Scarfski/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-09-30 22:15:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Find the stop byte of a string run without a byte loop

Browse Source 
find_string_special() and find_ascii_copyable_run() test eight bytes at a
time, but located the stopping byte inside a word with a byte loop. The
lowest flagged byte of the SWAR tests is always a true hit (the borrows of
the subtractions can only flag bytes above one), so its index is now the
trailing-zero count of the mask; words are read in little-endian order on
every platform, so this does not depend on the byte order.
scalar_string_bulk_run() validates a run of multi-byte UTF-8 sequences one
after another instead of searching for the next special byte in between,
which helps text in non-Latin scripts.

The kernels serve the lexer's contiguous fast path, the serializer, and the
binary formats. New tests compare all three with byte-by-byte reference
scans on 100,000 generated buffers at three alignments; the portable
fallback of count_trailing_zeros() was checked against the builtin.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-09-28 21:15:40 +02:00
parent f295970fb6
commit 31789f51cf
4 changed files with 193 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
include/nlohmann/detail/bit_ops.hpp
View File

@@ -39,6 +39,25 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
#endif
}
/// number of trailing zero bits of x (x != 0)
inline int count_trailing_zeros(std::uint64_t x) noexcept
{
#if defined(__GNUC__) || defined(__clang__)
return __builtin_ctzll(x);
#else
int n = 0;
for (int shift = 32; shift != 0; shift >>= 1)
{
if ((x << (64 - shift)) == 0)
{
n += shift;
x >>= shift;
}
}
return n;
#endif
}
/// the 128-bit product of two 64-bit numbers
struct uint128_parts
{
@@ -68,14 +87,19 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
/// eight bytes as a little-endian word (compilers fold this into one load on
/// little-endian targets)
inline std::uint64_t read_eight_bytes(const char* p) noexcept
inline std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
{
const auto* b = reinterpret_cast<const unsigned char*>(p); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
| (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
| (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
| (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
}
/// eight bytes as a little-endian word
inline std::uint64_t read_eight_bytes(const char* p) noexcept
{
return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
}
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END

51
include/nlohmann/detail/input/string_scan.hpp
View File

@@ -12,6 +12,7 @@
#include <cstdint> // uint64_t
#include <cstring> // memcpy
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -69,18 +70,12 @@ inline std::size_t find_string_special(const unsigned char* data, std::size_t n)
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t word = 0;
std::memcpy(&word, data + i, sizeof(word));
if (swar_string_special(word) != 0)
const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
if (special != 0)
{
// a special byte is in this word; locate it (endian-agnostic)
for (std::size_t j = 0; j < 8; ++j)
{
if (is_string_special(data[i + j]))
{
return i + j;
}
}
// the lowest flagged byte is the first special one: the borrows of
// the subtractions can only flag bytes above a true hit
return i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
}
}
for (; i < n; ++i)
@@ -114,8 +109,7 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull; // '"' (0x22)
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\' (0x5C)
const std::uint64_t d = v ^ 0x7F7F7F7F7F7F7F7Full; // DEL (0x7F)
@@ -126,7 +120,9 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
| (v & high); // >= 0x80
if (stop != 0)
{
break;
// the lowest flagged byte is the first one to stop at (see
// find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
}
}
for (; i < n; ++i)
@@ -253,12 +249,18 @@ inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t
{
break; // end of buffer, or a quote/escape/control byte
}
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
// a run of multi-byte sequences (e.g. CJK text) is validated sequence
// by sequence without searching for the next special byte in between
do
{
break; // ill-formed or truncated: let the byte path diagnose it
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
{
return pos; // ill-formed or truncated: let the byte path diagnose it
}
pos += seq;
}
pos += seq;
while (pos < n && data[pos] >= 0x80u);
}
return pos;
}
@@ -273,8 +275,7 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull;
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull;
const std::uint64_t hit = ((q - ones) & ~q & high)
@@ -282,14 +283,8 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
| ((v - 0x2020202020202020ull) & ~v & high);
if (hit != 0)
{
for (std::size_t j = 0; j < 8; ++j)
{
const unsigned char c = data[i + j];
if (c == '\"' || c == '\\' || c < 0x20u)
{
return i + j;
}
}
// the lowest flagged byte is the first delimiter (see find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(hit)) / 8);
}
}
for (; i < n; ++i)