})) == json({{"a", {{"b", {1, 2}}}}}));
|
||||
// array 16 and map 32, i.e. the counted forms
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0xDC, 0x00, 0x02, 0x01, 0x02})) == json({1, 2}));
|
||||
CHECK(json::from_msgpack(std::vector<uint8_t>({0xDF, 0x00, 0x00, 0x00, 0x01, 0xA1, 'k', 0xC3})) == json({{"k", true}}));
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("single MessagePack roundtrip")
|
||||
{
|
||||
SECTION("sample.json")
|
||||
|
||||
@@ -81,3 +81,84 @@ TEST_CASE("regression test for issue #3732 - iteration_proxy_value<iter_impl<ord
|
||||
};
|
||||
static_cast<void>(fn);
|
||||
}
|
||||
|
||||
TEST_CASE("regression test - diff() must account for ordered_json member order")
|
||||
{
|
||||
SECTION("pure reorder, no value changes")
|
||||
{
|
||||
ordered_json a = {{"a", 1}, {"b", 2}};
|
||||
ordered_json b = {{"b", 2}, {"a", 1}};
|
||||
CHECK(a != b); // order-sensitive equality
|
||||
CHECK(a.patch(ordered_json::diff(a, b)) == b);
|
||||
}
|
||||
|
||||
SECTION("new key must land at the front")
|
||||
{
|
||||
ordered_json c = {{"b", 2}};
|
||||
ordered_json e = {{"a", 1}, {"b", 2}};
|
||||
CHECK(c.patch(ordered_json::diff(c, e)) == e);
|
||||
}
|
||||
|
||||
SECTION("reorder plus a value change on one of the reordered keys")
|
||||
{
|
||||
ordered_json a = {{"a", 1}, {"b", 2}};
|
||||
ordered_json b = {{"b", 20}, {"a", 1}};
|
||||
CHECK(a != b);
|
||||
CHECK(a.patch(ordered_json::diff(a, b)) == b);
|
||||
}
|
||||
|
||||
SECTION("reorder plus a deleted key")
|
||||
{
|
||||
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
|
||||
ordered_json b = {{"b", 2}, {"a", 1}};
|
||||
CHECK(a != b);
|
||||
CHECK(a.patch(ordered_json::diff(a, b)) == b);
|
||||
}
|
||||
|
||||
SECTION("reorder plus a nested value that itself needs a recursive diff")
|
||||
{
|
||||
ordered_json a = {{"a", {{"x", 1}, {"y", 2}}}, {"b", 2}};
|
||||
ordered_json b = {{"b", 2}, {"a", {{"x", 1}, {"y", 99}}}};
|
||||
CHECK(a != b);
|
||||
CHECK(a.patch(ordered_json::diff(a, b)) == b);
|
||||
}
|
||||
|
||||
SECTION("three or more keys shuffled into a different order")
|
||||
{
|
||||
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}, {"d", 4}};
|
||||
ordered_json b = {{"d", 4}, {"b", 2}, {"a", 1}, {"c", 3}};
|
||||
CHECK(a != b);
|
||||
CHECK(a.patch(ordered_json::diff(a, b)) == b);
|
||||
}
|
||||
|
||||
SECTION("matching order still produces a minimal patch (fast path unaffected)")
|
||||
{
|
||||
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
|
||||
ordered_json b = {{"a", 1}, {"b", 20}, {"c", 3}};
|
||||
auto p = ordered_json::diff(a, b);
|
||||
// only the changed value should be touched, not a wholesale remove+add
|
||||
CHECK(p.size() == 1);
|
||||
CHECK(p[0]["op"] == "replace");
|
||||
CHECK(p[0]["path"] == "/b");
|
||||
CHECK(a.patch(p) == b);
|
||||
}
|
||||
|
||||
SECTION("plain json (std::map-backed) is unaffected by same-key-different-insertion-order")
|
||||
{
|
||||
json a;
|
||||
a["b"] = 2;
|
||||
a["a"] = 1;
|
||||
|
||||
json b;
|
||||
b["a"] = 1;
|
||||
b["b"] = 2;
|
||||
|
||||
// std::map iteration is always sorted by key, so a == b regardless of
|
||||
// insertion order, and diff() must still produce the same minimal
|
||||
// (empty) result as before this fix
|
||||
CHECK(a == b);
|
||||
auto p = json::diff(a, b);
|
||||
CHECK(p.empty());
|
||||
CHECK(a.patch(p) == b);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2149,67 +2149,6 @@ TEST_CASE("UBJSON")
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
|
||||
{
|
||||
// An element of type 'Z', 'T' or 'F' is encoded by its marker alone, so an
|
||||
// optimized array of one of those has no payload and the declared count is
|
||||
// the only thing deciding how much is allocated. Ten bytes used to produce
|
||||
// billions of values (#2793); every other type costs at least one byte per
|
||||
// element and is bounded by the end of the input.
|
||||
json _;
|
||||
|
||||
SECTION("an excessive count is rejected")
|
||||
{
|
||||
// 'l' is a big-endian int32: 0x7FFFFFFF elements, about 34 GB of value
|
||||
for (const auto marker :
|
||||
{'Z', 'T', 'F'
|
||||
})
|
||||
{
|
||||
const std::vector<uint8_t> input = {'[', '$', static_cast<uint8_t>(marker), '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input), "[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size", json::out_of_range&);
|
||||
CHECK(json::from_ubjson(input, true, false).is_discarded());
|
||||
}
|
||||
}
|
||||
|
||||
SECTION("ordinary counts are unaffected")
|
||||
{
|
||||
CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'Z', '#', 'i', 3})) == json({nullptr, nullptr, nullptr}));
|
||||
CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'T', '#', 'i', 2})) == json({true, true}));
|
||||
CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'F', '#', 'i', 2})) == json({false, false}));
|
||||
// 'N' is a no-op rather than a value, and still yields an empty array
|
||||
CHECK(json::from_ubjson(std::vector<uint8_t>({'[', '$', 'N', '#', 'i', 2})) == json::array());
|
||||
}
|
||||
|
||||
SECTION("a type with a payload is unaffected")
|
||||
{
|
||||
// A count past the limit is not rejected for 'U', which costs a byte
|
||||
// per element and is bounded by the end of the input instead. The
|
||||
// count is kept just past the limit rather than made huge, because a
|
||||
// count that also exceeds the array's max_size() is reported as
|
||||
// out_of_range before the input runs out, and max_size() depends on
|
||||
// the width of std::size_t.
|
||||
const std::vector<uint8_t> input = {'[', '$', 'U', '#', 'l', 0x00, 0x10, 0x00, 0x01};
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input), "[json.exception.parse_error.110] parse error at byte 10: syntax error while parsing UBJSON number: unexpected end of input", json::parse_error&);
|
||||
CHECK(json::from_ubjson(input, true, false).is_discarded());
|
||||
}
|
||||
|
||||
SECTION("the writer stays within what the reader accepts")
|
||||
{
|
||||
// below the limit the optimized form is used and is tiny; above it the
|
||||
// writer falls back so that the result can still be read back
|
||||
json const at_limit(1048576, nullptr);
|
||||
const auto v_at_limit = json::to_ubjson(at_limit, true, true);
|
||||
CHECK(v_at_limit.size() == 9);
|
||||
CHECK(v_at_limit.at(1) == '$');
|
||||
CHECK(json::from_ubjson(v_at_limit) == at_limit);
|
||||
|
||||
json const above_limit(1048577, nullptr);
|
||||
const auto v_above_limit = json::to_ubjson(above_limit, true, true);
|
||||
CHECK(v_above_limit.at(1) != '$');
|
||||
CHECK(json::from_ubjson(v_above_limit) == above_limit);
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("Universal Binary JSON Specification Examples 1")
|
||||
{
|
||||
SECTION("Null Value")
|
||||
|
||||
Reference in New Issue
Block a user