git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "René Scharfe" <rene.scharfe@lsrfire.ath.cx>
To: Git Mailing List <git@vger.kernel.org>
Cc: Junio C Hamano <gitster@pobox.com>
Subject: [PATCH 2/2] grep: don't call regexec() for fixed strings
Date: Sat, 10 Jan 2009 00:18:34 +0100	[thread overview]
Message-ID: <4967DB4A.2000702@lsrfire.ath.cx> (raw)
In-Reply-To: <4967D8F8.9070508@lsrfire.ath.cx>

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>
---
 grep.c |   29 +++++++++++++++++++++++++----
 grep.h |    1 +
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/grep.c b/grep.c
index 394703b..a1092df 100644
--- 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 45a222d..5102ce3 100644
--- 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 {
-- 
1.6.1

  reply	other threads:[~2009-01-09 23:21 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-09 23:08 [PATCH 1/2] grep -w: forward to next possible position after rejected match René Scharfe
2009-01-09 23:18 ` René Scharfe [this message]
2009-01-10 20:37   ` [PATCH 2/2] grep: don't call regexec() for fixed strings Junio C Hamano
2009-01-12 12:25   ` Mikael Magnusson
2009-01-12 13:33     ` Johannes Schindelin
2009-01-12 15:32   ` Alex Riesen
2009-01-12 19:18     ` René Scharfe
2009-01-13  8:13       ` Junio C Hamano
2009-01-17 15:50         ` [PATCH 1/4] Add ctype test René Scharfe
2009-01-17 15:50         ` [PATCH 2/4] Reformat ctype.c René Scharfe
2009-01-17 15:50         ` [PATCH 3/4] Change NUL char handling of isspecial() René Scharfe
2009-01-17 15:50         ` [PATCH 4/4] Add is_regex_special() René Scharfe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4967DB4A.2000702@lsrfire.ath.cx \
    --to=rene.scharfe@lsrfire.ath.cx \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).