diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2014-10-10 08:10:46 (GMT) |
|---|---|---|
| committer | Serhiy Storchaka <storchaka@gmail.com> | 2014-10-10 08:10:46 (GMT) |
| commit | 5aa47443c60deb5cafbf6ad195bf49e364cbce4c (patch) | |
| tree | edf801d59d61d818daabdd3d52424eaadf2b34f4 /Modules | |
| parent | 7438e4b56fa6a34a021f11e1220331e841419b96 (diff) | |
| download | cpython-5aa47443c60deb5cafbf6ad195bf49e364cbce4c.zip cpython-5aa47443c60deb5cafbf6ad195bf49e364cbce4c.tar.gz cpython-5aa47443c60deb5cafbf6ad195bf49e364cbce4c.tar.bz2 | |
Issue #22584: Got rid of character tables in _sre.c and use standard macros
Py_TOLOWER, Py_ISSPACE, etc.
Diffstat (limited to 'Modules')
| -rw-r--r-- | Modules/_sre.c | 40 |
1 files changed, 6 insertions, 34 deletions
diff --git a/Modules/_sre.c b/Modules/_sre.c index 5c3d105..0dc5212 100644 --- a/Modules/_sre.c +++ b/Modules/_sre.c @@ -97,48 +97,20 @@ static char copyright[] = /* -------------------------------------------------------------------- */ /* search engine state */ -/* default character predicates (run sre_chars.py to regenerate tables) */ - -#define SRE_DIGIT_MASK 1 -#define SRE_SPACE_MASK 2 -#define SRE_LINEBREAK_MASK 4 -#define SRE_ALNUM_MASK 8 -#define SRE_WORD_MASK 16 - -/* FIXME: this assumes ASCII. create tables in init_sre() instead */ - -static char sre_char_info[128] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 6, 2, -2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, -0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 25, 25, 25, 25, 25, 25, 25, 25, -25, 25, 0, 0, 0, 0, 0, 0, 0, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, -24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, -0, 0, 16, 0, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, -24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, 0, 0, 0 }; - -static char sre_char_lower[128] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, -27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, -44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, -61, 62, 63, 64, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, -108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, -122, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, -106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, -120, 121, 122, 123, 124, 125, 126, 127 }; - #define SRE_IS_DIGIT(ch)\ - ((ch) < 128 ? (sre_char_info[(ch)] & SRE_DIGIT_MASK) : 0) + ((ch) < 128 && Py_ISDIGIT(ch)) #define SRE_IS_SPACE(ch)\ - ((ch) < 128 ? (sre_char_info[(ch)] & SRE_SPACE_MASK) : 0) + ((ch) < 128 && Py_ISSPACE(ch)) #define SRE_IS_LINEBREAK(ch)\ - ((ch) < 128 ? (sre_char_info[(ch)] & SRE_LINEBREAK_MASK) : 0) + ((ch) == '\n') #define SRE_IS_ALNUM(ch)\ - ((ch) < 128 ? (sre_char_info[(ch)] & SRE_ALNUM_MASK) : 0) + ((ch) < 128 && Py_ISALNUM(ch)) #define SRE_IS_WORD(ch)\ - ((ch) < 128 ? (sre_char_info[(ch)] & SRE_WORD_MASK) : 0) + ((ch) < 128 && (Py_ISALNUM(ch) || (ch) == '_')) static unsigned int sre_lower(unsigned int ch) { - return ((ch) < 128 ? (unsigned int)sre_char_lower[ch] : ch); + return ((ch) < 128 ? Py_TOLOWER(ch) : ch); } /* locale-specific character predicates */ |