[PATCH v2 00/14] Sparse checkout

@@ -109,6 +109,26 @@ struct ondisk_cache_entry {
 	char name[FLEX_ARRAY]; /* more */
 };
 
+/*
+ * This struct is used when CE_EXTENDED bit is 1
+ * The struct must match ondisk_cache_entry exactly from
+ * ctime till flags
+ */
+struct ondisk_cache_entry_extended {
+	struct cache_time ctime;
+	struct cache_time mtime;
+	unsigned int dev;
+	unsigned int ino;
+	unsigned int mode;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned int size;
+	unsigned char sha1[20];
+	unsigned short flags;
+	unsigned short flags2;
+	char name[FLEX_ARRAY]; /* more */
+};
+
 struct cache_entry {
 	unsigned int ce_ctime;
 	unsigned int ce_mtime;

@@ -130,7 +150,15 @@ struct cache_entry {
 #define CE_VALID     (0x8000)
 #define CE_STAGESHIFT 12
 
-/* In-memory only */
+/*
+ * Range 0xFFFF0000 in ce_flags is divided into
+ * two parts: in-memory flags and on-disk ones.
+ * Flags in CE_EXTENDED_FLAGS will get saved on-disk
+ * if you want to save a new flag, add it in
+ * CE_EXTENDED_FLAGS
+ *
+ * In-memory only flags
+ */
 #define CE_UPDATE    (0x10000)
 #define CE_REMOVE    (0x20000)
 #define CE_UPTODATE  (0x40000)

@@ -140,6 +168,24 @@ struct cache_entry {
 #define CE_UNHASHED  (0x200000)
 
 /*
+ * Extended on-disk flags
+ */
+/* CE_EXTENDED2 is for future extension */
+#define CE_EXTENDED2 0x80000000
+
+#define CE_EXTENDED_FLAGS (0)
+
+/*
+ * Safeguard to avoid saving wrong flags:
+ *  - CE_EXTENDED2 won't get saved until its semantic is known
+ *  - Bits in 0x0000FFFF have been saved in ce_flags already
+ *  - Bits in 0x003F0000 are currently in-memory flags
+ */
+#if CE_EXTENDED_FLAGS & 0x80CFFFFF
+#error "CE_EXTENDED_FLAGS out of range"
+#endif
+
+/*
  * Copy the sha1 and stat state of a cache entry from one to
  * another. But we never change the name, or the hash state!
  */

@@ -171,7 +217,9 @@ static inline size_t ce_namelen(const struct cache_entry *ce)
 }
 
 #define ce_size(ce) cache_entry_size(ce_namelen(ce))
-#define ondisk_ce_size(ce) ondisk_cache_entry_size(ce_namelen(ce))
+#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \
+			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
+			    ondisk_cache_entry_size(ce_namelen(ce)))
 #define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT)
 #define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE)
 #define ce_mark_uptodate(ce) ((ce)->ce_flags |= CE_UPTODATE)

@@ -214,8 +262,10 @@ static inline int ce_to_dtype(const struct cache_entry *ce)
 	(S_ISREG(mode) ? (S_IFREG | ce_permissions(mode)) : \
 	S_ISLNK(mode) ? S_IFLNK : S_ISDIR(mode) ? S_IFDIR : S_IFGITLINK)
 
-#define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7)
-#define ondisk_cache_entry_size(len) ((offsetof(struct ondisk_cache_entry,name) + (len) + 8) & ~7)
+#define flexible_size(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7)
+#define cache_entry_size(len) flexible_size(cache_entry,len)
+#define ondisk_cache_entry_size(len) flexible_size(ondisk_cache_entry,len)
+#define ondisk_cache_entry_extended_size(len) flexible_size(ondisk_cache_entry_extended,len)
 
 struct index_state {
 	struct cache_entry **cache;

@@ -1096,7 +1096,7 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size)
 
 	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
 		return error("bad signature");
-	if (hdr->hdr_version != htonl(2))
+	if (hdr->hdr_version != htonl(2) && hdr->hdr_version != htonl(3))
 		return error("bad index version");
 	SHA1_Init(&c);
 	SHA1_Update(&c, hdr, size - 20);

@@ -1131,6 +1131,7 @@ int read_index(struct index_state *istate)
 static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
 {
 	size_t len;
+	const char *name;
 
 	ce->ce_ctime = ntohl(ondisk->ctime.sec);
 	ce->ce_mtime = ntohl(ondisk->mtime.sec);

@@ -1143,19 +1144,31 @@ static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_en
 	/* On-disk flags are just 16 bits */
 	ce->ce_flags = ntohs(ondisk->flags);
 
-	/* For future extension: we do not understand this entry yet */
-	if (ce->ce_flags & CE_EXTENDED)
-		die("Unknown index entry format");
 	hashcpy(ce->sha1, ondisk->sha1);
 
 	len = ce->ce_flags & CE_NAMEMASK;
+
+	if (ce->ce_flags & CE_EXTENDED) {
+		struct ondisk_cache_entry_extended *ondisk2;
+		int extended_flags;
+		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
+		extended_flags = ntohs(ondisk2->flags2) << 16;
+		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
+		if (extended_flags & ~CE_EXTENDED_FLAGS)
+			die("Unknown index entry format %08x", extended_flags);
+		ce->ce_flags |= extended_flags;
+		name = ondisk2->name;
+	}
+	else
+		name = ondisk->name;
+
 	if (len == CE_NAMEMASK)
-		len = strlen(ondisk->name);
+		len = strlen(name);
 	/*
 	 * NEEDSWORK: If the original index is crafted, this copy could
 	 * go unchecked.
 	 */
-	memcpy(ce->name, ondisk->name, len + 1);
+	memcpy(ce->name, name, len + 1);
 }
 
 static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)

@@ -1415,6 +1428,7 @@ static int ce_write_entry(SHA_CTX *c, int fd, struct cache_entry *ce)
 {
 	int size = ondisk_ce_size(ce);
 	struct ondisk_cache_entry *ondisk = xcalloc(1, size);
+	char *name;
 
 	ondisk->ctime.sec = htonl(ce->ce_ctime);
 	ondisk->ctime.nsec = 0;

@@ -1428,7 +1442,15 @@ static int ce_write_entry(SHA_CTX *c, int fd, struct cache_entry *ce)
 	ondisk->size = htonl(ce->ce_size);
 	hashcpy(ondisk->sha1, ce->sha1);
 	ondisk->flags = htons(ce->ce_flags);
-	memcpy(ondisk->name, ce->name, ce_namelen(ce));
+	if (ce->ce_flags & CE_EXTENDED) {
+		struct ondisk_cache_entry_extended *ondisk2;
+		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
+		ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
+		name = ondisk2->name;
+	}
+	else
+		name = ondisk->name;
+	memcpy(name, ce->name, ce_namelen(ce));
 
 	return ce_write(c, fd, ondisk, size);
 }

@@ -1437,16 +1459,25 @@ int write_index(const struct index_state *istate, int newfd)
 {
 	SHA_CTX c;
 	struct cache_header hdr;
-	int i, err, removed;
+	int i, err, removed, extended;
 	struct cache_entry **cache = istate->cache;
 	int entries = istate->cache_nr;
 
-	for (i = removed = 0; i < entries; i++)
+	for (i = removed = extended = 0; i < entries; i++) {
 		if (cache[i]->ce_flags & CE_REMOVE)
 			removed++;
 
+		/* reduce extended entries if possible */
+		cache[i]->ce_flags &= ~CE_EXTENDED;
+		if (cache[i]->ce_flags & CE_EXTENDED_FLAGS) {
+			extended++;
+			cache[i]->ce_flags |= CE_EXTENDED;
+		}
+	}
+
 	hdr.hdr_signature = htonl(CACHE_SIGNATURE);
-	hdr.hdr_version = htonl(2);
+	/* for extended format, increase version so older git won't try to read it */
+	hdr.hdr_version = htonl(extended ? 3 : 2);
 	hdr.hdr_entries = htonl(entries - removed);
 
 	SHA1_Init(&c);

@@ -171,6 +171,39 @@ the reflog for HEAD where you were, e.g.
 $ git log -g -2 HEAD
 ------------
 
+Sparse checkout
+---------------
+
+Normally when you checkout a branch, your working directory
+will be fully populated. In some situations, you just need to
+work on certain files, no full checkout is needed. Sparse
+checkout is a mode that limits the checkout area according to your
+needs. With sparse checkout, you can work on a single file, a
+collection of files, a subdirectory or a collection of separated
+subdirectories.
+
+Because sparse checkout uses a new index format, it will be
+incompatible with git prior to 1.6.0 regarding worktree operations.
+Operations that only need access to the repository itself, such as
+clone, push, or pull/fetch from another (normal) repository... should
+not be affected by sparse checkout.
+
+In sparse checkout mode, checkout status of every files in your
+working directory will be recorded in index. If a file is marked
+"no-checkout", it means that file is not needed to be present in
+working directory by user or any git command. When a new file is added
+to index, it will be marked "checkout" unless sparse patterns are
+applied.  Unmerged files are always "checkout". When you checkout new
+files using "git checkout <file>" they will be automatically marked
+"checkout". Other commands such as "git apply" can also checkout new
+files if they are needed.
+
+"No-checkout" status is very similar to "assume-unchanged bit"
+(see linkgit:git-update-index[1]). The main difference between them
+is "assume unchanged" bit just ignores corresponding files in working
+directory while sparse checkout goes a bit farther, remove those files
+when it is safe to do so.
+
 
 EXAMPLES
 --------

@@ -170,10 +170,11 @@ struct cache_entry {
 /*
  * Extended on-disk flags
  */
+#define CE_NO_CHECKOUT 0x40000000
 /* CE_EXTENDED2 is for future extension */
 #define CE_EXTENDED2 0x80000000
 
-#define CE_EXTENDED_FLAGS (0)
+#define CE_EXTENDED_FLAGS (CE_NO_CHECKOUT)
 
 /*
  * Safeguard to avoid saving wrong flags:

@@ -185,6 +186,9 @@ struct cache_entry {
 #error "CE_EXTENDED_FLAGS out of range"
 #endif
 
+/* "Assume unchanged" mask */
+#define CE_VALID_MASK (CE_VALID | CE_NO_CHECKOUT)
+
 /*
  * Copy the sha1 and stat state of a cache entry from one to
  * another. But we never change the name, or the hash state!

@@ -222,6 +226,10 @@ static inline size_t ce_namelen(const struct cache_entry *ce)
 			    ondisk_cache_entry_size(ce_namelen(ce)))
 #define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT)
 #define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE)
+#define ce_no_checkout(ce) ((ce)->ce_flags & CE_NO_CHECKOUT)
+#define ce_checkout(ce) (!ce_no_checkout(ce))
+#define ce_mark_no_checkout(ce) ((ce)->ce_flags |= CE_NO_CHECKOUT)
+#define ce_mark_checkout(ce) ((ce)->ce_flags &= ~CE_NO_CHECKOUT)
 #define ce_mark_uptodate(ce) ((ce)->ce_flags |= CE_UPTODATE)
 
 #define ce_permissions(mode) (((mode) & 0100) ? 0755 : 0644)

@@ -254,7 +254,7 @@ int ie_match_stat(const struct index_state *istate,
 	 * If it's marked as always valid in the index, it's
 	 * valid whatever the checked-out copy says.
 	 */
-	if (!ignore_valid && (ce->ce_flags & CE_VALID))
+	if (!ignore_valid && (ce->ce_flags & CE_VALID_MASK))
 		return 0;
 
 	changed = ce_match_stat_basic(ce, st);

@@ -962,10 +962,10 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate,
 		return ce;
 
 	/*
-	 * CE_VALID means the user promised us that the change to
+	 * CE_VALID_MASK means the user promised us that the change to
 	 * the work tree does not matter and told us not to worry.
 	 */
-	if (!ignore_valid && (ce->ce_flags & CE_VALID)) {
+	if (!ignore_valid && (ce->ce_flags & CE_VALID_MASK)) {
 		ce_mark_uptodate(ce);
 		return ce;
 	}

@@ -24,8 +24,8 @@ static int info_only;
 static int force_remove;
 static int verbose;
 static int mark_valid_only;
-#define MARK_VALID 1
-#define UNMARK_VALID 2
+#define MARK_FLAG 1
+#define UNMARK_FLAG 2
 
 static void report(const char *fmt, ...)
 {

@@ -40,19 +40,15 @@ static void report(const char *fmt, ...)
 	va_end(vp);
 }
 
-static int mark_valid(const char *path)
+static int mark_ce_flags(const char *path, int flag, int mark)
 {
 	int namelen = strlen(path);
 	int pos = cache_name_pos(path, namelen);
 	if (0 <= pos) {
-		switch (mark_valid_only) {
-		case MARK_VALID:
-			active_cache[pos]->ce_flags |= CE_VALID;
-			break;
-		case UNMARK_VALID:
-			active_cache[pos]->ce_flags &= ~CE_VALID;
-			break;
-		}
+		if (mark)
+			active_cache[pos]->ce_flags |= flag;
+		else
+			active_cache[pos]->ce_flags &= ~flag;
 		cache_tree_invalidate_path(active_cache_tree, path);
 		active_cache_changed = 1;
 		return 0;

@@ -276,7 +272,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 		goto free_return;
 	}
 	if (mark_valid_only) {
-		if (mark_valid(p))
+		if (mark_ce_flags(p, CE_VALID, mark_valid_only == MARK_FLAG))
 			die("Unable to mark file %s", path);
 		goto free_return;
 	}

@@ -649,11 +645,11 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 				continue;
 			}
 			if (!strcmp(path, "--assume-unchanged")) {
-				mark_valid_only = MARK_VALID;
+				mark_valid_only = MARK_FLAG;
 				continue;
 			}
 			if (!strcmp(path, "--no-assume-unchanged")) {
-				mark_valid_only = UNMARK_VALID;
+				mark_valid_only = UNMARK_FLAG;
 				continue;
 			}
 			if (!strcmp(path, "--info-only")) {

@@ -10,8 +10,9 @@ SYNOPSIS
 --------
 [verse]
 'git ls-files' [-z] [-t] [-v]
-		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])\*
+		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified|orphaned|no-checkout])\*
 		(-[c|d|o|i|s|u|k|m])\*
+		[--sparse]
 		[-x <pattern>|--exclude=<pattern>]
 		[-X <file>|--exclude-from=<file>]
 		[--exclude-per-directory=<file>]

@@ -32,7 +33,9 @@ OPTIONS
 -------
 -c::
 --cached::
-	Show cached files in the output (default)
+	Show cached files in the output (default). When used with --sparse,
+	show only cached files that are marked "checkout", no-checkout
+	entries will be excluded.
 
 -d::
 --deleted::

@@ -72,6 +75,21 @@ OPTIONS
 	to file/directory conflicts for checkout-index to
 	succeed.
 
+--no-checkout::
+	Show no-checkout entries. This option implies --sparse.
+
+--orphaned::
+	Show orphaned entries. Orphaned entries are no-checkout
+	entries that are present in working directory. This option
+	implies --sparse.
+
+--sparse::
+	When --sparse is passed, cached files will be divided into two
+	parts: checkout entries and no-checkout entries.
+	--cached will only show checkout entries.
+	No-checkout entries can be shown using --orphaned or
+	--no-checkout (or both).
+
 -z::
 	\0 line termination on output.
 

@@ -107,6 +125,8 @@ OPTIONS
 	Identify the file status with the following tags (followed by
 	a space) at the start of each line:
 	H::	cached
+	-::	no-checkout entries
+	O::	orphaned entries
 	M::	unmerged
 	R::	removed/deleted
 	C::	modified/changed

@@ -20,6 +20,9 @@ static int show_unmerged;
 static int show_modified;
 static int show_killed;
 static int show_valid_bit;
+static int show_orphaned;
+static int show_no_checkout;
+static int sparse_checkout;
 static int line_terminator = '\n';
 
 static int prefix_len;

@@ -35,6 +38,8 @@ static const char *tag_removed = "";
 static const char *tag_other = "";
 static const char *tag_killed = "";
 static const char *tag_modified = "";
+static const char *tag_orphaned = "";
+static const char *tag_no_checkout = "";
 
 
 /*

@@ -235,7 +240,7 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 		if (show_killed)
 			show_killed_files(dir);
 	}
-	if (show_cached | show_stage) {
+	if (show_cached | show_stage | show_orphaned | show_no_checkout) {
 		for (i = 0; i < active_nr; i++) {
 			struct cache_entry *ce = active_cache[i];
 			int dtype = ce_to_dtype(ce);

@@ -245,6 +250,16 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 				continue;
 			if (ce->ce_flags & CE_UPDATE)
 				continue;
+			if (sparse_checkout && ce_no_checkout(ce)) {
+				struct stat st;
+				if (show_no_checkout)
+					show_ce_entry(tag_no_checkout, ce);
+				if (show_orphaned && !lstat(ce->name, &st))
+					show_ce_entry(tag_orphaned, ce);
+				continue;
+			}
+			if (!(show_cached | show_stage))
+				continue;
 			show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce);
 		}
 	}

@@ -257,7 +272,7 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 			if (excluded(dir, ce->name, &dtype) != dir->show_ignored)
 				continue;
 			err = lstat(ce->name, &st);
-			if (show_deleted && err)
+			if (show_deleted && err && ce_checkout(ce))
 				show_ce_entry(tag_removed, ce);
 			if (show_modified && ce_modified(ce, &st, 0))
 				show_ce_entry(tag_modified, ce);

@@ -423,7 +438,8 @@ int report_path_error(const char *ps_matched, const char **pathspec, int prefix_
 }
 
 static const char ls_files_usage[] =
-	"git ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* "
+	"git ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified|orphaned|no-checkout])* "
+	"[ --sparse ] "
 	"[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] "
 	"[ --exclude-per-directory=<filename> ] [--exclude-standard] "
 	"[--full-name] [--abbrev] [--] [<file>]*";

@@ -457,6 +473,8 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 			tag_modified = "C ";
 			tag_other = "? ";
 			tag_killed = "K ";
+			tag_orphaned = "O ";
+			tag_no_checkout = "- ";
 			if (arg[1] == 'v')
 				show_valid_bit = 1;
 			continue;

@@ -465,6 +483,21 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 			show_cached = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--sparse")) {
+			sparse_checkout = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--orphaned")) {
+			show_orphaned = 1;
+			sparse_checkout = 1;
+			require_work_tree = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--no-checkout")) {
+			show_no_checkout = 1;
+			sparse_checkout = 1;
+			continue;
+		}
 		if (!strcmp(arg, "-d") || !strcmp(arg, "--deleted")) {
 			show_deleted = 1;
 			continue;

@@ -593,7 +626,7 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 
 	/* With no flags, we default to showing the cached files */
 	if (!(show_stage | show_deleted | show_others | show_unmerged |
-	      show_killed | show_modified))
+	      show_killed | show_modified | show_orphaned | show_no_checkout))
 		show_cached = 1;
 
 	read_cache();

@@ -147,6 +147,7 @@ test-date
 test-delta
 test-dump-cache-tree
 test-genrandom
+test-index-version
 test-match-trees
 test-parse-options
 test-path-utils

@@ -196,7 +196,8 @@ to index, it will be marked "checkout" unless sparse patterns are
 applied.  Unmerged files are always "checkout". When you checkout new
 files using "git checkout <file>" they will be automatically marked
 "checkout". Other commands such as "git apply" can also checkout new
-files if they are needed.
+files if they are needed. linkgit:git-update-index[1] can be used to
+update "checkout/no-checkout" status in index.
 
 "No-checkout" status is very similar to "assume-unchanged bit"
 (see linkgit:git-update-index[1]). The main difference between them

@@ -15,6 +15,7 @@ SYNOPSIS
 	     [--cacheinfo <mode> <object> <file>]\*
 	     [--chmod=(+|-)x]
 	     [--assume-unchanged | --no-assume-unchanged]
+	     [--checkout | --no-checkout]
 	     [--ignore-submodules]
 	     [--really-refresh] [--unresolve] [--again | -g]
 	     [--info-only] [--index-info]

@@ -99,6 +100,18 @@ in the index e.g. when merging in a commit;
 thus, in case the assumed-untracked file is changed upstream,
 you will need to handle the situation manually.
 
+--checkout::
+--no-checkout::
+	When one of these flags is specified, the object name recorded
+	for the paths are not updated. Instead, these options
+	set and unset the "no-checkout" bit for the paths. This
+	bit is used for marking files for sparse checkout. If
+	a path is marked "no-checkout", then it should not be
+	checked out unless requested by user or needed for a git
+	command to function.
+	See linkgit:git-checkout[1] for more information about
+	sparse checkout.
+
 -g::
 --again::
 	Runs 'git-update-index' itself on the paths whose index

@@ -1327,7 +1327,7 @@ endif
 
 ### Testing rules
 
-TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-parse-options$X test-path-utils$X
+TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-parse-options$X test-path-utils$X test-index-version$X
 
 all:: $(TEST_PROGRAMS)
 

@@ -24,6 +24,7 @@ static int info_only;
 static int force_remove;
 static int verbose;
 static int mark_valid_only;
+static int mark_no_checkout_only;
 #define MARK_FLAG 1
 #define UNMARK_FLAG 2
 

@@ -276,6 +277,11 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 			die("Unable to mark file %s", path);
 		goto free_return;
 	}
+	if (mark_no_checkout_only) {
+		if (mark_ce_flags(p, CE_NO_CHECKOUT, mark_no_checkout_only == MARK_FLAG))
+			die("Unable to mark file %s", path);
+		goto free_return;
+	}
 
 	if (force_remove) {
 		if (remove_file_from_cache(p))

@@ -386,7 +392,7 @@ static void read_index_info(int line_termination)
 }
 
 static const char update_index_usage[] =
-"git update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again | -g] [--ignore-missing] [-z] [--verbose] [--] <file>...";
+"git update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--checkout|--no-checkout] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again | -g] [--ignore-missing] [-z] [--verbose] [--] <file>...";
 
 static unsigned char head_sha1[20];
 static unsigned char merge_head_sha1[20];

@@ -652,6 +658,14 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 				mark_valid_only = UNMARK_FLAG;
 				continue;
 			}
+			if (!strcmp(path, "--checkout")) {
+				mark_no_checkout_only = UNMARK_FLAG;
+				continue;
+			}
+			if (!strcmp(path, "--no-checkout")) {
+				mark_no_checkout_only = MARK_FLAG;
+				continue;
+			}
 			if (!strcmp(path, "--info-only")) {
 				info_only = 1;
 				continue;

@@ -0,0 +1,36 @@
+#!/bin/sh
+#
+# Copyright (c) 2008 Nguyễn Thái Ngọc Duy
+#
+
+test_description='git update-index no-checkout bits (a.k.a sparse checkout)'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	mkdir sub &&
+	touch 1 2 sub/1 sub/2 &&
+	git add 1 2 sub/1 sub/2
+'
+
+test_expect_success 'index is at version 2' '
+	test "$(test-index-version < .git/index)" = 2
+'
+
+test_expect_success 'update-index --no-checkout' '
+	git update-index --no-checkout 1 sub/1 &&
+	test -z "$(git ls-files --sparse|grep 1)"'
+
+test_expect_success 'index is at version 3 after having some no-checkout entries' '
+	test "$(test-index-version < .git/index)" = 3
+'
+
+test_expect_success 'update-index --checkout' '
+	git update-index --checkout 1 sub/1 &&
+	test "$(git ls-files)" = "$(git ls-files --sparse)"'
+
+test_expect_success 'index version is back to 2 when there is no no-checkout entry' '
+	test "$(test-index-version < .git/index)" = 2
+'
+
+test_done

@@ -0,0 +1,14 @@
+#include "cache.h"
+
+int main(int argc, const char **argv)
+{
+	struct cache_header hdr;
+	int version;
+
+	memset(&hdr,0,sizeof(hdr));
+	if (read(0, &hdr, sizeof(hdr)) != sizeof(hdr))
+		return 0;
+	version = ntohl(hdr.hdr_version);
+	printf("%d\n", version);
+	return 0;
+}

@@ -0,0 +1,40 @@
+#!/bin/sh
+
+test_description="test ls-files in --sparse mode"
+
+. test-lib.sh
+
+test_ls_files() {
+	T=../t3004/$1.expected
+	shift
+	test_expect_success "ls-files $*" "git ls-files $* > result && test_cmp $T result"
+}
+
+test_expect_success 'setup' '
+	touch other orphaned no-checkout cached modified deleted &&
+	git add orphaned no-checkout cached modified deleted &&
+	git update-index --no-checkout orphaned no-checkout &&
+	echo modified >> modified &&
+	rm no-checkout deleted
+'
+
+test_ls_files cached
+test_ls_files cached --cached
+test_ls_files sparse-cached --sparse
+test_ls_files sparse-cached --sparse --cached
+test_ls_files no-checkout --no-checkout
+test_ls_files no-checkout --sparse --no-checkout
+test_ls_files orphaned --orphaned
+test_ls_files orphaned --sparse --orphaned
+test_ls_files orphaned-no-checkout -v --no-checkout --orphaned
+test_ls_files orphaned-no-checkout -v --sparse --no-checkout --orphaned
+test_ls_files deleted --deleted
+test_ls_files deleted --sparse --deleted
+test_ls_files modified --modified
+test_ls_files modified --sparse --modified
+test_ls_files others --others
+test_ls_files others --sparse --others
+test_ls_files everything -v --cached --deleted --modified --others
+test_ls_files sparse-everything -v --cached --no-checkout --orphaned --deleted --modified --others
+
+test_done

@@ -0,0 +1,5 @@
+cached
+deleted
+modified
+no-checkout
+orphaned

@@ -0,0 +1 @@
+deleted

@@ -0,0 +1,10 @@
+? other
+? result
+H cached
+H deleted
+H modified
+H no-checkout
+H orphaned
+R deleted
+C deleted
+C modified

@@ -0,0 +1,2 @@
+deleted
+modified

@@ -0,0 +1,2 @@
+no-checkout
+orphaned

@@ -0,0 +1,3 @@
+- no-checkout
+- orphaned
+O orphaned

@@ -0,0 +1 @@
+orphaned

@@ -0,0 +1,2 @@
+other
+result

@@ -0,0 +1,3 @@
+cached
+deleted
+modified

@@ -0,0 +1,11 @@
+? other
+? result
+H cached
+H deleted
+H modified
+- no-checkout
+- orphaned
+O orphaned
+R deleted
+C deleted
+C modified

@@ -161,7 +161,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 				continue;
 		}
 
-		if (ce_uptodate(ce))
+		if (ce_uptodate(ce) || ce_no_checkout(ce))
 			continue;
 
 		changed = check_removed(ce, &st);

@@ -348,6 +348,8 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	struct rev_info *revs = cbdata->revs;
 	int match_missing, cached;
 
+	/* if the entry is not checked out, don't examine work tree */
+	cached = o->index_only || (idx && ce_no_checkout(idx));
 	/*
 	 * Backward compatibility wart - "diff-index -m" does
 	 * not mean "do not ignore merges", but "match_missing".

@@ -355,7 +357,6 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	 * But with the revision flag parsing, that's found in
 	 * "!revs->ignore_merges".
 	 */
-	cached = o->index_only;
 	match_missing = !revs->ignore_merges;
 
 	if (cached && idx && ce_stage(idx)) {

@@ -1793,8 +1793,10 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 
 	/*
 	 * If ce matches the file in the work tree, we can reuse it.
+	 * For sparse checkout case, ce_uptodate() may be true although
+	 * the file may or may not exist in the work tree.
 	 */
-	if (ce_uptodate(ce) ||
+	if ((ce_uptodate(ce) && ce_checkout(ce)) ||
 	    (!lstat(name, &st) && !ce_match_stat(ce, &st, 0)))
 		return 1;
 

@@ -24,7 +24,9 @@ SYNOPSIS
 DESCRIPTION
 -----------
 Look for specified patterns in the working tree files, blobs
-registered in the index file, or given tree objects.
+registered in the index file, or given tree objects. By default
+it will search in the working tree files. When in sparse checkout
+mode, it only searches checked-out files.
 
 
 OPTIONS

@@ -343,6 +343,8 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 			continue;
 		if (!pathspec_matches(paths, ce->name))
 			continue;
+		if (ce_no_checkout(ce))
+			continue;
 		name = ce->name;
 		if (name[0] == '-') {
 			int len = ce_namelen(ce);

@@ -404,8 +406,11 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 				continue;
 			hit |= grep_sha1(opt, ce->sha1, ce->name, 0);
 		}
-		else
+		else {
+			if (ce_no_checkout(ce))
+				continue;
 			hit |= grep_file(opt, ce->name);
+		}
 		if (ce_stage(ce)) {
 			do {
 				nr++;

@@ -230,5 +230,6 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *t
 	} else if (state->not_new)
 		return 0;
 	create_directories(path, state);
+	ce_mark_checkout(ce);
 	return write_entry(ce, path, state, 0);
 }

@@ -205,6 +205,51 @@ is "assume unchanged" bit just ignores corresponding files in working
 directory while sparse checkout goes a bit farther, remove those files
 when it is safe to do so.
 
+Sparse patterns
+---------------
+
+Sparse patterns specify how do you want to form your checkout area.
+Many patterns can be specified on one line, separated by colons.
+The patterns specify what files should or should not be checked out
+on working directory (depends on the option used with the patterns).
+Patterns have the following format:
+
+ - An optional prefix '!' which negates the pattern; any
+   matching file by a previous pattern will become
+   unmatched again.  If a negated pattern matches, this will
+   override lower precedence patterns sources.
+
+ - If the pattern ends with a slash, it is removed for the
+   purpose of the following description, but it would only find
+   a match with a directory.  In other words, `foo/` will match a
+   directory `foo` and paths underneath it, but will not match a
+   regular file or a symbolic link `foo` (this is consistent
+   with the way how pathspec works in general in git).
+
+ - If the pattern does not contain a slash '/', git treats it as
+   a shell glob pattern and checks for a match against the
+   pathname without leading directories.
+
+ - Otherwise, git treats the pattern as a shell glob suitable
+   for consumption by fnmatch(3) with the FNM_PATHNAME flag:
+   wildcards in the pattern will not match a / in the pathname.
+   For example, "Documentation/\*.html" matches
+   "Documentation/git.html" but not
+   "Documentation/ppc/ppc.html".  A leading slash matches the
+   beginning of the pathname; for example, "/*.c" matches
+   "cat-file.c" but not "mozilla-sha1/sha1.c".
+
+ - Patterns begin with a slash will match against full pathname,
+   as opposed to normal case when it only matches pathnames relative
+   to current working directory.
+
+ - Patterns begin with "./" are treated like normal patterns. That is
+   it will follow above rules. But since it has a slash inside,
+   "fnmatch rule" will apply. This is a work-around when you do not
+   want to apply "no slash" rule.
+
+ - Because colons are used to separate patterns, you cannot put them
+   in patterns directly. You must quote them using backslash.
 
 EXAMPLES
 --------

@@ -12,7 +12,7 @@ SYNOPSIS
 'git ls-files' [-z] [-t] [-v]
 		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified|orphaned|no-checkout])\*
 		(-[c|d|o|i|s|u|k|m])\*
-		[--sparse]
+		[--sparse] [--narrow-match=<sparse patterns>]
 		[-x <pattern>|--exclude=<pattern>]
 		[-X <file>|--exclude-from=<file>]
 		[--exclude-per-directory=<file>]

@@ -90,6 +90,12 @@ OPTIONS
 	No-checkout entries can be shown using --orphaned or
 	--no-checkout (or both).
 
+--narrow-match=<sparse patterns>::
+	This option can be used to test sparse patterns. The given sparse patterns will
+	be used to filter ls-files output. Entries not matching the spec will be
+	ignored. This option can only be used with --cached or --stage.
+	See linkgit:git-checkout[1] for more information about sparse patterns.
+
 -z::
 	\0 line termination on output.
 

@@ -10,6 +10,8 @@
 #include "dir.h"
 #include "builtin.h"
 #include "tree.h"
+#include "tree-walk.h"
+#include "unpack-trees.h"
 
 static int abbrev;
 static int show_deleted;

@@ -31,6 +33,7 @@ static const char **pathspec;
 static int error_unmatch;
 static char *ps_matched;
 static const char *with_tree;
+static struct narrow_spec *narrow_spec;
 
 static const char *tag_cached = "";
 static const char *tag_unmerged = "";

@@ -187,7 +190,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	int len = prefix_len;
 	int offset = prefix_offset;
 
-	if (len >= ce_namelen(ce))
+	if (len >= ce_namelen(ce) && !narrow_spec)
 		die("git ls-files: internal error - cache entry not superset of prefix");
 
 	if (pathspec && !pathspec_match(pathspec, ps_matched, ce->name, len))

@@ -260,6 +263,8 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 			}
 			if (!(show_cached | show_stage))
 				continue;
+			if (narrow_spec && !match_narrow_spec(narrow_spec, ce->name))
+				continue;
 			show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce);
 		}
 	}

@@ -439,7 +444,7 @@ int report_path_error(const char *ps_matched, const char **pathspec, int prefix_
 
 static const char ls_files_usage[] =
 	"git ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified|orphaned|no-checkout])* "
-	"[ --sparse ] "
+	"[ --sparse ] [--narrow-match=<narrow_spec>] "
 	"[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] "
 	"[ --exclude-per-directory=<filename> ] [--exclude-standard] "
 	"[--full-name] [--abbrev] [--] [<file>]*";

@@ -498,6 +503,10 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 			sparse_checkout = 1;
 			continue;
 		}
+		if (!prefixcmp(arg, "--narrow-match=")) {
+			narrow_spec = parse_narrow_spec(arg+15, prefix);
+			continue;
+		}
 		if (!strcmp(arg, "-d") || !strcmp(arg, "--deleted")) {
 			show_deleted = 1;
 			continue;

@@ -629,8 +638,14 @@ int cmd_ls_files(int argc, const char **argv, const char *prefix)
 	      show_killed | show_modified | show_orphaned | show_no_checkout))
 		show_cached = 1;
 
+	if (narrow_spec && !show_cached && !show_stage)
+		die("ls-files: --narrow-match can only be used with either --cached or --stage");
+
+	if (narrow_spec && narrow_spec->has_root && prefix_offset != 0)
+		die("ls-files: --narrow-match with root matching patterns requires --full-name");
+
 	read_cache();
-	if (prefix)
+	if (prefix && (!narrow_spec || !narrow_spec->has_root))
 		prune_cache(prefix);
 	if (with_tree) {
 		/*

@@ -0,0 +1,39 @@
+#!/bin/sh
+
+test_description='This test is for narrow spec matching'
+
+. test-lib.sh
+
+D="$(cd ..;pwd)"/t3003
+
+test_pattern() {
+	test_expect_success "pattern $1" '
+		(
+		if [ -n "'$3'" ]; then cd '$3'; fi
+		git ls-files --full-name --narrow-match="'"$2"'" > result &&
+		diff -u result "'"$D/$1"'"
+		)
+	'
+}
+
+test_expect_success 'setup' '
+	touch 1 2 3 "1:2" &&
+	mkdir -p sub/subsub &&
+	touch sub/1 sub/2 sub/3 &&
+	touch sub/subsub/1 sub/subsub/2 sub/subsub/3 &&
+	git add .
+'
+
+test_pattern 1 1
+test_pattern sub sub
+test_pattern sub-1 1 sub
+test_pattern root-sub-1 /1 sub
+test_pattern subsub-slash subsub/ sub
+test_pattern sub-only 'sub/:!sub/subsub/'
+test_pattern 12 1:2
+test_pattern cur-12 ./1:./2
+test_pattern slash-1 'sub/*1'
+test_pattern clone-escape '1\:2:1'
+
+test_done
+

@@ -0,0 +1,3 @@
+1
+sub/1
+sub/subsub/1

@@ -0,0 +1,6 @@
+1
+2
+sub/1
+sub/2
+sub/subsub/1
+sub/subsub/2

@@ -0,0 +1,4 @@
+1
+1:2
+sub/1
+sub/subsub/1

@@ -0,0 +1,2 @@
+1
+2

@@ -0,0 +1 @@
+1

@@ -0,0 +1 @@
+sub/1

@@ -0,0 +1,2 @@
+sub/1
+sub/subsub/1

@@ -0,0 +1,3 @@
+sub/1
+sub/2
+sub/3

@@ -0,0 +1,3 @@
+sub/subsub/1
+sub/subsub/2
+sub/subsub/3

@@ -726,6 +726,142 @@ static void show_stage_entry(FILE *o,
 }
 #endif
 
+struct narrow_spec *parse_narrow_spec(const char *spec, const char *prefix)
+{
+	struct narrow_spec *ns;
+	struct narrow_pattern *p;
+	const char *start = spec, *end;
+	int has_wildcards, has_slashes;
+
+	ns = xmalloc(sizeof(*ns));
+	memset(ns, 0, sizeof(*ns));
+	if (prefix)
+		ns->prefix = xstrdup(prefix);
+
+	while (*start) {
+		end = start;
+		has_slashes = has_wildcards = 0;
+		while (*end && *end != ':') {
+			if (*end == '*' || *end == '[' || *end == '?')
+				has_wildcards = 1;
+			if (*end == '/')
+				has_slashes = 1;
+			if (*end == '\\') {
+				end++;
+				has_wildcards = 1;
+				if (*end == '\0') /* trailing backslash */
+					break;
+			}
+			end++;
+		}
+		if (start == end)
+			continue;
+
+		p = xmalloc(offsetof(struct narrow_pattern, pattern)+(end-start)+1);
+		p->negative = *start == '!';
+		if (p->negative)
+			start++;
+		p->has_slashes = has_slashes;
+		p->has_wildcards = has_wildcards;
+		p->has_trailing_slash = end[-1] == '/';
+		p->has_root = *start == '/';
+		if (p->has_root)
+			start++;
+		else if (*start == '.' && start[1] == '/')
+			start += 2;
+		p->len = end-start;
+		memcpy(p->pattern, start, p->len);
+		p->pattern[p->len] = '\0';
+
+		ALLOC_GROW(ns->patterns, ns->nr + 1, ns->alloc);
+		ns->patterns[ns->nr++] = p;
+		ns->has_root |= p->has_root;
+
+		if (*end != ':')
+			break;
+		start = end + 1;
+	}
+	return ns;
+}
+
+int match_narrow_spec(struct narrow_spec *spec, const char *path)
+{
+	int i, prefix_len = 0;
+
+	if (!spec || !spec->nr)
+		return 1; /* always match if spec is NULL */
+
+	if (spec->prefix) {
+		/*
+		 * optimization:
+		 * if there is no pattern with leading slash
+		 * then it is safe to only match inside prefix
+		 */
+		if (!spec->has_root && prefixcmp(path, spec->prefix))
+			return 0;
+		prefix_len = strlen(spec->prefix);
+	}
+
+	for (i = spec->nr - 1;i >= 0; i--) {
+		struct narrow_pattern *p = spec->patterns[i];
+		const char *new_path = path + prefix_len;
+		int match;
+
+		if (p->has_root)
+			new_path = path; /* match full path */
+		else if (spec->has_root) {
+			if (prefixcmp(path, spec->prefix))
+				continue;
+		}
+		/* !spec->has_root case has been handled above */
+
+		if (p->has_trailing_slash) {
+			/* the only "wildcard" here is backslash escape */
+			if (p->has_wildcards) {
+				char *unescaped_pattern = xstrdup(p->pattern);
+				char *src, *dst;
+
+				src = dst = unescaped_pattern;
+				while (*src) {
+					if (*src == '\\')
+						src++;
+					if (src != dst)
+						*dst = *src;
+					src++;
+					dst++;
+				}
+				*dst = '\0';
+				match = prefixcmp(new_path, unescaped_pattern) == 0;
+				free(unescaped_pattern);
+			}
+			else
+				match = prefixcmp(new_path, p->pattern) == 0;
+		}
+		else if (p->has_slashes) {
+			if (p->has_wildcards)
+				match = fnmatch(p->pattern, new_path, FNM_PATHNAME) == 0;
+			else
+				match = strcmp(p->pattern, new_path) == 0;
+		}
+		else {
+			const char *basename = strrchr(path + prefix_len, '/');
+			if (basename)
+				basename++;
+			else
+				basename = path + prefix_len;
+			if (p->has_wildcards)
+				match = fnmatch(p->pattern, basename, 0) == 0;
+			else
+				match = strcmp(p->pattern, basename) == 0;
+		}
+		if (match)
+			return p->negative ? 0 : 1;
+	}
+
+	/* no pattern is matched */
+	return 0;
+}
+
 int threeway_merge(struct cache_entry **stages, struct unpack_trees_options *o)
 {
 	struct cache_entry *index;