Merge branch 'vd/sparse-clean-etc' into seen

"git update-index", "git checkout-index", and "git clean" are
taught to work better with the sparse checkout feature.
source: <pull.1109.v2.git.1641924306.gitgitgadget@gmail.com>

* vd/sparse-clean-etc:
  update-index: reduce scope of index expansion in do_reupdate
  update-index: integrate with sparse index
  update-index: add tests for sparse-checkout compatibility
  checkout-index: integrate with sparse index
  checkout-index: add --ignore-skip-worktree-bits option
  checkout-index: expand sparse checkout compatibility tests
  clean: integrate with sparse index
  reset: reorder wildcard pathspec conditions
  reset: fix validation in sparse index test

Author: gitster

Documentation/git-checkout-index.txt

@@ -12,6 +12,7 @@ SYNOPSIS
 'git checkout-index' [-u] [-q] [-a] [-f] [-n] [--prefix=<string>]
 		   [--stage=<number>|all]
 		   [--temp]
+		   [--ignore-skip-worktree-bits]
 		   [-z] [--stdin]
 		   [--] [<file>...]
 
@@ -37,8 +38,9 @@ OPTIONS
 
 -a::
 --all::
-	checks out all files in the index.  Cannot be used
-	together with explicit filenames.
+	checks out all files in the index except for those with the
+	skip-worktree bit set (see `--ignore-skip-worktree-bits`).
+	Cannot be used together with explicit filenames.
 
 -n::
 --no-create::
@@ -59,6 +61,10 @@ OPTIONS
 	write the content to temporary files.  The temporary name
 	associations will be written to stdout.
 
+--ignore-skip-worktree-bits::
+	Check out all files, including those with the skip-worktree bit
+	set.
+
 --stdin::
 	Instead of taking list of paths from the command line,
 	read list of paths from the standard input.  Paths are

builtin/checkout-index.c

@@ -7,6 +7,7 @@
 #define USE_THE_INDEX_COMPATIBILITY_MACROS
 #include "builtin.h"
 #include "config.h"
+#include "dir.h"
 #include "lockfile.h"
 #include "quote.h"
 #include "cache-tree.h"
@@ -17,6 +18,7 @@
 #define CHECKOUT_ALL 4
 static int nul_term_line;
 static int checkout_stage; /* default to checkout stage0 */
+static int ignore_skip_worktree; /* default to 0 */
 static int to_tempfile;
 static char topath[4][TEMPORARY_FILENAME_LENGTH + 1];
 
@@ -65,6 +67,8 @@ static int checkout_file(const char *name, const char *prefix)
 	int namelen = strlen(name);
 	int pos = cache_name_pos(name, namelen);
 	int has_same_name = 0;
+	int is_file = 0;
+	int is_skipped = 1;
 	int did_checkout = 0;
 	int errs = 0;
 
@@ -78,6 +82,12 @@ static int checkout_file(const char *name, const char *prefix)
 			break;
 		has_same_name = 1;
 		pos++;
+		if (S_ISSPARSEDIR(ce->ce_mode))
+			break;
+		is_file = 1;
+		if (!ignore_skip_worktree && ce_skip_worktree(ce))
+			break;
+		is_skipped = 0;
 		if (ce_stage(ce) != checkout_stage
 		    && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce)))
 			continue;
@@ -106,6 +116,11 @@ static int checkout_file(const char *name, const char *prefix)
 		fprintf(stderr, "git checkout-index: %s ", name);
 		if (!has_same_name)
 			fprintf(stderr, "is not in the cache");
+		else if (!is_file)
+			fprintf(stderr, "is a sparse directory");
+		else if (is_skipped)
+			fprintf(stderr, "has skip-worktree enabled; "
+					"use '--ignore-skip-worktree-bits' to checkout");
 		else if (checkout_stage)
 			fprintf(stderr, "does not exist at stage %d",
 				checkout_stage);
@@ -121,10 +136,27 @@ static int checkout_all(const char *prefix, int prefix_length)
 	int i, errs = 0;
 	struct cache_entry *last_ce = NULL;
 
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(&the_index);
 	for (i = 0; i < active_nr ; i++) {
 		struct cache_entry *ce = active_cache[i];
+
+		if (S_ISSPARSEDIR(ce->ce_mode)) {
+			if (!ce_skip_worktree(ce))
+				BUG("sparse directory '%s' does not have skip-worktree set", ce->name);
+
+			/*
+			 * If the current entry is a sparse directory and skip-worktree
+			 * entries are being checked out, expand the index and continue
+			 * the loop on the current index position (now pointing to the
+			 * first entry inside the expanded sparse directory).
+			 */
+			if (ignore_skip_worktree) {
+				ensure_full_index(&the_index);
+				ce = active_cache[i];
+			}
+		}
+
+		if (!ignore_skip_worktree && ce_skip_worktree(ce))
+			continue;
 		if (ce_stage(ce) != checkout_stage
 		    && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce)))
 			continue;
@@ -185,6 +217,8 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	struct option builtin_checkout_index_options[] = {
 		OPT_BOOL('a', "all", &all,
 			N_("check out all files in the index")),
+		OPT_BOOL(0, "ignore-skip-worktree-bits", &ignore_skip_worktree,
+			N_("do not skip files with skip-worktree set")),
 		OPT__FORCE(&force, N_("force overwrite of existing files"), 0),
 		OPT__QUIET(&quiet,
 			N_("no warning for existing files and files not in index")),
@@ -212,6 +246,9 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	git_config(git_default_config, NULL);
 	prefix_length = prefix ? strlen(prefix) : 0;
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	if (read_cache() < 0) {
 		die("invalid cache");
 	}

builtin/clean.c

@@ -1009,6 +1009,9 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 		dir.flags |= DIR_KEEP_UNTRACKED_CONTENTS;
 	}
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
 

builtin/reset.c

@@ -204,10 +204,16 @@ static int pathspec_needs_expanded_index(const struct pathspec *pathspec)
 			/*
 			 * Special case: if the pattern is a path inside the cone
 			 * followed by only wildcards, the pattern cannot match
-			 * partial sparse directories, so we don't expand the index.
+			 * partial sparse directories, so we know we don't need to
+			 * expand the index.
+			 *
+			 * Examples:
+			 * - in-cone/foo***: doesn't need expanded index
+			 * - not-in-cone/bar*: may need expanded index
+			 * - **.c: may need expanded index
 			 */
-			if (path_in_cone_mode_sparse_checkout(item.original, &the_index) &&
-			    strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len)
+			if (strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len &&
+			    path_in_cone_mode_sparse_checkout(item.original, &the_index))
 				continue;
 
 			for (pos = 0; pos < active_nr; pos++) {

builtin/update-index.c

@@ -606,7 +606,7 @@ static struct cache_entry *read_one_ent(const char *which,
 			error("%s: not in %s branch.", path, which);
 		return NULL;
 	}
-	if (mode == S_IFDIR) {
+	if (!the_index.sparse_index && mode == S_IFDIR) {
 		if (which)
 			error("%s: not a blob in %s branch.", path, which);
 		return NULL;
@@ -743,8 +743,6 @@ static int do_reupdate(int ac, const char **av,
 		 */
 		has_head = 0;
  redo:
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(&the_index);
 	for (pos = 0; pos < active_nr; pos++) {
 		const struct cache_entry *ce = active_cache[pos];
 		struct cache_entry *old = NULL;
@@ -761,6 +759,16 @@ static int do_reupdate(int ac, const char **av,
 			discard_cache_entry(old);
 			continue; /* unchanged */
 		}
+
+		/* At this point, we know the contents of the sparse directory are
+		 * modified with respect to HEAD, so we expand the index and restart
+		 * to process each path individually
+		 */
+		if (S_ISSPARSEDIR(ce->ce_mode)) {
+			ensure_full_index(&the_index);
+			goto redo;
+		}
+
 		/* Be careful.  The working tree may not have the
 		 * path anymore, in which case, under 'allow_remove',
 		 * or worse yet 'allow_replace', active_nr may decrease.
@@ -1088,6 +1096,9 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 
 	git_config(git_default_config, NULL);
 
+	prepare_repo_settings(r);
+	the_repository->settings.command_requires_full_index = 0;
+
 	/* we will diagnose later if it turns out that we need to update it */
 	newfd = hold_locked_index(&lock_file, 0);
 	if (newfd < 0)

read-cache.c

@@ -1340,9 +1340,6 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
 	int new_only = option & ADD_CACHE_NEW_ONLY;
 
-	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
-		cache_tree_invalidate_path(istate, ce->name);
-
 	/*
 	 * If this entry's path sorts after the last entry in the index,
 	 * we can avoid searching for it.
@@ -1353,6 +1350,13 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 	else
 		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE);
 
+	/*
+	 * Cache tree path should be invalidated only after index_name_stage_pos,
+	 * in case it expands a sparse index.
+	 */
+	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
+		cache_tree_invalidate_path(istate, ce->name);
+
 	/* existing match? Just replace it. */
 	if (pos >= 0) {
 		if (!new_only)

t/perf/p2000-sparse-operations.sh

@@ -117,5 +117,7 @@ test_perf_on_all git diff
 test_perf_on_all git diff --cached
 test_perf_on_all git blame $SPARSE_CONE/a
 test_perf_on_all git blame $SPARSE_CONE/f3/a
+test_perf_on_all git checkout-index -f --all
+test_perf_on_all git update-index --add --remove $SPARSE_CONE/a
 
 test_done