[PATCH] gitweb: Improve repository verification

From

Jakub Narebski <jnareb@gmail.com>

Date

Apr 19, 2012, 16:07 UTC

Message-ID

<201204191807.32410.jnareb@gmail.com>

In-Reply-To

<201204180136.08570.jnareb@gmail.com>

Issues of note:
* is_git_directory() in gitweb is a bit stricter: it checks that
  "/objects" and "/refs" are directories, and not only 'executable'
  permission,
* validate_headref() in gitweb is a bit stricter: it checks that
  reference symlink or symref points to starts with "refs/heads/",
  and not only with "refs/",
* calls to check_head_link(), all of which were meant to check if
  given directory can be a git repository, were replaced by newly
  introduced is_git_directory().

Suggested-by: Kacper Kornet <draenog@pld-linux.org>
Signed-off-by: Jakub Narebski <jnareb@gmail.com>
---
Here is how such first step could look like...

 gitweb/gitweb.perl |   52 ++++++++++++++++++++++++++++++++++++++++++----------
 1 files changed, 42 insertions(+), 10 deletions(-)

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 098e527..767d7a5 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -621,19 +621,51 @@ sub feature_avatar {
 	return @val ? @val : @_;
 }
 
-# checking HEAD file with -e is fragile if the repository was
-# initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed
-# and then pruned.
-sub check_head_link {
-	my ($dir) = @_;
-	my $headfile = "$dir/HEAD";
-	return ((-e $headfile) ||
-		(-l $headfile && readlink($headfile) =~ /^refs\/heads\//));
+# Test if it looks like we're at a git directory.
+# We want to see:
+#
+#  - an objects/ directory,
+#  - a refs/ directory,
+#  - either a HEAD symlink or a HEAD file that is formatted as
+#    a proper "ref:", or a regular file HEAD that has a properly
+#    formatted sha1 object name.
+#
+# See is_git_directory() in setup.c
+sub is_git_directory {
+	my $dir = shift;
+	return
+		-x "$dir/objects" && -d _ &&
+		-x "$dir/refs"    && -d _ &&
+		validate_headref("$dir/HEAD");
+}
+
+# Check HEAD file, that it is either
+#
+#  - a "refs/heads/.." symlink, or
+#  - a symbolic ref to "refs/heads/..", or
+#  - a detached HEAD.
+#
+# See validate_headref() in path.c
+sub validate_headref {
+	my $headfile = shift;
+	if (-l $headfile) {
+		return readlink($headfile) =~ m!^refs/heads/!;
+
+	} elsif (-e _) {
+		open my $fh, '<', $headfile or return;
+		my $line = <$fh>;
+		close $fh or return;
+
+		return
+			$line =~ m!^ref:\s*refs/heads/! ||  # symref
+			$line =~ m!^[0-9a-z]{40}$!i;        # detached HEAD
+	}
+	return;
 }
 
 sub check_export_ok {
 	my ($dir) = @_;
-	return (check_head_link($dir) &&
+	return (is_git_directory($dir) &&
 		(!$export_ok || -e "$dir/$export_ok") &&
 		(!$export_auth_hook || $export_auth_hook->($dir)));
 }
@@ -842,7 +874,7 @@ sub evaluate_path_info {
 	# find which part of PATH_INFO is project
 	my $project = $path_info;
 	$project =~ s,/+$,,;
-	while ($project && !check_head_link("$projectroot/$project")) {
+	while ($project && !is_git_directory("$projectroot/$project")) {
 		$project =~ s,/*[^/]*$,,;
 	}
 	return unless $project;

-- 
1.7.9