mirror of
https://github.com/nlohmann/json.git
synced 2026-10-05 14:21:05 +01:00
Cover every byte class in the ill-formed UTF-8 sweeps
Pinning the bytes around the invalid one to 0x80 lost coverage: with error_handler_t::ignore/replace, the serializer re-reads the invalid byte and decodes the following bytes, and its decoder distinguishes the continuation classes 0x80-0x8F, 0x90-0x9F, and 0xA0-0xBF, as do the lexer's range checks. Iterate those positions over the first and last byte of each class within the valid range instead (utils::utf8_continuation_bytes). The invalid byte still takes all 256 values. Defining JSON_TEST_UTF8_EXHAUSTIVE restores the full Cartesian product, with the same assertion counts as before #5418. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
@@ -8,6 +8,7 @@
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <array> // array
|
||||
#include <cstdint> // uint8_t
|
||||
#include <cstddef> // size_t
|
||||
#include <fstream> // ifstream, istreambuf_iterator, ios
|
||||
@@ -42,6 +43,33 @@ T next_integer_sample(T i, T last, T stride)
|
||||
return n < last ? n : last;
|
||||
}
|
||||
|
||||
// UTF-8 continuation bytes in [lo, hi] that stand in for all of them in the
|
||||
// ill-formed UTF-8 tests. Both the lexer's range checks and the serializer's
|
||||
// decoder (detail::decode) only distinguish the classes 0x80..0x8F, 0x90..0x9F,
|
||||
// and 0xA0..0xBF, so the first and last byte of each class within [lo, hi]
|
||||
// exercise every behavior while a test sweeps another byte position through
|
||||
// all 256 values (#5418). Define JSON_TEST_UTF8_EXHAUSTIVE to get every byte.
|
||||
inline std::vector<int> utf8_continuation_bytes(int lo, int hi)
|
||||
{
|
||||
std::vector<int> result;
|
||||
#ifdef JSON_TEST_UTF8_EXHAUSTIVE
|
||||
for (int byte = lo; byte <= hi; ++byte)
|
||||
{
|
||||
result.push_back(byte);
|
||||
}
|
||||
#else
|
||||
static const std::array<int, 6> class_ends = {{0x80, 0x8F, 0x90, 0x9F, 0xA0, 0xBF}};
|
||||
for (const int byte : class_ends)
|
||||
{
|
||||
if (lo <= byte && byte <= hi)
|
||||
{
|
||||
result.push_back(byte);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
inline std::vector<std::uint8_t> read_binary_file(const std::string& filename)
|
||||
{
|
||||
std::ifstream file(filename, std::ios::binary);
|
||||
|
||||
Reference in New Issue
Block a user