From: Hamza Mahfooz <someguy@effective-light.com>
To: git@vger.kernel.org
Cc: Junio C Hamano <gitster@pobox.com>,
Hamza Mahfooz <someguy@effective-light.com>
Subject: [PATCH v13 1/3] grep: refactor next_match() and match_one_pattern() for external use
Date: Fri, 15 Oct 2021 12:13:54 -0400 [thread overview]
Message-ID: <20211015161356.3372-1-someguy@effective-light.com> (raw)
These changes are made in preparation of, the colorization support for the
"git log" subcommands that, rely on regex functionality (i.e. "--author",
"--committer" and "--grep"). These changes are necessary primarily because
match_one_pattern() expects header lines to be prefixed, however, in
pretty, the prefixes are stripped from the lines because the name-email
pairs need to go through additional parsing, before they can be printed and
because next_match() doesn't handle the case of
"ctx == GREP_CONTEXT_HEAD" at all. So, teach next_match() how to handle the
new case and move match_one_pattern()'s core logic to
headerless_match_one_pattern() while preserving match_one_pattern()'s uses
that depend on the additional processing.
Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
---
v5: separate grep changes from pretty changes.
v6: rescope some variables.
v7: export header_field[] and allow for subsequent matches on header lines
in match_one_pattern().
v8: add headerless_match_one_pattern() and move header_field[] back.
v9: get rid of the new check in headerless_match_one_pattern(), move the
header pattern filtering logic in grep_next_match() and document
grep_next_match() in grep.h.
v10: add a "magic" comment in grep_next_match() to signify a fall through
in the switch statement.
---
grep.c | 79 ++++++++++++++++++++++++++++++++++++----------------------
grep.h | 9 +++++++
2 files changed, 58 insertions(+), 30 deletions(-)
diff --git a/grep.c b/grep.c
index 14fe8a0fd2..fe847a0111 100644
--- a/grep.c
+++ b/grep.c
@@ -944,10 +944,10 @@ static struct {
{ "reflog ", 7 },
};
-static int match_one_pattern(struct grep_pat *p,
- const char *bol, const char *eol,
- enum grep_context ctx,
- regmatch_t *pmatch, int eflags)
+static int headerless_match_one_pattern(struct grep_pat *p,
+ const char *bol, const char *eol,
+ enum grep_context ctx,
+ regmatch_t *pmatch, int eflags)
{
int hit = 0;
const char *start = bol;
@@ -956,25 +956,6 @@ static int match_one_pattern(struct grep_pat *p,
((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
return 0;
- if (p->token == GREP_PATTERN_HEAD) {
- const char *field;
- size_t len;
- assert(p->field < ARRAY_SIZE(header_field));
- field = header_field[p->field].field;
- len = header_field[p->field].len;
- if (strncmp(bol, field, len))
- return 0;
- bol += len;
- switch (p->field) {
- case GREP_HEADER_AUTHOR:
- case GREP_HEADER_COMMITTER:
- strip_timestamp(bol, &eol);
- break;
- default:
- break;
- }
- }
-
again:
hit = patmatch(p, bol, eol, pmatch, eflags);
@@ -1025,6 +1006,36 @@ static int match_one_pattern(struct grep_pat *p,
return hit;
}
+static int match_one_pattern(struct grep_pat *p,
+ const char *bol, const char *eol,
+ enum grep_context ctx, regmatch_t *pmatch,
+ int eflags)
+{
+ const char *field;
+ size_t len;
+
+ if (p->token == GREP_PATTERN_HEAD) {
+ assert(p->field < ARRAY_SIZE(header_field));
+ field = header_field[p->field].field;
+ len = header_field[p->field].len;
+ if (strncmp(bol, field, len))
+ return 0;
+ bol += len;
+
+ switch (p->field) {
+ case GREP_HEADER_AUTHOR:
+ case GREP_HEADER_COMMITTER:
+ strip_timestamp(bol, &eol);
+ break;
+ default:
+ break;
+ }
+ }
+
+ return headerless_match_one_pattern(p, bol, eol, ctx, pmatch, eflags);
+}
+
+
static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x,
const char *bol, const char *eol,
enum grep_context ctx, ssize_t *col,
@@ -1143,7 +1154,7 @@ static int match_next_pattern(struct grep_pat *p,
{
regmatch_t match;
- if (!match_one_pattern(p, bol, eol, ctx, &match, eflags))
+ if (!headerless_match_one_pattern(p, bol, eol, ctx, &match, eflags))
return 0;
if (match.rm_so < 0 || match.rm_eo < 0)
return 0;
@@ -1158,19 +1169,26 @@ static int match_next_pattern(struct grep_pat *p,
return 1;
}
-static int next_match(struct grep_opt *opt,
- const char *bol, const char *eol,
- enum grep_context ctx, regmatch_t *pmatch, int eflags)
+int grep_next_match(struct grep_opt *opt,
+ const char *bol, const char *eol,
+ enum grep_context ctx, regmatch_t *pmatch,
+ enum grep_header_field field, int eflags)
{
struct grep_pat *p;
int hit = 0;
pmatch->rm_so = pmatch->rm_eo = -1;
if (bol < eol) {
- for (p = opt->pattern_list; p; p = p->next) {
+ for (p = ((ctx == GREP_CONTEXT_HEAD)
+ ? opt->header_list : opt->pattern_list);
+ p; p = p->next) {
switch (p->token) {
- case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
+ if ((field != GREP_HEADER_FIELD_MAX) &&
+ (p->field != field))
+ continue;
+ /* fall thru */
+ case GREP_PATTERN: /* atom */
case GREP_PATTERN_BODY:
hit |= match_next_pattern(p, bol, eol, ctx,
pmatch, eflags);
@@ -1261,7 +1279,8 @@ static void show_line(struct grep_opt *opt,
else if (sign == '=')
line_color = opt->colors[GREP_COLOR_FUNCTION];
}
- while (next_match(opt, bol, eol, ctx, &match, eflags)) {
+ while (grep_next_match(opt, bol, eol, ctx, &match,
+ GREP_HEADER_FIELD_MAX, eflags)) {
if (match.rm_so == match.rm_eo)
break;
diff --git a/grep.h b/grep.h
index 3cb8a83ae8..808ad76f0c 100644
--- a/grep.h
+++ b/grep.h
@@ -191,6 +191,15 @@ void compile_grep_patterns(struct grep_opt *opt);
void free_grep_patterns(struct grep_opt *opt);
int grep_buffer(struct grep_opt *opt, const char *buf, unsigned long size);
+/* The field parameter is only used to filter header patterns
+ * (where appropriate). If filtering isn't desirable
+ * GREP_HEADER_FIELD_MAX should be supplied.
+ */
+int grep_next_match(struct grep_opt *opt,
+ const char *bol, const char *eol,
+ enum grep_context ctx, regmatch_t *pmatch,
+ enum grep_header_field field, int eflags);
+
struct grep_source {
char *name;
--
2.33.0
next reply other threads:[~2021-10-15 16:14 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-15 16:13 Hamza Mahfooz [this message]
2021-10-15 16:13 ` [PATCH v13 2/3] pretty: colorize pattern matches in commit messages Hamza Mahfooz
2021-10-15 16:13 ` [PATCH v13 3/3] grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data Hamza Mahfooz
2021-10-15 20:03 ` Junio C Hamano
2021-10-16 16:25 ` René Scharfe
2021-10-16 17:12 ` Ævar Arnfjörð Bjarmason
2021-10-16 19:44 ` René Scharfe
2021-10-17 6:00 ` Junio C Hamano
2021-10-17 6:55 ` René Scharfe
2021-10-17 9:44 ` Ævar Arnfjörð Bjarmason
2021-11-15 20:43 ` Andreas Schwab
2021-11-15 22:41 ` Ævar Arnfjörð Bjarmason
2021-11-16 2:12 ` Carlo Arenas
2021-11-16 8:41 ` Andreas Schwab
2021-11-16 9:06 ` Carlo Arenas
2021-11-16 9:18 ` Andreas Schwab
2021-11-16 9:29 ` Andreas Schwab
2021-11-16 9:38 ` Carlo Arenas
2021-11-16 9:55 ` Andreas Schwab
2021-11-16 11:00 ` [PATCH] grep: avoid setting UTF mode when not needed Carlo Marcelo Arenas Belón
2021-11-16 12:32 ` Ævar Arnfjörð Bjarmason
2021-11-16 13:35 ` Hamza Mahfooz
2021-11-17 14:31 ` Ævar Arnfjörð Bjarmason
2021-11-16 18:22 ` Carlo Arenas
2021-11-16 18:48 ` Junio C Hamano
2021-11-17 10:23 ` [PATCH v2] grep: avoid setting UTF mode when dangerous with PCRE Carlo Marcelo Arenas Belón
2021-11-18 7:29 ` Junio C Hamano
2021-11-18 10:15 ` Carlo Arenas
2021-11-18 12:49 ` Hamza Mahfooz
2021-11-19 6:58 ` Ævar Arnfjörð Bjarmason
2021-11-18 21:21 ` Hamza Mahfooz
2021-11-17 18:46 ` [PATCH v13 3/3] grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data René Scharfe
2021-11-17 19:56 ` Carlo Arenas
2021-11-17 20:59 ` Ævar Arnfjörð Bjarmason
2021-11-17 21:53 ` Carlo Arenas
2021-11-18 0:00 ` Ævar Arnfjörð Bjarmason
2021-11-18 18:17 ` Junio C Hamano
2021-11-18 20:57 ` René Scharfe
2021-11-19 7:00 ` Ævar Arnfjörð Bjarmason
2021-11-19 16:08 ` René Scharfe
2021-11-19 17:33 ` Carlo Arenas
2021-11-19 17:11 ` Junio C Hamano
2021-10-15 18:05 ` [PATCH v13 1/3] grep: refactor next_match() and match_one_pattern() for external use Junio C Hamano
2021-10-15 18:24 ` Hamza Mahfooz
2021-10-15 19:28 ` Junio C Hamano
2021-10-15 19:40 ` Hamza Mahfooz
2021-10-15 19:49 ` Junio C Hamano
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=20211015161356.3372-1-someguy@effective-light.com \
--to=someguy@effective-light.com \
--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.
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).