Merge branch 'nd/checkout-paths-reduce-match-pathspec-calls'

Consolidate repeated pathspec matches on the same paths, while
fixing a bug in "git checkout dir/" code started from an unmerged
index.

* nd/checkout-paths-reduce-match-pathspec-calls:
  checkout: avoid unnecessary match_pathspec calls

builtin/checkout.c

@@ -271,24 +271,55 @@ static int checkout_paths(const struct checkout_opts *opts,
 		;
 	ps_matched = xcalloc(1, pos);
 
+	/*
+	 * Make sure all pathspecs participated in locating the paths
+	 * to be checked out.
+	 */
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
+		ce->ce_flags &= ~CE_MATCHED;
 		if (opts->source_tree && !(ce->ce_flags & CE_UPDATE))
+			/*
+			 * "git checkout tree-ish -- path", but this entry
+			 * is in the original index; it will not be checked
+			 * out to the working tree and it does not matter
+			 * if pathspec matched this entry.  We will not do
+			 * anything to this entry at all.
+			 */
 			continue;
-		match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, ps_matched);
+		/*
+		 * Either this entry came from the tree-ish we are
+		 * checking the paths out of, or we are checking out
+		 * of the index.
+		 *
+		 * If it comes from the tree-ish, we already know it
+		 * matches the pathspec and could just stamp
+		 * CE_MATCHED to it from update_some(). But we still
+		 * need ps_matched and read_tree_recursive (and
+		 * eventually tree_entry_interesting) cannot fill
+		 * ps_matched yet. Once it can, we can avoid calling
+		 * match_pathspec() for _all_ entries when
+		 * opts->source_tree != NULL.
+		 */
+		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce),
+				   0, ps_matched))
+			ce->ce_flags |= CE_MATCHED;
 	}
 
-	if (report_path_error(ps_matched, opts->pathspec, opts->prefix))
+	if (report_path_error(ps_matched, opts->pathspec, opts->prefix)) {
+		free(ps_matched);
 		return 1;
+	}
+	free(ps_matched);
 
 	/* "checkout -m path" to recreate conflicted state */
 	if (opts->merge)
-		unmerge_cache(opts->pathspec);
+		unmerge_marked_index(&the_index);
 
 	/* Any unmerged paths? */
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
+		if (ce->ce_flags & CE_MATCHED) {
 			if (!ce_stage(ce))
 				continue;
 			if (opts->force) {
@@ -313,9 +344,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 	state.refresh_cache = 1;
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (opts->source_tree && !(ce->ce_flags & CE_UPDATE))
-			continue;
-		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
+		if (ce->ce_flags & CE_MATCHED) {
 			if (!ce_stage(ce)) {
 				errs |= checkout_entry(ce, &state, NULL);
 				continue;

cache.h

@@ -162,6 +162,9 @@ struct cache_entry {
 #define CE_UNPACKED          (1 << 24)
 #define CE_NEW_SKIP_WORKTREE (1 << 25)
 
+/* used to temporarily mark paths matched by pathspecs */
+#define CE_MATCHED           (1 << 26)
+
 /*
  * Extended on-disk flags
  */

resolve-undo.c

@@ -118,7 +118,7 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 	struct cache_entry *ce;
 	struct string_list_item *item;
 	struct resolve_undo_info *ru;
-	int i, err = 0;
+	int i, err = 0, matched;
 
 	if (!istate->resolve_undo)
 		return pos;
@@ -137,6 +137,7 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 	ru = item->util;
 	if (!ru)
 		return pos;
+	matched = ce->ce_flags & CE_MATCHED;
 	remove_index_entry_at(istate, pos);
 	for (i = 0; i < 3; i++) {
 		struct cache_entry *nce;
@@ -144,6 +145,8 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 			continue;
 		nce = make_cache_entry(ru->mode[i], ru->sha1[i],
 				       ce->name, i + 1, 0);
+		if (matched)
+			nce->ce_flags |= CE_MATCHED;
 		if (add_index_entry(istate, nce, ADD_CACHE_OK_TO_ADD)) {
 			err = 1;
 			error("cannot unmerge '%s'", ce->name);
@@ -156,6 +159,20 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 	return unmerge_index_entry_at(istate, pos);
 }
 
+void unmerge_marked_index(struct index_state *istate)
+{
+	int i;
+
+	if (!istate->resolve_undo)
+		return;
+
+	for (i = 0; i < istate->cache_nr; i++) {
+		struct cache_entry *ce = istate->cache[i];
+		if (ce->ce_flags & CE_MATCHED)
+			i = unmerge_index_entry_at(istate, i);
+	}
+}
+
 void unmerge_index(struct index_state *istate, const char **pathspec)
 {
 	int i;

resolve-undo.h

@@ -12,5 +12,6 @@ extern struct string_list *resolve_undo_read(const char *, unsigned long);
 extern void resolve_undo_clear_index(struct index_state *);
 extern int unmerge_index_entry_at(struct index_state *, int);
 extern void unmerge_index(struct index_state *, const char **);
+extern void unmerge_marked_index(struct index_state *);
 
 #endif

t/t2022-checkout-paths.sh

@@ -39,4 +39,26 @@ test_expect_success 'checking out paths out of a tree does not clobber unrelated
 	test_cmp expect.next2 dir/next2
 '
 
+test_expect_success 'do not touch unmerged entries matching $path but not in $tree' '
+	git checkout next &&
+	git reset --hard &&
+
+	cat dir/common >expect.common &&
+	EMPTY_SHA1=$(git hash-object -w --stdin </dev/null) &&
+	git rm dir/next0 &&
+	cat >expect.next0 <<-EOF &&
+	100644 $EMPTY_SHA1 1	dir/next0
+	100644 $EMPTY_SHA1 2	dir/next0
+	EOF
+	git update-index --index-info <expect.next0 &&
+
+	git checkout master dir &&
+
+	test_cmp expect.common dir/common &&
+	test_path_is_file dir/master &&
+	git diff --exit-code master dir/master &&
+	git ls-files -s dir/next0 >actual.next0 &&
+	test_cmp expect.next0 actual.next0
+'
+
 test_done