[PATCH 09/13] cgit: support running cgit as a standalone CGI

[Eric Wong <e@80x24.org>]

We depend on git-http-backend for smart HTTP clone support,
however; since cgit does not support smart clones natively.
WWW.pm will be able to cascade down to this as a 404 handler in
the future.
---
 MANIFEST                |  2 +
 examples/cgit.psgi      | 29 ++++++++++++++
 lib/PublicInbox/Cgit.pm | 87 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 118 insertions(+)
 create mode 100644 examples/cgit.psgi
 create mode 100644 lib/PublicInbox/Cgit.pm

diff --git a/MANIFEST b/MANIFEST
index e6316ef..150e337 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -38,6 +38,7 @@ examples/apache2_perl.conf
 examples/apache2_perl_old.conf
 examples/cgi-webrick.rb
 examples/cgit-commit-filter.lua
+examples/cgit.psgi
 examples/highlight.psgi
 examples/logrotate.conf
 examples/newswww.psgi
@@ -58,6 +59,7 @@ examples/varnish-4.vcl
 lib/PublicInbox/Address.pm
 lib/PublicInbox/Admin.pm
 lib/PublicInbox/AltId.pm
+lib/PublicInbox/Cgit.pm
 lib/PublicInbox/Config.pm
 lib/PublicInbox/ContentId.pm
 lib/PublicInbox/Daemon.pm
diff --git a/examples/cgit.psgi b/examples/cgit.psgi
new file mode 100644
index 0000000..ca93f92
--- /dev/null
+++ b/examples/cgit.psgi
@@ -0,0 +1,29 @@
+#!/usr/bin/perl -w
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# License: GPL-3.0+ <https://www.gnu.org/licenses/gpl-3.0.txt>
+#
+# PublicInbox::Cgit may be used independently of WWW.
+#
+# Usage:
+#	plackup -I lib -o 127.0.0.1 -R lib -r examples/cgit.psgi
+use strict;
+use warnings;
+use Plack::Builder;
+use PublicInbox::Cgit;
+use PublicInbox::Config;
+my $pi_config = PublicInbox::Config->new;
+my $cgit = PublicInbox::Cgit->new($pi_config);
+
+builder {
+	eval {
+		enable 'Deflater',
+			content_type => [ qw(
+				text/html
+				text/plain
+				application/atom+xml
+				)]
+	};
+	eval { enable 'ReverseProxy' };
+	enable 'Head';
+	sub { $cgit->call($_[0]) }
+}
diff --git a/lib/PublicInbox/Cgit.pm b/lib/PublicInbox/Cgit.pm
new file mode 100644
index 0000000..3d1a0d5
--- /dev/null
+++ b/lib/PublicInbox/Cgit.pm
@@ -0,0 +1,87 @@
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# wrapper for cgit(1) and git-http-backend(1) for browsing and
+# serving git code repositories.  Requires 'publicinbox.cgitrc'
+# directive to be set in the public-inbox config file.
+
+package PublicInbox::Cgit;
+use strict;
+use PublicInbox::GitHTTPBackend;
+# not bothering with Exporter for a one-off
+*r = *PublicInbox::GitHTTPBackend::r;
+*input_prepare = *PublicInbox::GitHTTPBackend::input_prepare;
+*parse_cgi_headers = *PublicInbox::GitHTTPBackend::parse_cgi_headers;
+*serve = *PublicInbox::GitHTTPBackend::serve;
+use warnings;
+use PublicInbox::Qspawn;
+
+sub new {
+	my ($class, $pi_config) = @_;
+	my $cgit_bin = $pi_config->{'publicinbox.cgitbin'} ||
+		# Debian default location:
+		'/usr/lib/cgit/cgit.cgi';
+
+	my $self = bless {
+		cmd => [ $cgit_bin ],
+		pi_config => $pi_config,
+	}, $class;
+
+	$pi_config->each_inbox(sub {}); # fill in -code_repos mapped to inboxes
+
+	# some cgit repos may not be mapped to inboxes, so ensure those exist:
+	my $code_repos = $pi_config->{-code_repos};
+	foreach my $k (keys %$pi_config) {
+		$k =~ /\Acoderepo\.(.+)\.dir\z/ or next;
+		my $dir = $pi_config->{$k};
+		$code_repos->{$1} ||= PublicInbox::Git->new($dir);
+	}
+	while (my ($nick, $repo) = each %$code_repos) {
+		$self->{"\0$nick"} = $repo;
+	}
+	$self;
+}
+
+# only what cgit cares about:
+my @PASS_ENV = qw(
+	HTTP_HOST
+	QUERY_STRING
+	REQUEST_METHOD
+	SCRIPT_NAME
+	SERVER_NAME
+	SERVER_PORT
+	HTTP_COOKIE
+	HTTP_REFERER
+	CONTENT_LENGTH
+);
+# XXX: cgit filters may care about more variables...
+
+sub call {
+	my ($self, $env) = @_;
+	my $path_info = $env->{PATH_INFO};
+
+	# handle requests without spawning cgit iff possible:
+	if ($path_info =~ m!\A/(.+?)/($PublicInbox::GitHTTPBackend::ANY)\z!ox) {
+		my ($nick, $path) = ($1, $2);
+		if (my $git = $self->{"\0$nick"}) {
+			return serve($env, $git, $path);
+		}
+	}
+
+	my $cgi_env = { PATH_INFO => $path_info };
+	foreach (@PASS_ENV) {
+		defined(my $v = $env->{$_}) or next;
+		$cgi_env->{$_} = $v;
+	}
+	$cgi_env->{'HTTPS'} = 'on' if $env->{'psgi.url_scheme'} eq 'https';
+
+	my $rdr = input_prepare($env) or return r(500);
+	my $qsp = PublicInbox::Qspawn->new($self->{cmd}, $cgi_env, $rdr);
+	$qsp->psgi_return($env, undef, sub {
+		my ($r, $bref) = @_;
+		my $res = parse_cgi_headers($r, $bref) or return; # incomplete
+		$res;
+	});
+}
+
+1;
-- 
EW