attr: more matching optimizations from .gitignore
.gitattributes and .gitignore share the same pattern syntax but has separate matching implementation. Over the years, ignore's implementation accumulates more optimizations while attr's stays the same. This patch reuses the core matching functions that are also used by excluded_from_list. excluded_from_list and path_matches can't be merged due to differences in exclude and attr, for example: * "!pattern" syntax is forbidden in .gitattributes. As an attribute can be unset (i.e. set to a special value "false") or made back to unspecified (i.e. not even set to "false"), "!pattern attr" is unclear which one it means. * we support attaching attributes to directories, but git-core internally does not currently make use of attributes on directories. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Nguyễn Thái Ngọc Duy committed
Oct 15, 2012 at 13:24 UTC
82dce998c2028b6ee96691921b7037a6e182ec89
5 files changed
+64
-32
Documentation/gitattributes.txt
+1
@@ -56,6 +56,7 @@ When more than one pattern matches the path, a later line
56
overrides an earlier line. This overriding is done per
57
attribute. The rules how the pattern matches paths are the
58
same as in `.gitignore` files; see linkgit:gitignore[5].
59
+Unlike `.gitignore`, negative patterns are forbidden.
60
61
When deciding what attributes are assigned to a path, git
62
consults `$GIT_DIR/info/attributes` file (which has the highest
attr.c
+31
-21
@@ -115,6 +115,13 @@ struct attr_state {
115
const char *setto;
116
};
117
118
+struct pattern {
119
+ const char *pattern;
120
+ int patternlen;
121
+ int nowildcardlen;
122
+ int flags; /* EXC_FLAG_* */
123
+};
124
+
125
/*
126
* One rule, as from a .gitattributes file.
127
*
@@ -131,7 +138,7 @@ struct attr_state {
138
*/
139
struct match_attr {
140
union {
134
- char *pattern;
141
+ struct pattern pat;
142
struct git_attr *attr;
143
} u;
144
char is_macro;
@@ -241,9 +248,16 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
248
if (is_macro)
249
res->u.attr = git_attr_internal(name, namelen);
250
else {
244
- res->u.pattern = (char *)&(res->state[num_attr]);
245
- memcpy(res->u.pattern, name, namelen);
246
- res->u.pattern[namelen] = 0;
251
+ char *p = (char *)&(res->state[num_attr]);
252
+ memcpy(p, name, namelen);
253
+ res->u.pat.pattern = p;
254
+ parse_exclude_pattern(&res->u.pat.pattern,
255
+ &res->u.pat.patternlen,
256
+ &res->u.pat.flags,
257
+ &res->u.pat.nowildcardlen);
258
+ if (res->u.pat.flags & EXC_FLAG_NEGATIVE)
259
+ die(_("Negative patterns are forbidden in git attributes\n"
260
+ "Use '\\!' for literal leading exclamation."));
261
}
262
res->is_macro = is_macro;
263
res->num_attr = num_attr;
@@ -640,25 +654,21 @@ static void prepare_attr_stack(const char *path)
654
655
static int path_matches(const char *pathname, int pathlen,
656
const char *basename,
643
- const char *pattern,
657
+ const struct pattern *pat,
658
const char *base, int baselen)
659
{
646
- if (!strchr(pattern, '/')) {
647
- return (fnmatch_icase(pattern, basename, 0) == 0);
660
+ const char *pattern = pat->pattern;
661
+ int prefix = pat->nowildcardlen;
662
+
663
+ if (pat->flags & EXC_FLAG_NODIR) {
664
+ return match_basename(basename,
665
+ pathlen - (basename - pathname),
666
+ pattern, prefix,
667
+ pat->patternlen, pat->flags);
668
}
649
- /*
650
- * match with FNM_PATHNAME; the pattern has base implicitly
651
- * in front of it.
652
- */
653
- if (*pattern == '/')
654
- pattern++;
655
- if (pathlen < baselen ||
656
- (baselen && pathname[baselen] != '/') ||
657
- strncmp(pathname, base, baselen))
658
- return 0;
659
- if (baselen != 0)
660
- baselen++;
661
- return fnmatch_icase(pattern, pathname + baselen, FNM_PATHNAME) == 0;
669
+ return match_pathname(pathname, pathlen,
670
+ base, baselen,
671
+ pattern, prefix, pat->patternlen, pat->flags);
672
}
673
674
static int macroexpand_one(int attr_nr, int rem);
@@ -696,7 +706,7 @@ static int fill(const char *path, int pathlen, const char *basename,
706
if (a->is_macro)
707
continue;
708
if (path_matches(path, pathlen, basename,
699
- a->u.pattern, base, stk->originlen))
709
+ &a->u.pat, base, stk->originlen))
710
rem = fill_one("fill", a, rem);
711
}
712
return rem;
dir.c
+11
-11
@@ -308,10 +308,10 @@ static int no_wildcard(const char *string)
308
return string[simple_length(string)] == '\0';
309
}
310
311
-static void parse_exclude_pattern(const char **pattern,
312
- int *patternlen,
313
- int *flags,
314
- int *nowildcardlen)
311
+void parse_exclude_pattern(const char **pattern,
312
+ int *patternlen,
313
+ int *flags,
314
+ int *nowildcardlen)
315
{
316
const char *p = *pattern;
317
size_t i, len;
@@ -530,9 +530,9 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
530
dir->basebuf[baselen] = '\0';
531
}
532
533
-static int match_basename(const char *basename, int basenamelen,
534
- const char *pattern, int prefix, int patternlen,
535
- int flags)
533
+int match_basename(const char *basename, int basenamelen,
534
+ const char *pattern, int prefix, int patternlen,
535
+ int flags)
536
{
537
if (prefix == patternlen) {
538
if (!strcmp_icase(pattern, basename))
@@ -549,10 +549,10 @@ static int match_basename(const char *basename, int basenamelen,
549
return 0;
550
}
551
552
-static int match_pathname(const char *pathname, int pathlen,
553
- const char *base, int baselen,
554
- const char *pattern, int prefix, int patternlen,
555
- int flags)
552
+int match_pathname(const char *pathname, int pathlen,
553
+ const char *base, int baselen,
554
+ const char *pattern, int prefix, int patternlen,
555
+ int flags)
556
{
557
const char *name;
558
int namelen;
dir.h
+11
@@ -80,6 +80,16 @@ extern int excluded_from_list(const char *pathname, int pathlen, const char *bas
80
int *dtype, struct exclude_list *el);
81
struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len);
82
83
+/*
84
+ * these implement the matching logic for dir.c:excluded_from_list and
85
+ * attr.c:path_matches()
86
+ */
87
+extern int match_basename(const char *, int,
88
+ const char *, int, int, int);
89
+extern int match_pathname(const char *, int,
90
+ const char *, int,
91
+ const char *, int, int, int);
92
+
93
/*
94
* The excluded() API is meant for callers that check each level of leading
95
* directory hierarchies with excluded() to avoid recursing into excluded
@@ -97,6 +107,7 @@ extern int path_excluded(struct path_exclude_check *, const char *, int namelen,
107
extern int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen,
108
char **buf_p, struct exclude_list *which, int check_index);
109
extern void add_excludes_from_file(struct dir_struct *, const char *fname);
110
+extern void parse_exclude_pattern(const char **string, int *patternlen, int *flags, int *nowildcardlen);
111
extern void add_exclude(const char *string, const char *base,
112
int baselen, struct exclude_list *which);
113
extern void free_excludes(struct exclude_list *el);
t/t0003-attributes.sh
+10
@@ -206,6 +206,16 @@ test_expect_success 'root subdir attribute test' '
206
attr_check subdir/a/i unspecified
207
'
208
209
+test_expect_success 'negative patterns' '
210
+ echo "!f test=bar" >.gitattributes &&
211
+ test_must_fail git check-attr test -- f
212
+'
213
+
214
+test_expect_success 'patterns starting with exclamation' '
215
+ echo "\!f test=foo" >.gitattributes &&
216
+ attr_check "!f" foo
217
+'
218
+
219
test_expect_success 'setup bare' '
220
git clone --bare . bare.git &&
221
cd bare.git