git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 18/25] make add_object_array_with_context interface more sane

From
Jeff King <peff@peff.net>
Date
Oct 15, 2014, 22:42 UTC
Message-ID
<20141015224256.GR25630@peff.net>
In-Reply-To
<20141015223244.GA25368@peff.net>

When you resolve a sha1, you can optionally keep any context found during the resolution, including the path and mode of a tree entry (e.g., when looking up "HEAD:subdir/file.c").

The add_object_array_with_context function lets you then attach that context to an entry in a list. Unfortunately, the interface for doing so is horrible. The object_context structure is large and most object_array users do not use it. Therefore we keep a pointer to the structure to avoid burdening other users too much. But that means when we do use it that we must allocate the struct ourselves. And the struct contains a fixed PATH_MAX-sized buffer, which makes this wholly unsuitable for any large arrays.

We can observe that there is only a single user of the "with_context" variant: builtin/grep.c. And in that use case, the only element we care about is the path. We can therefore store only the path as a pointer (the context's mode field was redundant with the object_array_entry itself, and nobody actually cared about the surrounding tree). This still requires a strdup of the pathname, but at least we are only consuming the minimum amount of memory for each string.

We can also handle the copying ourselves in add_object_array_*, and free it as appropriate in object_array_release_entry.

Signed-off-by: Jeff King <peff@peff.net>
---
 builtin/grep.c |  8 ++++----
 object.c       | 23 +++++++++--------------
 object.h       |  4 ++--
 3 files changed, 15 insertions(+), 20 deletions(-)
diff --git a/builtin/grep.c b/builtin/grep.c
index c86a142..4063882 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -456,10 +456,10 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 }
 
 static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
-		       struct object *obj, const char *name, struct object_context *oc)
+		       struct object *obj, const char *name, const char *path)
 {
 	if (obj->type == OBJ_BLOB)
-		return grep_sha1(opt, obj->sha1, name, 0, oc ? oc->path : NULL);
+		return grep_sha1(opt, obj->sha1, name, 0, path);
 	if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
 		struct tree_desc tree;
 		void *data;
@@ -501,7 +501,7 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
 	for (i = 0; i < nr; i++) {
 		struct object *real_obj;
 		real_obj = deref_tag(list->objects[i].item, NULL, 0);
-		if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].context)) {
+		if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].path)) {
 			hit = 1;
 			if (opt->status_only)
 				break;
@@ -821,7 +821,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			struct object *object = parse_object_or_die(sha1, arg);
 			if (!seen_dashdash)
 				verify_non_filename(prefix, arg);
-			add_object_array_with_context(object, arg, &list, xmemdupz(&oc, sizeof(struct object_context)));
+			add_object_array_with_path(object, arg, &list, oc.mode, oc.path);
 			continue;
 		}
 		if (!strcmp(arg, "--")) {
diff --git a/object.c b/object.c
index 6aeb1bb..df86bdd 100644
--- a/object.c
+++ b/object.c
@@ -307,10 +307,9 @@ int object_list_contains(struct object_list *list, struct object *obj)
  */
 static char object_array_slopbuf[1];
 
-static void add_object_array_with_mode_context(struct object *obj, const char *name,
-					       struct object_array *array,
-					       unsigned mode,
-					       struct object_context *context)
+void add_object_array_with_path(struct object *obj, const char *name,
+				struct object_array *array,
+				unsigned mode, const char *path)
 {
 	unsigned nr = array->nr;
 	unsigned alloc = array->alloc;
@@ -333,7 +332,10 @@ static void add_object_array_with_mode_context(struct object *obj, const char *n
 	else
 		entry->name = xstrdup(name);
 	entry->mode = mode;
-	entry->context = context;
+	if (path)
+		entry->path = xstrdup(path);
+	else
+		entry->path = NULL;
 	array->nr = ++nr;
 }
 
@@ -344,15 +346,7 @@ void add_object_array(struct object *obj, const char *name, struct object_array
 
 void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode)
 {
-	add_object_array_with_mode_context(obj, name, array, mode, NULL);
-}
-
-void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context)
-{
-	if (context)
-		add_object_array_with_mode_context(obj, name, array, context->mode, context);
-	else
-		add_object_array_with_mode_context(obj, name, array, S_IFINVALID, context);
+	add_object_array_with_path(obj, name, array, mode, NULL);
 }
 
 /*
@@ -363,6 +357,7 @@ static void object_array_release_entry(struct object_array_entry *ent)
 {
 	if (ent->name != object_array_slopbuf)
 		free(ent->name);
+	free(ent->path);
 }
 
 void object_array_filter(struct object_array *array,
diff --git a/object.h b/object.h
index 2a755a2..e5178a5 100644
--- a/object.h
+++ b/object.h
@@ -18,8 +18,8 @@ struct object_array {
 		 * empty string.
 		 */
 		char *name;
+		char *path;
 		unsigned mode;
-		struct object_context *context;
 	} *objects;
 };
 
@@ -115,7 +115,7 @@ int object_list_contains(struct object_list *list, struct object *obj);
 /* Object array handling .. */
 void add_object_array(struct object *obj, const char *name, struct object_array *array);
 void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode);
-void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context);
+void add_object_array_with_path(struct object *obj, const char *name, struct object_array *array, unsigned mode, const char *path);
 
 typedef int (*object_array_each_func_t)(struct object_array_entry *, void *);
 
-- 
2.1.2.596.g7379948
Previous: Jeff KingNext: Jeff King
Message 25 of 48 in “prune-safety”
  1. 0/25 prune-safetyJeff King, Oct 15, 2014
  2. 01/25 foreach_alt_odb: propagate return value from callbackJeff King, Oct 15, 2014
  3. 02/25 isxdigit: cast input to unsigned charJeff King, Oct 15, 2014
  4. Junio C HamanoOct 16, 2014
  5. 03/25 object_array: factor out slopbuf-freeing logicJeff King, Oct 15, 2014
  6. Junio C HamanoOct 16, 2014
  7. git-bundle rev handling and de-dupingJeff King, Oct 17, 2014
  8. Philip OakleyOct 17, 2014
  9. Junio C HamanoOct 17, 2014
  10. 04/25 object_array: add a "clear" functionJeff King, Oct 15, 2014
  11. 05/25 clean up name allocation in prepare_revision_walkJeff King, Oct 15, 2014
  12. 06/25 reachable: use traverse_commit_list instead of custom walkJeff King, Oct 15, 2014
  13. Junio C HamanoOct 16, 2014
  14. 07/25 reachable: reuse revision.c "add all reflogs" codeJeff King, Oct 15, 2014
  15. 08/25 prune: factor out loose-object directory traversalJeff King, Oct 15, 2014
  16. 09/25 reachable: mark index blobs as SEENJeff King, Oct 15, 2014
  17. 10/25 prune-packed: use for_each_loose_file_in_objdirJeff King, Oct 15, 2014
  18. 11/25 count-objects: do not use xsize_t when counting object sizeJeff King, Oct 15, 2014
  19. 12/25 count-objects: use for_each_loose_file_in_objdirJeff King, Oct 15, 2014
  20. 13/25 sha1_file: add for_each iterators for loose and packed objectsJeff King, Oct 15, 2014
  21. 14/25 prune: keep objects reachable from recent objectsJeff King, Oct 15, 2014
  22. 15/25 pack-objects: refactor unpack-unreachable expiration checkJeff King, Oct 15, 2014
  23. 16/25 pack-objects: match prune logic for discarding objectsJeff King, Oct 15, 2014
  24. 17/25 write_sha1_file: freshen existing objectsJeff King, Oct 15, 2014
  25. 18/25 make add_object_array_with_context interface more saneJeff King, Oct 15, 2014
  26. 19/25 traverse_commit_list: support pending blobs/trees with pathsJeff King, Oct 15, 2014
  27. 20/25 rev-list: document --reflog optionJeff King, Oct 15, 2014
  28. 21/25 rev-list: add --index-objects optionJeff King, Oct 15, 2014
  29. Junio C HamanoOct 16, 2014
  30. Jeff KingOct 17, 2014
  31. Jeff KingOct 17, 2014
  32. 22/26 rev-list: add --indexed-objects optionJeff King, Oct 17, 2014
  33. 23/26 reachable: use revision machinery's --indexed-objects codeJeff King, Oct 17, 2014
  34. 24/26 pack-objects: use argv_arrayJeff King, Oct 17, 2014
  35. 25/26 repack: pack objects mentioned by the indexJeff King, Oct 17, 2014
  36. 26/26 pack-objects: double-check options before discarding objectsJeff King, Oct 17, 2014
  37. 22/25 reachable: use revision machinery's --index-objects codeJeff King, Oct 15, 2014
  38. 23/25 pack-objects: use argv_arrayJeff King, Oct 15, 2014
  39. 24/25 repack: pack objects mentioned by the indexJeff King, Oct 15, 2014
  40. 25/25 pack-objects: double-check options before discarding objectsJeff King, Oct 15, 2014
  41. Junio C HamanoOct 16, 2014
  42. Junio C HamanoOct 16, 2014
  43. Jeff KingOct 16, 2014
  44. Jeff KingOct 16, 2014
  45. Junio C HamanoOct 16, 2014
  46. Jeff KingOct 17, 2014
  47. Jeff KingOct 18, 2014
  48. Jeff KingOct 17, 2014

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.