amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-08-22 09:03:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
b91675bca1657fd8f697aff24e035f4e49c31747
json/tests/src/unit-serialization.cpp
T
Niels Lohmann b91675bca1 Fill the indentation buffer once instead of once per flush 
@gregmarr's point on the fill-and-flush loop: flushing does not disturb what
the write buffer holds, so an indentation spanning several buffer-fulls only
has to be written into the buffer once and can then be handed to the adapter
as many times as needed. The loop re-filled it every time, doing work it
already knew was there.

put_indent() now fills the room left in the buffer, and if anything remains,
flushes, fills the buffer once, and re-flushes that same content. It also
returns early for a zero-width indentation, which is what the closing brace of
every outermost value asks for.

Measured over a dump(), counting memset calls and bytes inside put_indent:

    indent       before              after
         4       1 call /     4 B    1 call /     4 B
      2000       2 calls /  2000 B   2 calls /  2046 B
    100000      98 calls / 100000 B  2 calls /  2046 B

The wide case is now constant work rather than proportional to the indentation
width; ordinary widths are unchanged. Tests extended to cover several whole
buffer-fulls and an exact multiple of the buffer size.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-08-21 04:51:22 +02:00

527 lines
21 KiB
C++
Raw Blame History

// __ _____ _____ _____
// __| | __| | | | 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 <array>
#include <sstream>
#include <iomanip>
TEST_CASE("serialization")
{
SECTION("operator<<")
{
SECTION("no given width")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
ss << j;
CHECK(ss.str() == "[\"foo\",1,2,3,false,{\"one\":1}]");
}
SECTION("given width")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
ss << std::setw(4) << j;
CHECK(ss.str() ==
"[\n \"foo\",\n 1,\n 2,\n 3,\n false,\n {\n \"one\": 1\n }\n]");
}
SECTION("given fill")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
ss << std::setw(1) << std::setfill('\t') << j;
CHECK(ss.str() ==
"[\n\t\"foo\",\n\t1,\n\t2,\n\t3,\n\tfalse,\n\t{\n\t\t\"one\": 1\n\t}\n]");
}
}
SECTION("operator>>")
{
SECTION("no given width")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
j >> ss;
CHECK(ss.str() == "[\"foo\",1,2,3,false,{\"one\":1}]");
}
SECTION("given width")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
ss.width(4);
j >> ss;
CHECK(ss.str() ==
"[\n \"foo\",\n 1,\n 2,\n 3,\n false,\n {\n \"one\": 1\n }\n]");
}
SECTION("given fill")
{
std::stringstream ss;
const json j = {"foo", 1, 2, 3, false, {{"one", 1}}};
ss.width(1);
ss.fill('\t');
j >> ss;
CHECK(ss.str() ==
"[\n\t\"foo\",\n\t1,\n\t2,\n\t3,\n\tfalse,\n\t{\n\t\t\"one\": 1\n\t}\n]");
}
}
SECTION("dump")
{
SECTION("invalid character")
{
const json j = "ä\xA9ü";
CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
CHECK_THROWS_WITH_AS(j.dump(1, ' ', false, json::error_handler_t::strict), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"äü\"");
CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"ä\xEF\xBF\xBDü\"");
CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"\\u00e4\\ufffd\\u00fc\"");
}
SECTION("ending with incomplete character")
{
const json j = "123\xC2";
CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] incomplete UTF-8 string; last byte: 0xC2", json::type_error&);
CHECK_THROWS_AS(j.dump(1, ' ', false, json::error_handler_t::strict), json::type_error&);
CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"123\"");
CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"123\xEF\xBF\xBD\"");
CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"123\\ufffd\"");
}
SECTION("unexpected character")
{
const json j = "123\xF1\xB0\x34\x35\x36";
CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0x34", json::type_error&);
CHECK_THROWS_AS(j.dump(1, ' ', false, json::error_handler_t::strict), json::type_error&);
CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"123456\"");
CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"123\xEF\xBF\xBD\x34\x35\x36\"");
CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"123\\ufffd456\"");
}
SECTION("U+FFFD Substitution of Maximal Subparts")
{
// Some tests (mostly) from
// https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf
// Section 3.9 -- U+FFFD Substitution of Maximal Subparts
auto test = [&](std::string const & input, std::string const & expected)
{
const json j = input;
CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"" + expected + "\"");
};
test("\xC2", "\\ufffd");
test("\xC2\x41\x42", "\\ufffd" "\x41" "\x42");
test("\xC2\xF4", "\\ufffd" "\\ufffd");
test("\xF0\x80\x80\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xF1\x80\x80\x41", "\\ufffd" "\x41");
test("\xF2\x80\x80\x41", "\\ufffd" "\x41");
test("\xF3\x80\x80\x41", "\\ufffd" "\x41");
test("\xF4\x80\x80\x41", "\\ufffd" "\x41");
test("\xF5\x80\x80\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xF0\x90\x80\x41", "\\ufffd" "\x41");
test("\xF1\x90\x80\x41", "\\ufffd" "\x41");
test("\xF2\x90\x80\x41", "\\ufffd" "\x41");
test("\xF3\x90\x80\x41", "\\ufffd" "\x41");
test("\xF4\x90\x80\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xF5\x90\x80\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xC0\xAF\xE0\x80\xBF\xF0\x81\x82\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xED\xA0\x80\xED\xBF\xBF\xED\xAF\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
test("\xF4\x91\x92\x93\xFF\x41\x80\xBF\x42", "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\x41" "\\ufffd""\\ufffd" "\x42");
test("\xE1\x80\xE2\xF0\x91\x92\xF1\xBF\x41", "\\ufffd" "\\ufffd" "\\ufffd" "\\ufffd" "\x41");
}
}
SECTION("to_string")
{
auto test = [&](std::string const & input, std::string const & expected)
{
using std::to_string;
const json j = input;
CHECK(to_string(j) == "\"" + expected + "\"");
};
test(R"({"x":5,"y":6})", R"({\"x\":5,\"y\":6})");
test("{\"x\":[10,null,null,null]}", R"({\"x\":[10,null,null,null]})");
test("test", "test");
test("[3,\"false\",false]", R"([3,\"false\",false])");
}
}
TEST_CASE_TEMPLATE("serialization for extreme integer values", T, int32_t, uint32_t, int64_t, uint64_t) // NOLINT(readability-math-missing-parentheses, bugprone-throwing-static-initialization)
{
SECTION("minimum")
{
constexpr auto minimum = (std::numeric_limits<T>::min)();
const json j = minimum;
CHECK(j.dump() == std::to_string(minimum));
}
SECTION("maximum")
{
constexpr auto maximum = (std::numeric_limits<T>::max)();
const json j = maximum;
CHECK(j.dump() == std::to_string(maximum));
}
}
TEST_CASE("dump with binary values")
{
auto binary = json::binary({1, 2, 3, 4});
auto binary_empty = json::binary({});
auto binary_with_subtype = json::binary({1, 2, 3, 4}, 128);
auto binary_empty_with_subtype = json::binary({}, 128);
const json object = {{"key", binary}};
const json object_empty = {{"key", binary_empty}};
const json object_with_subtype = {{"key", binary_with_subtype}};
const json object_empty_with_subtype = {{"key", binary_empty_with_subtype}};
const json array = {"value", 1, binary};
const json array_empty = {"value", 1, binary_empty};
const json array_with_subtype = {"value", 1, binary_with_subtype};
const json array_empty_with_subtype = {"value", 1, binary_empty_with_subtype};
SECTION("normal")
{
CHECK(binary.dump() == "{\"bytes\":[1,2,3,4],\"subtype\":null}");
CHECK(binary_empty.dump() == "{\"bytes\":[],\"subtype\":null}");
CHECK(binary_with_subtype.dump() == "{\"bytes\":[1,2,3,4],\"subtype\":128}");
CHECK(binary_empty_with_subtype.dump() == "{\"bytes\":[],\"subtype\":128}");
CHECK(object.dump() == "{\"key\":{\"bytes\":[1,2,3,4],\"subtype\":null}}");
CHECK(object_empty.dump() == "{\"key\":{\"bytes\":[],\"subtype\":null}}");
CHECK(object_with_subtype.dump() == "{\"key\":{\"bytes\":[1,2,3,4],\"subtype\":128}}");
CHECK(object_empty_with_subtype.dump() == "{\"key\":{\"bytes\":[],\"subtype\":128}}");
CHECK(array.dump() == "[\"value\",1,{\"bytes\":[1,2,3,4],\"subtype\":null}]");
CHECK(array_empty.dump() == "[\"value\",1,{\"bytes\":[],\"subtype\":null}]");
CHECK(array_with_subtype.dump() == "[\"value\",1,{\"bytes\":[1,2,3,4],\"subtype\":128}]");
CHECK(array_empty_with_subtype.dump() == "[\"value\",1,{\"bytes\":[],\"subtype\":128}]");
}
SECTION("pretty-printed")
{
CHECK(binary.dump(4) == "{\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": null\n"
"}");
CHECK(binary_empty.dump(4) == "{\n"
" \"bytes\": [],\n"
" \"subtype\": null\n"
"}");
CHECK(binary_with_subtype.dump(4) == "{\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": 128\n"
"}");
CHECK(binary_empty_with_subtype.dump(4) == "{\n"
" \"bytes\": [],\n"
" \"subtype\": 128\n"
"}");
CHECK(object.dump(4) == "{\n"
" \"key\": {\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": null\n"
" }\n"
"}");
CHECK(object_empty.dump(4) == "{\n"
" \"key\": {\n"
" \"bytes\": [],\n"
" \"subtype\": null\n"
" }\n"
"}");
CHECK(object_with_subtype.dump(4) == "{\n"
" \"key\": {\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": 128\n"
" }\n"
"}");
CHECK(object_empty_with_subtype.dump(4) == "{\n"
" \"key\": {\n"
" \"bytes\": [],\n"
" \"subtype\": 128\n"
" }\n"
"}");
CHECK(array.dump(4) == "[\n"
" \"value\",\n"
" 1,\n"
" {\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": null\n"
" }\n"
"]");
CHECK(array_empty.dump(4) == "[\n"
" \"value\",\n"
" 1,\n"
" {\n"
" \"bytes\": [],\n"
" \"subtype\": null\n"
" }\n"
"]");
CHECK(array_with_subtype.dump(4) == "[\n"
" \"value\",\n"
" 1,\n"
" {\n"
" \"bytes\": [1, 2, 3, 4],\n"
" \"subtype\": 128\n"
" }\n"
"]");
CHECK(array_empty_with_subtype.dump(4) == "[\n"
" \"value\",\n"
" 1,\n"
" {\n"
" \"bytes\": [],\n"
" \"subtype\": 128\n"
" }\n"
"]");
}
}
TEST_CASE("dump for basic_json with long double number_float_t")
{
// Custom basic_json instantiation with long double as NumberFloatType.
// On platforms where long double is wider than double (e.g. GCC/Clang on
// Linux/macOS x86_64), dump() goes through the snprintf path in
// serializer::dump_float(x, std::false_type). That branch must use the
// "%.*Lg" format specifier; using "%.*g" with a long double argument is
// undefined behavior and corrupts the output.
using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string,
bool, std::int64_t, std::uint64_t, long double>;
SECTION("round-trip dump/parse")
{
constexpr std::array<long double, 13> values =
{
{
0.0L, -0.0L, 1.0L, -1.0L,
0.5L, -0.5L, 1.5L, -2.25L,
1.23e45L, 1.23e-45L,
(std::numeric_limits<long double>::min)(),
std::numeric_limits<long double>::lowest(),
(std::numeric_limits<long double>::max)()
}
};
for (long double v : values)
{
const long_double_json j = v;
const auto s = j.dump();
const auto j2 = long_double_json::parse(s);
CHECK(j2.template get<long double>() == v);
}
}
SECTION("exact dump string for simple values")
{
CHECK(long_double_json(0.5L).dump() == "0.5");
CHECK(long_double_json(-0.5L).dump() == "-0.5");
CHECK(long_double_json(1.5L).dump() == "1.5");
CHECK(long_double_json(-2.25L).dump() == "-2.25");
CHECK(long_double_json(0.0L).dump() == "0.0");
CHECK(long_double_json(1.0L).dump() == "1.0");
CHECK(long_double_json(-1.0L).dump() == "-1.0");
CHECK(long_double_json(100.0L).dump() == "100.0");
}
SECTION("NaN and infinity dump as null")
{
CHECK(long_double_json(std::numeric_limits<long double>::quiet_NaN()).dump() == "null");
// Probe the platform's runtime behavior — `volatile` forces a runtime
// call rather than constexpr-folding to a known answer at compile time.
// Skip the infinity assertions if std::isfinite() doesn't actually
// recognize long double infinity on this platform (notably, Valgrind
// 3.22's x87 80-bit emulation reports +/-inf as a large finite value).
// TODO(rusloker): remove this guard once Valgrind's 80-bit long double
// support ships (Valgrind bug https://bugs.kde.org/show_bug.cgi?id=197915,
// ASSIGNED since 2009 — the Valgrind project tracks its bugs on
// bugs.kde.org) and the minimum supported Valgrind version contains it.
const volatile long double inf_probe = std::numeric_limits<long double>::infinity();
if (!std::isfinite(inf_probe))
{
CHECK(long_double_json(std::numeric_limits<long double>::infinity()).dump() == "null");
CHECK(long_double_json(-std::numeric_limits<long double>::infinity()).dump() == "null");
}
}
SECTION("dump output matches double for exactly-representable values")
{
auto check_same = [](long double v_ld, double v_d)
{
const long_double_json j_ld = v_ld;
const json j_d = v_d;
CHECK(j_ld.dump() == j_d.dump());
};
check_same(0.0L, 0.0);
check_same(0.5L, 0.5);
check_same(-0.5L, -0.5);
check_same(1.5L, 1.5);
check_same(-2.25L, -2.25);
check_same(1.0L, 1.0);
check_same(100.0L, 100.0);
}
}
TEST_CASE("serialization of strings (bulk fast path)")
{
// These cases exercise the SWAR bulk-copy fast path in dump_escaped and the
// internal write buffer: long runs, escapes interrupting runs, 0x7F/DEL,
// multibyte UTF-8 under both ensure_ascii settings, and payloads larger than
// the write buffer.
SECTION("long unescaped ASCII exceeds the write buffer")
{
const std::string big(3000, 'a');
const json j = big;
CHECK(j.dump() == '"' + big + '"');
CHECK(j.dump(-1, ' ', true) == '"' + big + '"');
// round-trips
CHECK(json::parse(j.dump()) == j);
}
SECTION("runs interrupted by escapes")
{
const json j = std::string(500, 'x') + "\n\"\\" + std::string(500, 'y');
const std::string out = j.dump();
CHECK(out == '"' + std::string(500, 'x') + "\\n\\\"\\\\" + std::string(500, 'y') + '"');
CHECK(json::parse(out) == j);
}
SECTION("DEL (0x7F) depends on ensure_ascii")
{
const json j = std::string("a\x7f" "b");
CHECK(j.dump(-1, ' ', false) == "\"a\x7f" "b\""); // copied verbatim
CHECK(j.dump(-1, ' ', true) == "\"a\\u007fb\""); // escaped
}
SECTION("multibyte UTF-8 under both ensure_ascii settings")
{
const json j = std::string("A\xc3\xa9\xe4\xbd\xa0\xf0\x9f\x98\x80Z"); // A é 你 😀 Z
// not escaping non-ASCII: bytes are copied through the bulk validator
CHECK(j.dump(-1, ' ', false) == "\"A\xc3\xa9\xe4\xbd\xa0\xf0\x9f\x98\x80Z\"");
// ensure_ascii: escaped (with a surrogate pair for the emoji)
CHECK(j.dump(-1, ' ', true) == "\"A\\u00e9\\u4f60\\ud83d\\ude00Z\"");
CHECK(json::parse(j.dump(-1, ' ', true)) == j);
}
SECTION("many small structural writes exceed the write buffer")
{
json arr = json::array();
for (int i = 0; i < 2000; ++i)
{
arr.push_back(i);
}
const std::string out = arr.dump();
CHECK(out.front() == '[');
CHECK(out.back() == ']');
CHECK(json::parse(out) == arr);
json obj = json::object();
for (int i = 0; i < 500; ++i)
{
obj["key" + std::to_string(i)] = i;
}
CHECK(json::parse(obj.dump()) == obj);
CHECK(json::parse(obj.dump(2)) == obj);
// an array of many empty strings emits a long run of single-character
// writes ('"', '"', ',') at shallow nesting depth, so the write buffer
// fills and flushes mid-run without the deep recursion that would
// overflow the stack on some debug builds
json many_empty = json::array();
for (int i = 0; i < 500; ++i)
{
many_empty.push_back("");
}
const std::string out2 = many_empty.dump();
CHECK(out2.size() > 1024); // spans multiple write-buffer flushes
CHECK(out2.front() == '[');
CHECK(out2.back() == ']');
CHECK(json::parse(out2) == many_empty);
}
SECTION("invalid UTF-8 handling is unaffected by the fast path")
{
const json j = std::string("valid\xff" "more");
CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0xFF", json::type_error&);
CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"valid\xef\xbf\xbd" "more\"");
CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"valid\\ufffdmore\"");
CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"validmore\"");
}
}
TEST_CASE("indentation is written straight into the write buffer")
{
// put_indent() memsets the indentation into the write buffer instead of
// copying it out of a pre-grown indentation string. These cases cover an
// indentation wider than the buffer, a non-space indentation character, and
// nesting deep enough that the accumulated indentation spans several
// buffer-fulls - the situations the old grow-a-string approach got wrong.
SECTION("indent_step wider than the write buffer")
{
const json j = {{"a", 1}};
// 2000 > the 1024-byte write buffer, and > the 512 the indentation
// string used to start at
CHECK(j.dump(2000) == "{\n" + std::string(2000, ' ') + "\"a\": 1\n}");
// several whole buffer-fulls, so the buffer is refilled once and then
// flushed repeatedly
CHECK(j.dump(5000) == "{\n" + std::string(5000, ' ') + "\"a\": 1\n}");
CHECK(j.dump(5000, '\t') == "{\n" + std::string(5000, '\t') + "\"a\": 1\n}");
// an exact multiple of the buffer size
CHECK(j.dump(4096) == "{\n" + std::string(4096, ' ') + "\"a\": 1\n}");
}
SECTION("a non-space indentation character is used throughout")
{
const json j = {{"a", 1}};
// 600 is past the point where the indentation used to be grown, which
// is where a hard-coded space would have shown up
CHECK(j.dump(600, '\t') == "{\n" + std::string(600, '\t') + "\"a\": 1\n}");
CHECK(j.dump(3, '.') == "{\n...\"a\": 1\n}");
}
SECTION("accumulated indentation spans several buffer-fulls")
{
// five levels deep at 400 per level: the innermost value is indented by
// 2000 characters, reached in steps that each straddle the buffer end
json j = json::array({1});
for (int i = 0; i < 4; ++i)
{
j = json::array({j});
}
const std::string out = j.dump(400);
CHECK(out.find(std::string("\n") + std::string(2000, ' ') + "1\n") != std::string::npos);
CHECK(json::parse(out) == j);
}
SECTION("indentation is unchanged for ordinary widths")
{
const json j = {{"a", {1, 2}}, {"b", nullptr}};
CHECK(j.dump(2) == "{\n \"a\": [\n 1,\n 2\n ],\n \"b\": null\n}");
CHECK(j.dump(0) == "{\n\"a\": [\n1,\n2\n],\n\"b\": null\n}");
}
}
Reference in New Issue View Git Blame Copy Permalink