Files
json/tests/src/unit-cbor.cpp
T
Niels Lohmann 253e4c3926 Bound what the DOM parsers reserve for arrays that announce a size (#6082)
* Bound the total number of valueless UBJSON elements per input

An optimized UBJSON array of type Z, T or F has no payload, so its
declared count is not bounded by the input. The limit of 1048576 applied
to each array on its own, so 9 bytes (`[$Z#l` and a count) produced
1048576 values and every further 9 bytes another 1048576: 362 bytes
allocated 661 MB in a DOM, and a SAX handler received 1M events per 9
bytes.

The reader now adds the counts of all such arrays of one input and
rejects the input with out_of_range.408 when the sum exceeds 1048576
plus 4 for every byte read so far. The base is the per-array limit, so
an array that was accepted on its own before is still accepted at the
start of an input. These arrays add about 80 bytes of memory per input
byte (measured 77; one `Z` per byte needs 32), plus the base; the memory
of a document as a whole is not bounded by this. The check runs once per
valueless array, before its start event, with plain size_t arithmetic
that cannot overflow for a 32-bit size_t. Containers with a payload type
and objects (every member needs a key) are bounded by the input already
and are unchanged. BJData rejects these types.

to_ubjson counts the elements of the typed arrays it writes in one call
and writes an array in the unoptimized form (`[#n Z Z ...`) once it would
bring the total above 1048576, which a reader accepts at any input size.
The check is made only for a typed array of a valueless type, so BJData
and other arrays do not pay for it. Everything to_ubjson writes in
version 3.13.0 can therefore be read back.

Two consequences:
- to_ubjson output changes for values with more than 1048576 elements in
  arrays of type Z, T or F: such an array is written at one byte per
  element, e.g. 270000 rows of 100 nulls take 26.8 MB instead of 1.35 MB.
- Output of version 3.12.0 and earlier (typed arrays without such a
  total) is rejected by from_ubjson when the arrays hold more than
  1048576 elements plus 4 per byte of input. 3.12.0 writes a row of up to 255 nulls in 5 bytes (6 above
  255), so a table is rejected from 1075 rows of 1000 nulls or 209723
  rows of 25 (accepted: 1000 rows of 1000, 209000 rows of 25); rows of
  20 or fewer are never rejected.

Measured on the test data: no file of json_test_data (converted with
to_ubjson in all three modes, 846 round trips) holds an array of this
kind with more than 0.17 values per byte. All of them are read back.

Reproducer (K arrays of 1048576 nulls), Apple clang -O2:
  K=40 (362 bytes): before 41943040 values, 664 MB; after rejected, 33 MB
  K=2 (20 bytes):   before 2097152 values, 53 MB;   after rejected, 33 MB

The new tests count events with a SAX handler where they can: building
and comparing million-element values made the first version take 176 s
under Valgrind, the current one about 22 s.

Behaviour change: an input that holds more than 1048576 elements in
arrays of type Z, T or F at more than 4 per byte is now rejected.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Report an empty array for UBJSON `[$N#<n>` instead of n elements

A no-op (N) is not a value, so an optimized array of type N holds no
element whatever count it declares. The reader skipped the elements but
still passed the declared count to the SAX parser: a handler was told
start_array(n) and no element followed, and the DOM parser reserved
min(n, 16384) values (256 KB) for an array that stays empty. Nine bytes
(`[$N#l 0x7FFFFFFF`) therefore committed 256 KB: 2000 of them in one
input, 18 KB, committed 512 MB of heap (capacity 163,840,000 values for
the 10000 arrays of the original probe: 2.6 GB for 70 KB of input).
Untouched pages keep the resident size small, but the commit charge and
a 32-bit address space are consumed.

The reader now announces 0 elements for an optimized array of type N.
The loop that skips the elements is unchanged (it never ran). A count
that does not fit into std::size_t is still rejected by the count
reader; a count that is too large for the array type of the DOM (before:
out_of_range.408 "excessive array size" from the DOM handler) is
accepted now, because the array is empty.

Behaviour change: sax_parse reports start_array(0) for `[$N#n` (before:
n); from_ubjson no longer throws out_of_range.408 for an N-typed array
whose count exceeds the maximum size of the array type.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Bound what the DOM parsers reserve for arrays that announce a size

Cause: #5476 made the DOM parsers reserve storage (up to 16384 elements)
for a counted array of CBOR, MessagePack, UBJSON and BJData when it
opens, before any input backs the count. The arrays that are open at the
same time keep their storage until the parse ends, so N nested headers
that announce 16384 elements and are never completed hold
N * 16384 * sizeof(json): 100,000 nested CBOR headers `99 40 00`
(300,000 bytes) peaked at 1.65 GiB, 3.12.0 at 12 MiB; the same for
MessagePack `DC 40 00`, UBJSON `[#I 16384` and BJData.

Fix: json_sax_dom_error_state, the base of the three DOM parsers, keeps a
credit of elements that may still be reserved: 65,536 at the start plus
2 for every byte the reader has read. An array that announces no more
than the credit left is reserved as before (one comparison and one
subtraction per counted array); a larger one is reserved what is left
and grows as its elements arrive. binary_reader tells a DOM parser (a
handler whose pointer converts to json_sax_dom_error_state*; a handler
that derives from one privately or protectedly, or any other SAX handler,
is not told anything and reserves as in the base of this change) where to
find its count of characters read for the duration of sax_parse(). An
RAII guard puts back the previous binding on every exit, also by
exception, so the parser never keeps a pointer to a reader that is gone
(unbound, only the per-array cap of 16384 applies); the public SAX
interface is unchanged, and start_array() still reports the announced number. A
bound per array by the remaining input would not help, since the same
bytes would back every open level; the bound has to be over all arrays.

The elements of an array take at least one byte of input each, so the
credit is more than honest input needs: none of the 19 inputs measured
(canada, citm_catalog, twitter, mesh, update-center, random, numbers,
animation, ik_rig, instruments, geo_response, jeopardy and 7 synthetic
ones, each as CBOR, MessagePack, UBJSON and BJData, with and without
size/type optimization) was given less than it announced. A value that
nests five or more arrays of 16384 elements, each with an array as its
first element, is the exception: the later ones grow as before.

Measurements (clang -O2, macOS arm64, peak memory footprint of
`/usr/bin/time -l`, reproducer: n nested headers):

              n = 20,000                n = 100,000
              develop   fix   3.12.0   develop    fix   3.12.0
  CBOR        338.7    5.9    8.2      1687.7    23.3   11.8   MiB
  MessagePack 338.9    6.0    7.3      1687.9    23.8   11.9   MiB
  UBJSON      339.0    7.6    8.0      1687.9    30.1   11.6   MiB
  BJData      339.0    7.3    7.9      1688.0    30.8   11.6   MiB

That is at most (65,536 + 2 per input byte) values: 1 MiB plus 32 bytes
per input byte with 16-byte values (a value is 24 bytes with
JSON_DIAGNOSTICS and up to 40 with JSON_DIAGNOSTIC_POSITIONS), as
documented in untrusted_input.md. Lower fixed caps do not get there: a
cap of 64 elements still peaks at 113 MiB (n = 100,000) and costs 4.7 %
on arrays of 300 elements (mat300.cbor) and 5.0 % on arrays of 10,000
(arrays_of_big.cbor).

Reader instructions retired (min of 7, 108 rows: 18 inputs in the 6 forms
CBOR, MessagePack, UBJSON and BJData plain and optimized; jeopardy, 46 MB,
is within 0.1 %), compared with the base of this change: -0.19 % to +0.37 % in the formats that announce
sizes (canada.cbor 81.9 M -> 82.1 M, many_small.cbor 333.5 M -> 334.2 M);
the benefit of #5476 is kept (without any reserve canada.cbor takes
116.8 M, +42.6 %, many_small.cbor +71.5 %, mat300.cbor +81.6 %). Rows of
plain UBJSON and BJData, whose arrays announce no size, move by -2.7 % to
+2.6 % without any code of theirs changing: the base alternates
between two instruction counts per process (452 M and 463 M for
many_pairs.ubjson, equal in cycles), and a struct with three unused
members added to the same class reproduces the 474 M mode.

Tests (CBOR, MessagePack, UBJSON, BJData): 200 nested headers that
announce 16384 elements peak at 52,433,600 bytes of DOM allocations on
the base and below 128 Ki values with the fix (scaled by sizeof(value),
so that it holds with the diagnostic macros) (counting allocator, no
process memory measured); an array that completes is still reserved in
one allocation; CBOR also checks that a DOM parser is not bound to a finished
parse (ASan: stack-use-after-scope without the guard), that wrappers
derived publicly (also with a parse inside the parse), privately and
protectedly compile and are bound or not as described, that an array that got less than it
announced decodes and that a SAX handler is told the announced size.
The new tests take 4.6 s under Valgrind at -O0 (gcc:12, all four files).

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Clarify the reservation note for announced array counts

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Report an empty array for UBJSON [$N#<n>] instead of n elements (#6079)

* Report an empty array for UBJSON `[$N#<n>` instead of n elements

A no-op (N) is not a value, so an optimized array of type N holds no
element whatever count it declares. The reader skipped the elements but
still passed the declared count to the SAX parser: a handler was told
start_array(n) and no element followed, and the DOM parser reserved
min(n, 16384) values (256 KB) for an array that stays empty. Nine bytes
(`[$N#l 0x7FFFFFFF`) therefore committed 256 KB: 2000 of them in one
input, 18 KB, committed 512 MB of heap (capacity 163,840,000 values for
the 10000 arrays of the original probe: 2.6 GB for 70 KB of input).
Untouched pages keep the resident size small, but the commit charge and
a 32-bit address space are consumed.

The reader now announces 0 elements for an optimized array of type N.
The loop that skips the elements is unchanged (it never ran). A count
that does not fit into std::size_t is still rejected by the count
reader; a count that is too large for the array type of the DOM (before:
out_of_range.408 "excessive array size" from the DOM handler) is
accepted now, because the array is empty.

Behaviour change: sax_parse reports start_array(0) for `[$N#n` (before:
n); from_ubjson no longer throws out_of_range.408 for an N-typed array
whose count exceeds the maximum size of the array type.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Clarify the reservation note for announced array counts

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

---------

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Add JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE to set the UBJSON whole-input budget (#6083)

* Add JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE to set the UBJSON whole-input budget

The whole-input budget for the elements of optimized UBJSON arrays of
type Z, T and F (1048576 plus 4 per byte read) rejects files written by
3.12.0 that have long arrays of these types, such as 1100 rows of 1000
nulls with a `$Z` annotation, and there was no way to read them. The
per-byte rate is now the macro JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE.

Semantics:
- default 4, so the default build is unchanged (the generated code of
  from_ubjson is identical at -O2 up to source line numbers);
- the value must be a positive integer: 0, negative, non-integral, bool,
  character and wider-than-uintmax_t values fail to compile with a
  static_assert that names the macro;
- a value that does not fit into std::size_t is the largest size_t, so
  one spelling works for 32- and 64-bit targets;
- the limit base + rate * bytes_read saturates at the largest size_t
  instead of wrapping around, for any rate and input size; a rate of
  131072 (2^20 / 8) or more cannot be exceeded by any input (the
  shortest header of an array of more than 32767 elements is 8 bytes),
  which switches the whole-input budget off;
- the limit of one array (1048576) and the base (1048576) stay fixed
  constants, so the writer fallback still follows the base only and a
  reader with any rate reads everything the writer produces;
- the macro is not part of the ABI tag and must have the same value in
  every translation unit; it is documented that way.

The memory the arrays can take in a DOM is about 20 bytes per rate and
byte of input (measured, macOS, containers of 9 * rate elements:
25 bytes per input byte at rate 1, 81 at 4, 312 at 16, 1226 at 64, 5493
at 256) plus about 33 MB for the base. A 3.12.0 row of N values has a
header of b bytes (5 up to 255, 6 up to 32767, 8 above), so a table is
read completely if N <= rate * b, and otherwise up to
(1048576 + h * rate, h = outer header: 6, 7 or 9 bytes) / (N - rate * b) rows; 1100 rows of 1000 nulls need
a rate of 8. The new page of the macro documents the formulas, the
measurements, and two examples that are run by the documentation checks.

The tests of the budget move to tests/src/unit-ubjson_valueless.cpp, which
derives every boundary from the macro and is built with the rates 1,
1000000 and 0xFFFFFFFFFFFFFFFF in addition to the default (the last two
check that nothing is refused and that the limit does not wrap around);
they fail with the unchanged header for rate 1, 1000000 and the maximum.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Refuse char8_t for JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE and clarify its documentation

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

---------

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Use fseek instead of rewind in the UBJSON FILE* test

clang-tidy (bugprone-unsafe-functions) rejects rewind() because it has no
error detection. Check the result of fseek() instead.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Charge an announced array only what is reserved for it

An array that announced more than reserve_cap() elements but no more than
the credit left was charged the announced count, while reserve_array()
reserved at most reserve_cap() of them. An outer array of 20000 elements
therefore left a third nested array of 16384 with 12796 instead of the
full reservation. reserve_count() now caps the count first and charges
that, and the DOM parsers reserve it through reserve_array_capped(),
which does not cap again, so the fast path costs the same as before
(instructions retired within +-0.06 % on canada, citm_catalog and twitter
in CBOR, MessagePack and UBJSON).

Also re-wrap the comment of valueless_elements_base.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

---------

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-11-15 17:02:05 +01:00

3947 lines
192 KiB
C++

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++ (supporting code)
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#include "doctest_compatibility.h"
// capture whether JSON_DELETE_DEPRECATED_FUNCTIONS was enabled on the command
// line *before* including json.hpp, since the library #undefs it once the header
// has been fully processed (see include/nlohmann/detail/macro_unscope.hpp); the
// tests of deprecated functions are skipped if these functions are deleted
#if defined(JSON_DELETE_DEPRECATED_FUNCTIONS) && (JSON_DELETE_DEPRECATED_FUNCTIONS == 1)
#define JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
#endif
#include <nlohmann/json.hpp>
using nlohmann::json;
#include <fstream>
#include <sstream>
#include <iomanip>
#include <limits>
#include <list>
#include <set>
#include "make_test_data_available.hpp"
#include "round_trip_corpus.hpp"
#include "test_utils.hpp"
#include "sax_countdown.hpp"
#include "allocation_counter.hpp"
#include "sax_event_loggers.hpp"
using utils::SaxCountdown;
using utils::SaxEventLogger;
TEST_CASE("CBOR")
{
SECTION("individual values")
{
SECTION("discarded")
{
// a discarded value cannot be serialized to CBOR
json const j = json::value_t::discarded;
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] cannot serialize discarded value to CBOR", json::type_error&);
}
SECTION("discarded values nested in a container")
{
json const discarded = json::value_t::discarded;
SECTION("in an array")
{
json const j = {1, discarded, 2};
#if JSON_DIAGNOSTICS
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] (/1) cannot serialize discarded value to CBOR", json::type_error&);
#else
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] cannot serialize discarded value to CBOR", json::type_error&);
#endif
}
SECTION("as an object value")
{
json j;
j["a"] = 1;
j["b"] = discarded;
#if JSON_DIAGNOSTICS
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] (/b) cannot serialize discarded value to CBOR", json::type_error&);
#else
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] cannot serialize discarded value to CBOR", json::type_error&);
#endif
}
SECTION("nested deeper (array in object in array)")
{
json inner_array = {1, discarded};
json middle_object;
middle_object["x"] = inner_array;
json const j = {middle_object};
#if JSON_DIAGNOSTICS
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] (/0/x/1) cannot serialize discarded value to CBOR", json::type_error&);
#else
CHECK_THROWS_WITH_AS(json::to_cbor(j), "[json.exception.type_error.321] cannot serialize discarded value to CBOR", json::type_error&);
#endif
}
}
SECTION("NaN")
{
// NaN value
json const j = std::numeric_limits<json::number_float_t>::quiet_NaN();
const std::vector<uint8_t> expected = {0xf9, 0x7e, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
}
SECTION("Infinity")
{
// Infinity value
json const j = std::numeric_limits<json::number_float_t>::infinity();
const std::vector<uint8_t> expected = {0xf9, 0x7c, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
}
SECTION("null")
{
const json j = nullptr;
const std::vector<uint8_t> expected = {0xf6};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("boolean")
{
SECTION("true")
{
const json j = true;
const std::vector<uint8_t> expected = {0xf5};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("false")
{
const json j = false;
const std::vector<uint8_t> expected = {0xf4};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("number")
{
SECTION("signed")
{
SECTION("-9223372036854775808..-4294967297")
{
const std::vector<int64_t> numbers
{
(std::numeric_limits<int64_t>::min)(),
-1000000000000000000,
-100000000000000000,
-10000000000000000,
-1000000000000000,
-100000000000000,
-10000000000000,
-1000000000000,
-100000000000,
-10000000000,
-4294967297,
};
for (const auto i : numbers)
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const auto positive = static_cast<uint64_t>(-1 - i);
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x3b),
static_cast<uint8_t>((positive >> 56) & 0xff),
static_cast<uint8_t>((positive >> 48) & 0xff),
static_cast<uint8_t>((positive >> 40) & 0xff),
static_cast<uint8_t>((positive >> 32) & 0xff),
static_cast<uint8_t>((positive >> 24) & 0xff),
static_cast<uint8_t>((positive >> 16) & 0xff),
static_cast<uint8_t>((positive >> 8) & 0xff),
static_cast<uint8_t>(positive & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 9);
// check individual bytes
CHECK(result[0] == 0x3b);
const uint64_t restored = (static_cast<uint64_t>(result[1]) << 070) +
(static_cast<uint64_t>(result[2]) << 060) +
(static_cast<uint64_t>(result[3]) << 050) +
(static_cast<uint64_t>(result[4]) << 040) +
(static_cast<uint64_t>(result[5]) << 030) +
(static_cast<uint64_t>(result[6]) << 020) +
(static_cast<uint64_t>(result[7]) << 010) +
static_cast<uint64_t>(result[8]);
CHECK(restored == positive);
CHECK(-1 - static_cast<int64_t>(restored) == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("-4294967296..-65537")
{
const std::vector<int64_t> numbers
{
-65537,
-100000,
-1000000,
-10000000,
-100000000,
-1000000000,
-4294967296,
};
for (const auto i : numbers)
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
auto positive = static_cast<uint32_t>(static_cast<uint64_t>(-1 - i) & 0x00000000ffffffff);
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x3a),
static_cast<uint8_t>((positive >> 24) & 0xff),
static_cast<uint8_t>((positive >> 16) & 0xff),
static_cast<uint8_t>((positive >> 8) & 0xff),
static_cast<uint8_t>(positive & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 5);
// check individual bytes
CHECK(result[0] == 0x3a);
const uint32_t restored = (static_cast<uint32_t>(result[1]) << 030) +
(static_cast<uint32_t>(result[2]) << 020) +
(static_cast<uint32_t>(result[3]) << 010) +
static_cast<uint32_t>(result[4]);
CHECK(restored == positive);
CHECK(-1LL - restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("-65536..-257")
{
for (int32_t i = -65536; i <= -257; i = utils::next_integer_sample(i, -257, 7))
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const auto positive = static_cast<uint16_t>(-1 - i);
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x39),
static_cast<uint8_t>((positive >> 8) & 0xff),
static_cast<uint8_t>(positive & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 3);
// check individual bytes
CHECK(result[0] == 0x39);
const auto restored = static_cast<uint16_t>((static_cast<uint8_t>(result[1]) * 256) + static_cast<uint8_t>(result[2]));
CHECK(restored == positive);
CHECK(-1 - restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("-9263 (int 16)")
{
const json j = -9263;
std::vector<uint8_t> expected = {0x39, 0x24, 0x2e};
const auto result = json::to_cbor(j);
CHECK(result == expected);
const auto restored = static_cast<int16_t>(-1 - ((result[1] << 8) + result[2]));
CHECK(restored == -9263);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("-256..-24")
{
for (auto i = -256; i < -24; ++i)
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x38,
static_cast<uint8_t>(-1 - i),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 2);
// check individual bytes
CHECK(result[0] == 0x38);
CHECK(static_cast<int16_t>(-1 - result[1]) == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("-24..-1")
{
for (auto i = -24; i <= -1; ++i)
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x20 - 1 - static_cast<uint8_t>(i)),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 1);
// check individual bytes
CHECK(static_cast<int8_t>(0x20 - 1 - result[0]) == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("0..23")
{
for (size_t i = 0; i <= 23; ++i)
{
CAPTURE(i)
// create JSON value with integer number
json j = -1;
j.get_ref<json::number_integer_t&>() = static_cast<json::number_integer_t>(i);
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(i),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 1);
// check individual bytes
CHECK(result[0] == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("24..255")
{
for (size_t i = 24; i <= 255; ++i)
{
CAPTURE(i)
// create JSON value with integer number
json j = -1;
j.get_ref<json::number_integer_t&>() = static_cast<json::number_integer_t>(i);
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x18),
static_cast<uint8_t>(i),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 2);
// check individual bytes
CHECK(result[0] == 0x18);
CHECK(result[1] == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("256..65535")
{
for (size_t i = 256; i <= 65535; i = utils::next_integer_sample(i, static_cast<size_t>(65535), static_cast<size_t>(7)))
{
CAPTURE(i)
// create JSON value with integer number
json j = -1;
j.get_ref<json::number_integer_t&>() = static_cast<json::number_integer_t>(i);
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(0x19),
static_cast<uint8_t>((i >> 8) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 3);
// check individual bytes
CHECK(result[0] == 0x19);
const auto restored = static_cast<uint16_t>((static_cast<uint8_t>(result[1]) * 256) + static_cast<uint8_t>(result[2]));
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("65536..4294967295")
{
for (const uint32_t i :
{
65536u, 77777u, 1048576u
})
{
CAPTURE(i)
// create JSON value with integer number
json j = -1;
j.get_ref<json::number_integer_t&>() = static_cast<json::number_integer_t>(i);
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x1a,
static_cast<uint8_t>((i >> 24) & 0xff),
static_cast<uint8_t>((i >> 16) & 0xff),
static_cast<uint8_t>((i >> 8) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 5);
// check individual bytes
CHECK(result[0] == 0x1a);
const uint32_t restored = (static_cast<uint32_t>(result[1]) << 030) +
(static_cast<uint32_t>(result[2]) << 020) +
(static_cast<uint32_t>(result[3]) << 010) +
static_cast<uint32_t>(result[4]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("4294967296..4611686018427387903")
{
for (const uint64_t i :
{
4294967296ul, 4611686018427387903ul
})
{
CAPTURE(i)
// create JSON value with integer number
json j = -1;
j.get_ref<json::number_integer_t&>() = static_cast<json::number_integer_t>(i);
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x1b,
static_cast<uint8_t>((i >> 070) & 0xff),
static_cast<uint8_t>((i >> 060) & 0xff),
static_cast<uint8_t>((i >> 050) & 0xff),
static_cast<uint8_t>((i >> 040) & 0xff),
static_cast<uint8_t>((i >> 030) & 0xff),
static_cast<uint8_t>((i >> 020) & 0xff),
static_cast<uint8_t>((i >> 010) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 9);
// check individual bytes
CHECK(result[0] == 0x1b);
const uint64_t restored = (static_cast<uint64_t>(result[1]) << 070) +
(static_cast<uint64_t>(result[2]) << 060) +
(static_cast<uint64_t>(result[3]) << 050) +
(static_cast<uint64_t>(result[4]) << 040) +
(static_cast<uint64_t>(result[5]) << 030) +
(static_cast<uint64_t>(result[6]) << 020) +
(static_cast<uint64_t>(result[7]) << 010) +
static_cast<uint64_t>(result[8]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("-32768..-129 (int 16)")
{
for (int16_t i = -32768; i <= static_cast<std::int16_t>(-129); i = utils::next_integer_sample(i, static_cast<int16_t>(-129), static_cast<int16_t>(7)))
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_integer());
// create expected byte vector
const std::vector<uint8_t> expected
{
0xd1,
static_cast<uint8_t>((i >> 8) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_msgpack(j);
CHECK(result == expected);
CHECK(result.size() == 3);
// check individual bytes
CHECK(result[0] == 0xd1);
const auto restored = static_cast<int16_t>((result[1] << 8) + result[2]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_msgpack(result) == j);
}
}
}
SECTION("unsigned")
{
SECTION("0..23 (Integer)")
{
for (size_t i = 0; i <= 23; ++i)
{
CAPTURE(i)
// create JSON value with unsigned integer number
const json j = i;
// check type
CHECK(j.is_number_unsigned());
// create expected byte vector
const std::vector<uint8_t> expected
{
static_cast<uint8_t>(i),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 1);
// check individual bytes
CHECK(result[0] == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("24..255 (one-byte uint8_t)")
{
for (size_t i = 24; i <= 255; ++i)
{
CAPTURE(i)
// create JSON value with unsigned integer number
const json j = i;
// check type
CHECK(j.is_number_unsigned());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x18,
static_cast<uint8_t>(i),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 2);
// check individual bytes
CHECK(result[0] == 0x18);
const auto restored = static_cast<uint8_t>(result[1]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("256..65535 (two-byte uint16_t)")
{
for (size_t i = 256; i <= 65535; i = utils::next_integer_sample(i, static_cast<size_t>(65535), static_cast<size_t>(7)))
{
CAPTURE(i)
// create JSON value with unsigned integer number
const json j = i;
// check type
CHECK(j.is_number_unsigned());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x19,
static_cast<uint8_t>((i >> 8) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 3);
// check individual bytes
CHECK(result[0] == 0x19);
const auto restored = static_cast<uint16_t>((static_cast<uint8_t>(result[1]) * 256) + static_cast<uint8_t>(result[2]));
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("65536..4294967295 (four-byte uint32_t)")
{
for (const uint32_t i :
{
65536u, 77777u, 1048576u
})
{
CAPTURE(i)
// create JSON value with unsigned integer number
const json j = i;
// check type
CHECK(j.is_number_unsigned());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x1a,
static_cast<uint8_t>((i >> 24) & 0xff),
static_cast<uint8_t>((i >> 16) & 0xff),
static_cast<uint8_t>((i >> 8) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 5);
// check individual bytes
CHECK(result[0] == 0x1a);
const uint32_t restored = (static_cast<uint32_t>(result[1]) << 030) +
(static_cast<uint32_t>(result[2]) << 020) +
(static_cast<uint32_t>(result[3]) << 010) +
static_cast<uint32_t>(result[4]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("4294967296..4611686018427387903 (eight-byte uint64_t)")
{
for (const uint64_t i :
{
4294967296ul, 4611686018427387903ul
})
{
CAPTURE(i)
// create JSON value with integer number
const json j = i;
// check type
CHECK(j.is_number_unsigned());
// create expected byte vector
const std::vector<uint8_t> expected
{
0x1b,
static_cast<uint8_t>((i >> 070) & 0xff),
static_cast<uint8_t>((i >> 060) & 0xff),
static_cast<uint8_t>((i >> 050) & 0xff),
static_cast<uint8_t>((i >> 040) & 0xff),
static_cast<uint8_t>((i >> 030) & 0xff),
static_cast<uint8_t>((i >> 020) & 0xff),
static_cast<uint8_t>((i >> 010) & 0xff),
static_cast<uint8_t>(i & 0xff),
};
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == 9);
// check individual bytes
CHECK(result[0] == 0x1b);
const uint64_t restored = (static_cast<uint64_t>(result[1]) << 070) +
(static_cast<uint64_t>(result[2]) << 060) +
(static_cast<uint64_t>(result[3]) << 050) +
(static_cast<uint64_t>(result[4]) << 040) +
(static_cast<uint64_t>(result[5]) << 030) +
(static_cast<uint64_t>(result[6]) << 020) +
(static_cast<uint64_t>(result[7]) << 010) +
static_cast<uint64_t>(result[8]);
CHECK(restored == i);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
}
SECTION("double-precision float")
{
SECTION("3.1415925")
{
double v = 3.1415925;
const json j = v;
std::vector<uint8_t> expected =
{
0xfb, 0x40, 0x09, 0x21, 0xfb, 0x3f, 0xa6, 0xde, 0xfc
};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("single-precision float")
{
SECTION("0.5")
{
double v = 0.5;
const json j = v;
// its double-precision float binary value is
// {0xfb, 0x3f, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
// but to save memory, we can store it as single-precision float.
const std::vector<uint8_t> expected = {0xfa, 0x3f, 0x00, 0x00, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("0.0")
{
double v = 0.0;
const json j = v;
// its double-precision binary value is:
// {0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
const std::vector<uint8_t> expected = {0xfa, 0x00, 0x00, 0x00, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("-0.0")
{
double v = -0.0;
const json j = v;
// its double-precision binary value is:
// {0xfb, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
const std::vector<uint8_t> expected = {0xfa, 0x80, 0x00, 0x00, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("100.0")
{
double v = 100.0;
const json j = v;
// its double-precision binary value is:
// {0xfb, 0x40, 0x59, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
const std::vector<uint8_t> expected = {0xfa, 0x42, 0xc8, 0x00, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("200.0")
{
double v = 200.0;
const json j = v;
// its double-precision binary value is:
// {0xfb, 0x40, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
const std::vector<uint8_t> expected = {0xfa, 0x43, 0x48, 0x00, 0x00};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("3.40282e+38(max float)")
{
float v = (std::numeric_limits<float>::max)();
const json j = v;
const std::vector<uint8_t> expected =
{
0xfa, 0x7f, 0x7f, 0xff, 0xff
};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("-3.40282e+38(lowest float)")
{
auto v = static_cast<double>(std::numeric_limits<float>::lowest());
const json j = v;
const std::vector<uint8_t> expected =
{
0xfa, 0xff, 0x7f, 0xff, 0xff
};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("1 + 3.40282e+38(more than max float)")
{
double v = static_cast<double>((std::numeric_limits<float>::max)()) + 0.1e+34;
const json j = v;
const std::vector<uint8_t> expected =
{
0xfb, 0x47, 0xf0, 0x00, 0x03, 0x04, 0xdc, 0x64, 0x49
};
// double
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
SECTION("-1 - 3.40282e+38(less than lowest float)")
{
double v = static_cast<double>(std::numeric_limits<float>::lowest()) - 1.0;
const json j = v;
const std::vector<uint8_t> expected =
{
0xfa, 0xff, 0x7f, 0xff, 0xff
};
// the same with the lowest float
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result) == v);
}
}
SECTION("half-precision float (edge cases)")
{
SECTION("errors")
{
SECTION("no byte follows")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xf9})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0xf9}), true, false).is_discarded());
}
SECTION("only one byte follows")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xf9, 0x7c})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0xf9, 0x7c}), true, false).is_discarded());
}
}
SECTION("exp = 0b00000")
{
SECTION("0 (0 00000 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x00}));
const json::number_float_t d{j};
CHECK(d == 0.0);
}
SECTION("-0 (1 00000 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x80, 0x00}));
const json::number_float_t d{j};
CHECK(d == -0.0);
}
SECTION("2**-24 (0 00000 0000000001)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x01}));
const json::number_float_t d{j};
CHECK(d == std::pow(2.0, -24.0));
}
}
SECTION("exp = 0b11111")
{
SECTION("infinity (0 11111 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x7c, 0x00}));
const json::number_float_t d{j};
CHECK(d == std::numeric_limits<json::number_float_t>::infinity());
CHECK(j.dump() == "null");
}
SECTION("-infinity (1 11111 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0xfc, 0x00}));
const json::number_float_t d{j};
CHECK(d == -std::numeric_limits<json::number_float_t>::infinity());
CHECK(j.dump() == "null");
}
}
SECTION("other values from https://en.wikipedia.org/wiki/Half-precision_floating-point_format")
{
SECTION("1 (0 01111 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x3c, 0x00}));
const json::number_float_t d{j};
CHECK(d == 1);
}
SECTION("-2 (1 10000 0000000000)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0xc0, 0x00}));
const json::number_float_t d{j};
CHECK(d == -2);
}
SECTION("65504 (0 11110 1111111111)")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x7b, 0xff}));
const json::number_float_t d{j};
CHECK(d == 65504);
}
}
SECTION("infinity")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x7c, 0x00}));
json::number_float_t const d{j};
CHECK(!std::isfinite(d));
CHECK(j.dump() == "null");
}
SECTION("NaN")
{
json const j = json::from_cbor(std::vector<uint8_t>({0xf9, 0x7e, 0x00}));
json::number_float_t const d{j};
CHECK(std::isnan(d));
CHECK(j.dump() == "null");
}
}
}
SECTION("string")
{
SECTION("N = 0..23")
{
for (size_t N = 0; N <= 0x17; ++N)
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::string(N, 'x');
const json j = s;
// create expected byte vector
std::vector<uint8_t> expected;
expected.push_back(static_cast<uint8_t>(0x60 + N));
for (size_t i = 0; i < N; ++i)
{
expected.push_back('x');
}
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 1);
// check that no null byte is appended
if (N > 0)
{
CHECK(result.back() != '\x00');
}
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 24..255")
{
for (size_t N = 24; N <= 255; ++N)
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::string(N, 'x');
const json j = s;
// create expected byte vector
std::vector<uint8_t> expected;
expected.push_back(0x78);
expected.push_back(static_cast<uint8_t>(N));
for (size_t i = 0; i < N; ++i)
{
expected.push_back('x');
}
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 2);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 256..65535")
{
for (const size_t N :
{
256u, 999u, 1025u, 3333u, 2048u, 65535u
})
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::string(N, 'x');
const json j = s;
// create expected byte vector (hack: create string first)
std::vector<uint8_t> expected(N, 'x');
// reverse order of commands, because we insert at begin()
expected.insert(expected.begin(), static_cast<uint8_t>(N & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 8) & 0xff));
expected.insert(expected.begin(), 0x79);
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 3);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 65536..4294967295")
{
for (const size_t N :
{
65536u, 77777u, 1048576u
})
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::string(N, 'x');
const json j = s;
// create expected byte vector (hack: create string first)
std::vector<uint8_t> expected(N, 'x');
// reverse order of commands, because we insert at begin()
expected.insert(expected.begin(), static_cast<uint8_t>(N & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 8) & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 16) & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 24) & 0xff));
expected.insert(expected.begin(), 0x7a);
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 5);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
}
SECTION("array")
{
SECTION("empty")
{
const json j = json::array();
std::vector<uint8_t> expected = {0x80};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("[null]")
{
const json j = {nullptr};
const std::vector<uint8_t> expected = {0x81, 0xf6};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("[1,2,3,4,5]")
{
const json j = json::parse("[1,2,3,4,5]");
const std::vector<uint8_t> expected = {0x85, 0x01, 0x02, 0x03, 0x04, 0x05};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("[[[[]]]]")
{
const json j = json::parse("[[[[]]]]");
const std::vector<uint8_t> expected = {0x81, 0x81, 0x81, 0x80};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("array with uint16_t elements")
{
const json j(257, nullptr);
std::vector<uint8_t> expected(j.size() + 3, 0xf6); // all null
expected[0] = 0x99; // array 16 bit
expected[1] = 0x01; // size (0x0101), byte 0
expected[2] = 0x01; // size (0x0101), byte 1
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("array with uint32_t elements")
{
const json j(65793, nullptr);
std::vector<uint8_t> expected(j.size() + 5, 0xf6); // all null
expected[0] = 0x9a; // array 32 bit
expected[1] = 0x00; // size (0x00010101), byte 0
expected[2] = 0x01; // size (0x00010101), byte 1
expected[3] = 0x01; // size (0x00010101), byte 2
expected[4] = 0x01; // size (0x00010101), byte 3
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("object")
{
SECTION("empty")
{
const json j = json::object();
const std::vector<uint8_t> expected = {0xa0};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("{\"\":null}")
{
const json j = {{"", nullptr}};
const std::vector<uint8_t> expected = {0xa1, 0x60, 0xf6};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("{\"a\": {\"b\": {\"c\": {}}}}")
{
const json j = json::parse(R"({"a": {"b": {"c": {}}}})");
const std::vector<uint8_t> expected =
{
0xa1, 0x61, 0x61, 0xa1, 0x61, 0x62, 0xa1, 0x61, 0x63, 0xa0
};
const auto result = json::to_cbor(j);
CHECK(result == expected);
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("object with uint8_t elements")
{
json j;
for (auto i = 0; i < 255; ++i)
{
// format i to a fixed width of 5
// each entry will need 7 bytes: 6 for string, 1 for null
std::stringstream ss;
ss << std::setw(5) << std::setfill('0') << i;
j.emplace(ss.str(), nullptr);
}
const auto result = json::to_cbor(j);
// Checking against an expected vector byte by byte is
// difficult, because no assumption on the order of key/value
// pairs are made. We therefore only check the prefix (type and
// size and the overall size. The rest is then handled in the
// roundtrip check.
CHECK(result.size() == 1787); // 1 type, 1 size, 255*7 content
CHECK(result[0] == 0xb8); // map 8 bit
CHECK(result[1] == 0xff); // size byte (0xff)
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("object with uint16_t elements")
{
json j;
for (auto i = 0; i < 256; ++i)
{
// format i to a fixed width of 5
// each entry will need 7 bytes: 6 for string, 1 for null
std::stringstream ss;
ss << std::setw(5) << std::setfill('0') << i;
j.emplace(ss.str(), nullptr);
}
const auto result = json::to_cbor(j);
// Checking against an expected vector byte by byte is
// difficult, because no assumption on the order of key/value
// pairs are made. We therefore only check the prefix (type and
// size and the overall size. The rest is then handled in the
// roundtrip check.
CHECK(result.size() == 1795); // 1 type, 2 size, 256*7 content
CHECK(result[0] == 0xb9); // map 16 bit
CHECK(result[1] == 0x01); // byte 0 of size (0x0100)
CHECK(result[2] == 0x00); // byte 1 of size (0x0100)
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
SECTION("object with uint32_t elements")
{
json j;
for (auto i = 0; i < 65536; ++i)
{
// format i to a fixed width of 5
// each entry will need 7 bytes: 6 for string, 1 for null
std::stringstream ss;
ss << std::setw(5) << std::setfill('0') << i;
j.emplace(ss.str(), nullptr);
}
const auto result = json::to_cbor(j);
// Checking against an expected vector byte by byte is
// difficult, because no assumption on the order of key/value
// pairs are made. We therefore only check the prefix (type and
// size and the overall size. The rest is then handled in the
// roundtrip check.
CHECK(result.size() == 458757); // 1 type, 4 size, 65536*7 content
CHECK(result[0] == 0xba); // map 32 bit
CHECK(result[1] == 0x00); // byte 0 of size (0x00010000)
CHECK(result[2] == 0x01); // byte 1 of size (0x00010000)
CHECK(result[3] == 0x00); // byte 2 of size (0x00010000)
CHECK(result[4] == 0x00); // byte 3 of size (0x00010000)
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("binary")
{
SECTION("N = 0..23")
{
for (size_t N = 0; N <= 0x17; ++N)
{
CAPTURE(N)
// create JSON value with byte array containing of N * 'x'
const auto s = std::vector<uint8_t>(N, 'x');
const json j = json::binary(s);
// create expected byte vector
std::vector<uint8_t> expected;
expected.push_back(static_cast<uint8_t>(0x40 + N));
for (size_t i = 0; i < N; ++i)
{
expected.push_back(0x78);
}
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 1);
// check that no null byte is appended
if (N > 0)
{
CHECK(result.back() != '\x00');
}
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 24..255")
{
for (size_t N = 24; N <= 255; ++N)
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::vector<uint8_t>(N, 'x');
const json j = json::binary(s);
// create expected byte vector
std::vector<uint8_t> expected;
expected.push_back(0x58);
expected.push_back(static_cast<uint8_t>(N));
for (size_t i = 0; i < N; ++i)
{
expected.push_back('x');
}
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 2);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 256..65535")
{
for (const size_t N :
{
256u, 999u, 1025u, 3333u, 2048u, 65535u
})
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::vector<uint8_t>(N, 'x');
const json j = json::binary(s);
// create expected byte vector (hack: create string first)
std::vector<uint8_t> expected(N, 'x');
// reverse order of commands, because we insert at begin()
expected.insert(expected.begin(), static_cast<uint8_t>(N & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 8) & 0xff));
expected.insert(expected.begin(), 0x59);
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 3);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("N = 65536..4294967295")
{
for (const size_t N :
{
65536u, 77777u, 1048576u
})
{
CAPTURE(N)
// create JSON value with string containing of N * 'x'
const auto s = std::vector<uint8_t>(N, 'x');
const json j = json::binary(s);
// create expected byte vector (hack: create string first)
std::vector<uint8_t> expected(N, 'x');
// reverse order of commands, because we insert at begin()
expected.insert(expected.begin(), static_cast<uint8_t>(N & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 8) & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 16) & 0xff));
expected.insert(expected.begin(), static_cast<uint8_t>((N >> 24) & 0xff));
expected.insert(expected.begin(), 0x5a);
// compare result + size
const auto result = json::to_cbor(j);
CHECK(result == expected);
CHECK(result.size() == N + 5);
// check that no null byte is appended
CHECK(result.back() != '\x00');
// roundtrip
CHECK(json::from_cbor(result) == j);
CHECK(json::from_cbor(result, true, false) == j);
}
}
SECTION("indefinite size")
{
std::vector<std::uint8_t> const input = {0x5F, 0x44, 0xaa, 0xbb, 0xcc, 0xdd, 0x43, 0xee, 0xff, 0x99, 0xFF};
auto j = json::from_cbor(input);
CHECK(j.is_binary());
auto k = json::binary({0xaa, 0xbb, 0xcc, 0xdd, 0xee, 0xff, 0x99});
CAPTURE(j.dump(0, ' ', false, json::error_handler_t::strict))
CHECK(j == k);
}
SECTION("binary in array")
{
// array with three empty byte strings
std::vector<std::uint8_t> const input = {0x83, 0x40, 0x40, 0x40};
json _;
CHECK_NOTHROW(_ = json::from_cbor(input));
}
SECTION("binary in object")
{
// object mapping "foo" to empty byte string
std::vector<std::uint8_t> const input = {0xA1, 0x63, 0x66, 0x6F, 0x6F, 0x40};
json _;
CHECK_NOTHROW(_ = json::from_cbor(input));
}
SECTION("SAX callback with binary")
{
// object mapping "foo" to byte string
std::vector<std::uint8_t> const input = {0xA1, 0x63, 0x66, 0x6F, 0x6F, 0x41, 0x00};
// callback to set binary_seen to true if a binary value was seen
bool binary_seen = false;
auto callback = [&binary_seen](int /*depth*/, json::parse_event_t /*event*/, json & parsed) noexcept
{
if (parsed.is_binary())
{
binary_seen = true;
}
return true;
};
json j;
auto cbp = nlohmann::detail::json_sax_dom_callback_parser<json, nlohmann::detail::string_input_adapter_type>(j, callback, true);
CHECK(json::sax_parse(input, &cbp, json::input_format_t::cbor));
CHECK(j.at("foo").is_binary());
CHECK(binary_seen);
}
}
}
SECTION("additional deserialization")
{
SECTION("0x5b (byte array)")
{
std::vector<uint8_t> const given = {0x5b, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x01, 0x61
};
const json j = json::from_cbor(given);
CHECK(j == json::binary(std::vector<uint8_t> {'a'}));
}
SECTION("0x7b (string)")
{
std::vector<uint8_t> const given = {0x7b, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x01, 0x61
};
const json j = json::from_cbor(given);
CHECK(j == "a");
}
SECTION("0x9b (array)")
{
std::vector<uint8_t> const given = {0x9b, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x01, 0xf4
};
const json j = json::from_cbor(given);
CHECK(j == json::parse("[false]"));
}
SECTION("0xbb (map)")
{
std::vector<uint8_t> const given = {0xbb, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x01, 0x60, 0xf4
};
const json j = json::from_cbor(given);
CHECK(j == json::parse("{\"\": false}"));
}
}
SECTION("errors")
{
SECTION("empty byte vector")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>()), "[json.exception.parse_error.110] parse error at byte 1: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>(), true, false).is_discarded());
}
SECTION("too short byte vector")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x18})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x19})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x19, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1a})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1a, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1a, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1a, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 7: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 8: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 9: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x38})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x39})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x39, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3a})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3a, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3a, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3a, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3b})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3b, 0x00})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x3b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00})), "[json.exception.parse_error.110] parse error at byte 9: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x62})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x62, 0x60})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x60})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x82, 0x01})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x9F, 0x01})), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0x61, 0xF5})), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x61, 0X61})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0X61})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B); last byte: 0x00", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x41})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0x18}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x19}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x19, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1a}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1a, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1a, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1a, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x38}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x39}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x39, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3a}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3a, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3a, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3a, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3b}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3b, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x3b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x62}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x62, 0x60}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x60}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x82, 0x01}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0x01}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0x61, 0xF5}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x61, 0x61}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0x61}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x00}), true, false).is_discarded());
CHECK(json::from_cbor(std::vector<uint8_t>({0x41}), true, false).is_discarded());
}
SECTION("unsupported bytes")
{
SECTION("concrete examples")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x1c})), "[json.exception.parse_error.112] parse error at byte 1: syntax error while parsing CBOR value: invalid byte: 0x1C", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0x1c}), true, false).is_discarded());
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xf8})), "[json.exception.parse_error.112] parse error at byte 1: syntax error while parsing CBOR value: invalid byte: 0xF8", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0xf8}), true, false).is_discarded());
}
SECTION("all unsupported bytes")
{
for (const auto byte :
{
// ?
0x1c, 0x1d, 0x1e, 0x1f,
// ?
0x3c, 0x3d, 0x3e, 0x3f,
// ?
0x5c, 0x5d, 0x5e,
// ?
0x7c, 0x7d, 0x7e,
// ?
0x9c, 0x9d, 0x9e,
// ?
0xbc, 0xbd, 0xbe,
// date/time
0xc0, 0xc1,
// bignum
0xc2, 0xc3,
// fraction
0xc4,
// bigfloat
0xc5,
// tagged item
0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4,
// expected conversion
0xd5, 0xd6, 0xd7,
// more tagged items
0xd8, 0xd9, 0xda, 0xdb,
// ?
0xdc, 0xdd, 0xde, 0xdf,
// (simple value)
0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3,
// undefined
0xf7,
// simple value
0xf8
})
{
json _;
CHECK_THROWS_AS(_ = json::from_cbor(std::vector<uint8_t>({static_cast<uint8_t>(byte)})), json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({static_cast<uint8_t>(byte)}), true, false).is_discarded());
}
}
}
SECTION("invalid string in map")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
CHECK(json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01}), true, false).is_discarded());
}
SECTION("tag in front of a key that is cut off by the end of the input")
{
// 0xD8: the tag number is in the next byte, which is missing
const std::vector<std::uint8_t> input = {0xA1, 0xD8};
json _;
for (const auto handler :
{
json::cbor_tag_handler_t::ignore, json::cbor_tag_handler_t::store
})
{
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input, true, true, handler), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR number: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(input, true, false, handler).is_discarded());
}
}
SECTION("chunk of an indefinite-length string that is cut off by the end of the input")
{
// the second byte announces a chunk of three bytes, but two follow
const std::vector<std::uint8_t> input = {0x7F, 0x63, 'a', 'b'};
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 5: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("tag in front of a key")
{
const auto ignore = json::cbor_tag_handler_t::ignore;
const auto store = json::cbor_tag_handler_t::store;
const json expected = {{"a", 10}};
// the tags are skipped in front of a text string key, like in
// front of a value
const std::vector<std::vector<std::uint8_t>> tagged =
{
{0xA1, 0xC0, 0x61, 0x61, 0x0A}, // tag in the head
{0xA1, 0xD8, 0x05, 0x61, 0x61, 0x0A}, // 1-byte tag number
{0xA1, 0xD9, 0x01, 0x2C, 0x61, 0x61, 0x0A}, // 2-byte tag number
{0xA1, 0xDA, 0x00, 0x01, 0x00, 0x00, 0x61, 0x61, 0x0A}, // 4-byte tag number
{0xA1, 0xDB, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x61, 0x61, 0x0A}, // 8-byte tag number
{0xA1, 0xC0, 0xD8, 0x05, 0xC1, 0x61, 0x61, 0x0A}, // chained tags
{0xBF, 0xC0, 0x61, 0x61, 0x0A, 0xFF}, // indefinite-length map
{0xBF, 0x61, 0x62, 0x01, 0xC0, 0x61, 0x61, 0x0A, 0xFF}, // second key tagged
{0xA1, 0xC0, 0x7F, 0x61, 0x61, 0xFF, 0x0A}, // indefinite-length text key
{0xA1, 0xC0, 0x61, 0x61, 0xC0, 0x0A}, // tagged key and value
};
for (const auto& input : tagged)
{
CAPTURE(input)
json const j_ignore = json::from_cbor(input, true, true, ignore);
json const j_store = json::from_cbor(input, true, true, store);
CHECK(j_ignore.at("a") == 10);
CHECK(j_store.at("a") == 10);
CHECK(j_ignore == j_store);
}
CHECK(json::from_cbor(tagged[0], true, true, ignore) == expected);
CHECK(json::from_cbor(tagged[1], true, true, store) == expected);
// nested maps
CHECK(json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xC0, 0x61, 0x61, 0xA1, 0xD8, 0x05, 0x61, 0x62, 0x01}), true, true, ignore) == json{{"a", {{"b", 1}}}});
// the tag handler error still rejects every tag
for (const auto& input : tagged)
{
CAPTURE(input)
json _;
CHECK_THROWS_AS(_ = json::from_cbor(input), json::parse_error&);
}
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xD8, 0x05, 0x61, 0x61, 0x0A})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a tag; last byte: 0xD8", json::parse_error&);
}
// a tag does not turn a key of another type into a text string
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xC0, 0x01, 0x01}), true, true, ignore), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR object key: only string keys are supported, but found an unsigned integer; last byte: 0x01", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xD8, 0x05, 0x41, 0x61, 0x01}), true, true, store), "[json.exception.parse_error.113] parse error at byte 4: syntax error while parsing CBOR object key: only string keys are supported, but found a byte string; last byte: 0x41", json::parse_error&);
CHECK(json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xC0, 0x01, 0x01}), true, false, ignore).is_discarded());
}
// end of input after the tag, or inside the tag number
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xC0}), true, true, ignore), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xD8}), true, true, ignore), json::parse_error&);
CHECK_THROWS_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0xDB, 0x00, 0x00}), true, true, store), json::parse_error&);
CHECK_THROWS_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xBF, 0xC0}), true, true, store), json::parse_error&);
}
// SAX: the key event is reported without the tag (start_object,
// key, number_unsigned, end_object are four events)
{
const std::vector<std::uint8_t> input = {0xA1, 0xC0, 0x61, 0x61, 0x0A};
SaxCountdown four(4);
CHECK(json::sax_parse(input, &four, json::input_format_t::cbor, true, false, false, ignore));
SaxCountdown three(3);
CHECK(!json::sax_parse(input, &three, json::input_format_t::cbor, true, false, false, ignore));
SaxCountdown error_handler(4);
CHECK(!json::sax_parse(input, &error_handler, json::input_format_t::cbor));
}
// a long chain of tags needs no recursion
{
std::vector<std::uint8_t> input = {0xA1};
input.insert(input.end(), 100000, 0xC0);
input.insert(input.end(), {0x61, 0x61, 0x0A});
CHECK(json::from_cbor(input, true, true, ignore) == expected);
}
}
SECTION("non-string key (see #2766 and #3381)")
{
// only text strings map to JSON object keys; any other key is
// rejected with a message naming its type
const std::vector<std::pair<std::vector<std::uint8_t>, std::string>> cases =
{
{{0xA1, 0x01, 0x01}, "an unsigned integer; last byte: 0x01"},
{{0xA1, 0x20, 0x01}, "a negative integer; last byte: 0x20"},
{{0xA1, 0x41, 0x61, 0x01}, "a byte string; last byte: 0x41"},
{{0xA1, 0x80, 0x01}, "an array; last byte: 0x80"},
{{0xA1, 0xA0, 0x01}, "a map; last byte: 0xA0"},
{{0xA1, 0xC0, 0x61, 0x61, 0x01}, "a tag; last byte: 0xC0"},
{{0xA1, 0xF4, 0x01}, "a boolean; last byte: 0xF4"},
{{0xA1, 0xF5, 0x01}, "a boolean; last byte: 0xF5"},
{{0xA1, 0xF6, 0x01}, "null; last byte: 0xF6"},
{{0xA1, 0xF7, 0x01}, "undefined; last byte: 0xF7"},
{{0xA1, 0xF9, 0x3C, 0x00, 0x01}, "a floating-point number; last byte: 0xF9"},
{{0xA1, 0xFA, 0x3F, 0x80, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFA"},
{{0xA1, 0xFB, 0x3F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFB"},
{{0xA1, 0xE0, 0x01}, "a simple value; last byte: 0xE0"},
{{0xA1, 0xF8, 0x20, 0x01}, "a simple value; last byte: 0xF8"},
// indefinite-length map
{{0xBF, 0x01, 0x01, 0xFF}, "an unsigned integer; last byte: 0x01"},
};
for (const auto& c : cases)
{
CAPTURE(c.first)
const std::string expected = "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found " + c.second;
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(c.first), expected.c_str(), json::parse_error&);
CHECK(json::from_cbor(c.first, true, false).is_discarded());
}
// a key of major type 3 with a reserved length is still reported as
// a malformed string, and a missing key as the end of input
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x7C, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C", json::parse_error&);
}
SECTION("ill-formed UTF-8 in string (see #5529, #5651)")
{
// RFC 8949 §3.1 leaves it up to the decoder whether to reject
// ill-formed UTF-8 in a text string; this library does not, and
// hands the original bytes back unchanged, matching the
// MessagePack reader and the behavior before #5185/#5531 (not in
// any release)
// a two-character text string (major type 3) whose bytes are not
// valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') round-trips
// byte for byte as a string value
const std::vector<uint8_t> ill_formed_value = {0x62, 0xc0, 0xae};
json j_value;
CHECK_NOTHROW(j_value = json::from_cbor(ill_formed_value));
REQUIRE(j_value.is_string());
CHECK(j_value.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
// dump() still requires valid UTF-8 and throws for such a value,
// unless an error handler that replaces or ignores the bytes is
// passed
CHECK_THROWS_AS(utils::ignore_return_value(j_value.dump()), json::type_error&);
// to_cbor() writes the bytes back unchanged, as before 3.13.0,
// unless JSON_STRICT_BINARY_UTF8 is enabled (see unit-binary_utf8_strict.cpp)
CHECK(json::from_cbor(json::to_cbor(j_value)) == j_value);
// the same bytes as an object key round-trip as well
const std::vector<uint8_t> ill_formed_key = {0xa1, 0x62, 0xc0, 0xae, 0x01};
json j_key;
CHECK_NOTHROW(j_key = json::from_cbor(ill_formed_key));
REQUIRE(j_key.is_object());
CHECK(j_key.contains(std::string("\xc0\xae")));
CHECK(json::from_cbor(json::to_cbor(j_key)) == j_key);
// a CBOR byte string (major type 2) with the very same bytes is
// NOT text and must still be accepted as-is
json _;
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x42, 0xc0, 0xae})));
CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
// valid UTF-8 must still round-trip
const json j = "h\xc3\xa9llo, w\xc3\xb6rld! \xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e"; // héllo, wörld! 日本語
CHECK(json::from_cbor(json::to_cbor(j)) == j);
}
SECTION("to_cbor keeps ill-formed UTF-8 (see #5651)")
{
// to_cbor() writes the bytes unchanged, as before 3.13.0, unless
// JSON_STRICT_BINARY_UTF8 is enabled (see
// unit-binary_utf8_strict.cpp); from_cbor() reads them back as is
CHECK(json::from_cbor(json::to_cbor(json("\xFF"))) == json("\xFF"));
// a truncated multi-byte sequence
CHECK(json::from_cbor(json::to_cbor(json("\xC3"))) == json("\xC3"));
// an encoded surrogate half (U+D800)
CHECK(json::from_cbor(json::to_cbor(json("\xED\xA0\x80"))) == json("\xED\xA0\x80"));
// an overlong encoding of '.'
CHECK(json::from_cbor(json::to_cbor(json("\xC0\xAF"))) == json("\xC0\xAF"));
// an object key with ill-formed UTF-8 is kept the same way
CHECK(json::from_cbor(json::to_cbor(json{{"\xFF", 1}})) == json{{"\xFF", 1}});
// binary values are not text and are unaffected
CHECK_NOTHROW(json::to_cbor(json::binary(std::vector<std::uint8_t>({0xFF}))));
}
SECTION("ill-formed UTF-8 in indefinite-length string")
{
json _;
// with the default error handler keep, the chunks are concatenated
// as is, without checking that each chunk is valid UTF-8 on its
// own (RFC 8949, Section 3.2.3), so a code point split across two
// chunks yields a valid string
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})));
CHECK(_ == "\xc3\xa9");
CHECK(_.dump() == "\"\xc3\xa9\"");
// a truncated code point is kept as is
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0xff})));
CHECK(_ == "\xc3");
CHECK_THROWS_AS(utils::ignore_return_value(_.dump()), json::type_error&);
CHECK(json::from_cbor(json::to_cbor(_)) == _);
// an ill-formed later chunk is kept after valid ones
CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})));
CHECK(_ == "\xc3\xa9\xc0\xae");
CHECK_THROWS_AS(utils::ignore_return_value(_.dump()), json::type_error&);
// valid multi-byte chunks are accepted
CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc3, 0xb6, 0xff})) == "\xc3\xa9\xc3\xb6");
}
SECTION("ill-formed UTF-8 in a chunk of an indefinite-length string (RFC 8949, Section 3.2.3)")
{
const auto strict = json::error_handler_t::strict;
const auto replace = json::error_handler_t::replace;
const auto ignore = json::error_handler_t::ignore;
const auto keep = json::error_handler_t::keep;
const auto tags = json::cbor_tag_handler_t::error;
// a code point split over two chunks
const std::vector<std::uint8_t> split = {0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff};
// a 4-byte code point split over two chunks
const std::vector<std::uint8_t> split_emoji = {0x7f, 0x62, 0xf0, 0x9f, 0x62, 0x98, 0x80, 0xff};
// the same in an object key
const std::vector<std::uint8_t> split_key = {0xa1, 0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff, 0x01};
// a valid chunk followed by one with a truncated code point
const std::vector<std::uint8_t> truncated = {0x7f, 0x62, 0x41, 0xc3, 0x61, 0xa9, 0xff};
// strict: the string is invalid
for (const auto& input :
{
split, split_emoji, split_key, truncated
})
{
CAPTURE(input)
json _;
CHECK_THROWS_AS(_ = json::from_cbor(input, true, true, tags, strict), json::parse_error&);
CHECK(json::from_cbor(input, true, false, tags, strict).is_discarded());
}
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(split, true, true, tags, strict), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(split_key, true, true, tags, strict), "[json.exception.parse_error.113] parse error at byte 4: syntax error while parsing CBOR key: invalid string: ill-formed UTF-8 byte", json::parse_error&);
}
// replace and ignore: every chunk is sanitized on its own
CHECK(json::from_cbor(split, true, true, tags, replace) == "\xEF\xBF\xBD\xEF\xBF\xBD");
CHECK(json::from_cbor(split, true, true, tags, ignore) == "");
CHECK(json::from_cbor(truncated, true, true, tags, replace) == "A\xEF\xBF\xBD\xEF\xBF\xBD");
CHECK(json::from_cbor(truncated, true, true, tags, ignore) == "A");
CHECK(json::from_cbor(split_key, true, true, tags, replace) == json{{"\xEF\xBF\xBD\xEF\xBF\xBD", 1}});
// keep: unchanged, the chunks are concatenated as is
CHECK(json::from_cbor(split, true, true, tags, keep) == "\xc3\xa9");
CHECK(json::from_cbor(split_emoji, true, true, tags, keep) == "\xf0\x9f\x98\x80");
// conforming input is unaffected by the error handler
const std::vector<std::uint8_t> valid = {0x7f, 0x62, 0xc3, 0xa9, 0x64, 0xf0, 0x9f, 0x98, 0x80, 0x60, 0xff};
for (const auto handler :
{
strict, replace, ignore, keep
})
{
CHECK(json::from_cbor(valid, true, true, tags, handler) == "\xc3\xa9\xf0\x9f\x98\x80");
CHECK(json::from_cbor(std::vector<std::uint8_t>({0x7f, 0xff}), true, true, tags, handler) == "");
}
}
SECTION("many chunks in indefinite-length string")
{
constexpr std::size_t chunks = 100000;
std::vector<uint8_t> v{0x7f};
for (std::size_t i = 0; i < chunks; ++i)
{
v.push_back(0x61);
v.push_back('a');
}
v.push_back(0xff);
CHECK(json::from_cbor(v) == std::string(chunks, 'a'));
}
SECTION("strict mode")
{
std::vector<uint8_t> const vec = {0xf6, 0xf6};
SECTION("non-strict mode")
{
const auto result = json::from_cbor(vec, false);
CHECK(result == json());
CHECK(!json::from_cbor(vec, false, false).is_discarded());
}
SECTION("strict mode")
{
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR value: expected end of input; last byte: 0xF6", json::parse_error&);
CHECK(json::from_cbor(vec, true, false).is_discarded());
}
}
}
SECTION("SAX aborts")
{
SECTION("start_array(len)")
{
std::vector<uint8_t> const v = {0x83, 0x01, 0x02, 0x03};
SaxCountdown scp(0);
CHECK(!json::sax_parse(v, &scp, json::input_format_t::cbor));
}
SECTION("start_object(len)")
{
std::vector<uint8_t> const v = {0xA1, 0x63, 0x66, 0x6F, 0x6F, 0xF4};
SaxCountdown scp(0);
CHECK(!json::sax_parse(v, &scp, json::input_format_t::cbor));
}
SECTION("key()")
{
std::vector<uint8_t> const v = {0xA1, 0x63, 0x66, 0x6F, 0x6F, 0xF4};
SaxCountdown scp(1);
CHECK(!json::sax_parse(v, &scp, json::input_format_t::cbor));
}
}
}
// use this testcase outside [hide] to run it with Valgrind
TEST_CASE("single CBOR roundtrip")
{
SECTION("sample.json")
{
std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json";
// parse JSON file
std::ifstream f_json(filename);
const json j1 = json::parse(f_json);
// parse CBOR file
auto packed = utils::read_binary_file(filename + ".cbor");
json j2;
CHECK_NOTHROW(j2 = json::from_cbor(packed));
// compare parsed JSON values
CHECK(j1 == j2);
SECTION("roundtrips")
{
SECTION("std::ostringstream")
{
std::basic_ostringstream<char> ss;
json::to_cbor(j1, ss);
json j3 = json::from_cbor(ss.str());
CHECK(j1 == j3);
}
SECTION("std::string")
{
std::string s;
json::to_cbor(j1, s);
json j3 = json::from_cbor(s);
CHECK(j1 == j3);
}
}
// check with different start index
packed.insert(packed.begin(), 5, 0xff);
CHECK(j1 == json::from_cbor(packed.begin() + 5, packed.end()));
}
}
TEST_CASE("Parse CBOR directly from a file using iterator and sentinel")
{
std::string const filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json.cbor";
std::ifstream file(filename, std::ios::binary);
const std::istreambuf_iterator<char> first(file);
const json parsed = json::from_cbor(first, utils::istreambuf_sentinel{});
CHECK((parsed.is_object() || parsed.is_array()));
}
#if !defined(JSON_NOEXCEPTION)
TEST_CASE("CBOR regressions")
{
SECTION("fuzz test results")
{
/*
The following test cases were found during a two-day session with
AFL-Fuzz. As a result, empty byte vectors and excessive lengths are
detected.
*/
for (const std::string filename :
{
TEST_DATA_DIRECTORY "/cbor_regression/test01",
TEST_DATA_DIRECTORY "/cbor_regression/test02",
TEST_DATA_DIRECTORY "/cbor_regression/test03",
TEST_DATA_DIRECTORY "/cbor_regression/test04",
TEST_DATA_DIRECTORY "/cbor_regression/test05",
TEST_DATA_DIRECTORY "/cbor_regression/test06",
TEST_DATA_DIRECTORY "/cbor_regression/test07",
TEST_DATA_DIRECTORY "/cbor_regression/test08",
TEST_DATA_DIRECTORY "/cbor_regression/test09",
TEST_DATA_DIRECTORY "/cbor_regression/test10",
TEST_DATA_DIRECTORY "/cbor_regression/test11",
TEST_DATA_DIRECTORY "/cbor_regression/test12",
TEST_DATA_DIRECTORY "/cbor_regression/test13",
TEST_DATA_DIRECTORY "/cbor_regression/test14",
TEST_DATA_DIRECTORY "/cbor_regression/test15",
TEST_DATA_DIRECTORY "/cbor_regression/test16",
TEST_DATA_DIRECTORY "/cbor_regression/test17",
TEST_DATA_DIRECTORY "/cbor_regression/test18",
TEST_DATA_DIRECTORY "/cbor_regression/test19",
TEST_DATA_DIRECTORY "/cbor_regression/test20",
TEST_DATA_DIRECTORY "/cbor_regression/test21"
})
{
CAPTURE(filename)
try
{
// parse CBOR file
auto vec1 = utils::read_binary_file(filename);
const json j1 = json::from_cbor(vec1);
try
{
// step 2: round trip
std::vector<uint8_t> const vec2 = json::to_cbor(j1);
// parse serialization
json j2 = json::from_cbor(vec2);
// deserializations must match
CHECK(j1 == j2);
}
catch (const json::parse_error&)
{
// parsing a CBOR serialization must not fail
CHECK(false);
}
}
catch (const json::parse_error&) // NOLINT(bugprone-empty-catch)
{
// parse errors are ok, because input may be random bytes
}
}
}
}
#endif
TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
{
// A definite-length array or map whose declared element count equals the
// reserved unknown_size() sentinel (SIZE_MAX) must be rejected. Otherwise
// it is read as an indefinite-length container and the following bytes are
// silently accepted instead of the (impossible) count being reported.
json _;
SECTION("array")
{
// 0x9B: array with eight-byte length; length = 0xFFFFFFFFFFFFFFFF
const std::vector<uint8_t> input = {0x9B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x01, 0x02, 0xFF};
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive array size", json::out_of_range&);
}
SECTION("map")
{
// 0xBB: map with eight-byte length; length = 0xFFFFFFFFFFFFFFFF
const std::vector<uint8_t> input = {0xBB, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x61, 0x61, 0x01, 0xFF};
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.out_of_range.408] syntax error while parsing CBOR size: excessive map size", json::out_of_range&);
}
SECTION("indefinite-length containers are unaffected")
{
CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0x01, 0x02, 0xFF})) == json({1, 2}));
CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0x61, 0x01, 0xFF})) == json({{"a", 1}}));
}
SECTION("ordinary four-byte length containers are unaffected")
{
// 0x9A/0xBA carry a four-byte length; a normal count still parses
CHECK(json::from_cbor(std::vector<uint8_t>({0x9A, 0x00, 0x00, 0x00, 0x02, 0x01, 0x02})) == json({1, 2}));
CHECK(json::from_cbor(std::vector<uint8_t>({0xBA, 0x00, 0x00, 0x00, 0x01, 0x61, 0x61, 0x01})) == json({{"a", 1}}));
}
}
TEST_CASE("CBOR nesting does not consume the call stack")
{
// Containers used to be read by calling back into the value reader once
// per element, and a tag by calling it for the tagged value, so the native
// call stack grew with the nesting depth of the input. Each of the three
// costs a single byte to encode -- 0x9F, 0x81 and 0xC2 -- so a payload of
// repeated bytes crashed the process (#5104). The containers are kept on a
// heap stack now, and a tag is read in a loop.
//
// Deeply nested values must not be compared, copied or dumped here: those
// operations are still recursive and would reintroduce the crash.
json _;
SECTION("indefinite-length containers")
{
const std::vector<uint8_t> input(500000, 0x9F);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 500001: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("definite-length containers")
{
const std::vector<uint8_t> input(500000, 0x81);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 500001: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("tags")
{
// a tag is not a value of its own, so a chain of them used to recurse
const std::vector<uint8_t> input(500000, 0xC2);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input, true, true, json::cbor_tag_handler_t::ignore), "[json.exception.parse_error.110] parse error at byte 500001: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK(json::from_cbor(input, true, false, json::cbor_tag_handler_t::ignore).is_discarded());
}
SECTION("stored tags")
{
// a tag over something other than a byte string is read like for
// ignore, so a chain of them must not recurse either (#5316)
std::vector<uint8_t> input;
for (std::size_t i = 0; i < 500000; ++i)
{
input.push_back(0xD8);
input.push_back(0x18);
}
input.push_back(0x01);
CHECK(json::from_cbor(input, true, true, json::cbor_tag_handler_t::store) == 1);
}
SECTION("a well-formed deep value is read through the SAX interface")
{
std::vector<uint8_t> input(200000, 0x9F);
input.insert(input.end(), 200000, 0xFF);
SaxCountdown accept_all(1000000);
CHECK(json::sax_parse(input, &accept_all, json::input_format_t::cbor));
}
SECTION("a well-formed deep value is read into a value")
{
const std::size_t depth = 10000;
std::vector<uint8_t> input(depth, 0x81);
input.push_back(0x00);
json j = json::from_cbor(input);
std::size_t measured = 0;
const json* p = &j;
while (p->is_array() && !p->empty())
{
p = &p->front();
++measured;
}
CHECK(measured == depth);
CHECK(p->is_number());
}
SECTION("containers are still read the same way")
{
CHECK(json::from_cbor(std::vector<uint8_t>({0x80})) == json::array());
CHECK(json::from_cbor(std::vector<uint8_t>({0xA0})) == json::object());
CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0xFF})) == json::array());
CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0xFF})) == json::object());
CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0x01, 0x02, 0xFF})) == json({1, 2}));
CHECK(json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 'a', 0x01, 0xFF})) == json({{"a", 1}}));
// definite and indefinite forms nested inside each other
CHECK(json::from_cbor(std::vector<uint8_t>({0x9F, 0x82, 0x01, 0x02, 0xA1, 0x61, 'k', 0xBF, 0xFF, 0xFF})) == json({{1, 2}, {{"k", json::object()}}}));
}
SECTION("tagged values are still read the same way")
{
const auto ignore = json::cbor_tag_handler_t::ignore;
CHECK(json::from_cbor(std::vector<uint8_t>({0xC2, 0x01}), true, true, ignore) == json(1));
// a chain of tags resolves to the value that follows it
CHECK(json::from_cbor(std::vector<uint8_t>({0xC2, 0xC2, 0xC2, 0x01}), true, true, ignore) == json(1));
// a tag inside a container, and one in front of a container
CHECK(json::from_cbor(std::vector<uint8_t>({0x82, 0xC2, 0x01, 0x02}), true, true, ignore) == json({1, 2}));
CHECK(json::from_cbor(std::vector<uint8_t>({0xC2, 0x82, 0x01, 0x02}), true, true, ignore) == json({1, 2}));
}
}
TEST_CASE("CBOR input that cannot be read is discarded by every overload")
{
std::vector<std::uint8_t> input = json::to_cbor(json({{"a", {1, 2}}}));
input.pop_back();
json _;
CHECK_THROWS_AS(_ = json::from_cbor(input.begin(), input.end()), json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
CHECK(json::from_cbor(input.begin(), input.end(), true, false).is_discarded());
#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
CHECK(json::from_cbor(input.data(), input.size(), true, false).is_discarded());
CHECK(json::from_cbor({input.data(), input.size()}, true, false).is_discarded());
#endif
// a string that ends early, read through iterators that are not
// contiguous and have to be copied from one element at a time
const std::list<std::uint8_t> truncated_string = {0x63, 'a', 'b'};
CHECK(json::from_cbor(truncated_string.begin(), truncated_string.end(), true, false).is_discarded());
const std::list<std::uint8_t> complete_string = {0x63, 'a', 'b', 'c'};
CHECK(json::from_cbor(complete_string.begin(), complete_string.end()) == "abc");
}
TEST_CASE("CBOR SAX parsing stops at every event")
{
// Containers are opened and closed by the loop that reads them; a SAX
// handler that rejects any event - including the end of a nested
// container - must stop the parse right there.
const auto count_events = [](const std::vector<std::uint8_t>& input)
{
int events = 0;
while (true)
{
SaxCountdown scp(events);
if (json::sax_parse(input, &scp, json::input_format_t::cbor))
{
return events;
}
++events;
REQUIRE(events < 1000);
}
};
// 20 events: every container kind closes inside another one
const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
CHECK(count_events(json::to_cbor(j)) == 20);
CHECK(count_events(std::vector<std::uint8_t>({0xBF, 0x61, 'a', 0x9F, 0x01, 0xFF, 0xFF})) == 6);
}
TEST_CASE("CBOR arrays of scalars from contiguous and non-contiguous input")
{
// contiguous input reads the integers, floats, booleans, and nulls an
// array begins with in one loop, other input value by value; both must
// give the same events, value, or error for the complete document and for
// every truncation of it, and stop at every event a SAX handler rejects
const std::vector<std::uint8_t> cbor =
{
0xA3, // map(3)
0x61, 'a', // "a"
0x98, 0x16, // array(22)
0x00, 0x17, 0x18, 0xFF, 0x19, 0x01, 0x00, // 0, 23, 255, 256
0x1A, 0x00, 0x01, 0x00, 0x00, // 65536
0x1B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 18446744073709551615
0x20, 0x37, 0x38, 0xFF, 0x39, 0x01, 0x00, // -1, -24, -256, -257
0x3A, 0x00, 0x01, 0x00, 0x00, // -65537
0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // -18446744073709551616 (a float)
0x3B, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // -9223372036854775808
0xF4, 0xF5, 0xF6, // false, true, null
0xFA, 0x3F, 0xC0, 0x00, 0x00, // 1.5 (float32)
0xFB, 0xBF, 0xB9, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9A, // -0.1
0xF9, 0x3C, 0x00, // 1.0 (float16, ends the loop)
0x01, 0x61, 'a', // 1, "a"
0xFB, 0x40, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 2.5
0x61, 'b', // "b"
0x83, // array(3)
0x82, 0xFB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
0xFB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // -3.75]
0x82, 0xFB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
0xFB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // -3.75]
0x80, // []
0x61, 'c', // "c"
0x84, 0xA0, 0x01, 0xC1, 0x02, 0x81, 0x03 // [{}, 1, tag(1) 2, [3]]
};
const auto tags = json::cbor_tag_handler_t::ignore;
const json j = json::from_cbor(cbor, true, true, tags);
CHECK(j["a"].size() == 22);
CHECK(j["a"][5] == 18446744073709551615u);
CHECK(j["a"][11].is_number_float());
CHECK(j["a"][11] == -18446744073709551616.0);
CHECK(j["a"][12] == (std::numeric_limits<std::int64_t>::min)());
CHECK(j["a"][17] == -0.1);
CHECK(j["b"] == json::parse("[[1.25, -3.75], [1.25, -3.75], []]"));
CHECK(j["c"] == json::parse("[{}, 1, 2, [3]]"));
for (std::size_t length = 0; length <= cbor.size(); ++length)
{
CAPTURE(length)
const std::vector<std::uint8_t> contiguous(cbor.begin(), cbor.begin() + static_cast<std::ptrdiff_t>(length));
const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
CHECK(json::from_cbor(contiguous, true, false, tags).dump() == json::from_cbor(bytewise.begin(), bytewise.end(), true, false, tags).dump());
SaxEventLogger from_contiguous;
SaxEventLogger from_bytewise;
CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::cbor, true, false, false, tags)
== json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false, false, tags));
CHECK(from_contiguous.events == from_bytewise.events);
}
for (int events = 0; events <= 60; ++events)
{
CAPTURE(events)
const std::list<std::uint8_t> bytewise(cbor.begin(), cbor.end());
SaxCountdown from_contiguous(events);
SaxCountdown from_bytewise(events);
CHECK(json::sax_parse(cbor, &from_contiguous, json::input_format_t::cbor, true, false, false, tags)
== json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false, false, tags));
}
}
TEST_CASE("CBOR arrays of one element from contiguous and non-contiguous input")
{
// contiguous input leaves an array of one element to the general path
// rather than to the loop that reads arrays of scalars; both inputs must
// still give the same events, value, or error for the complete document
// and for every truncation of it, with enough bytes after each array that
// the loop could have been entered
const json j = json::parse(R"({"a": [[[[1.5]]]], "b": [7], "c": [{"x": 2.5}], "d": ["s"], "e": [[1, 2]], "f": [null], "g": 1.25})");
const std::vector<std::uint8_t> bytes = json::to_cbor(j);
CHECK(json::from_cbor(bytes) == j);
for (std::size_t length = 0; length <= bytes.size(); ++length)
{
CAPTURE(length)
const std::vector<std::uint8_t> contiguous(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length));
const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
CHECK(json::from_cbor(contiguous, true, false).dump() == json::from_cbor(bytewise.begin(), bytewise.end(), true, false).dump());
SaxEventLogger from_contiguous;
SaxEventLogger from_bytewise;
CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::cbor, true, false)
== json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false));
CHECK(from_contiguous.events == from_bytewise.events);
}
}
TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
{
// Reading an indefinite-length string or byte array used to call itself
// once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
// the call stack before any of the input was rejected. Nested indefinite
// chunks are now rejected at the second byte, without recursing.
json _;
SECTION("nested levels are rejected, not crashed on")
{
const std::vector<uint8_t> input(200000, 0x7F);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: indefinite-length string is not allowed inside indefinite-length string; last byte: 0x7F", json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("nested levels are rejected, not crashed on (binary)")
{
const std::vector<uint8_t> input(200000, 0x5F);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: indefinite-length binary array is not allowed inside indefinite-length binary array; last byte: 0x5F", json::parse_error&);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
SECTION("chunks are still concatenated")
{
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
// empty and nonempty definite-length chunks concatenate in order
CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 'a', 0x60, 0x61, 'b', 0x61, 'c', 0xFF})) == json("abc"));
CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
}
SECTION("chunks are still concatenated (binary)")
{
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0xFF})) == json::binary({}));
CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0x40, 0x41, 0x62, 0x41, 0x63, 0xFF})) == json::binary({0x61, 0x62, 0x63}));
}
SECTION("a chunk that is not a string is still rejected")
{
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B); last byte: 0x00", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B); last byte: 0x00", json::parse_error&);
}
SECTION("a break marker outside an indefinite-length string is not a string")
{
// 0xFF only closes a string that was opened; on its own it is not one
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
}
}
TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
{
#if !defined(JSON_NOEXCEPTION)
// this SECTION relies on catching a thrown exception to distinguish
// which of two acceptable, bounded rejections a hostile header took;
// under JSON_NOEXCEPTION, JSON_THROW never produces a catchable C++
// exception (it aborts instead), so this cannot be tested that way here
SECTION("a huge claimed length with no element data must not over-allocate")
{
// 0x9A: array with a four-byte length; claims 0xFFFFFFFF (4294967295)
// elements but provides none. max_size() for a std::vector is far
// larger than this count, so it does not reject the header outright;
// the (capped) reservation must not attempt to allocate space for
// billions of elements before the missing data is detected.
json _;
const std::vector<uint8_t> input = {0x9A, 0xFF, 0xFF, 0xFF, 0xFF};
// On a platform where std::size_t is narrower than 64 bits (e.g.
// 32-bit), the claimed count 0xFFFFFFFF coincides with that
// platform's detail::unknown_size() sentinel (SIZE_MAX), so the
// format-level size check rejects it outright (out_of_range.408,
// "excessive ... size") before the SAX consumer's own max_size()
// check would even run; on a 64-bit platform it passes both of
// those checks and is only found short of data once the (capped)
// reservation looks for element bytes that were never provided
// (parse_error.110). Either is an acceptable, bounded rejection of
// the hostile header -- the property under test is that no path
// attempts to allocate space for billions of elements.
bool threw = false;
try
{
_ = json::from_cbor(input);
}
catch (const json::parse_error& e)
{
threw = true;
CHECK(e.id == 110);
CHECK(std::string(e.what()) == "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing CBOR value: unexpected end of input");
}
catch (const json::out_of_range& e)
{
threw = true;
CHECK(e.id == 408);
CHECK(std::string(e.what()).find("excessive") != std::string::npos);
}
CHECK(threw);
CHECK(json::from_cbor(input, true, false).is_discarded());
}
#endif
SECTION("arrays of various sizes decode to the same value as before the reserve optimization")
{
for (const auto size :
{
std::size_t{0}, std::size_t{1}, std::size_t{5}, // small
std::size_t{16384}, // exactly at the reserve cap
std::size_t{20000} // above the reserve cap
})
{
CAPTURE(size)
json j = json::array();
for (std::size_t i = 0; i < size; ++i)
{
j.push_back(static_cast<int>(i % 1000));
}
const auto packed = json::to_cbor(j);
CHECK(json::from_cbor(packed) == j);
}
}
SECTION("a user-defined SAX consumer is unaffected by the internal DOM reserve optimization")
{
// the reserve() call is local to json_sax_dom_parser / json_sax_dom_callback_parser;
// a custom SAX consumer that does not touch a DOM array sees identical events
json j = json::array();
for (int i = 0; i < 100; ++i)
{
j.push_back(i);
}
const auto packed = json::to_cbor(j);
SaxCountdown scp(1000000); // large enough to never trigger an abort
CHECK(json::sax_parse(packed, &scp, json::input_format_t::cbor));
}
}
namespace
{
// NOLINTBEGIN(bugprone-derived-method-shadowing-base-method)
using dom_parser = nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::input_stream_adapter>;
// handlers that wrap a DOM parser, as users of the SAX interface do
struct public_wrapper : dom_parser
{
explicit public_wrapper(json& result) : dom_parser(result, false)
{}
};
/// parses another input with itself while the first parse is still running
struct reentrant_wrapper : dom_parser
{
explicit reentrant_wrapper(json& result) : dom_parser(result, false)
{}
bool start_array(std::size_t len)
{
if (!inner_done)
{
inner_done = true;
const std::vector<std::uint8_t> input = {0x80};
json::sax_parse(input, this, json::input_format_t::cbor);
}
return dom_parser::start_array(len);
}
bool inner_done = false;
};
// ICC does not detect SAX members that a using-declaration exposes from a private or protected base
#if !defined(__INTEL_COMPILER)
class private_wrapper : private dom_parser
{
public:
explicit private_wrapper(json& result) : dom_parser(result, false)
{}
using dom_parser::null;
using dom_parser::boolean;
using dom_parser::number_integer;
using dom_parser::number_unsigned;
using dom_parser::number_float;
using dom_parser::string;
using dom_parser::binary;
using dom_parser::start_array;
using dom_parser::end_array;
using dom_parser::parse_error;
// the DOM parser has private overloads of these, which a using
// declaration cannot expose; the input of the test has no objects
static bool start_object(std::size_t /*len*/)
{
return false;
}
static bool key(std::string& /*val*/)
{
return false;
}
static bool end_object()
{
return false;
}
};
class protected_wrapper : protected dom_parser
{
public:
explicit protected_wrapper(json& result) : dom_parser(result, false)
{}
using dom_parser::null;
using dom_parser::boolean;
using dom_parser::number_integer;
using dom_parser::number_unsigned;
using dom_parser::number_float;
using dom_parser::string;
using dom_parser::binary;
using dom_parser::start_array;
using dom_parser::end_array;
using dom_parser::parse_error;
// the DOM parser has private overloads of these, which a using
// declaration cannot expose; the input of the test has no objects
static bool start_object(std::size_t /*len*/)
{
return false;
}
static bool key(std::string& /*val*/)
{
return false;
}
static bool end_object()
{
return false;
}
};
#endif
// NOLINTEND(bugprone-derived-method-shadowing-base-method)
/// the capacity of the fifth array of five that are open
std::size_t innermost_capacity(const json& result)
{
const json* node = &result;
for (int level = 0; level < 4; ++level)
{
node = &node->front();
}
return node->get_ref<const json::array_t&>().capacity();
}
} // namespace
TEST_CASE("CBOR - open arrays reserve only what the input has backed")
{
// an array that announces its size gets storage for (up to 16384 of) its
// elements when it opens; the arrays that are open at the same time must
// not hold more than the input read so far can back
SECTION("nested headers that announce 16384 elements and are never completed")
{
// 200 levels would hold 200 * 16384 * sizeof(json),
// if each of them reserved what it announces
const auto input = utils::repeated({0x99, 0x40, 0x00}, 200);
utils::counts() = utils::allocation_counts{};
const auto j = utils::counted_json::from_cbor(input, true, false);
CHECK(j.is_discarded());
CAPTURE(utils::counts().peak)
// the credit is 65,536 values; the base peaks at more than 3 million
CHECK(utils::counts().peak < sizeof(utils::counted_json) * 128 * 1024);
}
SECTION("a completed array is still reserved in one allocation")
{
json array = json::array();
for (int i = 0; i < 10000; ++i)
{
array.push_back(i % 100);
}
{
const auto packed = json::to_cbor(array);
utils::counts() = utils::allocation_counts{};
const auto j = utils::counted_json::from_cbor(packed);
CHECK(j.size() == 10000);
// the array and its storage; growing the storage as the elements
// arrive would take more than a dozen allocations
CAPTURE(utils::counts().allocations)
CHECK(utils::counts().allocations <= 4);
}
}
SECTION("an array that is given less than it announces is still decoded")
{
// five levels that announce 16384 elements each, the first of which
// is the next level: they are more than the input could back when
// they open
constexpr std::size_t levels = 5;
std::vector<std::uint8_t> input;
for (std::size_t level = 0; level < levels; ++level)
{
input.insert(input.end(), {0x99, 0x40, 0x00});
}
input.insert(input.end(), 16384, 0x01);
for (std::size_t level = 1; level < levels; ++level)
{
input.insert(input.end(), 16383, 0x02);
}
const auto j = json::from_cbor(input);
const json* node = &j;
for (std::size_t level = 0; level < levels; ++level)
{
REQUIRE(node->is_array());
CHECK(node->size() == 16384);
node = &node->front();
}
CHECK(*node == 1);
CHECK(j.back() == 2);
}
SECTION("an array that announces more than 16384 elements is charged what it is reserved")
{
// an array of 20000 elements (header 9A 00 00 4E 20) and three nested
// arrays of 16384: the four reservations of 16384 add up to the credit
// of 65,536. Charged the 20000 it announces, the outer array would
// leave the innermost one less than it announces
std::vector<std::uint8_t> input = {0x9A, 0x00, 0x00, 0x4E, 0x20};
const auto nested = utils::repeated({0x99, 0x40, 0x00}, 3);
input.insert(input.end(), nested.begin(), nested.end());
json result;
dom_parser parser(result, false);
CHECK_FALSE(json::sax_parse(input, &parser, json::input_format_t::cbor));
const json* node = &result;
for (int level = 0; level < 4; ++level)
{
CAPTURE(level)
REQUIRE(node->is_array());
CHECK(node->get_ref<const json::array_t&>().capacity() == 16384);
if (level < 3)
{
REQUIRE(node->size() == 1);
node = &node->front();
}
}
}
SECTION("a DOM parser that a parse has finished with is not bounded by the input of that parse")
{
// the DOM parser learns where the reader counts its characters, and
// must forget it when the parse is over: a handler may be driven by
// other code afterwards, while the reader no longer exists
// five levels announce more than the credit of one input, which a
// parse of one byte has hardly refilled
const auto check_unbounded = [](dom_parser & parser, json & result)
{
for (int level = 0; level < 5; ++level)
{
CHECK(parser.start_array(16384));
}
const json* node = &result;
for (int level = 0; level < 4; ++level)
{
REQUIRE(node->is_array());
REQUIRE(node->size() == 1);
node = &node->front();
}
REQUIRE(node->is_array());
CHECK(node->get_ref<const json::array_t&>().capacity() == 16384);
};
SECTION("after a parse that succeeded")
{
json result;
dom_parser parser(result, false);
const std::vector<std::uint8_t> input = {0x80};
CHECK(json::sax_parse(input, &parser, json::input_format_t::cbor));
check_unbounded(parser, result);
}
#if !defined(JSON_NOEXCEPTION)
SECTION("after a parse that threw")
{
json result;
dom_parser parser(result, true);
const std::vector<std::uint8_t> input = {0x1C}; // not a CBOR value
CHECK_THROWS_AS(json::sax_parse(input, &parser, json::input_format_t::cbor), json::parse_error&);
check_unbounded(parser, result);
}
#endif
}
SECTION("a handler that wraps a DOM parser is bound if the reader can reach the parser")
{
// five arrays announce 16384 elements: the credit of one input covers
// four of them, and a parse of 15 bytes has hardly refilled it
const auto input = utils::repeated({0x99, 0x40, 0x00}, 5);
SECTION("public base")
{
json result;
public_wrapper handler(result);
CHECK_FALSE(json::sax_parse(input, &handler, json::input_format_t::cbor));
CHECK(innermost_capacity(result) < 16384);
}
SECTION("public base, a parse inside the parse")
{
json result;
reentrant_wrapper handler(result);
CHECK_FALSE(json::sax_parse(input, &handler, json::input_format_t::cbor));
CHECK(handler.inner_done);
CHECK(innermost_capacity(result) < 16384);
}
#if !defined(__INTEL_COMPILER)
// the reader cannot convert these to the DOM parser: they are not bound
SECTION("private base")
{
json result;
private_wrapper handler(result);
CHECK_FALSE(json::sax_parse(input, &handler, json::input_format_t::cbor));
CHECK(innermost_capacity(result) == 16384);
}
SECTION("protected base")
{
json result;
protected_wrapper handler(result);
CHECK_FALSE(json::sax_parse(input, &handler, json::input_format_t::cbor));
CHECK(innermost_capacity(result) == 16384);
}
#endif
}
SECTION("SAX events report the announced size")
{
SaxEventLogger logger;
const std::vector<std::uint8_t> input = {0x99, 0x40, 0x00};
CHECK_FALSE(json::sax_parse(input, &logger, json::input_format_t::cbor));
REQUIRE(logger.events.size() == 2);
CHECK(logger.events[0] == "start_array(16384)");
CHECK(logger.events[1] == "parse_error(4)");
}
}
#if !defined(JSON_NOEXCEPTION) // corpus values that do not survive the round trip are skipped by catching the exception
TEST_CASE("CBOR round-trip invariants")
{
// This checks what the parse_cbor_fuzzer driver checks (see
// tests/src/fuzzer-parse_cbor.cpp), so that a regression shows up in CI
// rather than as an OSS-Fuzz report: anything from_cbor() returns (j1)
// can be serialized, parsed back (j2), and serialized again to reproduce
// the exact bytes.
for (const auto& j0 : utils::round_trip_corpus::values())
{
json j1;
try
{
// turn the corpus value into a value as from_cbor() returns it
j1 = json::from_cbor(json::to_cbor(j0));
}
catch (const json::exception&)
{
// not every corpus value survives a CBOR round trip (e.g., a
// binary subtype is written with a tag the default tag handler
// then rejects); the fuzzer driver only ever sees values
// from_cbor() actually produced, so skip those here, too
continue;
}
INFO("j1 = " << j1.dump());
const std::vector<std::uint8_t> vec = json::to_cbor(j1);
json j2;
// anything the library writes must be parsable by the library
REQUIRE_NOTHROW(j2 = json::from_cbor(vec));
CHECK(json::to_cbor(j2) == vec);
}
}
#endif
TEST_CASE("CBOR roundtrips" * doctest::skip())
{
SECTION("input from flynn")
{
// most of these are excluded due to differences in key order (not a real problem)
std::set<std::string> exclude_packed;
exclude_packed.insert(TEST_DATA_DIRECTORY "/json.org/1.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/json.org/2.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/json.org/3.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/json.org/4.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/json.org/5.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/json_testsuite/sample.json"); // kills AppVeyor
exclude_packed.insert(TEST_DATA_DIRECTORY "/json_tests/pass1.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/regression/working_file.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_duplicated_key.json");
exclude_packed.insert(TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_long_strings.json");
for (const std::string filename :
{
TEST_DATA_DIRECTORY "/json_nlohmann_tests/all_unicode.json",
TEST_DATA_DIRECTORY "/json.org/1.json",
TEST_DATA_DIRECTORY "/json.org/2.json",
TEST_DATA_DIRECTORY "/json.org/3.json",
TEST_DATA_DIRECTORY "/json.org/4.json",
TEST_DATA_DIRECTORY "/json.org/5.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip01.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip02.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip03.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip04.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip05.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip06.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip07.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip08.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip09.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip10.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip11.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip12.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip13.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip14.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip15.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip16.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip17.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip18.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip19.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip20.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip21.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip22.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip23.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip24.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip25.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip26.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip27.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip28.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip29.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip30.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip31.json",
TEST_DATA_DIRECTORY "/json_roundtrip/roundtrip32.json",
TEST_DATA_DIRECTORY "/json_testsuite/sample.json", // kills AppVeyor
TEST_DATA_DIRECTORY "/json_tests/pass1.json",
TEST_DATA_DIRECTORY "/json_tests/pass2.json",
TEST_DATA_DIRECTORY "/json_tests/pass3.json",
TEST_DATA_DIRECTORY "/regression/floats.json",
TEST_DATA_DIRECTORY "/regression/signed_ints.json",
TEST_DATA_DIRECTORY "/regression/unsigned_ints.json",
TEST_DATA_DIRECTORY "/regression/working_file.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_arraysWithSpaces.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_empty-string.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_empty.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_ending_with_newline.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_false.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_heterogeneous.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_null.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_with_1_and_newline.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_with_leading_space.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_with_several_null.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_array_with_trailing_space.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_0e+1.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_0e1.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_after_space.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_double_close_to_zero.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_double_huge_neg_exp.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_huge_exp.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_int_with_exp.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_minus_zero.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_negative_int.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_negative_one.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_negative_zero.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_capital_e.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_capital_e_neg_exp.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_capital_e_pos_exp.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_exponent.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_fraction_exponent.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_neg_exp.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_neg_overflow.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_pos_exponent.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_pos_overflow.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_real_underflow.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_simple_int.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_simple_real.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_too_big_neg_int.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_too_big_pos_int.json",
//TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_number_very_big_negative_int.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_basic.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_duplicated_key.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_duplicated_key_and_value.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_empty.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_empty_key.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_escaped_null_in_key.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_extreme_numbers.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_long_strings.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_simple.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_string_unicode.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_object_with_newlines.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_1_2_3_bytes_UTF-8_sequences.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_UTF-16_Surrogates_U+1D11E_MUSICAL_SYMBOL_G_CLEF.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_accepted_surrogate_pair.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_accepted_surrogate_pairs.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_allowed_escapes.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_backslash_and_u_escaped_zero.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_backslash_doublequotes.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_comments.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_double_escape_a.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_double_escape_n.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_escaped_control_character.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_escaped_noncharacter.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_in_array.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_in_array_with_leading_space.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_last_surrogates_1_and_2.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_newline_uescaped.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_nonCharacterInUTF-8_U+10FFFF.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_nonCharacterInUTF-8_U+1FFFF.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_nonCharacterInUTF-8_U+FFFF.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_null_escape.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_one-byte-utf-8.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_pi.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_simple_ascii.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_space.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_three-byte-utf-8.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_two-byte-utf-8.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_u+2028_line_sep.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_u+2029_par_sep.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_uEscape.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unescaped_char_delete.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicode.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicodeEscapedBackslash.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicode_2.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicode_U+200B_ZERO_WIDTH_SPACE.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicode_U+2064_invisible_plus.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_unicode_escaped_double_quote.json",
// TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_utf16.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_utf8.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_string_with_del_character.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_false.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_int.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_negative_real.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_null.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_string.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_lonely_true.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_string_empty.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_trailing_newline.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_true_in_array.json",
TEST_DATA_DIRECTORY "/nst_json_testsuite/test_parsing/y_structure_whitespace_array.json"
})
{
CAPTURE(filename)
std::ifstream f_json(filename);
const json j1 = json::parse(f_json);
const auto packed = utils::read_binary_file(filename + ".cbor");
{
INFO_WITH_TEMP(filename + ": std::vector<uint8_t>");
json j2;
CHECK_NOTHROW(j2 = json::from_cbor(packed));
CHECK(j1 == j2);
}
{
INFO_WITH_TEMP(filename + ": std::ifstream");
std::ifstream f_cbor(filename + ".cbor", std::ios::binary);
json j2;
CHECK_NOTHROW(j2 = json::from_cbor(f_cbor));
CHECK(j1 == j2);
}
#ifndef JSON_TEST_DEPRECATED_FUNCTIONS_DELETED
{
INFO_WITH_TEMP(filename + ": uint8_t* and size");
json j2;
CHECK_NOTHROW(j2 = json::from_cbor({packed.data(), packed.size()}));
CHECK(j1 == j2);
}
#endif
{
INFO_WITH_TEMP(filename + ": output to output adapters");
if (exclude_packed.count(filename) == 0u)
{
{
INFO_WITH_TEMP(filename + ": output adapters: std::vector<uint8_t>");
std::vector<uint8_t> vec;
json::to_cbor(j1, vec);
CHECK(vec == packed);
}
}
}
}
}
}
#if !defined(JSON_NOEXCEPTION)
TEST_CASE("all CBOR first bytes")
{
// these bytes will fail immediately with exception parse_error.112
std::set<uint8_t> unsupported =
{
//// types not supported by this library
// date/time
0xc0, 0xc1,
// bignum
0xc2, 0xc3,
// decimal fracion
0xc4,
// bigfloat
0xc5,
// tagged item
0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd,
0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd8,
0xd9, 0xda, 0xdb,
// expected conversion
0xd5, 0xd6, 0xd7,
// simple value
0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xef, 0xf0,
0xf1, 0xf2, 0xf3,
0xf8,
// undefined
0xf7,
//// bytes not specified by CBOR
0x1c, 0x1d, 0x1e, 0x1f,
0x3c, 0x3d, 0x3e, 0x3f,
0x5c, 0x5d, 0x5e,
0x7c, 0x7d, 0x7e,
0x9c, 0x9d, 0x9e,
0xbc, 0xbd, 0xbe,
0xdc, 0xdd, 0xde, 0xdf,
0xee,
0xfc, 0xfe, 0xfd,
/// break cannot be the first byte
0xff
};
for (auto i = 0; i < 256; ++i)
{
const auto byte = static_cast<uint8_t>(i);
try
{
auto res = json::from_cbor(std::vector<uint8_t>(1, byte));
}
catch (const json::parse_error& e)
{
// check that parse_error.112 is only thrown if the
// first byte is in the unsupported set
INFO_WITH_TEMP(e.what());
if (unsupported.find(byte) != unsupported.end())
{
CHECK(e.id == 112);
}
else
{
CHECK(e.id != 112);
}
}
}
}
#endif
TEST_CASE("examples from RFC 8949 Appendix A")
{
SECTION("numbers")
{
CHECK(json::to_cbor(json::parse("0")) == std::vector<uint8_t>({0x00}));
CHECK(json::parse("0") == json::from_cbor(std::vector<uint8_t>({0x00})));
CHECK(json::to_cbor(json::parse("1")) == std::vector<uint8_t>({0x01}));
CHECK(json::parse("1") == json::from_cbor(std::vector<uint8_t>({0x01})));
CHECK(json::to_cbor(json::parse("10")) == std::vector<uint8_t>({0x0a}));
CHECK(json::parse("10") == json::from_cbor(std::vector<uint8_t>({0x0a})));
CHECK(json::to_cbor(json::parse("23")) == std::vector<uint8_t>({0x17}));
CHECK(json::parse("23") == json::from_cbor(std::vector<uint8_t>({0x17})));
CHECK(json::to_cbor(json::parse("24")) == std::vector<uint8_t>({0x18, 0x18}));
CHECK(json::parse("24") == json::from_cbor(std::vector<uint8_t>({0x18, 0x18})));
CHECK(json::to_cbor(json::parse("25")) == std::vector<uint8_t>({0x18, 0x19}));
CHECK(json::parse("25") == json::from_cbor(std::vector<uint8_t>({0x18, 0x19})));
CHECK(json::to_cbor(json::parse("100")) == std::vector<uint8_t>({0x18, 0x64}));
CHECK(json::parse("100") == json::from_cbor(std::vector<uint8_t>({0x18, 0x64})));
CHECK(json::to_cbor(json::parse("1000")) == std::vector<uint8_t>({0x19, 0x03, 0xe8}));
CHECK(json::parse("1000") == json::from_cbor(std::vector<uint8_t>({0x19, 0x03, 0xe8})));
CHECK(json::to_cbor(json::parse("1000000")) == std::vector<uint8_t>({0x1a, 0x00, 0x0f, 0x42, 0x40}));
CHECK(json::parse("1000000") == json::from_cbor(std::vector<uint8_t>({0x1a, 0x00, 0x0f, 0x42, 0x40})));
CHECK(json::to_cbor(json::parse("1000000000000")) == std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0xe8, 0xd4, 0xa5, 0x10, 0x00}));
CHECK(json::parse("1000000000000") == json::from_cbor(std::vector<uint8_t>({0x1b, 0x00, 0x00, 0x00, 0xe8, 0xd4, 0xa5, 0x10, 0x00})));
CHECK(json::to_cbor(json::parse("18446744073709551615")) == std::vector<uint8_t>({0x1b, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}));
CHECK(json::parse("18446744073709551615") == json::from_cbor(std::vector<uint8_t>({0x1b, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff})));
// positive bignum is not supported
//CHECK(json::to_cbor(json::parse("18446744073709551616")) == std::vector<uint8_t>({0xc2, 0x49, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}));
//CHECK(json::parse("18446744073709551616") == json::from_cbor(std::vector<uint8_t>({0xc2, 0x49, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00})));
//CHECK(json::to_cbor(json::parse("-18446744073709551616")) == std::vector<uint8_t>({0x3b, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}));
//CHECK(json::parse("-18446744073709551616") == json::from_cbor(std::vector<uint8_t>({0x3b, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff})));
// negative bignum is not supported
//CHECK(json::to_cbor(json::parse("-18446744073709551617")) == std::vector<uint8_t>({0xc3, 0x49, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}));
//CHECK(json::parse("-18446744073709551617") == json::from_cbor(std::vector<uint8_t>({0xc3, 0x49, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00})));
CHECK(json::to_cbor(json::parse("-1")) == std::vector<uint8_t>({0x20}));
CHECK(json::parse("-1") == json::from_cbor(std::vector<uint8_t>({0x20})));
CHECK(json::to_cbor(json::parse("-10")) == std::vector<uint8_t>({0x29}));
CHECK(json::parse("-10") == json::from_cbor(std::vector<uint8_t>({0x29})));
CHECK(json::to_cbor(json::parse("-100")) == std::vector<uint8_t>({0x38, 0x63}));
CHECK(json::parse("-100") == json::from_cbor(std::vector<uint8_t>({0x38, 0x63})));
CHECK(json::to_cbor(json::parse("-1000")) == std::vector<uint8_t>({0x39, 0x03, 0xe7}));
CHECK(json::parse("-1000") == json::from_cbor(std::vector<uint8_t>({0x39, 0x03, 0xe7})));
// half-precision float
//CHECK(json::to_cbor(json::parse("0.0")) == std::vector<uint8_t>({0xf9, 0x00, 0x00}));
CHECK(json::parse("0.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x00})));
// half-precision float
//CHECK(json::to_cbor(json::parse("-0.0")) == std::vector<uint8_t>({0xf9, 0x80, 0x00}));
CHECK(json::parse("-0.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x80, 0x00})));
// half-precision float
//CHECK(json::to_cbor(json::parse("1.0")) == std::vector<uint8_t>({0xf9, 0x3c, 0x00}));
CHECK(json::parse("1.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x3c, 0x00})));
CHECK(json::to_cbor(json::parse("1.1")) == std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a}));
CHECK(json::parse("1.1") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a})));
// the writer never emits half-precision floats, so these can only be decoded, not encoded
CHECK(json::parse("1.5") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x3e, 0x00})));
CHECK(json::parse("65504.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x7b, 0xff})));
CHECK(json::to_cbor(json::parse("100000.0")) == std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00}));
CHECK(json::parse("100000.0") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00})));
CHECK(json::to_cbor(json::parse("3.4028234663852886e+38")) == std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff}));
CHECK(json::parse("3.4028234663852886e+38") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff})));
CHECK(json::to_cbor(json::parse("1.0e+300")) == std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c}));
CHECK(json::parse("1.0e+300") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c})));
CHECK(json::parse("5.960464477539063e-8") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x01})));
CHECK(json::parse("0.00006103515625") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x04, 0x00})));
CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
CHECK(json::to_cbor(json::parse("-4.1")) == std::vector<uint8_t>({0xfb, 0xc0, 0x10, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66}));
CHECK(json::parse("-4.1") == json::from_cbor(std::vector<uint8_t>({0xfb, 0xc0, 0x10, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66})));
}
SECTION("simple values")
{
CHECK(json::to_cbor(json::parse("false")) == std::vector<uint8_t>({0xf4}));
CHECK(json::parse("false") == json::from_cbor(std::vector<uint8_t>({0xf4})));
CHECK(json::to_cbor(json::parse("true")) == std::vector<uint8_t>({0xf5}));
CHECK(json::parse("true") == json::from_cbor(std::vector<uint8_t>({0xf5})));
CHECK(json::to_cbor(json::parse("true")) == std::vector<uint8_t>({0xf5}));
CHECK(json::parse("true") == json::from_cbor(std::vector<uint8_t>({0xf5})));
}
SECTION("strings")
{
CHECK(json::to_cbor(json::parse("\"\"")) == std::vector<uint8_t>({0x60}));
CHECK(json::parse("\"\"") == json::from_cbor(std::vector<uint8_t>({0x60})));
CHECK(json::to_cbor(json::parse("\"a\"")) == std::vector<uint8_t>({0x61, 0x61}));
CHECK(json::parse("\"a\"") == json::from_cbor(std::vector<uint8_t>({0x61, 0x61})));
CHECK(json::to_cbor(json::parse("\"IETF\"")) == std::vector<uint8_t>({0x64, 0x49, 0x45, 0x54, 0x46}));
CHECK(json::parse("\"IETF\"") == json::from_cbor(std::vector<uint8_t>({0x64, 0x49, 0x45, 0x54, 0x46})));
CHECK(json::to_cbor(json::parse("\"\\u00fc\"")) == std::vector<uint8_t>({0x62, 0xc3, 0xbc}));
CHECK(json::parse("\"\\u00fc\"") == json::from_cbor(std::vector<uint8_t>({0x62, 0xc3, 0xbc})));
CHECK(json::to_cbor(json::parse("\"\\u6c34\"")) == std::vector<uint8_t>({0x63, 0xe6, 0xb0, 0xb4}));
CHECK(json::parse("\"\\u6c34\"") == json::from_cbor(std::vector<uint8_t>({0x63, 0xe6, 0xb0, 0xb4})));
CHECK(json::to_cbor(json::parse("\"\\ud800\\udd51\"")) == std::vector<uint8_t>({0x64, 0xf0, 0x90, 0x85, 0x91}));
CHECK(json::parse("\"\\ud800\\udd51\"") == json::from_cbor(std::vector<uint8_t>({0x64, 0xf0, 0x90, 0x85, 0x91})));
// indefinite length strings
CHECK(json::parse("\"streaming\"") == json::from_cbor(std::vector<uint8_t>({0x7f, 0x65, 0x73, 0x74, 0x72, 0x65, 0x61, 0x64, 0x6d, 0x69, 0x6e, 0x67, 0xff})));
}
SECTION("byte arrays")
{
const auto packed = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.cbor");
json j;
// the fixture's tail contains nested indefinite-length byte strings.
CHECK_THROWS_WITH_AS(j = json::from_cbor(packed), "[json.exception.parse_error.113] parse error at byte 513: syntax error while parsing CBOR binary: indefinite-length binary array is not allowed inside indefinite-length binary array; last byte: 0x5F", json::parse_error&);
// keep the byte-for-byte decoding check for its valid prefix: the first
// 512 encoded bytes contain 468 payload bytes in definite-length chunks.
auto valid_prefix = packed;
valid_prefix.resize(512);
valid_prefix.push_back(0xFF);
auto expected = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.out");
expected.resize(468);
CHECK_NOTHROW(j = json::from_cbor(valid_prefix));
CHECK(j == json::binary(expected));
// 0xd8
CHECK(json::to_cbor(json::binary(std::vector<uint8_t> {}, 0x42)) == std::vector<uint8_t> {0xd8, 0x42, 0x40});
CHECK(!json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 0x42)), true, true, json::cbor_tag_handler_t::ignore).get_binary().has_subtype());
CHECK(json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 0x42)), true, true, json::cbor_tag_handler_t::store).get_binary().subtype() == 0x42);
// 0xd9
CHECK(json::to_cbor(json::binary(std::vector<uint8_t> {}, 1000)) == std::vector<uint8_t> {0xd9, 0x03, 0xe8, 0x40});
CHECK(!json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 1000)), true, true, json::cbor_tag_handler_t::ignore).get_binary().has_subtype());
CHECK(json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 1000)), true, true, json::cbor_tag_handler_t::store).get_binary().subtype() == 1000);
// 0xda
CHECK(json::to_cbor(json::binary(std::vector<uint8_t> {}, 394216)) == std::vector<uint8_t> {0xda, 0x00, 0x06, 0x03, 0xe8, 0x40});
CHECK(!json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 394216)), true, true, json::cbor_tag_handler_t::ignore).get_binary().has_subtype());
CHECK(json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 394216)), true, true, json::cbor_tag_handler_t::store).get_binary().subtype() == 394216);
// 0xdb
CHECK(json::to_cbor(json::binary(std::vector<uint8_t> {}, 8589934590)) == std::vector<uint8_t> {0xdb, 0x00, 0x00, 0x00, 0x01, 0xff, 0xff, 0xff, 0xfe, 0x40});
CHECK(!json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 8589934590)), true, true, json::cbor_tag_handler_t::ignore).get_binary().has_subtype());
CHECK(json::from_cbor(json::to_cbor(json::binary(std::vector<uint8_t> {}, 8589934590)), true, true, json::cbor_tag_handler_t::store).get_binary().subtype() == 8589934590);
}
SECTION("arrays")
{
CHECK(json::to_cbor(json::parse("[]")) == std::vector<uint8_t>({0x80}));
CHECK(json::parse("[]") == json::from_cbor(std::vector<uint8_t>({0x80})));
CHECK(json::to_cbor(json::parse("[1, 2, 3]")) == std::vector<uint8_t>({0x83, 0x01, 0x02, 0x03}));
CHECK(json::parse("[1, 2, 3]") == json::from_cbor(std::vector<uint8_t>({0x83, 0x01, 0x02, 0x03})));
CHECK(json::to_cbor(json::parse("[1, [2, 3], [4, 5]]")) == std::vector<uint8_t>({0x83, 0x01, 0x82, 0x02, 0x03, 0x82, 0x04, 0x05}));
CHECK(json::parse("[1, [2, 3], [4, 5]]") == json::from_cbor(std::vector<uint8_t>({0x83, 0x01, 0x82, 0x02, 0x03, 0x82, 0x04, 0x05})));
CHECK(json::to_cbor(json::parse("[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25]")) == std::vector<uint8_t>({0x98, 0x19, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x18, 0x18, 0x19}));
CHECK(json::parse("[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25]") == json::from_cbor(std::vector<uint8_t>({0x98, 0x19, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x18, 0x18, 0x19})));
// indefinite length arrays
CHECK(json::parse("[]") == json::from_cbor(std::vector<uint8_t>({0x9f, 0xff})));
CHECK(json::parse("[1, [2, 3], [4, 5]] ") == json::from_cbor(std::vector<uint8_t>({0x9f, 0x01, 0x82, 0x02, 0x03, 0x9f, 0x04, 0x05, 0xff, 0xff})));
CHECK(json::parse("[1, [2, 3], [4, 5]]") == json::from_cbor(std::vector<uint8_t>({0x9f, 0x01, 0x82, 0x02, 0x03, 0x82, 0x04, 0x05, 0xff})));
CHECK(json::parse("[1, [2, 3], [4, 5]]") == json::from_cbor(std::vector<uint8_t>({0x83, 0x01, 0x82, 0x02, 0x03, 0x9f, 0x04, 0x05, 0xff})));
CHECK(json::parse("[1, [2, 3], [4, 5]]") == json::from_cbor(std::vector<uint8_t>({0x83, 0x01, 0x9f, 0x02, 0x03, 0xff, 0x82, 0x04, 0x05})));
CHECK(json::parse("[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25]") == json::from_cbor(std::vector<uint8_t>({0x9f, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x18, 0x18, 0x19, 0xff})));
}
SECTION("objects")
{
CHECK(json::to_cbor(json::parse("{}")) == std::vector<uint8_t>({0xa0}));
CHECK(json::parse("{}") == json::from_cbor(std::vector<uint8_t>({0xa0})));
CHECK(json::to_cbor(json::parse("{\"a\": 1, \"b\": [2, 3]}")) == std::vector<uint8_t>({0xa2, 0x61, 0x61, 0x01, 0x61, 0x62, 0x82, 0x02, 0x03}));
CHECK(json::parse("{\"a\": 1, \"b\": [2, 3]}") == json::from_cbor(std::vector<uint8_t>({0xa2, 0x61, 0x61, 0x01, 0x61, 0x62, 0x82, 0x02, 0x03})));
CHECK(json::to_cbor(json::parse("[\"a\", {\"b\": \"c\"}]")) == std::vector<uint8_t>({0x82, 0x61, 0x61, 0xa1, 0x61, 0x62, 0x61, 0x63}));
CHECK(json::parse("[\"a\", {\"b\": \"c\"}]") == json::from_cbor(std::vector<uint8_t>({0x82, 0x61, 0x61, 0xa1, 0x61, 0x62, 0x61, 0x63})));
CHECK(json::to_cbor(json::parse("{\"a\": \"A\", \"b\": \"B\", \"c\": \"C\", \"d\": \"D\", \"e\": \"E\"}")) == std::vector<uint8_t>({0xa5, 0x61, 0x61, 0x61, 0x41, 0x61, 0x62, 0x61, 0x42, 0x61, 0x63, 0x61, 0x43, 0x61, 0x64, 0x61, 0x44, 0x61, 0x65, 0x61, 0x45}));
CHECK(json::parse("{\"a\": \"A\", \"b\": \"B\", \"c\": \"C\", \"d\": \"D\", \"e\": \"E\"}") == json::from_cbor(std::vector<uint8_t>({0xa5, 0x61, 0x61, 0x61, 0x41, 0x61, 0x62, 0x61, 0x42, 0x61, 0x63, 0x61, 0x43, 0x61, 0x64, 0x61, 0x44, 0x61, 0x65, 0x61, 0x45})));
// indefinite length objects
CHECK(json::parse("{\"a\": 1, \"b\": [2, 3]}") == json::from_cbor(std::vector<uint8_t>({0xbf, 0x61, 0x61, 0x01, 0x61, 0x62, 0x9f, 0x02, 0x03, 0xff, 0xff})));
CHECK(json::parse("[\"a\", {\"b\": \"c\"}]") == json::from_cbor(std::vector<uint8_t>({0x82, 0x61, 0x61, 0xbf, 0x61, 0x62, 0x61, 0x63, 0xff})));
CHECK(json::parse("{\"Fun\": true, \"Amt\": -2}") == json::from_cbor(std::vector<uint8_t>({0xbf, 0x63, 0x46, 0x75, 0x6e, 0xf5, 0x63, 0x41, 0x6d, 0x74, 0x21, 0xff})));
}
}
TEST_CASE("Tagged values")
{
const json j = "s";
auto v = json::to_cbor(j);
const json j_bin_payload = json::binary(std::vector<std::uint8_t> {0x01, 0x02, 0x03});
auto v_bin_payload = json::to_cbor(j_bin_payload);
SECTION("0xC0..0xD7")
{
for (const auto b : std::vector<std::uint8_t>
{
0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5,
0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4,
0xD5, 0xD6, 0xD7
})
{
CAPTURE(b)
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), b);
// check that parsing fails in error mode
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
// check that parsing succeeds and gets original value in ignore mode
auto j_tagged = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore);
CHECK(j_tagged == j);
auto j_tagged_stored = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::store);
CHECK(j_tagged_stored == j);
auto v_binary_tagged = v_bin_payload;
v_binary_tagged.insert(v_binary_tagged.begin(), b);
auto j_binary_tagged_stored = json::from_cbor(v_binary_tagged, true, true, json::cbor_tag_handler_t::store);
CHECK(j_binary_tagged_stored == j_bin_payload);
CHECK(!j_binary_tagged_stored.get_binary().has_subtype());
}
}
SECTION("0xD8 - 1 byte follows")
{
SECTION("success")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xD8); // tag
// check that parsing fails in error mode
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
// check that parsing succeeds and gets original value in ignore mode
auto j_tagged = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore);
CHECK(j_tagged == j);
}
SECTION("missing byte after tag")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0xD8); // tag
// check that parsing fails in all modes
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore), json::parse_error);
}
}
SECTION("0xD9 - 2 byte follow")
{
SECTION("success")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xD9); // tag
// check that parsing fails in error mode
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
// check that parsing succeeds and gets original value in ignore mode
auto j_tagged = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore);
CHECK(j_tagged == j);
}
SECTION("missing byte after tag")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xD9); // tag
// check that parsing fails in all modes
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore), json::parse_error);
}
}
SECTION("0xDA - 4 bytes follow")
{
SECTION("success")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xDA); // tag
// check that parsing fails in error mode
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
// check that parsing succeeds and gets original value in ignore mode
auto j_tagged = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore);
CHECK(j_tagged == j);
}
SECTION("missing bytes after tag")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xDA); // tag
// check that parsing fails in all modes
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore), json::parse_error);
}
}
SECTION("0xDB - 8 bytes follow")
{
SECTION("success")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xDB); // tag
// check that parsing fails in error mode
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
// check that parsing succeeds and gets original value in ignore mode
auto j_tagged = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore);
CHECK(j_tagged == j);
}
SECTION("missing byte after tag")
{
// add tag to value
auto v_tagged = v;
v_tagged.insert(v_tagged.begin(), 0x42); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x23); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x22); // 1 byte
v_tagged.insert(v_tagged.begin(), 0x11); // 1 byte
v_tagged.insert(v_tagged.begin(), 0xDB); // tag
// check that parsing fails in all modes
json _;
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::error), json::parse_error);
CHECK_THROWS_AS(_ = json::from_cbor(v_tagged, true, true, json::cbor_tag_handler_t::ignore), json::parse_error);
}
SECTION("issue #5316 - cbor_tag_handler_t::store on non-binary tagged items")
{
// 55799({"a": 1}) -- CBOR self-describe magic followed by a map
const std::vector<std::uint8_t> v_map{0xD9, 0xD9, 0xF7, 0xA1, 0x61, 0x61, 0x01};
CHECK(json::from_cbor(v_map, true, true, json::cbor_tag_handler_t::ignore) == json({{"a", 1}}));
CHECK(json::from_cbor(v_map, true, true, json::cbor_tag_handler_t::store) == json({{"a", 1}}));
// Tag 24 over unsigned integer 5
const std::vector<std::uint8_t> v_int{0xD8, 0x18, 0x05};
CHECK(json::from_cbor(v_int, true, true, json::cbor_tag_handler_t::ignore) == 5);
CHECK(json::from_cbor(v_int, true, true, json::cbor_tag_handler_t::store) == 5);
// Tag 24 over text string "foo"
const std::vector<std::uint8_t> v_str{0xD8, 0x18, 0x63, 'f', 'o', 'o'};
CHECK(json::from_cbor(v_str, true, true, json::cbor_tag_handler_t::ignore) == "foo");
CHECK(json::from_cbor(v_str, true, true, json::cbor_tag_handler_t::store) == "foo");
// Tag 24 over array [1, 2]
const std::vector<std::uint8_t> v_arr{0xD8, 0x18, 0x82, 0x01, 0x02};
CHECK(json::from_cbor(v_arr, true, true, json::cbor_tag_handler_t::ignore) == json({1, 2}));
CHECK(json::from_cbor(v_arr, true, true, json::cbor_tag_handler_t::store) == json({1, 2}));
// Tag 24 over boolean true
const std::vector<std::uint8_t> v_bool{0xD8, 0x18, 0xF5};
CHECK(json::from_cbor(v_bool, true, true, json::cbor_tag_handler_t::ignore) == true);
CHECK(json::from_cbor(v_bool, true, true, json::cbor_tag_handler_t::store) == true);
// Tag 24 over null
const std::vector<std::uint8_t> v_null{0xD8, 0x18, 0xF6};
CHECK(json::from_cbor(v_null, true, true, json::cbor_tag_handler_t::ignore) == nullptr);
CHECK(json::from_cbor(v_null, true, true, json::cbor_tag_handler_t::store) == nullptr);
// Nested tags: tag 55799 over tag 24 over integer 42
const std::vector<std::uint8_t> v_nested{0xD9, 0xD9, 0xF7, 0xD8, 0x18, 0x18, 0x2A};
CHECK(json::from_cbor(v_nested, true, true, json::cbor_tag_handler_t::ignore) == 42);
CHECK(json::from_cbor(v_nested, true, true, json::cbor_tag_handler_t::store) == 42);
// Tag 24 over byte string continues to store subtype as before
const std::vector<std::uint8_t> v_bin{0xD8, 0x18, 0x42, 0xCA, 0xFE};
auto j_bin_store = json::from_cbor(v_bin, true, true, json::cbor_tag_handler_t::store);
CHECK(j_bin_store.is_binary());
CHECK(j_bin_store.get_binary().has_subtype());
CHECK(j_bin_store.get_binary().subtype() == 24);
CHECK(j_bin_store.get_binary() == json::binary({0xCA, 0xFE}, 24).get_binary());
// Tagged values inside a container under store: [24(1), 25(h'0001')]
const std::vector<std::uint8_t> v_container{0x82, 0xD8, 0x18, 0x01, 0xD8, 0x19, 0x42, 0x00, 0x01};
auto j_container_store = json::from_cbor(v_container, true, true, json::cbor_tag_handler_t::store);
CHECK(j_container_store.is_array());
CHECK(j_container_store.size() == 2);
CHECK(j_container_store[0] == 1);
CHECK(j_container_store[1].is_binary());
CHECK(j_container_store[1].get_binary().has_subtype());
CHECK(j_container_store[1].get_binary().subtype() == 25);
CHECK(j_container_store[1].get_binary() == json::binary({0x00, 0x01}, 25).get_binary());
// Tagged values as object values under store: {"a": 55799(1), "b": 24(h'01')}
const std::vector<std::uint8_t> v_object{0xA2, 0x61, 'a', 0xD9, 0xD9, 0xF7, 0x01, 0x61, 'b', 0xD8, 0x18, 0x41, 0x01};
CHECK(json::from_cbor(v_object, true, true, json::cbor_tag_handler_t::store) == json({{"a", 1}, {"b", json::binary({0x01}, 24)}}));
// two tags in a row before a byte string: the inner tag is stored
// (this uses item_read and then the byte-string path)
const std::vector<std::uint8_t> v_nested_byte_string{0xD8, 0x18, 0xD8, 0x19, 0x42, 0x00, 0x01};
CHECK(json::from_cbor(v_nested_byte_string, true, true, json::cbor_tag_handler_t::store) == json::binary({0x00, 0x01}, 25));
// errors after a stored tag are now the same as with ignore
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t> {0xD8, 0x18}, true, true, json::cbor_tag_handler_t::store), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t> {0xD8, 0x18, 0x1C}, true, true, json::cbor_tag_handler_t::store), "[json.exception.parse_error.112] parse error at byte 3: syntax error while parsing CBOR value: invalid byte: 0x1C", json::parse_error&);
}
}
SECTION("negative integer overflow")
{
// CBOR encodes negative integers as: result = -1 - n
// For type 0x3B, n is an 8-byte uint64_t. Valid range for n with
// the default int64_t is [0, INT64_MAX], producing results in [INT64_MIN, -1].
// When n > INT64_MAX, the result exceeds int64_t range and is stored
// as a floating-point number, as the lexer does for JSON text.
SECTION("n = 0 is valid (result = -1)")
{
// n = 0, result = -1 - 0 = -1 (smallest magnitude negative)
const std::vector<uint8_t> input = {0x3B, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
const auto result = json::from_cbor(input);
CHECK(result.is_number_integer());
CHECK(result.get<int64_t>() == -1);
}
SECTION("n = INT64_MAX is valid (result = INT64_MIN)")
{
// n = INT64_MAX (0x7FFFFFFFFFFFFFFF)
// result = -1 - INT64_MAX = INT64_MIN (-9223372036854775808)
const std::vector<uint8_t> input = {0x3B, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
const auto result = json::from_cbor(input);
CHECK(result.is_number_integer());
CHECK(result.get<int64_t>() == (std::numeric_limits<int64_t>::min)());
}
SECTION("n = INT64_MAX + 1 is stored as float")
{
// n = INT64_MAX + 1 (0x8000000000000000)
// result = -1 - n = -9223372036854775809, which exceeds int64_t range;
// the nearest double is -9223372036854775808.0
const std::vector<uint8_t> input = {0x3B, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
const auto result = json::from_cbor(input);
CHECK(result.is_number_float());
CHECK(result.get<double>() == -9223372036854775808.0);
CHECK(result == json::parse("-9223372036854775809"));
}
SECTION("n = UINT64_MAX is stored as float")
{
// n = UINT64_MAX (0xFFFFFFFFFFFFFFFF)
// result = -1 - n = -18446744073709551616, which exceeds int64_t range
const std::vector<uint8_t> input = {0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
const auto result = json::from_cbor(input);
CHECK(result.is_number_float());
CHECK(result.get<double>() == -18446744073709551616.0);
CHECK(result == json::parse("-18446744073709551616"));
}
SECTION("overflow with allow_exceptions=false is not an error")
{
const std::vector<uint8_t> input = {0x3B, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
const auto result = json::from_cbor(input, true, false);
CHECK(result.is_number_float());
}
}
SECTION("tagged binary")
{
// create a binary value of subtype 42
json j_binary;
j_binary["binary"] = json::binary({0xCA, 0xFE, 0xBA, 0xBE}, 42);
// convert to CBOR
const auto vec = json::to_cbor(j_binary);
CHECK(vec == std::vector<std::uint8_t> {0xA1, 0x66, 0x62, 0x69, 0x6E, 0x61, 0x72, 0x79, 0xD8, 0x2A, 0x44, 0xCA, 0xFE, 0xBA, 0xBE});
// parse error when parsing tagged value
json _;
CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.112] parse error at byte 9: syntax error while parsing CBOR value: invalid byte: 0xD8", json::parse_error);
// binary without subtype when tags are ignored
json jb = json::from_cbor(vec, true, true, json::cbor_tag_handler_t::ignore);
CHECK(jb.is_object());
CHECK(jb["binary"].is_binary());
CHECK(!jb["binary"].get_binary().has_subtype());
}
}
TEST_CASE("CBOR large strings and binaries (chunked reader)")
{
// The binary reader reads strings and byte arrays in bounded chunks; make
// sure roundtripping is correct for lengths around and beyond the internal
// chunk size (4096 bytes), for both vector (iterator) and pointer inputs.
for (const std::size_t len :
{
std::size_t{0}, std::size_t{1}, std::size_t{4095}, std::size_t{4096},
std::size_t{4097}, std::size_t{8192}, std::size_t{100000}
})
{
CAPTURE(len)
// text string
const json j_string = std::string(len, 'x');
const std::vector<std::uint8_t> v_string = json::to_cbor(j_string);
CHECK(json::from_cbor(v_string) == j_string);
// pointer input exercises the std::memcpy fast path
CHECK(json::from_cbor(reinterpret_cast<const char*>(v_string.data()),
reinterpret_cast<const char*>(v_string.data()) + v_string.size()) == j_string);
// byte string
const json j_binary = json::binary(std::vector<std::uint8_t>(len, 0xCD));
const std::vector<std::uint8_t> v_binary = json::to_cbor(j_binary);
CHECK(json::from_cbor(v_binary) == j_binary);
CHECK(json::from_cbor(reinterpret_cast<const char*>(v_binary.data()),
reinterpret_cast<const char*>(v_binary.data()) + v_binary.size()) == j_binary);
// a truncated payload must still be reported as an error, never crash
// or loop, regardless of the (large) announced length
if (len > 16)
{
std::vector<std::uint8_t> truncated = v_string;
truncated.resize(truncated.size() - 8);
json _;
CHECK_THROWS_AS(_ = json::from_cbor(truncated), json::parse_error);
}
}
}