grep: don't call regexec() for fixed strings

Add the new flag "fixed" to struct grep_pat and set it if the pattern
is doesn't contain any regex control characters in addition to if the
flag -F/--fixed-strings was specified.

This gives a nice speed up on msysgit, where regexec() seems to be
extra slow.  Before (best of five runs):

	$ time git grep grep v1.6.1 >/dev/null

	real    0m0.552s
	user    0m0.000s
	sys     0m0.000s

	$ time git grep -F grep v1.6.1 >/dev/null

	real    0m0.170s
	user    0m0.000s
	sys     0m0.015s

With the patch:

	$ time git grep grep v1.6.1 >/dev/null

	real    0m0.173s
	user    0m0.000s
	sys     0m0.000s

The difference is much smaller on Linux, but still measurable.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/grep.c b/grep.c
index 22a56b5d543d7924d4bd76d3d220b026b23ed3a9..6485760ff30e0575ee13b43fc8c7fb8e2e291346 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -28,9 +28,31 @@ void append_grep_pattern(struct grep_opt *opt, const char *pat,
        p->next = NULL;
 }
 
+static int isregexspecial(int c)
+{
+       return isspecial(c) || c == '$' || c == '(' || c == ')' || c == '+' ||
+                              c == '.' || c == '^' || c == '{' || c == '|';
+}
+
+static int is_fixed(const char *s)
+{
+       while (!isregexspecial(*s))
+               s++;
+       return !*s;
+}
+
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
-       int err = regcomp(&p->regexp, p->pattern, opt->regflags);
+       int err;
+
+       if (opt->fixed || is_fixed(p->pattern))
+               p->fixed = 1;
+       if (opt->regflags & REG_ICASE)
+               p->fixed = 0;
+       if (p->fixed)
+               return;
+
+       err = regcomp(&p->regexp, p->pattern, opt->regflags);
        if (err) {
                char errbuf[1024];
                char where[1024];
@@ -159,8 +181,7 @@ void compile_grep_patterns(struct grep_opt *opt)
                case GREP_PATTERN: /* atom */
                case GREP_PATTERN_HEAD:
                case GREP_PATTERN_BODY:
-                       if (!opt->fixed)
-                               compile_regexp(p, opt);
+                       compile_regexp(p, opt);
                        break;
                default:
                        opt->extended = 1;
@@ -314,7 +335,7 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
        }
 
  again:
-       if (!opt->fixed) {
+       if (!p->fixed) {
                regex_t *exp = &p->regexp;
                hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
                               pmatch, 0);

diff --git a/grep.h b/grep.h
index 45a222d904b5898758c3c84f6ef1e0119c81f6b2..5102ce335d29811dd448e173f2e90e8d03b5f011 100644 (file)
--- a/grep.h
+++ b/grep.h
@@ -30,6 +30,7 @@ struct grep_pat {
        const char *pattern;
        enum grep_header_field field;
        regex_t regexp;
+       unsigned fixed:1;
 };
 
 enum grep_expr_node {