Re: [PATCH 3/9] clone: add --sparse mode

> On Tue, Aug 20, 2019 at 8:12 AM Derrick Stolee via GitGitGadget
> <gitgitgadget@gmail.com> wrote:
>>
>> From: Derrick Stolee <dstolee@microsoft.com>
>>
>> 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.
> 
> Nice.
> 
>>
>> Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
>> ---
>>  Documentation/git-clone.txt        |  8 +++++++-
>>  builtin/clone.c                    | 27 +++++++++++++++++++++++++++
>>  t/t1091-sparse-checkout-builtin.sh | 13 +++++++++++++
>>  3 files changed, 47 insertions(+), 1 deletion(-)
>>
>> diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
>> index 34011c2940..0fe91d2f04 100644
>> --- 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 f665b28ccc..d6d49a73ff 100644
>> --- a/builtin/clone.c
>> +++ b/builtin/clone.c
>> @@ -60,6 +60,7 @@ 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;
>> @@ -147,6 +148,8 @@ 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()
>>  };
>>
>> @@ -734,6 +737,27 @@ 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;
>> +       }
> 
> Sigh...so much forking of additional processes.  I'd really rather
> that we were reducing how much of this we are doing in the codebase
> instead of adding more.  Every fork makes following stuff in a
> debugger harder.

>> +
>> +       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,
>> diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
>> index 35ab84aabd..b7d5f15830 100755
>> --- a/t/t1091-sparse-checkout-builtin.sh
>> +++ b/t/t1091-sparse-checkout-builtin.sh
>> @@ -87,4 +87,17 @@ 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
> 
> Checking that a toplevel entry is present, but not checking that an
> entry from a subdir is missing as expected?