Merge branch 'json-view/02b-float-parser' into json-view/23-zmij

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

docs/mkdocs/docs/api/basic_json/number_float_t.md

@@ -23,10 +23,10 @@ type to use.
 ## Template parameters
 
 `NumberFloatType`
-:   the type to store floating-point numbers. The parser converts `#!cpp float`, `#!cpp double`, and a
-    `#!cpp long double` that is IEEE 754 binary64 itself and other `#!cpp long double` formats with
-    `#!cpp std::from_chars` or `#!cpp std::strtold`, and serialization falls back to `#!cpp std::snprintf`, so the
-    type must be `#!cpp float`, `#!cpp double`, or `#!cpp long double`. The
+:   the type to store floating-point numbers. The type must be `#!cpp float`, `#!cpp double`, or
+    `#!cpp long double`. The parser converts `#!cpp float`, `#!cpp double`, and a `#!cpp long double` that is IEEE 754
+    binary64 itself. It converts other `#!cpp long double` formats with `#!cpp std::from_chars` where available, or
+    with `#!cpp std::strtold` otherwise. Serialization falls back to `#!cpp std::snprintf`. The
     [binary formats](../../features/binary_formats/index.md) additionally require `#!cpp float` or `#!cpp double`,
     because they have no encoding for `#!cpp long double`. See
     [Template Parameter Requirements](../../features/types/template_parameters.md#numberfloattype).

docs/mkdocs/docs/features/types/template_parameters.md

@@ -353,16 +353,21 @@ using array_t = ArrayType<basic_json, AllocatorType<basic_json>>;
 ### Always required
 
 - A member type `value_type` that is one byte wide and `char`-compatible. The library stores and processes UTF-8
-  encoded `char` data and passes `data()` to functions that take a `#!cpp const char*`, such as `#!cpp std::strtod`.
+  encoded `char` data and passes `data()` to functions that take a `#!cpp const char*`, such as `#!cpp std::strtold`
+  (only used to parse a `#!cpp long double` that is not IEEE 754 binary64, see
+  [`NumberFloatType`](#numberfloattype)).
   `#!cpp std::wstring`, `#!cpp std::u16string`, and `#!cpp std::u32string` are **not** valid choices; see the FAQ on
   [wide string handling](../../home/faq.md#wide-string-handling).
 - Constructors: default, copy, move, from `#!cpp const char*` (which must not be `#!cpp explicit`), from
   `#!cpp (const char*, size_type)`, and from `#!cpp (size_type, char)`; and copy or move assignment.
 - Member functions `size()`, `clear()`, `resize(n, c)`, `data()`, `push_back(char)`, and `operator[]`
   (const and non-const, returning references). `c_str()` and `back()` are **not** required.
-- `data()` must return a pointer to a contiguous, **null-terminated** buffer -- the parser may hand it to
-  `#!cpp std::strtod`, which reads up to the null character. A type whose `data()` is not null-terminated does not
-  fail to compile; it can silently misparse floating-point numbers.
+- `data()` must return a pointer to a contiguous, **null-terminated** buffer. `#!cpp float`, `#!cpp double`, and a
+  `#!cpp long double` that is IEEE 754 binary64 are converted by the library itself and do not depend on this. For any
+  other `NumberFloatType` (a `#!cpp long double` of another format), the parser falls back to `#!cpp std::strtold` when
+  `#!cpp std::from_chars` is not available or declines the token, and `std::strtold` reads up to the null character. A type whose `data()`
+  is not null-terminated does not fail to compile; with such a `NumberFloatType` it can silently misparse
+  floating-point numbers.
 - `append(const char*, size_type)`, used by [`dump`](../../api/basic_json/dump.md), and `append(const StringType&)`,
   used by the CBOR reader for indefinite-length strings. The library's internal string concatenation additionally has
   to append a `#!cpp char` and a `#!cpp const char*`; for each it selects between `append(arg)`, `#!cpp operator+=`,

include/nlohmann/detail/bit_ops.hpp

@@ -9,8 +9,9 @@
 #pragma once
 
 #include <cstdint> // uint64_t
-#if !defined(__SIZEOF_INT128__) && defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
-    #include <intrin0.h> // __umulh, _umul128
+#include <cstring> // memcpy
+#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64)) && (!defined(__SIZEOF_INT128__) || (!defined(__GNUC__) && !defined(__clang__)))
+    #include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
 #endif
 
 #include <nlohmann/detail/macro_scope.hpp> // JSON_HEDLEY_ALWAYS_INLINE, NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -28,6 +29,10 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
 {
 #if defined(__GNUC__) || defined(__clang__)
     return __builtin_clzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0;
+    _BitScanReverse64(&index, x);
+    return 63 - static_cast<int>(index);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -47,6 +52,10 @@ inline int count_trailing_zeros(std::uint64_t x) noexcept
 {
 #if defined(__GNUC__) || defined(__clang__)
     return __builtin_ctzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0;
+    _BitScanForward64(&index, x);
+    return static_cast<int>(index);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -94,15 +103,21 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
 #endif
 }
 
-/// eight bytes as a little-endian word (compilers fold this into one load on
-/// little-endian targets; always inlined, as GCC otherwise calls it in the
-/// number loops)
+/// eight bytes as a little-endian word (a single load on little-endian
+/// targets; always inlined, as GCC otherwise calls it in the number loops)
 JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
 {
+#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+    // the byte order already matches (all MSVC targets are little-endian)
+    std::uint64_t result = 0;
+    std::memcpy(&result, b, sizeof(result));
+    return result;
+#else
     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);
+#endif
 }
 
 /// eight bytes as a little-endian word

single_include/nlohmann/json.hpp

@@ -8793,8 +8793,9 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 #include <cstdint> // uint64_t
-#if !defined(__SIZEOF_INT128__) && defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
-    #include <intrin0.h> // __umulh, _umul128
+#include <cstring> // memcpy
+#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64)) && (!defined(__SIZEOF_INT128__) || (!defined(__GNUC__) && !defined(__clang__)))
+    #include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
 #endif
 
 // #include <nlohmann/detail/macro_scope.hpp>
@@ -8813,6 +8814,10 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
 {
 #if defined(__GNUC__) || defined(__clang__)
     return __builtin_clzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0;
+    _BitScanReverse64(&index, x);
+    return 63 - static_cast<int>(index);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -8832,6 +8837,10 @@ inline int count_trailing_zeros(std::uint64_t x) noexcept
 {
 #if defined(__GNUC__) || defined(__clang__)
     return __builtin_ctzll(x);
+#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
+    unsigned long index = 0;
+    _BitScanForward64(&index, x);
+    return static_cast<int>(index);
 #else
     int n = 0;
     for (int shift = 32; shift != 0; shift >>= 1)
@@ -8879,15 +8888,21 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
 #endif
 }
 
-/// eight bytes as a little-endian word (compilers fold this into one load on
-/// little-endian targets; always inlined, as GCC otherwise calls it in the
-/// number loops)
+/// eight bytes as a little-endian word (a single load on little-endian
+/// targets; always inlined, as GCC otherwise calls it in the number loops)
 JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
 {
+#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
+    // the byte order already matches (all MSVC targets are little-endian)
+    std::uint64_t result = 0;
+    std::memcpy(&result, b, sizeof(result));
+    return result;
+#else
     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);
+#endif
 }
 
 /// eight bytes as a little-endian word

tests/src/unit-class_lexer.cpp

@@ -1792,4 +1792,11 @@ TEST_CASE("string scanning kernels")
         CHECK(nlohmann::detail::count_trailing_zeros(bit) == k);
         CHECK(nlohmann::detail::count_trailing_zeros(bit | (bit << 1u) | 0x8000000000000000u) == k);
     }
+
+    // eight bytes as a little-endian word, at any alignment
+    const unsigned char bytes[16] = {0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF};
+    CHECK(nlohmann::detail::read_eight_bytes(bytes) == 0x0807060504030201u);
+    CHECK(nlohmann::detail::read_eight_bytes(bytes + 1) == 0x0908070605040302u);
+    CHECK(nlohmann::detail::read_eight_bytes(bytes + 8) == 0xFF0F0E0D0C0B0A09u);
+    CHECK(nlohmann::detail::read_eight_bytes(reinterpret_cast<const char*>(bytes) + 3) == 0x0B0A090807060504u);
 }