Merge branch 'dt/pre-refs-backend'

Code restructuring around the "refs" area to prepare for pluggable
refs backends.

* dt/pre-refs-backend: (24 commits)
  refs: on symref reflog expire, lock symref not referrent
  refs: move resolve_ref_unsafe into common code
  show_head_ref(): check the result of resolve_ref_namespace()
  check_aliased_update(): check that dst_name is non-NULL
  checkout_paths(): remove unneeded flag variable
  cmd_merge(): remove unneeded flag variable
  fsck_head_link(): remove unneeded flag variable
  read_raw_ref(): change flags parameter to unsigned int
  files-backend: inline resolve_ref_1() into resolve_ref_unsafe()
  read_raw_ref(): manage own scratch space
  files-backend: break out ref reading
  resolve_ref_1(): eliminate local variable "bad_name"
  resolve_ref_1(): reorder code
  resolve_ref_1(): eliminate local variable
  resolve_ref_unsafe(): ensure flags is always set
  resolve_ref_unsafe(): use for loop to count up to MAXDEPTH
  resolve_missing_loose_ref(): simplify semantics
  t1430: improve test coverage of deletion of badly-named refs
  t1430: test for-each-ref in the presence of badly-named refs
  t1430: don't rely on symbolic-ref for creating broken symrefs
  ...

2 files changed, 153 insertions, 268 deletions

diff --git a/refs/files-backend.c b/refs/files-backend.c
index ea78ce9d90..1f38076411 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -513,9 +513,6 @@ static void sort_ref_dir(struct ref_dir *dir)
 	dir->sorted = dir->nr = i;
 }
 
-/* Include broken references in a do_for_each_ref*() iteration: */
-#define DO_FOR_EACH_INCLUDE_BROKEN 0x01
-
 /*
  * Return true iff the reference described by entry can be resolved to
  * an object in the database.  Emit a warning if the referred-to
@@ -1272,8 +1269,6 @@ static struct ref_dir *get_loose_refs(struct ref_cache *refs)
 	return get_ref_dir(refs->loose);
 }
 
-/* We allow "recursive" symbolic refs. Only within reason, though */
-#define MAXDEPTH 5
 #define MAXREFLEN (1024)
 
 /*
@@ -1303,7 +1298,7 @@ static int resolve_gitlink_ref_recursive(struct ref_cache *refs,
 	char buffer[128], *p;
 	char *path;
 
-	if (recursion > MAXDEPTH || strlen(refname) > MAXREFLEN)
+	if (recursion > SYMREF_MAXDEPTH || strlen(refname) > MAXREFLEN)
 		return -1;
 	path = *refs->name
 		? git_pathdup_submodule(refs->name, "%s", refname)
@@ -1371,13 +1366,11 @@ static struct ref_entry *get_packed_ref(const char *refname)
 }
 
 /*
- * A loose ref file doesn't exist; check for a packed ref.  The
- * options are forwarded from resolve_safe_unsafe().
+ * A loose ref file doesn't exist; check for a packed ref.
  */
 static int resolve_missing_loose_ref(const char *refname,
-				     int resolve_flags,
 				     unsigned char *sha1,
-				     int *flags)
+				     unsigned int *flags)
 {
 	struct ref_entry *entry;
 
@@ -1388,205 +1381,158 @@ static int resolve_missing_loose_ref(const char *refname,
 	entry = get_packed_ref(refname);
 	if (entry) {
 		hashcpy(sha1, entry->u.value.oid.hash);
-		if (flags)
-			*flags |= REF_ISPACKED;
-		return 0;
-	}
-	/* The reference is not a packed reference, either. */
-	if (resolve_flags & RESOLVE_REF_READING) {
-		errno = ENOENT;
-		return -1;
-	} else {
-		hashclr(sha1);
+		*flags |= REF_ISPACKED;
 		return 0;
 	}
+	/* refname is not a packed reference. */
+	return -1;
 }
 
-/* This function needs to return a meaningful errno on failure */
-static const char *resolve_ref_1(const char *refname,
-				 int resolve_flags,
-				 unsigned char *sha1,
-				 int *flags,
-				 struct strbuf *sb_refname,
-				 struct strbuf *sb_path,
-				 struct strbuf *sb_contents)
+/*
+ * Read a raw ref from the filesystem or packed refs file.
+ *
+ * If the ref is a sha1, fill in sha1 and return 0.
+ *
+ * If the ref is symbolic, fill in *symref with the referrent
+ * (e.g. "refs/heads/master") and return 0.  The caller is responsible
+ * for validating the referrent.  Set REF_ISSYMREF in flags.
+ *
+ * If the ref doesn't exist, set errno to ENOENT and return -1.
+ *
+ * If the ref exists but is neither a symbolic ref nor a sha1, it is
+ * broken. Set REF_ISBROKEN in flags, set errno to EINVAL, and return
+ * -1.
+ *
+ * If there is another error reading the ref, set errno appropriately and
+ * return -1.
+ *
+ * Backend-specific flags might be set in flags as well, regardless of
+ * outcome.
+ *
+ * sb_path is workspace: the caller should allocate and free it.
+ *
+ * It is OK for refname to point into symref. In this case:
+ * - if the function succeeds with REF_ISSYMREF, symref will be
+ *   overwritten and the memory pointed to by refname might be changed
+ *   or even freed.
+ * - in all other cases, symref will be untouched, and therefore
+ *   refname will still be valid and unchanged.
+ */
+int read_raw_ref(const char *refname, unsigned char *sha1,
+		 struct strbuf *symref, unsigned int *flags)
 {
-	int depth = MAXDEPTH;
-	int bad_name = 0;
+	struct strbuf sb_contents = STRBUF_INIT;
+	struct strbuf sb_path = STRBUF_INIT;
+	const char *path;
+	const char *buf;
+	struct stat st;
+	int fd;
+	int ret = -1;
+	int save_errno;
 
-	if (flags)
-		*flags = 0;
+	strbuf_reset(&sb_path);
+	strbuf_git_path(&sb_path, "%s", refname);
+	path = sb_path.buf;
 
-	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
-		if (flags)
-			*flags |= REF_BAD_NAME;
+stat_ref:
+	/*
+	 * We might have to loop back here to avoid a race
+	 * condition: first we lstat() the file, then we try
+	 * to read it as a link or as a file.  But if somebody
+	 * changes the type of the file (file <-> directory
+	 * <-> symlink) between the lstat() and reading, then
+	 * we don't want to report that as an error but rather
+	 * try again starting with the lstat().
+	 */
 
-		if (!(resolve_flags & RESOLVE_REF_ALLOW_BAD_NAME) ||
-		    !refname_is_safe(refname)) {
-			errno = EINVAL;
-			return NULL;
+	if (lstat(path, &st) < 0) {
+		if (errno != ENOENT)
+			goto out;
+		if (resolve_missing_loose_ref(refname, sha1, flags)) {
+			errno = ENOENT;
+			goto out;
 		}
-		/*
-		 * dwim_ref() uses REF_ISBROKEN to distinguish between
-		 * missing refs and refs that were present but invalid,
-		 * to complain about the latter to stderr.
-		 *
-		 * We don't know whether the ref exists, so don't set
-		 * REF_ISBROKEN yet.
-		 */
-		bad_name = 1;
+		ret = 0;
+		goto out;
 	}
-	for (;;) {
-		const char *path;
-		struct stat st;
-		char *buf;
-		int fd;
-
-		if (--depth < 0) {
-			errno = ELOOP;
-			return NULL;
-		}
-
-		strbuf_reset(sb_path);
-		strbuf_git_path(sb_path, "%s", refname);
-		path = sb_path->buf;
-
-		/*
-		 * We might have to loop back here to avoid a race
-		 * condition: first we lstat() the file, then we try
-		 * to read it as a link or as a file.  But if somebody
-		 * changes the type of the file (file <-> directory
-		 * <-> symlink) between the lstat() and reading, then
-		 * we don't want to report that as an error but rather
-		 * try again starting with the lstat().
-		 */
-	stat_ref:
-		if (lstat(path, &st) < 0) {
-			if (errno != ENOENT)
-				return NULL;
-			if (resolve_missing_loose_ref(refname, resolve_flags,
-						      sha1, flags))
-				return NULL;
-			if (bad_name) {
-				hashclr(sha1);
-				if (flags)
-					*flags |= REF_ISBROKEN;
-			}
-			return refname;
-		}
-
-		/* Follow "normalized" - ie "refs/.." symlinks by hand */
-		if (S_ISLNK(st.st_mode)) {
-			strbuf_reset(sb_contents);
-			if (strbuf_readlink(sb_contents, path, 0) < 0) {
-				if (errno == ENOENT || errno == EINVAL)
-					/* inconsistent with lstat; retry */
-					goto stat_ref;
-				else
-					return NULL;
-			}
-			if (starts_with(sb_contents->buf, "refs/") &&
-			    !check_refname_format(sb_contents->buf, 0)) {
-				strbuf_swap(sb_refname, sb_contents);
-				refname = sb_refname->buf;
-				if (flags)
-					*flags |= REF_ISSYMREF;
-				if (resolve_flags & RESOLVE_REF_NO_RECURSE) {
-					hashclr(sha1);
-					return refname;
-				}
-				continue;
-			}
-		}
 
-		/* Is it a directory? */
-		if (S_ISDIR(st.st_mode)) {
-			errno = EISDIR;
-			return NULL;
-		}
-
-		/*
-		 * Anything else, just open it and try to use it as
-		 * a ref
-		 */
-		fd = open(path, O_RDONLY);
-		if (fd < 0) {
-			if (errno == ENOENT)
+	/* Follow "normalized" - ie "refs/.." symlinks by hand */
+	if (S_ISLNK(st.st_mode)) {
+		strbuf_reset(&sb_contents);
+		if (strbuf_readlink(&sb_contents, path, 0) < 0) {
+			if (errno == ENOENT || errno == EINVAL)
 				/* inconsistent with lstat; retry */
 				goto stat_ref;
 			else
-				return NULL;
+				goto out;
 		}
-		strbuf_reset(sb_contents);
-		if (strbuf_read(sb_contents, fd, 256) < 0) {
-			int save_errno = errno;
-			close(fd);
-			errno = save_errno;
-			return NULL;
+		if (starts_with(sb_contents.buf, "refs/") &&
+		    !check_refname_format(sb_contents.buf, 0)) {
+			strbuf_swap(&sb_contents, symref);
+			*flags |= REF_ISSYMREF;
+			ret = 0;
+			goto out;
 		}
-		close(fd);
-		strbuf_rtrim(sb_contents);
+	}
 
-		/*
-		 * Is it a symbolic ref?
-		 */
-		if (!starts_with(sb_contents->buf, "ref:")) {
-			/*
-			 * Please note that FETCH_HEAD has a second
-			 * line containing other data.
-			 */
-			if (get_sha1_hex(sb_contents->buf, sha1) ||
-			    (sb_contents->buf[40] != '\0' && !isspace(sb_contents->buf[40]))) {
-				if (flags)
-					*flags |= REF_ISBROKEN;
-				errno = EINVAL;
-				return NULL;
-			}
-			if (bad_name) {
-				hashclr(sha1);
-				if (flags)
-					*flags |= REF_ISBROKEN;
-			}
-			return refname;
-		}
-		if (flags)
-			*flags |= REF_ISSYMREF;
-		buf = sb_contents->buf + 4;
+	/* Is it a directory? */
+	if (S_ISDIR(st.st_mode)) {
+		errno = EISDIR;
+		goto out;
+	}
+
+	/*
+	 * Anything else, just open it and try to use it as
+	 * a ref
+	 */
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		if (errno == ENOENT)
+			/* inconsistent with lstat; retry */
+			goto stat_ref;
+		else
+			goto out;
+	}
+	strbuf_reset(&sb_contents);
+	if (strbuf_read(&sb_contents, fd, 256) < 0) {
+		int save_errno = errno;
+		close(fd);
+		errno = save_errno;
+		goto out;
+	}
+	close(fd);
+	strbuf_rtrim(&sb_contents);
+	buf = sb_contents.buf;
+	if (starts_with(buf, "ref:")) {
+		buf += 4;
 		while (isspace(*buf))
 			buf++;
-		strbuf_reset(sb_refname);
-		strbuf_addstr(sb_refname, buf);
-		refname = sb_refname->buf;
-		if (resolve_flags & RESOLVE_REF_NO_RECURSE) {
-			hashclr(sha1);
-			return refname;
-		}
-		if (check_refname_format(buf, REFNAME_ALLOW_ONELEVEL)) {
-			if (flags)
-				*flags |= REF_ISBROKEN;
-
-			if (!(resolve_flags & RESOLVE_REF_ALLOW_BAD_NAME) ||
-			    !refname_is_safe(buf)) {
-				errno = EINVAL;
-				return NULL;
-			}
-			bad_name = 1;
-		}
+
+		strbuf_reset(symref);
+		strbuf_addstr(symref, buf);
+		*flags |= REF_ISSYMREF;
+		ret = 0;
+		goto out;
 	}
-}
 
-const char *resolve_ref_unsafe(const char *refname, int resolve_flags,
-			       unsigned char *sha1, int *flags)
-{
-	static struct strbuf sb_refname = STRBUF_INIT;
-	struct strbuf sb_contents = STRBUF_INIT;
-	struct strbuf sb_path = STRBUF_INIT;
-	const char *ret;
+	/*
+	 * Please note that FETCH_HEAD has additional
+	 * data after the sha.
+	 */
+	if (get_sha1_hex(buf, sha1) ||
+	    (buf[40] != '\0' && !isspace(buf[40]))) {
+		*flags |= REF_ISBROKEN;
+		errno = EINVAL;
+		goto out;
+	}
+
+	ret = 0;
 
-	ret = resolve_ref_1(refname, resolve_flags, sha1, flags,
-			    &sb_refname, &sb_path, &sb_contents);
+out:
+	save_errno = errno;
 	strbuf_release(&sb_path);
 	strbuf_release(&sb_contents);
+	errno = save_errno;
 	return ret;
 }
 
@@ -1727,10 +1673,13 @@ static int do_for_each_entry(struct ref_cache *refs, const char *base,
  * value, stop the iteration and return that value; otherwise, return
  * 0.
  */
-static int do_for_each_ref(struct ref_cache *refs, const char *base,
-			   each_ref_fn fn, int trim, int flags, void *cb_data)
+int do_for_each_ref(const char *submodule, const char *base,
+		    each_ref_fn fn, int trim, int flags, void *cb_data)
 {
 	struct ref_entry_cb data;
+	struct ref_cache *refs;
+
+	refs = get_ref_cache(submodule);
 	data.base = base;
 	data.trim = trim;
 	data.flags = flags;
@@ -1745,86 +1694,6 @@ static int do_for_each_ref(struct ref_cache *refs, const char *base,
 	return do_for_each_entry(refs, base, do_one_ref, &data);
 }
 
-static int do_head_ref(const char *submodule, each_ref_fn fn, void *cb_data)
-{
-	struct object_id oid;
-	int flag;
-
-	if (submodule) {
-		if (resolve_gitlink_ref(submodule, "HEAD", oid.hash) == 0)
-			return fn("HEAD", &oid, 0, cb_data);
-
-		return 0;
-	}
-
-	if (!read_ref_full("HEAD", RESOLVE_REF_READING, oid.hash, &flag))
-		return fn("HEAD", &oid, flag, cb_data);
-
-	return 0;
-}
-
-int head_ref(each_ref_fn fn, void *cb_data)
-{
-	return do_head_ref(NULL, fn, cb_data);
-}
-
-int head_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
-{
-	return do_head_ref(submodule, fn, cb_data);
-}
-
-int for_each_ref(each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(&ref_cache, "", fn, 0, 0, cb_data);
-}
-
-int for_each_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(get_ref_cache(submodule), "", fn, 0, 0, cb_data);
-}
-
-int for_each_ref_in(const char *prefix, each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(&ref_cache, prefix, fn, strlen(prefix), 0, cb_data);
-}
-
-int for_each_fullref_in(const char *prefix, each_ref_fn fn, void *cb_data, unsigned int broken)
-{
-	unsigned int flag = 0;
-
-	if (broken)
-		flag = DO_FOR_EACH_INCLUDE_BROKEN;
-	return do_for_each_ref(&ref_cache, prefix, fn, 0, flag, cb_data);
-}
-
-int for_each_ref_in_submodule(const char *submodule, const char *prefix,
-		each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(get_ref_cache(submodule), prefix, fn, strlen(prefix), 0, cb_data);
-}
-
-int for_each_replace_ref(each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(&ref_cache, git_replace_ref_base, fn,
-			       strlen(git_replace_ref_base), 0, cb_data);
-}
-
-int for_each_namespaced_ref(each_ref_fn fn, void *cb_data)
-{
-	struct strbuf buf = STRBUF_INIT;
-	int ret;
-	strbuf_addf(&buf, "%srefs/", get_git_namespace());
-	ret = do_for_each_ref(&ref_cache, buf.buf, fn, 0, 0, cb_data);
-	strbuf_release(&buf);
-	return ret;
-}
-
-int for_each_rawref(each_ref_fn fn, void *cb_data)
-{
-	return do_for_each_ref(&ref_cache, "", fn, 0,
-			       DO_FOR_EACH_INCLUDE_BROKEN, cb_data);
-}
-
 static void unlock_ref(struct ref_lock *lock)
 {
 	/* Do not free lock->lk -- atexit() still looks at them */
@@ -3481,7 +3350,8 @@ int reflog_expire(const char *refname, const unsigned char *sha1,
 	 * reference itself, plus we might need to update the
 	 * reference if --updateref was specified:
 	 */
-	lock = lock_ref_sha1_basic(refname, sha1, NULL, NULL, 0, &type, &err);
+	lock = lock_ref_sha1_basic(refname, sha1, NULL, NULL, REF_NODEREF,
+				   &type, &err);
 	if (!lock) {
 		error("cannot lock ref '%s': %s", refname, err.buf);
 		strbuf_release(&err);
diff --git a/refs/refs-internal.h b/refs/refs-internal.h
index c7dded35f4..3a4f634cb4 100644
--- a/refs/refs-internal.h
+++ b/refs/refs-internal.h
@@ -197,4 +197,19 @@ const char *find_descendant_ref(const char *dirname,
 
 int rename_ref_available(const char *oldname, const char *newname);
 
+/* We allow "recursive" symbolic refs. Only within reason, though */
+#define SYMREF_MAXDEPTH 5
+
+/* Include broken references in a do_for_each_ref*() iteration: */
+#define DO_FOR_EACH_INCLUDE_BROKEN 0x01
+
+/*
+ * The common backend for the for_each_*ref* functions
+ */
+int do_for_each_ref(const char *submodule, const char *base,
+		    each_ref_fn fn, int trim, int flags, void *cb_data);
+
+int read_raw_ref(const char *refname, unsigned char *sha1,
+		 struct strbuf *symref, unsigned int *flags);
+
 #endif /* REFS_REFS_INTERNAL_H */