Merge branch 'kn/for-all-refs' into HEAD

"git for-each-ref" learned "--include-root-refs" option to show
even the stuff outside the 'refs/' hierarchy.

* kn/for-all-refs:
  for-each-ref: add new option to include root refs
  ref-filter: rename 'FILTER_REFS_ALL' to 'FILTER_REFS_REGULAR'
  refs: introduce `refs_for_each_include_root_refs()`
  refs: extract out `loose_fill_ref_dir_regular_file()`
  refs: introduce `is_pseudoref()` and `is_headref()`

11 files changed, 243 insertions, 53 deletions

diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt
index 3a9ad91..c1dd12b 100644
--- a/Documentation/git-for-each-ref.txt
+++ b/Documentation/git-for-each-ref.txt
@@ -10,7 +10,7 @@ SYNOPSIS
 [verse]
 'git for-each-ref' [--count=<count>] [--shell|--perl|--python|--tcl]
 		   [(--sort=<key>)...] [--format=<format>]
-		   [ --stdin | <pattern>... ]
+		   [--include-root-refs] [ --stdin | <pattern>... ]
 		   [--points-at=<object>]
 		   [--merged[=<object>]] [--no-merged[=<object>]]
 		   [--contains[=<object>]] [--no-contains[=<object>]]
@@ -105,6 +105,9 @@ TAB %(refname)`.
 	any excluded pattern(s) are shown. Matching is done using the
 	same rules as `<pattern>` above.
 
+--include-root-refs::
+	List root refs (HEAD and pseudorefs) apart from regular refs.
+
 FIELD NAMES
 -----------
 
diff --git a/builtin/for-each-ref.c b/builtin/for-each-ref.c
index 3885a9c..919282e 100644
--- a/builtin/for-each-ref.c
+++ b/builtin/for-each-ref.c
@@ -20,10 +20,10 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix)
 {
 	struct ref_sorting *sorting;
 	struct string_list sorting_options = STRING_LIST_INIT_DUP;
-	int icase = 0;
+	int icase = 0, include_root_refs = 0, from_stdin = 0;
 	struct ref_filter filter = REF_FILTER_INIT;
 	struct ref_format format = REF_FORMAT_INIT;
-	int from_stdin = 0;
+	unsigned int flags = FILTER_REFS_REGULAR;
 	struct strvec vec = STRVEC_INIT;
 
 	struct option opts[] = {
@@ -53,6 +53,7 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix)
 		OPT_NO_CONTAINS(&filter.no_commit, N_("print only refs which don't contain the commit")),
 		OPT_BOOL(0, "ignore-case", &icase, N_("sorting and filtering are case insensitive")),
 		OPT_BOOL(0, "stdin", &from_stdin, N_("read reference patterns from stdin")),
+		OPT_BOOL(0, "include-root-refs", &include_root_refs, N_("also include HEAD ref and pseudorefs")),
 		OPT_END(),
 	};
 
@@ -96,8 +97,11 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix)
 		filter.name_patterns = argv;
 	}
 
+	if (include_root_refs)
+		flags |= FILTER_REFS_ROOT_REFS;
+
 	filter.match_as_path = 1;
-	filter_and_format_refs(&filter, FILTER_REFS_ALL, sorting, &format);
+	filter_and_format_refs(&filter, flags, sorting, &format);
 
 	ref_filter_clear(&filter);
 	ref_sorting_release(sorting);
diff --git a/ref-filter.c b/ref-filter.c
index be14b56..0ec29f7 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -2628,6 +2628,12 @@ static int for_each_fullref_in_pattern(struct ref_filter *filter,
 				       each_ref_fn cb,
 				       void *cb_data)
 {
+	if (filter->kind == FILTER_REFS_KIND_MASK) {
+		/* In this case, we want to print all refs including root refs. */
+		return refs_for_each_include_root_refs(get_main_ref_store(the_repository),
+						       cb, cb_data);
+	}
+
 	if (!filter->match_as_path) {
 		/*
 		 * in this case, the patterns are applied after
@@ -2750,6 +2756,9 @@ static int ref_kind_from_refname(const char *refname)
 			return ref_kind[i].kind;
 	}
 
+	if (is_pseudoref(get_main_ref_store(the_repository), refname))
+		return FILTER_REFS_PSEUDOREFS;
+
 	return FILTER_REFS_OTHERS;
 }
 
@@ -2781,7 +2790,16 @@ static struct ref_array_item *apply_ref_filter(const char *refname, const struct
 
 	/* Obtain the current ref kind from filter_ref_kind() and ignore unwanted refs. */
 	kind = filter_ref_kind(filter, refname);
-	if (!(kind & filter->kind))
+
+	/*
+	 * Generally HEAD refs are printed with special description denoting a rebase,
+	 * detached state and so forth. This is useful when only printing the HEAD ref
+	 * But when it is being printed along with other pseudorefs, it makes sense to
+	 * keep the formatting consistent. So we mask the type to act like a pseudoref.
+	 */
+	if (filter->kind == FILTER_REFS_KIND_MASK && kind == FILTER_REFS_DETACHED_HEAD)
+		kind = FILTER_REFS_PSEUDOREFS;
+	else if (!(kind & filter->kind))
 		return NULL;
 
 	if (!filter_pattern_match(filter, refname))
@@ -3047,9 +3065,15 @@ static int do_filter_refs(struct ref_filter *filter, unsigned int type, each_ref
 			ret = for_each_fullref_in("refs/remotes/", fn, cb_data);
 		else if (filter->kind == FILTER_REFS_TAGS)
 			ret = for_each_fullref_in("refs/tags/", fn, cb_data);
-		else if (filter->kind & FILTER_REFS_ALL)
+		else if (filter->kind & FILTER_REFS_REGULAR)
 			ret = for_each_fullref_in_pattern(filter, fn, cb_data);
-		if (!ret && (filter->kind & FILTER_REFS_DETACHED_HEAD))
+
+		/*
+		 * When printing all ref types, HEAD is already included,
+		 * so we don't want to print HEAD again.
+		 */
+		if (!ret && (filter->kind != FILTER_REFS_KIND_MASK) &&
+		    (filter->kind & FILTER_REFS_DETACHED_HEAD))
 			head_ref(fn, cb_data);
 	}
 
diff --git a/ref-filter.h b/ref-filter.h
index 07cd6f6..0ca28d2 100644
--- a/ref-filter.h
+++ b/ref-filter.h
@@ -19,10 +19,13 @@
 #define FILTER_REFS_BRANCHES       0x0004
 #define FILTER_REFS_REMOTES        0x0008
 #define FILTER_REFS_OTHERS         0x0010
-#define FILTER_REFS_ALL            (FILTER_REFS_TAGS | FILTER_REFS_BRANCHES | \
+#define FILTER_REFS_REGULAR        (FILTER_REFS_TAGS | FILTER_REFS_BRANCHES | \
 				    FILTER_REFS_REMOTES | FILTER_REFS_OTHERS)
 #define FILTER_REFS_DETACHED_HEAD  0x0020
-#define FILTER_REFS_KIND_MASK      (FILTER_REFS_ALL | FILTER_REFS_DETACHED_HEAD)
+#define FILTER_REFS_PSEUDOREFS     0x0040
+#define FILTER_REFS_ROOT_REFS      (FILTER_REFS_DETACHED_HEAD | FILTER_REFS_PSEUDOREFS)
+#define FILTER_REFS_KIND_MASK      (FILTER_REFS_REGULAR | FILTER_REFS_DETACHED_HEAD | \
+				    FILTER_REFS_PSEUDOREFS)
 
 struct atom_value;
 struct ref_sorting;
diff --git a/refs.c b/refs.c
index c6d4128..55d2e0b 100644
--- a/refs.c
+++ b/refs.c
@@ -860,6 +860,47 @@ static int is_pseudoref_syntax(const char *refname)
 	return 1;
 }
 
+int is_pseudoref(struct ref_store *refs, const char *refname)
+{
+	static const char *const irregular_pseudorefs[] = {
+		"AUTO_MERGE",
+		"BISECT_EXPECTED_REV",
+		"NOTES_MERGE_PARTIAL",
+		"NOTES_MERGE_REF",
+		"MERGE_AUTOSTASH",
+	};
+	struct object_id oid;
+	size_t i;
+
+	if (!is_pseudoref_syntax(refname))
+		return 0;
+
+	if (ends_with(refname, "_HEAD")) {
+		refs_resolve_ref_unsafe(refs, refname,
+					RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE,
+					&oid, NULL);
+		return !is_null_oid(&oid);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(irregular_pseudorefs); i++)
+		if (!strcmp(refname, irregular_pseudorefs[i])) {
+			refs_resolve_ref_unsafe(refs, refname,
+						RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE,
+						&oid, NULL);
+			return !is_null_oid(&oid);
+		}
+
+	return 0;
+}
+
+int is_headref(struct ref_store *refs, const char *refname)
+{
+	if (!strcmp(refname, "HEAD"))
+		return refs_ref_exists(refs, refname);
+
+	return 0;
+}
+
 static int is_current_worktree_ref(const char *ref) {
 	return is_pseudoref_syntax(ref) || is_per_worktree_ref(ref);
 }
@@ -1715,6 +1756,13 @@ int for_each_rawref(each_ref_fn fn, void *cb_data)
 	return refs_for_each_rawref(get_main_ref_store(the_repository), fn, cb_data);
 }
 
+int refs_for_each_include_root_refs(struct ref_store *refs, each_ref_fn fn,
+				    void *cb_data)
+{
+	return do_for_each_ref(refs, "", NULL, fn, 0,
+			       DO_FOR_EACH_INCLUDE_ROOT_REFS, cb_data);
+}
+
 static int qsort_strcmp(const void *va, const void *vb)
 {
 	const char *a = *(const char **)va;
diff --git a/refs.h b/refs.h
index 0bd3fab..298caf6 100644
--- a/refs.h
+++ b/refs.h
@@ -399,6 +399,12 @@ int refs_for_each_rawref(struct ref_store *refs, each_ref_fn fn, void *cb_data);
 int for_each_rawref(each_ref_fn fn, void *cb_data);
 
 /*
+ * Iterates over all refs including root refs, i.e. pseudorefs and HEAD.
+ */
+int refs_for_each_include_root_refs(struct ref_store *refs, each_ref_fn fn,
+				    void *cb_data);
+
+/*
  * Normalizes partial refs to their fully qualified form.
  * Will prepend <prefix> to the <pattern> if it doesn't start with 'refs/'.
  * <prefix> will default to 'refs/' if NULL.
@@ -1043,4 +1049,7 @@ extern struct ref_namespace_info ref_namespace[NAMESPACE__COUNT];
  */
 void update_ref_namespace(enum ref_namespace namespace, char *ref);
 
+int is_pseudoref(struct ref_store *refs, const char *refname);
+int is_headref(struct ref_store *refs, const char *refname);
+
 #endif /* REFS_H */
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 6f98168..a098d14 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -229,6 +229,38 @@ static void add_per_worktree_entries_to_dir(struct ref_dir *dir, const char *dir
 	}
 }
 
+static void loose_fill_ref_dir_regular_file(struct files_ref_store *refs,
+					    const char *refname,
+					    struct ref_dir *dir)
+{
+	struct object_id oid;
+	int flag;
+
+	if (!refs_resolve_ref_unsafe(&refs->base, refname, RESOLVE_REF_READING,
+				     &oid, &flag)) {
+		oidclr(&oid);
+		flag |= REF_ISBROKEN;
+	} else if (is_null_oid(&oid)) {
+		/*
+		 * It is so astronomically unlikely
+		 * that null_oid is the OID of an
+		 * actual object that we consider its
+		 * appearance in a loose reference
+		 * file to be repo corruption
+		 * (probably due to a software bug).
+		 */
+		flag |= REF_ISBROKEN;
+	}
+
+	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
+		if (!refname_is_safe(refname))
+			die("loose refname is dangerous: %s", refname);
+		oidclr(&oid);
+		flag |= REF_BAD_NAME | REF_ISBROKEN;
+	}
+	add_entry_to_dir(dir, create_ref_entry(refname, &oid, flag));
+}
+
 /*
  * Read the loose references from the namespace dirname into dir
  * (without recursing).  dirname must end with '/'.  dir must be the
@@ -257,8 +289,6 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 	strbuf_add(&refname, dirname, dirnamelen);
 
 	while ((de = readdir(d)) != NULL) {
-		struct object_id oid;
-		int flag;
 		unsigned char dtype;
 
 		if (de->d_name[0] == '.')
@@ -274,33 +304,7 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 					 create_dir_entry(dir->cache, refname.buf,
 							  refname.len));
 		} else if (dtype == DT_REG) {
-			if (!refs_resolve_ref_unsafe(&refs->base,
-						     refname.buf,
-						     RESOLVE_REF_READING,
-						     &oid, &flag)) {
-				oidclr(&oid);
-				flag |= REF_ISBROKEN;
-			} else if (is_null_oid(&oid)) {
-				/*
-				 * It is so astronomically unlikely
-				 * that null_oid is the OID of an
-				 * actual object that we consider its
-				 * appearance in a loose reference
-				 * file to be repo corruption
-				 * (probably due to a software bug).
-				 */
-				flag |= REF_ISBROKEN;
-			}
-
-			if (check_refname_format(refname.buf,
-						 REFNAME_ALLOW_ONELEVEL)) {
-				if (!refname_is_safe(refname.buf))
-					die("loose refname is dangerous: %s", refname.buf);
-				oidclr(&oid);
-				flag |= REF_BAD_NAME | REF_ISBROKEN;
-			}
-			add_entry_to_dir(dir,
-					 create_ref_entry(refname.buf, &oid, flag));
+			loose_fill_ref_dir_regular_file(refs, refname.buf, dir);
 		}
 		strbuf_setlen(&refname, dirnamelen);
 	}
@@ -311,9 +315,59 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 	add_per_worktree_entries_to_dir(dir, dirname);
 }
 
-static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs)
+/*
+ * Add pseudorefs to the ref dir by parsing the directory for any files
+ * which follow the pseudoref syntax.
+ */
+static void add_pseudoref_and_head_entries(struct ref_store *ref_store,
+					 struct ref_dir *dir,
+					 const char *dirname)
+{
+	struct files_ref_store *refs =
+		files_downcast(ref_store, REF_STORE_READ, "fill_ref_dir");
+	struct strbuf path = STRBUF_INIT, refname = STRBUF_INIT;
+	struct dirent *de;
+	size_t dirnamelen;
+	DIR *d;
+
+	files_ref_path(refs, &path, dirname);
+
+	d = opendir(path.buf);
+	if (!d) {
+		strbuf_release(&path);
+		return;
+	}
+
+	strbuf_addstr(&refname, dirname);
+	dirnamelen = refname.len;
+
+	while ((de = readdir(d)) != NULL) {
+		unsigned char dtype;
+
+		if (de->d_name[0] == '.')
+			continue;
+		if (ends_with(de->d_name, ".lock"))
+			continue;
+		strbuf_addstr(&refname, de->d_name);
+
+		dtype = get_dtype(de, &path, 1);
+		if (dtype == DT_REG && (is_pseudoref(ref_store, de->d_name) ||
+								is_headref(ref_store, de->d_name)))
+			loose_fill_ref_dir_regular_file(refs, refname.buf, dir);
+
+		strbuf_setlen(&refname, dirnamelen);
+	}
+	strbuf_release(&refname);
+	strbuf_release(&path);
+	closedir(d);
+}
+
+static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs,
+					     unsigned int flags)
 {
 	if (!refs->loose) {
+		struct ref_dir *dir;
+
 		/*
 		 * Mark the top-level directory complete because we
 		 * are about to read the only subdirectory that can
@@ -324,12 +378,17 @@ static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs)
 		/* We're going to fill the top level ourselves: */
 		refs->loose->root->flag &= ~REF_INCOMPLETE;
 
+		dir = get_ref_dir(refs->loose->root);
+
+		if (flags & DO_FOR_EACH_INCLUDE_ROOT_REFS)
+			add_pseudoref_and_head_entries(dir->cache->ref_store, dir,
+						       refs->loose->root->name);
+
 		/*
 		 * Add an incomplete entry for "refs/" (to be filled
 		 * lazily):
 		 */
-		add_entry_to_dir(get_ref_dir(refs->loose->root),
-				 create_dir_entry(refs->loose, "refs/", 5));
+		add_entry_to_dir(dir, create_dir_entry(refs->loose, "refs/", 5));
 	}
 	return refs->loose;
 }
@@ -857,7 +916,7 @@ static struct ref_iterator *files_ref_iterator_begin(
 	 * disk, and re-reads it if not.
 	 */
 
-	loose_iter = cache_ref_iterator_begin(get_loose_ref_cache(refs),
+	loose_iter = cache_ref_iterator_begin(get_loose_ref_cache(refs, flags),
 					      prefix, ref_store->repo, 1);
 
 	/*
@@ -1217,7 +1276,7 @@ static int files_pack_refs(struct ref_store *ref_store,
 
 	packed_refs_lock(refs->packed_ref_store, LOCK_DIE_ON_ERROR, &err);
 
-	iter = cache_ref_iterator_begin(get_loose_ref_cache(refs), NULL,
+	iter = cache_ref_iterator_begin(get_loose_ref_cache(refs, 0), NULL,
 					the_repository, 0);
 	while ((ok = ref_iterator_advance(iter)) == ITER_OK) {
 		/*
diff --git a/refs/refs-internal.h b/refs/refs-internal.h
index a9b6e88..56641aa 100644
--- a/refs/refs-internal.h
+++ b/refs/refs-internal.h
@@ -260,6 +260,12 @@ enum do_for_each_ref_flags {
 	 * INCLUDE_BROKEN, since they are otherwise not included at all.
 	 */
 	DO_FOR_EACH_OMIT_DANGLING_SYMREFS = (1 << 2),
+
+	/*
+	 * Include root refs i.e. HEAD and pseudorefs along with the regular
+	 * refs.
+	 */
+	DO_FOR_EACH_INCLUDE_ROOT_REFS = (1 << 3),
 };
 
 /*
diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
index 6c11c4a..eaa8296 100644
--- a/refs/reftable-backend.c
+++ b/refs/reftable-backend.c
@@ -364,12 +364,15 @@ static int reftable_ref_iterator_advance(struct ref_iterator *ref_iterator)
 			break;
 
 		/*
-		 * The files backend only lists references contained in
-		 * "refs/". We emulate the same behaviour here and thus skip
-		 * all references that don't start with this prefix.
+		 * The files backend only lists references contained in "refs/" unless
+		 * the root refs are to be included. We emulate the same behaviour here.
 		 */
-		if (!starts_with(iter->ref.refname, "refs/"))
+		if (!starts_with(iter->ref.refname, "refs/") &&
+		    !(iter->flags & DO_FOR_EACH_INCLUDE_ROOT_REFS &&
+		     (is_pseudoref(&iter->refs->base, iter->ref.refname) ||
+		      is_headref(&iter->refs->base, iter->ref.refname)))) {
 			continue;
+		}
 
 		if (iter->prefix &&
 		    strncmp(iter->prefix, iter->ref.refname, strlen(iter->prefix))) {
diff --git a/t/t0600-reffiles-backend.sh b/t/t0600-reffiles-backend.sh
index 09e71b2..6421434 100755
--- a/t/t0600-reffiles-backend.sh
+++ b/t/t0600-reffiles-backend.sh
@@ -279,18 +279,18 @@ test_expect_success 'setup worktree' '
 # direct FS access for creating the reflogs. 3) PSEUDO-WT and refs/bisect/random
 # do not create reflogs by default, so it is not testing a realistic scenario.
 test_expect_success 'for_each_reflog()' '
-	echo $ZERO_OID > .git/logs/PSEUDO-MAIN &&
+	echo $ZERO_OID >.git/logs/PSEUDO_MAIN_HEAD &&
 	mkdir -p     .git/logs/refs/bisect &&
-	echo $ZERO_OID > .git/logs/refs/bisect/random &&
+	echo $ZERO_OID >.git/logs/refs/bisect/random &&
 
-	echo $ZERO_OID > .git/worktrees/wt/logs/PSEUDO-WT &&
+	echo $ZERO_OID >.git/worktrees/wt/logs/PSEUDO_WT_HEAD &&
 	mkdir -p     .git/worktrees/wt/logs/refs/bisect &&
-	echo $ZERO_OID > .git/worktrees/wt/logs/refs/bisect/wt-random &&
+	echo $ZERO_OID >.git/worktrees/wt/logs/refs/bisect/wt-random &&
 
 	$RWT for-each-reflog >actual &&
 	cat >expected <<-\EOF &&
 	HEAD
-	PSEUDO-WT
+	PSEUDO_WT_HEAD
 	refs/bisect/wt-random
 	refs/heads/main
 	refs/heads/wt-main
@@ -300,7 +300,7 @@ test_expect_success 'for_each_reflog()' '
 	$RMAIN for-each-reflog >actual &&
 	cat >expected <<-\EOF &&
 	HEAD
-	PSEUDO-MAIN
+	PSEUDO_MAIN_HEAD
 	refs/bisect/random
 	refs/heads/main
 	refs/heads/wt-main
diff --git a/t/t6302-for-each-ref-filter.sh b/t/t6302-for-each-ref-filter.sh
index 82f3d1e..948f1bb 100755
--- a/t/t6302-for-each-ref-filter.sh
+++ b/t/t6302-for-each-ref-filter.sh
@@ -31,6 +31,37 @@ test_expect_success 'setup some history and refs' '
 	git update-ref refs/odd/spot main
 '
 
+test_expect_success '--include-root-refs pattern prints pseudorefs' '
+	cat >expect <<-\EOF &&
+	HEAD
+	ORIG_HEAD
+	refs/heads/main
+	refs/heads/side
+	refs/odd/spot
+	refs/tags/annotated-tag
+	refs/tags/doubly-annotated-tag
+	refs/tags/doubly-signed-tag
+	refs/tags/four
+	refs/tags/one
+	refs/tags/signed-tag
+	refs/tags/three
+	refs/tags/two
+	EOF
+	git update-ref ORIG_HEAD main &&
+	git for-each-ref --format="%(refname)" --include-root-refs >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '--include-root-refs with other patterns' '
+	cat >expect <<-\EOF &&
+	HEAD
+	ORIG_HEAD
+	EOF
+	git update-ref ORIG_HEAD main &&
+	git for-each-ref --format="%(refname)" --include-root-refs "*HEAD" >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'filtering with --points-at' '
 	cat >expect <<-\EOF &&
 	refs/heads/main