Sparse-checkout builtin: upstreamable version

.gitignore

@@ -158,6 +158,7 @@
 /git-show-branch
 /git-show-index
 /git-show-ref
+/git-sparse-checkout
 /git-stage
 /git-stash
 /git-status

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 +1,90 @@
+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.
+
+
+COMMANDS
+--------
+'list'::
+	Provide a list of the contents in the sparse-checkout file.
+
+
+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 `$GIT_DIR/info/sparse-checkout` file is used to define the
+skip-worktree reference bitmap. When Git updates the working
+directory, it resets the skip-worktree bit in the index based on this
+file. If an entry
+matches a pattern in this file, skip-worktree will not be set on
+that entry. Otherwise, skip-worktree will be set.
+
+Then it compares the new skip-worktree value with the previous one. If
+skip-worktree turns from set to unset, it will add the corresponding
+file back. If it turns from unset to set, that file will be removed.
+
+## FULL PATTERN SET
+
+By default, the sparse-checkout file uses the same syntax as `.gitignore`
+files.
+
+While `$GIT_DIR/info/sparse-checkout` is usually used to specify what
+files are in, you can also specify what files are _not_ in, using
+negate patterns. For example, to remove the file `unwanted`:
+
+----------------
+/*
+!unwanted
+----------------
+
+Another tricky thing is fully repopulating the working directory when you
+no longer want sparse checkout. You cannot just disable "sparse
+checkout" because skip-worktree bits are still in the index and your working
+directory is still sparsely populated. You should re-populate the 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. You need to
+set `core.sparseCheckout` to `true` in order to have sparse checkout
+support.
+
+SEE ALSO
+--------
+
+linkgit:git-read-tree[1]
+linkgit:gitignore[1]
+
+GIT
+---
+Part of the linkgit:git[1] suite

Makefile

@@ -1126,6 +1126,7 @@ 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

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/sparse-checkout.c

@@ -0,0 +1,90 @@
+#include "builtin.h"
+#include "config.h"
+#include "dir.h"
+#include "parse-options.h"
+#include "pathspec.h"
+#include "repository.h"
+#include "run-command.h"
+#include "strbuf.h"
+
+static char const * const builtin_sparse_checkout_usage[] = {
+	N_("git sparse-checkout [list]"),
+	NULL
+};
+
+struct opts_sparse_checkout {
+	const char *subcommand;
+	int read_stdin;
+} opts;
+
+static char *get_sparse_checkout_filename(void)
+{
+	return git_pathdup("info/sparse-checkout");
+}
+
+static void write_excludes_to_file(FILE *fp, struct exclude_list *el)
+{
+	int i;
+
+	for (i = 0; i < el->nr; i++) {
+		struct exclude *x = el->excludes[i];
+
+		if (x->flags & EXC_FLAG_NEGATIVE)
+			fprintf(fp, "!");
+
+		fprintf(fp, "%s", x->pattern);
+
+		if (x->flags & EXC_FLAG_MUSTBEDIR)
+			fprintf(fp, "/");
+
+		fprintf(fp, "\n");
+	}
+}
+
+static int sparse_checkout_list(int argc, const char **argv)
+{
+	struct exclude_list el;
+	char *sparse_filename;
+	int res;
+
+	memset(&el, 0, sizeof(el));
+
+	sparse_filename = get_sparse_checkout_filename();
+	res = add_excludes_from_file_to_list(sparse_filename, "", 0, &el, NULL);
+	free(sparse_filename);
+
+	if (res < 0) {
+		warning(_("failed to parse sparse-checkout file; it may not exist"));
+		return 0;
+	}
+
+	write_excludes_to_file(stdout, &el);
+	clear_exclude_list(&el);
+
+	return 0;
+}
+
+int cmd_sparse_checkout(int argc, const char **argv, const char *prefix)
+{
+	static struct option builtin_sparse_checkout_options[] = {
+		OPT_END(),
+	};
+
+	if (argc == 2 && !strcmp(argv[1], "-h"))
+		usage_with_options(builtin_sparse_checkout_usage,
+				   builtin_sparse_checkout_options);
+
+	git_config(git_default_config, NULL);
+	argc = parse_options(argc, argv, prefix,
+			     builtin_sparse_checkout_options,
+			     builtin_sparse_checkout_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (argc > 0) {
+		if (!strcmp(argv[0], "list"))
+			return sparse_checkout_list(argc, argv);
+	}
+
+	usage_with_options(builtin_sparse_checkout_usage,
+			   builtin_sparse_checkout_options);
+}

git.c

@@ -573,6 +573,7 @@ static struct cmd_struct commands[] = {
 	{ "show-branch", cmd_show_branch, RUN_SETUP },
 	{ "show-index", cmd_show_index },
 	{ "show-ref", cmd_show_ref, RUN_SETUP },
+	{ "sparse-checkout", cmd_sparse_checkout, RUN_SETUP | NEED_WORK_TREE },
 	{ "stage", cmd_add, RUN_SETUP | NEED_WORK_TREE },
 	/*
 	 * NEEDSWORK: Until the builtin stash is thoroughly robust and no

t/t1091-sparse-checkout-builtin.sh

@@ -0,0 +1,50 @@
+#!/bin/sh
+
+test_description='sparse checkout builtin tests'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	git init repo &&
+	(
+		cd repo &&
+		echo "initial" >a &&
+		mkdir folder1 folder2 deep &&
+		mkdir deep/deeper1 deep/deeper2 &&
+		mkdir deep/deeper1/deepest &&
+		cp a folder1 &&
+		cp a folder2 &&
+		cp a deep &&
+		cp a deep/deeper1 &&
+		cp a deep/deeper2 &&
+		cp a deep/deeper1/deepest &&
+		git add . &&
+		git commit -m "initial commit"
+	)
+'
+
+test_expect_success 'git sparse-checkout list (empty)' '
+	git -C repo sparse-checkout list >list 2>err &&
+	test_line_count = 0 list &&
+	test_i18ngrep "failed to parse sparse-checkout file; it may not exist" err
+'
+
+test_expect_success 'git sparse-checkout list (populated)' '
+	test_when_finished rm -f repo/.git/info/sparse-checkout &&
+	cat >repo/.git/info/sparse-checkout <<-EOF &&
+		/folder1/*
+		/deep/
+		**/a
+		!*bin*
+	EOF
+	git -C repo sparse-checkout list >list &&
+	cat >expect <<-EOF &&
+		/folder1/*
+		/deep/
+		**/a
+		!*bin*
+	EOF
+	test_cmp expect list
+'
+
+test_done