git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Ævar Arnfjörð Bjarmason" <avarab@gmail.com>
To: git@vger.kernel.org
Cc: git-packagers@googlegroups.com, gitgitgadget@gmail.com,
	gitster@pobox.com, johannes.schindelin@gmx.de, peff@peff.net,
	sandals@crustytoothpaste.net, szeder.dev@gmail.com,
	"Ævar Arnfjörð Bjarmason" <avarab@gmail.com>
Subject: [RFC/PATCH 6/7] grep: remove the kwset optimization
Date: Wed, 26 Jun 2019 02:03:28 +0200	[thread overview]
Message-ID: <20190626000329.32475-7-avarab@gmail.com> (raw)
In-Reply-To: <87r27u8pie.fsf@evledraar.gmail.com>

A later change will replace this optimization with a different one,
but as removing it and running the tests demonstrates no grep
semantics depend on this backend anymore.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
---
 grep.c | 63 +++-------------------------------------------------------
 grep.h |  2 --
 2 files changed, 3 insertions(+), 62 deletions(-)

diff --git a/grep.c b/grep.c
index 14570c7ac1..4716217837 100644
--- a/grep.c
+++ b/grep.c
@@ -356,18 +356,6 @@ static NORETURN void compile_regexp_failed(const struct grep_pat *p,
 	die("%s'%s': %s", where, p->pattern, error);
 }
 
-static int is_fixed(const char *s, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len; i++) {
-		if (is_regex_special(s[i]))
-			return 0;
-	}
-
-	return 1;
-}
-
 #ifdef USE_LIBPCRE1
 static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 {
@@ -643,38 +631,12 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 
 	p->word_regexp = opt->word_regexp;
 	p->ignore_case = opt->ignore_case;
+	p->fixed = opt->fixed;
 
 	if (memchr(p->pattern, 0, p->patternlen) && !opt->pcre2)
 		die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
 
-	/*
-	 * Even when -F (fixed) asks us to do a non-regexp search, we
-	 * may not be able to correctly case-fold when -i
-	 * (ignore-case) is asked (in which case, we'll synthesize a
-	 * regexp to match the pattern that matches regexp special
-	 * characters literally, while ignoring case differences).  On
-	 * the other hand, even without -F, if the pattern does not
-	 * have any regexp special characters and there is no need for
-	 * case-folding search, we can internally turn it into a
-	 * simple string match using kws.  p->fixed tells us if we
-	 * want to use kws.
-	 */
-	if (opt->fixed || is_fixed(p->pattern, p->patternlen))
-		p->fixed = !p->ignore_case || !has_non_ascii(p->pattern);
-
-	if (p->fixed) {
-		p->kws = kwsalloc(p->ignore_case ? tolower_trans_tbl : NULL);
-		kwsincr(p->kws, p->pattern, p->patternlen);
-		kwsprep(p->kws);
-		return;
-	}
-
 	if (opt->fixed) {
-		/*
-		 * We come here when the pattern has the non-ascii
-		 * characters we cannot case-fold, and asked to
-		 * ignore-case.
-		 */
 		compile_fixed_regexp(p, opt);
 		return;
 	}
@@ -1042,9 +1004,7 @@ void free_grep_patterns(struct grep_opt *opt)
 		case GREP_PATTERN: /* atom */
 		case GREP_PATTERN_HEAD:
 		case GREP_PATTERN_BODY:
-			if (p->kws)
-				kwsfree(p->kws);
-			else if (p->pcre1_regexp)
+			if (p->pcre1_regexp)
 				free_pcre1_regexp(p);
 			else if (p->pcre2_pattern)
 				free_pcre2_pattern(p);
@@ -1104,29 +1064,12 @@ static void show_name(struct grep_opt *opt, const char *name)
 	opt->output(opt, opt->null_following_name ? "\0" : "\n", 1);
 }
 
-static int fixmatch(struct grep_pat *p, char *line, char *eol,
-		    regmatch_t *match)
-{
-	struct kwsmatch kwsm;
-	size_t offset = kwsexec(p->kws, line, eol - line, &kwsm);
-	if (offset == -1) {
-		match->rm_so = match->rm_eo = -1;
-		return REG_NOMATCH;
-	} else {
-		match->rm_so = offset;
-		match->rm_eo = match->rm_so + kwsm.size[0];
-		return 0;
-	}
-}
-
 static int patmatch(struct grep_pat *p, char *line, char *eol,
 		    regmatch_t *match, int eflags)
 {
 	int hit;
 
-	if (p->fixed)
-		hit = !fixmatch(p, line, eol, match);
-	else if (p->pcre1_regexp)
+	if (p->pcre1_regexp)
 		hit = !pcre1match(p, line, eol, match, eflags);
 	else if (p->pcre2_pattern)
 		hit = !pcre2match(p, line, eol, match, eflags);
diff --git a/grep.h b/grep.h
index 1875880f37..90ca435aad 100644
--- a/grep.h
+++ b/grep.h
@@ -32,7 +32,6 @@ typedef int pcre2_compile_context;
 typedef int pcre2_match_context;
 typedef int pcre2_jit_stack;
 #endif
-#include "kwset.h"
 #include "thread-utils.h"
 #include "userdiff.h"
 
@@ -97,7 +96,6 @@ struct grep_pat {
 	pcre2_match_context *pcre2_match_context;
 	pcre2_jit_stack *pcre2_jit_stack;
 	uint32_t pcre2_jit_on;
-	kwset_t kws;
 	unsigned fixed:1;
 	unsigned ignore_case:1;
 	unsigned word_regexp:1;
-- 
2.22.0.455.g172b71a6c5


  parent reply	other threads:[~2019-06-26  0:04 UTC|newest]

Thread overview: 90+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-13 11:49 [PATCH 0/4] Support building with GCC v8.x/v9.x Johannes Schindelin via GitGitGadget
2019-06-13 11:49 ` [PATCH 1/4] poll (mingw): allow compiling with GCC 8 and DEVELOPER=1 Johannes Schindelin via GitGitGadget
2019-06-13 11:49 ` [PATCH 2/4] kwset: allow building with GCC 8 Johannes Schindelin via GitGitGadget
2019-06-13 16:11   ` Junio C Hamano
2019-06-14  9:53   ` SZEDER Gábor
2019-06-14 10:00     ` [RFC/PATCH v1 0/4] compat/obstack: update from upstream SZEDER Gábor
2019-06-14 10:00       ` [PATCH v1 1/4] " SZEDER Gábor
2019-06-14 10:00       ` [PATCH v1 2/4] SQUASH??? compat/obstack: fix portability issues SZEDER Gábor
2019-06-14 10:00       ` [PATCH v1 3/4] SQUASH??? compat/obstack: fix build errors with Clang SZEDER Gábor
2019-06-14 10:00       ` [PATCH v1 4/4] compat/obstack: fix some sparse warnings SZEDER Gábor
2019-06-14 17:57       ` [RFC/PATCH v1 0/4] compat/obstack: update from upstream Jeff King
2019-06-14 18:19       ` Junio C Hamano
2019-06-14 20:30       ` Ramsay Jones
2019-06-14 21:24         ` Ramsay Jones
2019-06-17 18:36         ` SZEDER Gábor
2019-06-14 16:12     ` [PATCH 2/4] kwset: allow building with GCC 8 Junio C Hamano
2019-06-17 18:26       ` SZEDER Gábor
2019-06-14 22:09   ` Ævar Arnfjörð Bjarmason
2019-06-14 22:55   ` Can we just get rid of kwset & obstack in favor of optimistically using PCRE v2 JIT? Ævar Arnfjörð Bjarmason
2019-06-14 23:19     ` Ævar Arnfjörð Bjarmason
2019-06-20 10:35       ` Jeff King
2019-06-15  9:01     ` Carlo Arenas
2019-06-15 19:15     ` brian m. carlson
2019-06-15 22:14       ` Ævar Arnfjörð Bjarmason
2019-06-26  0:03         ` [RFC/PATCH 0/7] grep: move from kwset to optional PCRE v2 Ævar Arnfjörð Bjarmason
2019-06-26 14:02           ` Johannes Schindelin
2019-06-27  9:16             ` Johannes Schindelin
2019-06-27 16:27               ` Ævar Arnfjörð Bjarmason
2019-06-27 18:21                 ` Johannes Schindelin
2019-06-27 23:39           ` [PATCH v2 0/9] " Ævar Arnfjörð Bjarmason
2019-06-28  7:23             ` Ævar Arnfjörð Bjarmason
2019-06-28 16:10               ` Junio C Hamano
2019-07-01 21:20             ` [PATCH v3 00/10] " Ævar Arnfjörð Bjarmason
2019-07-01 21:31               ` Junio C Hamano
2019-07-02 11:10                 ` Ævar Arnfjörð Bjarmason
2019-07-02 12:32               ` Johannes Schindelin
2019-07-02 19:57                 ` Junio C Hamano
2019-07-03 10:08                   ` Johannes Schindelin
2019-07-03 10:25                 ` Johannes Schindelin
2019-07-03 11:27                   ` Johannes Schindelin
2019-07-01 21:20             ` [PATCH v3 01/10] log tests: test regex backends in "--encode=<enc>" tests Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 02/10] grep: don't use PCRE2?_UTF8 with "log --encoding=<non-utf8>" Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 03/10] t4210: skip more command-line encoding tests on MinGW Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 04/10] grep: inline the return value of a function call used only once Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 05/10] grep tests: move "grep binary" alongside the rest Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 06/10] grep tests: move binary pattern tests into their own file Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 07/10] grep: make the behavior for NUL-byte in patterns sane Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 08/10] grep: drop support for \0 in --fixed-strings <pattern> Ævar Arnfjörð Bjarmason
2019-07-01 21:20             ` [PATCH v3 09/10] grep: remove the kwset optimization Ævar Arnfjörð Bjarmason
2019-07-01 21:21             ` [PATCH v3 10/10] grep: use PCRE v2 for optimized fixed-string search Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 1/9] log tests: test regex backends in "--encode=<enc>" tests Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 2/9] grep: don't use PCRE2?_UTF8 with "log --encoding=<non-utf8>" Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 3/9] grep: inline the return value of a function call used only once Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 4/9] grep tests: move "grep binary" alongside the rest Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 5/9] grep tests: move binary pattern tests into their own file Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 6/9] grep: make the behavior for NUL-byte in patterns sane Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 7/9] grep: drop support for \0 in --fixed-strings <pattern> Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 8/9] grep: remove the kwset optimization Ævar Arnfjörð Bjarmason
2019-06-27 23:39           ` [PATCH v2 9/9] grep: use PCRE v2 for optimized fixed-string search Ævar Arnfjörð Bjarmason
2019-06-26  0:03         ` [RFC/PATCH 1/7] grep: inline the return value of a function call used only once Ævar Arnfjörð Bjarmason
2019-06-26  0:03         ` [RFC/PATCH 2/7] grep tests: move "grep binary" alongside the rest Ævar Arnfjörð Bjarmason
2019-06-26 14:05           ` Johannes Schindelin
2019-06-26 18:13           ` Junio C Hamano
2019-06-26  0:03         ` [RFC/PATCH 3/7] grep tests: move binary pattern tests into their own file Ævar Arnfjörð Bjarmason
2019-06-26  0:03         ` [RFC/PATCH 4/7] grep: make the behavior for \0 in patterns sane Ævar Arnfjörð Bjarmason
2019-06-27  2:03           ` brian m. carlson
2019-06-26  0:03         ` [RFC/PATCH 5/7] grep: drop support for \0 in --fixed-strings <pattern> Ævar Arnfjörð Bjarmason
2019-06-26 16:14           ` Junio C Hamano
2019-06-26  0:03         ` Ævar Arnfjörð Bjarmason [this message]
2019-06-26  0:03         ` [RFC/PATCH 7/7] grep: use PCRE v2 for optimized fixed-string search Ævar Arnfjörð Bjarmason
2019-06-26 14:13           ` Johannes Schindelin
2019-06-26 18:45             ` Junio C Hamano
2019-06-27  9:31               ` Johannes Schindelin
2019-06-27 18:45                 ` Johannes Schindelin
2019-06-27 19:06                   ` Junio C Hamano
2019-06-28 10:56                     ` Johannes Schindelin
2019-06-13 11:49 ` [PATCH 3/4] winansi: simplify loading the GetCurrentConsoleFontEx() function Johannes Schindelin via GitGitGadget
2019-06-13 11:49 ` [PATCH 4/4] config: avoid calling `labs()` on too-large data type Johannes Schindelin via GitGitGadget
2019-06-13 16:13   ` Junio C Hamano
2019-06-16  6:48   ` René Scharfe
2019-06-16  8:24     ` René Scharfe
2019-06-16 14:01       ` René Scharfe
2019-06-16 22:26         ` Junio C Hamano
2019-06-20 19:58           ` René Scharfe
2019-06-20 21:07             ` Junio C Hamano
2019-06-21 18:35             ` Johannes Schindelin
2019-06-22 10:03               ` René Scharfe
2019-06-22 10:03           ` [PATCH v2 1/3] config: use unsigned_mult_overflows to check for overflows René Scharfe
2019-06-22 10:03           ` [PATCH v2 2/3] config: don't multiply in parse_unit_factor() René Scharfe
2019-06-22 10:03           ` [PATCH v2 3/3] config: simplify parsing of unit factors 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

  List information: http://vger.kernel.org/majordomo-info.html

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

  git send-email \
    --in-reply-to=20190626000329.32475-7-avarab@gmail.com \
    --to=avarab@gmail.com \
    --cc=git-packagers@googlegroups.com \
    --cc=git@vger.kernel.org \
    --cc=gitgitgadget@gmail.com \
    --cc=gitster@pobox.com \
    --cc=johannes.schindelin@gmx.de \
    --cc=peff@peff.net \
    --cc=sandals@crustytoothpaste.net \
    --cc=szeder.dev@gmail.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.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

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 read-only IMAP folder(s) and NNTP newsgroup(s).