From 782570d46fffc54ff1a98fc3045a7b9e509138b5 Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Mon, 3 Apr 2017 22:58:46 +0200 Subject: [PATCH] :hammer: cleanup --- src/json.hpp | 683 +++++++-------------------------------------------- 1 file changed, 89 insertions(+), 594 deletions(-) diff --git a/src/json.hpp b/src/json.hpp index 9fadcae82..91a83731d 100644 --- a/src/json.hpp +++ b/src/json.hpp @@ -8397,505 +8397,6 @@ class basic_json } } - /*! - @brief create a JSON value from a given CBOR vector - - @param[in] v CBOR serialization - @param[in] idx byte index to start reading from @a v - - @return deserialized JSON value - - @throw parse_error.110 if the given vector ends prematurely - @throw parse_error.112 if unsupported features from CBOR were - used in the given vector @a v or if the input is not valid CBOR - @throw parse_error.113 if a string was expected as map key, but not found - - @sa https://tools.ietf.org/html/rfc7049 - */ - static basic_json from_cbor_internal(const std::vector& v, size_t& idx) - { - // store and increment index - const size_t current_idx = idx++; - - // make sure reading 1 byte is safe - check_length(v.size(), 1, current_idx); - - switch (v[current_idx]) - { - // 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 v[current_idx]; - } - - case 0x18: // Unsigned integer (one-byte uint8_t follows) - { - idx += 1; // skip content byte - return get_from_vector(v, current_idx); - } - - case 0x19: // Unsigned integer (two-byte uint16_t follows) - { - idx += 2; // skip 2 content bytes - return get_from_vector(v, current_idx); - } - - case 0x1a: // Unsigned integer (four-byte uint32_t follows) - { - idx += 4; // skip 4 content bytes - return get_from_vector(v, current_idx); - } - - case 0x1b: // Unsigned integer (eight-byte uint64_t follows) - { - idx += 8; // skip 8 content bytes - return get_from_vector(v, current_idx); - } - - // 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 static_cast(0x20 - 1 - v[current_idx]); - } - - case 0x38: // Negative integer (one-byte uint8_t follows) - { - idx += 1; // skip content byte - // must be uint8_t ! - return static_cast(-1) - get_from_vector(v, current_idx); - } - - case 0x39: // Negative integer -1-n (two-byte uint16_t follows) - { - idx += 2; // skip 2 content bytes - return static_cast(-1) - get_from_vector(v, current_idx); - } - - case 0x3a: // Negative integer -1-n (four-byte uint32_t follows) - { - idx += 4; // skip 4 content bytes - return static_cast(-1) - get_from_vector(v, current_idx); - } - - case 0x3b: // Negative integer -1-n (eight-byte uint64_t follows) - { - idx += 8; // skip 8 content bytes - return static_cast(-1) - static_cast(get_from_vector(v, current_idx)); - } - - // 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: - { - const auto len = static_cast(v[current_idx] - 0x60); - const size_t offset = current_idx + 1; - idx += len; // skip content bytes - check_length(v.size(), len, offset); - return std::string(reinterpret_cast(v.data()) + offset, len); - } - - case 0x78: // UTF-8 string (one-byte uint8_t for n follows) - { - const auto len = static_cast(get_from_vector(v, current_idx)); - const size_t offset = current_idx + 2; - idx += len + 1; // skip size byte + content bytes - check_length(v.size(), len, offset); - return std::string(reinterpret_cast(v.data()) + offset, len); - } - - case 0x79: // UTF-8 string (two-byte uint16_t for n follow) - { - const auto len = static_cast(get_from_vector(v, current_idx)); - const size_t offset = current_idx + 3; - idx += len + 2; // skip 2 size bytes + content bytes - check_length(v.size(), len, offset); - return std::string(reinterpret_cast(v.data()) + offset, len); - } - - case 0x7a: // UTF-8 string (four-byte uint32_t for n follow) - { - const auto len = static_cast(get_from_vector(v, current_idx)); - const size_t offset = current_idx + 5; - idx += len + 4; // skip 4 size bytes + content bytes - check_length(v.size(), len, offset); - return std::string(reinterpret_cast(v.data()) + offset, len); - } - - case 0x7b: // UTF-8 string (eight-byte uint64_t for n follow) - { - const auto len = static_cast(get_from_vector(v, current_idx)); - const size_t offset = current_idx + 9; - idx += len + 8; // skip 8 size bytes + content bytes - check_length(v.size(), len, offset); - return std::string(reinterpret_cast(v.data()) + offset, len); - } - - case 0x7f: // UTF-8 string (indefinite length) - { - std::string result; - while (static_cast(check_length(v.size(), 1, idx)), v[idx] != 0xff) - { - string_t s = from_cbor_internal(v, idx); - result += s; - } - // skip break byte (0xFF) - idx += 1; - return result; - } - - // 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: - { - basic_json result = value_t::array; - const auto len = static_cast(v[current_idx] - 0x80); - for (size_t i = 0; i < len; ++i) - { - result.push_back(from_cbor_internal(v, idx)); - } - return result; - } - - case 0x98: // array (one-byte uint8_t for n follows) - { - basic_json result = value_t::array; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 1; // skip 1 size byte - for (size_t i = 0; i < len; ++i) - { - result.push_back(from_cbor_internal(v, idx)); - } - return result; - } - - case 0x99: // array (two-byte uint16_t for n follow) - { - basic_json result = value_t::array; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 2; // skip 4 size bytes - for (size_t i = 0; i < len; ++i) - { - result.push_back(from_cbor_internal(v, idx)); - } - return result; - } - - case 0x9a: // array (four-byte uint32_t for n follow) - { - basic_json result = value_t::array; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 4; // skip 4 size bytes - for (size_t i = 0; i < len; ++i) - { - result.push_back(from_cbor_internal(v, idx)); - } - return result; - } - - case 0x9b: // array (eight-byte uint64_t for n follow) - { - basic_json result = value_t::array; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 8; // skip 8 size bytes - for (size_t i = 0; i < len; ++i) - { - result.push_back(from_cbor_internal(v, idx)); - } - return result; - } - - case 0x9f: // array (indefinite length) - { - basic_json result = value_t::array; - while (static_cast(check_length(v.size(), 1, idx)), v[idx] != 0xff) - { - result.push_back(from_cbor_internal(v, idx)); - } - // skip break byte (0xFF) - idx += 1; - return result; - } - - // 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: - { - basic_json result = value_t::object; - const auto len = static_cast(v[current_idx] - 0xa0); - for (size_t i = 0; i < len; ++i) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - return result; - } - - case 0xb8: // map (one-byte uint8_t for n follows) - { - basic_json result = value_t::object; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 1; // skip 1 size byte - for (size_t i = 0; i < len; ++i) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - return result; - } - - case 0xb9: // map (two-byte uint16_t for n follow) - { - basic_json result = value_t::object; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 2; // skip 2 size bytes - for (size_t i = 0; i < len; ++i) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - return result; - } - - case 0xba: // map (four-byte uint32_t for n follow) - { - basic_json result = value_t::object; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 4; // skip 4 size bytes - for (size_t i = 0; i < len; ++i) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - return result; - } - - case 0xbb: // map (eight-byte uint64_t for n follow) - { - basic_json result = value_t::object; - const auto len = static_cast(get_from_vector(v, current_idx)); - idx += 8; // skip 8 size bytes - for (size_t i = 0; i < len; ++i) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - return result; - } - - case 0xbf: // map (indefinite length) - { - basic_json result = value_t::object; - while (static_cast(check_length(v.size(), 1, idx)), v[idx] != 0xff) - { - cbor_expect_string(v, idx); - std::string key = from_cbor_internal(v, idx); - result[key] = from_cbor_internal(v, idx); - } - // skip break byte (0xFF) - idx += 1; - return result; - } - - case 0xf4: // false - { - return false; - } - - case 0xf5: // true - { - return true; - } - - case 0xf6: // null - { - return value_t::null; - } - - case 0xf9: // Half-Precision Float (two-byte IEEE 754) - { - idx += 2; // skip two content bytes - - // 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. - check_length(v.size(), 2, current_idx + 1); - const int half = (v[current_idx + 1] << 8) + v[current_idx + 2]; - const int exp = (half >> 10) & 0x1f; - const int mant = half & 0x3ff; - double val; - if (exp == 0) - { - val = std::ldexp(mant, -24); - } - else if (exp != 31) - { - val = std::ldexp(mant + 1024, exp - 25); - } - else - { - val = mant == 0 - ? std::numeric_limits::infinity() - : std::numeric_limits::quiet_NaN(); - } - return (half & 0x8000) != 0 ? -val : val; - } - - case 0xfa: // Single-Precision Float (four-byte IEEE 754) - { - // copy bytes in reverse order into the float variable - float res; - check_length(v.size(), sizeof(float), current_idx + 1); - for (size_t byte = 0; byte < sizeof(float); ++byte) - { - reinterpret_cast(&res)[sizeof(float) - byte - 1] = v[current_idx + 1 + byte]; - } - idx += sizeof(float); // skip content bytes - return res; - } - - case 0xfb: // Double-Precision Float (eight-byte IEEE 754) - { - // copy bytes in reverse order into the double variable - double res; - check_length(v.size(), sizeof(double), current_idx + 1); - for (size_t byte = 0; byte < sizeof(double); ++byte) - { - reinterpret_cast(&res)[sizeof(double) - byte - 1] = v[current_idx + 1 + byte]; - } - idx += sizeof(double); // skip content bytes - return res; - } - - default: // anything else (0xFF is handled inside the other types) - { - std::stringstream ss; - ss << std::hex << static_cast(v[current_idx]); - JSON_THROW(parse_error::create(112, current_idx + 1, "error reading CBOR; last byte: 0x" + ss.str())); - } - } - } - public: /*! @brief create a MessagePack serialization of a given JSON value @@ -9053,7 +8554,7 @@ class basic_json } /*! - @brief create a MessagePack serialization of a given JSON value + @brief create a CBOR serialization of a given JSON value Serializes a given JSON value @a j to a byte vector using the CBOR (Concise Binary Object Representation) serialization format. CBOR is a binary @@ -9141,100 +8642,6 @@ class basic_json return result; } - /*! - @brief create a JSON value from a byte vector in CBOR format - - Deserializes a given byte vector @a v to a JSON value using the CBOR - (Concise Binary Object Representation) serialization format. - - The library maps CBOR types to JSON value types as follows: - - CBOR type | JSON value type | first byte - ---------------------- | --------------- | ---------- - Integer | number_unsigned | 0x00..0x17 - Unsigned integer | number_unsigned | 0x18 - Unsigned integer | number_unsigned | 0x19 - Unsigned integer | number_unsigned | 0x1a - Unsigned integer | number_unsigned | 0x1b - Negative integer | number_integer | 0x20..0x37 - Negative integer | number_integer | 0x38 - Negative integer | number_integer | 0x39 - Negative integer | number_integer | 0x3a - Negative integer | number_integer | 0x3b - Negative integer | number_integer | 0x40..0x57 - UTF-8 string | string | 0x60..0x77 - UTF-8 string | string | 0x78 - UTF-8 string | string | 0x79 - UTF-8 string | string | 0x7a - UTF-8 string | string | 0x7b - UTF-8 string | string | 0x7f - array | array | 0x80..0x97 - array | array | 0x98 - array | array | 0x99 - array | array | 0x9a - array | array | 0x9b - array | array | 0x9f - map | object | 0xa0..0xb7 - map | object | 0xb8 - map | object | 0xb9 - map | object | 0xba - map | object | 0xbb - map | object | 0xbf - False | `false` | 0xf4 - True | `true` | 0xf5 - Nill | `null` | 0xf6 - Half-Precision Float | number_float | 0xf9 - Single-Precision Float | number_float | 0xfa - Double-Precision Float | number_float | 0xfb - - @warning The mapping is **incomplete** in the sense that not all CBOR - types can be converted to a JSON value. The following CBOR types - are not supported and will yield parse errors (parse_error.112): - - byte strings (0x40..0x5f) - - date/time (0xc0..0xc1) - - bignum (0xc2..0xc3) - - decimal fraction (0xc4) - - bigfloat (0xc5) - - tagged items (0xc6..0xd4, 0xd8..0xdb) - - expected conversions (0xd5..0xd7) - - simple values (0xe0..0xf3, 0xf8) - - undefined (0xf7) - - @warning CBOR allows map keys of any type, whereas JSON only allows - strings as keys in object values. Therefore, CBOR maps with keys - other than UTF-8 strings are rejected (parse_error.113). - - @note Any CBOR output created @ref to_cbor can be successfully parsed by - @ref from_cbor. - - @param[in] v a byte vector in CBOR format - @param[in] start_index the index to start reading from @a v (0 by default) - @return deserialized JSON value - - @throw parse_error.110 if the given vector ends prematurely - @throw parse_error.112 if unsupported features from CBOR were - used in the given vector @a v or if the input is not valid CBOR - @throw parse_error.113 if a string was expected as map key, but not found - - @complexity Linear in the size of the byte vector @a v. - - @liveexample{The example shows the deserialization of a byte vector in CBOR - format to a JSON value.,from_cbor} - - @sa http://cbor.io - @sa @ref to_cbor(const basic_json&) for the analogous serialization - @sa @ref from_msgpack(const std::vector&, const size_t) for the - related MessagePack format - - @since version 2.0.9, parameter @a start_index since 2.1.1 - */ - //static basic_json from_cbor(const std::vector& v, - // const size_t start_index = 0) - //{ - // size_t i = start_index; - // return from_cbor_internal(v, i); - //} - /// @} /////////////////////////// @@ -10996,6 +10403,94 @@ class basic_json }; public: + + /*! + @brief create a JSON value from a byte vector in CBOR format + + Deserializes a given byte vector @a v to a JSON value using the CBOR + (Concise Binary Object Representation) serialization format. + + The library maps CBOR types to JSON value types as follows: + + CBOR type | JSON value type | first byte + ---------------------- | --------------- | ---------- + Integer | number_unsigned | 0x00..0x17 + Unsigned integer | number_unsigned | 0x18 + Unsigned integer | number_unsigned | 0x19 + Unsigned integer | number_unsigned | 0x1a + Unsigned integer | number_unsigned | 0x1b + Negative integer | number_integer | 0x20..0x37 + Negative integer | number_integer | 0x38 + Negative integer | number_integer | 0x39 + Negative integer | number_integer | 0x3a + Negative integer | number_integer | 0x3b + Negative integer | number_integer | 0x40..0x57 + UTF-8 string | string | 0x60..0x77 + UTF-8 string | string | 0x78 + UTF-8 string | string | 0x79 + UTF-8 string | string | 0x7a + UTF-8 string | string | 0x7b + UTF-8 string | string | 0x7f + array | array | 0x80..0x97 + array | array | 0x98 + array | array | 0x99 + array | array | 0x9a + array | array | 0x9b + array | array | 0x9f + map | object | 0xa0..0xb7 + map | object | 0xb8 + map | object | 0xb9 + map | object | 0xba + map | object | 0xbb + map | object | 0xbf + False | `false` | 0xf4 + True | `true` | 0xf5 + Nill | `null` | 0xf6 + Half-Precision Float | number_float | 0xf9 + Single-Precision Float | number_float | 0xfa + Double-Precision Float | number_float | 0xfb + + @warning The mapping is **incomplete** in the sense that not all CBOR + types can be converted to a JSON value. The following CBOR types + are not supported and will yield parse errors (parse_error.112): + - byte strings (0x40..0x5f) + - date/time (0xc0..0xc1) + - bignum (0xc2..0xc3) + - decimal fraction (0xc4) + - bigfloat (0xc5) + - tagged items (0xc6..0xd4, 0xd8..0xdb) + - expected conversions (0xd5..0xd7) + - simple values (0xe0..0xf3, 0xf8) + - undefined (0xf7) + + @warning CBOR allows map keys of any type, whereas JSON only allows + strings as keys in object values. Therefore, CBOR maps with keys + other than UTF-8 strings are rejected (parse_error.113). + + @note Any CBOR output created @ref to_cbor can be successfully parsed by + @ref from_cbor. + + @param[in] v a byte vector in CBOR format + @param[in] start_index the index to start reading from @a v (0 by default) + @return deserialized JSON value + + @throw parse_error.110 if the given vector ends prematurely + @throw parse_error.112 if unsupported features from CBOR were + used in the given vector @a v or if the input is not valid CBOR + @throw parse_error.113 if a string was expected as map key, but not found + + @complexity Linear in the size of the byte vector @a v. + + @liveexample{The example shows the deserialization of a byte vector in CBOR + format to a JSON value.,from_cbor} + + @sa http://cbor.io + @sa @ref to_cbor(const basic_json&) for the analogous serialization + @sa @ref from_msgpack(const std::vector&, const size_t) for the + related MessagePack format + + @since version 2.0.9, parameter @a start_index since 2.1.1 + */ static basic_json from_cbor(const std::vector& v, const size_t start_index = 0) {