amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-23 14:28:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into claude/fix-issue-3989-db7e45

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-23 06:35:52 +02:00
2 parents 510ee0ab4f ace1030107
commit 5c2aba70f9
60 files changed
+7977 -595357
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/input/json_sax.hpp
+3 -2
View File
@@ -423,8 +423,9 @@ class json_sax_dom_parser
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(ref_stack.back()->is_object());
// add null at the given key and store the reference for later
object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val));
// add null at the given key and store the reference for later; the
// key is moved, as the lexer starts the next token with reset()
object_element = &(ref_stack.back()->m_data.m_value.object->operator[](std::move(val)));
return true;
}
include/nlohmann/detail/input/lexer.hpp
+72 -39
View File
@@ -12,6 +12,7 @@
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint32_t
#include <cstdio> // snprintf
#include <cstring> // memcmp
#include <initializer_list> // initializer_list
#include <string> // char_traits, string
#include <utility> // move
@@ -432,30 +433,43 @@ class lexer : public lexer_base<BasicJsonType>
}
/// contiguous input: bulk-append the run of ordinary characters and complete
/// well-formed UTF-8 sequences starting at the current read position, leaving
/// the first byte that needs individual handling (the closing quote, an
/// escape, a control character, or an ill-formed UTF-8 byte) for get()
void scan_string_bulk(std::true_type /*bulk*/)
/// well-formed UTF-8 sequences starting at the current read position, then
/// read the first byte that needs individual handling (the closing quote, an
/// escape, a control character, or an ill-formed UTF-8 byte) like get().
/// That byte is taken from the buffer that was just scanned. Through get(),
/// Apple Clang merged this read with the other get() calls of the scan
/// function, which load the read position again right after it was stored
/// (3% of json::accept() on jeopardy.json on Apple M1).
char_int_type get_after_string_run(std::true_type /*bulk*/)
{
// a pending unget must be consumed through the normal path first
if (next_unget)
{
return;
return get();
}
const std::size_t remaining = ia.bulk_remaining();
if (remaining == 0)
{
return;
return get();
}
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
const auto* const raw = ia.bulk_data();
const auto* const data = reinterpret_cast<const unsigned char*>(raw);
const std::size_t pos = string_bulk_run(data, remaining);
if (pos == 0)
const std::size_t pos = lexer_string_bulk_run(data, remaining);
if (pos != 0)
{
return;
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
bulk_consume(reinterpret_cast<const char*>(data), pos);
}
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
bulk_consume(reinterpret_cast<const char*>(data), pos);
if (pos == remaining)
{
return get(); // end of the contiguous input
}
// what get() does, with the byte at hand
advance_position();
ia.bulk_skip(1);
current = char_traits<char_type>::to_int_type(raw[pos]);
return track_after_read();
}
/// consume @a n characters at @a data (the adapter's bulk_data()) and do
@@ -488,7 +502,10 @@ class lexer : public lexer_base<BasicJsonType>
}
/// streaming input: no bulk fast path
void scan_string_bulk(std::false_type /*bulk*/) const noexcept {}
char_int_type get_after_string_run(std::false_type /*bulk*/)
{
return get();
}
/*!
@brief scan a string literal
@@ -516,11 +533,8 @@ class lexer : public lexer_base<BasicJsonType>
while (true)
{
// bulk-consume ordinary characters from contiguous input, then
// handle the next special byte through the switch below
scan_string_bulk(std::integral_constant<bool, bulk_scan> {});
// get the next character
switch (get())
// get the next character, the one that ends the run
switch (get_after_string_run(std::integral_constant<bool, bulk_scan>()))
{
// end of file while parsing the string
case char_traits<char_type>::eof():
@@ -1906,18 +1920,23 @@ scan_number_done:
}
/*!
@param[in] literal_text the literal text to expect
@param[in] length the length of the passed literal text
@param[in] return_type the token type to return on success
@param[in] rest the literal text after its first character, which
is current (its length is a template parameter, so
that the comparison of the contiguous fast path is
a fixed-size load, not a call of memcmp)
@param[in] return_type the token type to return on success
*/
JSON_HEDLEY_NON_NULL(2)
token_type scan_literal(const char_type* literal_text, const std::size_t length,
token_type return_type)
template<std::size_t N>
JSON_HEDLEY_NEVER_INLINE token_type scan_literal(const char (&rest)[N], token_type return_type) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
{
JSON_ASSERT(char_traits<char_type>::to_char_type(current) == literal_text[0]);
for (std::size_t i = 1; i < length; ++i)
constexpr std::size_t length = N - 1;
if (scan_literal_bulk(rest, length, std::integral_constant<bool, bulk_scan> {}))
{
if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != literal_text[i]))
return return_type;
}
for (std::size_t i = 0; i < length; ++i)
{
if (JSON_HEDLEY_UNLIKELY(char_traits<char_type>::to_char_type(get()) != static_cast<char_type>(rest[i])))
{
error_message = "invalid literal";
error_cause = error_kind::other;
@@ -1927,6 +1946,27 @@ scan_number_done:
return return_type;
}
/// contiguous input: compare the rest of a literal at once; false (and
/// nothing consumed) if it does not match, so that the byte path reports
/// the error at the right character
JSON_HEDLEY_ALWAYS_INLINE bool scan_literal_bulk(const char* rest, const std::size_t length, std::true_type /*bulk*/)
{
if (next_unget || ia.bulk_remaining() < length
|| std::memcmp(ia.bulk_data(), rest, length) != 0)
{
return false;
}
bulk_consume(reinterpret_cast<const char*>(ia.bulk_data()), length);
current = static_cast<char_int_type>(static_cast<unsigned char>(rest[length - 1]));
return true;
}
/// streaming input: no bulk fast path
bool scan_literal_bulk(const char* /*rest*/, const std::size_t /*length*/, std::false_type /*bulk*/) const noexcept
{
return false;
}
/////////////////////
// input management
/////////////////////
@@ -2561,21 +2601,14 @@ scan_number_done:
return token_type::value_separator;
// literals
// (the text after the first character; no local arrays, which
// would give this function a stack canary on every token)
case 't':
{
std::array<char_type, 4> true_literal = {{static_cast<char_type>('t'), static_cast<char_type>('r'), static_cast<char_type>('u'), static_cast<char_type>('e')}};
return scan_literal(true_literal.data(), true_literal.size(), token_type::literal_true);
}
return scan_literal("rue", token_type::literal_true);
case 'f':
{
std::array<char_type, 5> false_literal = {{static_cast<char_type>('f'), static_cast<char_type>('a'), static_cast<char_type>('l'), static_cast<char_type>('s'), static_cast<char_type>('e')}};
return scan_literal(false_literal.data(), false_literal.size(), token_type::literal_false);
}
return scan_literal("alse", token_type::literal_false);
case 'n':
{
std::array<char_type, 4> null_literal = {{static_cast<char_type>('n'), static_cast<char_type>('u'), static_cast<char_type>('l'), static_cast<char_type>('l')}};
return scan_literal(null_literal.data(), null_literal.size(), token_type::literal_null);
}
return scan_literal("ull", token_type::literal_null);
// string
case '\"':
include/nlohmann/detail/input/number_parse.hpp
+2 -4
View File
@@ -16,7 +16,6 @@
#include <cstddef> // size_t
#include <cstdint> // int64_t, uint64_t
#include <cstdlib> // strtof, strtod, strtold
#include <cstring> // memcpy
#include <limits> // numeric_limits
#include <string> // string
#include <type_traits> // conditional, integral_constant, is_signed, true_type, false_type
@@ -758,15 +757,14 @@ std::uint64_t digit_comparison(const char* first, const char* last, std::uint64_
inline void float_from_bits(std::uint64_t bits, double& value) noexcept
{
static_assert(sizeof(double) == sizeof(std::uint64_t), "double must have 64 bits");
std::memcpy(&value, &bits, sizeof(value));
value = bit_cast<double>(bits);
}
/// the float with the IEEE-754 bits @a bits (the lower 32)
inline void float_from_bits(std::uint64_t bits, float& value) noexcept
{
static_assert(sizeof(float) == sizeof(std::uint32_t), "float must have 32 bits");
const auto bits32 = static_cast<std::uint32_t>(bits);
std::memcpy(&value, &bits32, sizeof(bits32));
value = bit_cast<float>(static_cast<std::uint32_t>(bits));
}
/// the powers of ten that are exact in binary64 (up to 10^22)
include/nlohmann/detail/input/parser.hpp
+12 -11
View File
@@ -288,8 +288,9 @@ class parser
const std::integral_constant<bool, AllowRecovery> allow_recovery{};
// stack to remember the hierarchy of structured values we are parsing
// true = array; false = object
std::vector<bool> states;
// true = array; false = object (bytes, not std::vector<bool>, whose
// push_back() is a call with GCC)
std::vector<std::uint8_t> states;
// value to avoid a goto (see comment where set to true)
bool skip_to_state_evaluation = false;
@@ -318,7 +319,7 @@ class parser
}
// remember we are now inside an object
states.push_back(false);
states.push_back(0);
// parse key (the steps of parse_key(), which are
// repeated here and below for speed)
@@ -368,7 +369,7 @@ class parser
}
// remember we are now inside an array
states.push_back(true);
states.push_back(1);
// parse values (no need to call get_token)
continue;
@@ -562,7 +563,7 @@ class parser
return true;
}
if (states.back()) // array
if (states.back() != 0) // array
{
// comma -> next value
// or end of array (ignore_trailing_commas = true)
@@ -969,18 +970,18 @@ class parser
/// @copydoc recover_missing_value
template<typename SAX>
JSON_INTERNAL_ALWAYS_INLINE
static std::false_type recover_missing_value(SAX* /*sax*/, const std::vector<bool>& /*states*/, std::false_type /*allow_recovery*/) noexcept
static std::false_type recover_missing_value(SAX* /*sax*/, const std::vector<std::uint8_t>& /*states*/, std::false_type /*allow_recovery*/) noexcept
{
return {};
}
/// pass the end events of all open containers
template<typename SAX>
bool close_containers(SAX* sax, std::vector<bool>& states, std::true_type /*allow_recovery*/)
bool close_containers(SAX* sax, std::vector<std::uint8_t>& states, std::true_type /*allow_recovery*/)
{
while (!states.empty())
{
const bool is_array = states.back();
const bool is_array = states.back() != 0;
states.pop_back();
if (JSON_HEDLEY_UNLIKELY(is_array ? !sax->end_array() : !sax->end_object()))
{
@@ -993,7 +994,7 @@ class parser
/// @copydoc close_containers
template<typename SAX>
JSON_INTERNAL_ALWAYS_INLINE
static std::false_type close_containers(SAX* /*sax*/, std::vector<bool>& /*states*/, std::false_type /*allow_recovery*/) noexcept
static std::false_type close_containers(SAX* /*sax*/, std::vector<std::uint8_t>& /*states*/, std::false_type /*allow_recovery*/) noexcept
{
return {};
}
@@ -1111,10 +1112,10 @@ class parser
ends there just ends.
*/
template<typename SAX>
bool recover_missing_value(SAX* sax, const std::vector<bool>& states, std::true_type /*allow_recovery*/)
bool recover_missing_value(SAX* sax, const std::vector<std::uint8_t>& states, std::true_type /*allow_recovery*/)
{
JSON_ASSERT(!states.empty());
if (!states.back() || last_token == token_type::value_separator)
if (states.back() == 0 || last_token == token_type::value_separator)
{
return sax->null();
}
include/nlohmann/detail/input/simd_scan.hpp
+321
View File
@@ -0,0 +1,321 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-FileCopyrightText: 2018-2025 The simdjson authors <https://github.com/simdjson/simdjson>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <atomic> // atomic
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint64_t
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Vector code for runs of string bytes, used by the lexer for contiguous input
// (see string_bulk_run()). NEON (AArch64) and SSE2 (x86-64) belong to the
// baseline instruction sets and are used by default. The vector UTF-8 check
// needs NEON or SSSE3. SSSE3 is not part of x86-64, and the code must not
// depend on the flags of a translation unit (two translation units with
// different flags would have different definitions of the same inline
// functions): the check is compiled for SSSE3 with a function attribute and
// used where the CPU has SSSE3 (all x86-64 CPUs since about 2011), else the
// portable check. Code compiled for SSSE3 anyway (-mssse3 or more) skips the
// CPU check. JSON_NO_SIMD selects the portable code everywhere.
// NLOHMANN_JSON_NO_TARGET_ATTRIBUTE (for compilers that ignore the target
// attribute and then reject the SSSE3 intrinsics) keeps the check portable
// without disabling the SSE2 code.
#if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#include <arm_neon.h>
#define JSON_SCAN_NEON 1
#else
#define JSON_SCAN_NEON 0
#endif
// (x86 only: other targets can define __SSE2__ as well, e.g., WebAssembly with -msse2, but have no <cpuid.h>)
#if !defined(JSON_NO_SIMD) && !JSON_SCAN_NEON && (defined(__x86_64__) || defined(__i386__) || defined(_M_X64) || defined(_M_IX86)) && !defined(_M_ARM64EC) && (defined(__SSE2__) || defined(_M_X64) || (defined(_M_IX86_FP) && _M_IX86_FP >= 2))
#include <emmintrin.h>
#define JSON_SCAN_SSE2 1
#else
#define JSON_SCAN_SSE2 0
#endif
#if JSON_SCAN_SSE2 && defined(__SSSE3__)
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#else
#define JSON_SCAN_SSSE3 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#endif
#if JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && !defined(NLOHMANN_JSON_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)) && !defined(__cpp_modules)))
// (GCC before 4.9 has no SSSE3 intrinsics without -mssse3; GCC with C++20
// modules drops the target attribute from functions it reads from a module
// interface and then rejects the intrinsics: "needs isa option -mssse3")
// <cpuid.h> of GCC before 11 has no include guard, and json.hpp and
// json_view.hpp both include it
#ifndef NLOHMANN_JSON_CPUID_INCLUDED
#define NLOHMANN_JSON_CPUID_INCLUDED
#include <cpuid.h>
#endif
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET __attribute__((target("ssse3")))
#elif JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && defined(_MSC_VER)
// (MSVC compiles intrinsics of any instruction set)
#include <intrin.h>
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET
#else
#define JSON_SCAN_SSSE3_DISPATCH 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET
#endif
#define JSON_SCAN_VECTOR (JSON_SCAN_NEON || JSON_SCAN_SSE2)
#define JSON_SCAN_VECTOR_UTF8 (JSON_SCAN_NEON || JSON_SCAN_SSSE3 || JSON_SCAN_SSSE3_DISPATCH)
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
#if JSON_SCAN_VECTOR
/*!
@brief the first byte of a string run that is a quote, a backslash, a control
character, or not ASCII, 16 bytes per step
Stops at such a byte, or where fewer than 16 bytes are left (the caller tells
the two apart). A signed compare with 0x20 finds control characters and
non-ASCII bytes at once.
*/
JSON_HEDLEY_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
{
while (e - p >= 16)
{
#if JSON_SCAN_NEON
const uint8x16_t in = vld1q_u8(p);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
// one nibble per byte (the usual NEON replacement of x86's movemask, see
// D. Kutenin, "Porting x86 vector bitmask optimizations to Arm NEON", 2022)
const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
if (bits != 0)
{
return p + (count_trailing_zeros(bits) >> 2u);
}
#else
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
if (bits != 0)
{
return p + count_trailing_zeros(bits);
}
#endif
p += 16;
}
return p;
}
#endif
#if JSON_SCAN_VECTOR
/// vector_plain_run() for runs that are already longer than a few words:
/// inline with SSE2, out of line with NEON, where a larger string loop slows
/// down the rest of the lexer
#if JSON_SCAN_NEON
JSON_HEDLEY_NEVER_INLINE inline
#else
JSON_HEDLEY_ALWAYS_INLINE
#endif
const unsigned char* vector_plain_run_long(const unsigned char* p, const unsigned char* e) noexcept
{
return vector_plain_run(p, e);
}
#endif
#if JSON_SCAN_SSSE3_DISPATCH
/// whether the CPU has SSSE3 (CPUID leaf 1, ECX bit 9)
inline bool cpu_ssse3() noexcept
{
#if defined(_MSC_VER) && !defined(__clang__)
std::array<int, 4> regs {{}};
__cpuid(regs.data(), 1);
return (static_cast<unsigned>(regs[2]) & (1u << 9u)) != 0;
#else
unsigned eax = 0;
unsigned ebx = 0;
unsigned ecx = 0;
unsigned edx = 0;
return __get_cpuid(1, &eax, &ebx, &ecx, &edx) != 0 && (ecx & (1u << 9u)) != 0;
#endif
}
/// whether the CPU has SSSE3, asked once: the answer is kept in an atomic
/// that is initialized at compile time, so that neither a guard of a local
/// static nor a global constructor is needed (threads that ask at the same
/// time all store the same answer)
JSON_HEDLEY_ALWAYS_INLINE bool cpu_has_ssse3() noexcept
{
static std::atomic<int> known{0}; // 0: not asked yet, 1: no, 2: yes
int state = known.load(std::memory_order_relaxed);
if (JSON_HEDLEY_UNLIKELY(state == 0))
{
state = cpu_ssse3() ? 2 : 1;
known.store(state, std::memory_order_relaxed);
}
return state == 2;
}
#endif
#if JSON_SCAN_VECTOR_UTF8
/// Tables of the UTF-8 check of J. Keiser and D. Lemire, "Validating UTF-8 In
/// Less Than One Instruction Per Byte" (2021), as in simdjson ("lookup4"): each
/// maps a nibble (high and low nibble of the previous byte, high nibble of the
/// current byte) to the errors it allows; a byte pair is ill-formed if all
/// three have an error bit in common.
template<typename Dummy = void>
struct utf8_lookup4
{
static constexpr std::uint8_t too_short = 1u << 0u, too_long = 1u << 1u, overlong_3 = 1u << 2u, too_large = 1u << 3u;
static constexpr std::uint8_t surrogate = 1u << 4u, overlong_2 = 1u << 5u, too_large_1000 = 1u << 6u, overlong_4 = 1u << 6u;
static constexpr std::uint8_t two_conts = 1u << 7u, carry = too_short | too_long | two_conts;
static const std::array<std::uint8_t, 16> byte_1_high;
static const std::array<std::uint8_t, 16> byte_1_low;
static const std::array<std::uint8_t, 16> byte_2_high;
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_high =
{
{
too_long, too_long, too_long, too_long, too_long, too_long, too_long, too_long,
two_conts, two_conts, two_conts, two_conts,
too_short | overlong_2, too_short, too_short | overlong_3 | surrogate, too_short | too_large | too_large_1000 | overlong_4
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_low =
{
{
carry | overlong_3 | overlong_2 | overlong_4, carry | overlong_2, carry, carry,
carry | too_large, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000 | surrogate, carry | too_large | too_large_1000, carry | too_large | too_large_1000
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_2_high =
{
{
too_short, too_short, too_short, too_short, too_short, too_short, too_short, too_short,
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large_1000 | overlong_4),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
too_short, too_short, too_short, too_short
}
};
/*!
@brief the run of plain string bytes and well-formed UTF-8 at p (a character
boundary), 16 bytes per step
The first quote, backslash, or control character is found with vector
compares, and the UTF-8 check of J. Keiser and D. Lemire covers the bytes up
to it. Returns true with @a block at that byte; returns false with @a block at
the start of the 16 bytes where the check found ill-formed UTF-8 or where
fewer than 16 bytes are left, for the caller to finish one sequence at a time.
Out of line, so that no constants of the check occupy registers in the
caller's loop. On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
*/
JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline bool vector_utf8_run(const unsigned char* p, const unsigned char* e, const unsigned char*& block_out) noexcept
{
using lookup = utf8_lookup4<>;
const unsigned char* block = p;
#if JSON_SCAN_NEON
const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
uint8x16_t prev = vdupq_n_u8(0);
while (e - block >= 16)
{
const uint8x16_t in = vld1q_u8(block);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))), vcltq_u8(in, vdupq_n_u8(0x20)));
const uint8x16_t prev1 = vextq_u8(prev, in, 15);
const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
const std::uint64_t special_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
const std::uint64_t err_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(err, err)), 4)), 0);
if (special_bits != 0)
{
// errors up to the special byte count (an incomplete sequence
// before a quote shows at the quote); the bytes after it do not
const unsigned k = static_cast<unsigned>(count_trailing_zeros(special_bits)) >> 2u;
const std::uint64_t upto = k == 15 ? ~std::uint64_t{0} :
(std::uint64_t{1} << (4u * (k + 1u))) - 1u;
if ((err_bits & upto) == 0)
{
block_out = block + k;
return true;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#else
// the same with SSSE3 (pshufb for the table lookups; nibbles from 16-bit
// shifts, as there are no byte shifts)
const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i nibble = _mm_set1_epi8(0x0F);
const __m128i zero = _mm_setzero_si128();
__m128i prev = zero;
while (e - block >= 16)
{
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmpeq_epi8(_mm_subs_epu8(in, _mm_set1_epi8(0x1F)), zero)); // in < 0x20
const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
_mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
_mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
_mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
const auto special_bits = static_cast<unsigned>(_mm_movemask_epi8(special));
const auto err_bits = ~static_cast<unsigned>(_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero))) & 0xFFFFu;
if (special_bits != 0)
{
const auto k = static_cast<unsigned>(count_trailing_zeros(static_cast<std::uint64_t>(special_bits)));
if ((err_bits & ((2u << k) - 1u)) == 0)
{
block_out = block + k;
return true;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#endif
block_out = block;
return false;
}
#endif
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/input/string_scan.hpp
+161 -16
View File
@@ -14,6 +14,7 @@
#include <cstring> // memcpy
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/input/simd_scan.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -34,7 +35,7 @@
// This file contains the byte-level string-scanning helpers used by the lexer's
// contiguous fast path. They operate purely on raw bytes (no dependency on the
// lexer's template parameters) so they are free functions, keeping the lexer
// itself focused on the state machine; see lexer::scan_string_bulk().
// itself focused on the state machine; see lexer::get_after_string_run().
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
@@ -66,7 +67,7 @@ inline std::uint64_t swar_string_special(std::uint64_t v) noexcept
// return the index of the first is_string_special() byte in [data, data+n), or
// n if every byte is ordinary; scans 8 bytes at a time
inline std::size_t find_string_special(const unsigned char* data, std::size_t n) noexcept
JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* data, std::size_t n) noexcept
{
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
@@ -235,35 +236,143 @@ inline std::size_t valid_utf8_prefix(const unsigned char* data, std::size_t n) n
return pos;
}
// Scalar (C++11) computation of the bulk run length: the number of leading
// bytes in [data, data+n) that are ordinary ASCII or complete well-formed UTF-8
#if JSON_SCAN_VECTOR_UTF8
/// the end of scan_string_vector from block, where the vector loop stopped
/// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a
/// time, from the start of a sequence that crosses into the block
inline const unsigned char* scan_string_finish(const unsigned char* p, const unsigned char* block, const unsigned char* e) noexcept
{
for (int i = 1; i <= 3 && block - i >= p; ++i)
{
const unsigned char c = block[-i];
if (c < 0x80)
{
break;
}
if (c >= 0xC0)
{
const int len = 2 + static_cast<int>(c >= 0xE0) + static_cast<int>(c >= 0xF0);
if (len > i)
{
block -= i;
}
break;
}
}
for (p = block; p != e;)
{
if (*p < 0x80)
{
if (is_string_special(*p))
{
return p;
}
++p;
continue;
}
const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
if (n == 0)
{
return p;
}
p += n;
}
return p;
}
/// the rest of a string from p (a character boundary), with the vector UTF-8
/// check and the scalar check for the end of the block where it stopped
inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e) noexcept
{
const unsigned char* block = p;
if (vector_utf8_run(p, e, block))
{
return block;
}
return scan_string_finish(p, block, e);
}
#endif
#if JSON_SCAN_VECTOR
/// the end of the run of plain string characters at @a p: the first quote,
/// backslash, control character, or non-ASCII byte, or @a e. The first words
/// are checked with SWAR (one; four with NEON, where the vector mask costs
/// more), as most keys and short values end there; longer runs continue 16
/// bytes at a time.
JSON_HEDLEY_ALWAYS_INLINE const unsigned char* plain_run_end(const unsigned char* p, const unsigned char* e) noexcept
{
constexpr int prefix_words = JSON_SCAN_NEON ? 4 : 1;
for (int words = prefix_words; words > 0 && e - p >= 8; --words)
{
const std::uint64_t special = swar_string_special(read_eight_bytes(p));
if (special != 0)
{
return p + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
}
p += 8;
}
// the vector loop only for 16 bytes or more: the serializer passes a
// string without its closing quote, so most of its runs end at e, and a
// call of the out-of-line NEON loop for a shorter rest made dump() up to
// 10% slower
if (e - p >= 16)
{
p = vector_plain_run_long(p, e);
if (e - p >= 16)
{
return p; // the vector loop stopped at a special byte
}
}
return p + find_string_special(p, static_cast<std::size_t>(e - p));
}
#endif
// Computation of the bulk run length: the number of leading bytes in
// [data, data+n) that are ordinary ASCII or complete well-formed UTF-8
// sequences, stopping before the first byte that needs individual handling (the
// closing quote, an escape, a control character, or an ill-formed/truncated
// sequence). ASCII is skipped 8 bytes at a time.
inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
// sequence). ASCII is skipped 16 bytes at a time with SSE2 and 8 bytes at a
// time otherwise; runs of non-ASCII text use the vector UTF-8 check where
// available.
JSON_HEDLEY_ALWAYS_INLINE std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
{
std::size_t pos = 0;
while (pos < n)
const unsigned char* const e = data + n;
const unsigned char* p = data;
while (p != e)
{
pos += find_string_special(data + pos, n - pos);
if (pos >= n || data[pos] < 0x80u)
#if JSON_SCAN_VECTOR
p = plain_run_end(p, e);
#else
p += find_string_special(p, static_cast<std::size_t>(e - p));
#endif
if (p == e || *p < 0x80u)
{
break; // end of buffer, or a quote/escape/control byte
}
#if JSON_SCAN_VECTOR_UTF8
#if JSON_SCAN_SSSE3_DISPATCH
if (JSON_HEDLEY_LIKELY(cpu_has_ssse3()))
#endif
{
return static_cast<std::size_t>(scan_string_vector(p, e) - data);
}
#endif
#if !JSON_SCAN_VECTOR_UTF8 || JSON_SCAN_SSSE3_DISPATCH
// 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
{
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
const std::size_t seq = validate_one_utf8(p, static_cast<std::size_t>(e - p));
if (seq == 0)
{
return pos; // ill-formed or truncated: let the byte path diagnose it
return static_cast<std::size_t>(p - data); // ill-formed or truncated: let the byte path diagnose it
}
pos += seq;
p += seq;
}
while (pos < n && data[pos] >= 0x80u);
while (p != e && *p >= 0x80u);
#endif
}
return pos;
return static_cast<std::size_t>(p - data);
}
#if defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17)
@@ -304,7 +413,7 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
// next delimiter is validated in one shot by simdutf; on the rare failure the
// scalar helper recomputes the exact valid prefix so the byte path still
// produces the precise diagnostic. Without it, the pure scalar path is used.
inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noexcept
JSON_HEDLEY_ALWAYS_INLINE std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noexcept
{
#if defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17)
const std::size_t run = find_string_delimiter(data, n);
@@ -316,6 +425,42 @@ inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noe
return scalar_string_bulk_run(data, n);
}
#if JSON_SCAN_NEON && !(defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17))
/// scalar_string_bulk_run() from @a start on, out of line (see
/// lexer_string_bulk_run())
JSON_HEDLEY_NEVER_INLINE inline std::size_t string_bulk_run_from(const unsigned char* data, std::size_t start, std::size_t n) noexcept
{
return start + scalar_string_bulk_run(data + start, n - start);
}
#endif
// string_bulk_run() for the lexer. With NEON, only the first four words are
// checked inline (most keys and short values end there), and longer runs and
// non-ASCII text continue out of line. The lexer's scan function runs once per
// token, and the vector code inlined into it needs more registers, which every
// token pays for: 5% of json::accept() on jeopardy.json with Apple Clang on
// Apple M1, even though no string of that file reaches the vector code. The
// serializer keeps string_bulk_run() inline, which is faster there.
JSON_HEDLEY_ALWAYS_INLINE std::size_t lexer_string_bulk_run(const unsigned char* data, std::size_t n) noexcept
{
#if JSON_SCAN_NEON && !(defined(JSON_USE_SIMDUTF) && defined(JSON_HAS_CPP_17))
std::size_t i = 0;
for (int words = 4; words > 0 && n - i >= 8; --words)
{
const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
if (special != 0)
{
const std::size_t pos = i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
return data[pos] < 0x80u ? pos : string_bulk_run_from(data, pos, n);
}
i += 8;
}
return string_bulk_run_from(data, i, n);
#else
return string_bulk_run(data, n);
#endif
}
// Decode the 4 hex digits at [data, data+4) - the digits following a `\u`
// escape - into a codepoint 0x0000..0xFFFF via one table lookup per byte
// (after yyjson's read_hex_u16), or return -1 if any of the 4 bytes is not a