Merge branch 'bc/hash-algo'

An infrastructure to define what hash function is used in Git is
introduced, and an effort to plumb that throughout various
codepaths has been started.

* bc/hash-algo:
  repository: fix a sparse 'using integer as NULL pointer' warning
  Switch empty tree and blob lookups to use hash abstraction
  Integrate hash algorithm support with repo setup
  Add structure representing hash algorithm
  setup: expose enumerated repo info

builtin/am.c

@@ -1433,7 +1433,7 @@ static void write_index_patch(const struct am_state *state)
 	if (!get_oid_tree("HEAD", &head))
 		tree = lookup_tree(&head);
 	else
-		tree = lookup_tree(&empty_tree_oid);
+		tree = lookup_tree(the_hash_algo->empty_tree);
 
 	fp = xfopen(am_path(state, "patch"), "w");
 	init_revisions(&rev_info, NULL);

builtin/checkout.c

@@ -514,7 +514,7 @@ static int merge_working_tree(const struct checkout_opts *opts,
 		}
 		tree = parse_tree_indirect(old->commit ?
 					   &old->commit->object.oid :
-					   &empty_tree_oid);
+					   the_hash_algo->empty_tree);
 		init_tree_desc(&trees[0], tree->buffer, tree->size);
 		tree = parse_tree_indirect(&new->commit->object.oid);
 		init_tree_desc(&trees[1], tree->buffer, tree->size);

builtin/diff.c

@@ -379,7 +379,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix)
 				add_head_to_pending(&rev);
 				if (!rev.pending.nr) {
 					struct tree *tree;
-					tree = lookup_tree(&empty_tree_oid);
+					tree = lookup_tree(the_hash_algo->empty_tree);
 					add_pending_object(&rev, &tree->object, "HEAD");
 				}
 				break;

builtin/pull.c

@@ -557,7 +557,7 @@ static int pull_into_void(const struct object_id *merge_head,
 	 * index/worktree changes that the user already made on the unborn
 	 * branch.
 	 */
-	if (checkout_fast_forward(&empty_tree_oid, merge_head, 0))
+	if (checkout_fast_forward(the_hash_algo->empty_tree, merge_head, 0))
 		return 1;
 
 	if (update_ref("initial pull", "HEAD", merge_head, curr_head, 0, UPDATE_REFS_DIE_ON_ERR))

cache.h

@@ -14,6 +14,7 @@
 #include "hash.h"
 #include "path.h"
 #include "sha1-array.h"
+#include "repository.h"
 
 #ifndef platform_SHA_CTX
 /*
@@ -77,6 +78,8 @@ struct object_id {
 	unsigned char hash[GIT_MAX_RAWSZ];
 };
 
+#define the_hash_algo the_repository->hash_algo
+
 #if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT)
 #define DTYPE(de)	((de)->d_type)
 #else
@@ -907,6 +910,7 @@ struct repository_format {
 	int version;
 	int precious_objects;
 	int is_bare;
+	int hash_algo;
 	char *work_tree;
 	struct string_list unknown_extensions;
 };
@@ -1039,22 +1043,22 @@ extern const struct object_id empty_blob_oid;
 
 static inline int is_empty_blob_sha1(const unsigned char *sha1)
 {
-	return !hashcmp(sha1, EMPTY_BLOB_SHA1_BIN);
+	return !hashcmp(sha1, the_hash_algo->empty_blob->hash);
 }
 
 static inline int is_empty_blob_oid(const struct object_id *oid)
 {
-	return !hashcmp(oid->hash, EMPTY_BLOB_SHA1_BIN);
+	return !oidcmp(oid, the_hash_algo->empty_blob);
 }
 
 static inline int is_empty_tree_sha1(const unsigned char *sha1)
 {
-	return !hashcmp(sha1, EMPTY_TREE_SHA1_BIN);
+	return !hashcmp(sha1, the_hash_algo->empty_tree->hash);
 }
 
 static inline int is_empty_tree_oid(const struct object_id *oid)
 {
-	return !hashcmp(oid->hash, EMPTY_TREE_SHA1_BIN);
+	return !oidcmp(oid, the_hash_algo->empty_tree);
 }
 
 /* set default permissions by passing mode arguments to open(2) */

diff-lib.c

@@ -218,7 +218,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 			} else if (revs->diffopt.ita_invisible_in_index &&
 				   ce_intent_to_add(ce)) {
 				diff_addremove(&revs->diffopt, '+', ce->ce_mode,
-					       &empty_tree_oid, 0,
+					       the_hash_algo->empty_tree, 0,
 					       ce->name, 0);
 				continue;
 			}

hash.h

@@ -1,6 +1,8 @@
 #ifndef HASH_H
 #define HASH_H
 
+#include "git-compat-util.h"
+
 #if defined(SHA1_PPC)
 #include "ppc/sha1.h"
 #elif defined(SHA1_APPLE)
@@ -13,4 +15,59 @@
 #include "block-sha1/sha1.h"
 #endif
 
+/*
+ * Note that these constants are suitable for indexing the hash_algos array and
+ * comparing against each other, but are otherwise arbitrary, so they should not
+ * be exposed to the user or serialized to disk.  To know whether a
+ * git_hash_algo struct points to some usable hash function, test the format_id
+ * field for being non-zero.  Use the name field for user-visible situations and
+ * the format_id field for fixed-length fields on disk.
+ */
+/* An unknown hash function. */
+#define GIT_HASH_UNKNOWN 0
+/* SHA-1 */
+#define GIT_HASH_SHA1 1
+/* Number of algorithms supported (including unknown). */
+#define GIT_HASH_NALGOS (GIT_HASH_SHA1 + 1)
+
+typedef void (*git_hash_init_fn)(void *ctx);
+typedef void (*git_hash_update_fn)(void *ctx, const void *in, size_t len);
+typedef void (*git_hash_final_fn)(unsigned char *hash, void *ctx);
+
+struct git_hash_algo {
+	/*
+	 * The name of the algorithm, as appears in the config file and in
+	 * messages.
+	 */
+	const char *name;
+
+	/* A four-byte version identifier, used in pack indices. */
+	uint32_t format_id;
+
+	/* The size of a hash context (e.g. git_SHA_CTX). */
+	size_t ctxsz;
+
+	/* The length of the hash in binary. */
+	size_t rawsz;
+
+	/* The length of the hash in hex characters. */
+	size_t hexsz;
+
+	/* The hash initialization function. */
+	git_hash_init_fn init_fn;
+
+	/* The hash update function. */
+	git_hash_update_fn update_fn;
+
+	/* The hash finalization function. */
+	git_hash_final_fn final_fn;
+
+	/* The OID of the empty tree. */
+	const struct object_id *empty_tree;
+
+	/* The OID of the empty blob. */
+	const struct object_id *empty_blob;
+};
+extern const struct git_hash_algo hash_algos[GIT_HASH_NALGOS];
+
 #endif

merge-recursive.c

@@ -2082,7 +2082,7 @@ int merge_recursive(struct merge_options *o,
 		/* if there is no common ancestor, use an empty tree */
 		struct tree *tree;
 
-		tree = lookup_tree(&empty_tree_oid);
+		tree = lookup_tree(the_hash_algo->empty_tree);
 		merged_common_ancestors = make_virtual_commit(tree, "ancestor");
 	}
 

notes-merge.c

@@ -595,7 +595,7 @@ int notes_merge(struct notes_merge_options *o,
 	bases = get_merge_bases(local, remote);
 	if (!bases) {
 		base_oid = &null_oid;
-		base_tree_oid = &empty_tree_oid;
+		base_tree_oid = the_hash_algo->empty_tree;
 		if (o->verbosity >= 4)
 			printf("No merge base found; doing history-less merge\n");
 	} else if (!bases->next) {

repository.c

@@ -5,7 +5,7 @@
 
 /* The main repository */
 static struct repository the_repo = {
-	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, &the_index, 0, 0
+	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, &the_index, NULL, 0, 0
 };
 struct repository *the_repository = &the_repo;
 
@@ -64,6 +64,11 @@ void repo_set_gitdir(struct repository *repo, const char *path)
 	free(old_gitdir);
 }
 
+void repo_set_hash_algo(struct repository *repo, int hash_algo)
+{
+	repo->hash_algo = &hash_algos[hash_algo];
+}
+
 /*
  * Attempt to resolve and set the provided 'gitdir' for repository 'repo'.
  * Return 0 upon success and a non-zero value upon failure.
@@ -136,6 +141,8 @@ int repo_init(struct repository *repo, const char *gitdir, const char *worktree)
 	if (read_and_verify_repository_format(&format, repo->commondir))
 		goto error;
 
+	repo_set_hash_algo(repo, format.hash_algo);
+
 	if (worktree)
 		repo_set_worktree(repo, worktree);
 

repository.h

@@ -4,6 +4,7 @@
 struct config_set;
 struct index_state;
 struct submodule_cache;
+struct git_hash_algo;
 
 struct repository {
 	/* Environment */
@@ -67,6 +68,9 @@ struct repository {
 	 */
 	struct index_state *index;
 
+	/* Repository's current hash algorithm, as serialized on disk. */
+	const struct git_hash_algo *hash_algo;
+
 	/* Configurations */
 	/*
 	 * Bit used during initialization to indicate if repository state (like
@@ -86,6 +90,7 @@ extern struct repository *the_repository;
 
 extern void repo_set_gitdir(struct repository *repo, const char *path);
 extern void repo_set_worktree(struct repository *repo, const char *path);
+extern void repo_set_hash_algo(struct repository *repo, int algo);
 extern int repo_init(struct repository *repo, const char *gitdir, const char *worktree);
 extern int repo_submodule_init(struct repository *submodule,
 			       struct repository *superproject,

sequencer.c

@@ -347,7 +347,7 @@ static int read_oneliner(struct strbuf *buf,
 
 static struct tree *empty_tree(void)
 {
-	return lookup_tree(&empty_tree_oid);
+	return lookup_tree(the_hash_algo->empty_tree);
 }
 
 static int error_dirty_index(struct replay_opts *opts)
@@ -706,7 +706,7 @@ static int is_original_commit_empty(struct commit *commit)
 				oid_to_hex(&parent->object.oid));
 		ptree_oid = &parent->tree->object.oid;
 	} else {
-		ptree_oid = &empty_tree_oid; /* commit is root */
+		ptree_oid = the_hash_algo->empty_tree; /* commit is root */
 	}
 
 	return !oidcmp(ptree_oid, &commit->tree->object.oid);
@@ -959,7 +959,7 @@ static int do_pick_commit(enum todo_command command, struct commit *commit,
 	} else {
 		unborn = get_oid("HEAD", &head);
 		if (unborn)
-			oidcpy(&head, &empty_tree_oid);
+			oidcpy(&head, the_hash_algo->empty_tree);
 		if (index_differs_from(unborn ? EMPTY_TREE_SHA1_HEX : "HEAD",
 				       NULL, 0))
 			return error_dirty_index(opts);