1984 lines
60 KiB
C++
1984 lines
60 KiB
C++
#pragma once
|
|
|
|
#include <algorithm> // generate_n
|
|
#include <array> // array
|
|
#include <cassert> // assert
|
|
#include <cmath> // ldexp
|
|
#include <cstddef> // size_t
|
|
#include <cstdint> // uint8_t, uint16_t, uint32_t, uint64_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 <nlohmann/detail/exceptions.hpp>
|
|
#include <nlohmann/detail/input/input_adapters.hpp>
|
|
#include <nlohmann/detail/input/json_sax.hpp>
|
|
#include <nlohmann/detail/macro_scope.hpp>
|
|
#include <nlohmann/detail/meta/is_sax.hpp>
|
|
#include <nlohmann/detail/value_t.hpp>
|
|
|
|
namespace nlohmann
|
|
{
|
|
namespace detail
|
|
{
|
|
///////////////////
|
|
// binary reader //
|
|
///////////////////
|
|
|
|
/*!
|
|
@brief deserialization of CBOR, MessagePack, and UBJSON values
|
|
*/
|
|
template<typename BasicJsonType, typename SAX = json_sax_dom_parser<BasicJsonType>>
|
|
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 json_sax_t = SAX;
|
|
|
|
public:
|
|
/*!
|
|
@brief create a binary reader
|
|
|
|
@param[in] adapter input adapter to read from
|
|
*/
|
|
explicit binary_reader(input_adapter_t adapter) : ia(std::move(adapter))
|
|
{
|
|
(void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
|
|
assert(ia);
|
|
}
|
|
|
|
// make class move-only
|
|
binary_reader(const binary_reader&) = delete;
|
|
binary_reader(binary_reader&&) = default;
|
|
binary_reader& operator=(const binary_reader&) = delete;
|
|
binary_reader& operator=(binary_reader&&) = default;
|
|
~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
|
|
|
|
@return
|
|
*/
|
|
JSON_HEDLEY_NON_NULL(3)
|
|
bool sax_parse(const input_format_t format,
|
|
json_sax_t* sax_,
|
|
const bool strict = true)
|
|
{
|
|
sax = sax_;
|
|
bool result = false;
|
|
|
|
switch (format)
|
|
{
|
|
case input_format_t::bson:
|
|
result = parse_bson_internal();
|
|
break;
|
|
|
|
case input_format_t::cbor:
|
|
result = parse_cbor_internal();
|
|
break;
|
|
|
|
case input_format_t::msgpack:
|
|
result = parse_msgpack_internal();
|
|
break;
|
|
|
|
case input_format_t::ubjson:
|
|
result = parse_ubjson_internal();
|
|
break;
|
|
|
|
default: // LCOV_EXCL_LINE
|
|
assert(false); // LCOV_EXCL_LINE
|
|
}
|
|
|
|
// strict mode: next byte must be EOF
|
|
if (result and strict)
|
|
{
|
|
if (format == input_format_t::ubjson)
|
|
{
|
|
get_ignore_noop();
|
|
}
|
|
else
|
|
{
|
|
get();
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(current != std::char_traits<char>::eof()))
|
|
{
|
|
return sax->parse_error(chars_read, get_token_string(),
|
|
parse_error::create(110, chars_read, exception_message(format, "expected end of input; last byte: 0x" + get_token_string(), "value")));
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
/*!
|
|
@brief determine system byte order
|
|
|
|
@return true if and only if system's byte order is little endian
|
|
|
|
@note from http://stackoverflow.com/a/1001328/266378
|
|
*/
|
|
static constexpr bool little_endianess(int num = 1) noexcept
|
|
{
|
|
return *reinterpret_cast<char*>(&num) == 1;
|
|
}
|
|
|
|
private:
|
|
//////////
|
|
// BSON //
|
|
//////////
|
|
|
|
/*!
|
|
@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 parse_bson_internal()
|
|
{
|
|
std::int32_t document_size;
|
|
get_number<std::int32_t, true>(input_format_t::bson, document_size);
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_object(std::size_t(-1))))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_bson_element_list(/*is_array*/false)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
return sax->end_object();
|
|
}
|
|
|
|
/*!
|
|
@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(not unexpect_eof(input_format_t::bson, "cstring")))
|
|
{
|
|
return false;
|
|
}
|
|
if (current == 0x00)
|
|
{
|
|
return true;
|
|
}
|
|
*out++ = static_cast<char>(current);
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*!
|
|
@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, "string length must be at least 1, is " + std::to_string(len), "string")));
|
|
}
|
|
|
|
return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) and get() != std::char_traits<char>::eof();
|
|
}
|
|
|
|
/*!
|
|
@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 int 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) and 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) and get_bson_string(len, value) and sax->string(value);
|
|
}
|
|
|
|
case 0x03: // object
|
|
{
|
|
return parse_bson_internal();
|
|
}
|
|
|
|
case 0x04: // array
|
|
{
|
|
return parse_bson_array();
|
|
}
|
|
|
|
case 0x08: // boolean
|
|
{
|
|
return sax->boolean(get() != 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) and sax->number_integer(value);
|
|
}
|
|
|
|
case 0x12: // int64
|
|
{
|
|
std::int64_t value;
|
|
return get_number<std::int64_t, true>(input_format_t::bson, value) and sax->number_integer(value);
|
|
}
|
|
|
|
default: // anything else not supported (yet)
|
|
{
|
|
std::array<char, 3> cr{{}};
|
|
(std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(element_type));
|
|
return sax->parse_error(element_type_parse_position, std::string(cr.data()), parse_error::create(114, element_type_parse_position, "Unsupported BSON record type 0x" + std::string(cr.data())));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@brief Read a BSON element list (as specified in the BSON-spec)
|
|
|
|
The same binary layout is used for objects and arrays, hence it must be
|
|
indicated with the argument @a is_array which one is expected
|
|
(true --> array, false --> object).
|
|
|
|
@param[in] is_array Determines if the element list being read is to be
|
|
treated as an object (@a is_array == false), or as an
|
|
array (@a is_array == true).
|
|
@return whether a valid BSON-object/array was passed to the SAX parser
|
|
*/
|
|
bool parse_bson_element_list(const bool is_array)
|
|
{
|
|
string_t key;
|
|
while (int element_type = get())
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::bson, "element list")))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
const std::size_t element_type_parse_position = chars_read;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_bson_cstr(key)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (not is_array and not sax->key(key))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_bson_element_internal(element_type, element_type_parse_position)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
// get_bson_cstr only appends
|
|
key.clear();
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*!
|
|
@brief Reads an array from the BSON input and passes it to the SAX-parser.
|
|
@return whether a valid BSON-array was passed to the SAX parser
|
|
*/
|
|
bool parse_bson_array()
|
|
{
|
|
std::int32_t document_size;
|
|
get_number<std::int32_t, true>(input_format_t::bson, document_size);
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_array(std::size_t(-1))))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_bson_element_list(/*is_array*/true)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
return sax->end_array();
|
|
}
|
|
|
|
//////////
|
|
// CBOR //
|
|
//////////
|
|
|
|
/*!
|
|
@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 CBOR value was passed to the SAX parser
|
|
*/
|
|
bool parse_cbor_internal(const bool get_char = true)
|
|
{
|
|
switch (get_char ? get() : current)
|
|
{
|
|
// EOF
|
|
case std::char_traits<char>::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) and 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) and 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) and 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) and 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)
|
|
{
|
|
std::uint8_t number;
|
|
return get_number(input_format_t::cbor, number) and sax->number_integer(static_cast<number_integer_t>(-1) - number);
|
|
}
|
|
|
|
case 0x39: // Negative integer -1-n (two-byte uint16_t follows)
|
|
{
|
|
std::uint16_t number;
|
|
return get_number(input_format_t::cbor, number) and sax->number_integer(static_cast<number_integer_t>(-1) - number);
|
|
}
|
|
|
|
case 0x3A: // Negative integer -1-n (four-byte uint32_t follows)
|
|
{
|
|
std::uint32_t number;
|
|
return get_number(input_format_t::cbor, number) and sax->number_integer(static_cast<number_integer_t>(-1) - number);
|
|
}
|
|
|
|
case 0x3B: // Negative integer -1-n (eight-byte uint64_t follows)
|
|
{
|
|
std::uint64_t number;
|
|
return get_number(input_format_t::cbor, number) and sax->number_integer(static_cast<number_integer_t>(-1)
|
|
- static_cast<number_integer_t>(number));
|
|
}
|
|
|
|
// 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) and 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 get_cbor_array(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) and get_cbor_array(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0x99: // array (two-byte uint16_t for n follow)
|
|
{
|
|
std::uint16_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_array(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0x9A: // array (four-byte uint32_t for n follow)
|
|
{
|
|
std::uint32_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_array(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0x9B: // array (eight-byte uint64_t for n follow)
|
|
{
|
|
std::uint64_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_array(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0x9F: // array (indefinite length)
|
|
return get_cbor_array(std::size_t(-1));
|
|
|
|
// 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 get_cbor_object(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) and get_cbor_object(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0xB9: // map (two-byte uint16_t for n follow)
|
|
{
|
|
std::uint16_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_object(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0xBA: // map (four-byte uint32_t for n follow)
|
|
{
|
|
std::uint32_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_object(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0xBB: // map (eight-byte uint64_t for n follow)
|
|
{
|
|
std::uint64_t len;
|
|
return get_number(input_format_t::cbor, len) and get_cbor_object(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0xBF: // map (indefinite length)
|
|
return get_cbor_object(std::size_t(-1));
|
|
|
|
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 int byte1_raw = get();
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::cbor, "number")))
|
|
{
|
|
return false;
|
|
}
|
|
const int byte2_raw = get();
|
|
if (JSON_HEDLEY_UNLIKELY(not 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 7049, 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;
|
|
assert(0 <= exp and exp <= 32);
|
|
assert(mant <= 1024);
|
|
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) and 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) and 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, "invalid byte: 0x" + last_token, "value")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@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)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::cbor, "string")))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
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) and 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) and 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) and 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) and get_string(input_format_t::cbor, len, result);
|
|
}
|
|
|
|
case 0x7F: // UTF-8 string (indefinite length)
|
|
{
|
|
while (get() != 0xFF)
|
|
{
|
|
string_t chunk;
|
|
if (not get_cbor_string(chunk))
|
|
{
|
|
return false;
|
|
}
|
|
result.append(chunk);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
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, "expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x" + last_token, "string")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@param[in] len the length of the array or std::size_t(-1) for an
|
|
array of indefinite size
|
|
@return whether array creation completed
|
|
*/
|
|
bool get_cbor_array(const std::size_t len)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_array(len)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (len != std::size_t(-1))
|
|
{
|
|
for (std::size_t i = 0; i < len; ++i)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_cbor_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
while (get() != 0xFF)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_cbor_internal(false)))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
}
|
|
|
|
return sax->end_array();
|
|
}
|
|
|
|
/*!
|
|
@param[in] len the length of the object or std::size_t(-1) for an
|
|
object of indefinite size
|
|
@return whether object creation completed
|
|
*/
|
|
bool get_cbor_object(const std::size_t len)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_object(len)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
string_t key;
|
|
if (len != std::size_t(-1))
|
|
{
|
|
for (std::size_t i = 0; i < len; ++i)
|
|
{
|
|
get();
|
|
if (JSON_HEDLEY_UNLIKELY(not get_cbor_string(key) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_cbor_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
key.clear();
|
|
}
|
|
}
|
|
else
|
|
{
|
|
while (get() != 0xFF)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not get_cbor_string(key) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_cbor_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
key.clear();
|
|
}
|
|
}
|
|
|
|
return sax->end_object();
|
|
}
|
|
|
|
/////////////
|
|
// MsgPack //
|
|
/////////////
|
|
|
|
/*!
|
|
@return whether a valid MessagePack value was passed to the SAX parser
|
|
*/
|
|
bool parse_msgpack_internal()
|
|
{
|
|
switch (get())
|
|
{
|
|
// EOF
|
|
case std::char_traits<char>::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 get_msgpack_object(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 get_msgpack_array(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) and sax->string(s);
|
|
}
|
|
|
|
case 0xC0: // nil
|
|
return sax->null();
|
|
|
|
case 0xC2: // false
|
|
return sax->boolean(false);
|
|
|
|
case 0xC3: // true
|
|
return sax->boolean(true);
|
|
|
|
case 0xCA: // float 32
|
|
{
|
|
float number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_float(static_cast<number_float_t>(number), "");
|
|
}
|
|
|
|
case 0xCB: // float 64
|
|
{
|
|
double number;
|
|
return get_number(input_format_t::msgpack, number) and 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) and sax->number_unsigned(number);
|
|
}
|
|
|
|
case 0xCD: // uint 16
|
|
{
|
|
std::uint16_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_unsigned(number);
|
|
}
|
|
|
|
case 0xCE: // uint 32
|
|
{
|
|
std::uint32_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_unsigned(number);
|
|
}
|
|
|
|
case 0xCF: // uint 64
|
|
{
|
|
std::uint64_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_unsigned(number);
|
|
}
|
|
|
|
case 0xD0: // int 8
|
|
{
|
|
std::int8_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 0xD1: // int 16
|
|
{
|
|
std::int16_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 0xD2: // int 32
|
|
{
|
|
std::int32_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 0xD3: // int 64
|
|
{
|
|
std::int64_t number;
|
|
return get_number(input_format_t::msgpack, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 0xDC: // array 16
|
|
{
|
|
std::uint16_t len;
|
|
return get_number(input_format_t::msgpack, len) and 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) and get_msgpack_array(static_cast<std::size_t>(len));
|
|
}
|
|
|
|
case 0xDE: // map 16
|
|
{
|
|
std::uint16_t len;
|
|
return get_number(input_format_t::msgpack, len) and 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) and get_msgpack_object(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, "invalid byte: 0x" + last_token, "value")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@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(not 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) and get_string(input_format_t::msgpack, len, result);
|
|
}
|
|
|
|
case 0xDA: // str 16
|
|
{
|
|
std::uint16_t len;
|
|
return get_number(input_format_t::msgpack, len) and get_string(input_format_t::msgpack, len, result);
|
|
}
|
|
|
|
case 0xDB: // str 32
|
|
{
|
|
std::uint32_t len;
|
|
return get_number(input_format_t::msgpack, len) and 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, "expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x" + last_token, "string")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@param[in] len the length of the array
|
|
@return whether array creation completed
|
|
*/
|
|
bool get_msgpack_array(const std::size_t len)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_array(len)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
for (std::size_t i = 0; i < len; ++i)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_msgpack_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
|
|
return sax->end_array();
|
|
}
|
|
|
|
/*!
|
|
@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(not sax->start_object(len)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
string_t key;
|
|
for (std::size_t i = 0; i < len; ++i)
|
|
{
|
|
get();
|
|
if (JSON_HEDLEY_UNLIKELY(not get_msgpack_string(key) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_msgpack_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
key.clear();
|
|
}
|
|
|
|
return sax->end_object();
|
|
}
|
|
|
|
////////////
|
|
// 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)
|
|
{
|
|
return get_ubjson_value(get_char ? get_ignore_noop() : current);
|
|
}
|
|
|
|
/*!
|
|
@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)
|
|
{
|
|
get(); // TODO(niels): may we ignore N here?
|
|
}
|
|
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::ubjson, "value")))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
switch (current)
|
|
{
|
|
case 'U':
|
|
{
|
|
std::uint8_t len;
|
|
return get_number(input_format_t::ubjson, len) and get_string(input_format_t::ubjson, len, result);
|
|
}
|
|
|
|
case 'i':
|
|
{
|
|
std::int8_t len;
|
|
return get_number(input_format_t::ubjson, len) and get_string(input_format_t::ubjson, len, result);
|
|
}
|
|
|
|
case 'I':
|
|
{
|
|
std::int16_t len;
|
|
return get_number(input_format_t::ubjson, len) and get_string(input_format_t::ubjson, len, result);
|
|
}
|
|
|
|
case 'l':
|
|
{
|
|
std::int32_t len;
|
|
return get_number(input_format_t::ubjson, len) and get_string(input_format_t::ubjson, len, result);
|
|
}
|
|
|
|
case 'L':
|
|
{
|
|
std::int64_t len;
|
|
return get_number(input_format_t::ubjson, len) and get_string(input_format_t::ubjson, 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::ubjson, "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token, "string")));
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@param[out] result determined size
|
|
@return whether size determination completed
|
|
*/
|
|
bool get_ubjson_size_value(std::size_t& result)
|
|
{
|
|
switch (get_ignore_noop())
|
|
{
|
|
case 'U':
|
|
{
|
|
std::uint8_t number;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_number(input_format_t::ubjson, number)))
|
|
{
|
|
return false;
|
|
}
|
|
result = static_cast<std::size_t>(number);
|
|
return true;
|
|
}
|
|
|
|
case 'i':
|
|
{
|
|
std::int8_t number;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_number(input_format_t::ubjson, number)))
|
|
{
|
|
return false;
|
|
}
|
|
result = static_cast<std::size_t>(number);
|
|
return true;
|
|
}
|
|
|
|
case 'I':
|
|
{
|
|
std::int16_t number;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_number(input_format_t::ubjson, number)))
|
|
{
|
|
return false;
|
|
}
|
|
result = static_cast<std::size_t>(number);
|
|
return true;
|
|
}
|
|
|
|
case 'l':
|
|
{
|
|
std::int32_t number;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_number(input_format_t::ubjson, number)))
|
|
{
|
|
return false;
|
|
}
|
|
result = static_cast<std::size_t>(number);
|
|
return true;
|
|
}
|
|
|
|
case 'L':
|
|
{
|
|
std::int64_t number;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_number(input_format_t::ubjson, number)))
|
|
{
|
|
return false;
|
|
}
|
|
result = static_cast<std::size_t>(number);
|
|
return true;
|
|
}
|
|
|
|
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::ubjson, "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token, "size")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@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
|
|
|
|
@return whether pair creation completed
|
|
*/
|
|
bool get_ubjson_size_type(std::pair<std::size_t, int>& result)
|
|
{
|
|
result.first = string_t::npos; // size
|
|
result.second = 0; // type
|
|
|
|
get_ignore_noop();
|
|
|
|
if (current == '$')
|
|
{
|
|
result.second = get(); // must not ignore 'N', because 'N' maybe the type
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::ubjson, "type")))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
get_ignore_noop();
|
|
if (JSON_HEDLEY_UNLIKELY(current != '#'))
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::ubjson, "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_t::ubjson, "expected '#' after type information; last byte: 0x" + last_token, "size")));
|
|
}
|
|
|
|
return get_ubjson_size_value(result.first);
|
|
}
|
|
|
|
if (current == '#')
|
|
{
|
|
return get_ubjson_size_value(result.first);
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*!
|
|
@param prefix the previously read or set type prefix
|
|
@return whether value creation completed
|
|
*/
|
|
bool get_ubjson_value(const int prefix)
|
|
{
|
|
switch (prefix)
|
|
{
|
|
case std::char_traits<char>::eof(): // EOF
|
|
return unexpect_eof(input_format_t::ubjson, "value");
|
|
|
|
case 'T': // true
|
|
return sax->boolean(true);
|
|
case 'F': // false
|
|
return sax->boolean(false);
|
|
|
|
case 'Z': // null
|
|
return sax->null();
|
|
|
|
case 'U':
|
|
{
|
|
std::uint8_t number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_unsigned(number);
|
|
}
|
|
|
|
case 'i':
|
|
{
|
|
std::int8_t number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 'I':
|
|
{
|
|
std::int16_t number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 'l':
|
|
{
|
|
std::int32_t number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 'L':
|
|
{
|
|
std::int64_t number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_integer(number);
|
|
}
|
|
|
|
case 'd':
|
|
{
|
|
float number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_float(static_cast<number_float_t>(number), "");
|
|
}
|
|
|
|
case 'D':
|
|
{
|
|
double number;
|
|
return get_number(input_format_t::ubjson, number) and sax->number_float(static_cast<number_float_t>(number), "");
|
|
}
|
|
|
|
case 'C': // char
|
|
{
|
|
get();
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::ubjson, "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_t::ubjson, "byte after 'C' must be in range 0x00..0x7F; last byte: 0x" + last_token, "char")));
|
|
}
|
|
string_t s(1, static_cast<char>(current));
|
|
return sax->string(s);
|
|
}
|
|
|
|
case 'S': // string
|
|
{
|
|
string_t s;
|
|
return get_ubjson_string(s) and sax->string(s);
|
|
}
|
|
|
|
case '[': // array
|
|
return get_ubjson_array();
|
|
|
|
case '{': // object
|
|
return get_ubjson_object();
|
|
|
|
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::ubjson, "invalid byte: 0x" + last_token, "value")));
|
|
}
|
|
}
|
|
}
|
|
|
|
/*!
|
|
@return whether array creation completed
|
|
*/
|
|
bool get_ubjson_array()
|
|
{
|
|
std::pair<std::size_t, int> size_and_type;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_size_type(size_and_type)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (size_and_type.first != string_t::npos)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_array(size_and_type.first)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
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(not get_ubjson_value(size_and_type.second)))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
for (std::size_t i = 0; i < size_and_type.first; ++i)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_ubjson_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_array(std::size_t(-1))))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
while (current != ']')
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_ubjson_internal(false)))
|
|
{
|
|
return false;
|
|
}
|
|
get_ignore_noop();
|
|
}
|
|
}
|
|
|
|
return sax->end_array();
|
|
}
|
|
|
|
/*!
|
|
@return whether object creation completed
|
|
*/
|
|
bool get_ubjson_object()
|
|
{
|
|
std::pair<std::size_t, int> size_and_type;
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_size_type(size_and_type)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
string_t key;
|
|
if (size_and_type.first != string_t::npos)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_object(size_and_type.first)))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
if (size_and_type.second != 0)
|
|
{
|
|
for (std::size_t i = 0; i < size_and_type.first; ++i)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_string(key) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_value(size_and_type.second)))
|
|
{
|
|
return false;
|
|
}
|
|
key.clear();
|
|
}
|
|
}
|
|
else
|
|
{
|
|
for (std::size_t i = 0; i < size_and_type.first; ++i)
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_string(key) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_ubjson_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
key.clear();
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not sax->start_object(std::size_t(-1))))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
while (current != '}')
|
|
{
|
|
if (JSON_HEDLEY_UNLIKELY(not get_ubjson_string(key, false) or not sax->key(key)))
|
|
{
|
|
return false;
|
|
}
|
|
if (JSON_HEDLEY_UNLIKELY(not parse_ubjson_internal()))
|
|
{
|
|
return false;
|
|
}
|
|
get_ignore_noop();
|
|
key.clear();
|
|
}
|
|
}
|
|
|
|
return sax->end_object();
|
|
}
|
|
|
|
///////////////////////
|
|
// 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
|
|
`std::char_traits<char>::eof()` in that case.
|
|
|
|
@return character read from the input
|
|
*/
|
|
int get()
|
|
{
|
|
++chars_read;
|
|
return current = ia->get_character();
|
|
}
|
|
|
|
/*!
|
|
@return character read from the input after ignoring all 'N' entries
|
|
*/
|
|
int get_ignore_noop()
|
|
{
|
|
do
|
|
{
|
|
get();
|
|
}
|
|
while (current == 'N');
|
|
|
|
return current;
|
|
}
|
|
|
|
/*
|
|
@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 endianess, because
|
|
bytes in CBOR, MessagePack, and UBJSON are stored in network order
|
|
(big endian) and therefore need reordering on little endian systems.
|
|
*/
|
|
template<typename NumberType, bool InputIsLittleEndian = false>
|
|
bool get_number(const input_format_t format, NumberType& result)
|
|
{
|
|
// step 1: read input into array with system's byte order
|
|
std::array<std::uint8_t, sizeof(NumberType)> vec;
|
|
for (std::size_t i = 0; i < sizeof(NumberType); ++i)
|
|
{
|
|
get();
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(format, "number")))
|
|
{
|
|
return false;
|
|
}
|
|
|
|
// reverse byte order prior to conversion if necessary
|
|
if (is_little_endian != InputIsLittleEndian)
|
|
{
|
|
vec[sizeof(NumberType) - i - 1] = static_cast<std::uint8_t>(current);
|
|
}
|
|
else
|
|
{
|
|
vec[i] = static_cast<std::uint8_t>(current); // LCOV_EXCL_LINE
|
|
}
|
|
}
|
|
|
|
// step 2: convert array into number of type T and return
|
|
std::memcpy(&result, vec.data(), sizeof(NumberType));
|
|
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)
|
|
{
|
|
bool success = true;
|
|
std::generate_n(std::back_inserter(result), len, [this, &success, &format]()
|
|
{
|
|
get();
|
|
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(format, "string")))
|
|
{
|
|
success = false;
|
|
}
|
|
return static_cast<char>(current);
|
|
});
|
|
return success;
|
|
}
|
|
|
|
/*!
|
|
@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 == std::char_traits<char>::eof()))
|
|
{
|
|
return sax->parse_error(chars_read, "<end of file>",
|
|
parse_error::create(110, chars_read, exception_message(format, "unexpected end of input", context)));
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/*!
|
|
@return a string representation of the last read byte
|
|
*/
|
|
std::string get_token_string() const
|
|
{
|
|
std::array<char, 3> cr{{}};
|
|
(std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(current));
|
|
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;
|
|
|
|
default: // LCOV_EXCL_LINE
|
|
assert(false); // LCOV_EXCL_LINE
|
|
}
|
|
|
|
return error_msg + " " + context + ": " + detail;
|
|
}
|
|
|
|
private:
|
|
/// input adapter
|
|
input_adapter_t ia = nullptr;
|
|
|
|
/// the current character
|
|
int current = std::char_traits<char>::eof();
|
|
|
|
/// the number of characters read
|
|
std::size_t chars_read = 0;
|
|
|
|
/// whether we can assume little endianess
|
|
const bool is_little_endian = little_endianess();
|
|
|
|
/// the SAX parser
|
|
json_sax_t* sax = nullptr;
|
|
};
|
|
} // namespace detail
|
|
} // namespace nlohmann
|