builtin/sparse-checkout: add check-rules command

There exists no direct way to interrogate git about which paths are
matched by a given set of sparsity rules. It is possible to get this
information from git, but it includes checking out the commit that
contains the paths, applying the sparse checkout patterns and then using
something like 'git ls-files -t' to check if the skip worktree bit is
set. This works in some case, but there are cases where it is awkward or
infeasible to generate a checkout for this purpose.

Exposing the pattern matching of sparse checkout enables more tooling to
be built and avoids a situation where tools that want to reason about
sparse checkouts start containing parallel implementation of the rules.
To accommodate this, add a 'check-rules' subcommand to the
'sparse-checkout' builtin along the lines of the 'git check-ignore' and
'git check-attr' commands. The new command accepts a list of paths on
stdin and outputs just the ones the match the sparse checkout.

To allow for use in a bare repository and to allow for interrogating
about other patterns than the current ones, include a '--rules-file'
option which allows the caller to explicitly pass sparse checkout rules
in the format accepted by 'sparse-checkout set --stdin'.

To allow for reuse of the handling of input patterns for the
'--rules-file' flag, modify 'add_patterns_from_input()' to be able to
read from a 'FILE' instead of just stdin.

To allow for reuse of the logic which decides whether or not rules
should be interpreted as cone-mode patterns, split that part out of
'update_modes()' such that can be called without modifying the config.

An alternative could have been to create a new 'check-sparsity' command.
However, placing it under 'sparse-checkout' allows for a) more easily
re-using the sparse checkout pattern matching and cone/non-code mode
handling, and b) keeps the documentation for the command next to the
experimental warning and the cone-mode discussion.

Signed-off-by: William Sprent <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: williams-unity

Documentation/git-sparse-checkout.txt

@@ -9,7 +9,7 @@ git-sparse-checkout - Reduce your working tree to a subset of tracked files
 SYNOPSIS
 --------
 [verse]
-'git sparse-checkout' (init | list | set | add | reapply | disable) [<options>]
+'git sparse-checkout' (init | list | set | add | reapply | disable | check-rules) [<options>]
 
 
 DESCRIPTION
@@ -135,6 +135,29 @@ paths to pass to a subsequent 'set' or 'add' command.  However,
 the disable command, so the easy restore of calling a plain `init`
 decreased in utility.
 
+'check-rules'::
+	Check whether sparsity rules match one or more paths.
++
+By default `check-rules` reads a list of paths from stdin and outputs only
+the ones that match the current sparsity rules. The input is expected to consist
+of one path per line, matching the output of `git ls-tree --name-only` including
+that pathnames that begin with a double quote (") are interpreted as C-style
+quoted strings.
++
+When called with the `--rules-file <file>` flag the input files are matched
+against the sparse checkout rules found in `<file>` instead of the current ones.
+The rules in the files are expected to be in the same form as accepted by `git
+sparse-checkout set --stdin` (in particular, they must be newline-delimited).
++
+By default, the rules passed to the `--rules-file` option are interpreted as
+cone mode directories. To pass non-cone mode patterns with `--rules-file`,
+combine the option with the `--no-cone` option.
++
+When called with the `-z` flag, the format of the paths input on stdin as well
+as the output paths are \0 terminated and not quoted. Note that this does not
+apply to the format of the rules passed with the `--rules-file` option.
+
+
 EXAMPLES
 --------
 `git sparse-checkout set MY/DIR1 SUB/DIR2`::

builtin/sparse-checkout.c

@@ -20,7 +20,7 @@
 static const char *empty_base = "";
 
 static char const * const builtin_sparse_checkout_usage[] = {
-	N_("git sparse-checkout (init | list | set | add | reapply | disable) [<options>]"),
+	N_("git sparse-checkout (init | list | set | add | reapply | disable | check-rules) [<options>]"),
 	NULL
 };
 
@@ -382,26 +382,29 @@ static int set_config(enum sparse_checkout_mode mode)
 	return 0;
 }
 
-static int update_modes(int *cone_mode, int *sparse_index)
-{
-	int mode, record_mode;
-
-	/* Determine if we need to record the mode; ensure sparse checkout on */
-	record_mode = (*cone_mode != -1) || !core_apply_sparse_checkout;
-
+static enum sparse_checkout_mode update_cone_mode(int *cone_mode) {
 	/* If not specified, use previous definition of cone mode */
 	if (*cone_mode == -1 && core_apply_sparse_checkout)
 		*cone_mode = core_sparse_checkout_cone;
 
 	/* Set cone/non-cone mode appropriately */
 	core_apply_sparse_checkout = 1;
 	if (*cone_mode == 1 || *cone_mode == -1) {
-		mode = MODE_CONE_PATTERNS;
 		core_sparse_checkout_cone = 1;
-	} else {
-		mode = MODE_ALL_PATTERNS;
-		core_sparse_checkout_cone = 0;
+		return MODE_CONE_PATTERNS;
 	}
+	core_sparse_checkout_cone = 0;
+	return MODE_ALL_PATTERNS;
+}
+
+static int update_modes(int *cone_mode, int *sparse_index)
+{
+	int mode, record_mode;
+
+	/* Determine if we need to record the mode; ensure sparse checkout on */
+	record_mode = (*cone_mode != -1) || !core_apply_sparse_checkout;
+
+	mode = update_cone_mode(cone_mode);
 	if (record_mode && set_config(mode))
 		return 1;
 
@@ -545,7 +548,7 @@ static void strbuf_to_cone_pattern(struct strbuf *line, struct pattern_list *pl)
 
 static void add_patterns_from_input(struct pattern_list *pl,
 				    int argc, const char **argv,
-				    int use_stdin)
+				    FILE *file)
 {
 	int i;
 	if (core_sparse_checkout_cone) {
@@ -555,9 +558,9 @@ static void add_patterns_from_input(struct pattern_list *pl,
 		hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0);
 		pl->use_cone_patterns = 1;
 
-		if (use_stdin) {
+		if (file) {
 			struct strbuf unquoted = STRBUF_INIT;
-			while (!strbuf_getline(&line, stdin)) {
+			while (!strbuf_getline(&line, file)) {
 				if (line.buf[0] == '"') {
 					strbuf_reset(&unquoted);
 					if (unquote_c_style(&unquoted, line.buf, NULL))
@@ -579,10 +582,10 @@ static void add_patterns_from_input(struct pattern_list *pl,
 			}
 		}
 	} else {
-		if (use_stdin) {
+		if (file) {
 			struct strbuf line = STRBUF_INIT;
 
-			while (!strbuf_getline(&line, stdin)) {
+			while (!strbuf_getline(&line, file)) {
 				size_t len;
 				char *buf = strbuf_detach(&line, &len);
 				add_pattern(buf, empty_base, 0, pl, 0);
@@ -609,7 +612,8 @@ static void add_patterns_cone_mode(int argc, const char **argv,
 	struct pattern_list existing;
 	char *sparse_filename = get_sparse_checkout_filename();
 
-	add_patterns_from_input(pl, argc, argv, use_stdin);
+	add_patterns_from_input(pl, argc, argv,
+				use_stdin ? stdin : NULL);
 
 	memset(&existing, 0, sizeof(existing));
 	existing.use_cone_patterns = core_sparse_checkout_cone;
@@ -646,7 +650,7 @@ static void add_patterns_literal(int argc, const char **argv,
 					   pl, NULL, 0))
 		die(_("unable to load existing sparse-checkout patterns"));
 	free(sparse_filename);
-	add_patterns_from_input(pl, argc, argv, use_stdin);
+	add_patterns_from_input(pl, argc, argv, use_stdin ? stdin : NULL);
 }
 
 static int modify_pattern_list(int argc, const char **argv, int use_stdin,
@@ -665,7 +669,8 @@ static int modify_pattern_list(int argc, const char **argv, int use_stdin,
 		break;
 
 	case REPLACE:
-		add_patterns_from_input(pl, argc, argv, use_stdin);
+		add_patterns_from_input(pl, argc, argv,
+					use_stdin ? stdin : NULL);
 		break;
 	}
 
@@ -927,6 +932,91 @@ static int sparse_checkout_disable(int argc, const char **argv,
 	return set_config(MODE_NO_PATTERNS);
 }
 
+static char const * const builtin_sparse_checkout_check_rules_usage[] = {
+	N_("git sparse-checkout check-rules [-z] [--skip-checks]"
+	   "[--[no-]cone] [--rules-file <file>]"),
+	NULL
+};
+
+static struct sparse_checkout_check_rules_opts {
+	int cone_mode;
+	int null_termination;
+	char *rules_file;
+} check_rules_opts;
+
+static int check_rules(struct pattern_list *pl, int null_terminated) {
+	struct strbuf line = STRBUF_INIT;
+	struct strbuf unquoted = STRBUF_INIT;
+	char *path;
+	int line_terminator = null_terminated ? 0 : '\n';
+	strbuf_getline_fn getline_fn = null_terminated ? strbuf_getline_nul
+		: strbuf_getline;
+	the_repository->index->sparse_checkout_patterns = pl;
+	while (!getline_fn(&line, stdin)) {
+		path = line.buf;
+		if (!null_terminated && line.buf[0] == '"') {
+			strbuf_reset(&unquoted);
+			if (unquote_c_style(&unquoted, line.buf, NULL))
+				die(_("unable to unquote C-style string '%s'"),
+					line.buf);
+
+			path = unquoted.buf;
+		}
+
+		if (path_in_sparse_checkout(path, the_repository->index))
+			write_name_quoted(path, stdout, line_terminator);
+	}
+	strbuf_release(&line);
+	strbuf_release(&unquoted);
+
+	return 0;
+}
+
+static int sparse_checkout_check_rules(int argc, const char **argv, const char *prefix)
+{
+	static struct option builtin_sparse_checkout_check_rules_options[] = {
+		OPT_BOOL('z', NULL, &check_rules_opts.null_termination,
+			 N_("terminate input and output files by a NUL character")),
+		OPT_BOOL(0, "cone", &check_rules_opts.cone_mode,
+			 N_("when used with --rules-file interpret patterns as cone mode patterns")),
+		OPT_FILENAME(0, "rules-file", &check_rules_opts.rules_file,
+			 N_("use patterns in <file> instead of the current ones.")),
+		OPT_END(),
+	};
+
+	FILE *fp;
+	int ret;
+	struct pattern_list pl = {0};
+	char *sparse_filename;
+	check_rules_opts.cone_mode = -1;
+
+	argc = parse_options(argc, argv, prefix,
+			     builtin_sparse_checkout_check_rules_options,
+			     builtin_sparse_checkout_check_rules_usage,
+			     PARSE_OPT_KEEP_UNKNOWN_OPT);
+
+	if (check_rules_opts.rules_file && check_rules_opts.cone_mode < 0)
+		check_rules_opts.cone_mode = 1;
+
+	update_cone_mode(&check_rules_opts.cone_mode);
+	pl.use_cone_patterns = core_sparse_checkout_cone;
+	if (check_rules_opts.rules_file) {
+		fp = xfopen(check_rules_opts.rules_file, "r");
+		add_patterns_from_input(&pl, argc, argv, fp);
+		fclose(fp);
+	} else {
+		sparse_filename = get_sparse_checkout_filename();
+		if (add_patterns_from_file_to_list(sparse_filename, "", 0, &pl,
+						   NULL, 0))
+			die(_("unable to load existing sparse-checkout patterns"));
+		free(sparse_filename);
+	}
+
+	ret = check_rules(&pl, check_rules_opts.null_termination);
+	clear_pattern_list(&pl);
+	return ret;
+}
+
 int cmd_sparse_checkout(int argc, const char **argv, const char *prefix)
 {
 	parse_opt_subcommand_fn *fn = NULL;
@@ -937,6 +1027,7 @@ int cmd_sparse_checkout(int argc, const char **argv, const char *prefix)
 		OPT_SUBCOMMAND("add", &fn, sparse_checkout_add),
 		OPT_SUBCOMMAND("reapply", &fn, sparse_checkout_reapply),
 		OPT_SUBCOMMAND("disable", &fn, sparse_checkout_disable),
+		OPT_SUBCOMMAND("check-rules", &fn, sparse_checkout_check_rules),
 		OPT_END(),
 	};