MessagePack reader: read runs of scalar array elements in one loop (#5980)
* MessagePack reader: read runs of scalar array elements in one loop As for CBOR: when an array opens and the input is contiguous, read the integers, floats, booleans, and nils that follow in a tight loop instead of going through parse_msgpack_internal and parse_msgpack_value for every element. The loop stops at any other kind of value and when fewer than 9 bytes are left; those values are read by the general path as before. Non-contiguous inputs are not affected. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: enter the scalar run only when a scalar follows As for CBOR: enter_msgpack_array tests the first byte and the remaining length inline and calls the out-of-line run only for a scalar, so arrays of maps or strings no longer pay for a call that reads nothing; the run's loop condition moves to the end (do-while). Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: mark the initial accepted in the scalar run as a false-positive dead store ci_infer reports DEAD_STORE for 'bool accepted = true;' in the MessagePack scalar run, as in the CBOR one, because every case assigns accepted before it is read. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack tests: assign the parsed value instead of casting it to void GCC (ci_test_gcc) reports -Werror=unused-result for static_cast<void>(json::from_msgpack(...)): a cast to void does not silence warn_unused_result on GCC. Assign to a json, as the other tests in the file do. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: drop the scalar pre-check before the run enter_msgpack_array now calls the run directly, and parse_msgpack_scalar_run tests the remaining count and length at the top of a while loop instead of relying on msgpack_scalar_follows(); its own switch already leaves on any value that is not a scalar. Instructions per repetition, new/old: SAX canada 0.946 (clang) and 0.973 (GCC 13), DOM read canada 0.991 / 0.992; no row more than 0.3 % higher. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: say why the initial accepted in the scalar run stays As for CBOR: Infer's DEAD_STORE report is right, not a false positive. The initializer is kept for clang-tidy's cppcoreguidelines-init-variables. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: give the scalar run the bulk tag instead of a wrapper As for CBOR: parse_msgpack_scalar_run takes the bulk-scan tag itself and is the function kept out of line, so parse_msgpack_array_start goes. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: start the scalar run's accepted at false As for CBOR: Infer ignores dead stores of 0, so the suppression goes. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * MessagePack reader: let the scalar run find its array itself As for CBOR: parse_msgpack_scalar_run reads container_stack.back() in its bulk version, so the caller no longer evaluates it for input that is not contiguous. Signed-off-by: Niels Lohmann <mail@nlohmann.me> --------- Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann authored and GitHub committed
1 parent
aecbef3949
commit
edf8d17601
3 files changed
+367
-6
No files matched your search
@@ -27,12 +27,15 @@ using nlohmann::json;
|
||||
#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 "sax_event_loggers.hpp"
|
||||
using utils::SaxCountdown;
|
||||
using utils::SaxEventLogger;
|
||||
|
||||
|
||||
TEST_CASE("MessagePack")
|
||||
@@ -2212,3 +2215,99 @@ TEST_CASE("MessagePack large strings and binaries (chunked reader)")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("MessagePack arrays of scalars from contiguous and non-contiguous input")
|
||||
{
|
||||
// contiguous input reads the integers, floats, booleans, and nils 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> msgpack =
|
||||
{
|
||||
0x83, // map(3)
|
||||
0xA1, 'a', // "a"
|
||||
0xDC, 0x00, 0x16, // array 16 (22)
|
||||
0x00, 0x7F, 0xCC, 0xFF, 0xCD, 0x01, 0x00, // 0, 127, 255, 256
|
||||
0xCE, 0x00, 0x01, 0x00, 0x00, // 65536
|
||||
0xCF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 18446744073709551615
|
||||
0xFF, 0xE0, 0xD0, 0x80, 0xD1, 0xFF, 0x00, // -1, -32, -128, -256
|
||||
0xD2, 0xFF, 0xFE, 0xFF, 0xFF, // -65537
|
||||
0xD3, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // -9223372036854775808
|
||||
0xC2, 0xC3, 0xC0, // false, true, nil
|
||||
0xCA, 0x3F, 0xC0, 0x00, 0x00, // 1.5 (float 32)
|
||||
0xCB, 0xBF, 0xB9, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9A, // -0.1
|
||||
0xA1, 'x', // "x" (ends the loop)
|
||||
0x01, // 1
|
||||
0xCB, 0x40, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 2.5
|
||||
0xD9, 0x01, 'y', // "y" (str 8)
|
||||
0xC0, // nil
|
||||
0xA1, 'b', // "b"
|
||||
0x93, // fixarray(3)
|
||||
0x92, 0xCB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
|
||||
0xCB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // -3.75]
|
||||
0x92, 0xCB, 0x3F, 0xF4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // [1.25,
|
||||
0xCB, 0xC0, 0x0E, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // -3.75]
|
||||
0x90, // []
|
||||
0xA1, 'c', // "c"
|
||||
0x94, 0x80, 0x01, 0xC4, 0x01, 0x05, 0x91, 0x03 // [{}, 1, bin 8, [3]]
|
||||
};
|
||||
|
||||
const json j = json::from_msgpack(msgpack);
|
||||
CHECK(j["a"].size() == 22);
|
||||
CHECK(j["a"][5] == 18446744073709551615u);
|
||||
CHECK(j["a"][7] == -32);
|
||||
CHECK(j["a"][11] == (std::numeric_limits<std::int64_t>::min)());
|
||||
CHECK(j["a"][15] == 1.5);
|
||||
CHECK(j["a"][16] == -0.1);
|
||||
CHECK(j["a"][17] == "x");
|
||||
CHECK(j["b"] == json::parse("[[1.25, -3.75], [1.25, -3.75], []]"));
|
||||
CHECK(j["c"][2].is_binary());
|
||||
|
||||
for (std::size_t length = 0; length <= msgpack.size(); ++length)
|
||||
{
|
||||
CAPTURE(length)
|
||||
const std::vector<std::uint8_t> contiguous(msgpack.begin(), msgpack.begin() + static_cast<std::ptrdiff_t>(length));
|
||||
const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
|
||||
|
||||
CHECK(json::from_msgpack(contiguous, true, false).dump() == json::from_msgpack(bytewise.begin(), bytewise.end(), true, false).dump());
|
||||
#if !defined(JSON_NOEXCEPTION)
|
||||
std::string contiguous_error;
|
||||
std::string bytewise_error;
|
||||
try
|
||||
{
|
||||
json _;
|
||||
_ = json::from_msgpack(contiguous);
|
||||
}
|
||||
catch (const json::parse_error& e)
|
||||
{
|
||||
contiguous_error = e.what();
|
||||
}
|
||||
try
|
||||
{
|
||||
json _;
|
||||
_ = json::from_msgpack(bytewise.begin(), bytewise.end());
|
||||
}
|
||||
catch (const json::parse_error& e)
|
||||
{
|
||||
bytewise_error = e.what();
|
||||
}
|
||||
CHECK(contiguous_error == bytewise_error);
|
||||
#endif
|
||||
|
||||
SaxEventLogger from_contiguous;
|
||||
SaxEventLogger from_bytewise;
|
||||
CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::msgpack)
|
||||
== json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack));
|
||||
CHECK(from_contiguous.events == from_bytewise.events);
|
||||
}
|
||||
|
||||
for (int events = 0; events <= 60; ++events)
|
||||
{
|
||||
CAPTURE(events)
|
||||
const std::list<std::uint8_t> bytewise(msgpack.begin(), msgpack.end());
|
||||
SaxCountdown from_contiguous(events);
|
||||
SaxCountdown from_bytewise(events);
|
||||
CHECK(json::sax_parse(msgpack, &from_contiguous, json::input_format_t::msgpack)
|
||||
== json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack));
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user