grep: honor sparse checkout patterns

One of the main uses for a sparse checkout is to allow users to focus on
the subset of files in a repository in which they are interested. But
git-grep currently ignores the sparsity patterns and reports all matches
found outside this subset, which kind of goes in the opposite direction.
There are some use cases for ignoring the sparsity patterns and the next
commit will add an option to obtain this behavior, but here we start by
making grep honor the sparsity boundaries in every case where this is
relevant:

- git grep in worktree
- git grep --cached
- git grep $REVISION

For the worktree and cached cases, we iterate over paths without the
SKIP_WORKTREE bit set, and limit our searches to these paths. For the
$REVISION case, we limit the paths we search to those that match the
sparsity patterns. (We do not check the SKIP_WORKTREE bit for the
$REVISION case, because $REVISION may contain paths that do not exist in
HEAD and thus for which we have no SKIP_WORKTREE bit to consult. The
sparsity patterns tell us how the SKIP_WORKTREE bit would be set if we
were to check out $REVISION, so we consult those. Also, we don't use the
sparsity patterns with the worktree or cached cases, both because we
have a bit we can check directly and more efficiently, and because
unmerged entries from a merge or a rebase could cause more files to
temporarily be present than the sparsity patterns would normally
select.)

Note that there is a special case here: `git grep $TREE`. In this case,
we cannot know whether $TREE corresponds to the root of the repository
or some sub-tree, and thus there is no way for us to know which sparsity
patterns, if any, apply. So the $TREE case will not use sparsity
patterns or any SKIP_WORKTREE bits and will instead always search all
files within the $TREE.

Signed-off-by: Matheus Tavares <matheus.bernardino@usp.br>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/grep.c

@@ -410,7 +410,7 @@ static int grep_cache(struct grep_opt *opt,
 		      const struct pathspec *pathspec, int cached);
 static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		     struct tree_desc *tree, struct strbuf *base, int tn_len,
-		     int check_attr);
+		     int is_root_tree);
 
 static int grep_submodule(struct grep_opt *opt,
 			  const struct pathspec *pathspec,
@@ -508,6 +508,10 @@ static int grep_cache(struct grep_opt *opt,
 
 	for (nr = 0; nr < repo->index->cache_nr; nr++) {
 		const struct cache_entry *ce = repo->index->cache[nr];
+
+		if (ce_skip_worktree(ce))
+			continue;
+
 		strbuf_setlen(&name, name_base_len);
 		strbuf_addstr(&name, ce->name);
 
@@ -520,8 +524,7 @@ static int grep_cache(struct grep_opt *opt,
 			 * cache entry are identical, even if worktree file has
 			 * been modified, so use cache version instead
 			 */
-			if (cached || (ce->ce_flags & CE_VALID) ||
-			    ce_skip_worktree(ce)) {
+			if (cached || (ce->ce_flags & CE_VALID)) {
 				if (ce_stage(ce) || ce_intent_to_add(ce))
 					continue;
 				hit |= grep_oid(opt, &ce->oid, name.buf,
@@ -552,9 +555,76 @@ static int grep_cache(struct grep_opt *opt,
 	return hit;
 }
 
-static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
-		     struct tree_desc *tree, struct strbuf *base, int tn_len,
-		     int check_attr)
+static struct pattern_list *get_sparsity_patterns(struct repository *repo)
+{
+	struct pattern_list *patterns;
+	char *sparse_file;
+	int sparse_config, cone_config;
+
+	if (repo_config_get_bool(repo, "core.sparsecheckout", &sparse_config) ||
+	    !sparse_config) {
+		return NULL;
+	}
+
+	sparse_file = repo_git_path(repo, "info/sparse-checkout");
+	patterns = xcalloc(1, sizeof(*patterns));
+
+	if (repo_config_get_bool(repo, "core.sparsecheckoutcone", &cone_config))
+		cone_config = 0;
+	patterns->use_cone_patterns = cone_config;
+
+	if (add_patterns_from_file_to_list(sparse_file, "", 0, patterns, NULL)) {
+		if (file_exists(sparse_file)) {
+			warning(_("failed to load sparse-checkout file: '%s'"),
+				sparse_file);
+		}
+		free(sparse_file);
+		free(patterns);
+		return NULL;
+	}
+
+	free(sparse_file);
+	return patterns;
+}
+
+static int path_in_sparse_checkout(struct strbuf *path, int prefix_len,
+				   unsigned int entry_mode,
+				   struct index_state *istate,
+				   struct pattern_list *sparsity,
+				   enum pattern_match_result parent_match,
+				   enum pattern_match_result *match)
+{
+	int dtype = DT_UNKNOWN;
+	int is_dir = S_ISDIR(entry_mode);
+
+	if (parent_match == MATCHED_RECURSIVE) {
+		*match = parent_match;
+		return 1;
+	}
+
+	if (is_dir && !is_dir_sep(path->buf[path->len - 1]))
+		strbuf_addch(path, '/');
+
+	*match = path_matches_pattern_list(path->buf, path->len,
+					   path->buf + prefix_len, &dtype,
+					   sparsity, istate);
+	if (*match == UNDECIDED)
+		*match = parent_match;
+
+	if (is_dir)
+		strbuf_trim_trailing_dir_sep(path);
+
+	if (*match == NOT_MATCHED &&
+		(!is_dir || (is_dir && sparsity->use_cone_patterns)))
+	     return 0;
+
+	return 1;
+}
+
+static int do_grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
+			struct tree_desc *tree, struct strbuf *base, int tn_len,
+			int check_attr, struct pattern_list *sparsity,
+			enum pattern_match_result default_sparsity_match)
 {
 	struct repository *repo = opt->repo;
 	int hit = 0;
@@ -570,6 +640,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 	while (tree_entry(tree, &entry)) {
 		int te_len = tree_entry_len(&entry);
+		enum pattern_match_result sparsity_match = 0;
 
 		if (match != all_entries_interesting) {
 			strbuf_addstr(&name, base->buf + tn_len);
@@ -586,6 +657,19 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 		strbuf_add(base, entry.path, te_len);
 
+		if (sparsity) {
+			struct strbuf path = STRBUF_INIT;
+			strbuf_addstr(&path, base->buf + tn_len);
+
+			if (!path_in_sparse_checkout(&path, old_baselen - tn_len,
+						     entry.mode, repo->index,
+						     sparsity, default_sparsity_match,
+						     &sparsity_match)) {
+				strbuf_setlen(base, old_baselen);
+				continue;
+			}
+		}
+
 		if (S_ISREG(entry.mode)) {
 			hit |= grep_oid(opt, &entry.oid, base->buf, tn_len,
 					 check_attr ? base->buf + tn_len : NULL);
@@ -602,8 +686,8 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 			strbuf_addch(base, '/');
 			init_tree_desc(&sub, data, size);
-			hit |= grep_tree(opt, pathspec, &sub, base, tn_len,
-					 check_attr);
+			hit |= do_grep_tree(opt, pathspec, &sub, base, tn_len,
+					    check_attr, sparsity, sparsity_match);
 			free(data);
 		} else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
 			hit |= grep_submodule(opt, pathspec, &entry.oid,
@@ -621,6 +705,31 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 	return hit;
 }
 
+/*
+ * Note: sparsity patterns and paths' attributes will only be considered if
+ * is_root_tree has true value. (Otherwise, we cannot properly perform pattern
+ * matching on paths.)
+ */
+static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
+		     struct tree_desc *tree, struct strbuf *base, int tn_len,
+		     int is_root_tree)
+{
+	struct pattern_list *patterns = NULL;
+	int ret;
+
+	if (is_root_tree)
+		patterns = get_sparsity_patterns(opt->repo);
+
+	ret = do_grep_tree(opt, pathspec, tree, base, tn_len, is_root_tree,
+			   patterns, 0);
+
+	if (patterns) {
+		clear_pattern_list(patterns);
+		free(patterns);
+	}
+	return ret;
+}
+
 static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
 		       struct object *obj, const char *name, const char *path)
 {