Merge branch 'ot/ref-filter-object-info'

The "--format=<placeholder>" option of for-each-ref, branch and tag
learned to show a few more traits of objects that can be learned by
the object_info API.

* ot/ref-filter-object-info:
  ref-filter: give uintmax_t to format with %PRIuMAX
  ref-filter: add docs for new options
  ref-filter: add tests for deltabase
  ref-filter: add deltabase option
  ref-filter: add tests for objectsize:disk
  ref-filter: add check for negative file size
  ref-filter: add objectsize:disk option

Author: gitster

Documentation/git-for-each-ref.txt

@@ -128,13 +128,18 @@ objecttype::
 
 objectsize::
 	The size of the object (the same as 'git cat-file -s' reports).
-
+	Append `:disk` to get the size, in bytes, that the object takes up on
+	disk. See the note about on-disk sizes in the `CAVEATS` section below.
 objectname::
 	The object name (aka SHA-1).
 	For a non-ambiguous abbreviation of the object name append `:short`.
 	For an abbreviation of the object name with desired length append
 	`:short=<length>`, where the minimum length is MINIMUM_ABBREV. The
 	length may be exceeded to ensure unique object names.
+deltabase::
+	This expands to the object name of the delta base for the
+	given object, if it is stored as a delta.  Otherwise it
+	expands to the null object name (all zeroes).
 
 upstream::
 	The name of a local ref which can be considered ``upstream''
@@ -361,6 +366,20 @@ This prints the authorname, if present.
 git for-each-ref --format="%(refname)%(if)%(authorname)%(then) Authored by: %(authorname)%(end)"
 ------------
 
+CAVEATS
+-------
+
+Note that the sizes of objects on disk are reported accurately, but care
+should be taken in drawing conclusions about which refs or objects are
+responsible for disk usage. The size of a packed non-delta object may be
+much larger than the size of objects which delta against it, but the
+choice of which object is the base and which is the delta is arbitrary
+and is subject to change during a repack.
+
+Note also that multiple copies of an object may be present in the object
+database; in this case, it is undefined which copy's size or delta base
+will be reported.
+
 SEE ALSO
 --------
 linkgit:git-show-ref[1]

ref-filter.c

@@ -230,13 +230,31 @@ static int objecttype_atom_parser(const struct ref_format *format, struct used_a
 
 static int objectsize_atom_parser(const struct ref_format *format, struct used_atom *atom,
 				  const char *arg, struct strbuf *err)
+{
+	if (!arg) {
+		if (*atom->name == '*')
+			oi_deref.info.sizep = &oi_deref.size;
+		else
+			oi.info.sizep = &oi.size;
+	} else if (!strcmp(arg, "disk")) {
+		if (*atom->name == '*')
+			oi_deref.info.disk_sizep = &oi_deref.disk_size;
+		else
+			oi.info.disk_sizep = &oi.disk_size;
+	} else
+		return strbuf_addf_ret(err, -1, _("unrecognized %%(objectsize) argument: %s"), arg);
+	return 0;
+}
+
+static int deltabase_atom_parser(const struct ref_format *format, struct used_atom *atom,
+				 const char *arg, struct strbuf *err)
 {
 	if (arg)
-		return strbuf_addf_ret(err, -1, _("%%(objectsize) does not take arguments"));
+		return strbuf_addf_ret(err, -1, _("%%(deltabase) does not take arguments"));
 	if (*atom->name == '*')
-		oi_deref.info.sizep = &oi_deref.size;
+		oi_deref.info.delta_base_sha1 = oi_deref.delta_base_oid.hash;
 	else
-		oi.info.sizep = &oi.size;
+		oi.info.delta_base_sha1 = oi.delta_base_oid.hash;
 	return 0;
 }
 
@@ -431,6 +449,7 @@ static struct {
 	{ "objecttype", SOURCE_OTHER, FIELD_STR, objecttype_atom_parser },
 	{ "objectsize", SOURCE_OTHER, FIELD_ULONG, objectsize_atom_parser },
 	{ "objectname", SOURCE_OTHER, FIELD_STR, objectname_atom_parser },
+	{ "deltabase", SOURCE_OTHER, FIELD_STR, deltabase_atom_parser },
 	{ "tree", SOURCE_OBJ },
 	{ "parent", SOURCE_OBJ },
 	{ "numparent", SOURCE_OBJ, FIELD_ULONG },
@@ -880,10 +899,14 @@ static void grab_common_values(struct atom_value *val, int deref, struct expand_
 			name++;
 		if (!strcmp(name, "objecttype"))
 			v->s = xstrdup(type_name(oi->type));
-		else if (!strcmp(name, "objectsize")) {
+		else if (!strcmp(name, "objectsize:disk")) {
+			v->value = oi->disk_size;
+			v->s = xstrfmt("%"PRIuMAX, (uintmax_t)oi->disk_size);
+		} else if (!strcmp(name, "objectsize")) {
 			v->value = oi->size;
 			v->s = xstrfmt("%"PRIuMAX , (uintmax_t)oi->size);
-		}
+		} else if (!strcmp(name, "deltabase"))
+			v->s = xstrdup(oid_to_hex(&oi->delta_base_oid));
 		else if (deref)
 			grab_objectname(name, &oi->oid, v, &used_atom[i]);
 	}
@@ -1482,6 +1505,8 @@ static int get_object(struct ref_array_item *ref, int deref, struct object **obj
 				     OBJECT_INFO_LOOKUP_REPLACE))
 		return strbuf_addf_ret(err, -1, _("missing object %s for %s"),
 				       oid_to_hex(&oi->oid), ref->refname);
+	if (oi->info.disk_sizep && oi->disk_size < 0)
+		BUG("Object size is less than zero.");
 
 	if (oi->info.contentp) {
 		*obj = parse_object_buffer(the_repository, &oi->oid, oi->type, oi->size, oi->content, &eaten);

t/t6300-for-each-ref.sh

@@ -83,6 +83,8 @@ test_atom head push:strip=1 remotes/myfork/master
 test_atom head push:strip=-1 master
 test_atom head objecttype commit
 test_atom head objectsize 171
+test_atom head objectsize:disk 138
+test_atom head deltabase 0000000000000000000000000000000000000000
 test_atom head objectname $(git rev-parse refs/heads/master)
 test_atom head objectname:short $(git rev-parse --short refs/heads/master)
 test_atom head objectname:short=1 $(git rev-parse --short=1 refs/heads/master)
@@ -124,6 +126,10 @@ test_atom tag upstream ''
 test_atom tag push ''
 test_atom tag objecttype tag
 test_atom tag objectsize 154
+test_atom tag objectsize:disk 138
+test_atom tag '*objectsize:disk' 138
+test_atom tag deltabase 0000000000000000000000000000000000000000
+test_atom tag '*deltabase' 0000000000000000000000000000000000000000
 test_atom tag objectname $(git rev-parse refs/tags/testtag)
 test_atom tag objectname:short $(git rev-parse --short refs/tags/testtag)
 test_atom head objectname:short=1 $(git rev-parse --short=1 refs/heads/master)