features/sparse-checkout-2.24.0

.gitignore

@@ -72,6 +72,7 @@
 /git-gc
 /git-get-tar-commit-id
 /git-grep
+/git-gvfs-helper
 /git-hash-object
 /git-help
 /git-http-backend
@@ -158,6 +159,7 @@
 /git-show-branch
 /git-show-index
 /git-show-ref
+/git-sparse-checkout
 /git-stage
 /git-stash
 /git-status

Documentation/config.txt

@@ -371,6 +371,8 @@ include::config/gui.txt[]
 
 include::config/guitool.txt[]
 
+include::config/gvfs.txt[]
+
 include::config/help.txt[]
 
 include::config/http.txt[]

Documentation/config/core.txt

@@ -661,9 +661,18 @@ core.gvfs::
 		flag just blocks them from occurring at all.
 --
 
+core.useGvfsHelper::
+	TODO
+
 core.sparseCheckout::
-	Enable "sparse checkout" feature. See section "Sparse checkout" in
-	linkgit:git-read-tree[1] for more information.
+	Enable "sparse checkout" feature. See linkgit:git-sparse-checkout[1]
+	for more information.
+
+core.sparseCheckoutCone::
+	Enables the "cone mode" of the sparse checkout feature. When the
+	sparse-checkout file contains a limited set of patterns, then this
+	mode provides significant performance advantages. See
+	linkgit:git-sparse-checkout[1] for more information.
 
 core.abbrev::
 	Set the length object names are abbreviated to.  If

Documentation/config/gvfs.txt

@@ -0,0 +1,5 @@
+gvfs.cache-server::
+	TODO
+
+gvfs.sharedcache::
+	TODO

Documentation/git-clone.txt

@@ -15,7 +15,7 @@ SYNOPSIS
 	  [--dissociate] [--separate-git-dir <git dir>]
 	  [--depth <depth>] [--[no-]single-branch] [--no-tags]
 	  [--recurse-submodules[=<pathspec>]] [--[no-]shallow-submodules]
-	  [--[no-]remote-submodules] [--jobs <n>] [--] <repository>
+	  [--[no-]remote-submodules] [--jobs <n>] [--sparse] [--] <repository>
 	  [<directory>]
 
 DESCRIPTION
@@ -156,6 +156,12 @@ objects from the source repository into a pack in the cloned repository.
 	used, neither remote-tracking branches nor the related
 	configuration variables are created.
 
+--sparse::
+	Initialize the sparse-checkout file so the working
+	directory starts with only the files in the root
+	of the repository. The sparse-checkout file can be
+	modified to grow the working directory as needed.
+
 --mirror::
 	Set up a mirror of the source repository.  This implies `--bare`.
 	Compared to `--bare`, `--mirror` not only maps local branches of the

Documentation/git-read-tree.txt

@@ -436,7 +436,7 @@ support.
 SEE ALSO
 --------
 linkgit:git-write-tree[1]; linkgit:git-ls-files[1];
-linkgit:gitignore[5]
+linkgit:gitignore[5]; linkgit:git-sparse-checkout[1];
 
 GIT
 ---

Documentation/git-sparse-checkout.txt

@@ -0,0 +1,153 @@
+git-sparse-checkout(1)
+======================
+
+NAME
+----
+git-sparse-checkout - Initialize and modify the sparse-checkout
+configuration, which reduces the checkout to a set of directories
+given by a list of prefixes.
+
+
+SYNOPSIS
+--------
+[verse]
+'git sparse-checkout <subcommand> [options]'
+
+
+DESCRIPTION
+-----------
+
+Initialize and modify the sparse-checkout configuration, which reduces
+the checkout to a set of directories given by a list of prefixes.
+
+THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
+COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
+THE FUTURE.
+
+
+COMMANDS
+--------
+'list'::
+	Provide a list of the contents in the sparse-checkout file.
+
+'init'::
+	Enable the `core.sparseCheckout` setting. If the
+	sparse-checkout file does not exist, then populate it with
+	patterns that match every file in the root directory and
+	no other directories, then will remove all directories tracked
+	by Git. Add patterns to the sparse-checkout file to
+	repopulate the working directory.
++
+To avoid interfering with other worktrees, it first enables the
+`extensions.worktreeConfig` setting and makes sure to set the
+`core.sparseCheckout` setting in the worktree-specific config file.
+
+'set'::
+	Write a set of patterns to the sparse-checkout file, as given as
+	a list of arguments following the 'set' subcommand. Update the
+	working directory to match the new patterns. Enable the
+	core.sparseCheckout config setting if it is not already enabled.
+
+'disable'::
+	Remove the sparse-checkout file, set `core.sparseCheckout` to
+	`false`, and restore the working directory to include all files.
+
+SPARSE CHECKOUT
+---------------
+
+"Sparse checkout" allows populating the working directory sparsely.
+It uses the skip-worktree bit (see linkgit:git-update-index[1]) to tell
+Git whether a file in the working directory is worth looking at. If
+the skip-worktree bit is set, then the file is ignored in the working
+directory. Git will not populate the contents of those files, which
+makes a sparse checkout helpful when working in a repository with many
+files, but only a few are important to the current user.
+
+The `$GIT_DIR/info/sparse-checkout` file is used to define the
+skip-worktree reference bitmap. When Git updates the working
+directory, it updates the skip-worktree bits in the index based
+on this file. The files matching the patterns in the file will
+appear in the working directory, and the rest will not.
+
+To enable the sparse-checkout feature, run `git sparse-checkout init` to
+initialize a simple sparse-checkout file and enable the `core.sparseCheckout`
+config setting. Then, run `git sparse-checkout set` to modify the patterns in
+the sparse-checkout file.
+
+To repopulate the working directory with all files, use the
+`git sparse-checkout disable` command.
+
+## FULL PATTERN SET
+
+By default, the sparse-checkout file uses the same syntax as `.gitignore`
+files.
+
+While `$GIT_DIR/info/sparse-checkout` is usually used to specify what
+files are included, you can also specify what files are _not_ included,
+using negative patterns. For example, to remove the file `unwanted`:
+
+----------------
+/*
+!unwanted
+----------------
+
+
+## CONE PATTERN SET
+
+The full pattern set allows for arbitrary pattern matches and complicated
+inclusion/exclusion rules. These can result in O(N*M) pattern matches when
+updating the index, where N is the number of patterns and M is the number
+of paths in the index. To combat this performance issue, a more restricted
+pattern set is allowed when `core.spareCheckoutCone` is enabled.
+
+The accepted patterns in the cone pattern set are:
+
+1. *Recursive:* All paths inside a directory are included.
+
+2. *Parent:* All files immediately inside a directory are included.
+
+In addition to the above two patterns, we also expect that all files in the
+root directory are included. If a recursive pattern is added, then all
+leading directories are added as parent patterns.
+
+By default, when running `git sparse-checkout init`, the root directory is
+added as a parent pattern. At this point, the sparse-checkout file contains
+the following patterns:
+
+```
+/*
+!/*/
+```
+
+This says "include everything in root, but nothing two levels below root."
+If we then add the folder `A/B/C` as a recursive pattern, the folders `A` and
+`A/B` are added as parent patterns. The resulting sparse-checkout file is
+now
+
+```
+/*
+!/*/
+/A/
+!/A/*/
+/A/B/
+!/A/B/*/
+/A/B/C/
+```
+
+Here, order matters, so the negative patterns are overridden by the positive
+patterns that appear lower in the file.
+
+If `core.sparseCheckoutCone=true`, then Git will parse the sparse-checkout file
+expecting patterns of these types. Git will warn if the patterns do not match.
+If the patterns do match the expected format, then Git will use faster hash-
+based algorithms to compute inclusion in the sparse-checkout.
+
+SEE ALSO
+--------
+
+linkgit:git-read-tree[1]
+linkgit:gitignore[5]
+
+GIT
+---
+Part of the linkgit:git[1] suite

Makefile

@@ -893,6 +893,7 @@ LIB_OBJS += gpg-interface.o
 LIB_OBJS += graph.o
 LIB_OBJS += grep.o
 LIB_OBJS += gvfs.o
+LIB_OBJS += gvfs-helper-client.o
 LIB_OBJS += hashmap.o
 LIB_OBJS += linear-assignment.o
 LIB_OBJS += help.o
@@ -1133,6 +1134,7 @@ BUILTIN_OBJS += builtin/shortlog.o
 BUILTIN_OBJS += builtin/show-branch.o
 BUILTIN_OBJS += builtin/show-index.o
 BUILTIN_OBJS += builtin/show-ref.o
+BUILTIN_OBJS += builtin/sparse-checkout.o
 BUILTIN_OBJS += builtin/stash.o
 BUILTIN_OBJS += builtin/stripspace.o
 BUILTIN_OBJS += builtin/submodule--helper.o
@@ -1369,6 +1371,8 @@ else
 	CURL_LIBCURL += $(shell $(CURL_CONFIG) --libs)
 endif
 
+	PROGRAM_OBJS += gvfs-helper.o
+
 	REMOTE_CURL_PRIMARY = git-remote-http$X
 	REMOTE_CURL_ALIASES = git-remote-https$X git-remote-ftp$X git-remote-ftps$X
 	REMOTE_CURL_NAMES = $(REMOTE_CURL_PRIMARY) $(REMOTE_CURL_ALIASES)
@@ -2479,6 +2483,10 @@ $(REMOTE_CURL_PRIMARY): remote-curl.o http.o http-walker.o GIT-LDFLAGS $(GITLIBS
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(CURL_LIBCURL) $(EXPAT_LIBEXPAT) $(LIBS)
 
+git-gvfs-helper$X: gvfs-helper.o http.o GIT-LDFLAGS $(GITLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
+		$(CURL_LIBCURL) $(EXPAT_LIBEXPAT) $(LIBS)
+
 $(LIB_FILE): $(LIB_OBJS)
 	$(QUIET_AR)$(RM) $@ && $(AR) $(ARFLAGS) $@ $^
 

builtin.h

@@ -225,6 +225,7 @@ int cmd_shortlog(int argc, const char **argv, const char *prefix);
 int cmd_show(int argc, const char **argv, const char *prefix);
 int cmd_show_branch(int argc, const char **argv, const char *prefix);
 int cmd_show_index(int argc, const char **argv, const char *prefix);
+int cmd_sparse_checkout(int argc, const char **argv, const char *prefix);
 int cmd_status(int argc, const char **argv, const char *prefix);
 int cmd_stash(int argc, const char **argv, const char *prefix);
 int cmd_stripspace(int argc, const char **argv, const char *prefix);

builtin/clone.c

@@ -59,6 +59,7 @@ static const char *real_git_dir;
 static char *option_upload_pack = "git-upload-pack";
 static int option_verbosity;
 static int option_progress = -1;
+static int option_sparse_checkout;
 static enum transport_family family;
 static struct string_list option_config = STRING_LIST_INIT_NODUP;
 static struct string_list option_required_reference = STRING_LIST_INIT_NODUP;
@@ -146,6 +147,8 @@ static struct option builtin_clone_options[] = {
 	OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 	OPT_BOOL(0, "remote-submodules", &option_remote_submodules,
 		    N_("any cloned submodules will use their remote-tracking branch")),
+	OPT_BOOL(0, "sparse", &option_sparse_checkout,
+		    N_("initialize sparse-checkout file to include only files at root")),
 	OPT_END()
 };
 
@@ -733,6 +736,27 @@ static void update_head(const struct ref *our, const struct ref *remote,
 	}
 }
 
+static int git_sparse_checkout_init(const char *repo)
+{
+	struct argv_array argv = ARGV_ARRAY_INIT;
+	int result = 0;
+	argv_array_pushl(&argv, "-C", repo, "sparse-checkout", "init", NULL);
+
+	/*
+	 * We must apply the setting in the current process
+	 * for the later checkout to use the sparse-checkout file.
+	 */
+	core_apply_sparse_checkout = 1;
+
+	if (run_command_v_opt(argv.argv, RUN_GIT_CMD)) {
+		error(_("failed to initialize sparse-checkout"));
+		result = 1;
+	}
+
+	argv_array_clear(&argv);
+	return result;
+}
+
 static int checkout(int submodule_progress)
 {
 	struct object_id oid;
@@ -1107,6 +1131,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (option_required_reference.nr || option_optional_reference.nr)
 		setup_reference();
 
+	if (option_sparse_checkout && git_sparse_checkout_init(repo))
+		return 1;
+
 	remote = remote_get(option_origin);
 
 	strbuf_addf(&default_refspec, "+%s*:%s*", src_ref_prefix,

builtin/index-pack.c

@@ -781,7 +781,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 	if (startup_info->have_repository) {
 		read_lock();
 		collision_test_needed =
-			has_object_file_with_flags(oid, OBJECT_INFO_QUICK);
+			has_object_file_with_flags(oid, OBJECT_INFO_FOR_PREFETCH);
 		read_unlock();
 	}
 

builtin/read-tree.c

@@ -162,6 +162,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix)
 	opts.head_idx = -1;
 	opts.src_index = &the_index;
 	opts.dst_index = &the_index;
+	opts.verbose_update = isatty(2);
 
 	git_config(git_read_tree_config, NULL);
 
@@ -185,7 +186,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix)
 
 	if (opts.reset || opts.merge || opts.prefix) {
 		if (read_cache_unmerged() && (opts.prefix || opts.merge))
-			die("You need to resolve your current index first");
+			die(_("You need to resolve your current index first"));
 		stage = opts.merge = 1;
 	}
 	resolve_undo_clear();