mirror of
https://github.com/nlohmann/json.git
synced 2026-09-12 19:27:59 +00:00
* Read BSON documents without recursing per nesting level An embedded document (record type 0x03) or array (0x04) was read by calling back into the document reader, which read its element list, which called the element reader again for the next embedded one. The native call stack therefore grew with the nesting depth of the input, and about seven bytes buy a level, so a document of a few hundred kilobytes crashes the process (#5104). This is the last of the four binary formats to still do that. Apply the same shape as the other three: open_bson_document() reads the size prefix and opens the document, parse_bson_element_internal() calls it for both record types instead of recursing, and parse_bson_internal() loops over the element list of whichever document is innermost, closing it when its terminator is reached and resuming the one below. check_bson_document_size() is unchanged, and so is when it runs: a document is still measured from the byte before its size prefix to the byte after its terminator, and still reported before the end event. The frame carries those two values, which is what a per-document check needs once the reads are interleaved rather than nested. Nothing else about the element reader changes. unit-bson passes unchanged. Round trips through to_bson of nested objects, arrays, arrays of objects and mixed nesting are identical to the previous commit, as are the errors for a truncated document, an unsupported record type, a negative size and a size that does not match, including their byte offsets. A 30,000-level document built by to_bson is now read to completion where it used to crash. Note for sequencing: #5185 changes parse_bson_internal(), the element list and the array reader, which are the functions this commit restructures. It should land first; this commit then keeps its checks and moves them onto the loop. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * Make parse_bson_internal's end-of-document top a copy, not a reference Same issue as the CBOR and UBJSON/BJData readers: top aliased container_stack.back() and was read (top.is_object) right after container_stack.pop_back() ended its lifetime. A copy stays valid regardless of what happens to the stack; nothing here mutates the live entry, so no field needs to go through container_stack.back() directly. Signed-off-by: Niels Lohmann <mail@nlohmann.me> --------- Signed-off-by: Niels Lohmann <mail@nlohmann.me>
1691 lines
61 KiB
C++
1691 lines
61 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"
|
|
|
|
#include <nlohmann/json.hpp>
|
|
using nlohmann::json;
|
|
|
|
#include <cstdint>
|
|
#include <fstream>
|
|
#include <limits>
|
|
#include <sstream>
|
|
#include <vector>
|
|
#include "make_test_data_available.hpp"
|
|
#include "test_utils.hpp"
|
|
|
|
namespace
|
|
{
|
|
// a binary container that reports a size beyond INT32_MAX without allocating
|
|
// that much memory, so the BSON length overflow can be tested cheaply
|
|
class huge_binary_t : public std::vector<std::uint8_t>
|
|
{
|
|
public:
|
|
using std::vector<std::uint8_t>::vector;
|
|
|
|
size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
|
|
{
|
|
// one byte more than the BSON length field can represent
|
|
return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
|
|
}
|
|
};
|
|
|
|
using huge_binary_json = nlohmann::basic_json <
|
|
std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
|
|
double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
|
|
|
|
// a string type that can be made to report a size beyond INT32_MAX without
|
|
// allocating that much memory, so BSON length overflow can be tested for
|
|
// strings and (embedded) documents as well, following the same idea as
|
|
// huge_binary_t.
|
|
//
|
|
// Unlike huge_binary_t (which is only ever used as the BSON *value* type),
|
|
// this type doubles as basic_json's StringType and is therefore also used
|
|
// for *object keys* (e.g. "s" or "nested" below). Only the designated test
|
|
// value is meant to lie about its size - if every huge_string_t (including
|
|
// keys) reported a huge size, the running totals computed while walking the
|
|
// BSON document (see calc_bson_object_size & friends in binary_writer.hpp)
|
|
// would need more than 32 bits, and on platforms where std::size_t is only
|
|
// 32 bits wide that arithmetic would silently wrap around, producing wrong
|
|
// (or even unguarded) lengths. The fake size is therefore opt-in via
|
|
// as_huge(), and plain strings - in particular object keys - keep reporting
|
|
// their real, small size.
|
|
class huge_string_t : public std::string
|
|
{
|
|
public:
|
|
using std::string::string;
|
|
huge_string_t(const std::string& s) : std::string(s) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
|
|
|
|
// returns a copy of @a s whose size() pretends to be huge
|
|
static huge_string_t as_huge(const std::string& s)
|
|
{
|
|
huge_string_t result(s);
|
|
result.pretend_huge = true;
|
|
return result;
|
|
}
|
|
|
|
size_type size() const noexcept
|
|
{
|
|
if (pretend_huge)
|
|
{
|
|
// one byte more than the BSON length field can represent
|
|
return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
|
|
}
|
|
return std::string::size();
|
|
}
|
|
|
|
private:
|
|
bool pretend_huge = false;
|
|
};
|
|
|
|
using huge_string_json = nlohmann::basic_json <
|
|
std::map, std::vector, huge_string_t, bool, std::int64_t, std::uint64_t,
|
|
double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
|
|
} // namespace
|
|
|
|
TEST_CASE("BSON")
|
|
{
|
|
SECTION("individual values not supported")
|
|
{
|
|
SECTION("null")
|
|
{
|
|
json const j = nullptr;
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is null", json::type_error&);
|
|
}
|
|
|
|
SECTION("boolean")
|
|
{
|
|
SECTION("true")
|
|
{
|
|
json const j = true;
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is boolean", json::type_error&);
|
|
}
|
|
|
|
SECTION("false")
|
|
{
|
|
json const j = false;
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is boolean", json::type_error&);
|
|
}
|
|
}
|
|
|
|
SECTION("number")
|
|
{
|
|
json const j = 42;
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is number", json::type_error&);
|
|
}
|
|
|
|
SECTION("float")
|
|
{
|
|
json const j = 4.2;
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is number", json::type_error&);
|
|
}
|
|
|
|
SECTION("string")
|
|
{
|
|
json const j = "not supported";
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is string", json::type_error&);
|
|
}
|
|
|
|
SECTION("array")
|
|
{
|
|
json const j = std::vector<int> {1, 2, 3, 4, 5, 6, 7};
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.type_error.317] to serialize to BSON, top-level type must be object, but is array", json::type_error&);
|
|
}
|
|
}
|
|
|
|
SECTION("keys containing code-point U+0000 cannot be serialized to BSON")
|
|
{
|
|
json const j =
|
|
{
|
|
{ std::string("en\0try", 6), true }
|
|
};
|
|
#if JSON_DIAGNOSTICS
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.out_of_range.409] (/en) BSON key cannot contain code point U+0000 (at byte 2)", json::out_of_range&);
|
|
#else
|
|
CHECK_THROWS_WITH_AS(json::to_bson(j), "[json.exception.out_of_range.409] BSON key cannot contain code point U+0000 (at byte 2)", json::out_of_range&);
|
|
#endif
|
|
}
|
|
|
|
SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
|
|
{
|
|
// out_of_range.412 is thrown from a single shared helper
|
|
// (to_bson_length) that guards the BSON length fields of binary
|
|
// values, strings, and (embedded) documents alike
|
|
SECTION("binary")
|
|
{
|
|
huge_binary_json j;
|
|
j["b"] = huge_binary_json::binary(huge_binary_t{});
|
|
|
|
CHECK_THROWS_WITH_AS(huge_binary_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_binary_json::out_of_range&);
|
|
}
|
|
|
|
SECTION("string")
|
|
{
|
|
huge_string_json j;
|
|
j["s"] = huge_string_t::as_huge("value");
|
|
|
|
CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
|
|
}
|
|
|
|
SECTION("document")
|
|
{
|
|
// an oversized string nested one level deep makes the
|
|
// *embedded* document's own length exceed INT32_MAX as well
|
|
huge_string_json nested;
|
|
nested["s"] = huge_string_t::as_huge("value");
|
|
huge_string_json j;
|
|
j["nested"] = nested;
|
|
|
|
CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483674 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
|
|
}
|
|
}
|
|
|
|
SECTION("string length must be at least 1")
|
|
{
|
|
// from https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=11175
|
|
std::vector<std::uint8_t> const v =
|
|
{
|
|
0x20, 0x20, 0x20, 0x20,
|
|
0x02,
|
|
0x00,
|
|
0x00, 0x00, 0x00, 0x80
|
|
};
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(v), "[json.exception.parse_error.112] parse error at byte 10: syntax error while parsing BSON string: string length must be at least 1, is -2147483648", json::parse_error&);
|
|
}
|
|
|
|
SECTION("objects")
|
|
{
|
|
SECTION("empty object")
|
|
{
|
|
json const j = json::object();
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x05, 0x00, 0x00, 0x00, // size (little endian)
|
|
// no entries
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with bool")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", true }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x0D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x01, // value = true
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with bool")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", false }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x0D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x00, // value = false
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with bool from a non-0/1 byte (lenient parsing)")
|
|
{
|
|
// documented lenient behavior (see gh-5333): any non-zero byte
|
|
// is accepted as `true`, not just 0x01
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x0D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x02, // value = 0x02 (neither 0x00 nor 0x01)
|
|
0x00 // end marker
|
|
};
|
|
|
|
const json expected = { { "entry", true } };
|
|
CHECK(json::from_bson(input) == expected);
|
|
}
|
|
|
|
SECTION("non-empty object with double")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", 4.2 }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x14, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x01, /// entry: double
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0xcd, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x10, 0x40,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with string")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", "bsonstr" }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x18, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x02, /// entry: string (UTF-8)
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x08, 0x00, 0x00, 0x00, 'b', 's', 'o', 'n', 's', 't', 'r', '\x00',
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with null member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", nullptr }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x0C, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x0A, /// entry: null
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with integer (32-bit) member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::int32_t{0x12345678} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x10, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x78, 0x56, 0x34, 0x12,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with integer (64-bit) member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::int64_t{0x1234567804030201} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x14, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x12, /// entry: int64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x01, 0x02, 0x03, 0x04, 0x78, 0x56, 0x34, 0x12,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with negative integer (32-bit) member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::int32_t{-1} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x10, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0xFF, 0xFF, 0xFF, 0xFF,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with negative integer (64-bit) member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::int64_t{-1} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x10, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0xFF, 0xFF, 0xFF, 0xFF,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with unsigned integer (64-bit) member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::uint64_t{0x1234567804030201} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x14, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x12, /// entry: int64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x01, 0x02, 0x03, 0x04, 0x78, 0x56, 0x34, 0x12,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with small unsigned integer member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", std::uint64_t{0x42} }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x10, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x42, 0x00, 0x00, 0x00,
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with object member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", json::object() }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x11, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x03, /// entry: embedded document
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x05, 0x00, 0x00, 0x00, // size (little endian)
|
|
// no entries
|
|
0x00, // end marker (embedded document)
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with array member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", json::array() }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x11, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x04, /// entry: embedded document
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x05, 0x00, 0x00, 0x00, // size (little endian)
|
|
// no entries
|
|
0x00, // end marker (embedded document)
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with non-empty array member")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", json::array({1, 2, 3, 4, 5, 6, 7, 8}) }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x49, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x04, /// entry: embedded document
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x3D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, '0', 0x00, 0x01, 0x00, 0x00, 0x00,
|
|
0x10, '1', 0x00, 0x02, 0x00, 0x00, 0x00,
|
|
0x10, '2', 0x00, 0x03, 0x00, 0x00, 0x00,
|
|
0x10, '3', 0x00, 0x04, 0x00, 0x00, 0x00,
|
|
0x10, '4', 0x00, 0x05, 0x00, 0x00, 0x00,
|
|
0x10, '5', 0x00, 0x06, 0x00, 0x00, 0x00,
|
|
0x10, '6', 0x00, 0x07, 0x00, 0x00, 0x00,
|
|
0x10, '7', 0x00, 0x08, 0x00, 0x00, 0x00,
|
|
0x00, // end marker (embedded document)
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("array elements with non-conforming keys (lenient parsing)")
|
|
{
|
|
// documented lenient behavior (see gh-5333): BSON array element
|
|
// keys are not checked against the required decimal sequence
|
|
// "0", "1", "2", ... - elements are taken in encoded order
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x26, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x04, 'e', 'n', 't', 'r', 'y', '\x00', // entry: embedded array
|
|
|
|
0x1A, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, '5', 0x00, 0x0A, 0x00, 0x00, 0x00, // key "5" (bogus) -> 10
|
|
0x10, 'x', 0x00, 0x14, 0x00, 0x00, 0x00, // key "x" (non-numeric) -> 20
|
|
0x10, '1', 0x00, 0x1E, 0x00, 0x00, 0x00, // key "1" (out of order) -> 30
|
|
0x00, // end marker (embedded array)
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const json expected = { { "entry", json::array({10, 20, 30}) } };
|
|
CHECK(json::from_bson(input) == expected);
|
|
}
|
|
|
|
SECTION("non-empty object with binary member")
|
|
{
|
|
const size_t N = 10;
|
|
const auto s = std::vector<std::uint8_t>(N, 'x');
|
|
json const j =
|
|
{
|
|
{ "entry", json::binary(s, 0) }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x1B, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, // entry: binary
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x0A, 0x00, 0x00, 0x00, // size of binary (little endian)
|
|
0x00, // Generic binary subtype
|
|
0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78,
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("non-empty object with binary member without subtype")
|
|
{
|
|
const size_t N = 10;
|
|
const auto s = std::vector<std::uint8_t>(N, 'x');
|
|
json const j =
|
|
{
|
|
{ "entry", json::binary(s) }
|
|
};
|
|
|
|
CHECK(!j.at("entry").get_binary().has_subtype());
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x1B, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, // entry: binary
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x0A, 0x00, 0x00, 0x00, // size of binary (little endian)
|
|
0x00, // Generic binary subtype
|
|
0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78, 0x78,
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip adds the generic binary subtype
|
|
const auto roundtrip = json::from_bson(result);
|
|
CHECK(roundtrip != j);
|
|
CHECK(roundtrip.at("entry").get_binary().has_subtype());
|
|
CHECK(roundtrip.at("entry").get_binary().subtype() == 0);
|
|
CHECK(json::from_bson(result, true, false) == roundtrip);
|
|
}
|
|
|
|
SECTION("non-empty object with binary member with subtype")
|
|
{
|
|
// an MD5 hash
|
|
const std::vector<std::uint8_t> md5hash = {0xd7, 0x7e, 0x27, 0x54, 0xbe, 0x12, 0x37, 0xfe, 0xd6, 0x0c, 0x33, 0x98, 0x30, 0x3b, 0x8d, 0xc4};
|
|
json const j =
|
|
{
|
|
{ "entry", json::binary(md5hash, 5) }
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
0x21, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, // entry: binary
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x10, 0x00, 0x00, 0x00, // size of binary (little endian)
|
|
0x05, // MD5 binary subtype
|
|
0xd7, 0x7e, 0x27, 0x54, 0xbe, 0x12, 0x37, 0xfe, 0xd6, 0x0c, 0x33, 0x98, 0x30, 0x3b, 0x8d, 0xc4,
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
|
|
SECTION("binary member with subtype 0x02 (old binary) keeps its inner length prefix (lenient parsing)")
|
|
{
|
|
// documented lenient behavior (see gh-5333): the payload for
|
|
// binary subtype 0x02 ("old binary") is returned as-is,
|
|
// including its own inner 4-byte length prefix; it is not
|
|
// stripped or reinterpreted
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x17, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
|
|
|
|
0x06, 0x00, 0x00, 0x00, // size of binary (little endian)
|
|
0x02, // "old binary" subtype
|
|
0x02, 0x00, 0x00, 0x00, // inner length prefix (part of the old-binary payload)
|
|
0x68, 0x69, // payload ('h', 'i')
|
|
|
|
0x00 // end marker
|
|
};
|
|
|
|
// the inner length prefix is part of the (unmodified) payload
|
|
const std::vector<std::uint8_t> expected_payload = {0x02, 0x00, 0x00, 0x00, 0x68, 0x69};
|
|
const json expected = { { "entry", json::binary(expected_payload, 0x02) } };
|
|
CHECK(json::from_bson(input) == expected);
|
|
}
|
|
|
|
SECTION("Some more complex document")
|
|
{
|
|
json const j =
|
|
{
|
|
{"double", 42.5},
|
|
{"entry", 4.2},
|
|
{"number", 12345},
|
|
{"object", {{ "string", "value" }}}
|
|
};
|
|
|
|
std::vector<std::uint8_t> const expected =
|
|
{
|
|
/*size */ 0x4f, 0x00, 0x00, 0x00,
|
|
/*entry*/ 0x01, 'd', 'o', 'u', 'b', 'l', 'e', 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x45, 0x40,
|
|
/*entry*/ 0x01, 'e', 'n', 't', 'r', 'y', 0x00, 0xcd, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x10, 0x40,
|
|
/*entry*/ 0x10, 'n', 'u', 'm', 'b', 'e', 'r', 0x00, 0x39, 0x30, 0x00, 0x00,
|
|
/*entry*/ 0x03, 'o', 'b', 'j', 'e', 'c', 't', 0x00,
|
|
/*entry: obj-size */ 0x17, 0x00, 0x00, 0x00,
|
|
/*entry: obj-entry*/0x02, 's', 't', 'r', 'i', 'n', 'g', 0x00, 0x06, 0x00, 0x00, 0x00, 'v', 'a', 'l', 'u', 'e', 0,
|
|
/*entry: obj-term.*/0x00,
|
|
/*obj-term*/ 0x00
|
|
};
|
|
|
|
const auto result = json::to_bson(j);
|
|
CHECK(result == expected);
|
|
|
|
// roundtrip
|
|
CHECK(json::from_bson(result) == j);
|
|
CHECK(json::from_bson(result, true, false) == j);
|
|
}
|
|
}
|
|
|
|
SECTION("Examples from https://bsonspec.org/faq.html")
|
|
{
|
|
SECTION("Example 1")
|
|
{
|
|
std::vector<std::uint8_t> input = {0x16, 0x00, 0x00, 0x00, 0x02, 'h', 'e', 'l', 'l', 'o', 0x00, 0x06, 0x00, 0x00, 0x00, 'w', 'o', 'r', 'l', 'd', 0x00, 0x00};
|
|
const json parsed = json::from_bson(input);
|
|
const json expected = {{"hello", "world"}};
|
|
CHECK(parsed == expected);
|
|
const auto dumped = json::to_bson(parsed);
|
|
CHECK(dumped == input);
|
|
CHECK(json::from_bson(dumped) == expected);
|
|
}
|
|
|
|
SECTION("Example 2")
|
|
{
|
|
std::vector<std::uint8_t> input = {0x31, 0x00, 0x00, 0x00, 0x04, 'B', 'S', 'O', 'N', 0x00, 0x26, 0x00, 0x00, 0x00, 0x02, 0x30, 0x00, 0x08, 0x00, 0x00, 0x00, 'a', 'w', 'e', 's', 'o', 'm', 'e', 0x00, 0x01, 0x31, 0x00, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x14, 0x40, 0x10, 0x32, 0x00, 0xc2, 0x07, 0x00, 0x00, 0x00, 0x00};
|
|
const json parsed = json::from_bson(input);
|
|
const json expected = {{"BSON", {"awesome", 5.05, 1986}}};
|
|
CHECK(parsed == expected);
|
|
const auto dumped = json::to_bson(parsed);
|
|
CHECK(dumped == input);
|
|
CHECK(json::from_bson(dumped) == expected);
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST_CASE("BSON input/output_adapters")
|
|
{
|
|
const json json_representation =
|
|
{
|
|
{"double", 42.5},
|
|
{"entry", 4.2},
|
|
{"number", 12345},
|
|
{"object", {{ "string", "value" }}}
|
|
};
|
|
|
|
const std::vector<std::uint8_t> bson_representation =
|
|
{
|
|
/*size */ 0x4f, 0x00, 0x00, 0x00,
|
|
/*entry*/ 0x01, 'd', 'o', 'u', 'b', 'l', 'e', 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x45, 0x40,
|
|
/*entry*/ 0x01, 'e', 'n', 't', 'r', 'y', 0x00, 0xcd, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x10, 0x40,
|
|
/*entry*/ 0x10, 'n', 'u', 'm', 'b', 'e', 'r', 0x00, 0x39, 0x30, 0x00, 0x00,
|
|
/*entry*/ 0x03, 'o', 'b', 'j', 'e', 'c', 't', 0x00,
|
|
/*entry: obj-size */ 0x17, 0x00, 0x00, 0x00,
|
|
/*entry: obj-entry*/0x02, 's', 't', 'r', 'i', 'n', 'g', 0x00, 0x06, 0x00, 0x00, 0x00, 'v', 'a', 'l', 'u', 'e', 0,
|
|
/*entry: obj-term.*/0x00,
|
|
/*obj-term*/ 0x00
|
|
};
|
|
|
|
json j2;
|
|
CHECK_NOTHROW(j2 = json::from_bson(bson_representation));
|
|
|
|
// compare parsed JSON values
|
|
CHECK(json_representation == j2);
|
|
|
|
SECTION("roundtrips")
|
|
{
|
|
SECTION("std::ostringstream")
|
|
{
|
|
std::basic_ostringstream<char> ss;
|
|
json::to_bson(json_representation, ss);
|
|
const json j3 = json::from_bson(ss.str());
|
|
CHECK(json_representation == j3);
|
|
}
|
|
|
|
SECTION("std::string")
|
|
{
|
|
std::string s;
|
|
json::to_bson(json_representation, s);
|
|
const json j3 = json::from_bson(s);
|
|
CHECK(json_representation == j3);
|
|
}
|
|
|
|
SECTION("std::vector")
|
|
{
|
|
std::vector<std::uint8_t> v;
|
|
json::to_bson(json_representation, v);
|
|
const json j3 = json::from_bson(v);
|
|
CHECK(json_representation == j3);
|
|
}
|
|
}
|
|
}
|
|
|
|
namespace
|
|
{
|
|
class SaxCountdown
|
|
{
|
|
public:
|
|
explicit SaxCountdown(const int count) : events_left(count)
|
|
{}
|
|
|
|
bool null()
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool boolean(bool /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool number_integer(json::number_integer_t /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool number_unsigned(json::number_unsigned_t /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool string(std::string& /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool binary(std::vector<std::uint8_t>& /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool start_object(std::size_t /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool key(std::string& /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool end_object()
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool start_array(std::size_t /*unused*/)
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool end_array()
|
|
{
|
|
return events_left-- > 0;
|
|
}
|
|
|
|
bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
private:
|
|
int events_left = 0;
|
|
};
|
|
} // namespace
|
|
|
|
TEST_CASE("Incomplete BSON Input")
|
|
{
|
|
SECTION("Incomplete BSON Input 1")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x0D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean
|
|
'e', 'n', 't' // unexpected EOF
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 9: syntax error while parsing BSON cstring: unexpected end of input", json::parse_error&);
|
|
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Incomplete BSON Input 2")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x0D, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean, unexpected EOF
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 6: syntax error while parsing BSON cstring: unexpected end of input", json::parse_error&);
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Incomplete BSON Input 3")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x41, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x04, /// entry: embedded document
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0x35, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x10, 0x00, 0x01, 0x00, 0x00, 0x00,
|
|
0x10, 0x00, 0x02, 0x00, 0x00, 0x00
|
|
// missing input data...
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 28: syntax error while parsing BSON element list: unexpected end of input", json::parse_error&);
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(1);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Incomplete BSON Input 4")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x0D, 0x00, // size (incomplete), unexpected EOF
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 3: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Incomplete BSON Input 5")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x09, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x08, // entry: boolean
|
|
'b', '\x00' // key, unexpected EOF before the value
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 8: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Incomplete BSON Input 6")
|
|
{
|
|
std::vector<std::uint8_t> const incomplete_bson =
|
|
{
|
|
0x0F, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, // entry: binary
|
|
'b', '\x00', // key
|
|
0x00, 0x00, 0x00, 0x00 // length, unexpected EOF before the subtype
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(incomplete_bson), "[json.exception.parse_error.110] parse error at byte 12: syntax error while parsing BSON number: unexpected end of input", json::parse_error&);
|
|
CHECK(json::from_bson(incomplete_bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(incomplete_bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("Improve coverage")
|
|
{
|
|
SECTION("key")
|
|
{
|
|
json const j = {{"key", "value"}};
|
|
auto bson_vec = json::to_bson(j);
|
|
SaxCountdown scp(2);
|
|
CHECK(!json::sax_parse(bson_vec, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("array")
|
|
{
|
|
json const j =
|
|
{
|
|
{ "entry", json::array() }
|
|
};
|
|
auto bson_vec = json::to_bson(j);
|
|
SaxCountdown scp(2);
|
|
CHECK(!json::sax_parse(bson_vec, &scp, json::input_format_t::bson));
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST_CASE("Negative size of binary value")
|
|
{
|
|
// invalid BSON: the size of the binary value is -1
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x21, 0x00, 0x00, 0x00, // size (little endian)
|
|
0x05, // entry: binary
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
|
|
0xFF, 0xFF, 0xFF, 0xFF, // size of binary (little endian)
|
|
0x05, // MD5 binary subtype
|
|
0xd7, 0x7e, 0x27, 0x54, 0xbe, 0x12, 0x37, 0xfe, 0xd6, 0x0c, 0x33, 0x98, 0x30, 0x3b, 0x8d, 0xc4,
|
|
|
|
0x00 // end marker
|
|
};
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 15: syntax error while parsing BSON binary: byte array length cannot be negative, is -1", json::parse_error);
|
|
}
|
|
|
|
TEST_CASE("Unsupported BSON input")
|
|
{
|
|
std::vector<std::uint8_t> const bson =
|
|
{
|
|
0x0C, 0x00, 0x00, 0x00, // size (little endian)
|
|
0xFF, // entry type: Min key (not supported yet)
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
0x00 // end marker
|
|
};
|
|
|
|
json _;
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(bson), "[json.exception.parse_error.114] parse error at byte 5: Unsupported BSON record type 0xFF", json::parse_error&);
|
|
CHECK(json::from_bson(bson, true, false).is_discarded());
|
|
|
|
SaxCountdown scp(0);
|
|
CHECK(!json::sax_parse(bson, &scp, json::input_format_t::bson));
|
|
}
|
|
|
|
TEST_CASE("BSON document size mismatch")
|
|
{
|
|
json _;
|
|
|
|
SECTION("top-level document declaring more bytes than it contains")
|
|
{
|
|
// empty object, but the length prefix claims 6 bytes instead of 5
|
|
std::vector<std::uint8_t> const input = {0x06, 0x00, 0x00, 0x00, 0x00};
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size 6 does not match the number of bytes read (5)", json::parse_error&);
|
|
CHECK(json::from_bson(input, true, false).is_discarded());
|
|
}
|
|
|
|
SECTION("top-level document with a negative size")
|
|
{
|
|
std::vector<std::uint8_t> const input = {0xFF, 0xFF, 0xFF, 0xFF, 0x00};
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 5: syntax error while parsing BSON document: document size -1 does not match the number of bytes read (5)", json::parse_error&);
|
|
CHECK(json::from_bson(input, true, false).is_discarded());
|
|
}
|
|
|
|
SECTION("embedded document whose size disagrees with its terminator")
|
|
{
|
|
// the embedded document "d" declares 0x7FFFFFFF bytes but its 0x00
|
|
// terminator falls right after {"a":null}; the length prefix would
|
|
// otherwise let the following "h" element be read as a member of the
|
|
// enclosing document instead of "d"
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x00, 0x00, 0x00, 0x00, // outer size
|
|
0x03, 'd', 0x00, // entry: embedded document "d"
|
|
0xFF, 0xFF, 0xFF, 0x7F, // embedded size 0x7FFFFFFF
|
|
0x0A, 'a', 0x00, // entry: null "a"
|
|
0x00, // embedded end marker
|
|
0x08, 'h', 0x00, 0x01, // entry: bool "h" = true
|
|
0x00 // outer end marker
|
|
};
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 15: syntax error while parsing BSON document: document size 2147483647 does not match the number of bytes read (8)", json::parse_error&);
|
|
CHECK(json::from_bson(input, true, false).is_discarded());
|
|
}
|
|
|
|
SECTION("embedded array whose size disagrees with its terminator")
|
|
{
|
|
// array [42] is 12 bytes, but the length prefix claims 13
|
|
std::vector<std::uint8_t> const input =
|
|
{
|
|
0x00, 0x00, 0x00, 0x00, // outer size
|
|
0x04, 'a', 0x00, // entry: array "a"
|
|
0x0D, 0x00, 0x00, 0x00, // array size 13 (real is 12)
|
|
0x10, '0', 0x00, 0x2A, 0x00, 0x00, 0x00, // entry: int32 "0" = 42
|
|
0x00, // array end marker
|
|
0x00 // outer end marker
|
|
};
|
|
CHECK_THROWS_WITH_AS(_ = json::from_bson(input), "[json.exception.parse_error.112] parse error at byte 19: syntax error while parsing BSON document: document size 13 does not match the number of bytes read (12)", json::parse_error&);
|
|
CHECK(json::from_bson(input, true, false).is_discarded());
|
|
}
|
|
}
|
|
|
|
TEST_CASE("BSON nesting does not consume the call stack")
|
|
{
|
|
// An embedded document or array used to be read by calling back into the
|
|
// document reader, so the native call stack grew with the nesting depth of
|
|
// the input (#5104). The open documents are kept on a heap stack now.
|
|
//
|
|
// Deeply nested values must not be compared, copied or dumped here: those
|
|
// operations are still recursive and would reintroduce the crash.
|
|
|
|
// A document nested deeply enough to have crashed. The bytes are built
|
|
// here rather than with to_bson(), because the writer still recurses once
|
|
// per level and would overflow the stack before the reader is ever
|
|
// reached. Every level is
|
|
// <int32 size> 0x03 'a' 0x00 <inner document> 0x00
|
|
// so a level is eight bytes larger than the one it holds, and the sizes
|
|
// can be filled in from the outside in.
|
|
const std::size_t depth = 30000;
|
|
std::vector<uint8_t> input;
|
|
input.reserve(5 + (8 * depth));
|
|
for (std::size_t i = 0; i < depth; ++i)
|
|
{
|
|
const auto size = static_cast<std::uint32_t>(5 + (8 * (depth - i)));
|
|
input.push_back(static_cast<uint8_t>(size & 0xFF));
|
|
input.push_back(static_cast<uint8_t>((size >> 8) & 0xFF));
|
|
input.push_back(static_cast<uint8_t>((size >> 16) & 0xFF));
|
|
input.push_back(static_cast<uint8_t>((size >> 24) & 0xFF));
|
|
input.push_back(0x03); // embedded document
|
|
input.push_back('a');
|
|
input.push_back(0x00);
|
|
}
|
|
// the innermost document is empty, then one terminator closes each level
|
|
input.insert(input.end(), {0x05, 0x00, 0x00, 0x00, 0x00});
|
|
input.insert(input.end(), depth, 0x00);
|
|
|
|
SECTION("a well-formed deep document is read through the SAX interface")
|
|
{
|
|
SaxCountdown accept_all(1000000);
|
|
CHECK(json::sax_parse(input, &accept_all, json::input_format_t::bson));
|
|
}
|
|
|
|
SECTION("a well-formed deep document is read into a value")
|
|
{
|
|
json j = json::from_bson(input);
|
|
|
|
// walked rather than compared: comparing, copying or dumping a value
|
|
// this deep is still recursive
|
|
std::size_t measured = 0;
|
|
const json* q = &j;
|
|
while (q->is_object() && !q->empty())
|
|
{
|
|
q = &q->begin().value();
|
|
++measured;
|
|
}
|
|
CHECK(measured == depth);
|
|
}
|
|
|
|
SECTION("embedded documents and arrays are still read the same way")
|
|
{
|
|
const json values = {{"a", {{"b", {{"c", 1}}}}}};
|
|
CHECK(json::from_bson(json::to_bson(values)) == values);
|
|
|
|
const json array = {{"a", {1, 2, 3}}};
|
|
CHECK(json::from_bson(json::to_bson(array)) == array);
|
|
|
|
const json mixed = {{"a", {json{{"x", 1}}, json{{"y", 2}}}}};
|
|
CHECK(json::from_bson(json::to_bson(mixed)) == mixed);
|
|
|
|
CHECK(json::from_bson(json::to_bson(json::object())) == json::object());
|
|
}
|
|
|
|
SECTION("a size that does not match is still reported per document")
|
|
{
|
|
// the embedded document claims one byte too many
|
|
std::vector<uint8_t> const bad =
|
|
{
|
|
0x15, 0x00, 0x00, 0x00, 0x03, 'a', 0x00,
|
|
0x0D, 0x00, 0x00, 0x00, 0x08, 'b', 0x00, 0x01, 0x00,
|
|
0x00
|
|
};
|
|
json _;
|
|
CHECK_THROWS_AS(_ = json::from_bson(bad), json::parse_error&);
|
|
CHECK(json::from_bson(bad, true, false).is_discarded());
|
|
}
|
|
}
|
|
|
|
TEST_CASE("BSON numerical data")
|
|
{
|
|
SECTION("number")
|
|
{
|
|
SECTION("signed")
|
|
{
|
|
SECTION("std::int64_t: INT64_MIN .. INT32_MIN-1")
|
|
{
|
|
std::vector<int64_t> const numbers
|
|
{
|
|
(std::numeric_limits<int64_t>::min)(),
|
|
-1000000000000000000LL,
|
|
-100000000000000000LL,
|
|
-10000000000000000LL,
|
|
-1000000000000000LL,
|
|
-100000000000000LL,
|
|
-10000000000000LL,
|
|
-1000000000000LL,
|
|
-100000000000LL,
|
|
-10000000000LL,
|
|
static_cast<std::int64_t>((std::numeric_limits<std::int32_t>::min)()) - 1,
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
CHECK(j.at("entry").is_number_integer());
|
|
|
|
std::uint64_t const iu = *reinterpret_cast<const std::uint64_t*>(&i);
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x14u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x12u, /// entry: int64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 4u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 5u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 6u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 7u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j_roundtrip.at("entry").is_number_integer());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
|
|
}
|
|
}
|
|
|
|
SECTION("signed std::int32_t: INT32_MIN .. INT32_MAX")
|
|
{
|
|
std::vector<int32_t> const numbers
|
|
{
|
|
(std::numeric_limits<int32_t>::min)(),
|
|
-2147483647L,
|
|
-1000000000L,
|
|
-100000000L,
|
|
-10000000L,
|
|
-1000000L,
|
|
-100000L,
|
|
-10000L,
|
|
-1000L,
|
|
-100L,
|
|
-10L,
|
|
-1L,
|
|
0L,
|
|
1L,
|
|
10L,
|
|
100L,
|
|
1000L,
|
|
10000L,
|
|
100000L,
|
|
1000000L,
|
|
10000000L,
|
|
100000000L,
|
|
1000000000L,
|
|
2147483646L,
|
|
(std::numeric_limits<int32_t>::max)()
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
CHECK(j.at("entry").is_number_integer());
|
|
|
|
std::uint32_t const iu = *reinterpret_cast<const std::uint32_t*>(&i);
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x10u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x10u, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j_roundtrip.at("entry").is_number_integer());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
|
|
}
|
|
}
|
|
|
|
SECTION("signed std::int64_t: INT32_MAX+1 .. INT64_MAX")
|
|
{
|
|
std::vector<int64_t> const numbers
|
|
{
|
|
(std::numeric_limits<int64_t>::max)(),
|
|
1000000000000000000LL,
|
|
100000000000000000LL,
|
|
10000000000000000LL,
|
|
1000000000000000LL,
|
|
100000000000000LL,
|
|
10000000000000LL,
|
|
1000000000000LL,
|
|
100000000000LL,
|
|
10000000000LL,
|
|
static_cast<std::int64_t>((std::numeric_limits<int32_t>::max)()) + 1,
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
CHECK(j.at("entry").is_number_integer());
|
|
|
|
std::uint64_t const iu = *reinterpret_cast<const std::uint64_t*>(&i);
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x14u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x12u, /// entry: int64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 4u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 5u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 6u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 7u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j_roundtrip.at("entry").is_number_integer());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
|
|
}
|
|
}
|
|
}
|
|
|
|
SECTION("unsigned")
|
|
{
|
|
SECTION("unsigned std::uint64_t: 0 .. INT32_MAX")
|
|
{
|
|
std::vector<std::uint64_t> const numbers
|
|
{
|
|
0ULL,
|
|
1ULL,
|
|
10ULL,
|
|
100ULL,
|
|
1000ULL,
|
|
10000ULL,
|
|
100000ULL,
|
|
1000000ULL,
|
|
10000000ULL,
|
|
100000000ULL,
|
|
1000000000ULL,
|
|
2147483646ULL,
|
|
static_cast<std::uint64_t>((std::numeric_limits<int32_t>::max)())
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
|
|
auto iu = i;
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x10u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x10u, /// entry: int32
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j.at("entry").is_number_unsigned());
|
|
CHECK(j_roundtrip.at("entry").is_number_integer());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
|
|
}
|
|
}
|
|
|
|
SECTION("unsigned std::uint64_t: INT32_MAX+1 .. INT64_MAX")
|
|
{
|
|
std::vector<std::uint64_t> const numbers
|
|
{
|
|
static_cast<std::uint64_t>((std::numeric_limits<std::int32_t>::max)()) + 1,
|
|
4000000000ULL,
|
|
static_cast<std::uint64_t>((std::numeric_limits<std::uint32_t>::max)()),
|
|
10000000000ULL,
|
|
100000000000ULL,
|
|
1000000000000ULL,
|
|
10000000000000ULL,
|
|
100000000000000ULL,
|
|
1000000000000000ULL,
|
|
10000000000000000ULL,
|
|
100000000000000000ULL,
|
|
1000000000000000000ULL,
|
|
static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()),
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
|
|
auto iu = i;
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x14u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x12u, /// entry: int64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 4u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 5u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 6u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 7u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j.at("entry").is_number_unsigned());
|
|
CHECK(j_roundtrip.at("entry").is_number_integer());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
}
|
|
}
|
|
|
|
SECTION("unsigned std::uint64_t: INT64_MAX+1 .. UINT64_MAX")
|
|
{
|
|
std::vector<std::uint64_t> const numbers
|
|
{
|
|
static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()) + 1ULL,
|
|
0xffffffffffffffff,
|
|
};
|
|
|
|
for (const auto i : numbers)
|
|
{
|
|
|
|
CAPTURE(i)
|
|
|
|
json const j =
|
|
{
|
|
{ "entry", i }
|
|
};
|
|
|
|
auto iu = i;
|
|
std::vector<std::uint8_t> const expected_bson =
|
|
{
|
|
0x14u, 0x00u, 0x00u, 0x00u, // size (little endian)
|
|
0x11u, /// entry: uint64
|
|
'e', 'n', 't', 'r', 'y', '\x00',
|
|
static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 2u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 3u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 4u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 5u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 6u)) & 0xffu),
|
|
static_cast<std::uint8_t>((iu >> (8u * 7u)) & 0xffu),
|
|
0x00u // end marker
|
|
};
|
|
|
|
const auto bson = json::to_bson(j);
|
|
CHECK(bson == expected_bson);
|
|
|
|
auto j_roundtrip = json::from_bson(bson);
|
|
|
|
CHECK(j.at("entry").is_number_unsigned());
|
|
CHECK(j_roundtrip.at("entry").is_number_unsigned());
|
|
CHECK(j_roundtrip == j);
|
|
CHECK(json::from_bson(bson, true, false) == j);
|
|
}
|
|
}
|
|
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST_CASE("Parse BSON directly from a file using iterator and sentinel")
|
|
{
|
|
std::string const filename = TEST_DATA_DIRECTORY "/json.org/1.json";
|
|
|
|
std::ifstream f_json(filename);
|
|
const json expected = json::parse(f_json);
|
|
|
|
std::ifstream file(filename + ".bson", std::ios::binary);
|
|
const std::istreambuf_iterator<char> first(file);
|
|
const json parsed = json::from_bson(first, utils::istreambuf_sentinel{});
|
|
CHECK(parsed == expected);
|
|
}
|
|
|
|
TEST_CASE("BSON roundtrips" * doctest::skip())
|
|
{
|
|
SECTION("reference files")
|
|
{
|
|
for (const std::string filename :
|
|
{
|
|
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"
|
|
})
|
|
{
|
|
CAPTURE(filename)
|
|
|
|
{
|
|
INFO_WITH_TEMP(filename + ": std::vector<std::uint8_t>");
|
|
// parse JSON file
|
|
std::ifstream f_json(filename);
|
|
const json j1 = json::parse(f_json);
|
|
|
|
// parse BSON file
|
|
auto packed = utils::read_binary_file(filename + ".bson");
|
|
json j2;
|
|
CHECK_NOTHROW(j2 = json::from_bson(packed));
|
|
|
|
// compare parsed JSON values
|
|
CHECK(j1 == j2);
|
|
}
|
|
|
|
{
|
|
INFO_WITH_TEMP(filename + ": std::ifstream");
|
|
// parse JSON file
|
|
std::ifstream f_json(filename);
|
|
const json j1 = json::parse(f_json);
|
|
|
|
// parse BSON file
|
|
std::ifstream f_bson(filename + ".bson", std::ios::binary);
|
|
json j2;
|
|
CHECK_NOTHROW(j2 = json::from_bson(f_bson));
|
|
|
|
// compare parsed JSON values
|
|
CHECK(j1 == j2);
|
|
}
|
|
|
|
{
|
|
INFO_WITH_TEMP(filename + ": uint8_t* and size");
|
|
// parse JSON file
|
|
std::ifstream f_json(filename);
|
|
const json j1 = json::parse(f_json);
|
|
|
|
// parse BSON file
|
|
auto packed = utils::read_binary_file(filename + ".bson");
|
|
json j2;
|
|
CHECK_NOTHROW(j2 = json::from_bson({packed.data(), packed.size()}));
|
|
|
|
// compare parsed JSON values
|
|
CHECK(j1 == j2);
|
|
}
|
|
|
|
{
|
|
INFO_WITH_TEMP(filename + ": output to output adapters");
|
|
// parse JSON file
|
|
std::ifstream f_json(filename);
|
|
json const j1 = json::parse(f_json);
|
|
|
|
// parse BSON file
|
|
auto packed = utils::read_binary_file(filename + ".bson");
|
|
|
|
{
|
|
INFO_WITH_TEMP(filename + ": output adapters: std::vector<std::uint8_t>");
|
|
std::vector<std::uint8_t> vec;
|
|
json::to_bson(j1, vec);
|
|
|
|
if (vec != packed)
|
|
{
|
|
// the exact serializations may differ due to the order of
|
|
// object keys; in these cases, just compare whether both
|
|
// serializations create the same JSON value
|
|
CHECK(json::from_bson(vec) == json::from_bson(packed));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|