gitweb: Refactor feed generation, make output prettier, add Atom feed

Add support for more modern Atom web feed format. Both RSS and Atom
feeds are generated by git_feed subroutine to avoid code duplication;
git_rss and git_atom are thin wrappers around git_feed. Add links to
Atom feed in HTML header and in page footer (but not in OPML; we
should use APP, Atom Publishing Proptocol instead).

Allow for feed generation for branches other than current (HEAD)
branch, and for generation of feeds for file or directory history.

Do not use "pre ${\sub_returning_scalar(...)} post" trick, but join
strings instead: "pre " . sub_returning_scalar(...) . " post".
Use href(-full=>1, ...) instead of hand-crafting gitweb urls.

Make output prettier:
* Use title similar to the title of web page
* Use project description (if exists) for description/subtitle
* Do not add anything (committer name, commit date) to feed entry title
* Wrap the commit message in <pre>
* Make file names into an unordered list
* Add links (diff, conditional blame, history) to the file list.

In addition to the above points, the attached patch emits a
Last-Changed: HTTP response header field, and doesn't compute the feed
body if the HTTP request type was HEAD. This helps keep the web server
load down for well-behaved feed readers that check if the feed needs
updating.

If browser (feed reader) sent Accept: header, and it prefers 'text/xml' type
to 'application/rss+xml' (in the case of RSS feed) or 'application/atom+xml'
(in the case of Atom feed), then use 'text/xml' as content type.

Both RSS and Atom feeds validate at http://feedvalidator.org
and at http://validator.w3.org/feed/

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

1 files changed, 210 insertions, 45 deletions

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 873950126..a32a6b79c 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -425,6 +425,7 @@ my %actions = (
 	"history" => \&git_history,
 	"log" => \&git_log,
 	"rss" => \&git_rss,
+	"atom" => \&git_atom,
 	"search" => \&git_search,
 	"search_help" => \&git_search_help,
 	"shortlog" => \&git_shortlog,
@@ -1198,10 +1199,12 @@ sub parse_date {
 	$date{'mday'} = $mday;
 	$date{'day'} = $days[$wday];
 	$date{'month'} = $months[$mon];
-	$date{'rfc2822'} = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000",
-	                   $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec;
+	$date{'rfc2822'}   = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000",
+	                     $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec;
 	$date{'mday-time'} = sprintf "%d %s %02d:%02d",
 	                     $mday, $months[$mon], $hour ,$min;
+	$date{'iso-8601'}  = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ",
+	                     1900+$year, $mon, $mday, $hour ,$min, $sec;
 
 	$tz =~ m/^([+\-][0-9][0-9])([0-9][0-9])$/;
 	my $local = $epoch + ((int $1 + ($2/60)) * 3600);
@@ -1209,9 +1212,9 @@ sub parse_date {
 	$date{'hour_local'} = $hour;
 	$date{'minute_local'} = $min;
 	$date{'tz_local'} = $tz;
-	$date{'iso-tz'} = sprintf ("%04d-%02d-%02d %02d:%02d:%02d %s",
-				   1900+$year, $mon+1, $mday,
-				   $hour, $min, $sec, $tz);
+	$date{'iso-tz'} = sprintf("%04d-%02d-%02d %02d:%02d:%02d %s",
+	                          1900+$year, $mon+1, $mday,
+	                          $hour, $min, $sec, $tz);
 	return %date;
 }
 
@@ -1672,14 +1675,17 @@ EOF
 		}
 	}
 	if (defined $project) {
-		printf('<link rel="alternate" title="%s log" '.
-		       'href="%s" type="application/rss+xml"/>'."\n",
+		printf('<link rel="alternate" title="%s log RSS feed" '.
+		       'href="%s" type="application/rss+xml" />'."\n",
 		       esc_param($project), href(action=>"rss"));
+		printf('<link rel="alternate" title="%s log Atom feed" '.
+		       'href="%s" type="application/atom+xml" />'."\n",
+		       esc_param($project), href(action=>"atom"));
 	} else {
 		printf('<link rel="alternate" title="%s projects list" '.
 		       'href="%s" type="text/plain; charset=utf-8"/>'."\n",
 		       $site_name, href(project=>undef, action=>"project_index"));
-		printf('<link rel="alternate" title="%s projects logs" '.
+		printf('<link rel="alternate" title="%s projects feeds" '.
 		       'href="%s" type="text/x-opml"/>'."\n",
 		       $site_name, href(project=>undef, action=>"opml"));
 	}
@@ -1745,7 +1751,9 @@ sub git_footer_html {
 			print "<div class=\"page_footer_text\">" . esc_html($descr) . "</div>\n";
 		}
 		print $cgi->a({-href => href(action=>"rss"),
-		              -class => "rss_logo"}, "RSS") . "\n";
+		              -class => "rss_logo"}, "RSS") . " ";
+		print $cgi->a({-href => href(action=>"atom"),
+		              -class => "rss_logo"}, "Atom") . "\n";
 	} else {
 		print $cgi->a({-href => href(project=>undef, action=>"opml"),
 		              -class => "rss_logo"}, "OPML") . " ";
@@ -4150,26 +4158,125 @@ sub git_shortlog {
 }
 
 ## ......................................................................
-## feeds (RSS, OPML)
+## feeds (RSS, Atom; OPML)
 
-sub git_rss {
-	# http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ
+sub git_feed {
+	my $format = shift || 'atom';
+	my ($have_blame) = gitweb_check_feature('blame');
+
+	# Atom: http://www.atomenabled.org/developers/syndication/
+	# RSS:  http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ
+	if ($format ne 'rss' && $format ne 'atom') {
+		die_error(undef, "Unknown web feed format");
+	}
+
+	# log/feed of current (HEAD) branch, log of given branch, history of file/directory
+	my $head = $hash || 'HEAD';
 	open my $fd, "-|", git_cmd(), "rev-list", "--max-count=150",
-		git_get_head_hash($project), "--"
+		$head, "--", (defined $file_name ? $file_name : ())
 		or die_error(undef, "Open git-rev-list failed");
 	my @revlist = map { chomp; $_ } <$fd>;
 	close $fd or die_error(undef, "Reading git-rev-list failed");
-	print $cgi->header(-type => 'text/xml', -charset => 'utf-8');
-	print <<XML;
-<?xml version="1.0" encoding="utf-8"?>
+
+	my %latest_commit;
+	my %latest_date;
+	my $content_type = "application/$format+xml";
+	if (defined $cgi->http('HTTP_ACCEPT') &&
+		 $cgi->Accept('text/xml') > $cgi->Accept($content_type)) {
+		# browser (feed reader) prefers text/xml
+		$content_type = 'text/xml';
+	}
+	if (defined($revlist[0])) {
+		%latest_commit = parse_commit($revlist[0]);
+		%latest_date   = parse_date($latest_commit{'committer_epoch'});
+		print $cgi->header(
+			-type => $content_type,
+			-charset => 'utf-8',
+			-last_modified => $latest_date{'rfc2822'});
+	} else {
+		print $cgi->header(
+			-type => $content_type,
+			-charset => 'utf-8');
+	}
+
+	# Optimization: skip generating the body if client asks only
+	# for Last-Modified date.
+	return if ($cgi->request_method() eq 'HEAD');
+
+	# header variables
+	my $title = "$site_name - $project/$action";
+	my $feed_type = 'log';
+	if (defined $hash) {
+		$title .= " - '$hash'";
+		$feed_type = 'branch log';
+		if (defined $file_name) {
+			$title .= " :: $file_name";
+			$feed_type = 'history';
+		}
+	} elsif (defined $file_name) {
+		$title .= " - $file_name";
+		$feed_type = 'history';
+	}
+	$title .= " $feed_type";
+	my $descr = git_get_project_description($project);
+	if (defined $descr) {
+		$descr = esc_html($descr);
+	} else {
+		$descr = "$project " .
+		         ($format eq 'rss' ? 'RSS' : 'Atom') .
+		         " feed";
+	}
+	my $owner = git_get_project_owner($project);
+	$owner = esc_html($owner);
+
+	#header
+	my $alt_url;
+	if (defined $file_name) {
+		$alt_url = href(-full=>1, action=>"history", hash=>$hash, file_name=>$file_name);
+	} elsif (defined $hash) {
+		$alt_url = href(-full=>1, action=>"log", hash=>$hash);
+	} else {
+		$alt_url = href(-full=>1, action=>"summary");
+	}
+	print qq!<?xml version="1.0" encoding="utf-8"?>\n!;
+	if ($format eq 'rss') {
+		print <<XML;
 <rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/">
 <channel>
-<title>$project $my_uri $my_url</title>
-<link>${\esc_html("$my_url?p=$project;a=summary")}</link>
-<description>$project log</description>
-<language>en</language>
 XML
+		print "<title>$title</title>\n" .
+		      "<link>$alt_url</link>\n" .
+		      "<description>$descr</description>\n" .
+		      "<language>en</language>\n";
+	} elsif ($format eq 'atom') {
+		print <<XML;
+<feed xmlns="http://www.w3.org/2005/Atom">
+XML
+		print "<title>$title</title>\n" .
+		      "<subtitle>$descr</subtitle>\n" .
+		      '<link rel="alternate" type="text/html" href="' .
+		      $alt_url . '" />' . "\n" .
+		      '<link rel="self" type="' . $content_type . '" href="' .
+		      $cgi->self_url() . '" />' . "\n" .
+		      "<id>" . href(-full=>1) . "</id>\n" .
+		      # use project owner for feed author
+		      "<author><name>$owner</name></author>\n";
+		if (defined $favicon) {
+			print "<icon>" . esc_url($favicon) . "</icon>\n";
+		}
+		if (defined $logo_url) {
+			# not twice as wide as tall: 72 x 27 pixels
+			print "<logo>" . esc_url($logo_url) . "</logo>\n";
+		}
+		if (! %latest_date) {
+			# dummy date to keep the feed valid until commits trickle in:
+			print "<updated>1970-01-01T00:00:00Z</updated>\n";
+		} else {
+			print "<updated>$latest_date{'iso-8601'}</updated>\n";
+		}
+	}
 
+	# contents
 	for (my $i = 0; $i <= $#revlist; $i++) {
 		my $commit = $revlist[$i];
 		my %co = parse_commit($commit);
@@ -4178,42 +4285,100 @@ XML
 			last;
 		}
 		my %cd = parse_date($co{'committer_epoch'});
+
+		# get list of changed files
 		open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts,
-			$co{'parent'}, $co{'id'}, "--"
+			$co{'parent'}, $co{'id'}, "--", (defined $file_name ? $file_name : ())
 			or next;
 		my @difftree = map { chomp; $_ } <$fd>;
 		close $fd
 			or next;
-		print "<item>\n" .
-		      "<title>" .
-		      sprintf("%d %s %02d:%02d", $cd{'mday'}, $cd{'month'}, $cd{'hour'}, $cd{'minute'}) . " - " . esc_html($co{'title'}) .
-		      "</title>\n" .
-		      "<author>" . esc_html($co{'author'}) . "</author>\n" .
-		      "<pubDate>$cd{'rfc2822'}</pubDate>\n" .
-		      "<guid isPermaLink=\"true\">" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "</guid>\n" .
-		      "<link>" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "</link>\n" .
-		      "<description>" . esc_html($co{'title'}) . "</description>\n" .
-		      "<content:encoded>" .
-		      "<![CDATA[\n";
+
+		# print element (entry, item)
+		my $co_url = href(-full=>1, action=>"commit", hash=>$commit);
+		if ($format eq 'rss') {
+			print "<item>\n" .
+			      "<title>" . esc_html($co{'title'}) . "</title>\n" .
+			      "<author>" . esc_html($co{'author'}) . "</author>\n" .
+			      "<pubDate>$cd{'rfc2822'}</pubDate>\n" .
+			      "<guid isPermaLink=\"true\">$co_url</guid>\n" .
+			      "<link>$co_url</link>\n" .
+			      "<description>" . esc_html($co{'title'}) . "</description>\n" .
+			      "<content:encoded>" .
+			      "<![CDATA[\n";
+		} elsif ($format eq 'atom') {
+			print "<entry>\n" .
+			      "<title type=\"html\">" . esc_html($co{'title'}) . "</title>\n" .
+			      "<updated>$cd{'iso-8601'}</updated>\n" .
+			      "<author><name>" . esc_html($co{'author_name'}) . "</name></author>\n" .
+			      # use committer for contributor
+			      "<contributor><name>" . esc_html($co{'committer_name'}) . "</name></contributor>\n" .
+			      "<published>$cd{'iso-8601'}</published>\n" .
+			      "<link rel=\"alternate\" type=\"text/html\" href=\"$co_url\" />\n" .
+			      "<id>$co_url</id>\n" .
+			      "<content type=\"xhtml\" xml:base=\"" . esc_url($my_url) . "\">\n" .
+			      "<div xmlns=\"http://www.w3.org/1999/xhtml\">\n";
+		}
 		my $comment = $co{'comment'};
+		print "<pre>\n";
 		foreach my $line (@$comment) {
-			$line = to_utf8($line);
-			print "$line<br/>\n";
+			$line = esc_html($line);
+			print "$line\n";
 		}
-		print "<br/>\n";
-		foreach my $line (@difftree) {
-			if (!($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/)) {
-				next;
+		print "</pre><ul>\n";
+		foreach my $difftree_line (@difftree) {
+			my %difftree = parse_difftree_raw_line($difftree_line);
+			next if !$difftree{'from_id'};
+
+			my $file = $difftree{'file'} || $difftree{'to_file'};
+
+			print "<li>" .
+			      "[" .
+			      $cgi->a({-href => href(-full=>1, action=>"blobdiff",
+			                             hash=>$difftree{'to_id'}, hash_parent=>$difftree{'from_id'},
+			                             hash_base=>$co{'id'}, hash_parent_base=>$co{'parent'},
+			                             file_name=>$file, file_parent=>$difftree{'from_file'}),
+			              -title => "diff"}, 'D');
+			if ($have_blame) {
+				print $cgi->a({-href => href(-full=>1, action=>"blame",
+				                             file_name=>$file, hash_base=>$commit),
+				              -title => "blame"}, 'B');
 			}
-			my $file = esc_path(unquote($7));
-			$file = to_utf8($file);
-			print "$file<br/>\n";
+			# if this is not a feed of a file history
+			if (!defined $file_name || $file_name ne $file) {
+				print $cgi->a({-href => href(-full=>1, action=>"history",
+				                             file_name=>$file, hash=>$commit),
+				              -title => "history"}, 'H');
+			}
+			$file = esc_path($file);
+			print "] ".
+			      "$file</li>\n";
+		}
+		if ($format eq 'rss') {
+			print "</ul>]]>\n" .
+			      "</content:encoded>\n" .
+			      "</item>\n";
+		} elsif ($format eq 'atom') {
+			print "</ul>\n</div>\n" .
+			      "</content>\n" .
+			      "</entry>\n";
 		}
-		print "]]>\n" .
-		      "</content:encoded>\n" .
-		      "</item>\n";
 	}
-	print "</channel></rss>";
+
+	# end of feed
+	if ($format eq 'rss') {
+		print "</channel>\n</rss>\n";
+	}	elsif ($format eq 'atom') {
+		print "</feed>\n";
+	}
+}
+
+sub git_rss {
+	git_feed('rss');
+}
+
+sub git_atom {
+	git_feed('atom');
 }
 
 sub git_opml {