object-file API: add a format_object_header() function

Add a convenience function to wrap the xsnprintf() command that
generates loose object headers. This code was copy/pasted in various
parts of the codebase, let's define it in one place and re-use it from
there.

All except one caller of it had a valid "enum object_type" for us,
it's only write_object_file_prepare() which might need to deal with
"git hash-object --literally" and a potential garbage type. Let's have
the primary API use an "enum object_type", and define a *_literally()
function that can take an arbitrary "const char *" for the type.

See [1] for the discussion that prompted this patch, i.e. new code in
object-file.c that wanted to copy/paste the xsnprintf() invocation.

In the case of fast-import.c the callers unfortunately need to cast
back & forth between "unsigned char *" and "char *", since
format_object_header() ad encode_in_pack_object_header() take
different signedness.

1. https://lore.kernel.org/git/211213.86bl1l9bfz.gmgdl@evledraar.gmail.com/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

6 files changed, 35 insertions, 11 deletions

diff --git a/builtin/fast-import.c b/builtin/fast-import.c
index 2b2e28bad7..123df7d9a5 100644
--- a/builtin/fast-import.c
+++ b/builtin/fast-import.c
@@ -937,8 +937,8 @@ static int store_object(
 	git_hash_ctx c;
 	git_zstream s;
 
-	hdrlen = xsnprintf((char *)hdr, sizeof(hdr), "%s %lu",
-			   type_name(type), (unsigned long)dat->len) + 1;
+	hdrlen = format_object_header((char *)hdr, sizeof(hdr), type,
+				      dat->len);
 	the_hash_algo->init_fn(&c);
 	the_hash_algo->update_fn(&c, hdr, hdrlen);
 	the_hash_algo->update_fn(&c, dat->buf, dat->len);
@@ -1091,7 +1091,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
 	hashfile_checkpoint(pack_file, &checkpoint);
 	offset = checkpoint.offset;
 
-	hdrlen = xsnprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1;
+	hdrlen = format_object_header((char *)out_buf, out_sz, OBJ_BLOB, len);
 
 	the_hash_algo->init_fn(&c);
 	the_hash_algo->update_fn(&c, out_buf, hdrlen);
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 3c2e6aee3c..01574378ce 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -449,8 +449,7 @@ static void *unpack_entry_data(off_t offset, unsigned long size,
 	int hdrlen;
 
 	if (!is_delta_type(type)) {
-		hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX,
-				   type_name(type),(uintmax_t)size) + 1;
+		hdrlen = format_object_header(hdr, sizeof(hdr), type, size);
 		the_hash_algo->init_fn(&c);
 		the_hash_algo->update_fn(&c, hdr, hdrlen);
 	} else
diff --git a/bulk-checkin.c b/bulk-checkin.c
index 8785b2ac80..85b3ebaf97 100644
--- a/bulk-checkin.c
+++ b/bulk-checkin.c
@@ -220,8 +220,8 @@ static int deflate_to_pack(struct bulk_checkin_state *state,
 	if (seekback == (off_t) -1)
 		return error("cannot find the current offset");
 
-	header_len = xsnprintf((char *)obuf, sizeof(obuf), "%s %" PRIuMAX,
-			       type_name(type), (uintmax_t)size) + 1;
+	header_len = format_object_header((char *)obuf, sizeof(obuf),
+					  type, size);
 	the_hash_algo->init_fn(&ctx);
 	the_hash_algo->update_fn(&ctx, obuf, header_len);
 
diff --git a/http-push.c b/http-push.c
index 3309aaf004..f0c044dcf7 100644
--- a/http-push.c
+++ b/http-push.c
@@ -363,7 +363,7 @@ static void start_put(struct transfer_request *request)
 	git_zstream stream;
 
 	unpacked = read_object_file(&request->obj->oid, &type, &len);
-	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX , type_name(type), (uintmax_t)len) + 1;
+	hdrlen = format_object_header(hdr, sizeof(hdr), type, len);
 
 	/* Set it up */
 	git_deflate_init(&stream, zlib_compression_level);
diff --git a/object-file.c b/object-file.c
index eeb6814780..3fcd46cf9e 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1049,6 +1049,23 @@ void *xmmap(void *start, size_t length,
 	return ret;
 }
 
+static int format_object_header_literally(char *str, size_t size,
+					  const char *type, size_t objsize)
+{
+	return xsnprintf(str, size, "%s %"PRIuMAX, type, (uintmax_t)objsize) + 1;
+}
+
+int format_object_header(char *str, size_t size, enum object_type type,
+			 size_t objsize)
+{
+	const char *name = type_name(type);
+
+	if (!name)
+		BUG("could not get a type name for 'enum object_type' value %d", type);
+
+	return format_object_header_literally(str, size, name, objsize);
+}
+
 /*
  * With an in-core object data in "map", rehash it to make sure the
  * object name actually matches "oid" to detect object corruption.
@@ -1077,7 +1094,7 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
 		return -1;
 
 	/* Generate the header */
-	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX , type_name(obj_type), (uintmax_t)size) + 1;
+	hdrlen = format_object_header(hdr, sizeof(hdr), obj_type, size);
 
 	/* Sha1.. */
 	r->hash_algo->init_fn(&c);
@@ -1777,7 +1794,7 @@ static void write_object_file_prepare(const struct git_hash_algo *algo,
 	git_hash_ctx c;
 
 	/* Generate the header */
-	*hdrlen = xsnprintf(hdr, *hdrlen, "%s %"PRIuMAX , type, (uintmax_t)len)+1;
+	*hdrlen = format_object_header_literally(hdr, *hdrlen, type, len);
 
 	/* Sha1.. */
 	algo->init_fn(&c);
@@ -2051,7 +2068,7 @@ int force_object_loose(const struct object_id *oid, time_t mtime)
 	buf = read_object(the_repository, oid, &type, &len);
 	if (!buf)
 		return error(_("cannot read object for %s"), oid_to_hex(oid));
-	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX , type_name(type), (uintmax_t)len) + 1;
+	hdrlen = format_object_header(hdr, sizeof(hdr), type, len);
 	ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0);
 	free(buf);
 
diff --git a/object-store.h b/object-store.h
index 44f6868cc9..8b4413d0ce 100644
--- a/object-store.h
+++ b/object-store.h
@@ -331,6 +331,14 @@ int repo_has_object_file_with_flags(struct repository *r,
  */
 int has_loose_object_nonlocal(const struct object_id *);
 
+/**
+ * format_object_header() is a thin wrapper around s xsnprintf() that
+ * writes the initial "<type> <obj-len>" part of the loose object
+ * header. It returns the size that snprintf() returns + 1.
+ */
+int format_object_header(char *str, size_t size, enum object_type type,
+			 size_t objsize);
+
 void assert_oid_type(const struct object_id *oid, enum object_type expect);
 
 /*