dir: fix treatment of negated pathspecs

do_match_pathspec() started life as match_pathspec_depth_1() and for
correctness was only supposed to be called from match_pathspec_depth().
match_pathspec_depth() was later renamed to match_pathspec(), so the
invariant we expect today is that do_match_pathspec() has no direct
callers outside of match_pathspec().

Unfortunately, this intention was lost with the renames of the two
functions, and additional calls to do_match_pathspec() were added in
commits 75a6315 ("ls-files: add pathspec matching for submodules",
2016-10-07) and 89a1f4a ("dir: if our pathspec might match files
under a dir, recurse into it", 2019-09-17).  Of course,
do_match_pathspec() had an important advantge over match_pathspec() --
match_pathspec() would hardcode flags to one of two values, and these
new callers needed to pass some other value for flags.  Also, although
calling do_match_pathspec() directly was incorrect, there likely wasn't
any difference in the observable end output, because the bug just meant
that fill_diretory() would recurse into unneeded directories.  Since
subsequent does-this-path-match checks on individual paths under the
directory would cause those extra paths to be filtered out, the only
difference from using the wrong function was unnecessary computation.

The second of those bad calls to do_match_pathspec() was involved -- via
either direct movement or via copying+editing -- into a number of later
refactors.  See commits 777b420 ("dir: synchronize
treat_leading_path() and read_directory_recursive()", 2019-12-19),
8d92fb2 ("dir: replace exponential algorithm with a linear one",
2020-04-01), and 95c11ec ("Fix error-prone fill_directory() API; make
it only return matches", 2020-04-01).  The last of those introduced the
usage of do_match_pathspec() on an individual file, and thus resulted in
individual paths being returned that shouldn't be.

The problem with calling do_match_pathspec() instead of match_pathspec()
is that any negated patterns such as ':!unwanted_path` will be ignored.
Add a new match_pathspec_with_flags() function to fulfill the needs of
specifying special flags while still correctly checking negated
patterns, add a big comment above do_match_pathspec() to prevent others
from misusing it, and correct current callers of do_match_pathspec() to
instead use either match_pathspec() or match_pathspec_with_flags().

One final note is that DO_MATCH_LEADING_PATHSPEC needs special
consideration when working with DO_MATCH_EXCLUDE.  The point of
DO_MATCH_LEADING_PATHSPEC is that if we have a pathspec like
   */Makefile
and we are checking a directory path like
   src/module/component
that we want to consider it a match so that we recurse into the
directory because it _might_ have a file named Makefile somewhere below.
However, when we are using an exclusion pattern, i.e. we have a pathspec
like
   :(exclude)*/Makefile
we do NOT want to say that a directory path like
   src/module/component
is a (negative) match.  While there *might* be a file named 'Makefile'
somewhere below that directory, there could also be other files and we
cannot pre-emptively rule all the files under that directory out; we
need to recurse and then check individual files.  Adjust the
DO_MATCH_LEADING_PATHSPEC logic to only get activated for positive
pathspecs.

Reported-by: John Millikin <[email protected]>
Signed-off-by: Elijah Newren <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: newren

dir.c

@@ -364,7 +364,8 @@ static int match_pathspec_item(const struct index_state *istate,
 		return MATCHED_FNMATCH;
 
 	/* Perform checks to see if "name" is a leading string of the pathspec */
-	if (flags & DO_MATCH_LEADING_PATHSPEC) {
+	if ( (flags & DO_MATCH_LEADING_PATHSPEC) &&
+	    !(flags & DO_MATCH_EXCLUDE)) {
 		/* name is a literal prefix of the pathspec */
 		int offset = name[namelen-1] == '/' ? 1 : 0;
 		if ((namelen < matchlen) &&
@@ -401,6 +402,10 @@ static int match_pathspec_item(const struct index_state *istate,
 }
 
 /*
+ * do_match_pathspec() is meant to ONLY be called by
+ * match_pathspec_with_flags(); calling it directly risks pathspecs
+ * like ':!unwanted_path' being ignored.
+ *
  * Given a name and a list of pathspecs, returns the nature of the
  * closest (i.e. most specific) match of the name to any of the
  * pathspecs.
@@ -486,13 +491,12 @@ static int do_match_pathspec(const struct index_state *istate,
 	return retval;
 }
 
-int match_pathspec(const struct index_state *istate,
-		   const struct pathspec *ps,
-		   const char *name, int namelen,
-		   int prefix, char *seen, int is_dir)
+static int match_pathspec_with_flags(const struct index_state *istate,
+				     const struct pathspec *ps,
+				     const char *name, int namelen,
+				     int prefix, char *seen, unsigned flags)
 {
 	int positive, negative;
-	unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
 	positive = do_match_pathspec(istate, ps, name, namelen,
 				     prefix, seen, flags);
 	if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
@@ -503,6 +507,16 @@ int match_pathspec(const struct index_state *istate,
 	return negative ? 0 : positive;
 }
 
+int match_pathspec(const struct index_state *istate,
+		   const struct pathspec *ps,
+		   const char *name, int namelen,
+		   int prefix, char *seen, int is_dir)
+{
+	unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
+	return match_pathspec_with_flags(istate, ps, name, namelen,
+					 prefix, seen, flags);
+}
+
 /**
  * Check if a submodule is a superset of the pathspec
  */
@@ -511,11 +525,11 @@ int submodule_path_match(const struct index_state *istate,
 			 const char *submodule_name,
 			 char *seen)
 {
-	int matched = do_match_pathspec(istate, ps, submodule_name,
-					strlen(submodule_name),
-					0, seen,
-					DO_MATCH_DIRECTORY |
-					DO_MATCH_LEADING_PATHSPEC);
+	int matched = match_pathspec_with_flags(istate, ps, submodule_name,
+						strlen(submodule_name),
+						0, seen,
+						DO_MATCH_DIRECTORY |
+						DO_MATCH_LEADING_PATHSPEC);
 	return matched;
 }
 
@@ -1686,9 +1700,11 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	 * for matching patterns.
 	 */
 	if (pathspec && !excluded) {
-		matches_how = do_match_pathspec(istate, pathspec, dirname, len,
-						0 /* prefix */, NULL /* seen */,
-						DO_MATCH_LEADING_PATHSPEC);
+		matches_how = match_pathspec_with_flags(istate, pathspec,
+							dirname, len,
+							0 /* prefix */,
+							NULL /* seen */,
+							DO_MATCH_LEADING_PATHSPEC);
 		if (!matches_how)
 			return path_none;
 	}
@@ -2120,9 +2136,9 @@ static enum path_treatment treat_path(struct dir_struct *dir,
 		if (excluded)
 			return path_excluded;
 		if (pathspec &&
-		    !do_match_pathspec(istate, pathspec, path->buf, path->len,
-				       0 /* prefix */, NULL /* seen */,
-				       0 /* flags */))
+		    !match_pathspec(istate, pathspec, path->buf, path->len,
+				    0 /* prefix */, NULL /* seen */,
+				    0 /* is_dir */))
 			return path_none;
 		return path_untracked;
 	}

t/t6132-pathspec-exclude.sh

@@ -211,4 +211,37 @@ test_expect_success 't_e_i() exclude case #8' '
 	)
 '
 
+test_expect_success 'grep --untracked PATTERN' '
+	# This test is not an actual test of exclude patterns, rather it
+	# is here solely to ensure that if any tests are inserted, deleted, or
+	# changed above, that we still have untracked files with the expected
+	# contents for the NEXT two tests.
+	cat <<-\EOF >expect-grep &&
+	actual
+	expect
+	sub/actual
+	sub/expect
+	EOF
+	git grep -l --untracked file -- >actual-grep &&
+	test_cmp expect-grep actual-grep
+'
+
+test_expect_success 'grep --untracked PATTERN :(exclude)DIR' '
+	cat <<-\EOF >expect-grep &&
+	actual
+	expect
+	EOF
+	git grep -l --untracked file -- ":(exclude)sub" >actual-grep &&
+	test_cmp expect-grep actual-grep
+'
+
+test_expect_success 'grep --untracked PATTERN :(exclude)*FILE' '
+	cat <<-\EOF >expect-grep &&
+	actual
+	sub/actual
+	EOF
+	git grep -l --untracked file -- ":(exclude)*expect" >actual-grep &&
+	test_cmp expect-grep actual-grep
+'
+
 test_done