amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-09-08 01:07:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
1c6ca81b8a18c249c04446c6d494db0a95673e6a
json/tests/src/unit-unicode3.cpp
T
Niels Lohmann 1c6ca81b8a Fix dead ill-formed-fourth-byte UTF-8 test sections (byte3/byte4 typo) 
The "ill-formed: wrong fourth byte" SECTIONs in unit-unicode3.cpp,
unit-unicode4.cpp, and unit-unicode5.cpp guarded their loop with a check
on byte3 instead of byte4. Since the enclosing loop already restricts
byte3 to its valid range, the guard was always true and the section's
"continue" fired unconditionally, so check_utf8string()/check_utf8dump()
were never actually invoked for a malformed fourth byte.

Fixing the guard naively (byte3 -> byte4) would also have swept the full
byte2 x byte3 combinatorics for every byte4 value, adding millions of
redundant iterations: the lexer validates continuation bytes strictly in
sequence with early exit (see next_byte_in_range() in lexer.hpp), so once
byte2/byte3 are within their valid range, the byte4 outcome does not
depend on which valid byte2/byte3 values were chosen. Instead, byte2 and
byte3 are now held to a small hedge of representative valid prefixes
(range corners plus a midpoint) while byte4 is still swept exhaustively
over its full 0x00-0xFF range, since that is the actual property under
test. Also fixed the garbled "skip fourth second byte" comment in
unit-unicode3.cpp.

Verified offline: before the fix, the "wrong fourth byte" subcase
executes 0 assertions in all three files (proving it was dead code);
after the fix, it executes 11520 (unicode3), 34560 (unicode4), and 11520
(unicode5) assertions, and a deliberately reintroduced bug in the
lexer's byte4 range check causes it to fail (proving it is now
meaningful). Total per-file assertion counts grow by the same small
amounts, not by millions, and all other sections in these files still
pass unchanged.

Fixes #5416

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 23:05:42 +02:00

344 lines
12 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"
// for some reason including this after the json header leads to linker errors with VS 2017...
#include <locale>
#include <nlohmann/json.hpp>
using nlohmann::json;
#include <fstream>
#include <sstream>
#include <iostream>
#include <iomanip>
#include "make_test_data_available.hpp"
// this test suite uses static variables with non-trivial destructors
DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
namespace
{
extern size_t calls;
size_t calls = 0;
void check_utf8dump(bool success_expected, int byte1, int byte2, int byte3, int byte4);
void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
{
static std::string json_string;
json_string.clear();
CAPTURE(byte1)
CAPTURE(byte2)
CAPTURE(byte3)
CAPTURE(byte4)
json_string += std::string(1, static_cast<char>(byte1));
if (byte2 != -1)
{
json_string += std::string(1, static_cast<char>(byte2));
}
if (byte3 != -1)
{
json_string += std::string(1, static_cast<char>(byte3));
}
if (byte4 != -1)
{
json_string += std::string(1, static_cast<char>(byte4));
}
CAPTURE(json_string)
// store the string in a JSON value
static json j;
static json j2;
j = json_string;
j2 = "abc" + json_string + "xyz";
static std::string s_ignored;
static std::string s_ignored2;
static std::string s_ignored_ascii;
static std::string s_ignored2_ascii;
static std::string s_replaced;
static std::string s_replaced2;
static std::string s_replaced_ascii;
static std::string s_replaced2_ascii;
// dumping with ignore/replace must not throw in any case
s_ignored = j.dump(-1, ' ', false, json::error_handler_t::ignore);
s_ignored2 = j2.dump(-1, ' ', false, json::error_handler_t::ignore);
s_ignored_ascii = j.dump(-1, ' ', true, json::error_handler_t::ignore);
s_ignored2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::ignore);
s_replaced = j.dump(-1, ' ', false, json::error_handler_t::replace);
s_replaced2 = j2.dump(-1, ' ', false, json::error_handler_t::replace);
s_replaced_ascii = j.dump(-1, ' ', true, json::error_handler_t::replace);
s_replaced2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::replace);
if (success_expected)
{
static std::string s_strict;
// strict mode must not throw if success is expected
s_strict = j.dump();
// all dumps should agree on the string
CHECK(s_strict == s_ignored);
CHECK(s_strict == s_replaced);
}
else
{
// strict mode must throw if success is not expected
CHECK_THROWS_AS(j.dump(), json::type_error&);
// ignore and replace must create different dumps
CHECK(s_ignored != s_replaced);
// check that replace string contains a replacement character
CHECK(s_replaced.find("\xEF\xBF\xBD") != std::string::npos);
}
// check that prefix and suffix are preserved
CHECK(s_ignored2.substr(1, 3) == "abc");
CHECK(s_ignored2.substr(s_ignored2.size() - 4, 3) == "xyz");
CHECK(s_ignored2_ascii.substr(1, 3) == "abc");
CHECK(s_ignored2_ascii.substr(s_ignored2_ascii.size() - 4, 3) == "xyz");
CHECK(s_replaced2.substr(1, 3) == "abc");
CHECK(s_replaced2.substr(s_replaced2.size() - 4, 3) == "xyz");
CHECK(s_replaced2_ascii.substr(1, 3) == "abc");
CHECK(s_replaced2_ascii.substr(s_replaced2_ascii.size() - 4, 3) == "xyz");
}
void check_utf8string(bool success_expected, int byte1, int byte2, int byte3, int byte4);
// create and check a JSON string with up to four UTF-8 bytes
void check_utf8string(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
{
if (++calls % 100000 == 0)
{
std::cout << calls << " of 1641521 UTF-8 strings checked" << std::endl; // NOLINT(performance-avoid-endl)
}
static std::string json_string;
json_string = "\"";
CAPTURE(byte1)
json_string += std::string(1, static_cast<char>(byte1));
if (byte2 != -1)
{
CAPTURE(byte2)
json_string += std::string(1, static_cast<char>(byte2));
}
if (byte3 != -1)
{
CAPTURE(byte3)
json_string += std::string(1, static_cast<char>(byte3));
}
if (byte4 != -1)
{
CAPTURE(byte4)
json_string += std::string(1, static_cast<char>(byte4));
}
json_string += "\"";
CAPTURE(json_string)
json _;
if (success_expected)
{
CHECK_NOTHROW(_ = json::parse(json_string));
}
else
{
CHECK_THROWS_AS(_ = json::parse(json_string), json::parse_error&);
}
}
} // namespace
TEST_CASE("Unicode (3/5)" * doctest::skip())
{
SECTION("RFC 3629")
{
/*
RFC 3629 describes in Sect. 4 the syntax of UTF-8 byte sequences as
follows:
A UTF-8 string is a sequence of octets representing a sequence of UCS
characters. An octet sequence is valid UTF-8 only if it matches the
following syntax, which is derived from the rules for encoding UTF-8
and is expressed in the ABNF of [RFC2234].
UTF8-octets = *( UTF8-char )
UTF8-char = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
UTF8-1 = %x00-7F
UTF8-2 = %xC2-DF UTF8-tail
UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
%xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
%xF4 %x80-8F 2( UTF8-tail )
UTF8-tail = %x80-BF
*/
SECTION("UTF8-4 (xF0 x90-BF UTF8-tail UTF8-tail)")
{
SECTION("well-formed")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
{
for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
{
for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
{
check_utf8string(true, byte1, byte2, byte3, byte4);
check_utf8dump(true, byte1, byte2, byte3, byte4);
}
}
}
}
}
SECTION("ill-formed: missing second byte")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
check_utf8string(false, byte1);
check_utf8dump(false, byte1);
}
}
SECTION("ill-formed: missing third byte")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
{
check_utf8string(false, byte1, byte2);
check_utf8dump(false, byte1, byte2);
}
}
}
SECTION("ill-formed: missing fourth byte")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
{
for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
{
check_utf8string(false, byte1, byte2, byte3);
check_utf8dump(false, byte1, byte2, byte3);
}
}
}
}
SECTION("ill-formed: wrong second byte")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
{
// skip correct second byte
if (0x90 <= byte2 && byte2 <= 0xBF)
{
continue;
}
for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
{
for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
{
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
}
}
}
SECTION("ill-formed: wrong third byte")
{
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
{
for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
{
// skip correct third byte
if (0x80 <= byte3 && byte3 <= 0xBF)
{
continue;
}
for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
{
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
}
}
}
SECTION("ill-formed: wrong fourth byte")
{
// The lexer (see next_byte_in_range() in lexer.hpp) validates the
// continuation bytes strictly in sequence and bails out on the first
// byte that is out of range. So once byte2 and byte3 are anywhere
// inside their own valid range, whether byte4 is accepted or rejected
// depends only on byte4's value -- not on which particular valid
// byte2/byte3 combination was used to reach it. Sweeping the full
// byte2 x byte3 combinatorics here (as the other "wrong Nth byte"
// sections do for the byte they target) would therefore add a huge
// number of iterations for zero additional coverage. Instead, byte2
// and byte3 are held to a small hedge of representative valid
// prefixes -- the corners and midpoint of their valid ranges -- while
// byte4 is still swept exhaustively over 0x00-0xFF, since "byte4 out
// of range is rejected for every value it could take" is the actual
// property under test. If the UTF-8 decoder is ever reworked (e.g.
// into a table-driven/bulk scanner), this equivalence-class
// assumption should be re-audited.
static const int byte2_values[] = {0x90, 0x90, 0xBF, 0xBF, 0xA8};
static const int byte3_values[] = {0x80, 0xBF, 0x80, 0xBF, 0xA0};
for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
{
for (size_t idx = 0; idx < sizeof(byte2_values) / sizeof(byte2_values[0]); ++idx)
{
const int byte2 = byte2_values[idx];
const int byte3 = byte3_values[idx];
for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
{
// skip correct fourth byte
if (0x80 <= byte4 && byte4 <= 0xBF)
{
continue;
}
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
}
}
}
}
}
DOCTEST_CLANG_SUPPRESS_WARNING_POP
Reference in New Issue View Git Blame Copy Permalink