mirror of
https://github.com/nlohmann/json.git
synced 2026-11-19 09:45:20 +00:00
⚡ validate only newly read bytes of binary-format strings
get_string() validated the whole result after each call, but get_bytes() appends to it and CBOR indefinite-length strings collect all chunks in the same result, so every chunk re-validated everything read before it. An input of many small chunks took quadratic time (80000 one-byte chunks, 160 KB of input, took about 7 seconds). Only the newly read bytes are validated now, which also matches RFC 8949's requirement that every chunk is valid UTF-8 on its own. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
4 files changed
+56
-10
No files matched your search
@@ -109,16 +109,19 @@ MessagePack/BSON specifications all require text strings to be UTF-8), so
|
||||
that malformed input is caught immediately instead of only surfacing later
|
||||
as a type_error.316 when the resulting value is dumped.
|
||||
|
||||
@param[in] s the string to check
|
||||
@return whether @a s is valid UTF-8
|
||||
@param[in] s the string to check
|
||||
@param[in] first index of the first byte to check; the bytes before it are
|
||||
assumed to have been validated already and to end on a
|
||||
code point boundary
|
||||
@return whether @a s (from index @a first on) is valid UTF-8
|
||||
*/
|
||||
template<typename StringType>
|
||||
inline bool is_valid_utf8(const StringType& s) noexcept
|
||||
inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noexcept
|
||||
{
|
||||
std::uint8_t state = UTF8_ACCEPT;
|
||||
std::uint32_t codepoint = 0;
|
||||
|
||||
for (std::size_t i = 0; i < s.size(); ++i)
|
||||
for (std::size_t i = first; i < s.size(); ++i)
|
||||
{
|
||||
decode(state, codepoint, static_cast<std::uint8_t>(s[i]));
|
||||
if (state == UTF8_REJECT)
|
||||
|
||||
Reference in new issue
Block a user