grep: simplify config parsing and option parsing

Simplify the parsing of "grep.patternType" and
"grep.extendedRegexp". This changes no behavior, but gets rid of
complex parsing logic that isn't needed anymore.

When "grep.patternType" was introduced in 84befcd0a4a (grep: add a
grep.patternType configuration setting, 2012-08-03) we promised that:

 1. You can set "grep.patternType", and "[setting it to] 'default'
    will return to the default matching behavior".

    In that context "the default" meant whatever the configuration
    system specified before that change, i.e. via grep.extendedRegexp.

 2. We'd support the existing "grep.extendedRegexp" option, but ignore
    it when the new "grep.patternType" option is set. We said we'd
    only ignore the older "grep.extendedRegexp" option "when the
    `grep.patternType` option is set to a value other than
    'default'".

In a preceding commit we changed grep_config() to be called after
grep_init(), which means that much of the complexity here can go
away.

As before both "grep.patternType" and "grep.extendedRegexp" are
last-one-wins variable, with "grep.extendedRegexp" yielding to
"grep.patternType", except when "grep.patternType=default".

Note that as the previously added tests indicate this cannot be done
on-the-fly as we see the config variables, without introducing more
state keeping. I.e. if we see:

    -c grep.extendedRegexp=false
    -c grep.patternType=default
    -c extendedRegexp=true

We need to select ERE, since grep.patternType=default unselects that
variable, which normally has higher precedence, but we also need to
select BRE in cases of:

    -c grep.extendedRegexp=true \
    -c grep.extendedRegexp=false

Which would not be the case for this, which select ERE:

    -c grep.patternType=extended \
    -c grep.extendedRegexp=false

Therefore we cannot do this on-the-fly in grep_config without also
introducing tracking variables for not only the pattern type, but what
the source of that pattern type was.

So we need to decide on the pattern after our config was fully
parsed. Let's do that by deferring the decision on the pattern type
until it's time to compile it in compile_regexp().

By that time we've not only parsed the config, but also handled the
command-line options. Those will set "opt.pattern_type_option" (*not*
"opt.extended_regexp_option"!).

At that point all we need to do is see if "grep.patternType" was
UNSPECIFIED in the end (including an explicit "=default"), if so we'll
use the "grep.extendedRegexp" configuration, if any.

See my 07a3d411739 (grep: remove regflags from the public grep_opt
API, 2017-06-29) for addition of the two comments being removed here,
i.e. the complexity noted in that commit is now going away.

1. https://lore.kernel.org/git/patch-v8-09.10-c211bb0c69d-20220118T155211Z-avarab@gmail.com/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 9 insertions, 60 deletions

diff --git a/grep.c b/grep.c
index 60228a9..a8f503f 100644
--- a/grep.c
+++ b/grep.c
@@ -115,62 +115,6 @@ void grep_init(struct grep_opt *opt, struct repository *repo)
 	opt->header_tail = &opt->header_list;
 }
 
-static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
-{
-	/*
-	 * When committing to the pattern type by setting the relevant
-	 * fields in grep_opt it's generally not necessary to zero out
-	 * the fields we're not choosing, since they won't have been
-	 * set by anything. The extended_regexp_option field is the
-	 * only exception to this.
-	 *
-	 * This is because in the process of parsing grep.patternType
-	 * & grep.extendedRegexp we set opt->pattern_type_option and
-	 * opt->extended_regexp_option, respectively. We then
-	 * internally use opt->extended_regexp_option to see if we're
-	 * compiling an ERE. It must be unset if that's not actually
-	 * the case.
-	 */
-	if (pattern_type != GREP_PATTERN_TYPE_ERE &&
-	    opt->extended_regexp_option)
-		opt->extended_regexp_option = 0;
-
-	switch (pattern_type) {
-	case GREP_PATTERN_TYPE_UNSPECIFIED:
-		/* fall through */
-
-	case GREP_PATTERN_TYPE_BRE:
-		break;
-
-	case GREP_PATTERN_TYPE_ERE:
-		opt->extended_regexp_option = 1;
-		break;
-
-	case GREP_PATTERN_TYPE_FIXED:
-		opt->fixed = 1;
-		break;
-
-	case GREP_PATTERN_TYPE_PCRE:
-		opt->pcre2 = 1;
-		break;
-	}
-}
-
-void grep_commit_pattern_type(enum grep_pattern_type pattern_type, struct grep_opt *opt)
-{
-	if (pattern_type != GREP_PATTERN_TYPE_UNSPECIFIED)
-		grep_set_pattern_type_option(pattern_type, opt);
-	else if (opt->pattern_type_option != GREP_PATTERN_TYPE_UNSPECIFIED)
-		grep_set_pattern_type_option(opt->pattern_type_option, opt);
-	else if (opt->extended_regexp_option)
-		/*
-		 * This branch *must* happen after setting from the
-		 * opt->pattern_type_option above, we don't want
-		 * grep.extendedRegexp to override grep.patternType!
-		 */
-		grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, opt);
-}
-
 static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
 					const char *origin, int no,
 					enum grep_pat_token t,
@@ -488,11 +432,16 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 	int err;
 	int regflags = REG_NEWLINE;
 
+	if (opt->pattern_type_option == GREP_PATTERN_TYPE_UNSPECIFIED)
+		opt->pattern_type_option = (opt->extended_regexp_option
+					    ? GREP_PATTERN_TYPE_ERE
+					    : GREP_PATTERN_TYPE_BRE);
+
 	p->word_regexp = opt->word_regexp;
 	p->ignore_case = opt->ignore_case;
-	p->fixed = opt->fixed;
+	p->fixed = opt->pattern_type_option == GREP_PATTERN_TYPE_FIXED;
 
-	if (!opt->pcre2 &&
+	if (opt->pattern_type_option != GREP_PATTERN_TYPE_PCRE &&
 	    memchr(p->pattern, 0, p->patternlen))
 		die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
 
@@ -544,14 +493,14 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 		return;
 	}
 
-	if (opt->pcre2) {
+	if (opt->pattern_type_option == GREP_PATTERN_TYPE_PCRE) {
 		compile_pcre2_pattern(p, opt);
 		return;
 	}
 
 	if (p->ignore_case)
 		regflags |= REG_ICASE;
-	if (opt->extended_regexp_option)
+	if (opt->pattern_type_option == GREP_PATTERN_TYPE_ERE)
 		regflags |= REG_EXTENDED;
 	err = regcomp(&p->regexp, p->pattern, regflags);
 	if (err) {