@matheusbsbs / matheus-bagliano / commits / 8c6abbcd27

pathspec: apply "*.c" optimization from exclude

When a pattern contains only a single asterisk as wildcard, e.g. "foo*bar", after literally comparing the leading part "foo" with the string, we can compare the tail of the string and make sure it matches "bar", instead of running fnmatch() on "*bar" against the remainder of the string. -O2 build on linux-2.6, without the patch: $ time git rev-list --quiet HEAD -- '*.c' real 0m40.770s user 0m40.290s sys 0m0.256s With the patch $ time ~/w/git/git rev-list --quiet HEAD -- '*.c' real 0m34.288s user 0m33.997s sys 0m0.205s The above command is not supposed to be widely popular. It's chosen because it exercises pathspec matching a lot. The point is it cuts down matching time for popular patterns like *.c, which could be used as pathspec in other places. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Nguyễn Thái Ngọc Duy committed Nov 24, 2012 at 11:33 UTC 8c6abbcd2720dd80b1c9b6db8104c4dcc7cba6c7

4 files changed +24 -4

cache.h

@@ -473,6 +473,8 @@ extern int index_name_is_other(const struct index_state *, const char *, int);

473 extern int ie_match_stat(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);

474 extern int ie_modified(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);

475

476 +#define PATHSPEC_ONESTAR 1 /* the pathspec pattern sastisfies GFNM_ONESTAR */

477 +

478 struct pathspec {

479 const char **raw; /* get_pathspec() result, not freed by free_pathspec() */

480 int nr;

@@ -483,6 +485,7 @@ struct pathspec {

485 const char *match;

486 int len;

487 int nowildcard_len;

488 + int flags;

489 } *items;

490 };

491

dir.c

+16 -2

@@ -46,6 +46,13 @@ inline int git_fnmatch(const char *pattern, const char *string,

46 pattern += prefix;

47 string += prefix;

48 }

49 + if (flags & GFNM_ONESTAR) {

50 + int pattern_len = strlen(++pattern);

51 + int string_len = strlen(string);

52 + return string_len < pattern_len ||

53 + strcmp(pattern,

54 + string + string_len - pattern_len);

55 + }

56 return fnmatch(pattern, string, fnm_flags);

57 }

@@ -246,7 +253,9 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,

253 }

254

255 if (item->nowildcard_len < item->len &&

249 - !git_fnmatch(match, name, 0, item->nowildcard_len - prefix))

256 + !git_fnmatch(match, name,

257 + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0,

258 + item->nowildcard_len - prefix))

259 return MATCHED_FNMATCH;

260

261 return 0;

@@ -1446,8 +1455,13 @@ int init_pathspec(struct pathspec *pathspec, const char **paths)

1455 item->match = path;

1456 item->len = strlen(path);

1457 item->nowildcard_len = simple_length(path);

1449 - if (item->nowildcard_len < item->len)

1458 + item->flags = 0;

1459 + if (item->nowildcard_len < item->len) {

1460 pathspec->has_wildcard = 1;

1461 + if (path[item->nowildcard_len] == '*' &&

1462 + no_wildcard(path + item->nowildcard_len + 1))

1463 + item->flags |= PATHSPEC_ONESTAR;

1464 + }

1465 }

1466

1467 qsort(pathspec->items, pathspec->nr,

dir.h

@@ -143,6 +143,7 @@ extern int fnmatch_icase(const char *pattern, const char *string, int flags);

143 * The prefix part of pattern must not contains wildcards.

144 */

145 #define GFNM_PATHNAME 1 /* similar to FNM_PATHNAME */

146 +#define GFNM_ONESTAR 2 /* there is only _one_ wildcard, a star */

147

148 extern int git_fnmatch(const char *pattern, const char *string,

149 int flags, int prefix);

tree-walk.c

+4 -2

@@ -628,7 +628,8 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,

628

629 if (item->nowildcard_len < item->len) {

630 if (!git_fnmatch(match + baselen, entry->path,

631 - 0, item->nowildcard_len - baselen))

631 + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0,

632 + item->nowildcard_len - baselen))

633 return entry_interesting;

634

635 /*

@@ -654,7 +655,8 @@ match_wildcards:

655 strbuf_add(base, entry->path, pathlen);

656

657 if (!git_fnmatch(match, base->buf + base_offset,

657 - 0, item->nowildcard_len)) {

658 + item->flags & PATHSPEC_ONESTAR ? GFNM_ONESTAR : 0,

659 + item->nowildcard_len)) {

660 strbuf_setlen(base, base_offset + baselen);

661 return entry_interesting;

662 }