[PATCHv6 1/5] gitweb: parse project/action/hash_base:filename PATH_INFO

[Giuseppe Bilotta <giuseppe.bilotta@gmail.com>]

This patch enables gitweb to parse URLs with more information embedded
in PATH_INFO, reducing the need for CGI parameters. The typical gitweb
path is now $project/$action/$hash_base:$file_name or
$project/$action/$hash

This is mostly backwards compatible with the old-style gitweb paths,
$project/$branch[:$filename], except when it was used to access a branch
whose name matches a gitweb action.

Signed-off-by: Giuseppe Bilotta <giuseppe.bilotta@gmail.com>
---
 gitweb/gitweb.perl |   37 +++++++++++++++++++++++++++++++------
 1 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index c5254af..6d0dc26 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -534,23 +534,48 @@ sub evaluate_path_info {
 	return if $input_params{'action'};
 	$path_info =~ s,^\Q$project\E/*,,;
 
+	# next, check if we have an action
+	my $action = $path_info;
+	$action =~ s,/.*$,,;
+	if (exists $actions{$action}) {
+		$path_info =~ s,^$action/*,,;
+		$input_params{'action'} = $action;
+	}
+
+	# list of actions that want hash_base instead of hash
+	my @wants_base = (
+		'tree',
+		'history',
+	);
+
 	my ($refname, $pathname) = split(/:/, $path_info, 2);
 	if (defined $pathname) {
-		# we got "project.git/branch:filename" or "project.git/branch:dir/"
+		# we got "branch:filename" or "branch:dir/"
 		# we could use git_get_type(branch:pathname), but it needs $git_dir
 		$pathname =~ s,^/+,,;
 		if (!$pathname || substr($pathname, -1) eq "/") {
-			$input_params{'action'} = "tree";
+			$input_params{'action'} ||= "tree";
 			$pathname =~ s,/$,,;
 		} else {
-			$input_params{'action'} = "blob_plain";
+			$input_params{'action'} ||= "blob_plain";
 		}
 		$input_params{'hash_base'} ||= $refname;
 		$input_params{'file_name'} ||= $pathname;
 	} elsif (defined $refname) {
-		# we got "project.git/branch"
-		$input_params{'action'} = "shortlog";
-		$input_params{'hash'} ||= $refname;
+		# we got "branch". in this case we have to choose if we have to
+		# set hash or hash_base.
+		#
+		# Most of the actions without a pathname only want hash to be
+		# set, except for the ones specified in @wants_base that want
+		# hash_base instead. It should also be noted that hand-crafted
+		# links having 'history' as an action and no pathname or hash
+		# set will fail, but that happens regardless of PATH_INFO.
+		$input_params{'action'} ||= "shortlog";
+		if (grep {$input_params{'action'} eq $_} @wants_base) {
+			$input_params{'hash_base'} ||= $refname;
+		} else {
+			$input_params{'hash'} ||= $refname;
+		}
 	}
 }
 evaluate_path_info();
-- 
1.5.6.5