mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 17:08:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

Merged revisions 77241 via svnmerge from

Browse source 
svn+ssh://pythondev@svn.python.org/python/trunk

........
  r77241 | antoine.pitrou | 2010-01-02 22:12:58 +0100 (sam., 02 janv. 2010) | 4 lines

  Issue #7462: Implement the stringlib fast search algorithm for the `rfind`,
  `rindex`, `rsplit` and `rpartition` methods.  Patch by Florent Xicluna.
........
This commit is contained in:
Antoine Pitrou 2010-01-02 21:40:36 +00:00
parent 2952148dd2
commit da2ecaf334
10 changed files with 131 additions and 115 deletions
Download patch file Download diff file Expand all files Collapse all files

112
Objects/stringlib/fastsearch.h
View file

@ -5,7 +5,7 @@
/* 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.htm */
for some more background, see: http://effbot.org/zone/stringlib.htm */
/* 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
@ -16,6 +16,7 @@
#define FAST_COUNT 0
#define FAST_SEARCH 1
#define FAST_RSEARCH 2
Py_LOCAL_INLINE(Py_ssize_t)
fastsearch(const STRINGLIB_CHAR* s, Py_ssize_t n,
@ -41,51 +42,92 @@ fastsearch(const STRINGLIB_CHAR* s, Py_ssize_t n,
if (s[i] == p[0])
count++;
return count;
} else {
} else if (mode == FAST_SEARCH) {
for (i = 0; i < n; i++)
if (s[i] == p[0])
return i;
} else { /* FAST_RSEARCH */
for (i = n - 1; i > -1; 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;
if (mode != FAST_RSEARCH) {
/* create compressed boyer-moore delta 1 table */
/* 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;
}
}
} else { /* FAST_RSEARCH */
/* create compressed boyer-moore delta 1 table */
/* process pattern[0] outside the loop */
mask = (1 << (p[0] & 0x1F));
/* process pattern[:0:-1] */
for (i = mlast; i > 0; i--) {
mask |= (1 << (p[i] & 0x1F));
if (p[i] == p[0])
skip = i - 1;
}
for (i = w; i >= 0; i--) {
if (s[i] == p[0]) {
/* candidate match */
for (j = mlast; j > 0; j--)
if (s[i+j] != p[j])
break;
if (j == 0)
/* got a match! */
return i;
/* miss: check if previous character is part of pattern */
if (!(mask & (1 << (s[i-1] & 0x1F))))
i = i - m;
else
i = i - skip;
} else {
/* skip: check if previous character is part of pattern */
if (!(mask & (1 << (s[i-1] & 0x1F))))
i = i - m;
}
/* 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;
}
}