-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Provide an HTTP-accessible listing of inboxes.
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 PublicInbox::Inbox;
+use PublicInbox::GzipFilter qw(gzf_maybe);
+use bytes (); # bytes::length
use HTTP::Date qw(time2str);
-require Digest::SHA;
-require File::Spec;
-{ no warnings 'once'; *try_cat = *PublicInbox::Inbox::try_cat };
+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 ($$$) {
my ($self, $env, $hide_key) = @_;
- my @list;
- $self->{pi_config}->each_inbox(sub {
- my ($ibx) = @_;
- push @list, $ibx unless $ibx->{-hide}->{$hide_key};
- });
- \@list;
+ my $list = [];
+ $self->{pi_config}->each_inbox(\&list_all_i, [ $list, $hide_key ]);
+ $list;
+}
+
+sub list_match_domain_i {
+ my ($ibx, $arg) = @_;
+ my ($list, $hide_key, $re) = @$arg;
+ if (!$ibx->{-hide}->{$hide_key} && grep(/$re/, @{$ibx->{url}})) {
+ push @$list, $ibx;
+ }
}
sub list_match_domain ($$$) {
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 ($$) { [] }
sub ibx_entry {
my ($mtime, $ibx, $env) = @_;
- my $ts = PublicInbox::View::fmt_ts($mtime);
- my $url = PublicInbox::Hval::prurl($env, $ibx->{url});
+ my $ts = fmt_ts($mtime);
+ my $url = prurl($env, $ibx->{url});
my $tmp = <<"";
* $ts - $url
${\$ibx->description}
- if (defined(my $info_url = $ibx->{info_url})) {
- $tmp .= "\n$info_url";
+ if (defined(my $info_url = $ibx->{infourl})) {
+ $tmp .= ' ' . prurl($env, $info_url) . "\n";
}
$tmp;
}
sub html ($$) {
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('<html><head><title>' .
+ 'public-inbox listing</title>' .
+ '</head><body><pre>');
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);
- $out = '<pre>'.$l->linkify_2(ascii_html($tmp)).'</pre><hr>';
+ $gzf->zmore($l->to_html($tmp));
+ } else {
+ $gzf->zmore('no inboxes, yet');
}
- $out = "<html><head><title>$title</title></head><body>" . $out;
- $out .= '<pre>'. PublicInbox::WwwStream::code_footer($env) .
- '</pre></body></html>';
-
- my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
+ my $out = $gzf->zflush('</pre><hr><pre>'.
+ PublicInbox::WwwStream::code_footer($env) .
+ '</pre></body></html>');
+ $h->[3] = bytes::length($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: $!";
-
+ # TODO: convert to qspawn for fairness when there's
+ # thousands of repos
+ my ($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 ($$;$) {
- my ($manifest, $ibx, $epoch) = @_;
+sub manifest_add ($$;$$) {
+ my ($manifest, $ibx, $epoch, $default_desc) = @_;
my $url_path = "/$ibx->{name}";
- my $git_dir = $ibx->{mainrepo};
+ my $git_dir = $ibx->{inboxdir};
if (defined $epoch) {
$git_dir .= "/git/$epoch.git";
$url_path .= "/git/$epoch.git";
chomp(my $owner = $git->qx('config', 'gitweb.owner'));
chomp(my $desc = try_cat("$git_dir/description"));
+ utf8::decode($owner);
+ utf8::decode($desc);
$owner = undef if $owner eq '';
$desc = 'Unnamed repository' if $desc eq '';
+ # templates/hooks--update.sample and git-multimail in git.git
+ # only match "Unnamed repository", not the full contents of
+ # templates/this--description in git.git
+ if ($desc =~ /\AUnnamed repository/) {
+ $desc = "$default_desc [epoch $epoch]" if defined($epoch);
+ }
+
my $reference;
chomp(my $alt = try_cat("$git_dir/objects/info/alternates"));
if ($alt) {
# manifest.js.gz
sub js ($$) {
my ($env, $list) = @_;
- eval { require IO::Compress::Gzip } or return [ 404, [], [] ];
+ # $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_part)) {
+ if (defined(my $max = $ibx->max_git_epoch)) {
+ my $desc = $ibx->description;
for my $epoch (0..$max) {
- manifest_add($manifest, $ibx, $epoch);
+ manifest_add($manifest, $ibx, $epoch, $desc);
}
} else {
manifest_add($manifest, $ibx);
$repo->{reference} = $abs2urlpath->{$abs};
}
my $out;
- IO::Compress::Gzip::gzip(\(($json ||= _json())->encode($manifest)) =>
- \$out);
+ gzip(\($json->encode($manifest)) => \$out);
$manifest = undef;
[ 200, [ qw(Content-Type application/gzip),
'Last-Modified', time2str($mtime),