X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWwwListing.pm;h=12b0d9ad5f3f0bedae69919f3a9a4b0de557ff1f;hb=de9648ca847cf032aab6da9cac1217bf9cca9c90;hp=690976acdc9ae2a6f9afb811c69e3d3fec041c35;hpb=0b3e19584c90d958a723ac2d3dec3f84f5513688;p=public-inbox.git diff --git a/lib/PublicInbox/WwwListing.pm b/lib/PublicInbox/WwwListing.pm index 690976ac..12b0d9ad 100644 --- a/lib/PublicInbox/WwwListing.pm +++ b/lib/PublicInbox/WwwListing.pm @@ -1,52 +1,55 @@ -# Copyright (C) 2019 all contributors +# Copyright (C) 2019-2020 all contributors # License: AGPL-3.0+ # Provide an HTTP-accessible listing of inboxes. # Used by PublicInbox::WWW package PublicInbox::WwwListing; use strict; -use warnings; -use PublicInbox::Hval qw(ascii_html); +use PublicInbox::Hval qw(ascii_html prurl fmt_ts); use PublicInbox::Linkify; -use PublicInbox::View; -use bytes (); -use HTTP::Date qw(time2str); -require Digest::SHA; -require File::Spec; -{ no warnings 'once'; *try_cat = *PublicInbox::Inbox::try_cat }; +use PublicInbox::GzipFilter qw(gzf_maybe); +use PublicInbox::ManifestJsGz; +use bytes (); # bytes::length + +sub list_all_i { + my ($ibx, $arg) = @_; + my ($list, $hide_key) = @$arg; + push @$list, $ibx unless $ibx->{-hide}->{$hide_key}; +} sub list_all ($$$) { my ($self, $env, $hide_key) = @_; - my @list; - $self->{pi_config}->each_inbox(sub { - my ($ibx) = @_; - push @list, $ibx unless $ibx->{-hide}->{$hide_key}; - }); - \@list; + my $list = []; + $self->{pi_config}->each_inbox(\&list_all_i, [ $list, $hide_key ]); + $list; +} + +sub list_match_domain_i { + my ($ibx, $arg) = @_; + my ($list, $hide_key, $re) = @$arg; + if (!$ibx->{-hide}->{$hide_key} && grep(/$re/, @{$ibx->{url}})) { + push @$list, $ibx; + } } sub list_match_domain ($$$) { my ($self, $env, $hide_key) = @_; - my @list; + my $list = []; my $host = $env->{HTTP_HOST} // $env->{SERVER_NAME}; $host =~ s/:[0-9]+\z//; - my $re = qr!\A(?:https?:)?//\Q$host\E(?::[0-9]+)?/!i; - $self->{pi_config}->each_inbox(sub { - my ($ibx) = @_; - if (!$ibx->{-hide}->{$hide_key} && $ibx->{url} =~ $re) { - push @list, $ibx; - } - }); - \@list; + my $arg = [ $list, $hide_key, + qr!\A(?:https?:)?//\Q$host\E(?::[0-9]+)?/!i ]; + $self->{pi_config}->each_inbox(\&list_match_domain_i, $arg); + $list; } sub list_404 ($$) { [] } # TODO: +cgit my %VALID = ( - all => *list_all, - 'match=domain' => *list_match_domain, - 404 => *list_404, + all => \&list_all, + 'match=domain' => \&list_match_domain, + 404 => \&list_404, ); sub set_cb ($$$) { @@ -75,144 +78,47 @@ sub new { sub ibx_entry { my ($mtime, $ibx, $env) = @_; - my $ts = PublicInbox::View::fmt_ts($mtime); - my $url = PublicInbox::Hval::prurl($env, $ibx->{url}); + my $ts = fmt_ts($mtime); + my $url = prurl($env, $ibx->{url}); my $tmp = <<""; * $ts - $url ${\$ibx->description} - if (defined(my $info_url = $ibx->{info_url})) { - $tmp .= "\n$info_url"; + if (defined(my $info_url = $ibx->{infourl})) { + $tmp .= ' ' . prurl($env, $info_url) . "\n"; } $tmp; } sub html ($$) { my ($env, $list) = @_; - my $title = 'public-inbox'; - my $out = ''; + my $h = [ 'Content-Type', 'text/html; charset=UTF-8', + 'Content-Length', undef ]; + my $gzf = gzf_maybe($h, $env); + $gzf->zmore('' . + 'public-inbox listing' . + '
');
 	my $code = 404;
 	if (@$list) {
-		$title .= ' - listing';
 		$code = 200;
-
-		# Swartzian transform since ->modified is expensive
+		# Schwartzian transform since Inbox->modified is expensive
 		@$list = sort {
 			$b->[0] <=> $a->[0]
 		} map { [ $_->modified, $_ ] } @$list;
 
 		my $tmp = join("\n", map { ibx_entry(@$_, $env) } @$list);
 		my $l = PublicInbox::Linkify->new;
-		$l->linkify_1($tmp);
-		$out = '
'.$l->linkify_2(ascii_html($tmp)).'
';
+		$gzf->zmore($l->to_html($tmp));
+	} else {
+		$gzf->zmore('no inboxes, yet');
 	}
-	$out = "$title" . $out;
-	$out .= '
'. PublicInbox::WwwStream::code_footer($env) .
-		'
';
-
-	my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
+	my $out = $gzf->zflush('
'.
+				PublicInbox::WwwStream::code_footer($env) .
+				'
'); + $h->[3] = bytes::length($out); [ $code, $h, [ $out ] ]; } -my $json; -sub _json () { - for my $mod (qw(JSON::MaybeXS JSON JSON::PP)) { - eval "require $mod" or next; - # ->ascii encodes non-ASCII to "\uXXXX" - return $mod->new->ascii(1); - } - die; -} - -sub fingerprint ($) { - my ($git) = @_; - my $fh = $git->popen('show-ref') or - die "popen($git->{git_dir} show-ref) failed: $!"; - - my $dig = Digest::SHA->new(1); - while (read($fh, my $buf, 65536)) { - $dig->add($buf); - } - close $fh; - return if $?; # empty, uninitialized git repo - $dig->hexdigest; -} - -sub manifest_add ($$;$) { - my ($manifest, $ibx, $epoch) = @_; - my $url_path = "/$ibx->{name}"; - my $git_dir = $ibx->{mainrepo}; - if (defined $epoch) { - $git_dir .= "/git/$epoch.git"; - $url_path .= "/$epoch"; - } - return unless -d $git_dir; - my $git = PublicInbox::Git->new($git_dir); - my $fingerprint = fingerprint($git) or return; # no empty repos - - chomp(my $owner = $git->qx('config', 'gitweb.owner')); - chomp(my $desc = try_cat("$git_dir/description")); - $owner = undef if $owner eq ''; - $desc = 'Unnamed repository' if $desc eq ''; - - my $reference; - chomp(my $alt = try_cat("$git_dir/objects/info/alternates")); - if ($alt) { - # n.b.: GitPython doesn't seem to handle comments or C-quoted - # strings like native git does; and we don't for now, either. - my @alt = split(/\n+/, $alt); - - # grokmirror only supports 1 alternate for "reference", - if (scalar(@alt) == 1) { - my $objdir = "$git_dir/objects"; - $reference = File::Spec->rel2abs($alt[0], $objdir); - $reference =~ s!/[^/]+/?\z!!; # basename - } - } - $manifest->{-abs2urlpath}->{$git_dir} = $url_path; - my $modified = $git->modified; - if ($modified > $manifest->{-mtime}) { - $manifest->{-mtime} = $modified; - } - $manifest->{$url_path} = { - owner => $owner, - reference => $reference, - description => $desc, - modified => $modified, - fingerprint => $fingerprint, - }; -} - -# manifest.js.gz -sub js ($$) { - my ($env, $list) = @_; - eval { require IO::Compress::Gzip } or return [ 404, [], [] ]; - - my $manifest = { -abs2urlpath => {}, -mtime => 0 }; - for my $ibx (@$list) { - if (defined(my $max = $ibx->max_git_part)) { - for my $epoch (0..$max) { - manifest_add($manifest, $ibx, $epoch); - } - } else { - manifest_add($manifest, $ibx); - } - } - my $abs2urlpath = delete $manifest->{-abs2urlpath}; - my $mtime = delete $manifest->{-mtime}; - while (my ($url_path, $repo) = each %$manifest) { - defined(my $abs = $repo->{reference}) or next; - $repo->{reference} = $abs2urlpath->{$abs}; - } - my $out; - IO::Compress::Gzip::gzip(\(($json ||= _json())->encode($manifest)) => - \$out); - $manifest = undef; - [ 200, [ qw(Content-Type application/gzip), - 'Last-Modified', time2str($mtime), - 'Content-Length', bytes::length($out) ], [ $out ] ]; -} - # not really a stand-alone PSGI app, but maybe it could be... sub call { my ($self, $env) = @_; @@ -220,7 +126,7 @@ sub call { if ($env->{PATH_INFO} eq '/manifest.js.gz') { # grokmirror uses relative paths, so it's domain-dependent my $list = $self->{manifest_cb}->($self, $env, 'manifest'); - js($env, $list); + PublicInbox::ManifestJsGz::response($env, $list); } else { # / my $list = $self->{www_cb}->($self, $env, 'www'); html($env, $list);