Refactor calls to the grep machinery to always pass opt.ignore_case &
opt.extended_regexp_option instead of setting the equivalent regflags
bits.
The bug fixed when making -i work with -P in commit 9e3cbc59d5 ("log:
make --regexp-ignore-case work with --perl-regexp", 2017-05-20) was
really just plastering over the code smell which this change fixes.
See my "Re: [PATCH v3 05/30] log: make --regexp-ignore-case work with
--perl-regexp"[1] for the discussion leading up to this.
The reason for adding the extensive commentary here is that I
discovered some subtle complexity in implementing this that really
should be called out explicitly to future readers.
Before this change we'd rely on the difference between
`extended_regexp_option` and `regflags` to serve as a membrane between
our preliminary parsing of grep.extendedRegexp and grep.patternType,
and what we decided to do internally.
Now that those two are the same thing, it's necessary to unset
`extended_regexp_option` just before we commit in cases where both of
those config variables are set. See 84befcd0a4 ("grep: add a
grep.patternType configuration setting", 2012-08-03) for the code and
documentation related to that.
The explanation of why the if/else branches in
grep_commit_pattern_type() are ordered the way they are exists in that
commit message, but I think it's worth calling this subtlety out
explicitly with a comment for future readers.
Unrelated to that: I could have factored out the default REG_NEWLINE
flag into some custom GIT_GREP_H_DEFAULT_REGFLAGS or something, but
since it's just used in two places I didn't think it was worth the
effort.
As an aside we're really lacking test coverage regflags being
initiated as 0 instead of as REG_NEWLINE. Tests will fail if it's
removed from compile_regexp(), but not if it's removed from
compile_fixed_regexp(). I have not dug to see if it's actually needed
in the latter case or if the test coverage is lacking.
1. <CACBZZX6Hp4Q4TOj_X1fbdCA4twoXF5JemZ5ZbEn7wmkA=1k...@mail.gmail.com>
(https://public-inbox.org/git/CACBZZX6Hp4Q4TOj_X1fbdCA4twoXF5JemZ5ZbEn7wmkA=1k...@mail.gmail.com/)
Signed-off-by: Ævar Arnfjörð Bjarmason <ava...@gmail.com>
---
builtin/grep.c | 2 --
grep.c | 43 ++++++++++++++++++++++++++++++++++---------
grep.h | 1 -
revision.c | 2 --
4 files changed, 34 insertions(+), 14 deletions(-)
diff --git a/builtin/grep.c b/builtin/grep.c
index f61a9d938b..b682966439 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -1169,8 +1169,6 @@ int cmd_grep(int argc, const char **argv, const char
*prefix)
if (!opt.pattern_list)
die(_("no pattern given."));
- if (!opt.fixed && opt.ignore_case)
- opt.regflags |= REG_ICASE;
/*
* We have to find "--" in a separate pass, because its presence
diff --git a/grep.c b/grep.c
index 736e1e00d6..51aaad9f03 100644
--- a/grep.c
+++ b/grep.c
@@ -35,7 +35,6 @@ void init_grep_defaults(void)
memset(opt, 0, sizeof(*opt));
opt->relative = 1;
opt->pathname = 1;
- opt->regflags = REG_NEWLINE;
opt->max_depth = -1;
opt->pattern_type_option = GREP_PATTERN_TYPE_UNSPECIFIED;
color_set(opt->color_context, "");
@@ -154,7 +153,6 @@ void grep_init(struct grep_opt *opt, const char *prefix)
opt->linenum = def->linenum;
opt->max_depth = def->max_depth;
opt->pathname = def->pathname;
- opt->regflags = def->regflags;
opt->relative = def->relative;
opt->output = def->output;
@@ -170,6 +168,24 @@ void grep_init(struct grep_opt *opt, const char *prefix)
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 */
@@ -178,7 +194,7 @@ static void grep_set_pattern_type_option(enum
grep_pattern_type pattern_type, st
break;
case GREP_PATTERN_TYPE_ERE:
- opt->regflags |= REG_EXTENDED;
+ opt->extended_regexp_option = 1;
break;
case GREP_PATTERN_TYPE_FIXED:
@@ -208,6 +224,11 @@ void grep_commit_pattern_type(enum grep_pattern_type
pattern_type, struct grep_o
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);
}
@@ -573,7 +594,7 @@ static void compile_fixed_regexp(struct grep_pat *p, struct
grep_opt *opt)
{
struct strbuf sb = STRBUF_INIT;
int err;
- int regflags = opt->regflags;
+ int regflags = REG_NEWLINE;
basic_regex_quote_buf(&sb, p->pattern);
if (opt->ignore_case)
@@ -592,12 +613,12 @@ static void compile_fixed_regexp(struct grep_pat *p,
struct grep_opt *opt)
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
- int icase, ascii_only;
+ int ascii_only;
int err;
+ int regflags = REG_NEWLINE;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
- icase = opt->regflags & REG_ICASE || p->ignore_case;
ascii_only = !has_non_ascii(p->pattern);
/*
@@ -615,10 +636,10 @@ static void compile_regexp(struct grep_pat *p, struct
grep_opt *opt)
if (opt->fixed ||
has_null(p->pattern, p->patternlen) ||
is_fixed(p->pattern, p->patternlen))
- p->fixed = !icase || ascii_only;
+ p->fixed = !p->ignore_case || ascii_only;
if (p->fixed) {
- p->kws = kwsalloc(icase ? tolower_trans_tbl : NULL);
+ p->kws = kwsalloc(p->ignore_case ? tolower_trans_tbl : NULL);
kwsincr(p->kws, p->pattern, p->patternlen);
kwsprep(p->kws);
return;
@@ -642,7 +663,11 @@ static void compile_regexp(struct grep_pat *p, struct
grep_opt *opt)
return;
}
- err = regcomp(&p->regexp, p->pattern, opt->regflags);
+ if (p->ignore_case)
+ regflags |= REG_ICASE;
+ if (opt->extended_regexp_option)
+ regflags |= REG_EXTENDED;
+ err = regcomp(&p->regexp, p->pattern, regflags);
if (err) {
char errbuf[1024];
regerror(err, &p->regexp, errbuf, 1024);
diff --git a/grep.h b/grep.h
index b8f93bfc2d..0c091e5104 100644
--- a/grep.h
+++ b/grep.h
@@ -162,7 +162,6 @@ struct grep_opt {
char color_match_selected[COLOR_MAXLEN];
char color_selected[COLOR_MAXLEN];
char color_sep[COLOR_MAXLEN];
- int regflags;
unsigned pre_context;
unsigned post_context;
unsigned last_shown;
diff --git a/revision.c b/revision.c
index e181ad1b70..207103d211 100644
--- a/revision.c
+++ b/revision.c
@@ -1362,7 +1362,6 @@ void init_revisions(struct rev_info *revs, const char
*prefix)
init_grep_defaults();
grep_init(&revs->grep_filter, prefix);
revs->grep_filter.status_only = 1;
- revs->grep_filter.regflags = REG_NEWLINE;
diff_setup(&revs->diffopt);
if (prefix && !revs->diffopt.prefix) {
@@ -2022,7 +2021,6 @@ static int handle_revision_opt(struct rev_info *revs, int
argc, const char **arg
revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE;
} else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {
revs->grep_filter.ignore_case = 1;
- revs->grep_filter.regflags |= REG_ICASE;
DIFF_OPT_SET(&revs->diffopt, PICKAXE_IGNORE_CASE);
} else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) {
revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED;
--
2.13.1.611.g7e3b11ae1
