mirror of https://github.com/python/cpython
bpo-34636: Use fast path for more chars in SRE category macros. (GH-9170)
When handling \s, \d, or \w (and their inverse) escapes in bytes regexes this a small but measurable performance improvement. <!-- issue-number: [bpo-34636](https://www.bugs.python.org/issue34636) --> https://bugs.python.org/issue34636 <!-- /issue-number -->
This commit is contained in:
parent
d13e59c1b5
commit
ec014a101a
|
@ -0,0 +1,2 @@
|
|||
Speed up re scanning of many non-matching characters for \s \w and \d within
|
||||
bytes objects. (microoptimization)
|
|
@ -87,13 +87,13 @@ static const char copyright[] =
|
|||
/* search engine state */
|
||||
|
||||
#define SRE_IS_DIGIT(ch)\
|
||||
((ch) < 128 && Py_ISDIGIT(ch))
|
||||
((ch) <= '9' && Py_ISDIGIT(ch))
|
||||
#define SRE_IS_SPACE(ch)\
|
||||
((ch) < 128 && Py_ISSPACE(ch))
|
||||
((ch) <= ' ' && Py_ISSPACE(ch))
|
||||
#define SRE_IS_LINEBREAK(ch)\
|
||||
((ch) == '\n')
|
||||
#define SRE_IS_WORD(ch)\
|
||||
((ch) < 128 && (Py_ISALNUM(ch) || (ch) == '_'))
|
||||
((ch) <= 'z' && (Py_ISALNUM(ch) || (ch) == '_'))
|
||||
|
||||
static unsigned int sre_lower_ascii(unsigned int ch)
|
||||
{
|
||||
|
|
Loading…
Reference in New Issue