[RFC PATCH v4 07/19] Read .gitignore from index if it is skip-worktree

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

This adds index as a prerequisite for directory listing (with
exclude).  At the moment directory listing is used by "git clean",
"git add", "git ls-files" and "git status"/"git commit" and
unpack_trees()-related commands.  These commands have been
checked/modified to populate index before doing directory listing.

add_excludes_from_file() does not enable this feature, because it
is used to read .git/info/exclude and some explicit files specified
by "git ls-files".

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/technical/api-directory-listing.txt |    3 +
 builtin-clean.c                                   |    4 +-
 builtin-ls-files.c                                |    4 +-
 dir.c                                             |   65 ++++++++++++++------
 t/t3001-ls-files-others-exclude.sh                |   22 +++++++
 t/t7300-clean.sh                                  |   19 ++++++
 6 files changed, 95 insertions(+), 22 deletions(-)

diff --git a/Documentation/technical/api-directory-listing.txt b/Documentation/technical/api-directory-listing.txt
index 5bbd18f..add6f43 100644
--- a/Documentation/technical/api-directory-listing.txt
+++ b/Documentation/technical/api-directory-listing.txt
@@ -58,6 +58,9 @@ The result of the enumeration is left in these fields::
 Calling sequence
 ----------------
 
+Note: index may be looked at for .gitignore files that are CE_SKIP_WORKTREE
+marked. If you to exclude files, make sure you have loaded index first.
+
 * Prepare `struct dir_struct dir` and clear it with `memset(&dir, 0,
   sizeof(dir))`.
 
diff --git a/builtin-clean.c b/builtin-clean.c
index 05c763c..96ada75 100644
--- a/builtin-clean.c
+++ b/builtin-clean.c
@@ -75,11 +75,13 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 
 	dir.flags |= DIR_SHOW_OTHER_DIRECTORIES;
 
+	if (read_cache() < 0)
+		die("index file corrupt");
+
 	if (!ignored)
 		setup_standard_excludes(&dir);
 
 	pathspec = get_pathspec(prefix, argv);
-	read_cache();
 
 	fill_directory(&dir, pathspec);
 
diff --git a/builtin-ls-files.c b/builtin-ls-files.c
index ad7e447..2e47242 100644
--- a/builtin-ls-files.c
+++ b/builtin-ls-files.c
@@ -485,6 +485,9 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 		prefix_offset = strlen(prefix);
 	git_config(git_default_config, NULL);
 
+	if (read_cache() < 0)
+		die("index file corrupt");
+
 	argc = parse_options(argc, argv, prefix, builtin_ls_files_options,
 			ls_files_usage, 0);
 	if (show_tag || show_valid_bit) {
@@ -513,7 +516,6 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 	pathspec = get_pathspec(prefix, argv);
 
 	/* be nice with submodule paths ending in a slash */
-	read_cache();
 	if (pathspec)
 		strip_trailing_slash_from_submodules();
 
diff --git a/dir.c b/dir.c
index e9254d6..cda2556 100644
--- a/dir.c
+++ b/dir.c
@@ -200,11 +200,35 @@ void add_exclude(const char *string, const char *base,
 	which->excludes[which->nr++] = x;
 }
 
+static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
+{
+	int pos, len;
+	unsigned long sz;
+	enum object_type type;
+	void *data;
+	struct index_state *istate = &the_index;
+
+	len = strlen(path);
+	pos = index_name_pos(istate, path, len);
+	if (pos < 0)
+		return NULL;
+	if (!ce_skip_worktree(istate->cache[pos]))
+		return NULL;
+	data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
+	if (!data || type != OBJ_BLOB) {
+		free(data);
+		return NULL;
+	}
+	*size = xsize_t(sz);
+	return data;
+}
+
 static int add_excludes_from_file_1(const char *fname,
 				    const char *base,
 				    int baselen,
 				    char **buf_p,
-				    struct exclude_list *which)
+				    struct exclude_list *which,
+				    int check_index)
 {
 	struct stat st;
 	int fd, i;
@@ -212,20 +236,26 @@ static int add_excludes_from_file_1(const char *fname,
 	char *buf, *entry;
 
 	fd = open(fname, O_RDONLY);
-	if (fd < 0 || fstat(fd, &st) < 0)
-		goto err;
-	size = xsize_t(st.st_size);
-	if (size == 0) {
-		close(fd);
-		return 0;
+	if (fd < 0 || fstat(fd, &st) < 0) {
+		if (0 <= fd)
+			close(fd);
+		if (!check_index ||
+		    (buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
+			return -1;
 	}
-	buf = xmalloc(size+1);
-	if (read_in_full(fd, buf, size) != size)
-	{
-		free(buf);
-		goto err;
+	else {
+		size = xsize_t(st.st_size);
+		if (size == 0) {
+			close(fd);
+			return 0;
+		}
+		buf = xmalloc(size);
+		if (read_in_full(fd, buf, size) != size) {
+			close(fd);
+			return -1;
+		}
+		close(fd);
 	}
-	close(fd);
 
 	if (buf_p)
 		*buf_p = buf;
@@ -240,17 +270,12 @@ static int add_excludes_from_file_1(const char *fname,
 		}
 	}
 	return 0;
-
- err:
-	if (0 <= fd)
-		close(fd);
-	return -1;
 }
 
 void add_excludes_from_file(struct dir_struct *dir, const char *fname)
 {
 	if (add_excludes_from_file_1(fname, "", 0, NULL,
-				     &dir->exclude_list[EXC_FILE]) < 0)
+				     &dir->exclude_list[EXC_FILE], 0) < 0)
 		die("cannot use %s as an exclude file", fname);
 }
 
@@ -301,7 +326,7 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 		strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
 		add_excludes_from_file_1(dir->basebuf,
 					 dir->basebuf, stk->baselen,
-					 &stk->filebuf, el);
+					 &stk->filebuf, el, 1);
 		dir->exclude_stack = stk;
 		current = stk->baselen;
 	}
diff --git a/t/t3001-ls-files-others-exclude.sh b/t/t3001-ls-files-others-exclude.sh
index c65bca8..132c476 100755
--- a/t/t3001-ls-files-others-exclude.sh
+++ b/t/t3001-ls-files-others-exclude.sh
@@ -64,6 +64,8 @@ two/*.4
 echo '!*.2
 !*.8' >one/two/.gitignore
 
+allignores='.gitignore one/.gitignore one/two/.gitignore'
+
 test_expect_success \
     'git ls-files --others with various exclude options.' \
     'git ls-files --others \
@@ -85,6 +87,26 @@ test_expect_success \
        >output &&
      test_cmp expect output'
 
+test_expect_success 'setup skip-worktree gitignore' '
+	git add $allignores &&
+	git update-index --skip-worktree $allignores &&
+	rm $allignores
+'
+
+test_expect_success \
+    'git ls-files --others with various exclude options.' \
+    'git ls-files --others \
+       --exclude=\*.6 \
+       --exclude-per-directory=.gitignore \
+       --exclude-from=.git/ignore \
+       >output &&
+     test_cmp expect output'
+
+test_expect_success 'restore gitignore' '
+	git checkout $allignores &&
+	rm .git/index
+'
+
 cat > excludes-file <<\EOF
 *.[1-8]
 e*
diff --git a/t/t7300-clean.sh b/t/t7300-clean.sh
index 118c6eb..7d8ed68 100755
--- a/t/t7300-clean.sh
+++ b/t/t7300-clean.sh
@@ -22,6 +22,25 @@ test_expect_success 'setup' '
 
 '
 
+test_expect_success 'git clean with skip-worktree .gitignore' '
+	git update-index --skip-worktree .gitignore &&
+	rm .gitignore &&
+	mkdir -p build docs &&
+	touch a.out src/part3.c docs/manual.txt obj.o build/lib.so &&
+	git clean &&
+	test -f Makefile &&
+	test -f README &&
+	test -f src/part1.c &&
+	test -f src/part2.c &&
+	test ! -f a.out &&
+	test ! -f src/part3.c &&
+	test -f docs/manual.txt &&
+	test -f obj.o &&
+	test -f build/lib.so &&
+	git update-index --no-skip-worktree .gitignore &&
+	git checkout .gitignore
+'
+
 test_expect_success 'git clean' '
 
 	mkdir -p build docs &&
-- 
1.6.3.GIT