12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321 |
- #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
- {
- /*!
- @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
- */
- static inline bool little_endianess(int num = 1) noexcept
- {
- return *reinterpret_cast<char*>(&num) == 1;
- }
- ///////////////////
- // binary reader //
- ///////////////////
- /*!
- @brief deserialization of CBOR, MessagePack, and UBJSON values
- */
- template<typename BasicJsonType, typename InputAdapterType, 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 binary_t = typename BasicJsonType::binary_t;
- using json_sax_t = SAX;
- public:
- /*!
- @brief create a binary reader
- @param[in] adapter input adapter to read from
- */
- explicit binary_reader(InputAdapterType&& adapter) : ia(std::move(adapter))
- {
- (void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
- }
- // 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;
- }
- 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 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, "byte array length cannot be negative, is " + std::to_string(len), "binary")));
- }
- // All BSON binary values have a subtype
- std::uint8_t subtype;
- get_number<std::uint8_t>(input_format_t::bson, subtype);
- 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 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 0x05: // binary
- {
- std::int32_t len;
- 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);
- }
- 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));
- }
- // 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) and 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) 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")));
- }
- }
- }
- /*!
- @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)
- {
- 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)
- {
- 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
- @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 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) and sax->binary(b);
- }
- 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")));
- }
- }
- }
- /*!
- @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) 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;
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, len) and
- get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, len, result) and
- 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) and
- get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, len, result) and
- 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) and
- get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, len, result) and
- assign_and_return_true(subtype);
- }
- case 0xD4: // fixext 1
- {
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, 1, result) and
- assign_and_return_true(subtype);
- }
- case 0xD5: // fixext 2
- {
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, 2, result) and
- assign_and_return_true(subtype);
- }
- case 0xD6: // fixext 4
- {
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, 4, result) and
- assign_and_return_true(subtype);
- }
- case 0xD7: // fixext 8
- {
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, 8, result) and
- assign_and_return_true(subtype);
- }
- case 0xD8: // fixext 16
- {
- std::int8_t subtype;
- return get_number(input_format_t::msgpack, subtype) and
- get_binary(input_format_t::msgpack, 16, result) and
- assign_and_return_true(subtype);
- }
- default: // LCOV_EXCL_LINE
- return false; // LCOV_EXCL_LINE
- }
- }
- /*!
- @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();
- }
- // Note, no reader for UBJSON binary types is implemented because they do
- // not exist
- ///////////////////////
- // 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;
- }
- /*!
- @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)
- {
- 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<std::uint8_t>(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
- InputAdapterType ia;
- /// 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
|