mirror of
https://github.com/python/cpython.git
synced 2025-09-26 18:29:57 +00:00
needforspeed: stringlib refactoring (in progress)
This commit is contained in:
Fredrik Lundh
parent
877ab9bc23
commit
a50d201bd9
4 changed files with 111 additions and 179 deletions
5
Objects/stringlib/README.txt
Normal file
5
Objects/stringlib/README.txt
Normal file
|
|
@ -0,0 +1,5 @@
|
||||||
|
bits shared by the stringobject and unicodeobject implementations (and
|
||||||
|
possibly other modules, in a not too distant future).
|
||||||
|
|
||||||
|
the stuff in here is included into relevant places; see the individual
|
||||||
|
source files for details.
|
||||||
97
Objects/stringlib/fastsearch.h
Normal file
97
Objects/stringlib/fastsearch.h
Normal file
|
|
@ -0,0 +1,97 @@
|
||||||
|
/* stringlib: fastsearch implementation */
|
||||||
|
|
||||||
|
#ifndef STRINGLIB_FASTSEARCH_H
|
||||||
|
#define STRINGLIB_FASTSEARCH_H
|
||||||
|
|
||||||
|
/* fast search/count implementation, based on a mix between boyer-
|
||||||
|
moore and horspool, with a few more bells and whistles on the top.
|
||||||
|
for some more background, see: http://effbot.org/stringlib */
|
||||||
|
|
||||||
|
/* note: fastsearch may access s[n], which isn't a problem when using
|
||||||
|
Python's ordinary string types, but may cause problems if you're
|
||||||
|
using this code in other contexts. also, the count mode returns -1
|
||||||
|
if there cannot possible be a match in the target string, and 0 if
|
||||||
|
it has actually checked for matches, but didn't find any. callers
|
||||||
|
beware! */
|
||||||
|
|
||||||
|
#define FAST_COUNT 0
|
||||||
|
#define FAST_SEARCH 1
|
||||||
|
|
||||||
|
Py_LOCAL(Py_ssize_t)
|
||||||
|
fastsearch(const STRINGLIB_CHAR* s, Py_ssize_t n,
|
||||||
|
const STRINGLIB_CHAR* p, Py_ssize_t m,
|
||||||
|
int mode)
|
||||||
|
{
|
||||||
|
long mask;
|
||||||
|
Py_ssize_t skip, count = 0;
|
||||||
|
Py_ssize_t i, j, mlast, w;
|
||||||
|
|
||||||
|
w = n - m;
|
||||||
|
|
||||||
|
if (w < 0)
|
||||||
|
return -1;
|
||||||
|
|
||||||
|
/* look for special cases */
|
||||||
|
if (m <= 1) {
|
||||||
|
if (m <= 0)
|
||||||
|
return -1;
|
||||||
|
/* use special case for 1-character strings */
|
||||||
|
if (mode == FAST_COUNT) {
|
||||||
|
for (i = 0; i < n; i++)
|
||||||
|
if (s[i] == p[0])
|
||||||
|
count++;
|
||||||
|
return count;
|
||||||
|
} else {
|
||||||
|
for (i = 0; i < n; i++)
|
||||||
|
if (s[i] == p[0])
|
||||||
|
return i;
|
||||||
|
}
|
||||||
|
return -1;
|
||||||
|
}
|
||||||
|
|
||||||
|
mlast = m - 1;
|
||||||
|
|
||||||
|
/* create compressed boyer-moore delta 1 table */
|
||||||
|
skip = mlast - 1;
|
||||||
|
/* process pattern[:-1] */
|
||||||
|
for (mask = i = 0; i < mlast; i++) {
|
||||||
|
mask |= (1 << (p[i] & 0x1F));
|
||||||
|
if (p[i] == p[mlast])
|
||||||
|
skip = mlast - i - 1;
|
||||||
|
}
|
||||||
|
/* process pattern[-1] outside the loop */
|
||||||
|
mask |= (1 << (p[mlast] & 0x1F));
|
||||||
|
|
||||||
|
for (i = 0; i <= w; i++) {
|
||||||
|
/* note: using mlast in the skip path slows things down on x86 */
|
||||||
|
if (s[i+m-1] == p[m-1]) {
|
||||||
|
/* candidate match */
|
||||||
|
for (j = 0; j < mlast; j++)
|
||||||
|
if (s[i+j] != p[j])
|
||||||
|
break;
|
||||||
|
if (j == mlast) {
|
||||||
|
/* got a match! */
|
||||||
|
if (mode != FAST_COUNT)
|
||||||
|
return i;
|
||||||
|
count++;
|
||||||
|
i = i + mlast;
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
/* miss: check if next character is part of pattern */
|
||||||
|
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
||||||
|
i = i + m;
|
||||||
|
else
|
||||||
|
i = i + skip;
|
||||||
|
} else {
|
||||||
|
/* skip: check if next character is part of pattern */
|
||||||
|
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
||||||
|
i = i + m;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (mode != FAST_COUNT)
|
||||||
|
return -1;
|
||||||
|
return count;
|
||||||
|
}
|
||||||
|
|
||||||
|
#endif
|
||||||
|
|
@ -765,102 +765,17 @@ PyString_AsStringAndSize(register PyObject *obj,
|
||||||
}
|
}
|
||||||
|
|
||||||
/* -------------------------------------------------------------------- */
|
/* -------------------------------------------------------------------- */
|
||||||
/* Helpers */
|
/* stringlib components */
|
||||||
|
|
||||||
#define USE_FAST /* experimental fast search implementation */
|
#define USE_FAST
|
||||||
|
|
||||||
/* XXX - this code is copied from unicodeobject.c. we really should
|
#ifdef USE_FAST
|
||||||
refactor the core implementations (see _sre.c for how this can be
|
|
||||||
done), but that'll have to wait -- fredrik */
|
|
||||||
|
|
||||||
/* fast search/count implementation, based on a mix between boyer-
|
#define STRINGLIB_CHAR char
|
||||||
moore and horspool, with a few more bells and whistles on the top.
|
|
||||||
for some more background, see: http://effbot.org/stringlib */
|
|
||||||
|
|
||||||
/* note: fastsearch may access s[n], which isn't a problem when using
|
#include "stringlib/fastsearch.h"
|
||||||
Python's ordinary string types, but may cause problems if you're
|
|
||||||
using this code in other contexts. also, the count mode returns -1
|
|
||||||
if there cannot possibly be a match in the target string, and 0 if
|
|
||||||
it has actually checked for matches, but didn't find any. callers
|
|
||||||
beware! */
|
|
||||||
|
|
||||||
#define FAST_COUNT 0
|
#endif
|
||||||
#define FAST_SEARCH 1
|
|
||||||
|
|
||||||
Py_LOCAL(Py_ssize_t)
|
|
||||||
fastsearch(const char* s, Py_ssize_t n, const char* p, Py_ssize_t m, int mode)
|
|
||||||
{
|
|
||||||
long mask;
|
|
||||||
Py_ssize_t skip, count = 0;
|
|
||||||
Py_ssize_t i, j, mlast, w;
|
|
||||||
|
|
||||||
w = n - m;
|
|
||||||
|
|
||||||
if (w < 0)
|
|
||||||
return -1;
|
|
||||||
|
|
||||||
/* look for special cases */
|
|
||||||
if (m <= 1) {
|
|
||||||
if (m <= 0)
|
|
||||||
return -1;
|
|
||||||
/* use special case for 1-character strings */
|
|
||||||
if (mode == FAST_COUNT) {
|
|
||||||
for (i = 0; i < n; i++)
|
|
||||||
if (s[i] == p[0])
|
|
||||||
count++;
|
|
||||||
return count;
|
|
||||||
} else {
|
|
||||||
for (i = 0; i < n; i++)
|
|
||||||
if (s[i] == p[0])
|
|
||||||
return i;
|
|
||||||
}
|
|
||||||
return -1;
|
|
||||||
}
|
|
||||||
|
|
||||||
mlast = m - 1;
|
|
||||||
|
|
||||||
/* create compressed boyer-moore delta 1 table */
|
|
||||||
skip = mlast - 1;
|
|
||||||
/* process pattern[:-1] */
|
|
||||||
for (mask = i = 0; i < mlast; i++) {
|
|
||||||
mask |= (1 << (p[i] & 0x1F));
|
|
||||||
if (p[i] == p[mlast])
|
|
||||||
skip = mlast - i - 1;
|
|
||||||
}
|
|
||||||
/* process pattern[-1] outside the loop */
|
|
||||||
mask |= (1 << (p[mlast] & 0x1F));
|
|
||||||
|
|
||||||
for (i = 0; i <= w; i++) {
|
|
||||||
/* note: using mlast in the skip path slows things down on x86 */
|
|
||||||
if (s[i+m-1] == p[m-1]) {
|
|
||||||
/* candidate match */
|
|
||||||
for (j = 0; j < mlast; j++)
|
|
||||||
if (s[i+j] != p[j])
|
|
||||||
break;
|
|
||||||
if (j == mlast) {
|
|
||||||
/* got a match! */
|
|
||||||
if (mode != FAST_COUNT)
|
|
||||||
return i;
|
|
||||||
count++;
|
|
||||||
i = i + mlast;
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
/* miss: check if next character is part of pattern */
|
|
||||||
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
|
||||||
i = i + m;
|
|
||||||
else
|
|
||||||
i = i + skip;
|
|
||||||
} else {
|
|
||||||
/* skip: check if next character is part of pattern */
|
|
||||||
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
|
||||||
i = i + m;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if (mode != FAST_COUNT)
|
|
||||||
return -1;
|
|
||||||
return count;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* -------------------------------------------------------------------- */
|
/* -------------------------------------------------------------------- */
|
||||||
/* Methods */
|
/* Methods */
|
||||||
|
|
@ -2416,7 +2331,7 @@ string_count(PyStringObject *self, PyObject *args)
|
||||||
#else
|
#else
|
||||||
r = 0;
|
r = 0;
|
||||||
while (i < m) {
|
while (i < m) {
|
||||||
const char *t
|
const char *t;
|
||||||
if (!memcmp(s+i, sub, n)) {
|
if (!memcmp(s+i, sub, n)) {
|
||||||
r++;
|
r++;
|
||||||
i += n;
|
i += n;
|
||||||
|
|
|
||||||
|
|
@ -3854,94 +3854,9 @@ int PyUnicode_EncodeDecimal(Py_UNICODE *s,
|
||||||
|
|
||||||
/* --- Helpers ------------------------------------------------------------ */
|
/* --- Helpers ------------------------------------------------------------ */
|
||||||
|
|
||||||
/* fast search/count implementation, based on a mix between boyer-
|
#define STRINGLIB_CHAR Py_UNICODE
|
||||||
moore and horspool, with a few more bells and whistles on the top.
|
|
||||||
for some more background, see: http://effbot.org/stringlib */
|
|
||||||
|
|
||||||
/* note: fastsearch may access s[n], which isn't a problem when using
|
#include "stringlib/fastsearch.h"
|
||||||
Python's ordinary string types, but may cause problems if you're
|
|
||||||
using this code in other contexts. also, the count mode returns -1
|
|
||||||
if there cannot possible be a match in the target string, and 0 if
|
|
||||||
it has actually checked for matches, but didn't find any. callers
|
|
||||||
beware! */
|
|
||||||
|
|
||||||
#define FAST_COUNT 0
|
|
||||||
#define FAST_SEARCH 1
|
|
||||||
|
|
||||||
Py_LOCAL(Py_ssize_t)
|
|
||||||
fastsearch(Py_UNICODE* s, Py_ssize_t n, Py_UNICODE* p, Py_ssize_t m, int mode)
|
|
||||||
{
|
|
||||||
long mask;
|
|
||||||
Py_ssize_t skip, count = 0;
|
|
||||||
Py_ssize_t i, j, mlast, w;
|
|
||||||
|
|
||||||
w = n - m;
|
|
||||||
|
|
||||||
if (w < 0)
|
|
||||||
return -1;
|
|
||||||
|
|
||||||
/* look for special cases */
|
|
||||||
if (m <= 1) {
|
|
||||||
if (m <= 0)
|
|
||||||
return -1;
|
|
||||||
/* use special case for 1-character strings */
|
|
||||||
if (mode == FAST_COUNT) {
|
|
||||||
for (i = 0; i < n; i++)
|
|
||||||
if (s[i] == p[0])
|
|
||||||
count++;
|
|
||||||
return count;
|
|
||||||
} else {
|
|
||||||
for (i = 0; i < n; i++)
|
|
||||||
if (s[i] == p[0])
|
|
||||||
return i;
|
|
||||||
}
|
|
||||||
return -1;
|
|
||||||
}
|
|
||||||
|
|
||||||
mlast = m - 1;
|
|
||||||
|
|
||||||
/* create compressed boyer-moore delta 1 table */
|
|
||||||
skip = mlast - 1;
|
|
||||||
/* process pattern[:-1] */
|
|
||||||
for (mask = i = 0; i < mlast; i++) {
|
|
||||||
mask |= (1 << (p[i] & 0x1F));
|
|
||||||
if (p[i] == p[mlast])
|
|
||||||
skip = mlast - i - 1;
|
|
||||||
}
|
|
||||||
/* process pattern[-1] outside the loop */
|
|
||||||
mask |= (1 << (p[mlast] & 0x1F));
|
|
||||||
|
|
||||||
for (i = 0; i <= w; i++) {
|
|
||||||
/* note: using mlast in the skip path slows things down on x86 */
|
|
||||||
if (s[i+m-1] == p[m-1]) {
|
|
||||||
/* candidate match */
|
|
||||||
for (j = 0; j < mlast; j++)
|
|
||||||
if (s[i+j] != p[j])
|
|
||||||
break;
|
|
||||||
if (j == mlast) {
|
|
||||||
/* got a match! */
|
|
||||||
if (mode != FAST_COUNT)
|
|
||||||
return i;
|
|
||||||
count++;
|
|
||||||
i = i + mlast;
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
/* miss: check if next character is part of pattern */
|
|
||||||
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
|
||||||
i = i + m;
|
|
||||||
else
|
|
||||||
i = i + skip;
|
|
||||||
} else {
|
|
||||||
/* skip: check if next character is part of pattern */
|
|
||||||
if (!(mask & (1 << (s[i+m] & 0x1F))))
|
|
||||||
i = i + m;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if (mode != FAST_COUNT)
|
|
||||||
return -1;
|
|
||||||
return count;
|
|
||||||
}
|
|
||||||
|
|
||||||
Py_LOCAL(Py_ssize_t) count(PyUnicodeObject *self,
|
Py_LOCAL(Py_ssize_t) count(PyUnicodeObject *self,
|
||||||
Py_ssize_t start,
|
Py_ssize_t start,
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue