On Fri, Apr 25, 2025 at 9:47 PM Jonathan Wakely <jwak...@redhat.com> wrote:
> This will hardly make a dent in the very slow compile times for <regex>
> but it seems worth doing anyway.
>
> libstdc++-v3/ChangeLog:
>
> * include/bits/regex_compiler.h (_AnyMatcher::operator()):
> Replace tag dispatching with 'if constexpr'.
> (_AnyMatcher::_M_apply): Remove both overloads.
> (_BracketMatcher::operator(), _BracketMatcher::_M_ready):
> Replace tag dispatching with 'if constexpr'.
> (_BracketMatcher::_M_apply(_CharT, true_type)): Remove.
> (_BracketMatcher::_M_apply(_CharT, false_type)): Remove second
> parameter.
> (_BracketMatcher::_M_make_cache): Remove both overloads.
> * include/bits/regex_compiler.tcc (_BracketMatcher::_M_apply):
> Remove second parameter.
> ---
>
> Tested x86_64-linux.
>
> libstdc++-v3/include/bits/regex_compiler.h | 59 +++++++++-----------
> libstdc++-v3/include/bits/regex_compiler.tcc | 2 +-
> 2 files changed, 26 insertions(+), 35 deletions(-)
>
> diff --git a/libstdc++-v3/include/bits/regex_compiler.h
> b/libstdc++-v3/include/bits/regex_compiler.h
> index f24c7e3baa6..3931790091a 100644
> --- a/libstdc++-v3/include/bits/regex_compiler.h
> +++ b/libstdc++-v3/include/bits/regex_compiler.h
> @@ -376,26 +376,21 @@ namespace __detail
>
> bool
> operator()(_CharT __ch) const
> - { return _M_apply(__ch, typename is_same<_CharT, char>::type()); }
> -
> - bool
> - _M_apply(_CharT __ch, true_type) const
> {
> +#pragma GCC diagnostic push
> +#pragma GCC diagnostic ignored "-Wc++17-extensions" // if constexpr
> auto __c = _M_translator._M_translate(__ch);
> auto __n = _M_translator._M_translate('\n');
> auto __r = _M_translator._M_translate('\r');
> - return __c != __n && __c != __r;
> - }
> -
> - bool
> - _M_apply(_CharT __ch, false_type) const
> - {
> - auto __c = _M_translator._M_translate(__ch);
> - auto __n = _M_translator._M_translate('\n');
> - auto __r = _M_translator._M_translate('\r');
> - auto __u2028 = _M_translator._M_translate(u'\u2028');
> - auto __u2029 = _M_translator._M_translate(u'\u2029');
> - return __c != __n && __c != __r && __c != __u2028 && __c !=
> __u2029;
>
Could we implement this as, to avoid calling _M_translate when not
necessary?
```
if (__c == __n || __c == __r)
return false;
if constexpr (!is_same<_CharT, char>::value)
{
auto __ls = _M_translator._M_translate(u'\u2028'); // line sep
auto __ps = _M_translator._M_translate(u'\u2029'); // para sep
return __c != __ls && __c != __ps;
}
return true;
```
> + if constexpr (is_same<_CharT, char>::value)
> + return __c != __n && __c != __r;
> + else
> + {
> + auto __ls = _M_translator._M_translate(u'\u2028'); // line sep
> + auto __ps = _M_translator._M_translate(u'\u2029'); // para sep
> + return __c != __n && __c != __r && __c != __ls && __c != __ps;
> + }
> +#pragma GCC diagnostic pop
> }
>
> _TransT _M_translator;
> @@ -440,8 +435,14 @@ namespace __detail
> bool
> operator()(_CharT __ch) const
> {
> +#pragma GCC diagnostic push
> +#pragma GCC diagnostic ignored "-Wc++17-extensions" // if constexpr
> _GLIBCXX_DEBUG_ASSERT(_M_is_ready);
> - return _M_apply(__ch, _UseCache());
> + if constexpr (_UseCache::value)
> + if (!(__ch & 0x80)) [[__likely__]]
> + return _M_cache[static_cast<_UnsignedCharT>(__ch)];
> + return _M_apply(__ch);
> +#pragma GCC diagnostic pop
> }
>
> void
> @@ -509,11 +510,16 @@ namespace __detail
> void
> _M_ready()
> {
> +#pragma GCC diagnostic push
> +#pragma GCC diagnostic ignored "-Wc++17-extensions" // if constexpr
> std::sort(_M_char_set.begin(), _M_char_set.end());
> auto __end = std::unique(_M_char_set.begin(), _M_char_set.end());
> _M_char_set.erase(__end, _M_char_set.end());
> - _M_make_cache(_UseCache());
> + if constexpr (_UseCache::value)
> + for (unsigned __i = 0; __i < 128; __i++) // Only cache 7-bit
> chars
> + _M_cache[__i] = _M_apply(static_cast<_CharT>(__i));
> _GLIBCXX_DEBUG_ONLY(_M_is_ready = true);
> +#pragma GCC diagnostic pop
> }
>
> private:
> @@ -531,22 +537,7 @@ namespace __detail
> using _UnsignedCharT = typename std::make_unsigned<_CharT>::type;
>
> bool
> - _M_apply(_CharT __ch, false_type) const;
> -
> - bool
> - _M_apply(_CharT __ch, true_type) const
> - { return _M_cache[static_cast<_UnsignedCharT>(__ch)]; }
> -
> - void
> - _M_make_cache(true_type)
> - {
> - for (unsigned __i = 0; __i < _M_cache.size(); __i++)
> - _M_cache[__i] = _M_apply(static_cast<_CharT>(__i), false_type());
> - }
> -
> - void
> - _M_make_cache(false_type)
> - { }
> + _M_apply(_CharT __ch) const;
>
> private:
> _GLIBCXX_STD_C::vector<_CharT> _M_char_set;
> diff --git a/libstdc++-v3/include/bits/regex_compiler.tcc
> b/libstdc++-v3/include/bits/regex_compiler.tcc
> index cd0db2761b5..59b79fdd106 100644
> --- a/libstdc++-v3/include/bits/regex_compiler.tcc
> +++ b/libstdc++-v3/include/bits/regex_compiler.tcc
> @@ -598,7 +598,7 @@ namespace __detail
> template<typename _TraitsT, bool __icase, bool __collate>
> bool
> _BracketMatcher<_TraitsT, __icase, __collate>::
> - _M_apply(_CharT __ch, false_type) const
> + _M_apply(_CharT __ch) const
> {
> return [this, __ch]
> {
> --
> 2.49.0
>
>
