Unverified Commit bba15912 authored by Niels Lohmann's avatar Niels Lohmann

Merge branch 'feature/bson' of https://github.com/julian-becker/json into...

Merge branch 'feature/bson' of https://github.com/julian-becker/json into julian-becker-feature/bson
parents f102df3c ad11b6c3
......@@ -93,6 +93,7 @@ json.exception.parse_error.109 | parse error: array index 'one' is not a number
json.exception.parse_error.110 | parse error at 1: cannot read 2 bytes from vector | When parsing CBOR or MessagePack, the byte vector ends before the complete value has been read.
json.exception.parse_error.112 | parse error at 1: error reading CBOR; last byte: 0xF8 | Not all types of CBOR or MessagePack are supported. This exception occurs if an unsupported byte was read.
json.exception.parse_error.113 | parse error at 2: expected a CBOR string; last byte: 0x98 | While parsing a map key, a value that is not a string has been read.
json.exception.parse_error.114 | parse error: Unsupported BSON record type 0x0F | The parsing of the corresponding BSON record type is not implemented (yet).
@note For an input with n bytes, 1 is the index of the first character and n+1
is the index of the terminating null byte or the end of file. This also
......@@ -236,6 +237,7 @@ json.exception.type_error.313 | invalid value to unflatten | The @ref unflatten
json.exception.type_error.314 | only objects can be unflattened | The @ref unflatten function only works for an object whose keys are JSON Pointers.
json.exception.type_error.315 | values in object must be primitive | The @ref unflatten function only works for an object whose keys are JSON Pointers and whose values are primitive.
json.exception.type_error.316 | invalid UTF-8 byte at index 10: 0x7E | The @ref dump function only works with UTF-8 encoded strings; that is, if you assign a `std::string` to a JSON value, make sure it is UTF-8 encoded. |
json.exception.type_error.317 | JSON value cannot be serialized to requested format | The dynamic type of the object cannot be represented in the requested serialization format (e.g. a raw `true` or `null` JSON object cannot be serialized to BSON) |
@liveexample{The following code shows how a `type_error` exception can be
caught.,type_error}
......@@ -278,8 +280,9 @@ json.exception.out_of_range.403 | key 'foo' not found | The provided key was not
json.exception.out_of_range.404 | unresolved reference token 'foo' | A reference token in a JSON Pointer could not be resolved.
json.exception.out_of_range.405 | JSON pointer has no parent | The JSON Patch operations 'remove' and 'add' can not be applied to the root element of the JSON value.
json.exception.out_of_range.406 | number overflow parsing '10E1000' | A parsed number could not be stored as without changing it to NaN or INF.
json.exception.out_of_range.407 | number overflow serializing '9223372036854775808' | UBJSON only supports integers numbers up to 9223372036854775807. |
json.exception.out_of_range.407 | number overflow serializing '9223372036854775808' | UBJSON and BSON only support integer numbers up to 9223372036854775807. |
json.exception.out_of_range.408 | excessive array size: 8658170730974374167 | The size (following `#`) of an UBJSON array or object exceeds the maximal capacity. |
json.exception.out_of_range.409 | BSON key cannot contain code point U+0000 (at byte 2) | Key identifiers to be serialized to BSON cannot contain code point U+0000, since the key is stored as zero-terminated c-string |
@liveexample{The following code shows how an `out_of_range` exception can be
caught.,out_of_range}
......
......@@ -80,6 +80,10 @@ class binary_reader
result = parse_ubjson_internal();
break;
case input_format_t::bson:
result = parse_bson_internal();
break;
// LCOV_EXCL_START
default:
assert(false);
......@@ -121,6 +125,207 @@ class binary_reader
}
private:
/*!
@brief Parses a C-style string from the BSON input.
@param [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_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 [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 > 0
@return `true` if the string was successfully parsed
*/
template <typename NumberType>
bool get_bson_string(const NumberType len, string_t& result)
{
return get_string(input_format_t::bson, len - static_cast<NumberType>(1), result)
&& get() != std::char_traits<char>::eof();
}
/*!
@return A hexadecimal string representation of the given @a byte
@param byte The byte to convert to a string
*/
static std::string byte_hexstring(unsigned char byte)
{
char cr[3];
snprintf(cr, sizeof(cr), "%02hhX", byte);
return std::string{cr};
}
/*!
@brief Read a BSON document element of the given @a element_type.
@param element_type The BSON element type, c.f. http://bsonspec.org/spec.html
@param 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(int element_type, 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 0x08: // boolean
{
return sax->boolean(static_cast<bool>(get()));
}
case 0x10: // int32
{
std::int32_t value;
return get_number<std::int32_t, true>(input_format_t::bson, value)
&& sax->number_integer(static_cast<std::int32_t>(value));
}
case 0x12: // int64
{
std::int64_t value;
return get_number<std::int64_t, true>(input_format_t::bson, value)
&& sax->number_integer(static_cast<std::int64_t>(value));
}
case 0x0A: // null
{
return sax->null();
}
case 0x03: // object
{
return parse_bson_internal();
}
case 0x04: // array
{
return parse_bson_array();
}
default: // anything else not supported (yet)
{
auto element_type_str = byte_hexstring(element_type);
return sax->parse_error(element_type_parse_position, element_type_str, parse_error::create(114, element_type_parse_position, "Unsupported BSON record type 0x" + element_type_str));
}
}
}
/*!
@brief Read a BSON element list (as specified in the BSON-spec) from the input
and passes it to the SAX-parser.
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 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(bool is_array)
{
while (auto element_type = get())
{
if (JSON_UNLIKELY(not unexpect_eof(input_format_t::bson, "element list")))
{
return false;
}
const std::size_t element_type_parse_position = chars_read;
string_t key;
if (JSON_UNLIKELY(not get_bson_cstr(key)))
{
return false;
}
if (!is_array)
{
sax->key(key);
}
if (JSON_UNLIKELY(not parse_bson_element_internal(element_type, element_type_parse_position)))
{
return false;
}
}
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 documentSize;
get_number<std::int32_t, true>(input_format_t::bson, documentSize);
if (JSON_UNLIKELY(not sax->start_array(-1)))
{
return false;
}
if (JSON_UNLIKELY(not parse_bson_element_list(/*is_array*/true)))
{
return false;
}
return sax->end_array();
}
/*!
@brief Reads in a BSON-object and pass it to the SAX-parser.
@return whether a valid BSON-value was passed to the SAX parser
*/
bool parse_bson_internal()
{
std::int32_t documentSize;
get_number<std::int32_t, true>(input_format_t::bson, documentSize);
if (JSON_UNLIKELY(not sax->start_object(-1)))
{
return false;
}
if (JSON_UNLIKELY(not parse_bson_element_list(/*is_array*/false)))
{
return false;
}
return sax->end_object();
}
/*!
@param[in] get_char whether a new character should be retrieved from the
input (true, default) or whether the last read
......@@ -875,7 +1080,7 @@ class binary_reader
bytes in CBOR, MessagePack, and UBJSON are stored in network order
(big endian) and therefore need reordering on little endian systems.
*/
template<typename NumberType>
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
......@@ -889,7 +1094,7 @@ class binary_reader
}
// reverse byte order prior to conversion if necessary
if (is_little_endian)
if (is_little_endian && !InputIsLittleEndian)
{
vec[sizeof(NumberType) - i - 1] = static_cast<uint8_t>(current);
}
......@@ -904,6 +1109,7 @@ class binary_reader
return true;
}
/*!
@brief create a string by reading characters from the input
......@@ -1715,6 +1921,10 @@ class binary_reader
error_msg += "UBJSON";
break;
case input_format_t::bson:
error_msg += "BSON";
break;
// LCOV_EXCL_START
default:
assert(false);
......
......@@ -18,7 +18,7 @@ namespace nlohmann
namespace detail
{
/// the supported input formats
enum class input_format_t { json, cbor, msgpack, ubjson };
enum class input_format_t { json, cbor, msgpack, ubjson, bson };
////////////////////
// input adapters //
......
......@@ -6627,6 +6627,87 @@ class basic_json
binary_writer<char>(o).write_ubjson(j, use_size, use_type);
}
/*!
@brief Serializes the given JSON object `j` to BSON and returns a vector
containing the corresponding BSON-representation.
BSON (Binary JSON) is a binary format in which zero or more ordered key/value pairs are
stored as a single entity (a so-called document).
The library uses the following mapping from JSON values types to BSON types:
JSON value type | value/range | BSON type | marker
--------------- | --------------------------------- | ----------- | ------
null | `null` | null | 0x0A
boolean | `true`, `false` | boolean | 0x08
number_integer | -9223372036854775808..-2147483649 | int64 | 0x12
number_integer | -2147483648..2147483647 | int32 | 0x10
number_integer | 2147483648..9223372036854775807 | int64 | 0x12
number_unsigned | 0..2147483647 | int32 | 0x10
number_unsigned | 2147483648..9223372036854775807 | int64 | 0x12
number_unsigned | 9223372036854775808..18446744073709551615| -- | --
number_float | *any value* | double | 0x01
string | *any value* | string | 0x02
array | *any value* | document | 0x04
object | *any value* | document | 0x03
@warning The mapping is **incomplete**, since only JSON-objects (and things
contained therein) can be serialized to BSON.
Also, integers larger than 9223372036854775807 cannot be serialized to BSON,
and the keys may not contain U+0000, since they are serialized a
zero-terminated c-strings.
@throw out_of_range.407 if `j.is_number_unsigned() && j.get<std::uint64_t>() > 9223372036854775807`
@throw out_of_range.409 if a key in `j` contains a NULL (U+0000)
@throw type_error.317 if `!j.is_object()`
@pre The input `j` is required to be an object: `j.is_object() == true`.
@note Any BSON output created via @ref to_bson can be successfully parsed
by @ref from_bson.
@param[in] j JSON value to serialize
@return BSON serialization as byte vector
@complexity Linear in the size of the JSON value @a j.
@sa http://bsonspec.org/spec.html
@sa @ref from_bson(detail::input_adapter, const bool strict) for the
analogous deserialization
@sa @ref to_ubjson(const basic_json&) for the related UBJSON format
@sa @ref to_cbor(const basic_json&) for the related CBOR format
@sa @ref to_msgpack(const basic_json&) for the related MessagePack format
*/
static std::vector<uint8_t> to_bson(const basic_json& j)
{
std::vector<uint8_t> result;
to_bson(j, result);
return result;
}
/*!
@brief Serializes the given JSON object `j` to BSON and forwards the
corresponding BSON-representation to the given output_adapter `o`.
@param j The JSON object to convert to BSON.
@param o The output adapter that receives the binary BSON representation.
@pre The input `j` shall be an object: `j.is_object() == true`
@sa @ref to_bson(const basic_json&)
*/
static void to_bson(const basic_json& j, detail::output_adapter<uint8_t> o)
{
binary_writer<uint8_t>(o).write_bson(j);
}
/*!
@copydoc to_bson(const basic_json&, detail::output_adapter<uint8_t>)
*/
static void to_bson(const basic_json& j, detail::output_adapter<char> o)
{
binary_writer<char>(o).write_bson(j);
}
/*!
@brief create a JSON value from an input in CBOR format
......@@ -6821,6 +6902,8 @@ class basic_json
related CBOR format
@sa @ref from_ubjson(detail::input_adapter&&, const bool, const bool) for
the related UBJSON format
@sa @ref from_bson(detail::input_adapter, const bool, const bool) for
the related BSON format
@since version 2.0.9; parameter @a start_index since 2.1.1; changed to
consume input adapters, removed start_index parameter, and added
......@@ -6906,6 +6989,8 @@ class basic_json
related CBOR format
@sa @ref from_msgpack(detail::input_adapter&&, const bool, const bool) for
the related MessagePack format
@sa @ref from_bson(detail::input_adapter, const bool, const bool) for
the related BSON format
@since version 3.1.0; added @a allow_exceptions parameter since 3.2.0
*/
......@@ -6934,6 +7019,91 @@ class basic_json
return res ? result : basic_json(value_t::discarded);
}
/*!
@brief Create a JSON value from an input in BSON format
Deserializes a given input @a i to a JSON value using the BSON (Binary JSON)
serialization format.
The library maps BSON record types to JSON value types as follows:
BSON type | BSON marker byte | JSON value type
--------------- | ---------------- | ---------------------------
double | 0x01 | number_float
string | 0x02 | string
document | 0x03 | object
array | 0x04 | array
binary | 0x05 | still unsupported
undefined | 0x06 | still unsupported
ObjectId | 0x07 | still unsupported
boolean | 0x08 | boolean
UTC Date-Time | 0x09 | still unsupported
null | 0x0A | null
Regular Expr. | 0x0B | still unsupported
DB Pointer | 0x0C | still unsupported
JavaScript Code | 0x0D | still unsupported
Symbol | 0x0E | still unsupported
JavaScript Code | 0x0F | still unsupported
int32 | 0x10 | number_integer
Timestamp | 0x11 | still unsupported
128-bit decimal float | 0x13 | still unsupported
Max Key | 0x7F | still unsupported
Min Key | 0xFF | still unsupported
@warning The mapping is **incomplete**. The unsupported mappings
are indicated in the table above.
@param[in] i an input in BSON format convertible to an input adapter
@param[in] strict whether to expect the input to be consumed until EOF
(true by default)
@param[in] allow_exceptions whether to throw exceptions in case of a
parse error (optional, true by default)
@return deserialized JSON value
@throw parse_error.114 if an unsupported BSON record type is encountered
@sa http://bsonspec.org/spec.html
@sa @ref to_bson(const basic_json&, const bool, const bool) for the
analogous serialization
@sa @ref from_cbor(detail::input_adapter, const bool, const bool) for the
related CBOR format
@sa @ref from_msgpack(detail::input_adapter, const bool, const bool) for
the related MessagePack format
@sa @ref from_ubjson(detail::input_adapter, const bool, const bool) for the
related UBJSON format
*/
static basic_json from_bson(detail::input_adapter&& i,
const bool strict = true,
const bool allow_exceptions = true)
{
basic_json result;
detail::json_sax_dom_parser<basic_json> sdp(result, allow_exceptions);
const bool res = binary_reader(detail::input_adapter(i)).sax_parse(input_format_t::bson, &sdp, strict);
return res ? result : basic_json(value_t::discarded);
}
/*!
@copydoc from_bson(detail::input_adapter&&, const bool, const bool)
*/
template<typename A1, typename A2,
detail::enable_if_t<std::is_constructible<detail::input_adapter, A1, A2>::value, int> = 0>
static basic_json from_bson(A1 && a1, A2 && a2,
const bool strict = true,
const bool allow_exceptions = true)
{
basic_json result;
detail::json_sax_dom_parser<basic_json> sdp(result, allow_exceptions);
const bool res = binary_reader(detail::input_adapter(std::forward<A1>(a1), std::forward<A2>(a2))).sax_parse(input_format_t::bson, &sdp, strict);
return res ? result : basic_json(value_t::discarded);
}
/// @}
//////////////////////////
......
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment