remote.c: Fix overtight refspec validation

We tightened the refspec validation code in an earlier commit ef00d15
(Tighten refspec processing, 2008-03-17) per my suggestion, but the
suggestion was misguided to begin with and it broke this usage:

    $ git push origin HEAD~12:master

The syntax of push refspecs and fetch refspecs are similar in that they
are both colon separated LHS and RHS (possibly prefixed with a + to
force), but the similarity ends there.  For example, LHS in a push refspec
can be anything that evaluates to a valid object name at runtime (except
when colon and RHS is missing, or it is a glob), while it must be a
valid-looking refname in a fetch refspec.  To validate them correctly, the
caller needs to be able to say which kind of refspecs they are.  It is
unreasonable to keep a single interface that cannot tell which kind it is
dealing with, and ask it to behave sensibly.

This commit separates the parsing of the two into different functions, and
clarifies the code to implement the parsing proper (i.e. splitting into
two parts, making sure both sides are wildcard or neither side is).

This happens to also allow pushing a commit named with the esoteric "look
for that string" syntax:

    $ git push ../test.git ':/remote.c: Fix overtight refspec:master'

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 111 insertions, 46 deletions

diff --git a/remote.c b/remote.c
index 9700a33c5..40ed24633 100644
--- a/remote.c
+++ b/remote.c
@@ -393,58 +393,123 @@ static void read_config(void)
 	alias_all_urls();
 }
 
-struct refspec *parse_ref_spec(int nr_refspec, const char **refspec)
+static struct refspec *parse_refspec_internal(int nr_refspec, const char **refspec, int fetch)
 {
 	int i;
 	int st;
 	struct refspec *rs = xcalloc(sizeof(*rs), nr_refspec);
+
 	for (i = 0; i < nr_refspec; i++) {
-		const char *sp, *ep, *gp;
-		sp = refspec[i];
-		if (*sp == '+') {
+		size_t llen, rlen;
+		int is_glob;
+		const char *lhs, *rhs;
+
+		llen = rlen = is_glob = 0;
+
+		lhs = refspec[i];
+		if (*lhs == '+') {
 			rs[i].force = 1;
-			sp++;
-		}
-		gp = strstr(sp, "/*");
-		ep = strchr(sp, ':');
-		if (gp && ep && gp > ep)
-			gp = NULL;
-		if (ep) {
-			if (ep[1]) {
-				const char *glob = strstr(ep + 1, "/*");
-				if (glob && glob[2])
-					glob = NULL;
-				if (!glob)
-					gp = NULL;
-				if (gp)
-					rs[i].dst = xstrndup(ep + 1,
-							     glob - ep - 1);
-				else
-					rs[i].dst = xstrdup(ep + 1);
-			}
-		} else {
-			ep = sp + strlen(sp);
+			lhs++;
 		}
-		if (gp && gp + 2 != ep)
-			gp = NULL;
-		if (gp) {
-			rs[i].pattern = 1;
-			ep = gp;
+
+		rhs = strrchr(lhs, ':');
+		if (rhs) {
+			rhs++;
+			rlen = strlen(rhs);
+			is_glob = (2 <= rlen && !strcmp(rhs + rlen - 2, "/*"));
+			rs[i].dst = xstrndup(rhs, rlen - is_glob * 2);
 		}
-		rs[i].src = xstrndup(sp, ep - sp);
 
-		if (*rs[i].src) {
-			st = check_ref_format(rs[i].src);
-			if (st && st != CHECK_REF_FORMAT_ONELEVEL)
-				die("Invalid refspec '%s'", refspec[i]);
+		llen = (rhs ? (rhs - lhs - 1) : strlen(lhs));
+		if (is_glob != (2 <= llen && !memcmp(lhs + llen - 2, "/*", 2)))
+			goto invalid;
+
+		if (is_glob) {
+			llen -= 2;
+			rlen -= 2;
 		}
-		if (rs[i].dst && *rs[i].dst) {
-			st = check_ref_format(rs[i].dst);
-			if (st && st != CHECK_REF_FORMAT_ONELEVEL)
-				die("Invalid refspec '%s'", refspec[i]);
+		rs[i].pattern = is_glob;
+		rs[i].src = xstrndup(lhs, llen);
+
+		if (fetch) {
+			/*
+			 * LHS
+			 * - empty is allowed; it means HEAD.
+			 * - otherwise it must be a valid looking ref.
+			 */
+			if (!*rs[i].src)
+				; /* empty is ok */
+			else {
+				st = check_ref_format(rs[i].src);
+				if (st && st != CHECK_REF_FORMAT_ONELEVEL)
+					goto invalid;
+			}
+			/*
+			 * RHS
+			 * - missing is allowed.
+			 * - empty is ok; it means not to store.
+			 * - otherwise it must be a valid looking ref.
+			 */
+			if (!rs[i].dst) {
+				; /* ok */
+			} else if (!*rs[i].dst) {
+				; /* ok */
+			} else {
+				st = check_ref_format(rs[i].dst);
+				if (st && st != CHECK_REF_FORMAT_ONELEVEL)
+					goto invalid;
+			}
+		} else {
+			/*
+			 * LHS
+			 * - empty is allowed; it means delete.
+			 * - when wildcarded, it must be a valid looking ref.
+			 * - otherwise, it must be an extended SHA-1, but
+			 *   there is no existing way to validate this.
+			 */
+			if (!*rs[i].src)
+				; /* empty is ok */
+			else if (is_glob) {
+				st = check_ref_format(rs[i].src);
+				if (st && st != CHECK_REF_FORMAT_ONELEVEL)
+					goto invalid;
+			}
+			else
+				; /* anything goes, for now */
+			/*
+			 * RHS
+			 * - missing is allowed, but LHS then must be a
+			 *   valid looking ref.
+			 * - empty is not allowed.
+			 * - otherwise it must be a valid looking ref.
+			 */
+			if (!rs[i].dst) {
+				st = check_ref_format(rs[i].src);
+				if (st && st != CHECK_REF_FORMAT_ONELEVEL)
+					goto invalid;
+			} else if (!*rs[i].dst) {
+				goto invalid;
+			} else {
+				st = check_ref_format(rs[i].dst);
+				if (st && st != CHECK_REF_FORMAT_ONELEVEL)
+					goto invalid;
+			}
 		}
 	}
 	return rs;
+
+ invalid:
+	die("Invalid refspec '%s'", refspec[i]);
+}
+
+struct refspec *parse_fetch_refspec(int nr_refspec, const char **refspec)
+{
+	return parse_refspec_internal(nr_refspec, refspec, 1);
+}
+
+struct refspec *parse_push_refspec(int nr_refspec, const char **refspec)
+{
+	return parse_refspec_internal(nr_refspec, refspec, 0);
 }
 
 static int valid_remote_nick(const char *name)
@@ -475,8 +540,8 @@ struct remote *remote_get(const char *name)
 		add_url_alias(ret, name);
 	if (!ret->url)
 		return NULL;
-	ret->fetch = parse_ref_spec(ret->fetch_refspec_nr, ret->fetch_refspec);
-	ret->push = parse_ref_spec(ret->push_refspec_nr, ret->push_refspec);
+	ret->fetch = parse_fetch_refspec(ret->fetch_refspec_nr, ret->fetch_refspec);
+	ret->push = parse_push_refspec(ret->push_refspec_nr, ret->push_refspec);
 	return ret;
 }
 
@@ -489,11 +554,11 @@ int for_each_remote(each_remote_fn fn, void *priv)
 		if (!r)
 			continue;
 		if (!r->fetch)
-			r->fetch = parse_ref_spec(r->fetch_refspec_nr,
-					r->fetch_refspec);
+			r->fetch = parse_fetch_refspec(r->fetch_refspec_nr,
+						       r->fetch_refspec);
 		if (!r->push)
-			r->push = parse_ref_spec(r->push_refspec_nr,
-					r->push_refspec);
+			r->push = parse_push_refspec(r->push_refspec_nr,
+						     r->push_refspec);
 		result = fn(r, priv);
 	}
 	return result;
@@ -824,7 +889,7 @@ int match_refs(struct ref *src, struct ref *dst, struct ref ***dst_tail,
 	       int nr_refspec, const char **refspec, int flags)
 {
 	struct refspec *rs =
-		parse_ref_spec(nr_refspec, (const char **) refspec);
+		parse_push_refspec(nr_refspec, (const char **) refspec);
 	int send_all = flags & MATCH_REFS_ALL;
 	int send_mirror = flags & MATCH_REFS_MIRROR;