-# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
-# HTML body stream for which yields getline+close methods
+# HTML body stream for which yields getline+close methods for
+# generic PSGI servers and callbacks for public-inbox-httpd.
#
-# public-inbox-httpd favors "getline" response bodies to take a
-# "pull"-based approach to feeding slow clients (as opposed to a
-# more common "push" model)
+# See PublicInbox::GzipFilter parent class for more info.
package PublicInbox::WwwStream;
use strict;
-use warnings;
-use base qw(Exporter);
+use v5.10.1;
+use parent qw(Exporter PublicInbox::GzipFilter);
our @EXPORT_OK = qw(html_oneshot);
-use bytes (); # length
-use PublicInbox::Hval qw(ascii_html prurl);
-use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
-use PublicInbox::GzipFilter qw(gzip_maybe gzf_maybe);
-our $TOR_URL = 'https://www.torproject.org/';
-our $CODE_URL = 'https://public-inbox.org/public-inbox.git';
+use PublicInbox::Hval qw(ascii_html prurl ts2str);
-# noop for HTTP.pm (and any other PSGI servers)
-sub close {}
+our $CODE_URL = [ qw(
+http://7fh6tueqddpjyxjmgtdiueylzoqt6pt7hec3pukyptlmohoowvhde4yd.onion/public-inbox.git
+https://public-inbox.org/public-inbox.git) ];
sub base_url ($) {
my $ctx = shift;
- my $base_url = $ctx->{-inbox}->base_url($ctx->{env});
+ my $base_url = ($ctx->{ibx} // $ctx->{git})->base_url($ctx->{env});
chop $base_url; # no trailing slash for clone
$base_url;
}
-sub new {
- my ($class, $ctx, $cb) = @_;
-
- bless {
- nr => 0,
- cb => $cb,
- ctx => $ctx,
- base_url => base_url($ctx),
- }, $class;
+sub init {
+ my ($ctx, $cb) = @_;
+ $ctx->{cb} = $cb;
+ $ctx->{base_url} = base_url($ctx);
+ $ctx->{-res_hdr} = [ 'Content-Type' => 'text/html; charset=UTF-8' ];
+ $ctx->{gz} = PublicInbox::GzipFilter::gz_or_noop($ctx->{-res_hdr},
+ $ctx->{env});
+ bless $ctx, __PACKAGE__;
}
-sub response {
- my ($class, $ctx, $code, $cb) = @_;
- my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
- my $self = $class->new($ctx, $cb);
- $self->{gzf} = gzf_maybe($h, $ctx->{env});
- [ $code, $h, $self ]
+sub async_eml { # for async_blob_cb
+ my ($ctx, $eml) = @_;
+ $ctx->write($ctx->{cb}->($ctx, $eml));
}
-sub _html_top ($) {
- my ($self) = @_;
- my $ctx = $self->{ctx};
- my $ibx = $ctx->{-inbox};
+sub html_top ($) {
+ my ($ctx) = @_;
+ my $ibx = $ctx->{ibx} // $ctx->{git};
my $desc = ascii_html($ibx->description);
my $title = delete($ctx->{-title_html}) // $desc;
my $upfx = $ctx->{-upfx} || '';
- my $help = $upfx.'_/text/help';
- my $color = $upfx.'_/text/color';
my $atom = $ctx->{-atom} || $upfx.'new.atom';
my $top = "<b>$desc</b>";
- my $links = "<a\nhref=\"$help\">help</a> / ".
- "<a\nhref=\"$color\">color</a> / ".
- "<a\nhref=\"$atom\">Atom feed</a>";
- if ($ibx->search) {
+ if (my $t_max = $ctx->{-t_max}) {
+ $t_max = ts2str($t_max);
+ $top = qq(<a\nhref="$upfx?t=$t_max">$top</a>);
+ # we had some kind of query, link to /$INBOX/?t=YYYYMMDDhhmmss
+ } elsif ($ctx->{qp}->{t}) {
+ $top = qq(<a\nhref="./">$top</a>);
+ } elsif (length($upfx)) {
+ $top = qq(<a\nhref="$upfx">$top</a>);
+ }
+ my $code = $ibx->{coderepo} ? qq( / <a\nhref=#code>code</a>) : '';
+ # id=mirror must exist for legacy bookmarks
+ my $links = qq(<a\nhref="${upfx}_/text/help/">help</a> / ).
+ qq(<a\nhref="${upfx}_/text/color/">color</a> / ).
+ qq(<a\nid=mirror) .
+ qq(\nhref="${upfx}_/text/mirror/">mirror</a>$code / ).
+ qq(<a\nhref="$atom">Atom feed</a>);
+ if ($ibx->isrch) {
my $q_val = delete($ctx->{-q_value_html}) // '';
$q_val = qq(\nvalue="$q_val") if $q_val ne '';
# XXX gross, for SearchView.pm
'</head><body>'. $top . (delete($ctx->{-html_tip}) // '');
}
-sub code_footer ($) {
- my ($env) = @_;
- my $u = prurl($env, $CODE_URL);
- qq(AGPL code for this site: git clone <a\nhref="$u">$u</a>)
+sub inboxes { () } # TODO
+
+sub coderepos ($) {
+ my ($ctx) = @_;
+ $ctx->{ibx} // return inboxes($ctx);
+ my $cr = $ctx->{ibx}->{coderepo} // return ();
+ my $cfg = $ctx->{www}->{pi_cfg};
+ my $upfx = ($ctx->{-upfx} // ''). '../';
+ my $pfx = $ctx->{base_url} //= $ctx->base_url;
+ my $up = $upfx =~ tr!/!/!;
+ $pfx =~ s!/[^/]+\z!/! for (1..$up);
+ my @ret = ('<a id=code>' .
+ 'Code repositories for project(s) associated with this '.
+ $ctx->{ibx}->thing_type . "\n");
+ my $objs = $cfg->repo_objs($ctx->{ibx});
+ for my $git (@$objs) {
+ my @urls = $git->pub_urls($ctx->{env});
+ for (@urls) {
+ my $u = m!\A(?:[a-z\+]+:)?//! ? $_ : $pfx.$_;
+ $u = ascii_html(prurl($ctx->{env}, $u));
+ $ret[0] .= qq(\n\t<a\nhref="$u">$u</a>);
+ }
+ }
+ @ret; # may be empty, this sub is called as an arg for join()
}
sub _html_end {
- my ($self) = @_;
- my $urls = 'Archives are clonable:';
- my $ctx = $self->{ctx};
- my $ibx = $ctx->{-inbox};
- my $desc = ascii_html($ibx->description);
-
- my @urls;
- my $http = $self->{base_url};
- my $max = $ibx->max_git_epoch;
- my $dir = (split(m!/!, $http))[-1];
- my %seen = ($http => 1);
- if (defined($max)) { # v2
- for my $i (0..$max) {
- # old parts my be deleted:
- -d "$ibx->{inboxdir}/git/$i.git" or next;
- my $url = "$http/$i";
- $seen{$url} = 1;
- push @urls, "$url $dir/git/$i.git";
+ my ($ctx) = @_;
+ my $upfx = $ctx->{-upfx} || '';
+ my $m = "${upfx}_/text/mirror/";
+ my $x = '';
+ if ($ctx->{ibx} && $ctx->{ibx}->can('cloneurl')) {
+ $x = <<EOF;
+This is a public inbox, see <a
+href="$m">mirroring instructions</a>
+for how to clone and mirror all data and code used for this inbox
+EOF
+ my $has_nntp = @{$ctx->{ibx}->nntp_url($ctx)};
+ my $has_imap = @{$ctx->{ibx}->imap_url($ctx)};
+ if ($has_nntp || $has_imap) {
+ substr($x, -1, 1) = ";\n"; # s/\n/;\n
+ if ($has_nntp && $has_imap) {
+ $x .= <<EOM;
+as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).
+EOM
+ } elsif ($has_nntp) {
+ $x .= <<EOM;
+as well as URLs for NNTP newsgroup(s).
+EOM
+ } else {
+ $x .= <<EOM;
+as well as URLs for IMAP folder(s).
+EOM
+ }
}
- } else { # v1
- push @urls, $http;
- }
-
- # FIXME: epoch splits can be different in other repositories,
- # use the "cloneurl" file as-is for now:
- foreach my $u (@{$ibx->cloneurl}) {
- next if $seen{$u}++;
- push @urls, $u =~ /\Ahttps?:/ ? qq(<a\nhref="$u">$u</a>) : $u;
- }
-
- if (defined($max) || scalar(@urls) > 1) {
- $urls .= "\n" .
- join("\n", map { "\tgit clone --mirror $_" } @urls);
- } else {
- $urls .= " git clone --mirror $urls[0]";
- }
- if (defined $max) {
- my $addrs = $ibx->{address};
- $addrs = join(' ', @$addrs) if ref($addrs) eq 'ARRAY';
- $urls .= <<EOF
-
-
- # If you have public-inbox 1.1+ installed, you may
- # initialize and index your mirror using the following commands:
- public-inbox-init -V2 $ibx->{name} $dir/ $http \\
- $addrs
- public-inbox-index $dir
+ } elsif ($ctx->{ibx}) { # extindex
+ $x = <<EOF;
+This is an external index of several public inboxes,
+see <a href="$m">mirroring instructions</a> on how to clone and mirror
+all data and code used by this external index.
EOF
- } else { # v1
- $urls .= "\n";
- }
-
- my $cfg_link = ($ctx->{-upfx} // '').'_/text/config/raw';
- $urls .= qq(\nExample <a\nhref="$cfg_link">config snippet</a> for mirrors\n);
- my @nntp = map { qq(<a\nhref="$_">$_</a>) } @{$ibx->nntp_url};
- if (@nntp) {
- $urls .= "\n";
- $urls .= @nntp == 1 ? 'Newsgroup' : 'Newsgroups are';
- $urls .= ' available over NNTP:';
- $urls .= "\n\t" . join("\n\t", @nntp) . "\n";
- }
- if ($urls =~ m!\b[^:]+://\w+\.onion/!) {
- $urls .= "\n note: .onion URLs require Tor: ";
- $urls .= qq[<a\nhref="$TOR_URL">$TOR_URL</a>];
+ } elsif ($ctx->{git}) { # coderepo
+ $x = join('', map { "git clone $_\n" }
+ @{$ctx->{git}->cloneurl($ctx->{env})});
}
- '<hr><pre>'.join("\n\n",
- $desc,
- $urls,
- code_footer($ctx->{env})
- ).'</pre></body></html>';
+ chomp $x;
+ '<hr><pre>'.join("\n\n", coderepos($ctx), $x).'</pre></body></html>'
}
# callback for HTTP.pm (and any other PSGI servers)
sub getline {
- my ($self) = @_;
- my $nr = $self->{nr}++;
-
- my $buf = do {
- if ($nr == 0) {
- _html_top($self);
- } elsif (my $middle = $self->{cb}) {
- $middle->($nr, $self->{ctx});
+ my ($ctx) = @_;
+ my $cb = $ctx->{cb} or return;
+ while (defined(my $x = $cb->($ctx))) { # x = smsg or scalar non-ref
+ if (ref($x)) { # smsg
+ my $eml = $ctx->{ibx}->smsg_eml($x) or next;
+ $ctx->{smsg} = $x;
+ return $ctx->translate($cb->($ctx, $eml));
+ } else { # scalar
+ return $ctx->translate($x);
}
- } // (delete($self->{cb}) ? _html_end($self) : undef);
+ }
+ delete $ctx->{cb};
+ $ctx->zflush(_html_end($ctx));
+}
- # gzf may be GzipFilter, `undef' or `0'
- my $gzf = $self->{gzf} or return $buf;
+sub html_done ($;@) {
+ my $ctx = $_[0];
+ my $bdy = $ctx->zflush(@_[1..$#_], _html_end($ctx));
+ my $res_hdr = delete $ctx->{-res_hdr};
+ push @$res_hdr, 'Content-Length', length($bdy);
+ [ 200, $res_hdr, [ $bdy ] ]
+}
- return $gzf->translate($buf) if defined $buf;
- $self->{gzf} = 0; # next call to ->getline returns $buf (== undef)
- $gzf->translate(undef);
+sub html_oneshot ($$;@) {
+ my ($ctx, $code) = @_[0, 1];
+ my $res_hdr = [ 'Content-Type' => 'text/html; charset=UTF-8',
+ 'Content-Length' => undef ];
+ bless $ctx, __PACKAGE__;
+ $ctx->{gz} = PublicInbox::GzipFilter::gz_or_noop($res_hdr, $ctx->{env});
+ my @top;
+ $ctx->{base_url} // do {
+ @top = html_top($ctx);
+ $ctx->{base_url} = base_url($ctx);
+ };
+ my $bdy = $ctx->zflush(@top, @_[2..$#_], _html_end($ctx));
+ $res_hdr->[3] = length($bdy);
+ [ $code, $res_hdr, [ $bdy ] ]
}
-sub html_oneshot ($$;$) {
- my ($ctx, $code, $sref) = @_;
- my $self = bless {
- ctx => $ctx,
- base_url => base_url($ctx),
- }, __PACKAGE__;
- my @x;
- my $h = [ 'Content-Type' => 'text/html; charset=UTF-8' ];
- if (my $gz = gzip_maybe($h, $ctx->{env})) {
- my $err = $gz->deflate(_html_top($self), $x[0]);
- die "gzip->deflate: $err" if $err != Z_OK;
- if ($sref) {
- $err = $gz->deflate($sref, $x[0]);
- die "gzip->deflate: $err" if $err != Z_OK;
+sub async_next ($) {
+ my ($http) = @_; # PublicInbox::HTTP
+ my $ctx = $http->{forward} or return;
+ eval {
+ if (my $smsg = $ctx->{smsg} = $ctx->{cb}->($ctx)) {
+ $ctx->smsg_blob($smsg);
+ } else {
+ $ctx->write(_html_end($ctx));
+ $ctx->close; # GzipFilter->close
}
- $err = $gz->deflate(_html_end($self), $x[0]);
- die "gzip->deflate: $err" if $err != Z_OK;
- $err = $gz->flush($x[0], Z_FINISH);
- die "gzip->flush: $err" if $err != Z_OK;
- } else {
- @x = (_html_top($self), $sref ? $$sref : (), _html_end($self));
- }
+ };
+ warn "E: $@" if $@;
+}
+
+sub aresponse {
+ my ($ctx, $cb) = @_;
+ init($ctx, $cb);
+ $ctx->psgi_response(200, delete $ctx->{-res_hdr});
+}
+
+sub html_init {
+ my ($ctx) = @_;
+ $ctx->{base_url} = base_url($ctx);
+ my $h = $ctx->{-res_hdr} = ['Content-Type', 'text/html; charset=UTF-8'];
+ $ctx->{gz} = PublicInbox::GzipFilter::gz_or_noop($h, $ctx->{env});
+ bless $ctx, __PACKAGE__;
+ print { $ctx->zfh } html_top($ctx);
+}
- my $len = 0;
- $len += bytes::length($_) for @x;
- push @$h, 'Content-Length', $len;
- [ $code, $h, \@x ]
+sub DESTROY {
+ my ($ctx) = @_;
+ $ctx->{git}->cleanup if $ctx->{git} && $ctx->{git}->{-tmp};
}
1;