X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWwwListing.pm;h=bda2761c63d93091b4680065757a3b241a6eb895;hb=f303b4add8ea18835f7f304910ba8fac3ee4f912;hp=d641e6d5cf6d38c558147e03db002dd3db640d9c;hpb=f72164822464f630c56ac13edc6756987d1e48f6;p=public-inbox.git diff --git a/lib/PublicInbox/WwwListing.pm b/lib/PublicInbox/WwwListing.pm index d641e6d5..bda2761c 100644 --- a/lib/PublicInbox/WwwListing.pm +++ b/lib/PublicInbox/WwwListing.pm @@ -5,246 +5,104 @@ # Used by PublicInbox::WWW package PublicInbox::WwwListing; use strict; -use warnings; -use PublicInbox::Hval qw(ascii_html prurl); +use PublicInbox::Hval qw(prurl fmt_ts); use PublicInbox::Linkify; -use PublicInbox::View; -use PublicInbox::Inbox; -use PublicInbox::NoopFilter; use PublicInbox::GzipFilter qw(gzf_maybe); +use PublicInbox::ConfigIter; use bytes (); # bytes::length -use HTTP::Date qw(time2str); -use Digest::SHA (); -use File::Spec (); -use IO::Compress::Gzip qw(gzip); -*try_cat = \&PublicInbox::Inbox::try_cat; -our $json; -for my $mod (qw(JSON::MaybeXS JSON JSON::PP)) { - eval "require $mod" or next; - # ->ascii encodes non-ASCII to "\uXXXX" - $json = $mod->new->ascii(1) and last; -} - -sub list_all_i { - my ($ibx, $arg) = @_; - my ($list, $hide_key) = @$arg; - push @$list, $ibx unless $ibx->{-hide}->{$hide_key}; -} -sub list_all ($$$) { - my ($self, $env, $hide_key) = @_; - my $list = []; - $self->{pi_config}->each_inbox(\&list_all_i, [ $list, $hide_key ]); - $list; -} +sub ibx_entry { + my ($ctx, $ibx) = @_; + my $mtime = $ibx->modified; + my $ts = fmt_ts($mtime); + my $url = prurl($ctx->{env}, $ibx->{url}); + my $tmp = <<""; +* $ts - $url + ${\$ibx->description} -sub list_match_domain_i { - my ($ibx, $arg) = @_; - my ($list, $hide_key, $re) = @$arg; - if (!$ibx->{-hide}->{$hide_key} && grep($re, @{$ibx->{url}})) { - push @$list, $ibx; + if (defined(my $info_url = $ibx->{infourl})) { + $tmp .= ' ' . prurl($ctx->{env}, $info_url) . "\n"; } + push @{$ctx->{-list}}, [ $mtime, $tmp ]; } -sub list_match_domain ($$$) { - my ($self, $env, $hide_key) = @_; - my $list = []; - my $host = $env->{HTTP_HOST} // $env->{SERVER_NAME}; - $host =~ s/:[0-9]+\z//; - 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 ($$) { [] } - -# TODO: +cgit -my %VALID = ( - all => *list_all, - 'match=domain' => *list_match_domain, - 404 => *list_404, -); - -sub set_cb ($$$) { - my ($pi_config, $k, $default) = @_; - my $v = $pi_config->{lc $k} // $default; - $VALID{$v} || do { - warn <<""; -`$v' is not a valid value for `$k' -$k be one of `all', `match=domain', or `404' - - $VALID{$default}; - }; +sub list_match_i { # ConfigIter callback + my ($cfg, $section, $re, $ctx) = @_; + if (defined($section)) { + return if $section !~ m!\Apublicinbox\.([^/]+)\z!; + my $ibx = $cfg->lookup_name($1) or return; + if (!$ibx->{-hide}->{$ctx->hide_key} && + grep(/$re/, @{$ibx->{url}})) { + $ctx->ibx_entry($ibx); + } + } else { # undef == "EOF" + $ctx->{-wcb}->($ctx->psgi_triple); + } } -sub new { - my ($class, $www) = @_; - my $pi_config = $www->{pi_config}; - bless { - pi_config => $pi_config, - style => $www->style("\0"), - www_cb => set_cb($pi_config, 'publicInbox.wwwListing', 404), - manifest_cb => set_cb($pi_config, 'publicInbox.grokManifest', - 'match=domain'), - }, $class; +sub url_regexp { + my ($ctx, $key, $default) = @_; + $key //= 'publicInbox.wwwListing'; + $default //= '404'; + my $v = $ctx->{www}->{pi_config}->{lc $key} // $default; +again: + if ($v eq 'match=domain') { + my $h = $ctx->{env}->{HTTP_HOST} // $ctx->{env}->{SERVER_NAME}; + $h =~ s/:[0-9]+\z//; + qr!\A(?:https?:)?//\Q$h\E(?::[0-9]+)?/!i; + } elsif ($v eq 'all') { + qr/./; + } elsif ($v eq '404') { + undef; + } else { + warn <{url}); - my $tmp = <<""; -* $ts - $url - ${\$ibx->description} - - if (defined(my $info_url = $ibx->{infourl})) { - $tmp .= ' ' . prurl($env, $info_url) . "\n"; +sub hide_key { 'www' } + +sub response { + my ($class, $ctx) = @_; + bless $ctx, $class; + my $re = $ctx->url_regexp or return $ctx->psgi_triple; + my $iter = PublicInbox::ConfigIter->new($ctx->{www}->{pi_config}, + \&list_match_i, $re, $ctx); + sub { + $ctx->{-wcb} = $_[0]; # HTTP server callback + $ctx->{env}->{'pi-httpd.async'} ? + $iter->event_step : $iter->each_section; } - $tmp; } -sub html ($$) { - my ($env, $list) = @_; +sub psgi_triple { + my ($ctx) = @_; my $h = [ 'Content-Type', 'text/html; charset=UTF-8', 'Content-Length', undef ]; - my $gzf = gzf_maybe($h, $env) || PublicInbox::NoopFilter::new(); + my $gzf = gzf_maybe($h, $ctx->{env}); $gzf->zmore('' . 'public-inbox listing' . '
');
 	my $code = 404;
-	if (@$list) {
+	if (my $list = $ctx->{-list}) {
 		$code = 200;
-		# Schwartzian transform since Inbox->modified is expensive
-		@$list = sort {
-			$b->[0] <=> $a->[0]
-		} map { [ $_->modified, $_ ] } @$list;
-
-		my $tmp = join("\n", map { ibx_entry(@$_, $env) } @$list);
+		# sort by ->modified
+		@$list = map { $_->[1] } sort { $b->[0] <=> $a->[0] } @$list;
+		$list = join("\n", @$list);
 		my $l = PublicInbox::Linkify->new;
-		$gzf->zmore($l->to_html($tmp));
+		$gzf->zmore($l->to_html($list));
 	} else {
 		$gzf->zmore('no inboxes, yet');
 	}
 	my $out = $gzf->zflush('
'.
-				PublicInbox::WwwStream::code_footer($env) .
-				'
'); + PublicInbox::WwwStream::code_footer($ctx->{env}) . + ''); $h->[3] = bytes::length($out); [ $code, $h, [ $out ] ]; } -sub fingerprint ($) { - my ($git) = @_; - # TODO: convert to qspawn for fairness when there's - # thousands of repos - my ($fh, $pid) = $git->popen('show-ref'); - my $dig = Digest::SHA->new(1); - while (read($fh, my $buf, 65536)) { - $dig->add($buf); - } - close $fh; - waitpid($pid, 0); - return if $?; # empty, uninitialized git repo - $dig->hexdigest; -} - -sub manifest_add ($$;$$) { - my ($manifest, $ibx, $epoch, $default_desc) = @_; - my $url_path = "/$ibx->{name}"; - my $git_dir = $ibx->{inboxdir}; - if (defined $epoch) { - $git_dir .= "/git/$epoch.git"; - $url_path .= "/git/$epoch.git"; - } - return unless -d $git_dir; - my $git = PublicInbox::Git->new($git_dir); - my $fingerprint = fingerprint($git) or return; # no empty repos - - chomp(my $owner = $git->qx('config', 'gitweb.owner')); - chomp(my $desc = try_cat("$git_dir/description")); - utf8::decode($owner); - utf8::decode($desc); - $owner = undef if $owner eq ''; - $desc = 'Unnamed repository' if $desc eq ''; - - # templates/hooks--update.sample and git-multimail in git.git - # only match "Unnamed repository", not the full contents of - # templates/this--description in git.git - if ($desc =~ /\AUnnamed repository/) { - $desc = "$default_desc [epoch $epoch]" if defined($epoch); - } - - my $reference; - chomp(my $alt = try_cat("$git_dir/objects/info/alternates")); - if ($alt) { - # n.b.: GitPython doesn't seem to handle comments or C-quoted - # strings like native git does; and we don't for now, either. - my @alt = split(/\n+/, $alt); - - # grokmirror only supports 1 alternate for "reference", - if (scalar(@alt) == 1) { - my $objdir = "$git_dir/objects"; - $reference = File::Spec->rel2abs($alt[0], $objdir); - $reference =~ s!/[^/]+/?\z!!; # basename - } - } - $manifest->{-abs2urlpath}->{$git_dir} = $url_path; - my $modified = $git->modified; - if ($modified > $manifest->{-mtime}) { - $manifest->{-mtime} = $modified; - } - $manifest->{$url_path} = { - owner => $owner, - reference => $reference, - description => $desc, - modified => $modified, - fingerprint => $fingerprint, - }; -} - -# manifest.js.gz -sub js ($$) { - my ($env, $list) = @_; - # $json won't be defined if IO::Compress::Gzip is missing - $json or return [ 404, [], [] ]; - - my $manifest = { -abs2urlpath => {}, -mtime => 0 }; - for my $ibx (@$list) { - if (defined(my $max = $ibx->max_git_epoch)) { - my $desc = $ibx->description; - for my $epoch (0..$max) { - manifest_add($manifest, $ibx, $epoch, $desc); - } - } else { - manifest_add($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; - gzip(\($json->encode($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, $env) = @_; - - if ($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); - } else { # / - my $list = $self->{www_cb}->($self, $env, 'www'); - html($env, $list); - } -} - 1;