[PATCH 00/23] nd/sparse reroll

@@ -194,6 +194,8 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 				continue;
 			if (ce->ce_flags & CE_UPDATE)
 				continue;
+			if (ce_skip_worktree(ce))
+				continue;
 			err = lstat(ce->name, &st);
 			if (show_deleted && err)
 				show_ce_entry(tag_removed, ce);

@@ -172,29 +172,29 @@ static int process_directory(const char *path, int len, struct stat *st)
 	return error("%s: is a directory - add files inside instead", path);
 }
 
-/*
- * Process a regular file
- */
-static int process_file(const char *path, int len, struct stat *st)
-{
-	int pos = cache_name_pos(path, len);
-	struct cache_entry *ce = pos < 0 ? NULL : active_cache[pos];
-
-	if (ce && S_ISGITLINK(ce->ce_mode))
-		return error("%s is already a gitlink, not replacing", path);
-
-	return add_one_path(ce, path, len, st);
-}
-
 static int process_path(const char *path)
 {
-	int len;
+	int pos, len;
 	struct stat st;
+	struct cache_entry *ce;
 
 	len = strlen(path);
 	if (has_symlink_leading_path(path, len))
 		return error("'%s' is beyond a symbolic link", path);
 
+	pos = cache_name_pos(path, len);
+	ce = pos < 0 ? NULL : active_cache[pos];
+	if (ce && ce_skip_worktree(ce)) {
+		/*
+		 * working directory version is assumed "good"
+		 * so updating it does not make sense.
+		 * On the other hand, removing it from index should work
+		 */
+		if (allow_remove && remove_file_from_cache(path))
+			return error("%s: cannot remove from the index", path);
+		return 0;
+	}
+
 	/*
 	 * First things first: get the stat information, to decide
 	 * what to do about the pathname!

@@ -205,7 +205,13 @@ static int process_path(const char *path)
 	if (S_ISDIR(st.st_mode))
 		return process_directory(path, len, &st);
 
-	return process_file(path, len, &st);
+	/*
+	 * Process a regular file
+	 */
+	if (ce && S_ISGITLINK(ce->ce_mode))
+		return error("%s is already a gitlink, not replacing", path);
+
+	return add_one_path(ce, path, len, &st);
 }
 
 static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,

@@ -0,0 +1,114 @@
+#!/bin/sh
+#
+# Copyright (c) 2008 Nguyễn Thái Ngọc Duy
+#
+
+test_description='skip-worktree bit test'
+
+. ./test-lib.sh
+
+cat >expect.full <<EOF
+H 1
+H 2
+H init.t
+H sub/1
+H sub/2
+EOF
+
+cat >expect.skip <<EOF
+S 1
+H 2
+H init.t
+S sub/1
+H sub/2
+EOF
+
+NULL_SHA1=e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+ZERO_SHA1=0000000000000000000000000000000000000000
+setup_absent() {
+	test -f 1 && rm 1
+	git update-index --remove 1 &&
+	git update-index --add --cacheinfo 100644 $NULL_SHA1 1 &&
+	git update-index --skip-worktree 1
+}
+
+test_absent() {
+	echo "100644 $NULL_SHA1 0	1" > expected &&
+	git ls-files --stage 1 > result &&
+	test_cmp expected result &&
+	test ! -f 1
+}
+
+setup_dirty() {
+	git update-index --force-remove 1 &&
+	echo dirty > 1 &&
+	git update-index --add --cacheinfo 100644 $NULL_SHA1 1 &&
+	git update-index --skip-worktree 1
+}
+
+test_dirty() {
+	echo "100644 $NULL_SHA1 0	1" > expected &&
+	git ls-files --stage 1 > result &&
+	test_cmp expected result &&
+	echo dirty > expected
+	test_cmp expected 1
+}
+
+test_expect_success 'setup' '
+	test_commit init &&
+	mkdir sub &&
+	touch ./1 ./2 sub/1 sub/2 &&
+	git add 1 2 sub/1 sub/2 &&
+	git update-index --skip-worktree 1 sub/1 &&
+	git ls-files -t > result &&
+	test_cmp expect.skip result
+'
+
+test_expect_success 'update-index' '
+	setup_absent &&
+	git update-index 1 &&
+	test_absent
+'
+
+test_expect_success 'update-index' '
+	setup_dirty &&
+	git update-index 1 &&
+	test_dirty
+'
+
+test_expect_success 'update-index --remove' '
+	setup_absent &&
+	git update-index --remove 1 &&
+	test -z "$(git ls-files 1)" &&
+	test ! -f 1
+'
+
+test_expect_success 'update-index --remove' '
+	setup_dirty &&
+	git update-index --remove 1 &&
+	test -z "$(git ls-files 1)" &&
+	echo dirty > expected &&
+	test_cmp expected 1
+'
+
+test_expect_success 'ls-files --delete' '
+	setup_absent &&
+	test -z "$(git ls-files -d)"
+'
+
+test_expect_success 'ls-files --delete' '
+	setup_dirty &&
+	test -z "$(git ls-files -d)"
+'
+
+test_expect_success 'ls-files --modified' '
+	setup_absent &&
+	test -z "$(git ls-files -m)"
+'
+
+test_expect_success 'ls-files --modified' '
+	setup_dirty &&
+	test -z "$(git ls-files -m)"
+'
+
+test_done

@@ -152,7 +152,7 @@ static int commit_index_files(void)
 static int list_paths(struct string_list *list, const char *with_tree,
 		      const char *prefix, const char **pattern)
 {
-	int i;
+	static int i;
 	char *m;
 
 	for (i = 0; pattern[i]; i++)

@@ -164,11 +164,15 @@ static int list_paths(struct string_list *list, const char *with_tree,
 
 	for (i = 0; i < active_nr; i++) {
 		struct cache_entry *ce = active_cache[i];
+		struct string_list_item *item;
+
 		if (ce->ce_flags & CE_UPDATE)
 			continue;
 		if (!match_pathspec(pattern, ce->name, ce_namelen(ce), 0, m))
 			continue;
-		string_list_insert(ce->name, list);
+		item = string_list_insert(ce->name, list);
+		if (ce_skip_worktree(ce))
+			item->util = &i; /* better a valid pointer than a fake one */
 	}
 
 	return report_path_error(m, pattern, prefix ? strlen(prefix) : 0);

@@ -181,6 +185,9 @@ static void add_remove_files(struct string_list *list)
 		struct stat st;
 		struct string_list_item *p = &(list->items[i]);
 
+		if (p->util)
+			continue;
+
 		if (!lstat(p->string, &st)) {
 			if (add_to_cache(p->string, &st, 0))
 				die("updating files failed");

@@ -143,4 +143,16 @@ test_expect_success 'diff-files does not examine skip-worktree dirty entries' '
 	test -z "$(git diff-files -- one)"
 '
 
+test_expect_success 'commit on skip-worktree absent entries' '
+	git reset &&
+	setup_absent &&
+	test_must_fail git commit -m null 1
+'
+
+test_expect_success 'commit on skip-worktree dirty entries' '
+	git reset &&
+	setup_dirty &&
+	test_must_fail git commit -m null 1
+'
+
 test_done

@@ -439,6 +439,10 @@ On some file system/operating system combinations, this is unreliable.
 Set this config setting to 'rename' there; However, This will remove the
 check that makes sure that existing object files will not get overwritten.
 
+core.sparseCheckout::
+	Enable "sparse checkout" feature. See section "Sparse checkout" in
+	linkgit:git-read-tree[1] for more information.
+
 add.ignore-errors::
 	Tells 'git-add' to continue adding files when some files cannot be
 	added due to indexing errors. Equivalent to the '--ignore-errors'

@@ -401,7 +401,9 @@ follows:
 ----------------
 
 Then you can disable sparse checkout. Sparse checkout support in "git
-read-tree" and similar commands is disabled by default.
+read-tree" and similar commands is disabled by default. You need to
+turn `core.sparseCheckout` on in order to have sparse checkout
+support.
 
 
 SEE ALSO

@@ -528,6 +528,7 @@ extern size_t delta_base_cache_limit;
 extern int auto_crlf;
 extern int fsync_object_files;
 extern int core_preload_index;
+extern int core_apply_sparse_checkout;
 
 enum safe_crlf {
 	SAFE_CRLF_FALSE = 0,

@@ -503,6 +503,11 @@ static int git_default_core_config(const char *var, const char *value)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.sparsecheckout")) {
+		core_apply_sparse_checkout = git_config_bool(var, value);
+		return 0;
+	}
+
 	/* Add other config variables here and to Documentation/config.txt. */
 	return 0;
 }

@@ -48,6 +48,7 @@ enum push_default_type push_default = PUSH_DEFAULT_MATCHING;
 #endif
 enum object_creation_mode object_creation_mode = OBJECT_CREATION_MODE;
 int grafts_replace_parents = 1;
+int core_apply_sparse_checkout;
 
 /* Parallel index stat data preload? */
 int core_preload_index = 0;

@@ -378,6 +378,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 {
 	int ret;
 	static struct cache_entry *dfc;
+	struct exclude_list el;
 
 	if (len > MAX_UNPACK_TREES)
 		die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES);

@@ -387,6 +388,16 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 	state.quiet = 1;
 	state.refresh_cache = 1;
 
+	memset(&el, 0, sizeof(el));
+	if (!core_apply_sparse_checkout || !o->update)
+		o->skip_sparse_checkout = 1;
+	if (!o->skip_sparse_checkout) {
+		if (add_excludes_from_file_to_list(git_path("info/sparse-checkout"), "", 0, NULL, &el, 0) < 0)
+			o->skip_sparse_checkout = 1;
+		else
+			o->el = &el;
+	}
+
 	memset(&o->result, 0, sizeof(o->result));
 	o->result.initialized = 1;
 	if (o->src_index) {

@@ -407,26 +418,39 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 		info.fn = unpack_callback;
 		info.data = o;
 
-		if (traverse_trees(len, t, &info) < 0)
-			return unpack_failed(o, NULL);
+		if (traverse_trees(len, t, &info) < 0) {
+			ret = unpack_failed(o, NULL);
+			goto done;
+		}
 	}
 
 	/* Any left-over entries in the index? */
 	if (o->merge) {
 		while (o->pos < o->src_index->cache_nr) {
 			struct cache_entry *ce = o->src_index->cache[o->pos];
-			if (unpack_index_entry(ce, o) < 0)
-				return unpack_failed(o, NULL);
+			if (unpack_index_entry(ce, o) < 0) {
+				ret = unpack_failed(o, NULL);
+				goto done;
+			}
 		}
 	}
 
-	if (o->trivial_merges_only && o->nontrivial_merge)
-		return unpack_failed(o, "Merge requires file-level merging");
+	if (o->trivial_merges_only && o->nontrivial_merge) {
+		ret = unpack_failed(o, "Merge requires file-level merging");
+		goto done;
+	}
 
 	o->src_index = NULL;
 	ret = check_updates(o) ? (-2) : 0;
 	if (o->dst_index)
 		*o->dst_index = o->result;
+
+done:
+	for (i = 0;i < el.nr;i++)
+		free(el.excludes[i]);
+	if (el.excludes)
+		free(el.excludes);
+
 	return ret;
 }
 

@@ -4,6 +4,7 @@
 #define MAX_UNPACK_TREES 8
 
 struct unpack_trees_options;
+struct exclude_list;
 
 typedef int (*merge_fn_t)(struct cache_entry **src,
 		struct unpack_trees_options *options);

@@ -28,6 +29,7 @@ struct unpack_trees_options {
 		     skip_unmerged,
 		     initial_checkout,
 		     diff_index_cached,
+		     skip_sparse_checkout,
 		     gently;
 	const char *prefix;
 	int pos;

@@ -44,6 +46,8 @@ struct unpack_trees_options {
 	struct index_state *dst_index;
 	struct index_state *src_index;
 	struct index_state result;
+
+	struct exclude_list *el; /* for internal use */
 };
 
 extern int unpack_trees(unsigned n, struct tree_desc *t,

@@ -177,6 +177,9 @@ struct cache_entry {
 #define CE_HASHED    (0x100000)
 #define CE_UNHASHED  (0x200000)
 
+/* Only remove in work directory, not index */
+#define CE_WT_REMOVE (0x400000)
+
 /*
  * Extended on-disk flags
  */

@@ -78,7 +78,7 @@ static int check_updates(struct unpack_trees_options *o)
 	if (o->update && o->verbose_update) {
 		for (total = cnt = 0; cnt < index->cache_nr; cnt++) {
 			struct cache_entry *ce = index->cache[cnt];
-			if (ce->ce_flags & (CE_UPDATE | CE_REMOVE))
+			if (ce->ce_flags & (CE_UPDATE | CE_REMOVE | CE_WT_REMOVE))
 				total++;
 		}
 

@@ -92,6 +92,13 @@ static int check_updates(struct unpack_trees_options *o)
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
+		if (ce->ce_flags & CE_WT_REMOVE) {
+			display_progress(progress, ++cnt);
+			if (o->update)
+				unlink_entry(ce);
+			continue;
+		}
+
 		if (ce->ce_flags & CE_REMOVE) {
 			display_progress(progress, ++cnt);
 			if (o->update)

@@ -32,6 +32,12 @@ static struct unpack_trees_error_msgs unpack_plumbing_errors = {
 
 	/* bind_overlap */
 	"Entry '%s' overlaps with '%s'.  Cannot bind.",
+
+	/* sparse_not_uptodate_file */
+	"Entry '%s' not uptodate. Cannot update sparse checkout.",
+
+	/* would_lose_orphaned */
+	"Working tree file '%s' would be %s by sparse checkout update.",
 };
 
 #define ERRORMSG(o,fld) \

@@ -125,6 +131,57 @@ static int check_updates(struct unpack_trees_options *o)
 	return errs != 0;
 }
 
+static int verify_uptodate_sparse(struct cache_entry *ce, struct unpack_trees_options *o);
+static int verify_absent_sparse(struct cache_entry *ce, const char *action, struct unpack_trees_options *o);
+
+static int will_have_skip_worktree(const struct cache_entry *ce, struct unpack_trees_options *o)
+{
+	const char *basename;
+
+	if (ce_stage(ce))
+		return 0;
+
+	basename = strrchr(ce->name, '/');
+	basename = basename ? basename+1 : ce->name;
+	return excluded_from_list(ce->name, ce_namelen(ce), basename, NULL, o->el) <= 0;
+}
+
+static int apply_sparse_checkout(struct cache_entry *ce, struct unpack_trees_options *o)
+{
+	int was_skip_worktree = ce_skip_worktree(ce);
+
+	if (will_have_skip_worktree(ce, o))
+		ce->ce_flags |= CE_SKIP_WORKTREE;
+	else
+		ce->ce_flags &= ~CE_SKIP_WORKTREE;
+
+	/*
+	 * We only care about files getting into the checkout area
+	 * If merge strategies want to remove some, go ahead, this
+	 * flag will be removed eventually in unpack_trees() if it's
+	 * outside checkout area.
+	 */
+	if (ce->ce_flags & CE_REMOVE)
+		return 0;
+
+	if (!was_skip_worktree && ce_skip_worktree(ce)) {
+		/*
+		 * If CE_UPDATE is set, verify_uptodate() must be called already
+		 * also stat info may have lost after merged_entry() so calling
+		 * verify_uptodate() again may fail
+		 */
+		if (!(ce->ce_flags & CE_UPDATE) && verify_uptodate_sparse(ce, o))
+			return -1;
+		ce->ce_flags |= CE_WT_REMOVE;
+	}
+	if (was_skip_worktree && !ce_skip_worktree(ce)) {
+		if (verify_absent_sparse(ce, "overwritten", o))
+			return -1;
+		ce->ce_flags |= CE_UPDATE;
+	}
+	return 0;
+}
+
 static inline int call_unpack_fn(struct cache_entry **src, struct unpack_trees_options *o)
 {
 	int ret = o->fn(src, o);

@@ -376,7 +433,7 @@ static int unpack_failed(struct unpack_trees_options *o, const char *message)
  */
 int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options *o)
 {
-	int ret;
+	int i, ret;
 	static struct cache_entry *dfc;
 	struct exclude_list el;
 

@@ -440,6 +497,17 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 		goto done;
 	}
 
+	if (!o->skip_sparse_checkout) {
+		for (i = 0;i < o->result.cache_nr;i++) {
+			struct cache_entry *ce = o->result.cache[i];
+
+			if (apply_sparse_checkout(ce, o)) {
+				ret = -1;
+				goto done;
+			}
+		}
+	}
+
 	o->src_index = NULL;
 	ret = check_updates(o) ? (-2) : 0;
 	if (o->dst_index)

@@ -512,6 +580,12 @@ static int verify_uptodate(struct cache_entry *ce,
 	return verify_uptodate_1(ce, o, ERRORMSG(o, not_uptodate_file));
 }
 
+static int verify_uptodate_sparse(struct cache_entry *ce,
+				  struct unpack_trees_options *o)
+{
+	return verify_uptodate_1(ce, o, ERRORMSG(o, sparse_not_uptodate_file));
+}
+
 static void invalidate_ce_path(struct cache_entry *ce, struct unpack_trees_options *o)
 {
 	if (ce)

@@ -705,6 +779,12 @@ static int verify_absent(struct cache_entry *ce, const char *action,
 	return verify_absent_1(ce, action, o, ERRORMSG(o, would_lose_untracked));
 }
 
+static int verify_absent_sparse(struct cache_entry *ce, const char *action,
+			 struct unpack_trees_options *o)
+{
+	return verify_absent_1(ce, action, o, ERRORMSG(o, would_lose_orphaned));
+}
+
 static int merged_entry(struct cache_entry *merge, struct cache_entry *old,
 		struct unpack_trees_options *o)
 {

@@ -15,6 +15,8 @@ struct unpack_trees_error_msgs {
 	const char *not_uptodate_dir;
 	const char *would_lose_untracked;
 	const char *bind_overlap;
+	const char *sparse_not_uptodate_file;
+	const char *would_lose_orphaned;
 };
 
 struct unpack_trees_options {

@@ -360,6 +360,50 @@ middle of doing, and when your working tree is ready (i.e. you
 have finished your work-in-progress), attempt the merge again.
 
 
+Sparse checkout
+---------------
+
+"Sparse checkout" allows to sparsely populate working directory.
+It uses skip-worktree bit (see linkgit:git-update-index[1]) to tell
+Git whether a file on working directory is worth looking at.
+
+"git read-tree" and other merge-based commands ("git merge", "git
+checkout"...) can help maintaining skip-worktree bitmap and working
+directory update. `$GIT_DIR/info/sparse-checkout` is used to
+define the skip-worktree reference bitmap. When "git read-tree" needs
+to update working directory, it will reset skip-worktree bit in index
+based on this file, which uses the same syntax as .gitignore files.
+If an entry matches a pattern in this file, skip-worktree will be
+set on that entry. Otherwise, skip-worktree will be unset.
+
+Then it compares the new skip-worktree value with the previous one. If
+skip-worktree turns from unset to set, it will add the corresponding
+file back. If it turns from set to unset, that file will be removed.
+
+While `$GIT_DIR/info/sparse-checkout` is usually used to specify what
+files are in. You can also specify what files are _not_ in, using
+negate patterns. For example, to remove file "unwanted":
+
+----------------
+*
+!unwanted
+----------------
+
+Another tricky thing is fully repopulating working directory when you
+no longer want sparse checkout. You cannot just disable "sparse
+checkout" because skip-worktree are still in the index and you working
+directory is still sparsely populated. You should re-populate working
+directory with the `$GIT_DIR/info/sparse-checkout` file content as
+follows:
+
+----------------
+*
+----------------
+
+Then you can disable sparse checkout. Sparse checkout support in "git
+read-tree" and similar commands is disabled by default.
+
+
 SEE ALSO
 --------
 linkgit:git-write-tree[1]; linkgit:git-ls-files[1];

@@ -223,12 +223,12 @@ static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
 	return data;
 }
 
-static int add_excludes_from_file_1(const char *fname,
-				    const char *base,
-				    int baselen,
-				    char **buf_p,
-				    struct exclude_list *which,
-				    int check_index)
+int add_excludes_from_file_to_list(const char *fname,
+				   const char *base,
+				   int baselen,
+				   char **buf_p,
+				   struct exclude_list *which,
+				   int check_index)
 {
 	struct stat st;
 	int fd, i;

@@ -274,8 +274,8 @@ static int add_excludes_from_file_1(const char *fname,
 
 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) < 0)
+	if (add_excludes_from_file_to_list(fname, "", 0, NULL,
+					   &dir->exclude_list[EXC_FILE], 0) < 0)
 		die("cannot use %s as an exclude file", fname);
 }
 

@@ -324,9 +324,9 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 		memcpy(dir->basebuf + current, base + current,
 		       stk->baselen - current);
 		strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
-		add_excludes_from_file_1(dir->basebuf,
-					 dir->basebuf, stk->baselen,
-					 &stk->filebuf, el, 1);
+		add_excludes_from_file_to_list(dir->basebuf,
+					       dir->basebuf, stk->baselen,
+					       &stk->filebuf, el, 1);
 		dir->exclude_stack = stk;
 		current = stk->baselen;
 	}

@@ -336,9 +336,9 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 /* Scan the list and let the last match determine the fate.
  * Return 1 for exclude, 0 for include and -1 for undecided.
  */
-static int excluded_1(const char *pathname,
-		      int pathlen, const char *basename, int *dtype,
-		      struct exclude_list *el)
+int excluded_from_list(const char *pathname,
+		       int pathlen, const char *basename, int *dtype,
+		       struct exclude_list *el)
 {
 	int i;
 

@@ -412,8 +412,8 @@ int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
 
 	prep_exclude(dir, pathname, basename-pathname);
 	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
-		switch (excluded_1(pathname, pathlen, basename,
-				   dtype_p, &dir->exclude_list[st])) {
+		switch (excluded_from_list(pathname, pathlen, basename,
+					   dtype_p, &dir->exclude_list[st])) {
 		case 0:
 			return 0;
 		case 1:

@@ -69,7 +69,11 @@ extern int match_pathspec(const char **pathspec, const char *name, int namelen,
 extern int fill_directory(struct dir_struct *dir, const char **pathspec);
 extern int read_directory(struct dir_struct *, const char *path, int len, const char **pathspec);
 
+extern int excluded_from_list(const char *pathname, int pathlen, const char *basename,
+			      int *dtype, struct exclude_list *el);
 extern int excluded(struct dir_struct *, const char *, int *);
+extern int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen,
+					  char **buf_p, struct exclude_list *which, int check_index);
 extern void add_excludes_from_file(struct dir_struct *, const char *fname);
 extern void add_exclude(const char *string, const char *base,
 			int baselen, struct exclude_list *which);

@@ -517,7 +517,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached,
 		 * are identical, even if worktree file has been modified, so use
 		 * cache version instead
 		 */
-		if (cached || (ce->ce_flags & CE_VALID)) {
+		if (cached || (ce->ce_flags & CE_VALID) || ce_skip_worktree(ce)) {
 			if (ce_stage(ce))
 				continue;
 			hit |= grep_sha1(opt, ce->sha1, ce->name, 0);

@@ -111,6 +111,15 @@ test_expect_success 'ls-files --modified' '
 	test -z "$(git ls-files -m)"
 '
 
+test_expect_success 'grep with skip-worktree file' '
+	git update-index --no-skip-worktree 1 &&
+	echo test > 1 &&
+	git update-index 1 &&
+	git update-index --skip-worktree 1 &&
+	rm 1 &&
+	test "$(git grep --no-ext-grep test)" = "1:test"
+'
+
 echo ":000000 100644 $ZERO_SHA1 $NULL_SHA1 A	1" > expected
 test_expect_success 'diff-index does not examine skip-worktree absent entries' '
 	setup_absent &&

@@ -0,0 +1,139 @@
+#!/bin/sh
+#
+# Copyright (c) 2008 Nguyễn Thái Ngọc Duy
+#
+
+test_description='test worktree writing operations when skip-worktree is used'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	test_commit init &&
+	echo modified >> init.t &&
+	touch added &&
+	git add init.t added &&
+	git commit -m "modified and added" &&
+	git tag top
+'
+
+test_expect_success 'read-tree updates worktree, absent case' '
+	git checkout -f top &&
+	git update-index --skip-worktree init.t &&
+	rm init.t &&
+	git read-tree -m -u HEAD^ &&
+	echo init > expected &&
+	test_cmp expected init.t
+'
+
+test_expect_success 'read-tree updates worktree, dirty case' '
+	git checkout -f top &&
+	git update-index --skip-worktree init.t &&
+	echo dirty >> init.t &&
+	test_must_fail git read-tree -m -u HEAD^ &&
+	grep -q dirty init.t &&
+	test "$(git ls-files -t init.t)" = "S init.t" &&
+	git update-index --no-skip-worktree init.t
+'
+
+test_expect_success 'read-tree removes worktree, absent case' '
+	git checkout -f top &&
+	git update-index --skip-worktree added &&
+	rm added &&
+	git read-tree -m -u HEAD^ &&
+	test ! -f added
+'
+
+test_expect_success 'read-tree removes worktree, dirty case' '
+	git checkout -f top &&
+	git update-index --skip-worktree added &&
+	echo dirty >> added &&
+	test_must_fail git read-tree -m -u HEAD^ &&
+	grep -q dirty added &&
+	test "$(git ls-files -t added)" = "S added" &&
+	git update-index --no-skip-worktree added
+'
+
+NULL_SHA1=e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+ZERO_SHA0=0000000000000000000000000000000000000000
+setup_absent() {
+	test -f 1 && rm 1
+	git update-index --remove 1 &&
+	git update-index --add --cacheinfo 100644 $NULL_SHA1 1 &&
+	git update-index --skip-worktree 1
+}
+
+test_absent() {
+	echo "100644 $NULL_SHA1 0	1" > expected &&
+	git ls-files --stage 1 > result &&
+	test_cmp expected result &&
+	test ! -f 1
+}
+
+setup_dirty() {
+	git update-index --force-remove 1 &&
+	echo dirty > 1 &&
+	git update-index --add --cacheinfo 100644 $NULL_SHA1 1 &&
+	git update-index --skip-worktree 1
+}
+
+test_dirty() {
+	echo "100644 $NULL_SHA1 0	1" > expected &&
+	git ls-files --stage 1 > result &&
+	test_cmp expected result &&
+	echo dirty > expected
+	test_cmp expected 1
+}
+
+cat >expected <<EOF
+S 1
+H 2
+H init.t
+S sub/1
+H sub/2
+EOF
+
+test_expect_success 'index setup' '
+	git checkout -f init &&
+	mkdir sub &&
+	touch ./1 ./2 sub/1 sub/2 &&
+	git add 1 2 sub/1 sub/2 &&
+	git update-index --skip-worktree 1 sub/1 &&
+	git ls-files -t > result &&
+	test_cmp expected result
+'
+
+test_expect_success 'git-add ignores worktree content' '
+	setup_absent &&
+	git add 1 &&
+	test_absent
+'
+
+test_expect_success 'git-add ignores worktree content' '
+	setup_dirty &&
+	git add 1 &&
+	test_dirty
+'
+
+test_expect_success 'git-rm fails if worktree is dirty' '
+	setup_dirty &&
+	test_must_fail git rm 1 &&
+	test_dirty
+'
+
+cat >expected <<EOF
+Would remove expected
+Would remove result
+EOF
+test_expect_success 'git-clean, absent case' '
+	setup_absent &&
+	git clean -n > result &&
+	test_cmp expected result
+'
+
+test_expect_success 'git-clean, dirty case' '
+	setup_dirty &&
+	git clean -n > result &&
+	test_cmp expected result
+'
+
+test_done

@@ -450,7 +450,7 @@ static int verify_uptodate(struct cache_entry *ce,
 {
 	struct stat st;
 
-	if (o->index_only || o->reset || ce_uptodate(ce))
+	if (o->index_only || (!ce_skip_worktree(ce) && (o->reset || ce_uptodate(ce))))
 		return 0;
 
 	if (!lstat(ce->name, &st)) {

@@ -1004,7 +1004,7 @@ int oneway_merge(struct cache_entry **src, struct unpack_trees_options *o)
 
 	if (old && same(old, a)) {
 		int update = 0;
-		if (o->reset && !ce_uptodate(old)) {
+		if (o->reset && !ce_uptodate(old) && !ce_skip_worktree(old)) {
 			struct stat st;
 			if (lstat(old->name, &st) ||
 			    ie_match_stat(o->src_index, old, &st, CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE))

@@ -680,6 +680,8 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old,
 		} else {
 			if (verify_uptodate(old, o))
 				return -1;
+			if (ce_skip_worktree(old))
+				update |= CE_SKIP_WORKTREE;
 			invalidate_ce_path(old, o);
 		}
 	}

@@ -349,6 +349,12 @@ static int excluded_1(const char *pathname,
 			int to_exclude = x->to_exclude;
 
 			if (x->flags & EXC_FLAG_MUSTBEDIR) {
+				if (!dtype) {
+					if (!prefixcmp(pathname, exclude))
+						return to_exclude;
+					else
+						continue;
+				}
 				if (*dtype == DT_UNKNOWN)
 					*dtype = get_dtype(NULL, pathname, pathlen);
 				if (*dtype != DT_DIR)

@@ -229,10 +229,9 @@ static int add_excludes_from_file_1(const char *fname,
 
 	if (buf_p)
 		*buf_p = buf;
-	buf[size++] = '\n';
 	entry = buf;
-	for (i = 0; i < size; i++) {
-		if (buf[i] == '\n') {
+	for (i = 0; i <= size; i++) {
+		if (i == size || buf[i] == '\n') {
 			if (entry != buf + i && entry[0] != '#') {
 				buf[i - (i && buf[i-1] == '\r')] = 0;
 				add_exclude(entry, base, baselen, which);

@@ -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))`.
 

@@ -71,11 +71,13 @@ 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);
 

@@ -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();
 

@@ -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;