j3d1/json
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Add binary type support to all binary file formats, as well as an internally represented binary type

Browse source
This commit is contained in:
Michael Reilly 2019-07-05 00:13:25 -04:00
parent 6121fc52cf
commit 012c9665ac
21 changed files with 3008 additions and 106 deletions
Download patch file Download diff file Expand all files Collapse all files

316
include/nlohmann/detail/input/binary_reader.hpp
View file

@ -38,6 +38,7 @@ class binary_reader
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 internal_binary_t = typename BasicJsonType::internal_binary_t;
using json_sax_t = SAX;
public:
@ -207,6 +208,30 @@ class binary_reader
return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result) and get() != std::char_traits<char>::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, internal_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, "byte array length cannot be negative, is " + std::to_string(len), "binary")));
}
result.has_subtype = true; // All BSON binary values have a subtype
get_number<std::uint8_t>(input_format_t::bson, result.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
@ -245,6 +270,13 @@ class binary_reader
return parse_bson_array();
}
case 0x05: // binary
{
std::int32_t len;
internal_binary_t value;
return get_number<std::int32_t, true>(input_format_t::bson, len) and get_bson_binary(len, value) and sax->binary(value);
}
case 0x08: // boolean
{
return sax->boolean(get() != 0);
@ -291,6 +323,7 @@ class binary_reader
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")))
@ -465,6 +498,41 @@ class binary_reader
- static_cast<number_integer_t>(number));
}
// 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)
{
internal_binary_t b;
return get_cbor_binary(b) and sax->binary(b);
}
// UTF-8 string (0x00..0x17 bytes follow)
case 0x60:
case 0x61:
@ -780,6 +848,101 @@ class binary_reader
}
}
/*!
@brief reads a CBOR byte array
This function first reads starting bytes to determine the expected
byte array length and then copies this number of bytes into the byte array.
Additionally, CBOR's byte arrays with indefinite lengths are supported.
@param[out] result created byte array
@return whether byte array creation completed
*/
bool get_cbor_binary(internal_binary_t& result)
{
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::cbor, "binary")))
{
return false;
}
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) and 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) and 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) and 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) and get_binary(input_format_t::cbor, len, result);
}
case 0x5F: // Binary data (indefinite length)
{
while (get() != 0xFF)
{
internal_binary_t chunk;
if (not get_cbor_binary(chunk))
{
return false;
}
result.insert(result.end(), chunk.begin(), chunk.end());
}
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 (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x" + last_token, "binary")));
}
}
}
/*!
@param[in] len the length of the array or std::size_t(-1) for an
array of indefinite size
@ -1100,6 +1263,22 @@ class binary_reader
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
{
internal_binary_t b;
return get_msgpack_binary(b) and sax->binary(b);
}
case 0xCA: // float 32
{
float number;
@ -1309,6 +1488,108 @@ class binary_reader
}
}
/*!
@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(internal_binary_t& result)
{
if (JSON_HEDLEY_UNLIKELY(not unexpect_eof(input_format_t::msgpack, "binary")))
{
return false;
}
switch (current)
{
case 0xC4: // bin 8
{
std::uint8_t len;
return get_number(input_format_t::msgpack, len) and get_binary(input_format_t::msgpack, len, result);
}
case 0xC5: // bin 16
{
std::uint16_t len;
return get_number(input_format_t::msgpack, len) and get_binary(input_format_t::msgpack, len, result);
}
case 0xC6: // bin 32
{
std::uint32_t len;
return get_number(input_format_t::msgpack, len) and get_binary(input_format_t::msgpack, len, result);
}
case 0xC7: // ext 8
{
std::uint8_t len;
result.has_subtype = true;
return get_number(input_format_t::msgpack, len) and
get_number(input_format_t::msgpack, result.subtype) and
get_binary(input_format_t::msgpack, len, result);
}
case 0xC8: // ext 16
{
std::uint16_t len;
result.has_subtype = true;
return get_number(input_format_t::msgpack, len) and
get_number(input_format_t::msgpack, result.subtype) and
get_binary(input_format_t::msgpack, len, result);
}
case 0xC9: // ext 32
{
std::uint32_t len;
result.has_subtype = true;
return get_number(input_format_t::msgpack, len) and
get_number(input_format_t::msgpack, result.subtype) and
get_binary(input_format_t::msgpack, len, result);
}
case 0xD4: // fixext 1
{
result.has_subtype = true;
return get_number(input_format_t::msgpack, result.subtype) and get_binary(input_format_t::msgpack, 1, result);
}
case 0xD5: // fixext 2
{
result.has_subtype = true;
return get_number(input_format_t::msgpack, result.subtype) and get_binary(input_format_t::msgpack, 2, result);
}
case 0xD6: // fixext 4
{
result.has_subtype = true;
return get_number(input_format_t::msgpack, result.subtype) and get_binary(input_format_t::msgpack, 4, result);
}
case 0xD7: // fixext 8
{
result.has_subtype = true;
return get_number(input_format_t::msgpack, result.subtype) and get_binary(input_format_t::msgpack, 8, result);
}
case 0xD8: // fixext 16
{
result.has_subtype = true;
return get_number(input_format_t::msgpack, result.subtype) and get_binary(input_format_t::msgpack, 16, 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 binary type specification (0xC4-0xC9, 0xD4-0xD8); last byte: 0x" + last_token, "binary")));
}
}
}
/*!
@param[in] len the length of the array
@return whether array creation completed
@ -1793,6 +2074,9 @@ class binary_reader
return sax->end_object();
}
// Note, no reader for UBJSON binary types is implemented because they do
// not exist
///////////////////////
// Utility functions //
///////////////////////
@ -1900,6 +2184,38 @@ class binary_reader
return success;
}
/*!
@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,
internal_binary_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, "binary")))
{
success = false;
}
return static_cast<uint8_t>(current);
});
return success;
}
/*!
@param[in] format the current format (for diagnostics)
@param[in] context further context information (for diagnostics)

63
include/nlohmann/detail/input/json_sax.hpp
View file

@ -31,6 +31,7 @@ struct json_sax
using number_float_t = typename BasicJsonType::number_float_t;
/// type for strings
using string_t = typename BasicJsonType::string_t;
using binary_t = typename BasicJsonType::binary_t;
/*!
@brief a null value was read
@ -75,6 +76,14 @@ struct json_sax
*/
virtual bool string(string_t& val) = 0;
/*!
@brief a binary string was read
@param[in] val binary value
@return whether parsing should proceed
@note It is safe to move the passed binary.
*/
virtual bool binary(binary_t& val) = 0;
/*!
@brief the beginning of an object was read
@param[in] elements number of object elements or -1 if unknown
@ -149,6 +158,7 @@ class json_sax_dom_parser
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;
/*!
@param[in, out] r reference to a JSON value that is manipulated while
@ -202,6 +212,12 @@ class json_sax_dom_parser
return true;
}
bool binary(binary_t& val)
{
handle_binary(val);
return true;
}
bool start_object(std::size_t len)
{
ref_stack.push_back(handle_value(BasicJsonType::value_t::object));
@ -311,6 +327,36 @@ class json_sax_dom_parser
return object_element;
}
/*!
@invariant If the ref stack is empty, then the passed value will be the new
root.
@invariant If the ref stack contains a value, then it is an array or an
object to which we can add elements
*/
template<typename BinaryValue>
JSON_HEDLEY_RETURNS_NON_NULL
BasicJsonType* handle_binary(BinaryValue&& v)
{
if (ref_stack.empty())
{
root = BasicJsonType::binary_array(std::forward<BinaryValue>(v));
return &root;
}
assert(ref_stack.back()->is_array() or ref_stack.back()->is_object());
if (ref_stack.back()->is_array())
{
ref_stack.back()->m_value.array->emplace_back(BasicJsonType::binary_array(std::forward<BinaryValue>(v)));
return &(ref_stack.back()->m_value.array->back());
}
assert(ref_stack.back()->is_object());
assert(object_element);
*object_element = BasicJsonType::binary_array(std::forward<BinaryValue>(v));
return object_element;
}
/// the parsed JSON value
BasicJsonType& root;
/// stack to model hierarchy of values
@ -331,6 +377,7 @@ class json_sax_dom_callback_parser
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 parser_callback_t = typename BasicJsonType::parser_callback_t;
using parse_event_t = typename BasicJsonType::parse_event_t;
@ -385,6 +432,12 @@ class json_sax_dom_callback_parser
return true;
}
bool binary(binary_t& val)
{
handle_value(val);
return true;
}
bool start_object(std::size_t len)
{
// check callback for object start
@ -635,6 +688,7 @@ class json_sax_acceptor
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;
bool null()
{
@ -666,7 +720,12 @@ class json_sax_acceptor
return true;
}
bool start_object(std::size_t /*unused*/ = std::size_t(-1))
bool binary(binary_t& /*unused*/)
{
return true;
}
bool start_object(std::size_t /*unused*/ = std::size_t(-1))
{
return true;
}
@ -681,7 +740,7 @@ class json_sax_acceptor
return true;
}
bool start_array(std::size_t /*unused*/ = std::size_t(-1))
bool start_array(std::size_t /*unused*/ = std::size_t(-1))
{
return true;
}