odb: use size_t for object_info.sizep and the size APIs

When `js/objects-larger-than-4gb-on-windows` widened the streaming,
index-pack and unpack-objects code paths, in the interest of keeping the
patches somewhat reasonably-sized, it left the public ODB API still
typed in `unsigned long`. In particular `struct object_info::sizep` and
the four wrappers built on top of it (`odb_read_object`,
`odb_read_object_peeled`, `odb_read_object_info`, `odb_pretend_object`)
still return the unpacked size through `unsigned long *`, so on Windows
`cat-file -s` and the `git add` / `git status` paths for a >4 GiB blob
silently cap at 4 GiB.

Widen the field and the four wrappers. The previous commits already
widened the `unpack_entry()` cascade and pack-objects' in-core size
accessors, so most of the cascade arrives here with no further work: the
temporary shims in `packed_object_info_with_index_pos()` and in
`unpack_entry()`'s delta-base recovery path go away, the two
`SET_SIZE(entry, cast_size_t_to_ulong(canonical_size))` calls in
`check_object()` and the matching one in `drop_reused_delta()` collapse
to plain `SET_SIZE`, and `oe_get_size_slow()`'s tail
`cast_size_t_to_ulong()` is gone too.

What remains narrow are the boundaries this series does not
intend to touch: the diff, blame, textconv and fast-import machinery.

Even so, this patch is unfortunately quite large.

Assisted-by: Opus 4.7
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>

Author: dscho

apply.c

@@ -3321,7 +3321,7 @@ static int apply_binary(struct apply_state *state,
 	if (odb_has_object(the_repository->objects, &oid, 0)) {
 		/* We already have the postimage */
 		enum object_type type;
-		unsigned long size;
+		size_t size;
 		char *result;
 
 		result = odb_read_object(the_repository->objects, &oid,
@@ -3384,7 +3384,7 @@ static int read_blob_object(struct strbuf *buf, const struct object_id *oid, uns
 		strbuf_addf(buf, "Subproject commit %s\n", oid_to_hex(oid));
 	} else {
 		enum object_type type;
-		unsigned long sz;
+		size_t sz;
 		char *result;
 
 		result = odb_read_object(the_repository->objects, oid,
@@ -3611,7 +3611,7 @@ static int load_preimage(struct apply_state *state,
 
 static int resolve_to(struct image *image, const struct object_id *result_id)
 {
-	unsigned long size;
+	size_t size;
 	enum object_type type;
 	char *data;
 

archive.c

@@ -87,7 +87,7 @@ static void *object_file_to_archive(const struct archiver_args *args,
 				    const struct object_id *oid,
 				    unsigned int mode,
 				    enum object_type *type,
-				    unsigned long *sizep)
+				    size_t *sizep)
 {
 	void *buffer;
 	const struct commit *commit = args->convert ? args->commit : NULL;
@@ -158,7 +158,7 @@ static int write_archive_entry(const struct object_id *oid, const char *base,
 	write_archive_entry_fn_t write_entry = c->write_entry;
 	int err;
 	const char *path_without_prefix;
-	unsigned long size;
+	size_t size;
 	void *buffer;
 	enum object_type type;
 

attr.c

@@ -768,7 +768,7 @@ static struct attr_stack *read_attr_from_blob(struct index_state *istate,
 					      const char *path, unsigned flags)
 {
 	struct object_id oid;
-	unsigned long sz;
+	size_t sz;
 	enum object_type type;
 	void *buf;
 	unsigned short mode;

bisect.c

@@ -154,7 +154,7 @@ static void show_list(const char *debug, int counted, int nr,
 		struct commit *commit = p->item;
 		unsigned commit_flags = commit->object.flags;
 		enum object_type type;
-		unsigned long size;
+		size_t size;
 		char *buf = odb_read_object(the_repository->objects,
 					    &commit->object.oid, &type,
 					    &size);

blame.c

@@ -1041,10 +1041,13 @@ static void fill_origin_blob(struct diff_options *opt,
 		    textconv_object(opt->repo, o->path, o->mode,
 				    &o->blob_oid, 1, &file->ptr, &file_size))
 			;
-		else
+		else {
+			size_t file_size_st = 0;
 			file->ptr = odb_read_object(the_repository->objects,
 						    &o->blob_oid, &type,
-						    &file_size);
+						    &file_size_st);
+			file_size = cast_size_t_to_ulong(file_size_st);
+		}
 		file->size = file_size;
 
 		if (!file->ptr)
@@ -2869,10 +2872,14 @@ void setup_scoreboard(struct blame_scoreboard *sb,
 		    textconv_object(sb->repo, sb->path, o->mode, &o->blob_oid, 1, (char **) &sb->final_buf,
 				    &sb->final_buf_size))
 			;
-		else
+		else {
+			size_t final_buf_size_st = 0;
 			sb->final_buf = odb_read_object(the_repository->objects,
 							&o->blob_oid, &type,
-							&sb->final_buf_size);
+							&final_buf_size_st);
+			sb->final_buf_size =
+				cast_size_t_to_ulong(final_buf_size_st);
+		}
 
 		if (!sb->final_buf)
 			die(_("cannot read blob %s for path %s"),

builtin/cat-file.c

@@ -70,7 +70,7 @@ static char *replace_idents_using_mailmap(char *object_buf, size_t *size)
 
 static int filter_object(const char *path, unsigned mode,
 			 const struct object_id *oid,
-			 char **buf, unsigned long *size)
+			 char **buf, size_t *size)
 {
 	enum object_type type;
 
@@ -106,7 +106,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 	struct object_id oid;
 	enum object_type type;
 	char *buf;
-	unsigned long size;
+	size_t size;
 	struct object_context obj_context = {0};
 	struct object_info oi = OBJECT_INFO_INIT;
 	unsigned flags = OBJECT_INFO_LOOKUP_REPLACE;
@@ -152,7 +152,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 		if (use_mailmap && (type == OBJ_COMMIT || type == OBJ_TAG)) {
 			size_t s = size;
 			buf = replace_idents_using_mailmap(buf, &s);
-			size = cast_size_t_to_ulong(s);
+			size = s;
 		}
 
 		printf("%"PRIuMAX"\n", (uintmax_t)size);
@@ -174,9 +174,15 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 		break;
 
 	case 'c':
-		if (textconv_object(the_repository, path, obj_context.mode,
-				    &oid, 1, &buf, &size))
+	{
+		unsigned long size_ul = 0;
+		int textconv_ret = textconv_object(the_repository, path,
+						   obj_context.mode, &oid, 1,
+						   &buf, &size_ul);
+		size = size_ul;
+		if (textconv_ret)
 			break;
+	}
 		/* else fallthrough */
 
 	case 'p':
@@ -205,7 +211,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 		if (use_mailmap) {
 			size_t s = size;
 			buf = replace_idents_using_mailmap(buf, &s);
-			size = cast_size_t_to_ulong(s);
+			size = s;
 		}
 
 		/* otherwise just spit out the data */
@@ -252,7 +258,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 		if (use_mailmap) {
 			size_t s = size;
 			buf = replace_idents_using_mailmap(buf, &s);
-			size = cast_size_t_to_ulong(s);
+			size = s;
 		}
 		break;
 	}
@@ -274,7 +280,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 struct expand_data {
 	struct object_id oid;
 	enum object_type type;
-	unsigned long size;
+	size_t size;
 	unsigned short mode;
 	off_t disk_size;
 	const char *rest;
@@ -391,7 +397,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 			fflush(stdout);
 		if (opt->transform_mode) {
 			char *contents;
-			unsigned long size;
+			size_t size;
 
 			if (!data->rest)
 				die("missing path for '%s'", oid_to_hex(oid));
@@ -403,9 +409,12 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 					    oid_to_hex(oid), data->rest);
 			} else if (opt->transform_mode == 'c') {
 				enum object_type type;
-				if (!textconv_object(the_repository,
-						     data->rest, 0100644, oid,
-						     1, &contents, &size))
+				unsigned long size_ul = 0;
+				if (textconv_object(the_repository,
+						    data->rest, 0100644, oid,
+						    1, &contents, &size_ul))
+					size = size_ul;
+				else
 					contents = odb_read_object(the_repository->objects,
 								   oid, &type, &size);
 				if (!contents)
@@ -421,7 +430,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 	}
 	else {
 		enum object_type type;
-		unsigned long size;
+		size_t size;
 		void *contents;
 
 		contents = odb_read_object(the_repository->objects, oid,
@@ -432,7 +441,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 		if (use_mailmap) {
 			size_t s = size;
 			contents = replace_idents_using_mailmap(contents, &s);
-			size = cast_size_t_to_ulong(s);
+			size = s;
 		}
 
 		if (type != data->type)
@@ -541,7 +550,7 @@ static void batch_object_write(const char *obj_name,
 			if (!buf)
 				die(_("unable to read %s"), oid_to_hex(&data->oid));
 			buf = replace_idents_using_mailmap(buf, &s);
-			data->size = cast_size_t_to_ulong(s);
+			data->size = s;
 
 			free(buf);
 		}

builtin/difftool.c

@@ -319,7 +319,7 @@ static char *get_symlink(struct repository *repo,
 		data = strbuf_detach(&link, NULL);
 	} else {
 		enum object_type type;
-		unsigned long size;
+		size_t size;
 		data = odb_read_object(repo->objects, oid, &type, &size);
 		if (!data)
 			die(_("could not read object %s for symlink %s"),

builtin/fast-export.c

@@ -317,7 +317,10 @@ static void export_blob(const struct object_id *oid)
 		object = (struct object *)lookup_blob(the_repository, oid);
 		eaten = 0;
 	} else {
-		buf = odb_read_object(the_repository->objects, oid, &type, &size);
+		size_t size_st = 0;
+		buf = odb_read_object(the_repository->objects, oid, &type,
+				      &size_st);
+		size = cast_size_t_to_ulong(size_st);
 		if (!buf)
 			die(_("could not read blob %s"), oid_to_hex(oid));
 		if (check_object_signature(the_repository, oid, buf, size,
@@ -880,7 +883,7 @@ static char *anonymize_tag(void)
 
 static void handle_tag(const char *name, struct tag *tag)
 {
-	unsigned long size;
+	size_t size;
 	enum object_type type;
 	char *buf;
 	const char *tagger, *tagger_end, *message;

builtin/fast-import.c

@@ -1291,7 +1291,10 @@ static void load_tree(struct tree_entry *root)
 			die(_("can't load tree %s"), oid_to_hex(oid));
 	} else {
 		enum object_type type;
-		buf = odb_read_object(the_repository->objects, oid, &type, &size);
+		size_t size_st = 0;
+		buf = odb_read_object(the_repository->objects, oid, &type,
+				      &size_st);
+		size = cast_size_t_to_ulong(size_st);
 		if (!buf || type != OBJ_TREE)
 			die(_("can't load tree %s"), oid_to_hex(oid));
 	}
@@ -2560,7 +2563,7 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa
 			die(_("mark :%" PRIuMAX " not a commit"), commit_mark);
 		oidcpy(&commit_oid, &commit_oe->idx.oid);
 	} else if (!repo_get_oid(the_repository, p, &commit_oid)) {
-		unsigned long size;
+		size_t size;
 		char *buf = odb_read_object_peeled(the_repository->objects,
 						   &commit_oid, OBJ_COMMIT, &size,
 						   &commit_oid);
@@ -2627,10 +2630,12 @@ static void parse_from_existing(struct branch *b)
 		oidclr(&b->branch_tree.versions[1].oid, the_repository->hash_algo);
 	} else {
 		unsigned long size;
+		size_t size_st = 0;
 		char *buf;
 
 		buf = odb_read_object_peeled(the_repository->objects, &b->oid,
-					     OBJ_COMMIT, &size, &b->oid);
+					     OBJ_COMMIT, &size_st, &b->oid);
+		size = cast_size_t_to_ulong(size_st);
 		parse_from_commit(b, buf, size);
 		free(buf);
 	}
@@ -2722,7 +2727,7 @@ static struct hash_list *parse_merge(unsigned int *count)
 				die(_("mark :%" PRIuMAX " not a commit"), idnum);
 			oidcpy(&n->oid, &oe->idx.oid);
 		} else if (!repo_get_oid(the_repository, from, &n->oid)) {
-			unsigned long size;
+			size_t size;
 			char *buf = odb_read_object_peeled(the_repository->objects,
 							   &n->oid, OBJ_COMMIT,
 							   &size, &n->oid);
@@ -3330,7 +3335,10 @@ static void cat_blob(struct object_entry *oe, struct object_id *oid)
 	char *buf;
 
 	if (!oe || oe->pack_id == MAX_PACK_ID) {
-		buf = odb_read_object(the_repository->objects, oid, &type, &size);
+		size_t size_st = 0;
+		buf = odb_read_object(the_repository->objects, oid, &type,
+				      &size_st);
+		size = cast_size_t_to_ulong(size_st);
 	} else {
 		type = oe->type;
 		buf = gfi_unpack_entry(oe, &size);
@@ -3438,8 +3446,10 @@ static struct object_entry *dereference(struct object_entry *oe,
 		buf = gfi_unpack_entry(oe, &size);
 	} else {
 		enum object_type unused;
+		size_t size_st = 0;
 		buf = odb_read_object(the_repository->objects, oid,
-				      &unused, &size);
+				      &unused, &size_st);
+		size = cast_size_t_to_ulong(size_st);
 	}
 	if (!buf)
 		die(_("can't load object %s"), oid_to_hex(oid));

builtin/fsck.c

@@ -724,7 +724,7 @@ static int fsck_loose(const struct object_id *oid, const char *path,
 	struct for_each_loose_cb *data = cb_data;
 	struct object *obj;
 	enum object_type type = OBJ_NONE;
-	unsigned long size;
+	size_t size;
 	void *contents = NULL;
 	int eaten;
 	struct object_info oi = OBJECT_INFO_INIT;