archive: don't add empty directories to archives

While git doesn't track empty directories, git archive can be tricked
into putting some into archives.  One way is to construct an empty tree
object, as t5004 does.  While that is supported by the object database,
it can't be represented in the index and thus it's unlikely to occur in
the wild.

Another way is using the literal name of a directory in an exclude
pathspec -- its contents are are excluded, but the directory stub is
included.  That's inconsistent: exclude pathspecs containing wildcards
don't leave empty directories in the archive.

Yet another way is have a few levels of nested subdirectories (e.g.
d1/d2/d3/file1) and ignoring the entries at the leaves (e.g. file1).
The directories with the ignored content are ignored as well (e.g. d3),
but their empty parents are included (e.g. d2).

As empty directories are not supported by git, they should also not be
written into archives.  If an empty directory is really needed then it
can be tracked and archived by placing an empty .gitignore file in it.

There already is a mechanism in place for suppressing empty directories.
When read_tree_recursive() encounters a directory excluded by a pathspec
then it enters it anyway because it might contain included entries.  It
calls the callback function before it is able to decide if the directory
is actually needed.  For that reason git archive adds directories to a
queue and writes entries for them only when it encounters the first
child item -- but currently only if pathspecs with wildcards are used.

Queue *all* directories, no matter if there even are pathspecs present.
This prevents git archive from writing entries for empty directories in
all cases.

Suggested-by: Jeff King <peff@peff.net>
Signed-off-by: Rene Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: rscharfe

archive.c

@@ -121,11 +121,6 @@ static int check_attr_export_subst(const struct attr_check *check)
 	return check && ATTR_TRUE(check->items[1].value);
 }
 
-static int should_queue_directories(const struct archiver_args *args)
-{
-	return args->pathspec.has_wildcard;
-}
-
 static int write_archive_entry(const unsigned char *sha1, const char *base,
 		int baselen, const char *filename, unsigned mode, int stage,
 		void *context)
@@ -147,7 +142,7 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 		strbuf_addch(&path, '/');
 	path_without_prefix = path.buf + args->baselen;
 
-	if (!S_ISDIR(mode) || !should_queue_directories(args)) {
+	if (!S_ISDIR(mode)) {
 		const struct attr_check *check;
 		check = get_archive_attrs(path_without_prefix);
 		if (check_attr_export_ignore(check))
@@ -169,14 +164,6 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 	return write_entry(args, sha1, path.buf, path.len, mode);
 }
 
-static int write_archive_entry_buf(const unsigned char *sha1, struct strbuf *base,
-		const char *filename, unsigned mode, int stage,
-		void *context)
-{
-	return write_archive_entry(sha1, base->buf, base->len,
-				     filename, mode, stage, context);
-}
-
 static void queue_directory(const unsigned char *sha1,
 		struct strbuf *base, const char *filename,
 		unsigned mode, int stage, struct archiver_context *c)
@@ -290,9 +277,7 @@ int write_archive_entries(struct archiver_args *args,
 	}
 
 	err = read_tree_recursive(args->tree, "", 0, 0, &args->pathspec,
-				  should_queue_directories(args) ?
-				  queue_or_write_archive_entry :
-				  write_archive_entry_buf,
+				  queue_or_write_archive_entry,
 				  &context);
 	if (err == READ_TREE_RECURSIVE)
 		err = 0;

t/t5001-archive-attr.sh

@@ -73,7 +73,7 @@ test_expect_missing	archive-pathspec/ignored-by-tree
 test_expect_missing	archive-pathspec/ignored-by-tree.d
 test_expect_missing	archive-pathspec/ignored-by-tree.d/file
 test_expect_exists	archive-pathspec/ignored-by-worktree
-test_expect_missing	archive-pathspec/excluded-by-pathspec.d failure
+test_expect_missing	archive-pathspec/excluded-by-pathspec.d
 test_expect_missing	archive-pathspec/excluded-by-pathspec.d/file
 
 test_expect_success 'git archive with wildcard pathspec' '

t/t5002-archive-attr-pattern.sh

@@ -76,7 +76,7 @@ test_expect_missing	archive/deep/and/slashless/ &&
 test_expect_missing	archive/deep/and/slashless/foo &&
 test_expect_missing	archive/deep/with/wildcard/ &&
 test_expect_missing	archive/deep/with/wildcard/foo &&
-test_expect_exists	archive/one-level-lower/
+test_expect_missing	archive/one-level-lower/
 test_expect_missing	archive/one-level-lower/two-levels-lower/ignored-only-if-dir/
 test_expect_missing	archive/one-level-lower/two-levels-lower/ignored-ony-if-dir/ignored-by-ignored-dir
 

t/t5004-archive-corner-cases.sh

@@ -108,14 +108,14 @@ test_expect_success 'archive empty subtree with no pathspec' '
 	git archive --format=tar $root_tree >subtree-all.tar &&
 	make_dir extract &&
 	"$TAR" xf subtree-all.tar -C extract &&
-	check_dir extract sub
+	check_dir extract
 '
 
 test_expect_success 'archive empty subtree by direct pathspec' '
 	git archive --format=tar $root_tree -- sub >subtree-path.tar &&
 	make_dir extract &&
 	"$TAR" xf subtree-path.tar -C extract &&
-	check_dir extract sub
+	check_dir extract
 '
 
 ZIPINFO=zipinfo