alternates: accept double-quoted paths

peff · gitster · commit cf3c6352100a · 2016-12-12T15:10:43.000-08:00
We read lists of alternates from objects/info/alternates files (delimited by newline), as well as from the GIT_ALTERNATE_OBJECT_DIRECTORIES environment variable (delimited by colon or semi-colon, depending on the platform). There's no mechanism for quoting the delimiters, so it's impossible to specify an alternate path that contains a colon in the environment, or one that contains a newline in a file. We've lived with that restriction for ages because both alternates and filenames with colons are relatively rare, and it's only a problem when the two meet. But since 722ff7f (receive-pack: quarantine objects until pre-receive accepts, 2016-10-03), which builds on the alternates system, every push causes the receiver to set GIT_ALTERNATE_OBJECT_DIRECTORIES internally. It would be convenient to have some way to quote the delimiter so that we can represent arbitrary paths. The simplest thing would be an escape character before a quoted delimiter (e.g., "\:" as a literal colon). But that creates a backwards compatibility problem: any path which uses that escape character is now broken, and we've just shifted the problem. We could choose an unlikely escape character (e.g., something from the non-printable ASCII range), but that's awkward to use. Instead, let's treat names as unquoted unless they begin with a double-quote, in which case they are interpreted via our usual C-stylke quoting rules. This also breaks backwards-compatibility, but in a smaller way: it only matters if your file has a double-quote as the very _first_ character in the path (whereas an escape character is a problem anywhere in the path). It's also consistent with many other parts of git, which accept either a bare pathname or a double-quoted one, and the sender can choose to quote or not as required. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/Documentation/git.txt b/Documentation/git.txt
@@ -859,6 +859,12 @@ Git so take care if using a foreign front-end.
 	specifies a ":" separated (on Windows ";" separated) list
 	of Git object directories which can be used to search for Git
 	objects. New objects will not be written to these directories.
++
+	Entries that begin with `"` (double-quote) will be interpreted
+	as C-style quoted paths, removing leading and trailing
+	double-quotes and respecting backslash escapes. E.g., the value
+	`"path-with-\"-and-:-in-it":vanilla-path` has two paths:
+	`path-with-"-and-:-in-it` and `vanilla-path`.
 
 `GIT_DIR`::
 	If the `GIT_DIR` environment variable is set then it
diff --git a/sha1_file.c b/sha1_file.c
@@ -26,6 +26,7 @@
 #include "mru.h"
 #include "list.h"
 #include "mergesort.h"
+#include "quote.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -329,13 +330,40 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base,
 	return 0;
 }
 
+static const char *parse_alt_odb_entry(const char *string,
+				       int sep,
+				       struct strbuf *out)
+{
+	const char *end;
+
+	strbuf_reset(out);
+
+	if (*string == '#') {
+		/* comment; consume up to next separator */
+		end = strchrnul(string, sep);
+	} else if (*string == '"' && !unquote_c_style(out, string, &end)) {
+		/*
+		 * quoted path; unquote_c_style has copied the
+		 * data for us and set "end". Broken quoting (e.g.,
+		 * an entry that doesn't end with a quote) falls
+		 * back to the unquoted case below.
+		 */
+	} else {
+		/* normal, unquoted path */
+		end = strchrnul(string, sep);
+		strbuf_add(out, string, end - string);
+	}
+
+	if (*end)
+		end++;
+	return end;
+}
+
 static void link_alt_odb_entries(const char *alt, int len, int sep,
 				 const char *relative_base, int depth)
 {
-	struct string_list entries = STRING_LIST_INIT_NODUP;
-	char *alt_copy;
-	int i;
 	struct strbuf objdirbuf = STRBUF_INIT;
+	struct strbuf entry = STRBUF_INIT;
 
 	if (depth > 5) {
 		error("%s: ignoring alternate object stores, nesting too deep.",
@@ -348,16 +376,13 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
 		die("unable to normalize object directory: %s",
 		    objdirbuf.buf);
 
-	alt_copy = xmemdupz(alt, len);
-	string_list_split_in_place(&entries, alt_copy, sep, -1);
-	for (i = 0; i < entries.nr; i++) {
-		const char *entry = entries.items[i].string;
-		if (entry[0] == '\0' || entry[0] == '#')
+	while (*alt) {
+		alt = parse_alt_odb_entry(alt, sep, &entry);
+		if (!entry.len)
 			continue;
-		link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
+		link_alt_odb_entry(entry.buf, relative_base, depth, objdirbuf.buf);
 	}
-	string_list_clear(&entries, 0);
-	free(alt_copy);
+	strbuf_release(&entry);
 	strbuf_release(&objdirbuf);
 }
 
diff --git a/t/t5615-alternate-env.sh b/t/t5615-alternate-env.sh
@@ -68,4 +68,22 @@ test_expect_success 'access alternate via relative path (subdir)' '
 	EOF
 '
 
+# set variables outside test to avoid quote insanity; the \057 is '/',
+# which doesn't need quoting, but just confirms that de-quoting
+# is working.
+quoted='"one.git\057objects"'
+unquoted='two.git/objects'
+test_expect_success 'mix of quoted and unquoted alternates' '
+	check_obj "$quoted:$unquoted" <<-EOF
+	$one blob
+	$two blob
+'
+
+test_expect_success 'broken quoting falls back to interpreting raw' '
+	mv one.git \"one.git &&
+	check_obj \"one.git/objects <<-EOF
+	$one blob
+	EOF
+'
+
 test_done
