Merge branch 'bc/hash-transition-16'

Conversion from unsigned char[20] to struct object_id continues.

* bc/hash-transition-16: (35 commits)
  gitweb: make hash size independent
  Git.pm: make hash size independent
  read-cache: read data in a hash-independent way
  dir: make untracked cache extension hash size independent
  builtin/difftool: use parse_oid_hex
  refspec: make hash size independent
  archive: convert struct archiver_args to object_id
  builtin/get-tar-commit-id: make hash size independent
  get-tar-commit-id: parse comment record
  hash: add a function to lookup hash algorithm by length
  remote-curl: make hash size independent
  http: replace sha1_to_hex
  http: compute hash of downloaded objects using the_hash_algo
  http: replace hard-coded constant with the_hash_algo
  http-walker: replace sha1_to_hex
  http-push: remove remaining uses of sha1_to_hex
  http-backend: allow 64-character hex names
  http-push: convert to use the_hash_algo
  builtin/pull: make hash-size independent
  builtin/am: make hash size independent
  ...

archive-tar.c

@@ -326,14 +326,15 @@ static int write_tar_entry(struct archiver_args *args,
 
 static void write_global_extended_header(struct archiver_args *args)
 {
-	const unsigned char *sha1 = args->commit_sha1;
+	const struct object_id *oid = args->commit_oid;
 	struct strbuf ext_header = STRBUF_INIT;
 	struct ustar_header header;
 	unsigned int mode;
 
-	if (sha1)
+	if (oid)
 		strbuf_append_ext_header(&ext_header, "comment",
-					 sha1_to_hex(sha1), 40);
+					 oid_to_hex(oid),
+					 the_hash_algo->hexsz);
 	if (args->time > USTAR_MAX_MTIME) {
 		strbuf_append_ext_header_uint(&ext_header, "mtime",
 					      args->time);

archive-zip.c

@@ -577,7 +577,7 @@ static void write_zip64_trailer(void)
 	write_or_die(1, &locator64, ZIP64_DIR_TRAILER_LOCATOR_SIZE);
 }
 
-static void write_zip_trailer(const unsigned char *sha1)
+static void write_zip_trailer(const struct object_id *oid)
 {
 	struct zip_dir_trailer trailer;
 	int clamped = 0;
@@ -590,14 +590,14 @@ static void write_zip_trailer(const unsigned char *sha1)
 	copy_le16_clamp(trailer.entries, zip_dir_entries, &clamped);
 	copy_le32(trailer.size, zip_dir.len);
 	copy_le32_clamp(trailer.offset, zip_offset, &clamped);
-	copy_le16(trailer.comment_length, sha1 ? GIT_SHA1_HEXSZ : 0);
+	copy_le16(trailer.comment_length, oid ? the_hash_algo->hexsz : 0);
 
 	write_or_die(1, zip_dir.buf, zip_dir.len);
 	if (clamped)
 		write_zip64_trailer();
 	write_or_die(1, &trailer, ZIP_DIR_TRAILER_SIZE);
-	if (sha1)
+	if (oid)
-		write_or_die(1, sha1_to_hex(sha1), GIT_SHA1_HEXSZ);
+		write_or_die(1, oid_to_hex(oid), the_hash_algo->hexsz);
 }
 
 static void dos_time(timestamp_t *timestamp, int *dos_date, int *dos_time)
@@ -635,7 +635,7 @@ static int write_zip_archive(const struct archiver *ar,
 
 	err = write_archive_entries(args, write_zip_entry);
 	if (!err)
-		write_zip_trailer(args->commit_sha1);
+		write_zip_trailer(args->commit_oid);
 
 	strbuf_release(&zip_dir);
 

archive.c

@@ -380,7 +380,7 @@ static void parse_treeish_arg(const char **argv,
 		int remote)
 {
 	const char *name = argv[0];
-	const unsigned char *commit_sha1;
+	const struct object_id *commit_oid;
 	time_t archive_time;
 	struct tree *tree;
 	const struct commit *commit;
@@ -402,10 +402,10 @@ static void parse_treeish_arg(const char **argv,
 
 	commit = lookup_commit_reference_gently(ar_args->repo, &oid, 1);
 	if (commit) {
-		commit_sha1 = commit->object.oid.hash;
+		commit_oid = &commit->object.oid;
 		archive_time = commit->date;
 	} else {
-		commit_sha1 = NULL;
+		commit_oid = NULL;
 		archive_time = time(NULL);
 	}
 
@@ -426,7 +426,7 @@ static void parse_treeish_arg(const char **argv,
 		tree = parse_tree_indirect(&tree_oid);
 	}
 	ar_args->tree = tree;
-	ar_args->commit_sha1 = commit_sha1;
+	ar_args->commit_oid = commit_oid;
 	ar_args->commit = commit;
 	ar_args->time = archive_time;
 }

archive.h

@@ -11,7 +11,7 @@ struct archiver_args {
 	const char *base;
 	size_t baselen;
 	struct tree *tree;
-	const unsigned char *commit_sha1;
+	const struct object_id *commit_oid;
 	const struct commit *commit;
 	timestamp_t time;
 	struct pathspec pathspec;

builtin/am.c

@@ -486,23 +486,24 @@ static int copy_notes_for_rebase(const struct am_state *state)
 
 	while (!strbuf_getline_lf(&sb, fp)) {
 		struct object_id from_obj, to_obj;
+		const char *p;
 
-		if (sb.len != GIT_SHA1_HEXSZ * 2 + 1) {
+		if (sb.len != the_hash_algo->hexsz * 2 + 1) {
 			ret = error(invalid_line, sb.buf);
 			goto finish;
 		}
 
-		if (get_oid_hex(sb.buf, &from_obj)) {
+		if (parse_oid_hex(sb.buf, &from_obj, &p)) {
 			ret = error(invalid_line, sb.buf);
 			goto finish;
 		}
 
-		if (sb.buf[GIT_SHA1_HEXSZ] != ' ') {
+		if (*p != ' ') {
 			ret = error(invalid_line, sb.buf);
 			goto finish;
 		}
 
-		if (get_oid_hex(sb.buf + GIT_SHA1_HEXSZ + 1, &to_obj)) {
+		if (get_oid_hex(p + 1, &to_obj)) {
 			ret = error(invalid_line, sb.buf);
 			goto finish;
 		}

builtin/difftool.c

@@ -65,14 +65,12 @@ static int parse_index_info(char *p, int *mode1, int *mode2,
 	*mode2 = (int)strtol(p + 1, &p, 8);
 	if (*p != ' ')
 		return error("expected ' ', got '%c'", *p);
-	if (get_oid_hex(++p, oid1))
+	if (parse_oid_hex(++p, oid1, (const char **)&p))
-		return error("expected object ID, got '%s'", p + 1);
+		return error("expected object ID, got '%s'", p);
-	p += GIT_SHA1_HEXSZ;
 	if (*p != ' ')
 		return error("expected ' ', got '%c'", *p);
-	if (get_oid_hex(++p, oid2))
+	if (parse_oid_hex(++p, oid2, (const char **)&p))
-		return error("expected object ID, got '%s'", p + 1);
+		return error("expected object ID, got '%s'", p);
-	p += GIT_SHA1_HEXSZ;
 	if (*p != ' ')
 		return error("expected ' ', got '%c'", *p);
 	*status = *++p;

builtin/get-tar-commit-id.c

@@ -21,6 +21,8 @@ int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix)
 	char *content = buffer + RECORDSIZE;
 	const char *comment;
 	ssize_t n;
+	long len;
+	char *end;
 
 	if (argc != 1)
 		usage(builtin_get_tar_commit_id_usage);
@@ -32,10 +34,18 @@ int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix)
 		die_errno("git get-tar-commit-id: EOF before reading tar header");
 	if (header->typeflag[0] != 'g')
 		return 1;
-	if (!skip_prefix(content, "52 comment=", &comment))
+
+	len = strtol(content, &end, 10);
+	if (errno == ERANGE || end == content || len < 0)
+		return 1;
+	if (!skip_prefix(end, " comment=", &comment))
+		return 1;
+	len -= comment - content;
+	if (len < 1 || !(len % 2) ||
+	    hash_algo_by_length((len - 1) / 2) == GIT_HASH_UNKNOWN)
 		return 1;
 
-	if (write_in_full(1, comment, 41) < 0)
+	if (write_in_full(1, comment, len) < 0)
 		die_errno("git get-tar-commit-id: write error");
 
 	return 0;

builtin/name-rev.c

@@ -361,23 +361,25 @@ static char const * const name_rev_usage[] = {
 static void name_rev_line(char *p, struct name_ref_data *data)
 {
 	struct strbuf buf = STRBUF_INIT;
-	int forty = 0;
+	int counter = 0;
 	char *p_start;
+	const unsigned hexsz = the_hash_algo->hexsz;
+
 	for (p_start = p; *p; p++) {
 #define ishex(x) (isdigit((x)) || ((x) >= 'a' && (x) <= 'f'))
 		if (!ishex(*p))
-			forty = 0;
+			counter = 0;
-		else if (++forty == GIT_SHA1_HEXSZ &&
+		else if (++counter == hexsz &&
 			 !ishex(*(p+1))) {
 			struct object_id oid;
 			const char *name = NULL;
 			char c = *(p+1);
 			int p_len = p - p_start + 1;
 
-			forty = 0;
+			counter = 0;
 
 			*(p+1) = 0;
-			if (!get_oid(p - (GIT_SHA1_HEXSZ - 1), &oid)) {
+			if (!get_oid(p - (hexsz - 1), &oid)) {
 				struct object *o =
 					lookup_object(the_repository,
 						      oid.hash);
@@ -390,7 +392,7 @@ static void name_rev_line(char *p, struct name_ref_data *data)
 				continue;
 
 			if (data->name_only)
-				printf("%.*s%s", p_len - GIT_SHA1_HEXSZ, p_start, name);
+				printf("%.*s%s", p_len - hexsz, p_start, name);
 			else
 				printf("%.*s (%s)", p_len, p_start, name);
 			p_start = p + 1;

builtin/pack-objects.c

@@ -1487,6 +1487,7 @@ static int can_reuse_delta(const unsigned char *base_sha1,
 			   struct object_entry **base_out)
 {
 	struct object_entry *base;
+	struct object_id base_oid;
 
 	if (!base_sha1)
 		return 0;
@@ -1508,10 +1509,9 @@ static int can_reuse_delta(const unsigned char *base_sha1,
 	 * even if it was buried too deep in history to make it into the
 	 * packing list.
 	 */
-	if (thin && bitmap_has_sha1_in_uninteresting(bitmap_git, base_sha1)) {
+	oidread(&base_oid, base_sha1);
+	if (thin && bitmap_has_oid_in_uninteresting(bitmap_git, &base_oid)) {
 		if (use_delta_islands) {
-			struct object_id base_oid;
-			hashcpy(base_oid.hash, base_sha1);
 			if (!in_same_island(&delta->idx.oid, &base_oid))
 				return 0;
 		}

builtin/pack-redundant.c

@@ -641,7 +641,7 @@ int cmd_pack_redundant(int argc, const char **argv, const char *prefix)
 	pl = red = pack_list_difference(local_packs, min);
 	while (pl) {
 		printf("%s\n%s\n",
-		       sha1_pack_index_name(pl->pack->sha1),
+		       sha1_pack_index_name(pl->pack->hash),
 		       pl->pack->pack_name);
 		pl = pl->next;
 	}

builtin/pull.c

@@ -369,9 +369,10 @@ static void get_merge_heads(struct oid_array *merge_heads)
 
 	fp = xfopen(filename, "r");
 	while (strbuf_getline_lf(&sb, fp) != EOF) {
-		if (get_oid_hex(sb.buf, &oid))
+		const char *p;
-			continue;  /* invalid line: does not start with SHA1 */
+		if (parse_oid_hex(sb.buf, &oid, &p))
-		if (starts_with(sb.buf + GIT_SHA1_HEXSZ, "\tnot-for-merge\t"))
+			continue;  /* invalid line: does not start with object ID */
+		if (starts_with(p, "\tnot-for-merge\t"))
 			continue;  /* ref is not-for-merge */
 		oid_array_append(merge_heads, &oid);
 	}
@@ -760,7 +761,7 @@ static int get_rebase_fork_point(struct object_id *fork_point, const char *repo,
 	cp.no_stderr = 1;
 	cp.git_cmd = 1;
 
-	ret = capture_command(&cp, &sb, GIT_SHA1_HEXSZ);
+	ret = capture_command(&cp, &sb, GIT_MAX_HEXSZ);
 	if (ret)
 		goto cleanup;
 
@@ -805,7 +806,7 @@ static int get_octopus_merge_base(struct object_id *merge_base,
 }
 
 /**
- * Given the current HEAD SHA1, the merge head returned from git-fetch and the
+ * Given the current HEAD oid, the merge head returned from git-fetch and the
  * fork point calculated by get_rebase_fork_point(), runs git-rebase with the
  * appropriate arguments and returns its exit status.
  */

dir.c

@@ -2544,13 +2544,9 @@ struct ondisk_untracked_cache {
 	struct stat_data info_exclude_stat;
 	struct stat_data excludes_file_stat;
 	uint32_t dir_flags;
-	unsigned char info_exclude_sha1[20];
-	unsigned char excludes_file_sha1[20];
-	char exclude_per_dir[FLEX_ARRAY];
 };
 
 #define ouc_offset(x) offsetof(struct ondisk_untracked_cache, x)
-#define ouc_size(len) (ouc_offset(exclude_per_dir) + len + 1)
 
 struct write_data {
 	int index;	   /* number of written untracked_cache_dir */
@@ -2633,20 +2629,21 @@ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untra
 	struct write_data wd;
 	unsigned char varbuf[16];
 	int varint_len;
-	size_t len = strlen(untracked->exclude_per_dir);
+	const unsigned hashsz = the_hash_algo->rawsz;
 
-	FLEX_ALLOC_MEM(ouc, exclude_per_dir, untracked->exclude_per_dir, len);
+	ouc = xcalloc(1, sizeof(*ouc));
 	stat_data_to_disk(&ouc->info_exclude_stat, &untracked->ss_info_exclude.stat);
 	stat_data_to_disk(&ouc->excludes_file_stat, &untracked->ss_excludes_file.stat);
-	hashcpy(ouc->info_exclude_sha1, untracked->ss_info_exclude.oid.hash);
-	hashcpy(ouc->excludes_file_sha1, untracked->ss_excludes_file.oid.hash);
 	ouc->dir_flags = htonl(untracked->dir_flags);
 
 	varint_len = encode_varint(untracked->ident.len, varbuf);
 	strbuf_add(out, varbuf, varint_len);
 	strbuf_addbuf(out, &untracked->ident);
 
-	strbuf_add(out, ouc, ouc_size(len));
+	strbuf_add(out, ouc, sizeof(*ouc));
+	strbuf_add(out, untracked->ss_info_exclude.oid.hash, hashsz);
+	strbuf_add(out, untracked->ss_excludes_file.oid.hash, hashsz);
+	strbuf_add(out, untracked->exclude_per_dir, strlen(untracked->exclude_per_dir) + 1);
 	FREE_AND_NULL(ouc);
 
 	if (!untracked->root) {
@@ -2833,6 +2830,9 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	int ident_len;
 	ssize_t len;
 	const char *exclude_per_dir;
+	const unsigned hashsz = the_hash_algo->rawsz;
+	const unsigned offset = sizeof(struct ondisk_untracked_cache);
+	const unsigned exclude_per_dir_offset = offset + 2 * hashsz;
 
 	if (sz <= 1 || end[-1] != '\0')
 		return NULL;
@@ -2844,7 +2844,7 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	ident = (const char *)next;
 	next += ident_len;
 
-	if (next + ouc_size(0) > end)
+	if (next + exclude_per_dir_offset + 1 > end)
 		return NULL;
 
 	uc = xcalloc(1, sizeof(*uc));
@@ -2852,15 +2852,15 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	strbuf_add(&uc->ident, ident, ident_len);
 	load_oid_stat(&uc->ss_info_exclude,
 		      next + ouc_offset(info_exclude_stat),
-		      next + ouc_offset(info_exclude_sha1));
+		      next + offset);
 	load_oid_stat(&uc->ss_excludes_file,
 		      next + ouc_offset(excludes_file_stat),
-		      next + ouc_offset(excludes_file_sha1));
+		      next + offset + hashsz);
 	uc->dir_flags = get_be32(next + ouc_offset(dir_flags));
-	exclude_per_dir = (const char *)next + ouc_offset(exclude_per_dir);
+	exclude_per_dir = (const char *)next + exclude_per_dir_offset;
 	uc->exclude_per_dir = xstrdup(exclude_per_dir);
 	/* NUL after exclude_per_dir is covered by sizeof(*ouc) */
-	next += ouc_size(strlen(exclude_per_dir));
+	next += exclude_per_dir_offset + strlen(exclude_per_dir) + 1;
 	if (next >= end)
 		goto done2;
 

fast-import.c

@@ -29,6 +29,13 @@
  */
 #define NO_DELTA S_ISUID
 
+/*
+ * The amount of additional space required in order to write an object into the
+ * current pack. This is the hash lengths at the end of the pack, plus the
+ * length of one object ID.
+ */
+#define PACK_SIZE_THRESHOLD (the_hash_algo->rawsz * 3)
+
 struct object_entry {
 	struct pack_idx_entry idx;
 	struct object_entry *next;
@@ -742,7 +749,8 @@ static const char *create_index(void)
 	if (c != last)
 		die("internal consistency error creating the index");
 
-	tmpfile = write_idx_file(NULL, idx, object_count, &pack_idx_opts, pack_data->sha1);
+	tmpfile = write_idx_file(NULL, idx, object_count, &pack_idx_opts,
+				 pack_data->hash);
 	free(idx);
 	return tmpfile;
 }
@@ -753,7 +761,7 @@ static char *keep_pack(const char *curr_index_name)
 	struct strbuf name = STRBUF_INIT;
 	int keep_fd;
 
-	odb_pack_name(&name, pack_data->sha1, "keep");
+	odb_pack_name(&name, pack_data->hash, "keep");
 	keep_fd = odb_pack_keep(name.buf);
 	if (keep_fd < 0)
 		die_errno("cannot create keep file");
@@ -761,11 +769,11 @@ static char *keep_pack(const char *curr_index_name)
 	if (close(keep_fd))
 		die_errno("failed to write keep file");
 
-	odb_pack_name(&name, pack_data->sha1, "pack");
+	odb_pack_name(&name, pack_data->hash, "pack");
 	if (finalize_object_file(pack_data->pack_name, name.buf))
 		die("cannot store pack file");
 
-	odb_pack_name(&name, pack_data->sha1, "idx");
+	odb_pack_name(&name, pack_data->hash, "idx");
 	if (finalize_object_file(curr_index_name, name.buf))
 		die("cannot store index file");
 	free((void *)curr_index_name);
@@ -779,7 +787,7 @@ static void unkeep_all_packs(void)
 
 	for (k = 0; k < pack_id; k++) {
 		struct packed_git *p = all_packs[k];
-		odb_pack_name(&name, p->sha1, "keep");
+		odb_pack_name(&name, p->hash, "keep");
 		unlink_or_warn(name.buf);
 	}
 	strbuf_release(&name);
@@ -821,9 +829,9 @@ static void end_packfile(void)
 
 		close_pack_windows(pack_data);
 		finalize_hashfile(pack_file, cur_pack_oid.hash, 0);
-		fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1,
+		fixup_pack_header_footer(pack_data->pack_fd, pack_data->hash,
-				    pack_data->pack_name, object_count,
+					 pack_data->pack_name, object_count,
-				    cur_pack_oid.hash, pack_size);
+					 cur_pack_oid.hash, pack_size);
 
 		if (object_count <= unpack_limit) {
 			if (!loosen_small_pack(pack_data)) {
@@ -948,8 +956,9 @@ static int store_object(
 	git_deflate_end(&s);
 
 	/* Determine if we should auto-checkpoint. */
-	if ((max_packsize && (pack_size + 60 + s.total_out) > max_packsize)
+	if ((max_packsize
-		|| (pack_size + 60 + s.total_out) < pack_size) {
+		&& (pack_size + PACK_SIZE_THRESHOLD + s.total_out) > max_packsize)
+		|| (pack_size + PACK_SIZE_THRESHOLD + s.total_out) < pack_size) {
 
 		/* This new object needs to *not* have the current pack_id. */
 		e->pack_id = pack_id + 1;
@@ -1044,8 +1053,9 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
 	int status = Z_OK;
 
 	/* Determine if we should auto-checkpoint. */
-	if ((max_packsize && (pack_size + 60 + len) > max_packsize)
+	if ((max_packsize
-		|| (pack_size + 60 + len) < pack_size)
+		&& (pack_size + PACK_SIZE_THRESHOLD + len) > max_packsize)
+		|| (pack_size + PACK_SIZE_THRESHOLD + len) < pack_size)
 		cycle_packfile();
 
 	hashfile_checkpoint(pack_file, &checkpoint);
@@ -1240,7 +1250,7 @@ static void load_tree(struct tree_entry *root)
 		c += e->name->str_len + 1;
 		hashcpy(e->versions[0].oid.hash, (unsigned char *)c);
 		hashcpy(e->versions[1].oid.hash, (unsigned char *)c);
-		c += GIT_SHA1_RAWSZ;
+		c += the_hash_algo->rawsz;
 	}
 	free(buf);
 }
@@ -1287,7 +1297,7 @@ static void mktree(struct tree_content *t, int v, struct strbuf *b)
 		strbuf_addf(b, "%o %s%c",
 			(unsigned int)(e->versions[v].mode & ~NO_DELTA),
 			e->name->str_dat, '\0');
-		strbuf_add(b, e->versions[v].oid.hash, GIT_SHA1_RAWSZ);
+		strbuf_add(b, e->versions[v].oid.hash, the_hash_algo->rawsz);
 	}
 }
 
@@ -2036,7 +2046,9 @@ static uintmax_t do_change_note_fanout(
 	unsigned int i, tmp_hex_oid_len, tmp_fullpath_len;
 	uintmax_t num_notes = 0;
 	struct object_id oid;
-	char realpath[60];
+	/* hex oid + '/' between each pair of hex digits + NUL */
+	char realpath[GIT_MAX_HEXSZ + ((GIT_MAX_HEXSZ / 2) - 1) + 1];
+	const unsigned hexsz = the_hash_algo->hexsz;
 
 	if (!root->tree)
 		load_tree(root);
@@ -2056,7 +2068,7 @@ static uintmax_t do_change_note_fanout(
 		 * of 2 chars.
 		 */
 		if (!e->versions[1].mode ||
-		    tmp_hex_oid_len > GIT_SHA1_HEXSZ ||
+		    tmp_hex_oid_len > hexsz ||
 		    e->name->str_len % 2)
 			continue;
 
@@ -2070,7 +2082,7 @@ static uintmax_t do_change_note_fanout(
 		tmp_fullpath_len += e->name->str_len;
 		fullpath[tmp_fullpath_len] = '\0';
 
-		if (tmp_hex_oid_len == GIT_SHA1_HEXSZ && !get_oid_hex(hex_oid, &oid)) {
+		if (tmp_hex_oid_len == hexsz && !get_oid_hex(hex_oid, &oid)) {
 			/* This is a note entry */
 			if (fanout == 0xff) {
 				/* Counting mode, no rename */
@@ -2348,7 +2360,7 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa
 	struct object_entry *oe;
 	struct branch *s;
 	struct object_id oid, commit_oid;
-	char path[60];
+	char path[GIT_MAX_RAWSZ * 3];
 	uint16_t inline_data = 0;
 	unsigned char new_fanout;
 
@@ -2401,7 +2413,7 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa
 		char *buf = read_object_with_reference(&commit_oid,
 						       commit_type, &size,
 						       &commit_oid);
-		if (!buf || size < 46)
+		if (!buf || size < the_hash_algo->hexsz + 6)
 			die("Not a valid commit: %s", p);
 		free(buf);
 	} else
@@ -2452,7 +2464,7 @@ static void file_change_deleteall(struct branch *b)
 
 static void parse_from_commit(struct branch *b, char *buf, unsigned long size)
 {
-	if (!buf || size < GIT_SHA1_HEXSZ + 6)
+	if (!buf || size < the_hash_algo->hexsz + 6)
 		die("Not a valid commit: %s", oid_to_hex(&b->oid));
 	if (memcmp("tree ", buf, 5)
 		|| get_oid_hex(buf + 5, &b->branch_tree.versions[1].oid))
@@ -2551,7 +2563,7 @@ static struct hash_list *parse_merge(unsigned int *count)
 			char *buf = read_object_with_reference(&n->oid,
 							       commit_type,
 							       &size, &n->oid);
-			if (!buf || size < 46)
+			if (!buf || size < the_hash_algo->hexsz + 6)
 				die("Not a valid commit: %s", from);
 			free(buf);
 		} else
@@ -2840,7 +2852,7 @@ static void parse_get_mark(const char *p)
 		die("Unknown mark: %s", command_buf.buf);
 
 	xsnprintf(output, sizeof(output), "%s\n", oid_to_hex(&oe->idx.oid));
-	cat_blob_write(output, GIT_SHA1_HEXSZ + 1);
+	cat_blob_write(output, the_hash_algo->hexsz + 1);
 }
 
 static void parse_cat_blob(const char *p)
@@ -2870,6 +2882,8 @@ static struct object_entry *dereference(struct object_entry *oe,
 {
 	unsigned long size;
 	char *buf = NULL;
+	const unsigned hexsz = the_hash_algo->hexsz;
+
 	if (!oe) {
 		enum object_type type = oid_object_info(the_repository, oid,
 							NULL);
@@ -2903,12 +2917,12 @@ static struct object_entry *dereference(struct object_entry *oe,
 	/* Peel one layer. */
 	switch (oe->type) {
 	case OBJ_TAG:
-		if (size < GIT_SHA1_HEXSZ + strlen("object ") ||
+		if (size < hexsz + strlen("object ") ||
 		    get_oid_hex(buf + strlen("object "), oid))
 			die("Invalid SHA1 in tag: %s", command_buf.buf);
 		break;
 	case OBJ_COMMIT:
-		if (size < GIT_SHA1_HEXSZ + strlen("tree ") ||
+		if (size < hexsz + strlen("tree ") ||
 		    get_oid_hex(buf + strlen("tree "), oid))
 			die("Invalid SHA1 in commit: %s", command_buf.buf);
 	}
@@ -2940,7 +2954,7 @@ static struct object_entry *parse_treeish_dataref(const char **p)
 	return e;
 }
 
-static void print_ls(int mode, const unsigned char *sha1, const char *path)
+static void print_ls(int mode, const unsigned char *hash, const char *path)
 {
 	static struct strbuf line = STRBUF_INIT;
 
@@ -2960,7 +2974,7 @@ static void print_ls(int mode, const unsigned char *sha1, const char *path)
 		/* mode SP type SP object_name TAB path LF */
 		strbuf_reset(&line);
 		strbuf_addf(&line, "%06o %s %s\t",
-				mode & ~NO_DELTA, type, sha1_to_hex(sha1));
+				mode & ~NO_DELTA, type, hash_to_hex(hash));
 		quote_c_style(path, &line, NULL, 0);
 		strbuf_addch(&line, '\n');
 	}

gitweb/gitweb.perl

@@ -788,6 +788,38 @@ sub check_loadavg {
 # ======================================================================
 # input validation and dispatch
 
+# Various hash size-related values.
+my $sha1_len = 40;
+my $sha256_extra_len = 24;
+my $sha256_len = $sha1_len + $sha256_extra_len;
+
+# A regex matching $len hex characters. $len may be a range (e.g. 7,64).
+sub oid_nlen_regex {
+	my $len = shift;
+	my $hchr = qr/[0-9a-fA-F]/;
+	return qr/(?:(?:$hchr){$len})/;
+}
+
+# A regex matching two sets of $nlen hex characters, prefixed by the literal
+# string $prefix and with the literal string $infix between them.
+sub oid_nlen_prefix_infix_regex {
+	my $nlen = shift;
+	my $prefix = shift;
+	my $infix = shift;
+
+	my $rx = oid_nlen_regex($nlen);
+
+	return qr/^\Q$prefix\E$rx\Q$infix\E$rx$/;
+}
+
+# A regex matching a valid object ID.
+our $oid_regex;
+{
+	my $x = oid_nlen_regex($sha1_len);
+	my $y = oid_nlen_regex($sha256_extra_len);
+	$oid_regex = qr/(?:$x(?:$y)?)/;
+}
+
 # input parameters can be collected from a variety of sources (presently, CGI
 # and PATH_INFO), so we define an %input_params hash that collects them all
 # together during validation: this allows subsequent uses (e.g. href()) to be
@@ -1516,7 +1548,7 @@ sub is_valid_refname {
 
 	return undef unless defined $input;
 	# textual hashes are O.K.
-	if ($input =~ m/^[0-9a-fA-F]{40}$/) {
+	if ($input =~ m/^$oid_regex$/) {
 		return 1;
 	}
 	# it must be correct pathname
@@ -2028,6 +2060,9 @@ sub file_type_long {
 sub format_log_line_html {
 	my $line = shift;
 
+	# Potentially abbreviated OID.
+	my $regex = oid_nlen_regex("7,64");
+
 	$line = esc_html($line, -nbsp=>1);
 	$line =~ s{
         \b
@@ -2037,10 +2072,10 @@ sub format_log_line_html {
             (?<!-) # see strbuf_check_tag_ref(). Tags can't start with -
             [A-Za-z0-9.-]+
             (?!\.) # refs can't end with ".", see check_refname_format()
-            -g[0-9a-fA-F]{7,40}
+            -g$regex
             |
             # Just a normal looking Git SHA1
-            [0-9a-fA-F]{7,40}
+	    $regex
         )
         \b
     }{
@@ -2286,7 +2321,8 @@ sub format_extended_diff_header_line {
 		         ')</span>';
 	}
 	# match <hash>
-	if ($line =~ m/^index [0-9a-fA-F]{40},[0-9a-fA-F]{40}/) {
+	if ($line =~ oid_nlen_prefix_infix_regex($sha1_len, "index ", ",") |
+	    $line =~ oid_nlen_prefix_infix_regex($sha256_len, "index ", ",")) {
 		# can match only for combined diff
 		$line = 'index ';
 		for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) {
@@ -2308,7 +2344,8 @@ sub format_extended_diff_header_line {
 			$line .= '0' x 7;
 		}
 
-	} elsif ($line =~ m/^index [0-9a-fA-F]{40}..[0-9a-fA-F]{40}/) {
+	} elsif ($line =~ oid_nlen_prefix_infix_regex($sha1_len, "index ", "..") |
+		 $line =~ oid_nlen_prefix_infix_regex($sha256_len, "index ", "..")) {
 		# can match only for ordinary diff
 		my ($from_link, $to_link);
 		if ($from->{'href'}) {
@@ -2834,7 +2871,7 @@ sub git_get_hash_by_path {
 	}
 
 	#'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa	panic.c'
-	$line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/;
+	$line =~ m/^([0-9]+) (.+) ($oid_regex)\t/;
 	if (defined $type && $type ne $2) {
 		# type doesn't match
 		return undef;
@@ -3333,7 +3370,7 @@ sub git_get_references {
 
 	while (my $line = <$fd>) {
 		chomp $line;
-		if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) {
+		if ($line =~ m!^($oid_regex)\srefs/($type.*)$!) {
 			if (defined $refs{$1}) {
 				push @{$refs{$1}}, $2;
 			} else {
@@ -3407,7 +3444,7 @@ sub parse_tag {
 	$tag{'id'} = $tag_id;
 	while (my $line = <$fd>) {
 		chomp $line;
-		if ($line =~ m/^object ([0-9a-fA-F]{40})$/) {
+		if ($line =~ m/^object ($oid_regex)$/) {
 			$tag{'object'} = $1;
 		} elsif ($line =~ m/^type (.+)$/) {
 			$tag{'type'} = $1;
@@ -3451,15 +3488,15 @@ sub parse_commit_text {
 	}
 
 	my $header = shift @commit_lines;
-	if ($header !~ m/^[0-9a-fA-F]{40}/) {
+	if ($header !~ m/^$oid_regex/) {
 		return;
 	}
 	($co{'id'}, my @parents) = split ' ', $header;
 	while (my $line = shift @commit_lines) {
 		last if $line eq "\n";
-		if ($line =~ m/^tree ([0-9a-fA-F]{40})$/) {
+		if ($line =~ m/^tree ($oid_regex)$/) {
 			$co{'tree'} = $1;
-		} elsif ((!defined $withparents) && ($line =~ m/^parent ([0-9a-fA-F]{40})$/)) {
+		} elsif ((!defined $withparents) && ($line =~ m/^parent ($oid_regex)$/)) {
 			push @parents, $1;
 		} elsif ($line =~ m/^author (.*) ([0-9]+) (.*)$/) {
 			$co{'author'} = to_utf8($1);
@@ -3591,7 +3628,7 @@ sub parse_difftree_raw_line {
 
 	# ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M	ls-files.c'
 	# ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M	rev-tree.c'
-	if ($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/) {
+	if ($line =~ m/^:([0-7]{6}) ([0-7]{6}) ($oid_regex) ($oid_regex) (.)([0-9]{0,3})\t(.*)$/) {
 		$res{'from_mode'} = $1;
 		$res{'to_mode'} = $2;
 		$res{'from_id'} = $3;
@@ -3606,7 +3643,7 @@ sub parse_difftree_raw_line {
 	}
 	# '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR	git-gui/git-gui.sh'
 	# combined diff (for merge commit)
-	elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:[0-9a-fA-F]{40} )+)([a-zA-Z]+)\t(.*)$//) {
+	elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:$oid_regex )+)([a-zA-Z]+)\t(.*)$//) {
 		$res{'nparents'}  = length($1);
 		$res{'from_mode'} = [ split(' ', $2) ];
 		$res{'to_mode'} = pop @{$res{'from_mode'}};
@@ -3616,7 +3653,7 @@ sub parse_difftree_raw_line {
 		$res{'to_file'} = unquote($5);
 	}
 	# 'c512b523472485aef4fff9e57b229d9d243c967f'
-	elsif ($line =~ m/^([0-9a-fA-F]{40})$/) {
+	elsif ($line =~ m/^($oid_regex)$/) {
 		$res{'commit'} = $1;
 	}
 
@@ -3644,7 +3681,7 @@ sub parse_ls_tree_line {
 
 	if ($opts{'-l'}) {
 		#'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa   16717	panic.c'
-		$line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40}) +(-|[0-9]+)\t(.+)$/s;
+		$line =~ m/^([0-9]+) (.+) ($oid_regex) +(-|[0-9]+)\t(.+)$/s;
 
 		$res{'mode'} = $1;
 		$res{'type'} = $2;
@@ -3657,7 +3694,7 @@ sub parse_ls_tree_line {
 		}
 	} else {
 		#'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa	panic.c'
-		$line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s;
+		$line =~ m/^([0-9]+) (.+) ($oid_regex)\t(.+)$/s;
 
 		$res{'mode'} = $1;
 		$res{'type'} = $2;
@@ -4799,7 +4836,7 @@ sub fill_from_file_info {
 sub is_deleted {
 	my $diffinfo = shift;
 
-	return $diffinfo->{'to_id'} eq ('0' x 40);
+	return $diffinfo->{'to_id'} eq ('0' x 40) || $diffinfo->{'to_id'} eq ('0' x 64);
 }
 
 # does patch correspond to [previous] difftree raw line
@@ -6285,7 +6322,7 @@ sub git_search_changes {
 			              -class => "list subject"},
 			              chop_and_escape_str($co{'title'}, 50) . "<br/>");
 		} elsif (defined $set{'to_id'}) {
-			next if ($set{'to_id'} =~ m/^0{40}$/);
+			next if is_deleted(\%set);
 
 			print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'},
 			                             hash=>$set{'to_id'}, file_name=>$set{'to_file'}),
@@ -6829,7 +6866,7 @@ sub git_blame_common {
 			# the header: <SHA-1> <src lineno> <dst lineno> [<lines in group>]
 			# no <lines in group> for subsequent lines in group of lines
 			my ($full_rev, $orig_lineno, $lineno, $group_size) =
-			   ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/);
+			   ($line =~ /^($oid_regex) (\d+) (\d+)(?: (\d+))?$/);
 			if (!exists $metainfo{$full_rev}) {
 				$metainfo{$full_rev} = { 'nprevious' => 0 };
 			}
@@ -6879,7 +6916,7 @@ sub git_blame_common {
 			}
 			# 'previous' <sha1 of parent commit> <filename at commit>
 			if (exists $meta->{'previous'} &&
-			    $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) {
+			    $meta->{'previous'} =~ /^($oid_regex) (.*)$/) {
 				$meta->{'parent'} = $1;
 				$meta->{'file_parent'} = unquote($2);
 			}
@@ -6996,7 +7033,7 @@ sub git_blob_plain {
 		} else {
 			die_error(400, "No file name defined");
 		}
-	} elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) {
+	} elsif ($hash =~ m/^$oid_regex$/) {
 		# blobs defined by non-textual hash id's can be cached
 		$expires = "+1d";
 	}
@@ -7057,7 +7094,7 @@ sub git_blob {
 		} else {
 			die_error(400, "No file name defined");
 		}
-	} elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) {
+	} elsif ($hash =~ m/^$oid_regex$/) {
 		# blobs defined by non-textual hash id's can be cached
 		$expires = "+1d";
 	}
@@ -7515,7 +7552,7 @@ sub git_commit {
 
 	# non-textual hash id's can be cached
 	my $expires;
-	if ($hash =~ m/^[0-9a-fA-F]{40}$/) {
+	if ($hash =~ m/^$oid_regex$/) {
 		$expires = "+1d";
 	}
 	my $refs = git_get_references();
@@ -7609,7 +7646,7 @@ sub git_object {
 		close $fd;
 
 		#'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa	panic.c'
-		unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) {
+		unless ($line && $line =~ m/^([0-9]+) (.+) ($oid_regex)\t/) {
 			die_error(404, "File or directory for given base does not exist");
 		}
 		$type = $2;
@@ -7649,7 +7686,7 @@ sub git_blobdiff {
 				or die_error(404, "Blob diff not found");
 
 		} elsif (defined $hash &&
-		         $hash =~ /[0-9a-fA-F]{40}/) {
+		         $hash =~ $oid_regex) {
 			# try to find filename from $hash
 
 			# read filtered raw output
@@ -7659,7 +7696,7 @@ sub git_blobdiff {
 			@difftree =
 				# ':100644 100644 03b21826... 3b93d5e7... M	ls-files.c'
 				# $hash == to_id
-				grep { /^:[0-7]{6} [0-7]{6} [0-9a-fA-F]{40} $hash/ }
+				grep { /^:[0-7]{6} [0-7]{6} $oid_regex $hash/ }
 				map { chomp; $_ } <$fd>;
 			close $fd
 				or die_error(404, "Reading git-diff-tree failed");
@@ -7682,8 +7719,8 @@ sub git_blobdiff {
 		$hash        ||= $diffinfo{'to_id'};
 
 		# non-textual hash id's can be cached
-		if ($hash_base =~ m/^[0-9a-fA-F]{40}$/ &&
+		if ($hash_base =~ m/^$oid_regex$/ &&
-		    $hash_parent_base =~ m/^[0-9a-fA-F]{40}$/) {
+		    $hash_parent_base =~ m/^$oid_regex$/) {
 			$expires = '+1d';
 		}
 
@@ -7819,7 +7856,7 @@ sub git_commitdiff {
 		    $hash_parent ne '-c' && $hash_parent ne '--cc') {
 			# commitdiff with two commits given
 			my $hash_parent_short = $hash_parent;
-			if ($hash_parent =~ m/^[0-9a-fA-F]{40}$/) {
+			if ($hash_parent =~ m/^$oid_regex$/) {
 				$hash_parent_short = substr($hash_parent, 0, 7);
 			}
 			$formats_nav .=
@@ -7928,7 +7965,7 @@ sub git_commitdiff {
 
 	# non-textual hash id's can be cached
 	my $expires;
-	if ($hash =~ m/^[0-9a-fA-F]{40}$/) {
+	if ($hash =~ m/^$oid_regex$/) {
 		$expires = "+1d";
 	}
 

hash.h

@@ -131,6 +131,8 @@ extern const struct git_hash_algo hash_algos[GIT_HASH_NALGOS];
 int hash_algo_by_name(const char *name);
 /* Identical, except based on the format ID. */
 int hash_algo_by_id(uint32_t format_id);
+/* Identical, except based on the length. */
+int hash_algo_by_length(int len);
 /* Identical, except for a pointer to struct git_hash_algo. */
 static inline int hash_algo_by_ptr(const struct git_hash_algo *p)
 {

http-backend.c

@@ -711,8 +711,11 @@ static struct service_cmd {
 	{"GET", "/objects/info/http-alternates$", get_text_file},
 	{"GET", "/objects/info/packs$", get_info_packs},
 	{"GET", "/objects/[0-9a-f]{2}/[0-9a-f]{38}$", get_loose_object},
+	{"GET", "/objects/[0-9a-f]{2}/[0-9a-f]{62}$", get_loose_object},
 	{"GET", "/objects/pack/pack-[0-9a-f]{40}\\.pack$", get_pack_file},
+	{"GET", "/objects/pack/pack-[0-9a-f]{64}\\.pack$", get_pack_file},
 	{"GET", "/objects/pack/pack-[0-9a-f]{40}\\.idx$", get_idx_file},
+	{"GET", "/objects/pack/pack-[0-9a-f]{64}\\.idx$", get_idx_file},
 
 	{"POST", "/git-upload-pack$", service_rpc},
 	{"POST", "/git-receive-pack$", service_rpc}

http-push.c

@@ -145,7 +145,7 @@ struct remote_lock {
 	char *url;
 	char *owner;
 	char *token;
-	char tmpfile_suffix[41];
+	char tmpfile_suffix[GIT_MAX_HEXSZ + 1];
 	time_t start_time;
 	long timeout;
 	int refreshing;
@@ -315,7 +315,8 @@ static void start_fetch_packed(struct transfer_request *request)
 		return;
 	}
 
-	fprintf(stderr,	"Fetching pack %s\n", sha1_to_hex(target->sha1));
+	fprintf(stderr,	"Fetching pack %s\n",
+		hash_to_hex(target->hash));
 	fprintf(stderr, " which contains %s\n", oid_to_hex(&request->obj->oid));
 
 	preq = new_http_pack_request(target, repo->url);
@@ -398,7 +399,7 @@ static void start_put(struct transfer_request *request)
 	request->dest = strbuf_detach(&buf, NULL);
 
 	append_remote_object_url(&buf, repo->url, hex, 0);
-	strbuf_add(&buf, request->lock->tmpfile_suffix, 41);
+	strbuf_add(&buf, request->lock->tmpfile_suffix, the_hash_algo->hexsz + 1);
 	request->url = strbuf_detach(&buf, NULL);
 
 	slot = get_active_slot();
@@ -757,8 +758,8 @@ static void handle_lockprop_ctx(struct xml_ctx *ctx, int tag_closed)
 static void handle_new_lock_ctx(struct xml_ctx *ctx, int tag_closed)
 {
 	struct remote_lock *lock = (struct remote_lock *)ctx->userData;
-	git_SHA_CTX sha_ctx;
+	git_hash_ctx hash_ctx;
-	unsigned char lock_token_sha1[20];
+	unsigned char lock_token_hash[GIT_MAX_RAWSZ];
 
 	if (tag_closed && ctx->cdata) {
 		if (!strcmp(ctx->name, DAV_ACTIVELOCK_OWNER)) {
@@ -770,12 +771,12 @@ static void handle_new_lock_ctx(struct xml_ctx *ctx, int tag_closed)
 		} else if (!strcmp(ctx->name, DAV_ACTIVELOCK_TOKEN)) {
 			lock->token = xstrdup(ctx->cdata);
 
-			git_SHA1_Init(&sha_ctx);
+			the_hash_algo->init_fn(&hash_ctx);
-			git_SHA1_Update(&sha_ctx, lock->token, strlen(lock->token));
+			the_hash_algo->update_fn(&hash_ctx, lock->token, strlen(lock->token));
-			git_SHA1_Final(lock_token_sha1, &sha_ctx);
+			the_hash_algo->final_fn(lock_token_hash, &hash_ctx);
 
 			lock->tmpfile_suffix[0] = '_';
-			memcpy(lock->tmpfile_suffix + 1, sha1_to_hex(lock_token_sha1), 40);
+			memcpy(lock->tmpfile_suffix + 1, hash_to_hex(lock_token_hash), the_hash_algo->hexsz);
 		}
 	}
 }
@@ -1017,7 +1018,7 @@ static void remote_ls(const char *path, int flags,
 /* extract hex from sharded "xx/x{38}" filename */
 static int get_oid_hex_from_objpath(const char *path, struct object_id *oid)
 {
-	if (strlen(path) != GIT_SHA1_HEXSZ + 1)
+	if (strlen(path) != the_hash_algo->hexsz + 1)
 		return -1;
 
 	if (hex_to_bytes(oid->hash, path, 1))
@@ -1025,7 +1026,7 @@ static int get_oid_hex_from_objpath(const char *path, struct object_id *oid)
 	path += 2;
 	path++; /* skip '/' */
 
-	return hex_to_bytes(oid->hash + 1, path, GIT_SHA1_RAWSZ - 1);
+	return hex_to_bytes(oid->hash + 1, path, the_hash_algo->rawsz - 1);
 }
 
 static void process_ls_object(struct remote_ls_ctx *ls)
@@ -1373,7 +1374,7 @@ static int get_delta(struct rev_info *revs, struct remote_lock *lock)
 	return count;
 }
 
-static int update_remote(unsigned char *sha1, struct remote_lock *lock)
+static int update_remote(const struct object_id *oid, struct remote_lock *lock)
 {
 	struct active_request_slot *slot;
 	struct slot_results results;
@@ -1382,7 +1383,7 @@ static int update_remote(unsigned char *sha1, struct remote_lock *lock)
 
 	dav_headers = get_dav_token_headers(lock, DAV_HEADER_IF);
 
-	strbuf_addf(&out_buffer.buf, "%s\n", sha1_to_hex(sha1));
+	strbuf_addf(&out_buffer.buf, "%s\n", oid_to_hex(oid));
 
 	slot = get_active_slot();
 	slot->results = &results;
@@ -1947,7 +1948,7 @@ int cmd_main(int argc, const char **argv)
 		run_request_queue();
 
 		/* Update the remote branch if all went well */
-		if (aborted || !update_remote(ref->new_oid.hash, ref_lock))
+		if (aborted || !update_remote(&ref->new_oid, ref_lock))
 			rc = 1;
 
 		if (!rc)

http-walker.c

@@ -442,9 +442,9 @@ static int http_fetch_pack(struct walker *walker, struct alt_base *repo, unsigne
 
 	if (walker->get_verbosely) {
 		fprintf(stderr, "Getting pack %s\n",
-			sha1_to_hex(target->sha1));
+			hash_to_hex(target->hash));
 		fprintf(stderr, " which contains %s\n",
-			sha1_to_hex(sha1));
+			hash_to_hex(sha1));
 	}
 
 	preq = new_http_pack_request(target, repo->base);
@@ -481,9 +481,9 @@ static void abort_object_request(struct object_request *obj_req)
 	release_object_request(obj_req);
 }
 
-static int fetch_object(struct walker *walker, unsigned char *sha1)
+static int fetch_object(struct walker *walker, unsigned char *hash)
 {
-	char *hex = sha1_to_hex(sha1);
+	char *hex = hash_to_hex(hash);
 	int ret = 0;
 	struct object_request *obj_req = NULL;
 	struct http_object_request *req;
@@ -491,7 +491,7 @@ static int fetch_object(struct walker *walker, unsigned char *sha1)
 
 	list_for_each(pos, head) {
 		obj_req = list_entry(pos, struct object_request, node);
-		if (hasheq(obj_req->oid.hash, sha1))
+		if (hasheq(obj_req->oid.hash, hash))
 			break;
 	}
 	if (obj_req == NULL)
@@ -556,20 +556,20 @@ static int fetch_object(struct walker *walker, unsigned char *sha1)
 	return ret;
 }
 
-static int fetch(struct walker *walker, unsigned char *sha1)
+static int fetch(struct walker *walker, unsigned char *hash)
 {
 	struct walker_data *data = walker->data;
 	struct alt_base *altbase = data->alt;
 
-	if (!fetch_object(walker, sha1))
+	if (!fetch_object(walker, hash))
 		return 0;
 	while (altbase) {
-		if (!http_fetch_pack(walker, altbase, sha1))
+		if (!http_fetch_pack(walker, altbase, hash))
 			return 0;
 		fetch_alternates(walker, data->alt->base);
 		altbase = altbase->next;
 	}
-	return error("Unable to find %s under %s", sha1_to_hex(sha1),
+	return error("Unable to find %s under %s", hash_to_hex(hash),
 		     data->alt->base);
 }
 

http.c

@@ -2071,7 +2071,7 @@ int http_fetch_ref(const char *base, struct ref *ref)
 	url = quote_ref_url(base, ref->name);
 	if (http_get_strbuf(url, &buffer, &options) == HTTP_OK) {
 		strbuf_rtrim(&buffer);
-		if (buffer.len == 40)
+		if (buffer.len == the_hash_algo->hexsz)
 			ret = get_oid_hex(buffer.buf, &ref->old_oid);
 		else if (starts_with(buffer.buf, "ref: ")) {
 			ref->symref = xstrdup(buffer.buf + 5);
@@ -2085,19 +2085,19 @@ int http_fetch_ref(const char *base, struct ref *ref)
 }
 
 /* Helpers for fetching packs */
-static char *fetch_pack_index(unsigned char *sha1, const char *base_url)
+static char *fetch_pack_index(unsigned char *hash, const char *base_url)
 {
 	char *url, *tmp;
 	struct strbuf buf = STRBUF_INIT;
 
 	if (http_is_verbose)
-		fprintf(stderr, "Getting index for pack %s\n", sha1_to_hex(sha1));
+		fprintf(stderr, "Getting index for pack %s\n", hash_to_hex(hash));
 
 	end_url_with_slash(&buf, base_url);
-	strbuf_addf(&buf, "objects/pack/pack-%s.idx", sha1_to_hex(sha1));
+	strbuf_addf(&buf, "objects/pack/pack-%s.idx", hash_to_hex(hash));
 	url = strbuf_detach(&buf, NULL);
 
-	strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(sha1));
+	strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(hash));
 	tmp = strbuf_detach(&buf, NULL);
 
 	if (http_get_file(url, tmp, NULL) != HTTP_OK) {
@@ -2235,10 +2235,10 @@ int finish_http_pack_request(struct http_pack_request *preq)
 		return -1;
 	}
 
-	unlink(sha1_pack_index_name(p->sha1));
+	unlink(sha1_pack_index_name(p->hash));
 
-	if (finalize_object_file(preq->tmpfile.buf, sha1_pack_name(p->sha1))
+	if (finalize_object_file(preq->tmpfile.buf, sha1_pack_name(p->hash))
-	 || finalize_object_file(tmp_idx, sha1_pack_index_name(p->sha1))) {
+	 || finalize_object_file(tmp_idx, sha1_pack_index_name(p->hash))) {
 		free(tmp_idx);
 		return -1;
 	}
@@ -2261,10 +2261,10 @@ struct http_pack_request *new_http_pack_request(
 
 	end_url_with_slash(&buf, base_url);
 	strbuf_addf(&buf, "objects/pack/pack-%s.pack",
-		sha1_to_hex(target->sha1));
+		hash_to_hex(target->hash));
 	preq->url = strbuf_detach(&buf, NULL);
 
-	strbuf_addf(&preq->tmpfile, "%s.temp", sha1_pack_name(target->sha1));
+	strbuf_addf(&preq->tmpfile, "%s.temp", sha1_pack_name(target->hash));
 	preq->packfile = fopen(preq->tmpfile.buf, "a");
 	if (!preq->packfile) {
 		error("Unable to open local file %s for pack",
@@ -2288,7 +2288,8 @@ struct http_pack_request *new_http_pack_request(
 		if (http_is_verbose)
 			fprintf(stderr,
 				"Resuming fetch of pack %s at byte %"PRIuMAX"\n",
-				sha1_to_hex(target->sha1), (uintmax_t)prev_posn);
+				hash_to_hex(target->hash),
+				(uintmax_t)prev_posn);
 		http_opt_request_remainder(preq->slot->curl, prev_posn);
 	}
 
@@ -2335,8 +2336,8 @@ static size_t fwrite_sha1_file(char *ptr, size_t eltsize, size_t nmemb,
 		freq->stream.next_out = expn;
 		freq->stream.avail_out = sizeof(expn);
 		freq->zret = git_inflate(&freq->stream, Z_SYNC_FLUSH);
-		git_SHA1_Update(&freq->c, expn,
+		the_hash_algo->update_fn(&freq->c, expn,
-				sizeof(expn) - freq->stream.avail_out);
+					 sizeof(expn) - freq->stream.avail_out);
 	} while (freq->stream.avail_in && freq->zret == Z_OK);
 	return size;
 }
@@ -2394,7 +2395,7 @@ struct http_object_request *new_http_object_request(const char *base_url,
 
 	git_inflate_init(&freq->stream);
 
-	git_SHA1_Init(&freq->c);
+	the_hash_algo->init_fn(&freq->c);
 
 	freq->url = get_remote_object_url(base_url, hex, 0);
 
@@ -2429,7 +2430,7 @@ struct http_object_request *new_http_object_request(const char *base_url,
 	if (prev_read == -1) {
 		memset(&freq->stream, 0, sizeof(freq->stream));
 		git_inflate_init(&freq->stream);
-		git_SHA1_Init(&freq->c);
+		the_hash_algo->init_fn(&freq->c);
 		if (prev_posn>0) {
 			prev_posn = 0;
 			lseek(freq->localfile, 0, SEEK_SET);
@@ -2500,7 +2501,7 @@ int finish_http_object_request(struct http_object_request *freq)
 	}
 
 	git_inflate_end(&freq->stream);
-	git_SHA1_Final(freq->real_oid.hash, &freq->c);
+	the_hash_algo->final_fn(freq->real_oid.hash, &freq->c);
 	if (freq->zret != Z_STREAM_END) {
 		unlink_or_warn(freq->tmpfile.buf);
 		return -1;

http.h

@@ -234,7 +234,7 @@ struct http_object_request {
 	long http_code;
 	struct object_id oid;
 	struct object_id real_oid;
-	git_SHA_CTX c;
+	git_hash_ctx c;
 	git_zstream stream;
 	int zret;
 	int rename;

khash.h

@@ -332,4 +332,22 @@ typedef kh_sha1_t khash_sha1;
 KHASH_INIT(sha1_pos, const unsigned char *, int, 1, sha1hash, __kh_oid_cmp)
 typedef kh_sha1_pos_t khash_sha1_pos;
 
+static inline unsigned int oid_hash(struct object_id oid)
+{
+	return sha1hash(oid.hash);
+}
+
+static inline int oid_equal(struct object_id a, struct object_id b)
+{
+	return oideq(&a, &b);
+}
+
+KHASH_INIT(oid, struct object_id, int, 0, oid_hash, oid_equal)
+
+KHASH_INIT(oid_map, struct object_id, void *, 1, oid_hash, oid_equal)
+typedef kh_oid_t khash_oid_map;
+
+KHASH_INIT(oid_pos, struct object_id, int, 1, oid_hash, oid_equal)
+typedef kh_oid_pos_t khash_oid_pos;
+
 #endif /* __AC_KHASH_H */

merge-recursive.c

@@ -1122,7 +1122,7 @@ static int find_first_merges(struct repository *repo,
 	struct commit *commit;
 	int contains_another;
 
-	char merged_revision[42];
+	char merged_revision[GIT_MAX_HEXSZ + 2];
 	const char *rev_args[] = { "rev-list", "--merges", "--ancestry-path",
 				   "--all", merged_revision, NULL };
 	struct rev_info revs;

notes-merge.c

@@ -29,14 +29,14 @@ void init_notes_merge_options(struct repository *r,
 
 static int path_to_oid(const char *path, struct object_id *oid)
 {
-	char hex_oid[GIT_SHA1_HEXSZ];
+	char hex_oid[GIT_MAX_HEXSZ];
 	int i = 0;
-	while (*path && i < GIT_SHA1_HEXSZ) {
+	while (*path && i < the_hash_algo->hexsz) {
 		if (*path != '/')
 			hex_oid[i++] = *path;
 		path++;
 	}
-	if (*path || i != GIT_SHA1_HEXSZ)
+	if (*path || i != the_hash_algo->hexsz)
 		return -1;
 	return get_oid_hex(hex_oid, oid);
 }

notes.c

@@ -67,8 +67,9 @@ struct non_note {
 
 #define GET_NIBBLE(n, sha1) ((((sha1)[(n) >> 1]) >> ((~(n) & 0x01) << 2)) & 0x0f)
 
-#define KEY_INDEX (GIT_SHA1_RAWSZ - 1)
+#define KEY_INDEX (the_hash_algo->rawsz - 1)
-#define FANOUT_PATH_SEPARATORS ((GIT_SHA1_HEXSZ / 2) - 1)
+#define FANOUT_PATH_SEPARATORS (the_hash_algo->rawsz - 1)
+#define FANOUT_PATH_SEPARATORS_MAX ((GIT_MAX_HEXSZ / 2) - 1)
 #define SUBTREE_SHA1_PREFIXCMP(key_sha1, subtree_sha1) \
 	(memcmp(key_sha1, subtree_sha1, subtree_sha1[KEY_INDEX]))
 
@@ -198,7 +199,7 @@ static void note_tree_remove(struct notes_tree *t,
 		struct leaf_node *entry)
 {
 	struct leaf_node *l;
-	struct int_node *parent_stack[GIT_SHA1_RAWSZ];
+	struct int_node *parent_stack[GIT_MAX_RAWSZ];
 	unsigned char i, j;
 	void **p = note_tree_search(t, &tree, &n, entry->key_oid.hash);
 
@@ -394,6 +395,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 	void *buf;
 	struct tree_desc desc;
 	struct name_entry entry;
+	const unsigned hashsz = the_hash_algo->rawsz;
 
 	buf = fill_tree_descriptor(&desc, &subtree->val_oid);
 	if (!buf)
@@ -401,7 +403,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 		     oid_to_hex(&subtree->val_oid));
 
 	prefix_len = subtree->key_oid.hash[KEY_INDEX];
-	if (prefix_len >= GIT_SHA1_RAWSZ)
+	if (prefix_len >= hashsz)
 		BUG("prefix_len (%"PRIuMAX") is out of range", (uintmax_t)prefix_len);
 	if (prefix_len * 2 < n)
 		BUG("prefix_len (%"PRIuMAX") is too small", (uintmax_t)prefix_len);
@@ -411,7 +413,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 		struct leaf_node *l;
 		size_t path_len = strlen(entry.path);
 
-		if (path_len == 2 * (GIT_SHA1_RAWSZ - prefix_len)) {
+		if (path_len == 2 * (hashsz - prefix_len)) {
 			/* This is potentially the remainder of the SHA-1 */
 
 			if (!S_ISREG(entry.mode))
@@ -419,7 +421,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 				goto handle_non_note;
 
 			if (hex_to_bytes(object_oid.hash + prefix_len, entry.path,
-					 GIT_SHA1_RAWSZ - prefix_len))
+					 hashsz - prefix_len))
 				goto handle_non_note; /* entry.path is not a SHA1 */
 
 			type = PTR_TYPE_NOTE;
@@ -439,7 +441,7 @@ static void load_subtree(struct notes_tree *t, struct leaf_node *subtree,
 			 * except for the last byte, where we write
 			 * the length:
 			 */
-			memset(object_oid.hash + len, 0, GIT_SHA1_RAWSZ - len - 1);
+			memset(object_oid.hash + len, 0, hashsz - len - 1);
 			object_oid.hash[KEY_INDEX] = (unsigned char)len;
 
 			type = PTR_TYPE_SUBTREE;
@@ -527,22 +529,22 @@ static unsigned char determine_fanout(struct int_node *tree, unsigned char n,
 	return fanout + 1;
 }
 
-/* hex SHA1 + 19 * '/' + NUL */
+/* hex oid + '/' between each pair of hex digits + NUL */
-#define FANOUT_PATH_MAX GIT_SHA1_HEXSZ + FANOUT_PATH_SEPARATORS + 1
+#define FANOUT_PATH_MAX GIT_MAX_HEXSZ + FANOUT_PATH_SEPARATORS_MAX + 1
 
-static void construct_path_with_fanout(const unsigned char *sha1,
+static void construct_path_with_fanout(const unsigned char *hash,
 		unsigned char fanout, char *path)
 {
 	unsigned int i = 0, j = 0;
-	const char *hex_sha1 = sha1_to_hex(sha1);
+	const char *hex_hash = hash_to_hex(hash);
-	assert(fanout < GIT_SHA1_RAWSZ);
+	assert(fanout < the_hash_algo->rawsz);
 	while (fanout) {
-		path[i++] = hex_sha1[j++];
+		path[i++] = hex_hash[j++];
-		path[i++] = hex_sha1[j++];
+		path[i++] = hex_hash[j++];
 		path[i++] = '/';
 		fanout--;
 	}
-	xsnprintf(path + i, FANOUT_PATH_MAX - i, "%s", hex_sha1 + j);
+	xsnprintf(path + i, FANOUT_PATH_MAX - i, "%s", hex_hash + j);
 }
 
 static int for_each_note_helper(struct notes_tree *t, struct int_node *tree,
@@ -637,10 +639,10 @@ static inline int matches_tree_write_stack(struct tree_write_stack *tws,
 
 static void write_tree_entry(struct strbuf *buf, unsigned int mode,
 		const char *path, unsigned int path_len, const
-		unsigned char *sha1)
+		unsigned char *hash)
 {
 	strbuf_addf(buf, "%o %.*s%c", mode, path_len, path, '\0');
-	strbuf_add(buf, sha1, GIT_SHA1_RAWSZ);
+	strbuf_add(buf, hash, the_hash_algo->rawsz);
 }
 
 static void tree_write_stack_init_subtree(struct tree_write_stack *tws,
@@ -652,7 +654,7 @@ static void tree_write_stack_init_subtree(struct tree_write_stack *tws,
 	n = (struct tree_write_stack *)
 		xmalloc(sizeof(struct tree_write_stack));
 	n->next = NULL;
-	strbuf_init(&n->buf, 256 * (32 + GIT_SHA1_HEXSZ)); /* assume 256 entries per tree */
+	strbuf_init(&n->buf, 256 * (32 + the_hash_algo->hexsz)); /* assume 256 entries per tree */
 	n->path[0] = n->path[1] = '\0';
 	tws->next = n;
 	tws->path[0] = path[0];
@@ -757,7 +759,7 @@ static int write_each_note(const struct object_id *object_oid,
 		note_path[note_path_len] = '\0';
 		mode = 040000;
 	}
-	assert(note_path_len <= GIT_SHA1_HEXSZ + FANOUT_PATH_SEPARATORS);
+	assert(note_path_len <= GIT_MAX_HEXSZ + FANOUT_PATH_SEPARATORS);
 
 	/* Weave non-note entries into note entries */
 	return  write_each_non_note_until(note_path, d) ||
@@ -1137,7 +1139,7 @@ int write_notes_tree(struct notes_tree *t, struct object_id *result)
 
 	/* Prepare for traversal of current notes tree */
 	root.next = NULL; /* last forward entry in list is grounded */
-	strbuf_init(&root.buf, 256 * (32 + GIT_SHA1_HEXSZ)); /* assume 256 entries */
+	strbuf_init(&root.buf, 256 * (32 + the_hash_algo->hexsz)); /* assume 256 entries */
 	root.path[0] = root.path[1] = '\0';
 	cb_data.root = &root;
 	cb_data.next_non_note = t->first_non_note;
@@ -1165,7 +1167,7 @@ void prune_notes(struct notes_tree *t, int flags)
 
 	while (l) {
 		if (flags & NOTES_PRUNE_VERBOSE)
-			printf("%s\n", sha1_to_hex(l->sha1));
+			printf("%s\n", hash_to_hex(l->sha1));
 		if (!(flags & NOTES_PRUNE_DRYRUN))
 			remove_note(t, l->sha1);
 		l = l->next;

object-store.h

@@ -77,7 +77,7 @@ struct packed_git {
 		 freshened:1,
 		 do_not_close:1,
 		 pack_promisor:1;
-	unsigned char sha1[20];
+	unsigned char hash[GIT_MAX_RAWSZ];
 	struct revindex_entry *revindex;
 	/* something like ".git/objects/pack/xxxxx.pack" */
 	char pack_name[FLEX_ARRAY]; /* more */

oidset.h

@@ -16,18 +16,6 @@
  *      table overhead.
  */
 
-static inline unsigned int oid_hash(struct object_id oid)
-{
-	return sha1hash(oid.hash);
-}
-
-static inline int oid_equal(struct object_id a, struct object_id b)
-{
-	return oideq(&a, &b);
-}
-
-KHASH_INIT(oid, struct object_id, int, 0, oid_hash, oid_equal)
-
 /**
  * A single oidset; should be zero-initialized (or use OIDSET_INIT).
  */

pack-bitmap-write.c

@@ -142,13 +142,13 @@ static inline void reset_all_seen(void)
 	seen_objects_nr = 0;
 }
 
-static uint32_t find_object_pos(const unsigned char *sha1)
+static uint32_t find_object_pos(const unsigned char *hash)
 {
-	struct object_entry *entry = packlist_find(writer.to_pack, sha1, NULL);
+	struct object_entry *entry = packlist_find(writer.to_pack, hash, NULL);
 
 	if (!entry) {
 		die("Failed to write bitmap index. Packfile doesn't have full closure "
-			"(object %s is missing)", sha1_to_hex(sha1));
+			"(object %s is missing)", hash_to_hex(hash));
 	}
 
 	return oe_in_pack_pos(writer.to_pack, entry);
@@ -535,7 +535,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 	header.entry_count = htonl(writer.selected_nr);
 	hashcpy(header.checksum, writer.pack_checksum);
 
-	hashwrite(f, &header, sizeof(header));
+	hashwrite(f, &header, sizeof(header) - GIT_MAX_RAWSZ + the_hash_algo->rawsz);
 	dump_bitmap(f, writer.commits);
 	dump_bitmap(f, writer.trees);
 	dump_bitmap(f, writer.blobs);

pack-bitmap.c

@@ -18,7 +18,7 @@
  * commit.
  */
 struct stored_bitmap {
-	unsigned char sha1[20];
+	struct object_id oid;
 	struct ewah_bitmap *root;
 	struct stored_bitmap *xor;
 	int flags;
@@ -60,8 +60,8 @@ struct bitmap_index {
 	struct ewah_bitmap *blobs;
 	struct ewah_bitmap *tags;
 
-	/* Map from SHA1 -> `stored_bitmap` for all the bitmapped commits */
+	/* Map from object ID -> `stored_bitmap` for all the bitmapped commits */
-	khash_sha1 *bitmaps;
+	kh_oid_map_t *bitmaps;
 
 	/* Number of bitmapped commits */
 	uint32_t entry_count;
@@ -80,7 +80,7 @@ struct bitmap_index {
 		struct object **objects;
 		uint32_t *hashes;
 		uint32_t count, alloc;
-		khash_sha1_pos *positions;
+		kh_oid_pos_t *positions;
 	} ext_index;
 
 	/* Bitmap result of the last performed walk */
@@ -138,7 +138,7 @@ static int load_bitmap_header(struct bitmap_index *index)
 {
 	struct bitmap_disk_header *header = (void *)index->map;
 
-	if (index->map_size < sizeof(*header) + 20)
+	if (index->map_size < sizeof(*header) + the_hash_algo->rawsz)
 		return error("Corrupted bitmap index (missing header data)");
 
 	if (memcmp(header->magic, BITMAP_IDX_SIGNATURE, sizeof(BITMAP_IDX_SIGNATURE)) != 0)
@@ -157,19 +157,19 @@ static int load_bitmap_header(struct bitmap_index *index)
 				"(Git requires BITMAP_OPT_FULL_DAG)");
 
 		if (flags & BITMAP_OPT_HASH_CACHE) {
-			unsigned char *end = index->map + index->map_size - 20;
+			unsigned char *end = index->map + index->map_size - the_hash_algo->rawsz;
 			index->hashes = ((uint32_t *)end) - index->pack->num_objects;
 		}
 	}
 
 	index->entry_count = ntohl(header->entry_count);
-	index->map_pos += sizeof(*header);
+	index->map_pos += sizeof(*header) - GIT_MAX_RAWSZ + the_hash_algo->rawsz;
 	return 0;
 }
 
 static struct stored_bitmap *store_bitmap(struct bitmap_index *index,
 					  struct ewah_bitmap *root,
-					  const unsigned char *sha1,
+					  const unsigned char *hash,
 					  struct stored_bitmap *xor_with,
 					  int flags)
 {
@@ -181,15 +181,15 @@ static struct stored_bitmap *store_bitmap(struct bitmap_index *index,
 	stored->root = root;
 	stored->xor = xor_with;
 	stored->flags = flags;
-	hashcpy(stored->sha1, sha1);
+	oidread(&stored->oid, hash);
 
-	hash_pos = kh_put_sha1(index->bitmaps, stored->sha1, &ret);
+	hash_pos = kh_put_oid_map(index->bitmaps, stored->oid, &ret);
 
 	/* a 0 return code means the insertion succeeded with no changes,
 	 * because the SHA1 already existed on the map. this is bad, there
 	 * shouldn't be duplicated commits in the index */
 	if (ret == 0) {
-		error("Duplicate entry in bitmap index: %s", sha1_to_hex(sha1));
+		error("Duplicate entry in bitmap index: %s", hash_to_hex(hash));
 		return NULL;
 	}
 
@@ -306,8 +306,8 @@ static int load_pack_bitmap(struct bitmap_index *bitmap_git)
 {
 	assert(bitmap_git->map);
 
-	bitmap_git->bitmaps = kh_init_sha1();
+	bitmap_git->bitmaps = kh_init_oid_map();
-	bitmap_git->ext_index.positions = kh_init_sha1_pos();
+	bitmap_git->ext_index.positions = kh_init_oid_pos();
 	if (load_pack_revindex(bitmap_git->pack))
 		goto failed;
 
@@ -363,10 +363,10 @@ struct include_data {
 };
 
 static inline int bitmap_position_extended(struct bitmap_index *bitmap_git,
-					   const unsigned char *sha1)
+					   const struct object_id *oid)
 {
-	khash_sha1_pos *positions = bitmap_git->ext_index.positions;
+	khash_oid_pos *positions = bitmap_git->ext_index.positions;
-	khiter_t pos = kh_get_sha1_pos(positions, sha1);
+	khiter_t pos = kh_get_oid_pos(positions, *oid);
 
 	if (pos < kh_end(positions)) {
 		int bitmap_pos = kh_value(positions, pos);
@@ -377,9 +377,9 @@ static inline int bitmap_position_extended(struct bitmap_index *bitmap_git,
 }
 
 static inline int bitmap_position_packfile(struct bitmap_index *bitmap_git,
-					   const unsigned char *sha1)
+					   const struct object_id *oid)
 {
-	off_t offset = find_pack_entry_one(sha1, bitmap_git->pack);
+	off_t offset = find_pack_entry_one(oid->hash, bitmap_git->pack);
 	if (!offset)
 		return -1;
 
@@ -387,10 +387,10 @@ static inline int bitmap_position_packfile(struct bitmap_index *bitmap_git,
 }
 
 static int bitmap_position(struct bitmap_index *bitmap_git,
-			   const unsigned char *sha1)
+			   const struct object_id *oid)
 {
-	int pos = bitmap_position_packfile(bitmap_git, sha1);
+	int pos = bitmap_position_packfile(bitmap_git, oid);
-	return (pos >= 0) ? pos : bitmap_position_extended(bitmap_git, sha1);
+	return (pos >= 0) ? pos : bitmap_position_extended(bitmap_git, oid);
 }
 
 static int ext_index_add_object(struct bitmap_index *bitmap_git,
@@ -402,7 +402,7 @@ static int ext_index_add_object(struct bitmap_index *bitmap_git,
 	int hash_ret;
 	int bitmap_pos;
 
-	hash_pos = kh_put_sha1_pos(eindex->positions, object->oid.hash, &hash_ret);
+	hash_pos = kh_put_oid_pos(eindex->positions, object->oid, &hash_ret);
 	if (hash_ret > 0) {
 		if (eindex->count >= eindex->alloc) {
 			eindex->alloc = (eindex->alloc + 16) * 3 / 2;
@@ -432,7 +432,7 @@ static void show_object(struct object *object, const char *name, void *data_)
 	struct bitmap_show_data *data = data_;
 	int bitmap_pos;
 
-	bitmap_pos = bitmap_position(data->bitmap_git, object->oid.hash);
+	bitmap_pos = bitmap_position(data->bitmap_git, &object->oid);
 
 	if (bitmap_pos < 0)
 		bitmap_pos = ext_index_add_object(data->bitmap_git, object,
@@ -447,7 +447,7 @@ static void show_commit(struct commit *commit, void *data)
 
 static int add_to_include_set(struct bitmap_index *bitmap_git,
 			      struct include_data *data,
-			      const unsigned char *sha1,
+			      const struct object_id *oid,
 			      int bitmap_pos)
 {
 	khiter_t hash_pos;
@@ -458,7 +458,7 @@ static int add_to_include_set(struct bitmap_index *bitmap_git,
 	if (bitmap_get(data->base, bitmap_pos))
 		return 0;
 
-	hash_pos = kh_get_sha1(bitmap_git->bitmaps, sha1);
+	hash_pos = kh_get_oid_map(bitmap_git->bitmaps, *oid);
 	if (hash_pos < kh_end(bitmap_git->bitmaps)) {
 		struct stored_bitmap *st = kh_value(bitmap_git->bitmaps, hash_pos);
 		bitmap_or_ewah(data->base, lookup_stored_bitmap(st));
@@ -474,13 +474,13 @@ static int should_include(struct commit *commit, void *_data)
 	struct include_data *data = _data;
 	int bitmap_pos;
 
-	bitmap_pos = bitmap_position(data->bitmap_git, commit->object.oid.hash);
+	bitmap_pos = bitmap_position(data->bitmap_git, &commit->object.oid);
 	if (bitmap_pos < 0)
 		bitmap_pos = ext_index_add_object(data->bitmap_git,
 						  (struct object *)commit,
 						  NULL);
 
-	if (!add_to_include_set(data->bitmap_git, data, commit->object.oid.hash,
+	if (!add_to_include_set(data->bitmap_git, data, &commit->object.oid,
 				bitmap_pos)) {
 		struct commit_list *parent = commit->parents;
 
@@ -518,7 +518,7 @@ static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
 		roots = roots->next;
 
 		if (object->type == OBJ_COMMIT) {
-			khiter_t pos = kh_get_sha1(bitmap_git->bitmaps, object->oid.hash);
+			khiter_t pos = kh_get_oid_map(bitmap_git->bitmaps, object->oid);
 
 			if (pos < kh_end(bitmap_git->bitmaps)) {
 				struct stored_bitmap *st = kh_value(bitmap_git->bitmaps, pos);
@@ -560,7 +560,7 @@ static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
 		int pos;
 
 		roots = roots->next;
-		pos = bitmap_position(bitmap_git, object->oid.hash);
+		pos = bitmap_position(bitmap_git, &object->oid);
 
 		if (pos < 0 || base == NULL || !bitmap_get(base, pos)) {
 			object->flags &= ~UNINTERESTING;
@@ -806,7 +806,7 @@ int reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
 
 		fprintf(stderr, "Failed to reuse at %d (%016llx)\n",
 			reuse_objects, result->words[i]);
-		fprintf(stderr, " %s\n", sha1_to_hex(sha1));
+		fprintf(stderr, " %s\n", hash_to_hex(sha1));
 	}
 #endif
 
@@ -926,7 +926,7 @@ static void test_show_object(struct object *object, const char *name,
 	struct bitmap_test_data *tdata = data;
 	int bitmap_pos;
 
-	bitmap_pos = bitmap_position(tdata->bitmap_git, object->oid.hash);
+	bitmap_pos = bitmap_position(tdata->bitmap_git, &object->oid);
 	if (bitmap_pos < 0)
 		die("Object not in bitmap: %s\n", oid_to_hex(&object->oid));
 
@@ -940,7 +940,7 @@ static void test_show_commit(struct commit *commit, void *data)
 	int bitmap_pos;
 
 	bitmap_pos = bitmap_position(tdata->bitmap_git,
-				     commit->object.oid.hash);
+				     &commit->object.oid);
 	if (bitmap_pos < 0)
 		die("Object not in bitmap: %s\n", oid_to_hex(&commit->object.oid));
 
@@ -967,7 +967,7 @@ void test_bitmap_walk(struct rev_info *revs)
 		bitmap_git->version, bitmap_git->entry_count);
 
 	root = revs->pending.objects[0].item;
-	pos = kh_get_sha1(bitmap_git->bitmaps, root->oid.hash);
+	pos = kh_get_oid_map(bitmap_git->bitmaps, root->oid);
 
 	if (pos < kh_end(bitmap_git->bitmaps)) {
 		struct stored_bitmap *st = kh_value(bitmap_git->bitmaps, pos);
@@ -1081,7 +1081,7 @@ int rebuild_existing_bitmaps(struct bitmap_index *bitmap_git,
 					    lookup_stored_bitmap(stored),
 					    rebuild)) {
 				hash_pos = kh_put_sha1(reused_bitmaps,
-						       stored->sha1,
+						       stored->oid.hash,
 						       &hash_ret);
 				kh_value(reused_bitmaps, hash_pos) =
 					bitmap_to_ewah(rebuild);
@@ -1109,7 +1109,7 @@ void free_bitmap_index(struct bitmap_index *b)
 	ewah_pool_free(b->trees);
 	ewah_pool_free(b->blobs);
 	ewah_pool_free(b->tags);
-	kh_destroy_sha1(b->bitmaps);
+	kh_destroy_oid_map(b->bitmaps);
 	free(b->ext_index.objects);
 	free(b->ext_index.hashes);
 	bitmap_free(b->result);
@@ -1117,8 +1117,8 @@ void free_bitmap_index(struct bitmap_index *b)
 	free(b);
 }
 
-int bitmap_has_sha1_in_uninteresting(struct bitmap_index *bitmap_git,
+int bitmap_has_oid_in_uninteresting(struct bitmap_index *bitmap_git,
-				     const unsigned char *sha1)
+				    const struct object_id *oid)
 {
 	int pos;
 
@@ -1127,7 +1127,7 @@ int bitmap_has_sha1_in_uninteresting(struct bitmap_index *bitmap_git,
 	if (!bitmap_git->haves)
 		return 0; /* walk had no "haves" */
 
-	pos = bitmap_position_packfile(bitmap_git, sha1);
+	pos = bitmap_position_packfile(bitmap_git, oid);
 	if (pos < 0)
 		return 0;
 

pack-bitmap.h

@@ -14,7 +14,7 @@ struct bitmap_disk_header {
 	uint16_t version;
 	uint16_t options;
 	uint32_t entry_count;
-	unsigned char checksum[20];
+	unsigned char checksum[GIT_MAX_RAWSZ];
 };
 
 static const char BITMAP_IDX_SIGNATURE[] = {'B', 'I', 'T', 'M'};
@@ -59,7 +59,7 @@ void free_bitmap_index(struct bitmap_index *);
  * queried to see if a particular object was reachable from any of the
  * objects flagged as UNINTERESTING.
  */
-int bitmap_has_sha1_in_uninteresting(struct bitmap_index *, const unsigned char *sha1);
+int bitmap_has_oid_in_uninteresting(struct bitmap_index *, const struct object_id *oid);
 
 void bitmap_writer_show_progress(int show);
 void bitmap_writer_set_checksum(unsigned char *sha1);

packfile.c

@@ -235,7 +235,7 @@ struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
 	struct packed_git *p = alloc_packed_git(alloc);
 
 	memcpy(p->pack_name, path, alloc); /* includes NUL */
-	hashcpy(p->sha1, sha1);
+	hashcpy(p->hash, sha1);
 	if (check_packed_git_idx(idx_path, p)) {
 		free(p);
 		return NULL;
@@ -732,8 +732,8 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
 	p->pack_local = local;
 	p->mtime = st.st_mtime;
 	if (path_len < the_hash_algo->hexsz ||
-	    get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->sha1))
+	    get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->hash))
-		hashclr(p->sha1);
+		hashclr(p->hash);
 	return p;
 }
 

perl/Git.pm

@@ -980,7 +980,7 @@ sub cat_blob {
 		return -1;
 	}
 
-	if ($description !~ /^[0-9a-fA-F]{40} \S+ (\d+)$/) {
+	if ($description !~ /^[0-9a-fA-F]{40}(?:[0-9a-fA-F]{24})? \S+ (\d+)$/) {
 		carp "Unexpected result returned from git cat-file";
 		return -1;
 	}

read-cache.c

@@ -1641,39 +1641,24 @@ struct ondisk_cache_entry {
 	uint32_t uid;
 	uint32_t gid;
 	uint32_t size;
-	unsigned char sha1[20];
+	/*
-	uint16_t flags;
+	 * unsigned char hash[hashsz];
-	char name[FLEX_ARRAY]; /* more */
+	 * uint16_t flags;
-};
+	 * if (flags & CE_EXTENDED)
-
+	 *	uint16_t flags2;
-/*
+	 */
- * This struct is used when CE_EXTENDED bit is 1
+	unsigned char data[GIT_MAX_RAWSZ + 2 * sizeof(uint16_t)];
- * The struct must match ondisk_cache_entry exactly from
+	char name[FLEX_ARRAY];
- * ctime till flags
- */
-struct ondisk_cache_entry_extended {
-	struct cache_time ctime;
-	struct cache_time mtime;
-	uint32_t dev;
-	uint32_t ino;
-	uint32_t mode;
-	uint32_t uid;
-	uint32_t gid;
-	uint32_t size;
-	unsigned char sha1[20];
-	uint16_t flags;
-	uint16_t flags2;
-	char name[FLEX_ARRAY]; /* more */
 };
 
 /* These are only used for v3 or lower */
 #define align_padding_size(size, len) ((size + (len) + 8) & ~7) - (size + len)
-#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7)
+#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,data) + (len) + 8) & ~7)
 #define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len)
-#define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len)
+#define ondisk_data_size(flags, len) (the_hash_algo->rawsz + \
-#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \
+				     ((flags & CE_EXTENDED) ? 2 : 1) * sizeof(uint16_t) + len)
-			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
+#define ondisk_data_size_max(len) (ondisk_data_size(CE_EXTENDED, len))
-			    ondisk_cache_entry_size(ce_namelen(ce)))
+#define ondisk_ce_size(ce) (ondisk_cache_entry_size(ondisk_data_size((ce)->ce_flags, ce_namelen(ce))))
 
 /* Allow fsck to force verification of the index checksum. */
 int verify_index_checksum;
@@ -1747,6 +1732,8 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
 	struct cache_entry *ce;
 	size_t len;
 	const char *name;
+	const unsigned hashsz = the_hash_algo->rawsz;
+	const uint16_t *flagsp = (const uint16_t *)(ondisk->data + hashsz);
 	unsigned int flags;
 	size_t copy_len = 0;
 	/*
@@ -1759,22 +1746,20 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
 	int expand_name_field = version == 4;
 
 	/* On-disk flags are just 16 bits */
-	flags = get_be16(&ondisk->flags);
+	flags = get_be16(flagsp);
 	len = flags & CE_NAMEMASK;
 
 	if (flags & CE_EXTENDED) {
-		struct ondisk_cache_entry_extended *ondisk2;
 		int extended_flags;
-		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
+		extended_flags = get_be16(flagsp + 1) << 16;
-		extended_flags = get_be16(&ondisk2->flags2) << 16;
 		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
 		if (extended_flags & ~CE_EXTENDED_FLAGS)
 			die(_("unknown index entry format 0x%08x"), extended_flags);
 		flags |= extended_flags;
-		name = ondisk2->name;
+		name = (const char *)(flagsp + 2);
 	}
 	else
-		name = ondisk->name;
+		name = (const char *)(flagsp + 1);
 
 	if (expand_name_field) {
 		const unsigned char *cp = (const unsigned char *)name;
@@ -1813,7 +1798,9 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
 	ce->ce_flags = flags & ~CE_NAMEMASK;
 	ce->ce_namelen = len;
 	ce->index = 0;
-	hashcpy(ce->oid.hash, ondisk->sha1);
+	hashcpy(ce->oid.hash, ondisk->data);
+	memcpy(ce->name, name, len);
+	ce->name[len] = '\0';
 
 	if (expand_name_field) {
 		if (copy_len)
@@ -2557,6 +2544,8 @@ static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
 				       struct cache_entry *ce)
 {
 	short flags;
+	const unsigned hashsz = the_hash_algo->rawsz;
+	uint16_t *flagsp = (uint16_t *)(ondisk->data + hashsz);
 
 	ondisk->ctime.sec = htonl(ce->ce_stat_data.sd_ctime.sec);
 	ondisk->mtime.sec = htonl(ce->ce_stat_data.sd_mtime.sec);
@@ -2568,15 +2557,13 @@ static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
 	ondisk->uid  = htonl(ce->ce_stat_data.sd_uid);
 	ondisk->gid  = htonl(ce->ce_stat_data.sd_gid);
 	ondisk->size = htonl(ce->ce_stat_data.sd_size);
-	hashcpy(ondisk->sha1, ce->oid.hash);
+	hashcpy(ondisk->data, ce->oid.hash);
 
 	flags = ce->ce_flags & ~CE_NAMEMASK;
 	flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce));
-	ondisk->flags = htons(flags);
+	flagsp[0] = htons(flags);
 	if (ce->ce_flags & CE_EXTENDED) {
-		struct ondisk_cache_entry_extended *ondisk2;
+		flagsp[1] = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
-		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
-		ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
 	}
 }
 
@@ -2595,10 +2582,7 @@ static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce,
 		stripped_name = 1;
 	}
 
-	if (ce->ce_flags & CE_EXTENDED)
+	size = offsetof(struct ondisk_cache_entry,data) + ondisk_data_size(ce->ce_flags, 0);
-		size = offsetof(struct ondisk_cache_entry_extended, name);
-	else
-		size = offsetof(struct ondisk_cache_entry, name);
 
 	if (!previous_name) {
 		int len = ce_namelen(ce);
@@ -2756,7 +2740,7 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 	struct cache_entry **cache = istate->cache;
 	int entries = istate->cache_nr;
 	struct stat st;
-	struct ondisk_cache_entry_extended ondisk;
+	struct ondisk_cache_entry ondisk;
 	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
 	int drop_cache_tree = istate->drop_cache_tree;
 	off_t offset;

refspec.c

@@ -72,7 +72,7 @@ static int parse_refspec(struct refspec_item *item, const char *refspec, int fet
 		/* LHS */
 		if (!*item->src)
 			; /* empty is ok; it means "HEAD" */
-		else if (llen == GIT_SHA1_HEXSZ && !get_oid_hex(item->src, &unused))
+		else if (llen == the_hash_algo->hexsz && !get_oid_hex(item->src, &unused))
 			item->exact_sha1 = 1; /* ok */
 		else if (!check_refname_format(item->src, flags))
 			; /* valid looking ref is ok */

remote-curl.c

@@ -250,7 +250,7 @@ static struct ref *parse_info_refs(struct discovery *heads)
 		if (data[i] == '\t')
 			mid = &data[i];
 		if (data[i] == '\n') {
-			if (mid - start != 40)
+			if (mid - start != the_hash_algo->hexsz)
 				die(_("%sinfo/refs not valid: is this a git repository?"),
 				    transport_anonymize_url(url.buf));
 			data[i] = 0;
@@ -1114,12 +1114,13 @@ static void parse_fetch(struct strbuf *buf)
 			const char *name;
 			struct ref *ref;
 			struct object_id old_oid;
+			const char *q;
 
-			if (get_oid_hex(p, &old_oid))
+			if (parse_oid_hex(p, &old_oid, &q))
 				die(_("protocol error: expected sha/ref, got %s'"), p);
-			if (p[GIT_SHA1_HEXSZ] == ' ')
+			if (*q == ' ')
-				name = p + GIT_SHA1_HEXSZ + 1;
+				name = q + 1;
-			else if (!p[GIT_SHA1_HEXSZ])
+			else if (!*q)
 				name = "";
 			else
 				die(_("protocol error: expected sha/ref, got %s'"), p);

sha1-file.c

@@ -189,6 +189,14 @@ int hash_algo_by_id(uint32_t format_id)
 	return GIT_HASH_UNKNOWN;
 }
 
+int hash_algo_by_length(int len)
+{
+	int i;
+	for (i = 1; i < GIT_HASH_NALGOS; i++)
+		if (len == hash_algos[i].rawsz)
+			return i;
+	return GIT_HASH_UNKNOWN;
+}
 
 /*
  * This is meant to hold a *small* number of objects that you would

submodule.c

@@ -994,7 +994,7 @@ static int submodule_needs_pushing(struct repository *r,
 		if (start_command(&cp))
 			die("Could not run 'git rev-list <commits> --not --remotes -n 1' command in submodule %s",
 					path);
-		if (strbuf_read(&buf, cp.out, 41))
+		if (strbuf_read(&buf, cp.out, the_hash_algo->hexsz + 1))
 			needs_pushing = 1;
 		finish_command(&cp);
 		close(cp.out);

t/lib-submodule-update.sh

@@ -139,7 +139,7 @@ create_lib_submodule_repo () {
 		git revert HEAD &&
 
 		git checkout -b invalid_sub1 add_sub1 &&
-		git update-index --cacheinfo 160000 0123456789012345678901234567890123456789 sub1 &&
+		git update-index --cacheinfo 160000 $(test_oid numeric) sub1 &&
 		git commit -m "Invalid sub1 commit" &&
 		git checkout -b valid_sub1 &&
 		git revert HEAD &&
@@ -196,6 +196,7 @@ test_git_directory_exists() {
 # the submodule repo if it doesn't exist and configures the most problematic
 # settings for diff.ignoreSubmodules.
 prolog () {
+	test_oid_init &&
 	(test -d submodule_update_repo || create_lib_submodule_repo) &&
 	test_config_global diff.ignoreSubmodules all &&
 	test_config diff.ignoreSubmodules all