#ifndef FASTFLOAT_PARSE_NUMBER_H #define FASTFLOAT_PARSE_NUMBER_H #include "ascii_number.h" #include "decimal_to_binary.h" #include "digit_comparison.h" #include "float_common.h" #include #include #include #include namespace fast_float { namespace detail { /** * Special case +inf, -inf, nan, infinity, -infinity. * The case comparisons could be made much faster given that we know that the * strings a null-free and fixed. **/ template from_chars_result_t FASTFLOAT_CONSTEXPR14 parse_infnan(UC const *first, UC const *last, T &value, chars_format fmt) noexcept { from_chars_result_t answer{}; answer.ptr = first; answer.ec = std::errc(); // be optimistic // assume first < last, so dereference without checks; bool const minusSign = (*first == UC('-')); // C++17 20.19.3.(7.1) explicitly forbids '+' sign here if ((*first == UC('-')) || (uint64_t(fmt & chars_format::allow_leading_plus) && (*first == UC('+')))) { ++first; } if (last - first >= 3) { if (fastfloat_strncasecmp(first, str_const_nan(), 3)) { answer.ptr = (first += 3); value = minusSign ? -std::numeric_limits::quiet_NaN() : std::numeric_limits::quiet_NaN(); // Check for possible nan(n-char-seq-opt), C++17 20.19.3.7, // C11 7.20.1.3.3. At least MSVC produces nan(ind) and nan(snan). if (first != last && *first == UC('(')) { for (UC const *ptr = first + 1; ptr != last; ++ptr) { if (*ptr == UC(')')) { answer.ptr = ptr + 1; // valid nan(n-char-seq-opt) break; } else if (!((UC('a') <= *ptr && *ptr <= UC('z')) || (UC('A') <= *ptr && *ptr <= UC('Z')) || (UC('0') <= *ptr && *ptr <= UC('9')) || *ptr == UC('_'))) break; // forbidden char, not nan(n-char-seq-opt) } } return answer; } if (fastfloat_strncasecmp(first, str_const_inf(), 3)) { if ((last - first >= 8) && fastfloat_strncasecmp(first + 3, str_const_inf() + 3, 5)) { answer.ptr = first + 8; } else { answer.ptr = first + 3; } value = minusSign ? -std::numeric_limits::infinity() : std::numeric_limits::infinity(); return answer; } } answer.ec = std::errc::invalid_argument; return answer; } /** * Returns true if the floating-pointing rounding mode is to 'nearest'. * It is the default on most system. This function is meant to be inexpensive. * Credit : @mwalcott3 * * If FASTFLOAT_ROUNDS_TO_NEAREST is defined, we trust the user that the * rounding mode is always 'nearest' and we skip the check (see README). */ fastfloat_really_inline bool rounds_to_nearest() noexcept { // https://lemire.me/blog/2020/06/26/gcc-not-nearest/ #if (FLT_EVAL_METHOD != 1) && (FLT_EVAL_METHOD != 0) // The arithmetic may be carried out with excess precision (e.g., x87): // Clinger's fast path could then round twice. FASTFLOAT_ROUNDS_TO_NEAREST // does not change this. return false; #elif defined(FASTFLOAT_ROUNDS_TO_NEAREST) return true; #else // See // A fast function to check your floating-point rounding mode // https://lemire.me/blog/2022/11/16/a-fast-function-to-check-your-floating-point-rounding-mode/ // // This function is meant to be equivalent to : // prior: #include // return fegetround() == FE_TONEAREST; // However, it is expected to be much faster than the fegetround() // function call. // // The volatile keyword prevents the compiler from computing the function // at compile-time. // There might be other ways to prevent compile-time optimizations (e.g., // asm). The value does not need to be std::numeric_limits::min(), any // small value so that 1 + x should round to 1 would do (after accounting for // excess precision, as in 387 instructions). static float volatile fmin = (std::numeric_limits::min)(); float fmini = fmin; // we copy it so that it gets loaded at most once. // // Explanation: // Only when fegetround() == FE_TONEAREST do we have that // fmin + 1.0f == 1.0f - fmin. // // FE_UPWARD: // fmin + 1.0f > 1 // 1.0f - fmin == 1 // // FE_DOWNWARD or FE_TOWARDZERO: // fmin + 1.0f == 1 // 1.0f - fmin < 1 // // Note: This may fail to be accurate if fast-math has been // enabled, as rounding conventions may not apply. #ifdef FASTFLOAT_VISUAL_STUDIO #pragma warning(push) // todo: is there a VS warning? // see // https://stackoverflow.com/questions/46079446/is-there-a-warning-for-floating-point-equality-checking-in-visual-studio-2013 #elif defined(__clang__) #pragma clang diagnostic push #pragma clang diagnostic ignored "-Wfloat-equal" #elif defined(__GNUC__) #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wfloat-equal" #endif return (fmini + 1.0f == 1.0f - fmini); #ifdef FASTFLOAT_VISUAL_STUDIO #pragma warning(pop) #elif defined(__clang__) #pragma clang diagnostic pop #elif defined(__GNUC__) #pragma GCC diagnostic pop #endif #endif // FASTFLOAT_ROUNDS_TO_NEAREST } } // namespace detail template struct from_chars_caller { template fastfloat_clang_really_inline FASTFLOAT_CONSTEXPR20 static from_chars_result_t call(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { return from_chars_advanced(first, last, value, options); } }; #ifdef __STDCPP_FLOAT32_T__ template <> struct from_chars_caller { template FASTFLOAT_CONSTEXPR20 static from_chars_result_t call(UC const *first, UC const *last, std::float32_t &value, parse_options_t options) noexcept { // if std::float32_t is defined, and we are in C++23 mode; macro set for // float32; set value to float due to equivalence between float and // float32_t float val = 0.0f; auto ret = from_chars_advanced(first, last, val, options); // If no characters match the pattern, value must be left unmodified. if (ret.ec != std::errc::invalid_argument) { value = val; } return ret; } }; #endif #ifdef __STDCPP_FLOAT64_T__ template <> struct from_chars_caller { template FASTFLOAT_CONSTEXPR20 static from_chars_result_t call(UC const *first, UC const *last, std::float64_t &value, parse_options_t options) noexcept { // if std::float64_t is defined, and we are in C++23 mode; macro set for // float64; set value as double due to equivalence between double and // float64_t double val = 0.0; auto ret = from_chars_advanced(first, last, val, options); // If no characters match the pattern, value must be left unmodified. if (ret.ec != std::errc::invalid_argument) { value = val; } return ret; } }; #endif #ifdef __clang__ // Parser instantiated for a format fixed at compile time, so that every test // on the format folds away inside it. GCC gets the same effect by inlining the // whole parser into each caller, where the format is a constant; clang keeps // it out of line and would otherwise re-test each format flag per conversion. template FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_fixed_format(UC const *first, UC const *last, T &value) noexcept { return from_chars_caller::call(first, last, value, parse_options_t(Fmt)); } #endif template FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars(UC const *first, UC const *last, T &value, chars_format fmt /*= chars_format::general*/) noexcept { #ifdef __clang__ if (fmt == chars_format::general) { return from_chars_fixed_format(first, last, value); } #endif return from_chars_caller::call(first, last, value, parse_options_t(fmt)); } template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 bool clinger_fast_path_impl(uint64_t mantissa, int64_t exponent, bool is_negative, T &value) noexcept { // The implementation of the Clinger's fast path is convoluted because // we want round-to-nearest in all cases, irrespective of the rounding mode // selected on the thread. // We proceed optimistically, assuming that detail::rounds_to_nearest() // returns true. if (binary_format::min_exponent_fast_path() <= exponent && exponent <= binary_format::max_exponent_fast_path() && mantissa <= binary_format::max_mantissa_fast_path()) { // The mantissa bound above is a necessary condition for BOTH branches // below: the rounding-mode-dependent branch checks the tighter // max_mantissa_fast_path(exponent) <= max_mantissa_fast_path(). Testing // it before detail::rounds_to_nearest() spares long-mantissa inputs // (which can never take the fast path) the volatile-float probe. // // Unfortunately, the conventional Clinger's fast path is only possible // when the system rounds to the nearest float. // // We expect the next branch to almost always be selected. // We could check it first (before the previous branch), but // there might be performance advantages at having the check // be last. if (!cpp20_and_in_constexpr() && detail::rounds_to_nearest()) { // We have that fegetround() == FE_TONEAREST. // Next is Clinger's fast path. value = T(mantissa); if (exponent < 0) { value = value / binary_format::exact_power_of_ten(-exponent); } else { value = value * binary_format::exact_power_of_ten(exponent); // Only std::float16_t can overflow here (e.g., "656e2"); let the // slow path report result_out_of_range. if (binary_format::fast_path_can_overflow() && value > (std::numeric_limits::max)()) { return false; } } if (is_negative) { value = -value; } return true; } else { // We do not have that fegetround() == FE_TONEAREST. // Next is a modified Clinger's fast path, inspired by Jakub JelĂ­nek's // proposal if (exponent >= 0 && mantissa <= binary_format::max_mantissa_fast_path(exponent)) { #if defined(__clang__) || defined(FASTFLOAT_32BIT) // Clang may map 0 to -0.0 when fegetround() == FE_DOWNWARD if (mantissa == 0) { value = is_negative ? T(-0.) : T(0.); return true; } #endif value = T(mantissa) * binary_format::exact_power_of_ten(exponent); if (is_negative) { value = -value; } return true; } } } return false; } /** * This function overload takes parsed_number_string_t structure that is created * and populated either by from_chars_advanced function taking chars range and * parsing options or other parsing custom function implemented by user. */ template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_advanced(parsed_number_string_t &pns, T &value) noexcept { static_assert(is_supported_float_type::value, "only some floating-point types are supported"); static_assert(is_supported_char_type::value, "only char, wchar_t, char16_t and char32_t are supported"); from_chars_result_t answer; answer.ec = std::errc(); // be optimistic answer.ptr = pns.lastmatch; if (!pns.too_many_digits && clinger_fast_path_impl(pns.mantissa, pns.exponent, pns.negative, value)) return answer; adjusted_mantissa am = compute_float>(pns.exponent, pns.mantissa); if (pns.too_many_digits && am.power2 >= 0) { if (am != compute_float>(pns.exponent, pns.mantissa + 1)) { am = compute_error>(pns.exponent, pns.mantissa); } } // If we called compute_float>(pns.exponent, pns.mantissa) // and we have an invalid power (am.power2 < 0), then we need to go the long // way around again. This is very uncommon. if (am.power2 < 0) { am = digit_comp(pns, am); } to_float(pns.negative, am, value); // Test for over/underflow. if ((pns.mantissa != 0 && am.mantissa == 0 && am.power2 == 0) || am.power2 == binary_format::infinite_power()) { answer.ec = std::errc::result_out_of_range; } return answer; } // Slow path: re-parse materializing the integer/fraction spans the hot no-span // parse skipped, then run the full algorithm. The two callers reach it only // through a fastfloat_unlikely branch, so the optimizer keeps this re-parse off // the hot path on its own (no function-level noinline needed). // from_chars_advanced already handles both the too_many_digits disambiguation // and the am.power2<0 digit_comp recompute, so both slow branches collapse to // one helper call. template FASTFLOAT_CONSTEXPR20 from_chars_result_t parse_number_slow_path(UC const *first, UC const *last, T &value, parse_options_t options, bool bjf) noexcept { parsed_number_string_t pns = bjf ? parse_number_string_impl(first, last, options, true) : parse_number_string_impl(first, last, options, true); return from_chars_advanced(pns, value); } // Cold: the whole chars_format::javascript conversion. Kept out of line and out // of from_chars_float_advanced so the common frame holds neither the javascript // parser body nor a call that would force the parsed number string onto the // stack. Mirrors the main path, only with the javascript parser. template fastfloat_never_inline FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_float_javascript(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { chars_format const fmt = detail::adjust_for_feature_macros(options.format); if (uint64_t(fmt & chars_format::skip_white_space)) { while ((first != last) && fast_float::is_space(*first)) { first++; } } from_chars_result_t answer; answer.ec = std::errc::invalid_argument; answer.ptr = first; if (first == last) { return answer; } parsed_number_string_t pns = parse_number_string_javascript(first, last, options, true); if (!pns.valid) { if (uint64_t(fmt & chars_format::no_infnan)) { return answer; } return detail::parse_infnan(first, last, value, fmt); } return from_chars_advanced(pns, value); } template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_float_advanced(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { static_assert(is_supported_float_type::value, "only some floating-point types are supported"); static_assert(is_supported_char_type::value, "only char, wchar_t, char16_t and char32_t are supported"); chars_format const fmt = detail::adjust_for_feature_macros(options.format); // Leave for the javascript conversion before anything else is live, so this // compiles to a tail call and the common path keeps its registers. The cold // function repeats the leading-whitespace and empty-input handling below. // See the comment on -Wc++20-extensions further down in this function. #ifdef __clang__ #pragma clang diagnostic push #if (!defined(__APPLE_CC__) && __clang_major__ >= 10) || (__clang_major__ >= 13) #pragma clang diagnostic ignored "-Wc++20-extensions" #endif #endif if fastfloat_unlikely (uint64_t(fmt & detail::basic_javascript_fmt)) { return from_chars_float_javascript(first, last, value, options); } #ifdef __clang__ #pragma clang diagnostic pop #endif from_chars_result_t answer; if (uint64_t(fmt & chars_format::skip_white_space)) { while ((first != last) && fast_float::is_space(*first)) { first++; } } if (first == last) { answer.ec = std::errc::invalid_argument; answer.ptr = first; return answer; } bool const bjf = uint64_t(fmt & detail::basic_json_fmt) != 0; // Fast path: parse WITHOUT materializing the integer/fraction spans (read // only by the rare slow paths). Skipping their stores keeps the fat // parsed_number_string_t off the hot path. store_spans is a runtime argument, // so this reuses the single parse_number_string_impl instantiation. parsed_number_string_t pns = bjf ? parse_number_string_impl(first, last, options, false) : parse_number_string_impl(first, last, options, false); if (!pns.valid) { if (uint64_t(fmt & chars_format::no_infnan)) { answer.ec = std::errc::invalid_argument; answer.ptr = first; return answer; } else { return detail::parse_infnan(first, last, value, fmt); } } // Slow path A (rare): > 19 significant digits. The no-span parse left the // mantissa un-truncated and skipped the span-based recompute; the cold helper // re-parses with spans and runs the full algorithm. // // We have to disable -Wc++20-extensions for the [[unlikely]] attribute // See comment for @jwakely at // https://github.com/fastfloat/fast_float/pull/387#discussion_r3366943539 // This is unfortunate. #ifdef __clang__ #pragma clang diagnostic push #if (!defined(__APPLE_CC__) && __clang_major__ >= 10) || (__clang_major__ >= 13) #pragma clang diagnostic ignored "-Wc++20-extensions" #endif #endif if fastfloat_unlikely (pns.too_many_digits) { return parse_number_slow_path(first, last, value, options, bjf); } answer.ec = std::errc(); // be optimistic answer.ptr = pns.lastmatch; if (clinger_fast_path_impl(pns.mantissa, pns.exponent, pns.negative, value)) { return answer; } adjusted_mantissa am = compute_float>(pns.exponent, pns.mantissa); // Slow path B (rare): Eisel-Lemire could not resolve; digit_comp needs the // integer/fraction spans. Route to the cold helper (clinger there is a // dead-effect since it already failed here; the cold re-parse + digit_comp // via from_chars_advanced reproduces this branch). if fastfloat_unlikely (am.power2 < 0) { return parse_number_slow_path(first, last, value, options, bjf); } to_float(pns.negative, am, value); // Test for over/underflow. Marked unlikely so that clang keeps it as a // branch instead of folding it into a chain of conditional moves that // every conversion pays for. if fastfloat_clang_unlikely ((pns.mantissa != 0 && am.mantissa == 0 && am.power2 == 0) || am.power2 == binary_format::infinite_power()) { answer.ec = std::errc::result_out_of_range; } #ifdef __clang__ #pragma clang diagnostic pop #endif return answer; } template FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars(UC const *first, UC const *last, T &value, int base) noexcept { static_assert(is_supported_integer_type::value, "only integer types are supported"); static_assert(is_supported_char_type::value, "only char, wchar_t, char16_t and char32_t are supported"); parse_options_t options; options.base = base; return from_chars_advanced(first, last, value, options); } template FASTFLOAT_CONSTEXPR20 typename std::enable_if::value, T>::type integer_times_pow10(uint64_t mantissa, int decimal_exponent) noexcept { T value; if (clinger_fast_path_impl(mantissa, decimal_exponent, false, value)) return value; adjusted_mantissa am = compute_float>(decimal_exponent, mantissa); to_float(false, am, value); return value; } template FASTFLOAT_CONSTEXPR20 typename std::enable_if::value, T>::type integer_times_pow10(int64_t mantissa, int decimal_exponent) noexcept { const bool is_negative = mantissa < 0; // Negate as unsigned: -mantissa overflows for the most negative int64_t. const uint64_t m = is_negative ? uint64_t(0) - static_cast(mantissa) : static_cast(mantissa); T value; if (clinger_fast_path_impl(m, decimal_exponent, is_negative, value)) return value; adjusted_mantissa am = compute_float>(decimal_exponent, m); to_float(is_negative, am, value); return value; } FASTFLOAT_CONSTEXPR20 inline double integer_times_pow10(uint64_t mantissa, int decimal_exponent) noexcept { return integer_times_pow10(mantissa, decimal_exponent); } FASTFLOAT_CONSTEXPR20 inline double integer_times_pow10(int64_t mantissa, int decimal_exponent) noexcept { return integer_times_pow10(mantissa, decimal_exponent); } // the following overloads are here to avoid surprising ambiguity for int, // unsigned, etc. template FASTFLOAT_CONSTEXPR20 typename std::enable_if< is_supported_float_type::value && std::is_integral::value && sizeof(Int) <= sizeof(uint64_t) && !std::is_signed::value, T>::type integer_times_pow10(Int mantissa, int decimal_exponent) noexcept { return integer_times_pow10(static_cast(mantissa), decimal_exponent); } template FASTFLOAT_CONSTEXPR20 typename std::enable_if< is_supported_float_type::value && std::is_integral::value && sizeof(Int) <= sizeof(int64_t) && std::is_signed::value, T>::type integer_times_pow10(Int mantissa, int decimal_exponent) noexcept { return integer_times_pow10(static_cast(mantissa), decimal_exponent); } template FASTFLOAT_CONSTEXPR20 typename std::enable_if::value && sizeof(Int) <= sizeof(uint64_t) && !std::is_signed::value, double>::type integer_times_pow10(Int mantissa, int decimal_exponent) noexcept { return integer_times_pow10(static_cast(mantissa), decimal_exponent); } template FASTFLOAT_CONSTEXPR20 typename std::enable_if::value && sizeof(Int) <= sizeof(int64_t) && std::is_signed::value, double>::type integer_times_pow10(Int mantissa, int decimal_exponent) noexcept { return integer_times_pow10(static_cast(mantissa), decimal_exponent); } template FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_int_advanced(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { static_assert(is_supported_integer_type::value, "only integer types are supported"); static_assert(is_supported_char_type::value, "only char, wchar_t, char16_t and char32_t are supported"); chars_format const fmt = detail::adjust_for_feature_macros(options.format); int const base = options.base; from_chars_result_t answer; if (uint64_t(fmt & chars_format::skip_white_space)) { while ((first != last) && fast_float::is_space(*first)) { first++; } } if (first == last || base < 2 || base > 36) { answer.ec = std::errc::invalid_argument; answer.ptr = first; return answer; } return parse_int_string(first, last, value, options); } template struct from_chars_advanced_caller { static_assert(TypeIx > 0, "unsupported type"); }; template <> struct from_chars_advanced_caller<1> { template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 static from_chars_result_t call(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { return from_chars_float_advanced(first, last, value, options); } }; template <> struct from_chars_advanced_caller<2> { template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 static from_chars_result_t call(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { return from_chars_int_advanced(first, last, value, options); } }; template fastfloat_really_inline FASTFLOAT_CONSTEXPR20 from_chars_result_t from_chars_advanced(UC const *first, UC const *last, T &value, parse_options_t options) noexcept { return from_chars_advanced_caller< size_t(is_supported_float_type::value) + 2 * size_t(is_supported_integer_type::value)>::call(first, last, value, options); } } // namespace fast_float #endif