[PATCH v4 1/5] [GSOC] ref-filter: add obj-type check in grab contents

From: ZheNing Hu via GitGitGadget <gitgitgadget@gmail.com>
Date: Jul 26, 2021, 03:26 UTC
Message-ID: <0e294ff1626ef2b7992e84e8d960f5058bd39bdc.1627270010.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1000.v4.git.1627270010.gitgitgadget@gmail.com>

From: ZheNing Hu <adlternative@gmail.com>

Only tag and commit objects use `grab_sub_body_contents()` to grab object contents in the current codebase. We want to teach the function to also handle blobs and trees to get their raw data, without parsing a blob (whose contents looks like a commit or a tag) incorrectly as a commit or a tag. So it's needed to pass a `struct expand_data *data` instread of only `void *buf` to both `grab_sub_body_contents()` and `grab_values()` to be able to check the object type.

Skip the block of code that is specific to handling commits and tags early when the given object is of a wrong type to help later addition to handle other types of objects in this function.

Reviewed-by: Jacob Keller <jacob.keller@gmail.com>
Mentored-by: Christian Couder <christian.couder@gmail.com>
Mentored-by: Hariom Verma <hariom18599@gmail.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 ref-filter.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/ref-filter.c b/ref-filter.c
index 4db0e40ff4c..5cee6512fba 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -1356,11 +1356,12 @@ static void append_lines(struct strbuf *out, const char *buf, unsigned long size
 }
 
 /* See grab_values */
-static void grab_sub_body_contents(struct atom_value *val, int deref, void *buf)
+static void grab_sub_body_contents(struct atom_value *val, int deref, struct expand_data *data)
 {
 	int i;
 	const char *subpos = NULL, *bodypos = NULL, *sigpos = NULL;
 	size_t sublen = 0, bodylen = 0, nonsiglen = 0, siglen = 0;
+	void *buf = data->content;
 
 	for (i = 0; i < used_atom_cnt; i++) {
 		struct used_atom *atom = &used_atom[i];
@@ -1371,10 +1372,13 @@ static void grab_sub_body_contents(struct atom_value *val, int deref, void *buf)
 			continue;
 		if (deref)
 			name++;
-		if (strcmp(name, "body") &&
-		    !starts_with(name, "subject") &&
-		    !starts_with(name, "trailers") &&
-		    !starts_with(name, "contents"))
+
+		if ((data->type != OBJ_TAG &&
+		     data->type != OBJ_COMMIT) ||
+		    (strcmp(name, "body") &&
+		     !starts_with(name, "subject") &&
+		     !starts_with(name, "trailers") &&
+		     !starts_with(name, "contents")))
 			continue;
 		if (!subpos)
 			find_subpos(buf,
@@ -1438,17 +1442,19 @@ static void fill_missing_values(struct atom_value *val)
  * pointed at by the ref itself; otherwise it is the object the
  * ref (which is a tag) refers to.
  */
-static void grab_values(struct atom_value *val, int deref, struct object *obj, void *buf)
+static void grab_values(struct atom_value *val, int deref, struct object *obj, struct expand_data *data)
 {
+	void *buf = data->content;
+
 	switch (obj->type) {
 	case OBJ_TAG:
 		grab_tag_values(val, deref, obj);
-		grab_sub_body_contents(val, deref, buf);
+		grab_sub_body_contents(val, deref, data);
 		grab_person("tagger", val, deref, buf);
 		break;
 	case OBJ_COMMIT:
 		grab_commit_values(val, deref, obj);
-		grab_sub_body_contents(val, deref, buf);
+		grab_sub_body_contents(val, deref, data);
 		grab_person("author", val, deref, buf);
 		grab_person("committer", val, deref, buf);
 		break;
@@ -1678,7 +1684,7 @@ static int get_object(struct ref_array_item *ref, int deref, struct object **obj
 			return strbuf_addf_ret(err, -1, _("parse_object_buffer failed on %s for %s"),
 					       oid_to_hex(&oi->oid), ref->refname);
 		}
-		grab_values(ref->value, deref, *obj, oi->content);
+		grab_values(ref->value, deref, *obj, oi);
 	}
 
 	grab_common_values(ref->value, deref, oi);

-- 
gitgitgadget