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)
-		write_or_die(1, sha1_to_hex(sha1), GIT_SHA1_HEXSZ);
+	if (oid)
+		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))
-		return error("expected object ID, got '%s'", p + 1);
-	p += GIT_SHA1_HEXSZ;
+	if (parse_oid_hex(++p, oid1, (const char **)&p))
+		return error("expected object ID, got '%s'", p);
 	if (*p != ' ')
 		return error("expected ' ', got '%c'", *p);
-	if (get_oid_hex(++p, oid2))
-		return error("expected object ID, got '%s'", p + 1);
-	p += GIT_SHA1_HEXSZ;
+	if (parse_oid_hex(++p, oid2, (const char **)&p))
+		return error("expected object ID, got '%s'", p);
 	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;
-		else if (++forty == GIT_SHA1_HEXSZ &&
+			counter = 0;
+		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))
-			continue;  /* invalid line: does not start with SHA1 */
-		if (starts_with(sb.buf + GIT_SHA1_HEXSZ, "\tnot-for-merge\t"))
+		const char *p;
+		if (parse_oid_hex(sb.buf, &oid, &p))
+			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;
@@ -2844,23 +2844,23 @@ 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));
 	strbuf_init(&uc->ident, ident_len);
 	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;