Accumulate number digits while scanning them (#5851)

* Accumulate number digits while scanning them

The contiguous number fast path validated a token byte by byte, copied it
into token_buffer, and then converted it in out-of-line functions that
scanned the digits a second time: parse_float_native() called
parse_float_significand(), which returned its result through memory and
called std::any_of (out of line with GCC) twice per number, and
parse_integer_signed() divided by ten on every digit for its overflow check.

scan_number_bulk_contiguous() now accumulates the significand while it
validates the digits, eight at a time where at least eight bytes remain
(is_eight_digits() and parse_eight_digits(), after fast_float). Floats with
at most 19 digits go straight to decimal_to_float(); integers with at most
18 digits are stored without an overflow check (a narrower number type
still rejects values that do not round-trip). Longer tokens take the
existing path. has_nonzero_digit() is a plain loop and
parse_float_significand() is always inlined, which helps that path.

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

* Skip the digit accumulation checks without exceptions

The section compares error messages from both lexer paths and parses
out-of-range numbers, so it does not compile (the caught exception does not
exist) and would abort with JSON_NOEXCEPTION.

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

* Share the significant-digit loop of the integer part and the fraction

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

---------

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

include/nlohmann/detail/input/number_parse.hpp

@@ -275,13 +275,77 @@ JSON_HEDLEY_ALWAYS_INLINE std::uint32_t parse_eight_digits(std::uint64_t v) noex
     return static_cast<std::uint32_t>(((v & 0x0000FFFF0000FFFFu) * 42949672960001u) >> 32u);
 }
 
-/// whether [first, last) contains a digit other than '0'
-inline bool has_nonzero_digit(const char* first, const char* last) noexcept
+/// whether the eight bytes in @a v (see read_eight_bytes()) are all ASCII
+/// digits (after fast_float)
+JSON_HEDLEY_ALWAYS_INLINE bool is_eight_digits(std::uint64_t v) noexcept
 {
-    return std::any_of(first, last, [](char c) noexcept
+    return ((v & 0xF0F0F0F0F0F0F0F0u) | (((v + 0x0606060606060606u) & 0xF0F0F0F0F0F0F0F0u) >> 4u)) == 0x3333333333333333u;
+}
+
+/*!
+@brief skip the ASCII digits starting at data[i] and accumulate their value
+
+Eight digits are taken at a time while at least eight bytes remain. @a w wraps
+around after 19 digits; the caller only uses it for shorter digit runs.
+
+@return the index of the first byte at or after @a i that is not a digit
+*/
+JSON_HEDLEY_ALWAYS_INLINE std::size_t accumulate_digits(const char* data, std::size_t i, std::size_t avail, std::uint64_t& w) noexcept
+{
+    while (avail - i >= 8)
     {
-        return c != '0';
-    });
+        const std::uint64_t v = read_eight_bytes(data + i);
+        if (!is_eight_digits(v))
+        {
+            break;
+        }
+        w = (w * 100000000u) + parse_eight_digits(v);
+        i += 8;
+    }
+    while (i < avail && data[i] >= '0' && data[i] <= '9')
+    {
+        w = (w * 10u) + static_cast<std::uint64_t>(data[i] - '0');
+        ++i;
+    }
+    return i;
+}
+
+/// whether [first, last) contains a digit other than '0'; a plain loop, as
+/// GCC calls std::any_of out of line even for the usual empty range
+JSON_HEDLEY_ALWAYS_INLINE bool has_nonzero_digit(const char* first, const char* last) noexcept
+{
+    for (; first != last; ++first)
+    {
+        if (*first != '0')
+        {
+            return true;
+        }
+    }
+    return false;
+}
+
+/*!
+@brief accumulate the validated digits [p, last) into @a w, as long as
+       @a remaining digits still fit into it
+
+Eight digits are taken at a time while at least eight remain, and @a remaining
+is decreased by the number of digits taken.
+
+@return a pointer past the last digit taken
+*/
+JSON_HEDLEY_ALWAYS_INLINE const char* accumulate_significant_digits(const char* p, const char* last, int& remaining, std::uint64_t& w) noexcept
+{
+    while (remaining >= 8 && last - p >= 8)
+    {
+        w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
+        p += 8;
+        remaining -= 8;
+    }
+    for (; remaining > 0 && p != last; ++p, --remaining)
+    {
+        w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
+    }
+    return p;
 }
 
 /// the value of the validated exponent digits [+-]?[0-9]+ in [first, last),
@@ -327,7 +391,7 @@ truncated is set.
                                    std::string::npos if there is none
 @param[in] mantissa_end            index of the 'e'/'E', or the token length
 */
-inline float_significand parse_float_significand(const char* first, const char* last,
+JSON_HEDLEY_ALWAYS_INLINE float_significand parse_float_significand(const char* first, const char* last,
         std::size_t decimal_point_position, std::size_t mantissa_end) noexcept
 {
     float_significand s;
@@ -342,16 +406,7 @@ inline float_significand parse_float_significand(const char* first, const char*
     int remaining = 19; // digits that still fit into w
     if (*p != '0') // the integer part is "0" or [1-9][0-9]*
     {
-        while (remaining >= 8 && integer_last - p >= 8)
-        {
-            w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
-            p += 8;
-            remaining -= 8;
-        }
-        for (; remaining > 0 && p != integer_last; ++p, --remaining)
-        {
-            w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
-        }
+        p = accumulate_significant_digits(p, integer_last, remaining, w);
         s.exponent = integer_last - p;
         s.truncated = has_nonzero_digit(p, integer_last);
     }
@@ -370,16 +425,7 @@ inline float_significand parse_float_significand(const char* first, const char*
             s.exponent -= p - zeros;
         }
         const char* const digits = p;
-        while (remaining >= 8 && mantissa_last - p >= 8)
-        {
-            w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
-            p += 8;
-            remaining -= 8;
-        }
-        for (; remaining > 0 && p != mantissa_last; ++p, --remaining)
-        {
-            w = (w * 10u) + static_cast<std::uint64_t>(*p - '0');
-        }
+        p = accumulate_significant_digits(p, mantissa_last, remaining, w);
         s.exponent -= p - digits;
         s.truncated = s.truncated || has_nonzero_digit(p, mantissa_last);
     }