gitweb: Split validate_input into validate_pathname and validate_refname

Split validate_input subroutine into validate_pathname which is used
for $project, $file_name and $file_parent parameters, and
validate_refname which is used for $hash, $hash_base, $hash_parent and
$hash_parent_base parameters.  Reintroduce validation of $file_name
and $file_parent parameters, removed in a2f3db2f

validate_pathname in addition to what validate_input did checks also
for doubled slashes and NUL character. It does not check if input is
textual hash, and does not check if all characters are from the
following set: [a-zA-Z0-9_\x80-\xff\ \t\.\/\-\+\#\~\%].

validate_refname first check if the input is textual hash, then checks
if it is valid pathname, then checks for invalid characters (according
to git-check-ref-format manpage). It does not check if all charactes
are from the [a-zA-Z0-9_\x80-\xff\ \t\.\/\-\+\#\~\%] set.

We do not have to validate pathnames we got from git.

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index eaa42b93cdacf8cc4b6e0b014bec7c94099dccbb..c51313581e3e2bf67d31b27a026cd29ed7ca54c1 100755 (executable)
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -200,9 +200,10 @@ sub feature_pickaxe {
        }
 }
 
+# parameters which are pathnames
 our $project = $cgi->param('p');
 if (defined $project) {
-       if (!validate_input($project) ||
+       if (!validate_pathname($project) ||
            !(-d "$projectroot/$project") ||
            !(-e "$projectroot/$project/HEAD") ||
            ($export_ok && !(-e "$projectroot/$project/$export_ok")) ||
@@ -212,38 +213,50 @@ sub feature_pickaxe {
        }
 }
 
-# We have to handle those containing any characters:
 our $file_name = $cgi->param('f');
+if (defined $file_name) {
+       if (!validate_pathname($file_name)) {
+               die_error(undef, "Invalid file parameter");
+       }
+}
+
 our $file_parent = $cgi->param('fp');
+if (defined $file_parent) {
+       if (!validate_pathname($file_parent)) {
+               die_error(undef, "Invalid file parent parameter");
+       }
+}
 
+# parameters which are refnames
 our $hash = $cgi->param('h');
 if (defined $hash) {
-       if (!validate_input($hash)) {
+       if (!validate_refname($hash)) {
                die_error(undef, "Invalid hash parameter");
        }
 }
 
 our $hash_parent = $cgi->param('hp');
 if (defined $hash_parent) {
-       if (!validate_input($hash_parent)) {
+       if (!validate_refname($hash_parent)) {
                die_error(undef, "Invalid hash parent parameter");
        }
 }
 
 our $hash_base = $cgi->param('hb');
 if (defined $hash_base) {
-       if (!validate_input($hash_base)) {
+       if (!validate_refname($hash_base)) {
                die_error(undef, "Invalid hash base parameter");
        }
 }
 
 our $hash_parent_base = $cgi->param('hpb');
 if (defined $hash_parent_base) {
-       if (!validate_input($hash_parent_base)) {
+       if (!validate_refname($hash_parent_base)) {
                die_error(undef, "Invalid hash parent base parameter");
        }
 }
 
+# other parameters
 our $page = $cgi->param('pg');
 if (defined $page) {
        if ($page =~ m/[^0-9]/) {
@@ -273,7 +286,7 @@ sub evaluate_path_info {
                $project =~ s,/*[^/]*$,,;
        }
        # validate project
-       $project = validate_input($project);
+       $project = validate_pathname($project);
        if (!$project ||
            ($export_ok && !-e "$projectroot/$project/$export_ok") ||
            ($strict_export && !project_in_list($project))) {
@@ -294,12 +307,12 @@ sub evaluate_path_info {
                } else {
                        $action  ||= "blob_plain";
                }
-               $hash_base ||= validate_input($refname);
-               $file_name ||= $pathname;
+               $hash_base ||= validate_refname($refname);
+               $file_name ||= validate_pathname($pathname);
        } elsif (defined $refname) {
                # we got "project.git/branch"
                $action ||= "shortlog";
-               $hash   ||= validate_input($refname);
+               $hash   ||= validate_refname($refname);
        }
 }
 evaluate_path_info();
@@ -387,16 +400,34 @@ (%)
 ## ======================================================================
 ## validation, quoting/unquoting and escaping
 
-sub validate_input {
-       my $input = shift;
+sub validate_pathname {
+       my $input = shift || return undef;
 
-       if ($input =~ m/^[0-9a-fA-F]{40}$/) {
-               return $input;
+       # no '.' or '..' as elements of path, i.e. no '.' nor '..'
+       # at the beginning, at the end, and between slashes.
+       # also this catches doubled slashes
+       if ($input =~ m!(^|/)(|\.|\.\.)(/|$)!) {
+               return undef;
        }
-       if ($input =~ m/(^|\/)(|\.|\.\.)($|\/)/) {
+       # no null characters
+       if ($input =~ m!\0!) {
                return undef;
        }
-       if ($input =~ m/[^a-zA-Z0-9_\x80-\xff\ \t\.\/\-\+\#\~\%]/) {
+       return $input;
+}
+
+sub validate_refname {
+       my $input = shift || return undef;
+
+       # textual hashes are O.K.
+       if ($input =~ m/^[0-9a-fA-F]{40}$/) {
+               return $input;
+       }
+       # it must be correct pathname
+       $input = validate_pathname($input)
+               or return undef;
+       # restrictions on ref name according to git-check-ref-format
+       if ($input =~ m!(/\.|\.\.|[\000-\040\177 ~^:?*\[]|/$)!) {
                return undef;
        }
        return $input;