clone: add --sparse mode

When someone wants to clone a large repository, but plans to work
using a sparse-checkout file, they either need to do a full
checkout first and then reduce the patterns they included, or
clone with --no-checkout, set up their patterns, and then run
a checkout manually. This requires knowing a lot about the repo
shape and how sparse-checkout works.

Add a new '--sparse' option to 'git clone' that initializes the
sparse-checkout file to include the following patterns:

	/*
	!/*/

These patterns include every file in the root directory, but
no directories. This allows a repo to include files like a
README or a bootstrapping script to grow enlistments from that
point.

During the 'git sparse-checkout init' call, we must first look
to see if HEAD is valid, since 'git clone' does not have a valid
HEAD at the point where it initializes the sparse-checkout. The
following checkout within the clone command will create the HEAD
ref and update the working directory correctly.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
index 34011c2940ad4b4d3115e3ddc41f18f8a00ecd01..0fe91d2f04766b69a66c4f5bf0ceb5aabd2ba868 100644 (file)
--- a/Documentation/git-clone.txt
+++ b/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

diff --git a/builtin/clone.c b/builtin/clone.c
index c46ee29f0ad57958199804ab4fd4bef209bb0bc6..4348d962c9c81e4f6681eb53163b4f1278952153 100644 (file)
--- a/builtin/clone.c
+++ b/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;
@@ -1106,6 +1130,9 @@ 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,

diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
index fcf97e9df8ec0d314d84a8f1166e87f06d5d0ce2..e3418fbe2a6b3e2e2481e7395daad7c1c123a9da 100644 (file)
--- a/builtin/sparse-checkout.c
+++ b/builtin/sparse-checkout.c
@@ -102,6 +102,7 @@ static int sparse_checkout_init(int argc, const char **argv)
        char *sparse_filename;
        FILE *fp;
        int res;
+       struct object_id oid;
 
        if (set_config(MODE_ALL_PATTERNS))
                return 1;
@@ -126,6 +127,11 @@ static int sparse_checkout_init(int argc, const char **argv)
        fprintf(fp, "/*\n!/*/\n");
        fclose(fp);
 
+       if (get_oid("HEAD", &oid)) {
+               /* assume we are in a fresh repo */
+               return 0;
+       }
+
 reset_dir:
        return update_working_directory();
 }

diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index 21143c529c698fea641e26e9bfd4313fed278ded..78c20cb7e342f7df3d2aba7a60820c9aad4fb069 100755 (executable)
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -82,4 +82,17 @@ test_expect_success 'init with existing sparse-checkout' '
        test_cmp expect dir
 '
 
+test_expect_success 'clone --sparse' '
+       git clone --sparse repo clone &&
+       git -C clone sparse-checkout list >actual &&
+       cat >expect <<-EOF &&
+               /*
+               !/*/
+       EOF
+       test_cmp expect actual &&
+       ls clone >dir &&
+       echo a >expect &&
+       test_cmp expect dir
+'
+
 test_done