Merge branch 'gb/gitweb-pathinfo'

* gb/gitweb-pathinfo:
  gitweb: generate parent..current URLs
  gitweb: parse parent..current syntax from PATH_INFO
  gitweb: use_pathinfo filenames start with /
  gitweb: generate project/action/hash URLs
  gitweb: parse project/action/hash_base:filename PATH_INFO

gitweb/gitweb.perl

@@ -534,24 +534,88 @@ sub evaluate_path_info {
 	return if $input_params{'action'};
 	$path_info =~ s,^\Q$project\E/*,,;
 
-	my ($refname, $pathname) = split(/:/, $path_info, 2);
+	# next, check if we have an action
+	my $action = $path_info;
+	$action =~ s,/.*$,,;
+	if (exists $actions{$action}) {
+		$path_info =~ s,^$action/*,,;
+		$input_params{'action'} = $action;
+	}
+
+	# list of actions that want hash_base instead of hash, but can have no
+	# pathname (f) parameter
+	my @wants_base = (
+		'tree',
+		'history',
+	);
+
+	# we want to catch
+	# [$hash_parent_base[:$file_parent]..]$hash_parent[:$file_name]
+	my ($parentrefname, $parentpathname, $refname, $pathname) =
+		($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?(.+?)(?::(.+))?$/);
+
+	# first, analyze the 'current' part
 	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
+		# we could use git_get_type(branch:pathname), but:
+		# - it needs $git_dir
+		# - it does a git() call
+		# - the convention of terminating directories with a slash
+		#   makes it superfluous
+		# - embedding the action in the PATH_INFO would make it even
+		#   more superfluous
 		$pathname =~ s,^/+,,;
 		if (!$pathname || substr($pathname, -1) eq "/") {
-			$input_params{'action'} = "tree";
+			$input_params{'action'} ||= "tree";
 			$pathname =~ s,/$,,;
 		} else {
-			$input_params{'action'} = "blob_plain";
+			# the default action depends on whether we had parent info
+			# or not
+			if ($parentrefname) {
+				$input_params{'action'} ||= "blobdiff_plain";
+			} else {
+				$input_params{'action'} ||= "blob_plain";
+			}
 		}
 		$input_params{'hash_base'} ||= $refname;
 		$input_params{'file_name'} ||= $pathname;
 	} elsif (defined $refname) {
-		# we got "project.git/branch"
+		# we got "branch". In this case we have to choose if we have to
-		$input_params{'action'} = "shortlog";
+		# 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 { $_ eq $input_params{'action'} } @wants_base) {
+			$input_params{'hash_base'} ||= $refname;
+		} else {
 			$input_params{'hash'} ||= $refname;
 		}
+	}
+
+	# next, handle the 'parent' part, if present
+	if (defined $parentrefname) {
+		# a missing pathspec defaults to the 'current' filename, allowing e.g.
+		# someproject/blobdiff/oldrev..newrev:/filename
+		if ($parentpathname) {
+			$parentpathname =~ s,^/+,,;
+			$parentpathname =~ s,/$,,;
+			$input_params{'file_parent'} ||= $parentpathname;
+		} else {
+			$input_params{'file_parent'} ||= $input_params{'file_name'};
+		}
+		# we assume that hash_parent_base is wanted if a path was specified,
+		# or if the action wants hash_base instead of hash
+		if (defined $input_params{'file_parent'} ||
+			grep { $_ eq $input_params{'action'} } @wants_base) {
+			$input_params{'hash_parent_base'} ||= $parentrefname;
+		} else {
+			$input_params{'hash_parent'} ||= $parentrefname;
+		}
+	}
 }
 evaluate_path_info();
 
@@ -699,14 +763,61 @@ sub href (%) {
 
 	my ($use_pathinfo) = gitweb_check_feature('pathinfo');
 	if ($use_pathinfo) {
-		# use PATH_INFO for project name
+		# try to put as many parameters as possible in PATH_INFO:
+		#   - project name
+		#   - action
+		#   - hash_parent or hash_parent_base:/file_parent
+		#   - hash or hash_base:/filename
+
+		# When the script is the root DirectoryIndex for the domain,
+		# $href here would be something like http://gitweb.example.com/
+		# Thus, we strip any trailing / from $href, to spare us double
+		# slashes in the final URL
+		$href =~ s,/$,,;
+
+		# Then add the project name, if present
 		$href .= "/".esc_url($params{'project'}) if defined $params{'project'};
 		delete $params{'project'};
 
-		# Summary just uses the project path URL
+		# Summary just uses the project path URL, any other action is
-		if (defined $params{'action'} && $params{'action'} eq 'summary') {
+		# added to the URL
+		if (defined $params{'action'}) {
+			$href .= "/".esc_url($params{'action'}) unless $params{'action'} eq 'summary';
 			delete $params{'action'};
 		}
+
+		# Next, we put hash_parent_base:/file_parent..hash_base:/file_name,
+		# stripping nonexistent or useless pieces
+		$href .= "/" if ($params{'hash_base'} || $params{'hash_parent_base'}
+			|| $params{'hash_parent'} || $params{'hash'});
+		if (defined $params{'hash_base'}) {
+			if (defined $params{'hash_parent_base'}) {
+				$href .= esc_url($params{'hash_parent_base'});
+				# skip the file_parent if it's the same as the file_name
+				delete $params{'file_parent'} if $params{'file_parent'} eq $params{'file_name'};
+				if (defined $params{'file_parent'} && $params{'file_parent'} !~ /\.\./) {
+					$href .= ":/".esc_url($params{'file_parent'});
+					delete $params{'file_parent'};
+				}
+				$href .= "..";
+				delete $params{'hash_parent'};
+				delete $params{'hash_parent_base'};
+			} elsif (defined $params{'hash_parent'}) {
+				$href .= esc_url($params{'hash_parent'}). "..";
+				delete $params{'hash_parent'};
+			}
+
+			$href .= esc_url($params{'hash_base'});
+			if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) {
+				$href .= ":/".esc_url($params{'file_name'});
+				delete $params{'file_name'};
+			}
+			delete $params{'hash'};
+			delete $params{'hash_base'};
+		} elsif (defined $params{'hash'}) {
+			$href .= esc_url($params{'hash'});
+			delete $params{'hash'};
+		}
 	}
 
 	# now encode the parameters explicitly