Merge branch 'bc/tree-walk-oid'

The code to walk tree objects has been taught that we may be
working with object names that are not computed with SHA-1.

* bc/tree-walk-oid:
  cache: make oidcpy always copy GIT_MAX_RAWSZ bytes
  tree-walk: store object_id in a separate member
  match-trees: use hashcpy to splice trees
  match-trees: compute buffer offset correctly when splicing
  tree-walk: copy object ID before use

builtin/grep.c

@@ -570,7 +570,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		strbuf_add(base, entry.path, te_len);
 
 		if (S_ISREG(entry.mode)) {
-			hit |= grep_oid(opt, entry.oid, base->buf, tn_len,
+			hit |= grep_oid(opt, &entry.oid, base->buf, tn_len,
 					 check_attr ? base->buf + tn_len : NULL);
 		} else if (S_ISDIR(entry.mode)) {
 			enum object_type type;
@@ -578,10 +578,10 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 			void *data;
 			unsigned long size;
 
-			data = lock_and_read_oid_file(entry.oid, &type, &size);
+			data = lock_and_read_oid_file(&entry.oid, &type, &size);
 			if (!data)
 				die(_("unable to read tree (%s)"),
-				    oid_to_hex(entry.oid));
+				    oid_to_hex(&entry.oid));
 
 			strbuf_addch(base, '/');
 			init_tree_desc(&sub, data, size);
@@ -589,7 +589,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 					 check_attr, repo);
 			free(data);
 		} else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
-			hit |= grep_submodule(opt, repo, pathspec, entry.oid,
+			hit |= grep_submodule(opt, repo, pathspec, &entry.oid,
 					      base->buf, base->buf + tn_len);
 		}
 

builtin/merge-tree.c

@@ -154,15 +154,15 @@ static void show_result(void)
 /* An empty entry never compares same, not even to another empty entry */
 static int same_entry(struct name_entry *a, struct name_entry *b)
 {
-	return	a->oid &&
+	return	!is_null_oid(&a->oid) &&
-		b->oid &&
+		!is_null_oid(&b->oid) &&
-		oideq(a->oid, b->oid) &&
+		oideq(&a->oid, &b->oid) &&
 		a->mode == b->mode;
 }
 
 static int both_empty(struct name_entry *a, struct name_entry *b)
 {
-	return !(a->oid || b->oid);
+	return is_null_oid(&a->oid) && is_null_oid(&b->oid);
 }
 
 static struct merge_list *create_entry(unsigned stage, unsigned mode, const struct object_id *oid, const char *path)
@@ -178,7 +178,7 @@ static struct merge_list *create_entry(unsigned stage, unsigned mode, const stru
 
 static char *traverse_path(const struct traverse_info *info, const struct name_entry *n)
 {
-	char *path = xmallocz(traverse_path_len(info, n));
+	char *path = xmallocz(traverse_path_len(info, n) + the_hash_algo->rawsz);
 	return make_traverse_path(path, info, n);
 }
 
@@ -192,8 +192,8 @@ static void resolve(const struct traverse_info *info, struct name_entry *ours, s
 		return;
 
 	path = traverse_path(info, result);
-	orig = create_entry(2, ours->mode, ours->oid, path);
+	orig = create_entry(2, ours->mode, &ours->oid, path);
-	final = create_entry(0, result->mode, result->oid, path);
+	final = create_entry(0, result->mode, &result->oid, path);
 
 	final->link = orig;
 
@@ -217,7 +217,7 @@ static void unresolved_directory(const struct traverse_info *info,
 
 	newbase = traverse_path(info, p);
 
-#define ENTRY_OID(e) (((e)->mode && S_ISDIR((e)->mode)) ? (e)->oid : NULL)
+#define ENTRY_OID(e) (((e)->mode && S_ISDIR((e)->mode)) ? &(e)->oid : NULL)
 	buf0 = fill_tree_descriptor(t + 0, ENTRY_OID(n + 0));
 	buf1 = fill_tree_descriptor(t + 1, ENTRY_OID(n + 1));
 	buf2 = fill_tree_descriptor(t + 2, ENTRY_OID(n + 2));
@@ -243,7 +243,7 @@ static struct merge_list *link_entry(unsigned stage, const struct traverse_info
 		path = entry->path;
 	else
 		path = traverse_path(info, n);
-	link = create_entry(stage, n->mode, n->oid, path);
+	link = create_entry(stage, n->mode, &n->oid, path);
 	link->link = entry;
 	return link;
 }
@@ -318,7 +318,7 @@ static int threeway_callback(int n, unsigned long mask, unsigned long dirmask, s
 	}
 
 	if (same_entry(entry+0, entry+1)) {
-		if (entry[2].oid && !S_ISDIR(entry[2].mode)) {
+		if (!is_null_oid(&entry[2].oid) && !S_ISDIR(entry[2].mode)) {
 			/* We did not touch, they modified -- take theirs */
 			resolve(info, entry+1, entry+2);
 			return mask;

builtin/pack-objects.c

@@ -1334,7 +1334,7 @@ static void add_pbase_object(struct tree_desc *tree,
 		if (cmp < 0)
 			return;
 		if (name[cmplen] != '/') {
-			add_object_entry(entry.oid,
+			add_object_entry(&entry.oid,
 					 object_type(entry.mode),
 					 fullname, 1);
 			return;
@@ -1345,7 +1345,7 @@ static void add_pbase_object(struct tree_desc *tree,
 			const char *down = name+cmplen+1;
 			int downlen = name_cmp_len(down);
 
-			tree = pbase_tree_get(entry.oid);
+			tree = pbase_tree_get(&entry.oid);
 			if (!tree)
 				return;
 			init_tree_desc(&sub, tree->tree_data, tree->tree_size);

builtin/reflog.c

@@ -94,8 +94,8 @@ static int tree_is_complete(const struct object_id *oid)
 	init_tree_desc(&desc, tree->buffer, tree->size);
 	complete = 1;
 	while (tree_entry(&desc, &entry)) {
-		if (!has_sha1_file(entry.oid->hash) ||
+		if (!has_sha1_file(entry.oid.hash) ||
-		    (S_ISDIR(entry.mode) && !tree_is_complete(entry.oid))) {
+		    (S_ISDIR(entry.mode) && !tree_is_complete(&entry.oid))) {
 			tree->object.flags |= INCOMPLETE;
 			complete = 0;
 		}

cache-tree.c

@@ -675,7 +675,7 @@ static void prime_cache_tree_rec(struct repository *r,
 			cnt++;
 		else {
 			struct cache_tree_sub *sub;
-			struct tree *subtree = lookup_tree(r, entry.oid);
+			struct tree *subtree = lookup_tree(r, &entry.oid);
 			if (!subtree->object.parsed)
 				parse_tree(subtree);
 			sub = cache_tree_sub(it, entry.path);
@@ -724,7 +724,7 @@ int cache_tree_matches_traversal(struct cache_tree *root,
 
 	it = find_cache_tree_from_traversal(root, info);
 	it = cache_tree_find(it, ent->path);
-	if (it && it->entry_count > 0 && oideq(ent->oid, &it->oid))
+	if (it && it->entry_count > 0 && oideq(&ent->oid, &it->oid))
 		return it->entry_count;
 	return 0;
 }

cache.h

@@ -1084,7 +1084,7 @@ static inline void hashcpy(unsigned char *sha_dst, const unsigned char *sha_src)
 
 static inline void oidcpy(struct object_id *dst, const struct object_id *src)
 {
-	hashcpy(dst->hash, src->hash);
+	memcpy(dst->hash, src->hash, GIT_MAX_RAWSZ);
 }
 
 static inline struct object_id *oiddup(const struct object_id *src)

contrib/coccinelle/object_id.cocci

@@ -86,36 +86,6 @@ struct object_id OID;
 - hashcmp(OID.hash, OIDPTR->hash)
 + oidcmp(&OID, OIDPTR)
 
-@@
-struct object_id OID1, OID2;
-@@
-- hashcpy(OID1.hash, OID2.hash)
-+ oidcpy(&OID1, &OID2)
-
-@@
-identifier f != oidcpy;
-struct object_id *OIDPTR1;
-struct object_id *OIDPTR2;
-@@
-  f(...) {<...
-- hashcpy(OIDPTR1->hash, OIDPTR2->hash)
-+ oidcpy(OIDPTR1, OIDPTR2)
-  ...>}
-
-@@
-struct object_id *OIDPTR;
-struct object_id OID;
-@@
-- hashcpy(OIDPTR->hash, OID.hash)
-+ oidcpy(OIDPTR, &OID)
-
-@@
-struct object_id *OIDPTR;
-struct object_id OID;
-@@
-- hashcpy(OID.hash, OIDPTR->hash)
-+ oidcpy(&OID, OIDPTR)
-
 @@
 struct object_id *OIDPTR1;
 struct object_id *OIDPTR2;

delta-islands.c

@@ -296,7 +296,7 @@ void resolve_tree_islands(struct repository *r,
 			if (S_ISGITLINK(entry.mode))
 				continue;
 
-			obj = lookup_object(r, entry.oid->hash);
+			obj = lookup_object(r, entry.oid.hash);
 			if (!obj)
 				continue;
 

fsck.c

@@ -410,14 +410,14 @@ static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *op
 			continue;
 
 		if (S_ISDIR(entry.mode)) {
-			obj = (struct object *)lookup_tree(the_repository, entry.oid);
+			obj = (struct object *)lookup_tree(the_repository, &entry.oid);
 			if (name && obj)
 				put_object_name(options, obj, "%s%s/", name,
 					entry.path);
 			result = options->walk(obj, OBJ_TREE, data, options);
 		}
 		else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode)) {
-			obj = (struct object *)lookup_blob(the_repository, entry.oid);
+			obj = (struct object *)lookup_blob(the_repository, &entry.oid);
 			if (name && obj)
 				put_object_name(options, obj, "%s%s", name,
 					entry.path);

http-push.c

@@ -1311,11 +1311,11 @@ static struct object_list **process_tree(struct tree *tree,
 	while (tree_entry(&desc, &entry))
 		switch (object_type(entry.mode)) {
 		case OBJ_TREE:
-			p = process_tree(lookup_tree(the_repository, entry.oid),
+			p = process_tree(lookup_tree(the_repository, &entry.oid),
 					 p);
 			break;
 		case OBJ_BLOB:
-			p = process_blob(lookup_blob(the_repository, entry.oid),
+			p = process_blob(lookup_blob(the_repository, &entry.oid),
 					 p);
 			break;
 		default:

list-objects.c

@@ -124,15 +124,15 @@ static void process_tree_contents(struct traversal_context *ctx,
 		}
 
 		if (S_ISDIR(entry.mode)) {
-			struct tree *t = lookup_tree(ctx->revs->repo, entry.oid);
+			struct tree *t = lookup_tree(ctx->revs->repo, &entry.oid);
 			t->object.flags |= NOT_USER_GIVEN;
 			process_tree(ctx, t, base, entry.path);
 		}
 		else if (S_ISGITLINK(entry.mode))
-			process_gitlink(ctx, entry.oid->hash,
+			process_gitlink(ctx, entry.oid.hash,
 					base, entry.path);
 		else {
-			struct blob *b = lookup_blob(ctx->revs->repo, entry.oid);
+			struct blob *b = lookup_blob(ctx->revs->repo, &entry.oid);
 			b->object.flags |= NOT_USER_GIVEN;
 			process_blob(ctx, b, base, entry.path);
 		}

match-trees.c

@@ -106,7 +106,7 @@ static int score_trees(const struct object_id *hash1, const struct object_id *ha
 			update_tree_entry(&two);
 		} else {
 			/* path appears in both */
-			if (!oideq(one.entry.oid, two.entry.oid)) {
+			if (!oideq(&one.entry.oid, &two.entry.oid)) {
 				/* they are different */
 				score += score_differs(one.entry.mode,
 						       two.entry.mode,
@@ -179,7 +179,7 @@ static int splice_tree(const struct object_id *oid1, const char *prefix,
 	char *buf;
 	unsigned long sz;
 	struct tree_desc desc;
-	struct object_id *rewrite_here;
+	unsigned char *rewrite_here;
 	const struct object_id *rewrite_with;
 	struct object_id subtree;
 	enum object_type type;
@@ -199,15 +199,26 @@ static int splice_tree(const struct object_id *oid1, const char *prefix,
 	while (desc.size) {
 		const char *name;
 		unsigned mode;
-		const struct object_id *oid;
 
-		oid = tree_entry_extract(&desc, &name, &mode);
+		tree_entry_extract(&desc, &name, &mode);
 		if (strlen(name) == toplen &&
 		    !memcmp(name, prefix, toplen)) {
 			if (!S_ISDIR(mode))
 				die("entry %s in tree %s is not a tree", name,
 				    oid_to_hex(oid1));
-			rewrite_here = (struct object_id *)oid;
+
+			/*
+			 * We cast here for two reasons:
+			 *
+			 *   - to flip the "char *" (for the path) to "unsigned
+			 *     char *" (for the hash stored after it)
+			 *
+			 *   - to discard the "const"; this is OK because we
+			 *     know it points into our non-const "buf"
+			 */
+			rewrite_here = (unsigned char *)(desc.entry.path +
+							 strlen(desc.entry.path) +
+							 1);
 			break;
 		}
 		update_tree_entry(&desc);
@@ -216,14 +227,16 @@ static int splice_tree(const struct object_id *oid1, const char *prefix,
 		die("entry %.*s not found in tree %s", toplen, prefix,
 		    oid_to_hex(oid1));
 	if (*subpath) {
-		status = splice_tree(rewrite_here, subpath, oid2, &subtree);
+		struct object_id tree_oid;
+		hashcpy(tree_oid.hash, rewrite_here);
+		status = splice_tree(&tree_oid, subpath, oid2, &subtree);
 		if (status)
 			return status;
 		rewrite_with = &subtree;
 	} else {
 		rewrite_with = oid2;
 	}
-	oidcpy(rewrite_here, rewrite_with);
+	hashcpy(rewrite_here, rewrite_with->hash);
 	status = write_object_file(buf, sz, tree_type, result);
 	free(buf);
 	return status;

notes.c

@@ -450,7 +450,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 
 		l = xcalloc(1, sizeof(*l));
 		oidcpy(&l->key_oid, &object_oid);
-		oidcpy(&l->val_oid, entry.oid);
+		oidcpy(&l->val_oid, &entry.oid);
 		if (note_tree_insert(t, node, n, l, type,
 				     combine_notes_concatenate))
 			die("Failed to load %s %s into notes tree "
@@ -481,7 +481,7 @@ handle_non_note:
 			}
 			strbuf_addstr(&non_note_path, entry.path);
 			add_non_note(t, strbuf_detach(&non_note_path, NULL),
-				     entry.mode, entry.oid->hash);
+				     entry.mode, entry.oid.hash);
 		}
 	}
 	free(buf);

packfile.c

@@ -2097,7 +2097,7 @@ static int add_promisor_object(const struct object_id *oid,
 			 */
 			return 0;
 		while (tree_entry_gently(&desc, &entry))
-			oidset_insert(set, entry.oid);
+			oidset_insert(set, &entry.oid);
 	} else if (obj->type == OBJ_COMMIT) {
 		struct commit *commit = (struct commit *) obj;
 		struct commit_list *parents = commit->parents;

revision.c

@@ -67,10 +67,10 @@ static void mark_tree_contents_uninteresting(struct repository *r,
 	while (tree_entry(&desc, &entry)) {
 		switch (object_type(entry.mode)) {
 		case OBJ_TREE:
-			mark_tree_uninteresting(r, lookup_tree(r, entry.oid));
+			mark_tree_uninteresting(r, lookup_tree(r, &entry.oid));
 			break;
 		case OBJ_BLOB:
-			mark_blob_uninteresting(lookup_blob(r, entry.oid));
+			mark_blob_uninteresting(lookup_blob(r, &entry.oid));
 			break;
 		default:
 			/* Subproject commit - not in this repository */

tree-diff.c

@@ -239,7 +239,7 @@ static struct combine_diff_path *emit_path(struct combine_diff_path *p,
 						DIFF_STATUS_ADDED;
 
 			if (tpi_valid) {
-				oid_i = tp[i].entry.oid;
+				oid_i = &tp[i].entry.oid;
 				mode_i = tp[i].entry.mode;
 			}
 			else {
@@ -280,7 +280,7 @@ static struct combine_diff_path *emit_path(struct combine_diff_path *p,
 			/* same rule as in emitthis */
 			int tpi_valid = tp && !(tp[i].entry.mode & S_IFXMIN_NEQ);
 
-			parents_oid[i] = tpi_valid ? tp[i].entry.oid : NULL;
+			parents_oid[i] = tpi_valid ? &tp[i].entry.oid : NULL;
 		}
 
 		strbuf_add(base, path, pathlen);
@@ -492,7 +492,7 @@ static struct combine_diff_path *ll_diff_tree_paths(
 						continue;
 
 					/* diff(t,pi) != ø */
-					if (!oideq(t.entry.oid, tp[i].entry.oid) ||
+					if (!oideq(&t.entry.oid, &tp[i].entry.oid) ||
 					    (t.entry.mode != tp[i].entry.mode))
 						continue;
 

tree-walk.c

@@ -48,7 +48,8 @@ static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned l
 	/* Initialize the descriptor entry */
 	desc->entry.path = path;
 	desc->entry.mode = canon_mode(mode);
-	desc->entry.oid  = (const struct object_id *)(path + len);
+	desc->entry.pathlen = len - 1;
+	hashcpy(desc->entry.oid.hash, (const unsigned char *)path + len);
 
 	return 0;
 }
@@ -107,7 +108,7 @@ static void entry_extract(struct tree_desc *t, struct name_entry *a)
 static int update_tree_entry_internal(struct tree_desc *desc, struct strbuf *err)
 {
 	const void *buf = desc->buffer;
-	const unsigned char *end = desc->entry.oid->hash + the_hash_algo->rawsz;
+	const unsigned char *end = (const unsigned char *)desc->entry.path + desc->entry.pathlen + 1 + the_hash_algo->rawsz;
 	unsigned long size = desc->size;
 	unsigned long len = end - (const unsigned char *)buf;
 
@@ -175,9 +176,11 @@ void setup_traverse_info(struct traverse_info *info, const char *base)
 		pathlen--;
 	info->pathlen = pathlen ? pathlen + 1 : 0;
 	info->name.path = base;
-	info->name.oid = (void *)(base + pathlen + 1);
+	info->name.pathlen = pathlen;
-	if (pathlen)
+	if (pathlen) {
+		hashcpy(info->name.oid.hash, (const unsigned char *)base + pathlen + 1);
 		info->prev = &dummy;
+	}
 }
 
 char *make_traverse_path(char *path, const struct traverse_info *info, const struct name_entry *n)
@@ -502,10 +505,10 @@ static int find_tree_entry(struct tree_desc *t, const char *name, struct object_
 	int namelen = strlen(name);
 	while (t->size) {
 		const char *entry;
-		const struct object_id *oid;
+		struct object_id oid;
 		int entrylen, cmp;
 
-		oid = tree_entry_extract(t, &entry, mode);
+		oidcpy(&oid, tree_entry_extract(t, &entry, mode));
 		entrylen = tree_entry_len(&t->entry);
 		update_tree_entry(t);
 		if (entrylen > namelen)
@@ -516,7 +519,7 @@ static int find_tree_entry(struct tree_desc *t, const char *name, struct object_
 		if (cmp < 0)
 			break;
 		if (entrylen == namelen) {
-			oidcpy(result, oid);
+			oidcpy(result, &oid);
 			return 0;
 		}
 		if (name[entrylen] != '/')
@@ -524,10 +527,10 @@ static int find_tree_entry(struct tree_desc *t, const char *name, struct object_
 		if (!S_ISDIR(*mode))
 			break;
 		if (++entrylen == namelen) {
-			oidcpy(result, oid);
+			oidcpy(result, &oid);
 			return 0;
 		}
-		return get_tree_entry(oid, name + entrylen, result, mode);
+		return get_tree_entry(&oid, name + entrylen, result, mode);
 	}
 	return -1;
 }

tree-walk.h

@@ -1,12 +1,12 @@
 #ifndef TREE_WALK_H
 #define TREE_WALK_H
 
-struct index_state;
+#include "cache.h"
-struct strbuf;
 
 struct name_entry {
-	const struct object_id *oid;
+	struct object_id oid;
 	const char *path;
+	int pathlen;
 	unsigned int mode;
 };
 
@@ -20,12 +20,12 @@ static inline const struct object_id *tree_entry_extract(struct tree_desc *desc,
 {
 	*pathp = desc->entry.path;
 	*modep = desc->entry.mode;
-	return desc->entry.oid;
+	return &desc->entry.oid;
 }
 
 static inline int tree_entry_len(const struct name_entry *ne)
 {
-	return (const char *)ne->oid - ne->path - 1;
+	return ne->pathlen;
 }
 
 /*

tree.c

@@ -86,7 +86,7 @@ static int read_tree_1(struct repository *r,
 				continue;
 		}
 
-		switch (fn(entry.oid, base,
+		switch (fn(&entry.oid, base,
 			   entry.path, entry.mode, stage, context)) {
 		case 0:
 			continue;
@@ -97,19 +97,19 @@ static int read_tree_1(struct repository *r,
 		}
 
 		if (S_ISDIR(entry.mode))
-			oidcpy(&oid, entry.oid);
+			oidcpy(&oid, &entry.oid);
 		else if (S_ISGITLINK(entry.mode)) {
 			struct commit *commit;
 
-			commit = lookup_commit(r, entry.oid);
+			commit = lookup_commit(r, &entry.oid);
 			if (!commit)
 				die("Commit %s in submodule path %s%s not found",
-				    oid_to_hex(entry.oid),
+				    oid_to_hex(&entry.oid),
 				    base->buf, entry.path);
 
 			if (parse_commit(commit))
 				die("Invalid commit %s in submodule path %s%s",
-				    oid_to_hex(entry.oid),
+				    oid_to_hex(&entry.oid),
 				    base->buf, entry.path);
 
 			oidcpy(&oid, get_commit_tree_oid(commit));

unpack-trees.c

@@ -679,7 +679,7 @@ static int switch_cache_bottom(struct traverse_info *info)
 
 static inline int are_same_oid(struct name_entry *name_j, struct name_entry *name_k)
 {
-	return name_j->oid && name_k->oid && oideq(name_j->oid, name_k->oid);
+	return !is_null_oid(&name_j->oid) && !is_null_oid(&name_k->oid) && oideq(&name_j->oid, &name_k->oid);
 }
 
 static int all_trees_same_as_cache_tree(int n, unsigned long dirmask,
@@ -857,7 +857,7 @@ static int traverse_trees_recursive(int n, unsigned long dirmask,
 		else {
 			const struct object_id *oid = NULL;
 			if (dirmask & 1)
-				oid = names[i].oid;
+				oid = &names[i].oid;
 			buf[nr_buf++] = fill_tree_descriptor(t + i, oid);
 		}
 	}
@@ -981,7 +981,7 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	ce->ce_mode = create_ce_mode(n->mode);
 	ce->ce_flags = create_ce_flags(stage);
 	ce->ce_namelen = len;
-	oidcpy(&ce->oid, n->oid);
+	oidcpy(&ce->oid, &n->oid);
 	make_traverse_path(ce->name, info, n);
 
 	return ce;

walker.c

@@ -50,13 +50,13 @@ static int process_tree(struct walker *walker, struct tree *tree)
 			continue;
 		if (S_ISDIR(entry.mode)) {
 			struct tree *tree = lookup_tree(the_repository,
-							entry.oid);
+							&entry.oid);
 			if (tree)
 				obj = &tree->object;
 		}
 		else {
 			struct blob *blob = lookup_blob(the_repository,
-							entry.oid);
+							&entry.oid);
 			if (blob)
 				obj = &blob->object;
 		}