xenia/kakoune
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Avoid iswlower, iswupper, towlower and towupper for ascii codepoints

Browse Source 
Avoid the costly shared object function call when most codepoints
will be ascii.

The regex benchmark gets a nice speedup:

Regex                                   Before     After
--------------------------------------+----------+---------
'Twain'                               |    25 ms | 15 ms
'(?i)Twain'                           |    74 ms | 57 ms
'[a-z]shing'                          |   323 ms | 303 ms
'Huck[a-zA-Z]+|Saw[a-zA-Z]+'          |    26 ms | 17 ms
'\b\w+nn\b'                           |   424 ms | 393 ms
'[a-q][^u-z]{13}x'                    |   869 ms | 815 ms
'Tom|Sawyer|Huckleberry|Finn'         |    33 ms | 24 ms
'(?i)Tom|Sawyer|Huckleberry|Finn'     |   319 ms | 281 ms
'.{0,2}(Tom|Sawyer|Huckleberry|Finn)' |  1294 ms | 1293 ms
'.{2,4}(Tom|Sawyer|Huckleberry|Finn)' |  1470 ms | 1429 ms
'Tom.{10,25}river|river.{10,25}Tom'   |    69 ms | 61 ms
'[a-zA-Z]+ing'                        |   447 ms | 408 ms
'\s[a-zA-Z]{0,12}ing\s'               |   539 ms | 543 ms
'([A-Za-z]awyer|[A-Za-z]inn)\s'       |   588 ms | 552 ms
'["'][^"']{0,30}[?!\.]["']'           |    92 ms | 81 ms
This commit is contained in:
Maxime Coste 2024-02-06 22:13:57 +11:00
parent 04a96b059f
commit 3ef68188b4
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/unicode.hh
View File

@ -124,18 +124,18 @@ inline CharCategories categorize(Codepoint c, ConstArrayView<Codepoint> extra_wo
return CharCategories::Punctuation; return CharCategories::Punctuation;
} }
inline Codepoint to_lower(Codepoint cp) noexcept { return towlower((wchar_t)cp); }
inline Codepoint to_upper(Codepoint cp) noexcept { return towupper((wchar_t)cp); }
inline bool is_lower(Codepoint cp) noexcept { return iswlower((wchar_t)cp); }
inline bool is_upper(Codepoint cp) noexcept { return iswupper((wchar_t)cp); }
inline char to_lower(char c) noexcept { return c >= 'A' and c <= 'Z' ? c - 'A' + 'a' : c; } inline char to_lower(char c) noexcept { return c >= 'A' and c <= 'Z' ? c - 'A' + 'a' : c; }
inline char to_upper(char c) noexcept { return c >= 'a' and c <= 'z' ? c - 'a' + 'A' : c; } inline char to_upper(char c) noexcept { return c >= 'a' and c <= 'z' ? c - 'a' + 'A' : c; }
inline bool is_lower(char c) noexcept { return c >= 'a' and c <= 'z'; } inline bool is_lower(char c) noexcept { return c >= 'a' and c <= 'z'; }
inline bool is_upper(char c) noexcept { return c >= 'A' and c <= 'Z'; } inline bool is_upper(char c) noexcept { return c >= 'A' and c <= 'Z'; }
inline Codepoint to_lower(Codepoint cp) noexcept { return cp < 128 ? (Codepoint)to_lower((char)cp) : towlower((wchar_t)cp); }
inline Codepoint to_upper(Codepoint cp) noexcept { return cp < 128 ? (Codepoint)to_upper((char)cp) : towupper((wchar_t)cp); }
inline bool is_lower(Codepoint cp) noexcept { return cp < 128 ? is_lower((char)cp) : iswlower((wchar_t)cp); }
inline bool is_upper(Codepoint cp) noexcept { return cp < 128 ? is_upper((char)cp) : iswupper((wchar_t)cp); }
} }
#endif // unicode_hh_INCLUDED #endif // unicode_hh_INCLUDED