amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-09-07 00:37:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
89994acc2c979db526509bd91d9d0f12cff2f515
json/include/nlohmann/detail/input/binary_reader.hpp
T
Niels Lohmann 89994acc2c Read BSON documents without recursing per nesting level 
An embedded document (record type 0x03) or array (0x04) was read by calling
back into the document reader, which read its element list, which called the
element reader again for the next embedded one. The native call stack
therefore grew with the nesting depth of the input, and about seven bytes buy
a level, so a document of a few hundred kilobytes crashes the process
(#5104). This is the last of the four binary formats to still do that.

Apply the same shape as the other three: open_bson_document() reads the size
prefix and opens the document, parse_bson_element_internal() calls it for both
record types instead of recursing, and parse_bson_internal() loops over the
element list of whichever document is innermost, closing it when its
terminator is reached and resuming the one below.

check_bson_document_size() is unchanged, and so is when it runs: a document is
still measured from the byte before its size prefix to the byte after its
terminator, and still reported before the end event. The frame carries those
two values, which is what a per-document check needs once the reads are
interleaved rather than nested. Nothing else about the element reader changes.

unit-bson passes unchanged. Round trips through to_bson of nested objects,
arrays, arrays of objects and mixed nesting are identical to the previous
commit, as are the errors for a truncated document, an unsupported record
type, a negative size and a size that does not match, including their byte
offsets. A 30,000-level document built by to_bson is now read to completion
where it used to crash.

Note for sequencing: #5185 changes parse_bson_internal(), the element list and
the array reader, which are the functions this commit restructures. It should
land first; this commit then keeps its checks and moves them onto the loop.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-06 18:34:00 +02:00

3503 lines
124 KiB
C++
Raw Blame History

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <algorithm> // generate_n
#include <array> // array
#include <cmath> // ldexp
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint16_t, uint32_t, uint64_t, uintmax_t
#include <cstdio> // snprintf
#include <cstring> // memcpy
#include <iterator> // back_inserter
#include <limits> // numeric_limits
#include <string> // char_traits, string
#include <utility> // make_pair, move
#include <vector> // vector
#ifdef __cpp_lib_byteswap
#include <bit> //byteswap
#endif
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/input/input_adapters.hpp>
#include <nlohmann/detail/input/json_sax.hpp>
#include <nlohmann/detail/input/lexer.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/is_sax.hpp>
#include <nlohmann/detail/meta/type_traits.hpp>
#include <nlohmann/detail/string_concat.hpp>
#include <nlohmann/detail/value_t.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
/// how to treat CBOR tags
enum class cbor_tag_handler_t
{
error, ///< throw a parse_error exception in case of a tag
ignore, ///< ignore tags
store ///< store tags as binary type
};
/*!
@brief determine system byte order
@return true if and only if system's byte order is little endian
@note from https://stackoverflow.com/a/1001328/266378
*/
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 //
///////////////////
/*!
@brief deserialization of CBOR, MessagePack, and UBJSON values
*/
template<typename BasicJsonType, typename InputAdapterType, typename SAX = json_sax_dom_parser<BasicJsonType, InputAdapterType>>
class binary_reader
{
using number_integer_t = typename BasicJsonType::number_integer_t;
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
using number_float_t = typename BasicJsonType::number_float_t;
using string_t = typename BasicJsonType::string_t;
using binary_t = typename BasicJsonType::binary_t;
using json_sax_t = SAX;
using char_type = typename InputAdapterType::char_type;
using char_int_type = typename char_traits<char_type>::int_type;
public:
/*!
@brief create a binary reader
@param[in] adapter input adapter to read from
*/
explicit binary_reader(InputAdapterType&& adapter, const input_format_t format = input_format_t::json) noexcept : ia(std::move(adapter)), input_format(format)
{
(void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
}
// make class move-only
binary_reader(const binary_reader&) = delete;
binary_reader(binary_reader&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor)
binary_reader& operator=(const binary_reader&) = delete;
binary_reader& operator=(binary_reader&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor)
~binary_reader() = default;
/*!
@param[in] format the binary format to parse
@param[in] sax_ a SAX event processor
@param[in] strict whether to expect the input to be consumed completed
@param[in] tag_handler how to treat CBOR tags
@return whether parsing was successful
*/
JSON_HEDLEY_NON_NULL(3)
bool sax_parse(const input_format_t format,
json_sax_t* sax_,
const bool strict = true,
const cbor_tag_handler_t tag_handler = cbor_tag_handler_t::error)
{
sax = sax_;
container_stack.clear();
bool result = false;
switch (format)
{
case input_format_t::bson:
result = parse_bson_internal();
break;
case input_format_t::cbor:
result = parse_cbor_internal(true, tag_handler);
break;
case input_format_t::msgpack:
result = parse_msgpack_internal();
break;
case input_format_t::ubjson:
case input_format_t::bjdata:
result = parse_ubjson_internal();
break;
case input_format_t::json: // LCOV_EXCL_LINE
default: // LCOV_EXCL_LINE
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
}
// strict mode: next byte must be EOF
if (result && strict)
{
if (input_format == input_format_t::ubjson || input_format == input_format_t::bjdata)
{
get_ignore_noop();
}
else
{
get();
}
if (JSON_HEDLEY_UNLIKELY(current != char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(110, chars_read,
exception_message(input_format, concat("expected end of input; last byte: 0x", get_token_string()), "value"), nullptr));
}
}
return result;
}
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 widest first: frames are stored in a vector, and
declaring the `bool` first would pad the struct out for no reason.
*/
struct container_frame
{
/// number of elements that have not been read yet, or npos when the
/// container is not sized and ends at a marker instead
std::size_t remaining = 0;
/// BSON: value of chars_read before this document's size prefix, which
/// check_bson_document_size() needs once the document has been read
std::size_t start_position = 0;
/// UBJSON/BJData: the type marker of an optimized container, so that
/// its elements are read without one of their own; 0 otherwise
char_int_type type_marker = 0;
/// BSON: the size this document declares, in bytes
std::int32_t declared_size = 0;
/// whether to close this container with end_object() or end_array()
bool is_object = false;
};
/*!
@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,
const char_int_type type_marker = 0)
{
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->start_object(len) : !sax->start_array(len)))
{
return false;
}
container_frame frame;
frame.remaining = len;
frame.type_marker = type_marker;
frame.is_object = is_object;
container_stack.push_back(frame);
return true;
}
//////////
// BSON //
//////////
/*!
@brief Validate a BSON document's declared size against the bytes read.
A BSON document starts with an int32 that counts its own total length in
bytes, including that prefix and the trailing 0x00. The reader is driven
by the terminator rather than the declared length, so without this check a
nested document could declare a length that disagrees with where its
terminator actually falls and quietly hand the bytes in between to the
enclosing document. A well-formed document is at least 5 bytes (the prefix
plus the terminator); the equality also rejects those impossible sizes,
since at least 5 bytes are always consumed.
@param[in] document_start value of chars_read before the size prefix
@param[in] document_size the declared document size
@return whether the declared size matches the number of bytes read
*/
bool check_bson_document_size(const std::size_t document_start, const std::int32_t document_size)
{
if (JSON_HEDLEY_UNLIKELY(document_size < 0 || static_cast<std::size_t>(document_size) != chars_read - document_start))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
exception_message(input_format_t::bson, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(chars_read - document_start), ")"), "document"), nullptr));
}
return true;
}
/*!
@brief Reads in a BSON-object and passes it to the SAX-parser.
@return whether a valid BSON-value was passed to the SAX parser
*/
bool open_bson_document(const bool is_object)
{
// recorded before the size prefix is read, because
// check_bson_document_size() measures the document from here
const std::size_t document_start = chars_read;
std::int32_t document_size{};
if (!get_number<std::int32_t, true>(input_format_t::bson, document_size))
{
return false;
}
if (JSON_HEDLEY_UNLIKELY(!enter_container(is_object, detail::unknown_size())))
{
return false;
}
container_stack.back().start_position = document_start;
container_stack.back().declared_size = document_size;
return true;
}
/*!
@brief read a BSON document and everything nested inside it
Reads elements until the document that was begun here is complete,
resuming the enclosing document each time an embedded one ends, so that
the nesting depth of the input costs heap rather than native stack
(see #5104).
@return whether reading the document succeeded
*/
bool parse_bson_internal()
{
if (JSON_HEDLEY_UNLIKELY(!open_bson_document(/*is_object*/true)))
{
return false;
}
// 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)
{
const auto element_type = get();
if (element_type == 0) // end of the innermost document
{
const container_frame& top = container_stack.back();
const bool is_object = top.is_object;
if (JSON_HEDLEY_UNLIKELY(!check_bson_document_size(top.start_position, top.declared_size)))
{
return false;
}
container_stack.pop_back();
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
{
return false;
}
// the document begun here is complete once it is not inside one
if (container_stack.empty())
{
return true;
}
continue;
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "element list")))
{
return false;
}
const std::size_t element_type_parse_position = chars_read;
key.clear();
if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key)))
{
return false;
}
// an array's elements are named "0", "1", ... in the wire format,
// and those names are not passed on
if (container_stack.back().is_object && !sax->key(key))
{
return false;
}
if (JSON_HEDLEY_UNLIKELY(!parse_bson_element_internal(element_type, element_type_parse_position)))
{
return false;
}
}
}
/*!
@brief Parses a C-style string from the BSON input.
@param[in,out] result A reference to the string variable where the read
string is to be stored.
@return `true` if the \x00-byte indicating the end of the string was
encountered before the EOF; false` indicates an unexpected EOF.
*/
bool get_bson_cstr(string_t& result)
{
auto out = std::back_inserter(result);
while (true)
{
get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::bson, "cstring")))
{
return false;
}
if (current == 0x00)
{
return true;
}
*out++ = static_cast<typename string_t::value_type>(current);
}
}
/*!
@brief Parses a zero-terminated string of length @a len from the BSON
input.
@param[in] len The length (including the zero-byte at the end) of the
string to be read.
@param[in,out] result A reference to the string variable where the read
string is to be stored.
@tparam NumberType The type of the length @a len
@pre len >= 1
@return `true` if the string was successfully parsed
*/
template<typename NumberType>
bool get_bson_string(const NumberType len, string_t& result)
{
if (JSON_HEDLEY_UNLIKELY(len < 1))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format_t::bson, concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
}
return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) && get() != char_traits<char_type>::eof();
}
/*!
@brief Parses a byte array input of length @a len from the BSON input.
@param[in] len The length of the byte array to be read.
@param[in,out] result A reference to the binary variable where the read
array is to be stored.
@tparam NumberType The type of the length @a len
@pre len >= 0
@return `true` if the byte array was successfully parsed
*/
template<typename NumberType>
bool get_bson_binary(const NumberType len, binary_t& result)
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format_t::bson, concat("byte array length cannot be negative, is ", std::to_string(len)), "binary"), nullptr));
}
// All BSON binary values have a subtype
std::uint8_t subtype{};
if (JSON_HEDLEY_UNLIKELY(!get_number<std::uint8_t>(input_format_t::bson, subtype)))
{
return false;
}
result.set_subtype(subtype);
return get_binary(input_format_t::bson, len, result);
}
/*!
@brief Read a BSON document element of the given @a element_type.
@param[in] element_type The BSON element type, c.f. http://bsonspec.org/spec.html
@param[in] element_type_parse_position The position in the input stream,
where the `element_type` was read.
@warning Not all BSON element types are supported yet. An unsupported
@a element_type will give rise to a parse_error.114:
Unsupported BSON record type 0x...
@return whether a valid BSON-object/array was passed to the SAX parser
*/
bool parse_bson_element_internal(const char_int_type element_type,
const std::size_t element_type_parse_position)
{
switch (element_type)
{
case 0x01: // double
{
double number{};
return get_number<double, true>(input_format_t::bson, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 0x02: // string
{
std::int32_t len{};
string_t value;
return get_number<std::int32_t, true>(input_format_t::bson, len) && get_bson_string(len, value) && sax->string(value);
}
case 0x03: // object
{
return open_bson_document(/*is_object*/true);
}
case 0x04: // array
{
return open_bson_document(/*is_object*/false);
}
case 0x05: // binary
{
std::int32_t len{};
binary_t value;
return get_number<std::int32_t, true>(input_format_t::bson, len) && get_bson_binary(len, value) && sax->binary(value);
}
case 0x08: // boolean
{
std::uint8_t value{};
return get_number<std::uint8_t>(input_format_t::bson, value) && sax->boolean(value != 0);
}
case 0x0A: // null
{
return sax->null();
}
case 0x10: // int32
{
std::int32_t value{};
return get_number<std::int32_t, true>(input_format_t::bson, value) && sax->number_integer(value);
}
case 0x12: // int64
{
std::int64_t value{};
return get_number<std::int64_t, true>(input_format_t::bson, value) && sax->number_integer(value);
}
case 0x11: // uint64
{
std::uint64_t value{};
return get_number<std::uint64_t, true>(input_format_t::bson, value) && sax->number_unsigned(value);
}
default: // anything else is not supported (yet)
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(element_type))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
const std::string cr_str{cr.data()};
return sax->parse_error(element_type_parse_position, cr_str,
parse_error::create(114, element_type_parse_position, concat("Unsupported BSON record type 0x", cr_str), nullptr));
}
}
}
//////////
// CBOR //
//////////
template<typename NumberType>
bool get_cbor_negative_integer()
{
NumberType number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format_t::cbor, number)))
{
return false;
}
const auto max_val = static_cast<NumberType>((std::numeric_limits<number_integer_t>::max)());
if (number > max_val)
{
return sax->parse_error(chars_read, get_token_string(),
parse_error::create(112, chars_read,
exception_message(input_format_t::cbor, "negative integer overflow", "value"), nullptr));
}
return sax->number_integer(static_cast<number_integer_t>(-1) - static_cast<number_integer_t>(number));
}
/*!
@param[in] get_char whether a new character should be retrieved from the
input (true) or whether the last read character should
be considered instead (false)
@param[in] tag_handler how CBOR tags should be treated
@return whether a valid CBOR value was passed to the SAX parser
*/
bool parse_cbor_value(const bool get_char,
const cbor_tag_handler_t tag_handler,
bool& tag_pending)
{
tag_pending = false;
switch (get_char ? get() : current)
{
// EOF
case char_traits<char_type>::eof():
return unexpect_eof(input_format_t::cbor, "value");
// Integer 0x00..0x17 (0..23)
case 0x00:
case 0x01:
case 0x02:
case 0x03:
case 0x04:
case 0x05:
case 0x06:
case 0x07:
case 0x08:
case 0x09:
case 0x0A:
case 0x0B:
case 0x0C:
case 0x0D:
case 0x0E:
case 0x0F:
case 0x10:
case 0x11:
case 0x12:
case 0x13:
case 0x14:
case 0x15:
case 0x16:
case 0x17:
return sax->number_unsigned(static_cast<number_unsigned_t>(current));
case 0x18: // Unsigned integer (one-byte uint8_t follows)
{
std::uint8_t number{};
return get_number(input_format_t::cbor, number) && sax->number_unsigned(number);
}
case 0x19: // Unsigned integer (two-byte uint16_t follows)
{
std::uint16_t number{};
return get_number(input_format_t::cbor, number) && sax->number_unsigned(number);
}
case 0x1A: // Unsigned integer (four-byte uint32_t follows)
{
std::uint32_t number{};
return get_number(input_format_t::cbor, number) && sax->number_unsigned(number);
}
case 0x1B: // Unsigned integer (eight-byte uint64_t follows)
{
std::uint64_t number{};
return get_number(input_format_t::cbor, number) && sax->number_unsigned(number);
}
// Negative integer -1-0x00..-1-0x17 (-1..-24)
case 0x20:
case 0x21:
case 0x22:
case 0x23:
case 0x24:
case 0x25:
case 0x26:
case 0x27:
case 0x28:
case 0x29:
case 0x2A:
case 0x2B:
case 0x2C:
case 0x2D:
case 0x2E:
case 0x2F:
case 0x30:
case 0x31:
case 0x32:
case 0x33:
case 0x34:
case 0x35:
case 0x36:
case 0x37:
return sax->number_integer(static_cast<std::int8_t>(0x20 - 1 - current));
case 0x38: // Negative integer (one-byte uint8_t follows)
return get_cbor_negative_integer<std::uint8_t>();
case 0x39: // Negative integer -1-n (two-byte uint16_t follows)
return get_cbor_negative_integer<std::uint16_t>();
case 0x3A: // Negative integer -1-n (four-byte uint32_t follows)
return get_cbor_negative_integer<std::uint32_t>();
case 0x3B: // Negative integer -1-n (eight-byte uint64_t follows)
return get_cbor_negative_integer<std::uint64_t>();
// Binary data (0x00..0x17 bytes follow)
case 0x40:
case 0x41:
case 0x42:
case 0x43:
case 0x44:
case 0x45:
case 0x46:
case 0x47:
case 0x48:
case 0x49:
case 0x4A:
case 0x4B:
case 0x4C:
case 0x4D:
case 0x4E:
case 0x4F:
case 0x50:
case 0x51:
case 0x52:
case 0x53:
case 0x54:
case 0x55:
case 0x56:
case 0x57:
case 0x58: // Binary data (one-byte uint8_t for n follows)
case 0x59: // Binary data (two-byte uint16_t for n follow)
case 0x5A: // Binary data (four-byte uint32_t for n follow)
case 0x5B: // Binary data (eight-byte uint64_t for n follow)
case 0x5F: // Binary data (indefinite length)
{
binary_t b;
return get_cbor_binary(b) && sax->binary(b);
}
// UTF-8 string (0x00..0x17 bytes follow)
case 0x60:
case 0x61:
case 0x62:
case 0x63:
case 0x64:
case 0x65:
case 0x66:
case 0x67:
case 0x68:
case 0x69:
case 0x6A:
case 0x6B:
case 0x6C:
case 0x6D:
case 0x6E:
case 0x6F:
case 0x70:
case 0x71:
case 0x72:
case 0x73:
case 0x74:
case 0x75:
case 0x76:
case 0x77:
case 0x78: // UTF-8 string (one-byte uint8_t for n follows)
case 0x79: // UTF-8 string (two-byte uint16_t for n follow)
case 0x7A: // UTF-8 string (four-byte uint32_t for n follow)
case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow)
case 0x7F: // UTF-8 string (indefinite length)
{
string_t s;
return get_cbor_string(s) && sax->string(s);
}
// array (0x00..0x17 data items follow)
case 0x80:
case 0x81:
case 0x82:
case 0x83:
case 0x84:
case 0x85:
case 0x86:
case 0x87:
case 0x88:
case 0x89:
case 0x8A:
case 0x8B:
case 0x8C:
case 0x8D:
case 0x8E:
case 0x8F:
case 0x90:
case 0x91:
case 0x92:
case 0x93:
case 0x94:
case 0x95:
case 0x96:
case 0x97:
return enter_container(/*is_object*/false,
conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
case 0x98: // array (one-byte uint8_t for n follows)
{
std::uint8_t len{};
return get_number(input_format_t::cbor, len) && enter_container(/*is_object*/false, static_cast<std::size_t>(len));
}
case 0x99: // array (two-byte uint16_t for n follow)
{
std::uint16_t len{};
return get_number(input_format_t::cbor, len) && enter_container(/*is_object*/false, static_cast<std::size_t>(len));
}
case 0x9A: // array (four-byte uint32_t for n follow)
{
std::uint32_t len{};
std::size_t size{};
return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && enter_container(/*is_object*/false, size);
}
case 0x9B: // array (eight-byte uint64_t for n follow)
{
std::uint64_t len{};
std::size_t size{};
return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "array") && enter_container(/*is_object*/false, size);
}
case 0x9F: // array (indefinite length)
return enter_container(/*is_object*/false, detail::unknown_size());
// map (0x00..0x17 pairs of data items follow)
case 0xA0:
case 0xA1:
case 0xA2:
case 0xA3:
case 0xA4:
case 0xA5:
case 0xA6:
case 0xA7:
case 0xA8:
case 0xA9:
case 0xAA:
case 0xAB:
case 0xAC:
case 0xAD:
case 0xAE:
case 0xAF:
case 0xB0:
case 0xB1:
case 0xB2:
case 0xB3:
case 0xB4:
case 0xB5:
case 0xB6:
case 0xB7:
return enter_container(/*is_object*/true, conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x1Fu));
case 0xB8: // map (one-byte uint8_t for n follows)
{
std::uint8_t len{};
return get_number(input_format_t::cbor, len) && enter_container(/*is_object*/true, static_cast<std::size_t>(len));
}
case 0xB9: // map (two-byte uint16_t for n follow)
{
std::uint16_t len{};
return get_number(input_format_t::cbor, len) && enter_container(/*is_object*/true, static_cast<std::size_t>(len));
}
case 0xBA: // map (four-byte uint32_t for n follow)
{
std::uint32_t len{};
std::size_t size{};
return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && enter_container(/*is_object*/true, size);
}
case 0xBB: // map (eight-byte uint64_t for n follow)
{
std::uint64_t len{};
std::size_t size{};
return get_number(input_format_t::cbor, len) && get_cbor_container_size(len, size, "map") && enter_container(/*is_object*/true, size);
}
case 0xBF: // map (indefinite length)
return enter_container(/*is_object*/true, detail::unknown_size());
case 0xC0: // tagged item
case 0xC1:
case 0xC2:
case 0xC3:
case 0xC4:
case 0xC5:
case 0xC6:
case 0xC7:
case 0xC8:
case 0xC9:
case 0xCA:
case 0xCB:
case 0xCC:
case 0xCD:
case 0xCE:
case 0xCF:
case 0xD0:
case 0xD1:
case 0xD2:
case 0xD3:
case 0xD4:
case 0xD5:
case 0xD6:
case 0xD7:
case 0xD8: // tagged item (1 byte follows)
case 0xD9: // tagged item (2 bytes follow)
case 0xDA: // tagged item (4 bytes follow)
case 0xDB: // tagged item (8 bytes follow)
{
switch (tag_handler)
{
case cbor_tag_handler_t::error:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format_t::cbor, concat("invalid byte: 0x", last_token), "value"), nullptr));
}
case cbor_tag_handler_t::ignore:
{
// ignore binary subtype
switch (current)
{
case 0xD8:
{
std::uint8_t subtype_to_ignore{};
if (!get_number(input_format_t::cbor, subtype_to_ignore))
{
return false;
}
break;
}
case 0xD9:
{
std::uint16_t subtype_to_ignore{};
if (!get_number(input_format_t::cbor, subtype_to_ignore))
{
return false;
}
break;
}
case 0xDA:
{
std::uint32_t subtype_to_ignore{};
if (!get_number(input_format_t::cbor, subtype_to_ignore))
{
return false;
}
break;
}
case 0xDB:
{
std::uint64_t subtype_to_ignore{};
if (!get_number(input_format_t::cbor, subtype_to_ignore))
{
return false;
}
break;
}
default:
break;
}
// the tagged value follows; it is read by the loop in
// parse_cbor_internal() rather than by recursing here
tag_pending = true;
return true;
}
case cbor_tag_handler_t::store:
{
binary_t b;
// use binary subtype and store in a binary container
switch (current)
{
case 0xD8:
{
std::uint8_t subtype{};
if (!get_number(input_format_t::cbor, subtype))
{
return false;
}
b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
break;
}
case 0xD9:
{
std::uint16_t subtype{};
if (!get_number(input_format_t::cbor, subtype))
{
return false;
}
b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
break;
}
case 0xDA:
{
std::uint32_t subtype{};
if (!get_number(input_format_t::cbor, subtype))
{
return false;
}
b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
break;
}
case 0xDB:
{
std::uint64_t subtype{};
if (!get_number(input_format_t::cbor, subtype))
{
return false;
}
b.set_subtype(detail::conditional_static_cast<typename binary_t::subtype_type>(subtype));
break;
}
default:
{
// as above, the tagged value is read by the caller
tag_pending = true;
return true;
}
}
get();
return get_cbor_binary(b) && sax->binary(b);
}
default: // LCOV_EXCL_LINE
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
return false; // LCOV_EXCL_LINE
}
}
case 0xF4: // false
return sax->boolean(false);
case 0xF5: // true
return sax->boolean(true);
case 0xF6: // null
return sax->null();
case 0xF9: // Half-Precision Float (two-byte IEEE 754)
{
const auto byte1_raw = get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number")))
{
return false;
}
const auto byte2_raw = get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "number")))
{
return false;
}
const auto byte1 = static_cast<unsigned char>(byte1_raw);
const auto byte2 = static_cast<unsigned char>(byte2_raw);
// Code from RFC 8949, Appendix D, Figure 3:
// As half-precision floating-point numbers were only added
// to IEEE 754 in 2008, today's programming platforms often
// still only have limited support for them. It is very
// easy to include at least decoding support for them even
// without such support. An example of a small decoder for
// half-precision floating-point numbers in the C language
// is shown in Fig. 3.
const auto half = static_cast<unsigned int>((byte1 << 8u) + byte2);
const double val = [&half]
{
const int exp = (half >> 10u) & 0x1Fu;
const unsigned int mant = half & 0x3FFu;
JSON_ASSERT(exp <= 31);
JSON_ASSERT(mant <= 1023);
switch (exp)
{
case 0:
return std::ldexp(mant, -24);
case 31:
return (mant == 0)
? std::numeric_limits<double>::infinity()
: std::numeric_limits<double>::quiet_NaN();
default:
return std::ldexp(mant + 1024, exp - 25);
}
}();
return sax->number_float((half & 0x8000u) != 0
? static_cast<number_float_t>(-val)
: static_cast<number_float_t>(val), "");
}
case 0xFA: // Single-Precision Float (four-byte IEEE 754)
{
float number{};
return get_number(input_format_t::cbor, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 0xFB: // Double-Precision Float (eight-byte IEEE 754)
{
double number{};
return get_number(input_format_t::cbor, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
default: // anything else (0xFF is handled inside the other types)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format_t::cbor, concat("invalid byte: 0x", last_token), "value"), nullptr));
}
}
}
/*!
@brief reads a definite-length 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.
@param[out] result string the bytes are appended to
@return whether string creation completed
@pre @a current is not EOF
*/
bool get_cbor_string_chunk(string_t& result)
{
switch (current)
{
// UTF-8 string (0x00..0x17 bytes follow)
case 0x60:
case 0x61:
case 0x62:
case 0x63:
case 0x64:
case 0x65:
case 0x66:
case 0x67:
case 0x68:
case 0x69:
case 0x6A:
case 0x6B:
case 0x6C:
case 0x6D:
case 0x6E:
case 0x6F:
case 0x70:
case 0x71:
case 0x72:
case 0x73:
case 0x74:
case 0x75:
case 0x76:
case 0x77:
{
return get_string(input_format_t::cbor, static_cast<unsigned int>(current) & 0x1Fu, result);
}
case 0x78: // UTF-8 string (one-byte uint8_t for n follows)
{
std::uint8_t len{};
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
}
case 0x79: // UTF-8 string (two-byte uint16_t for n follow)
{
std::uint16_t len{};
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
}
case 0x7A: // UTF-8 string (four-byte uint32_t for n follow)
{
std::uint32_t len{};
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
}
case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow)
{
std::uint64_t len{};
return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
}
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(input_format_t::cbor, concat("expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x", last_token), "string"), nullptr));
}
}
}
/*!
@brief reads a CBOR 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 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
@return whether byte array creation completed
@pre @a current is not EOF
*/
bool get_cbor_binary_chunk(binary_t& result)
{
switch (current)
{
// Binary data (0x00..0x17 bytes follow)
case 0x40:
case 0x41:
case 0x42:
case 0x43:
case 0x44:
case 0x45:
case 0x46:
case 0x47:
case 0x48:
case 0x49:
case 0x4A:
case 0x4B:
case 0x4C:
case 0x4D:
case 0x4E:
case 0x4F:
case 0x50:
case 0x51:
case 0x52:
case 0x53:
case 0x54:
case 0x55:
case 0x56:
case 0x57:
{
return get_binary(input_format_t::cbor, static_cast<unsigned int>(current) & 0x1Fu, result);
}
case 0x58: // Binary data (one-byte uint8_t for n follows)
{
std::uint8_t len{};
return get_number(input_format_t::cbor, len) &&
get_binary(input_format_t::cbor, len, result);
}
case 0x59: // Binary data (two-byte uint16_t for n follow)
{
std::uint16_t len{};
return get_number(input_format_t::cbor, len) &&
get_binary(input_format_t::cbor, len, result);
}
case 0x5A: // Binary data (four-byte uint32_t for n follow)
{
std::uint32_t len{};
return get_number(input_format_t::cbor, len) &&
get_binary(input_format_t::cbor, len, result);
}
case 0x5B: // Binary data (eight-byte uint64_t for n follow)
{
std::uint64_t len{};
return get_number(input_format_t::cbor, len) &&
get_binary(input_format_t::cbor, len, result);
}
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(input_format_t::cbor, concat("expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x", last_token), "binary"), nullptr));
}
}
}
/*!
@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
A definite length is rejected if it does not fit in std::size_t or if it
equals detail::unknown_size(), which is reserved to mark an indefinite-
length container and would otherwise make the length read as indefinite.
Both cases exceed any container's max_size(), so no representable input
is affected.
@param[in] len the declared length
@param[out] result the length narrowed to std::size_t
@param[in] context "array" or "map", for the error message
@return whether the length is usable
*/
bool get_cbor_container_size(const std::uint64_t len, std::size_t& result, const char* context)
{
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(len) || len == detail::unknown_size()))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message(input_format_t::cbor, concat("excessive ", context, " size"), "size"), nullptr));
}
result = conditional_static_cast<std::size_t>(len);
return true;
}
/*!
@brief read a CBOR value and everything nested inside it
Reads values until the one that was begun here is complete, resuming the
enclosing container after each element, so that the nesting depth of the
input costs heap rather than native stack (see #5104).
@param[in] get_char whether a new character should be retrieved from the
input (true) or whether the last read character
@a current should be considered instead
@param[in] tag_handler how CBOR tags should be treated
@return whether reading the value succeeded
*/
bool parse_cbor_internal(const bool get_char,
const cbor_tag_handler_t tag_handler)
{
// whether the next value starts at a fresh byte or at the one already
// read into `current`
bool fetch = get_char;
// 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())
{
// the reference is not held across parse_cbor_value() below,
// which can push onto the stack and reallocate it
container_frame& top = container_stack.back();
bool at_end;
if (top.remaining != npos)
{
// definite length: the container ends once its elements
// have been read
at_end = (top.remaining == 0);
if (!at_end)
{
// claim the element about to be read
--top.remaining;
if (top.is_object)
{
get();
}
}
fetch = true;
}
else
{
// indefinite length: the container ends at a break marker.
// Testing for it consumes a byte, which is the first byte
// of the next element when it is not one.
at_end = (get() == 0xFF);
fetch = top.is_object;
}
if (at_end)
{
const bool is_object = top.is_object;
container_stack.pop_back();
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
{
return false;
}
// the value begun here is complete once its container is
if (container_stack.empty())
{
return true;
}
continue;
}
if (top.is_object)
{
key.clear();
if (JSON_HEDLEY_UNLIKELY(!get_cbor_string(key) || !sax->key(key)))
{
return false;
}
fetch = true;
}
}
// a tag is not a value of its own: read on until the tagged value
bool tag_pending;
do
{
if (JSON_HEDLEY_UNLIKELY(!parse_cbor_value(fetch, tag_handler, tag_pending)))
{
return false;
}
fetch = true;
}
while (tag_pending);
// 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;
}
}
}
/////////////
// MsgPack //
/////////////
/*!
@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()
{
switch (get())
{
// EOF
case char_traits<char_type>::eof():
return unexpect_eof(input_format_t::msgpack, "value");
// positive fixint
case 0x00:
case 0x01:
case 0x02:
case 0x03:
case 0x04:
case 0x05:
case 0x06:
case 0x07:
case 0x08:
case 0x09:
case 0x0A:
case 0x0B:
case 0x0C:
case 0x0D:
case 0x0E:
case 0x0F:
case 0x10:
case 0x11:
case 0x12:
case 0x13:
case 0x14:
case 0x15:
case 0x16:
case 0x17:
case 0x18:
case 0x19:
case 0x1A:
case 0x1B:
case 0x1C:
case 0x1D:
case 0x1E:
case 0x1F:
case 0x20:
case 0x21:
case 0x22:
case 0x23:
case 0x24:
case 0x25:
case 0x26:
case 0x27:
case 0x28:
case 0x29:
case 0x2A:
case 0x2B:
case 0x2C:
case 0x2D:
case 0x2E:
case 0x2F:
case 0x30:
case 0x31:
case 0x32:
case 0x33:
case 0x34:
case 0x35:
case 0x36:
case 0x37:
case 0x38:
case 0x39:
case 0x3A:
case 0x3B:
case 0x3C:
case 0x3D:
case 0x3E:
case 0x3F:
case 0x40:
case 0x41:
case 0x42:
case 0x43:
case 0x44:
case 0x45:
case 0x46:
case 0x47:
case 0x48:
case 0x49:
case 0x4A:
case 0x4B:
case 0x4C:
case 0x4D:
case 0x4E:
case 0x4F:
case 0x50:
case 0x51:
case 0x52:
case 0x53:
case 0x54:
case 0x55:
case 0x56:
case 0x57:
case 0x58:
case 0x59:
case 0x5A:
case 0x5B:
case 0x5C:
case 0x5D:
case 0x5E:
case 0x5F:
case 0x60:
case 0x61:
case 0x62:
case 0x63:
case 0x64:
case 0x65:
case 0x66:
case 0x67:
case 0x68:
case 0x69:
case 0x6A:
case 0x6B:
case 0x6C:
case 0x6D:
case 0x6E:
case 0x6F:
case 0x70:
case 0x71:
case 0x72:
case 0x73:
case 0x74:
case 0x75:
case 0x76:
case 0x77:
case 0x78:
case 0x79:
case 0x7A:
case 0x7B:
case 0x7C:
case 0x7D:
case 0x7E:
case 0x7F:
return sax->number_unsigned(static_cast<number_unsigned_t>(current));
// fixmap
case 0x80:
case 0x81:
case 0x82:
case 0x83:
case 0x84:
case 0x85:
case 0x86:
case 0x87:
case 0x88:
case 0x89:
case 0x8A:
case 0x8B:
case 0x8C:
case 0x8D:
case 0x8E:
case 0x8F:
return enter_container(/*is_object*/true, conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
// fixarray
case 0x90:
case 0x91:
case 0x92:
case 0x93:
case 0x94:
case 0x95:
case 0x96:
case 0x97:
case 0x98:
case 0x99:
case 0x9A:
case 0x9B:
case 0x9C:
case 0x9D:
case 0x9E:
case 0x9F:
return enter_container(/*is_object*/false, conditional_static_cast<std::size_t>(static_cast<unsigned int>(current) & 0x0Fu));
// fixstr
case 0xA0:
case 0xA1:
case 0xA2:
case 0xA3:
case 0xA4:
case 0xA5:
case 0xA6:
case 0xA7:
case 0xA8:
case 0xA9:
case 0xAA:
case 0xAB:
case 0xAC:
case 0xAD:
case 0xAE:
case 0xAF:
case 0xB0:
case 0xB1:
case 0xB2:
case 0xB3:
case 0xB4:
case 0xB5:
case 0xB6:
case 0xB7:
case 0xB8:
case 0xB9:
case 0xBA:
case 0xBB:
case 0xBC:
case 0xBD:
case 0xBE:
case 0xBF:
case 0xD9: // str 8
case 0xDA: // str 16
case 0xDB: // str 32
{
string_t s;
return get_msgpack_string(s) && sax->string(s);
}
case 0xC0: // nil
return sax->null();
case 0xC2: // false
return sax->boolean(false);
case 0xC3: // true
return sax->boolean(true);
case 0xC4: // bin 8
case 0xC5: // bin 16
case 0xC6: // bin 32
case 0xC7: // ext 8
case 0xC8: // ext 16
case 0xC9: // ext 32
case 0xD4: // fixext 1
case 0xD5: // fixext 2
case 0xD6: // fixext 4
case 0xD7: // fixext 8
case 0xD8: // fixext 16
{
binary_t b;
return get_msgpack_binary(b) && sax->binary(b);
}
case 0xCA: // float 32
{
float number{};
return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 0xCB: // float 64
{
double number{};
return get_number(input_format_t::msgpack, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 0xCC: // uint 8
{
std::uint8_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number);
}
case 0xCD: // uint 16
{
std::uint16_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number);
}
case 0xCE: // uint 32
{
std::uint32_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number);
}
case 0xCF: // uint 64
{
std::uint64_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_unsigned(number);
}
case 0xD0: // int 8
{
std::int8_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_integer(number);
}
case 0xD1: // int 16
{
std::int16_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_integer(number);
}
case 0xD2: // int 32
{
std::int32_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_integer(number);
}
case 0xD3: // int 64
{
std::int64_t number{};
return get_number(input_format_t::msgpack, number) && sax->number_integer(number);
}
case 0xDC: // array 16
{
std::uint16_t len{};
return get_number(input_format_t::msgpack, len) && enter_container(/*is_object*/false, static_cast<std::size_t>(len));
}
case 0xDD: // array 32
{
std::uint32_t len{};
return get_number(input_format_t::msgpack, len) && enter_container(/*is_object*/false, conditional_static_cast<std::size_t>(len));
}
case 0xDE: // map 16
{
std::uint16_t len{};
return get_number(input_format_t::msgpack, len) && enter_container(/*is_object*/true, static_cast<std::size_t>(len));
}
case 0xDF: // map 32
{
std::uint32_t len{};
return get_number(input_format_t::msgpack, len) && enter_container(/*is_object*/true, conditional_static_cast<std::size_t>(len));
}
// negative fixint
case 0xE0:
case 0xE1:
case 0xE2:
case 0xE3:
case 0xE4:
case 0xE5:
case 0xE6:
case 0xE7:
case 0xE8:
case 0xE9:
case 0xEA:
case 0xEB:
case 0xEC:
case 0xED:
case 0xEE:
case 0xEF:
case 0xF0:
case 0xF1:
case 0xF2:
case 0xF3:
case 0xF4:
case 0xF5:
case 0xF6:
case 0xF7:
case 0xF8:
case 0xF9:
case 0xFA:
case 0xFB:
case 0xFC:
case 0xFD:
case 0xFE:
case 0xFF:
return sax->number_integer(static_cast<std::int8_t>(current));
default: // anything else
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format_t::msgpack, concat("invalid byte: 0x", last_token), "value"), nullptr));
}
}
}
/*!
@brief reads a MessagePack string
This function first reads starting bytes to determine the expected
string length and then copies this number of bytes into a string.
@param[out] result created string
@return whether string creation completed
*/
bool get_msgpack_string(string_t& result)
{
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::msgpack, "string")))
{
return false;
}
switch (current)
{
// fixstr
case 0xA0:
case 0xA1:
case 0xA2:
case 0xA3:
case 0xA4:
case 0xA5:
case 0xA6:
case 0xA7:
case 0xA8:
case 0xA9:
case 0xAA:
case 0xAB:
case 0xAC:
case 0xAD:
case 0xAE:
case 0xAF:
case 0xB0:
case 0xB1:
case 0xB2:
case 0xB3:
case 0xB4:
case 0xB5:
case 0xB6:
case 0xB7:
case 0xB8:
case 0xB9:
case 0xBA:
case 0xBB:
case 0xBC:
case 0xBD:
case 0xBE:
case 0xBF:
{
return get_string(input_format_t::msgpack, static_cast<unsigned int>(current) & 0x1Fu, result);
}
case 0xD9: // str 8
{
std::uint8_t len{};
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
}
case 0xDA: // str 16
{
std::uint16_t len{};
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
}
case 0xDB: // str 32
{
std::uint32_t len{};
return get_number(input_format_t::msgpack, len) && get_string(input_format_t::msgpack, len, result);
}
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(input_format_t::msgpack, concat("expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x", last_token), "string"), nullptr));
}
}
}
/*!
@brief reads a MessagePack byte array
This function first reads starting bytes to determine the expected
byte array length and then copies this number of bytes into a byte array.
@param[out] result created byte array
@return whether byte array creation completed
*/
bool get_msgpack_binary(binary_t& result)
{
// helper function to set the subtype
auto assign_and_return_true = [&result](std::int8_t subtype)
{
result.set_subtype(static_cast<std::uint8_t>(subtype));
return true;
};
switch (current)
{
case 0xC4: // bin 8
{
std::uint8_t len{};
return get_number(input_format_t::msgpack, len) &&
get_binary(input_format_t::msgpack, len, result);
}
case 0xC5: // bin 16
{
std::uint16_t len{};
return get_number(input_format_t::msgpack, len) &&
get_binary(input_format_t::msgpack, len, result);
}
case 0xC6: // bin 32
{
std::uint32_t len{};
return get_number(input_format_t::msgpack, len) &&
get_binary(input_format_t::msgpack, len, result);
}
case 0xC7: // ext 8
{
std::uint8_t len{};
std::int8_t subtype{};
return get_number(input_format_t::msgpack, len) &&
get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, len, result) &&
assign_and_return_true(subtype);
}
case 0xC8: // ext 16
{
std::uint16_t len{};
std::int8_t subtype{};
return get_number(input_format_t::msgpack, len) &&
get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, len, result) &&
assign_and_return_true(subtype);
}
case 0xC9: // ext 32
{
std::uint32_t len{};
std::int8_t subtype{};
return get_number(input_format_t::msgpack, len) &&
get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, len, result) &&
assign_and_return_true(subtype);
}
case 0xD4: // fixext 1
{
std::int8_t subtype{};
return get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, 1, result) &&
assign_and_return_true(subtype);
}
case 0xD5: // fixext 2
{
std::int8_t subtype{};
return get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, 2, result) &&
assign_and_return_true(subtype);
}
case 0xD6: // fixext 4
{
std::int8_t subtype{};
return get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, 4, result) &&
assign_and_return_true(subtype);
}
case 0xD7: // fixext 8
{
std::int8_t subtype{};
return get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, 8, result) &&
assign_and_return_true(subtype);
}
case 0xD8: // fixext 16
{
std::int8_t subtype{};
return get_number(input_format_t::msgpack, subtype) &&
get_binary(input_format_t::msgpack, 16, result) &&
assign_and_return_true(subtype);
}
default: // LCOV_EXCL_LINE
return false; // LCOV_EXCL_LINE
}
}
/*!
@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
*/
bool parse_msgpack_internal()
{
// the key currently being read; hoisted out of the loop so that its
// capacity is reused across elements and across nesting levels
string_t key;
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()))
{
return false;
}
// the value begun here is complete once its container is
if (container_stack.empty())
{
return true;
}
continue;
}
// claim the element about to be read
--container_stack.back().remaining;
if (is_object)
{
get();
key.clear();
if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
{
return false;
}
}
}
if (JSON_HEDLEY_UNLIKELY(!parse_msgpack_value()))
{
return false;
}
// 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;
}
}
}
////////////
// UBJSON //
////////////
/*!
@param[in] get_char whether a new character should be retrieved from the
input (true, default) or whether the last read
character should be considered instead
@return whether a valid UBJSON value was passed to the SAX parser
*/
bool parse_ubjson_internal(const bool get_char = true)
{
// the key currently being read; hoisted out of the loop so that its
// capacity is reused across elements and across nesting levels
string_t key;
// the type marker of the value to read next
char_int_type prefix = get_char ? get_ignore_noop() : current;
while (true)
{
const std::size_t depth = container_stack.size();
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(prefix)))
{
return false;
}
// the value begun here is complete once it is not inside anything
if (container_stack.empty())
{
return true;
}
// a value was completed rather than a container opened; a
// container that ends at a marker needs the next byte to test
if (container_stack.size() == depth && container_stack.back().remaining == npos)
{
get_ignore_noop();
}
// advance to the next element, closing the containers that ended.
// The reference is not held across get_ubjson_value() above, which
// can push onto the stack and reallocate it.
for (;;)
{
container_frame& top = container_stack.back();
if (top.remaining != npos)
{
if (top.remaining != 0)
{
--top.remaining;
if (top.is_object)
{
key.clear();
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key) || !sax->key(key)))
{
return false;
}
}
// an optimized container gives its elements no marker
prefix = (top.type_marker != 0) ? top.type_marker : get_ignore_noop();
break;
}
}
else if (current != (top.is_object ? '}' : ']'))
{
// a container that ends at a marker is never optimized, so
// every element carries its own marker; for an object the
// byte tested above is the first byte of the key
if (top.is_object)
{
key.clear();
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_string(key, false) || !sax->key(key)))
{
return false;
}
prefix = get_ignore_noop();
}
else
{
prefix = current;
}
break;
}
const bool is_object = top.is_object;
container_stack.pop_back();
if (JSON_HEDLEY_UNLIKELY(is_object ? !sax->end_object() : !sax->end_array()))
{
return false;
}
if (container_stack.empty())
{
return true;
}
// the container that just ended was an element of the one
// below it, which may need the next byte for its own test
if (container_stack.back().remaining == npos)
{
get_ignore_noop();
}
}
}
}
/*!
@brief reject a negative UBJSON/BJData string length
String and key lengths are written with signed integer markers (i, I, l,
L). A negative value is malformed; without this check get_string() would
silently treat it as an empty string and leave the following bytes to be
misread as the next value. This mirrors the non-negative check the
optimized-container count path already performs in get_ubjson_size_value.
@param[in] len the string length read from the input
@return whether the length is valid (non-negative)
*/
template<typename NumberType>
bool check_ubjson_string_length(const NumberType len)
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message(input_format, "string length must not be negative", "string"), nullptr));
}
return true;
}
/*!
@brief reads a UBJSON string
This function is either called after reading the 'S' byte explicitly
indicating a string, or in case of an object key where the 'S' byte can be
left out.
@param[out] result created string
@param[in] get_char whether a new character should be retrieved from the
input (true, default) or whether the last read
character should be considered instead
@return whether string creation completed
*/
bool get_ubjson_string(string_t& result, const bool get_char = true)
{
if (get_char)
{
// no get_ignore_noop() here: the byte read next must be a string
// length type specification, and a no-op ('N') is not valid in
// that position. No-ops at positions where a value may appear are
// already consumed by the callers via get_ignore_noop().
get();
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "value")))
{
return false;
}
switch (current)
{
case 'U':
{
std::uint8_t len{};
return get_number(input_format, len) && get_string(input_format, len, result);
}
case 'i':
{
std::int8_t len{};
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
}
case 'I':
{
std::int16_t len{};
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
}
case 'l':
{
std::int32_t len{};
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
}
case 'L':
{
std::int64_t len{};
return get_number(input_format, len) && check_ubjson_string_length(len) && get_string(input_format, len, result);
}
case 'u':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint16_t len{};
return get_number(input_format, len) && get_string(input_format, len, result);
}
case 'm':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint32_t len{};
return get_number(input_format, len) && get_string(input_format, len, result);
}
case 'M':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint64_t len{};
return get_number(input_format, len) && get_string(input_format, len, result);
}
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L); last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format, message, "string"), nullptr));
}
/*!
@param[out] dim an integer vector storing the ND array dimensions
@return whether reading ND array size vector is successful
*/
bool get_ubjson_ndarray_size(std::vector<size_t>& dim)
{
std::pair<std::size_t, char_int_type> size_and_type;
size_t dimlen = 0;
bool no_ndarray = true;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type, no_ndarray)))
{
return false;
}
if (size_and_type.first != npos)
{
if (size_and_type.second != 0)
{
if (size_and_type.second != 'N')
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, no_ndarray, size_and_type.second)))
{
return false;
}
dim.push_back(dimlen);
}
}
}
else
{
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, no_ndarray)))
{
return false;
}
dim.push_back(dimlen);
}
}
}
else
{
while (current != ']')
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_value(dimlen, no_ndarray, current)))
{
return false;
}
dim.push_back(dimlen);
get_ignore_noop();
}
}
return true;
}
/*!
@param[out] result determined size
@param[in,out] is_ndarray for input, `true` means already inside an ndarray vector
or ndarray dimension is not allowed; `false` means ndarray
is allowed; for output, `true` means an ndarray is found;
is_ndarray can only return `true` when its initial value
is `false`
@param[in] prefix type marker if already read, otherwise set to 0
@return whether size determination completed
*/
bool get_ubjson_size_value(std::size_t& result, bool& is_ndarray, char_int_type prefix = 0)
{
if (prefix == 0)
{
prefix = get_ignore_noop();
}
switch (prefix)
{
case 'U':
{
std::uint8_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
result = static_cast<std::size_t>(number);
return true;
}
case 'i':
{
std::int8_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
if (number < 0)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
}
result = static_cast<std::size_t>(number); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): number is not a char
return true;
}
case 'I':
{
std::int16_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
if (number < 0)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
}
result = static_cast<std::size_t>(number);
return true;
}
case 'l':
{
std::int32_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
if (number < 0)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
}
result = static_cast<std::size_t>(number);
return true;
}
case 'L':
{
std::int64_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
if (number < 0)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message(input_format, "count in an optimized container must be positive", "size"), nullptr));
}
if (!value_in_range_of<std::size_t>(number))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message(input_format, "integer value overflow", "size"), nullptr));
}
result = static_cast<std::size_t>(number);
return true;
}
case 'u':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint16_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
result = static_cast<std::size_t>(number);
return true;
}
case 'm':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint32_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
result = conditional_static_cast<std::size_t>(number);
return true;
}
case 'M':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint64_t number{};
if (JSON_HEDLEY_UNLIKELY(!get_number(input_format, number)))
{
return false;
}
if (!value_in_range_of<std::size_t>(number))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message(input_format, "integer value overflow", "size"), nullptr));
}
result = detail::conditional_static_cast<std::size_t>(number);
return true;
}
case '[':
{
if (input_format != input_format_t::bjdata)
{
break;
}
if (is_ndarray) // ndarray dimensional vector can only contain integers and cannot embed another array
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read, exception_message(input_format, "ndarray dimensional vector is not allowed", "size"), nullptr));
}
std::vector<size_t> dim;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_ndarray_size(dim)))
{
return false;
}
if (dim.size() == 1 || (dim.size() == 2 && dim.at(0) == 1)) // return normal array size if 1D row vector
{
result = dim.at(dim.size() - 1);
return true;
}
if (!dim.empty()) // if ndarray, convert to an object in JData annotated array format
{
for (auto i : dim) // test if any dimension in an ndarray is 0, if so, return a 1D empty container
{
if ( i == 0 )
{
result = 0;
return true;
}
}
string_t key = "_ArraySize_";
if (JSON_HEDLEY_UNLIKELY(!sax->start_object(3) || !sax->key(key) || !sax->start_array(dim.size())))
{
return false;
}
result = 1;
for (auto i : dim)
{
// Pre-multiplication overflow check: if i > 0 and result > SIZE_MAX/i, then result*i would overflow.
// This check must happen before multiplication since overflow detection after the fact is unreliable
// as modular arithmetic can produce any value, not just 0 or SIZE_MAX.
if (JSON_HEDLEY_UNLIKELY(i > 0 && result > (std::numeric_limits<std::size_t>::max)() / i))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message(input_format, "excessive ndarray size caused overflow", "size"), nullptr));
}
result *= i;
// Additional post-multiplication check to catch any edge cases the pre-check might miss
if (result == 0 || result == npos)
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message(input_format, "excessive ndarray size caused overflow", "size"), nullptr));
}
if (JSON_HEDLEY_UNLIKELY(!sax->number_unsigned(static_cast<number_unsigned_t>(i))))
{
return false;
}
}
is_ndarray = true;
return sax->end_array();
}
result = 0;
return true;
}
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(input_format, message, "size"), nullptr));
}
/*!
@brief determine the type and size for a container
In the optimized UBJSON format, a type and a size can be provided to allow
for a more compact representation.
@param[out] result pair of the size and the type
@param[in] inside_ndarray whether the parser is parsing an ND array dimensional vector
@return whether pair creation completed
*/
bool get_ubjson_size_type(std::pair<std::size_t, char_int_type>& result, bool inside_ndarray = false)
{
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;
get_ignore_noop();
if (current == '$')
{
result.second = get(); // must not ignore 'N', because 'N' maybe the type
if (input_format == input_format_t::bjdata
&& JSON_HEDLEY_UNLIKELY(std::binary_search(bjd_optimized_type_markers.begin(), bjd_optimized_type_markers.end(), result.second)))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, concat("marker 0x", last_token, " is not a permitted optimized array type"), "type"), nullptr));
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "type")))
{
return false;
}
get_ignore_noop();
if (JSON_HEDLEY_UNLIKELY(current != '#'))
{
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "value")))
{
return false;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
}
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)
{
result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
}
return is_error;
}
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)
{
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));
}
return is_error;
}
return true;
}
/*!
@param prefix the previously read or set type prefix
@return whether value creation completed
*/
bool get_ubjson_value(const char_int_type prefix)
{
switch (prefix)
{
case char_traits<char_type>::eof(): // EOF
return unexpect_eof(input_format, "value");
case 'T': // true
return sax->boolean(true);
case 'F': // false
return sax->boolean(false);
case 'Z': // null
return sax->null();
case 'B': // byte
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint8_t number{};
return get_number(input_format, number) && sax->number_unsigned(number);
}
case 'U':
{
std::uint8_t number{};
return get_number(input_format, number) && sax->number_unsigned(number);
}
case 'i':
{
std::int8_t number{};
return get_number(input_format, number) && sax->number_integer(number);
}
case 'I':
{
std::int16_t number{};
return get_number(input_format, number) && sax->number_integer(number);
}
case 'l':
{
std::int32_t number{};
return get_number(input_format, number) && sax->number_integer(number);
}
case 'L':
{
std::int64_t number{};
return get_number(input_format, number) && sax->number_integer(number);
}
case 'u':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint16_t number{};
return get_number(input_format, number) && sax->number_unsigned(number);
}
case 'm':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint32_t number{};
return get_number(input_format, number) && sax->number_unsigned(number);
}
case 'M':
{
if (input_format != input_format_t::bjdata)
{
break;
}
std::uint64_t number{};
return get_number(input_format, number) && sax->number_unsigned(number);
}
case 'h':
{
if (input_format != input_format_t::bjdata)
{
break;
}
const auto byte1_raw = get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "number")))
{
return false;
}
const auto byte2_raw = get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "number")))
{
return false;
}
const auto byte1 = static_cast<unsigned char>(byte1_raw);
const auto byte2 = static_cast<unsigned char>(byte2_raw);
// Code from RFC 8949, Appendix D, Figure 3:
// As half-precision floating-point numbers were only added
// to IEEE 754 in 2008, today's programming platforms often
// still only have limited support for them. It is very
// easy to include at least decoding support for them even
// without such support. An example of a small decoder for
// half-precision floating-point numbers in the C language
// is shown in Fig. 3.
const auto half = static_cast<unsigned int>((byte2 << 8u) + byte1);
const double val = [&half]
{
const int exp = (half >> 10u) & 0x1Fu;
const unsigned int mant = half & 0x3FFu;
JSON_ASSERT(exp <= 31);
JSON_ASSERT(mant <= 1023);
switch (exp)
{
case 0:
return std::ldexp(mant, -24);
case 31:
return (mant == 0)
? std::numeric_limits<double>::infinity()
: std::numeric_limits<double>::quiet_NaN();
default:
return std::ldexp(mant + 1024, exp - 25);
}
}();
return sax->number_float((half & 0x8000u) != 0
? static_cast<number_float_t>(-val)
: static_cast<number_float_t>(val), "");
}
case 'd':
{
float number{};
return get_number(input_format, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 'D':
{
double number{};
return get_number(input_format, number) && sax->number_float(static_cast<number_float_t>(number), "");
}
case 'H':
{
return get_ubjson_high_precision_number();
}
case 'C': // char
{
get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "char")))
{
return false;
}
if (JSON_HEDLEY_UNLIKELY(current > 127))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(input_format, concat("byte after 'C' must be in range 0x00..0x7F; last byte: 0x", last_token), "char"), nullptr));
}
string_t s(1, static_cast<typename string_t::value_type>(current));
return sax->string(s);
}
case 'S': // string
{
string_t s;
return get_ubjson_string(s) && sax->string(s);
}
case '[': // array
return get_ubjson_array();
case '{': // object
return get_ubjson_object();
default: // anything else
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read, exception_message(input_format, "invalid byte: 0x" + last_token, "value"), nullptr));
}
/*!
@return whether array creation completed
*/
bool get_ubjson_array()
{
std::pair<std::size_t, char_int_type> size_and_type;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type)))
{
return false;
}
// if bit-8 of size_and_type.second is set to 1, encode bjdata ndarray as an object in JData annotated array format (https://github.com/NeuroJSON/jdata):
// {"_ArrayType_" : "typeid", "_ArraySize_" : [n1, n2, ...], "_ArrayData_" : [v1, v2, ...]}
if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
{
size_and_type.second &= ~(static_cast<char_int_type>(1) << 8); // use bit 8 to indicate ndarray, here we remove the bit to restore the type marker
auto it = std::lower_bound(bjd_types_map.begin(), bjd_types_map.end(), size_and_type.second, [](const bjd_type & p, char_int_type t)
{
return p.first < t;
});
string_t key = "_ArrayType_";
if (JSON_HEDLEY_UNLIKELY(it == bjd_types_map.end() || it->first != size_and_type.second))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "invalid byte: 0x" + last_token, "type"), nullptr));
}
string_t type = it->second; // sax->string() takes a reference
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->string(type)))
{
return false;
}
if (size_and_type.second == 'C' || size_and_type.second == 'B')
{
size_and_type.second = 'U';
}
key = "_ArrayData_";
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->start_array(size_and_type.first) ))
{
return false;
}
for (std::size_t i = 0; i < size_and_type.first; ++i)
{
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_value(size_and_type.second)))
{
return false;
}
}
return (sax->end_array() && sax->end_object());
}
// If BJData type marker is 'B' decode as binary
if (input_format == input_format_t::bjdata && size_and_type.first != npos && size_and_type.second == 'B')
{
binary_t result;
return get_binary(input_format, size_and_type.first, result) && sax->binary(result);
}
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(!enter_container(/*is_object*/false, size_and_type.first, size_and_type.second)))
{
return false;
}
if (size_and_type.second == 'N')
{
// a no-op is not a value, so a container of them holds none;
// the declared size has already been passed to the SAX parser
container_stack.back().remaining = 0;
}
return true;
}
return enter_container(/*is_object*/false, detail::unknown_size());
}
/*!
@return whether object creation completed
*/
bool get_ubjson_object()
{
std::pair<std::size_t, char_int_type> size_and_type;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_size_type(size_and_type)))
{
return false;
}
// do not accept ND-array size in objects in BJData
if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(input_format, "BJData object does not support ND-array size in optimized format", "object"), nullptr));
}
if (size_and_type.first != npos)
{
return enter_container(/*is_object*/true, size_and_type.first, size_and_type.second);
}
return enter_container(/*is_object*/true, detail::unknown_size());
}
// Note, no reader for UBJSON binary types is implemented because they do
// not exist
bool get_ubjson_high_precision_number()
{
// get the size of the following number string
std::size_t size{};
bool no_ndarray = true;
auto res = get_ubjson_size_value(size, no_ndarray);
if (JSON_HEDLEY_UNLIKELY(!res))
{
return res;
}
// get number string
std::vector<char> number_vector;
for (std::size_t i = 0; i < size; ++i)
{
get();
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format, "number")))
{
return false;
}
number_vector.push_back(static_cast<char>(current));
}
// parse number string
using ia_type = decltype(detail::input_adapter(number_vector));
auto number_lexer = detail::lexer<BasicJsonType, ia_type>(detail::input_adapter(number_vector), false);
const auto result_number = number_lexer.scan();
const auto number_string = number_lexer.get_token_string();
const auto result_remainder = number_lexer.scan();
using token_type = typename detail::lexer_base<BasicJsonType>::token_type;
if (JSON_HEDLEY_UNLIKELY(result_remainder != token_type::end_of_input))
{
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
exception_message(input_format, concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
switch (result_number)
{
case token_type::value_integer:
return sax->number_integer(number_lexer.get_number_integer());
case token_type::value_unsigned:
return sax->number_unsigned(number_lexer.get_number_unsigned());
case token_type::value_float:
{
const auto parsed_float = number_lexer.get_number_float();
if (JSON_HEDLEY_UNLIKELY(!std::isfinite(parsed_float)))
{
return sax->parse_error(
chars_read,
number_string,
out_of_range::create(406, concat("number overflow parsing '", number_string, '\''), nullptr));
}
return sax->number_float(parsed_float, std::move(number_string));
}
case token_type::uninitialized:
case token_type::literal_true:
case token_type::literal_false:
case token_type::literal_null:
case token_type::value_string:
case token_type::begin_array:
case token_type::begin_object:
case token_type::end_array:
case token_type::end_object:
case token_type::name_separator:
case token_type::value_separator:
case token_type::parse_error:
case token_type::end_of_input:
case token_type::literal_or_value:
default:
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
exception_message(input_format, concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
}
///////////////////////
// Utility functions //
///////////////////////
/*!
@brief get next character from the input
This function provides the interface to the used input adapter. It does
not throw in case the input reached EOF, but returns a -'ve valued
`char_traits<char_type>::eof()` in that case.
@return character read from the input
*/
char_int_type get()
{
++chars_read;
return current = ia.get_character();
}
/*!
@brief get_to read into a primitive type
This function provides the interface to the used input adapter. It does
not throw in case the input reached EOF, but returns false instead
@return bool, whether the read was successful
*/
template<class T>
bool get_to(T& dest, const input_format_t format, const char* context)
{
auto new_chars_read = ia.get_elements(&dest);
chars_read += new_chars_read;
if (JSON_HEDLEY_UNLIKELY(new_chars_read < sizeof(T)))
{
// in case of failure, advance position by 1 to report the failing location
++chars_read;
sax->parse_error(chars_read, "<end of file>", parse_error::create(110, chars_read, exception_message(format, "unexpected end of input", context), nullptr));
return false;
}
return true;
}
/*!
@return character read from the input after ignoring all 'N' entries
*/
char_int_type get_ignore_noop()
{
do
{
get();
}
while (current == 'N');
return current;
}
template<class NumberType>
static void byte_swap(NumberType& number)
{
constexpr std::size_t sz = sizeof(number);
#ifdef __cpp_lib_byteswap
if constexpr (sz == 1)
{
return;
}
else if constexpr(std::is_integral_v<NumberType>)
{
number = std::byteswap(number);
return;
}
else
{
#endif
auto* ptr = reinterpret_cast<std::uint8_t*>(&number);
for (std::size_t i = 0; i < sz / 2; ++i)
{
std::swap(ptr[i], ptr[sz - i - 1]);
}
#ifdef __cpp_lib_byteswap
}
#endif
}
/*
@brief read a number from the input
@tparam NumberType the type of the number
@param[in] format the current format (for diagnostics)
@param[out] result number of type @a NumberType
@return whether conversion completed
@note This function needs to respect the system's endianness, because
bytes in CBOR, MessagePack, and UBJSON are stored in network order
(big endian) and therefore need reordering on little endian systems.
On the other hand, BSON and BJData use little endian and should reorder
on big endian systems.
*/
template<typename NumberType, bool InputIsLittleEndian = false>
bool get_number(const input_format_t format, NumberType& result)
{
// read in the original format
if (JSON_HEDLEY_UNLIKELY(!get_to(result, format, "number")))
{
return false;
}
if (is_little_endian != (InputIsLittleEndian || format == input_format_t::bjdata))
{
byte_swap(result);
}
return true;
}
/*!
@brief create a string by reading characters from the input
@tparam NumberType the type of the number
@param[in] format the current format (for diagnostics)
@param[in] len number of characters to read
@param[out] result string created by reading @a len bytes
@return whether string creation completed
@note We can not reserve @a len bytes for the result, because @a len
may be too large. Usually, @ref unexpect_eof() detects the end of
the input before we run out of string memory.
*/
template<typename NumberType>
bool get_string(const input_format_t format,
const NumberType len,
string_t& result)
{
return get_bytes(format, len, "string", result);
}
/*!
@brief create a byte array by reading bytes from the input
@tparam NumberType the type of the number
@param[in] format the current format (for diagnostics)
@param[in] len number of bytes to read
@param[out] result byte array created by reading @a len bytes
@return whether byte array creation completed
@note We can not reserve @a len bytes for the result, because @a len
may be too large. Usually, @ref unexpect_eof() detects the end of
the input before we run out of memory.
*/
template<typename NumberType>
bool get_binary(const input_format_t format,
const NumberType len,
binary_t& result)
{
return get_bytes(format, len, "binary", result);
}
/*!
@brief read @a len bytes from the input into a string or byte container
@tparam NumberType the type of the length
@tparam ContainerType the destination container (string_t or binary_t)
@param[in] format the current format (for diagnostics)
@param[in] len number of bytes to read
@param[in] context further context information (for diagnostics)
@param[out] result container the bytes are appended to
@return whether reading completed
@note We cannot reserve @a len bytes for the result up front, because
@a len may be far larger than the actual input. Instead we read in
bounded chunks, so the peak allocation is capped regardless of the
claimed length while the per-byte loop is replaced by block copies
(a std::memcpy for contiguous inputs). @ref unexpect_eof() still
detects a premature end of input.
*/
template<typename NumberType, typename ContainerType>
bool get_bytes(const input_format_t format,
NumberType len,
const char* context,
ContainerType& result)
{
// upper bound on the number of bytes read (and allocated) per chunk
constexpr std::size_t chunk_size = 4096;
while (len > 0)
{
// number of bytes to read this iteration: min(chunk_size, len),
// computed without truncating chunk_size to a narrow NumberType
const std::size_t wanted = (static_cast<std::uintmax_t>(len) < static_cast<std::uintmax_t>(chunk_size))
? static_cast<std::size_t>(len)
: chunk_size;
const std::size_t old_size = result.size();
result.resize(old_size + wanted);
// resize() is required to make size() exactly old_size + wanted;
// that is the room get_elements() is allowed to write into
JSON_ASSERT(result.size() == old_size + wanted);
const std::size_t bytes_read = ia.get_elements(&result[old_size], wanted);
chars_read += bytes_read;
if (JSON_HEDLEY_UNLIKELY(bytes_read < wanted))
{
// premature end of input: shrink to what was actually read and
// report the failure at the first missing byte (same position
// accounting as get_to() for partial number reads)
result.resize(old_size + bytes_read);
++chars_read;
current = char_traits<char_type>::eof();
return unexpect_eof(format, context);
}
// a full chunk was read; get_elements() never returns more than requested
JSON_ASSERT(bytes_read == wanted);
len = static_cast<NumberType>(len - static_cast<NumberType>(wanted));
}
return true;
}
/*!
@param[in] format the current format (for diagnostics)
@param[in] context further context information (for diagnostics)
@return whether the last read character is not EOF
*/
JSON_HEDLEY_NON_NULL(3)
bool unexpect_eof(const input_format_t format, const char* context) const
{
if (JSON_HEDLEY_UNLIKELY(current == char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, "<end of file>",
parse_error::create(110, chars_read, exception_message(format, "unexpected end of input", context), nullptr));
}
return true;
}
/*!
@return a string representation of the last read byte
*/
std::string get_token_string() const
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(current))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
return std::string{cr.data()};
}
/*!
@param[in] format the current format
@param[in] detail a detailed error message
@param[in] context further context information
@return a message string to use in the parse_error exceptions
*/
std::string exception_message(const input_format_t format,
const std::string& detail,
const std::string& context) const
{
std::string error_msg = "syntax error while parsing ";
switch (format)
{
case input_format_t::cbor:
error_msg += "CBOR";
break;
case input_format_t::msgpack:
error_msg += "MessagePack";
break;
case input_format_t::ubjson:
error_msg += "UBJSON";
break;
case input_format_t::bson:
error_msg += "BSON";
break;
case input_format_t::bjdata:
error_msg += "BJData";
break;
case input_format_t::json: // LCOV_EXCL_LINE
default: // LCOV_EXCL_LINE
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
}
return concat(error_msg, ' ', context, ": ", detail);
}
private:
static JSON_INLINE_VARIABLE constexpr std::size_t npos = detail::unknown_size();
/// input adapter
InputAdapterType ia;
/// the current character
char_int_type current = char_traits<char_type>::eof();
/// the number of characters read
std::size_t chars_read = 0;
/// whether we can assume little endianness
const bool is_little_endian = little_endianness();
/// input format
const input_format_t input_format = input_format_t::json;
/// 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', '[', '{')
#define JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_ \
make_array<bjd_type>( \
bjd_type{'B', "byte"}, \
bjd_type{'C', "char"}, \
bjd_type{'D', "double"}, \
bjd_type{'I', "int16"}, \
bjd_type{'L', "int64"}, \
bjd_type{'M', "uint64"}, \
bjd_type{'U', "uint8"}, \
bjd_type{'d', "single"}, \
bjd_type{'i', "int8"}, \
bjd_type{'l', "int32"}, \
bjd_type{'m', "uint32"}, \
bjd_type{'u', "uint16"})
JSON_PRIVATE_UNLESS_TESTED:
// lookup tables
// NOLINTNEXTLINE(cppcoreguidelines-non-private-member-variables-in-classes)
const decltype(JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_) bjd_optimized_type_markers =
JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_;
using bjd_type = std::pair<char_int_type, string_t>;
// NOLINTNEXTLINE(cppcoreguidelines-non-private-member-variables-in-classes)
const decltype(JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_) bjd_types_map =
JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_;
#undef JSON_BINARY_READER_MAKE_BJD_OPTIMIZED_TYPE_MARKERS_
#undef JSON_BINARY_READER_MAKE_BJD_TYPES_MAP_
};
#ifndef JSON_HAS_CPP_17
template<typename BasicJsonType, typename InputAdapterType, typename SAX>
constexpr std::size_t binary_reader<BasicJsonType, InputAdapterType, SAX>::npos;
#endif
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
Reference in New Issue View Git Blame Copy Permalink