-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2021 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.
# Used by PublicInbox::WWW
package PublicInbox::WwwListing;
use strict;
-use warnings;
-use PublicInbox::Hval qw(ascii_html);
-use PublicInbox::Linkify;
-use PublicInbox::View;
+use v5.10.1;
+use PublicInbox::Hval qw(prurl fmt_ts ascii_html);
+use PublicInbox::GzipFilter qw(gzf_maybe);
+use PublicInbox::ConfigIter;
+use PublicInbox::WwwStream;
+use URI::Escape qw(uri_escape_utf8);
-sub list_all ($$) {
- my ($self, undef) = @_;
- my @list;
- $self->{pi_config}->each_inbox(sub {
- my ($ibx) = @_;
- push @list, $ibx unless $ibx->{-hide}->{www};
- });
- \@list;
+sub ibx_entry {
+ my ($ctx, $ibx, $ce) = @_;
+ my $desc = ascii_html($ce->{description} //= $ibx->description);
+ my $ts = fmt_ts($ce->{-modified} //= $ibx->modified);
+ my ($url, $href);
+ if (scalar(@{$ibx->{url} // []})) {
+ $url = $href = ascii_html(prurl($ctx->{env}, $ibx->{url}));
+ } else {
+ $href = ascii_html(uri_escape_utf8($ibx->{name})) . '/';
+ $url = ascii_html($ibx->{name});
+ }
+ my $tmp = <<EOM;
+* $ts - <a\nhref="$href">$url</a>
+ $desc
+EOM
+ if (defined($url = $ibx->{infourl})) {
+ $url = ascii_html(prurl($ctx->{env}, $url));
+ $tmp .= qq( <a\nhref="$url">$url</a>\n);
+ }
+ push(@{$ctx->{-list}}, (scalar(@_) == 3 ? # $misc in use, already sorted
+ $tmp : [ $ce->{-modified}, $tmp ] ));
}
-sub list_match_domain ($$) {
- my ($self, $env) = @_;
- 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) = @_;
- push @list, $ibx if !$ibx->{-hide}->{www} && $ibx->{url} =~ $re;
- });
- \@list;
+sub list_match_i { # ConfigIter callback
+ my ($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 list_404 ($$) { [] }
+sub url_filter {
+ my ($ctx, $key, $default) = @_;
+ $key //= 'publicInbox.wwwListing';
+ $default //= '404';
+ my $v = $ctx->{www}->{pi_cfg}->{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, "url:$h");
+ } elsif ($v eq 'all') {
+ (qr/./, undef);
+ } elsif ($v eq '404') {
+ (undef, undef);
+ } else {
+ warn <<EOF;
+`$v' is not a valid value for `$key'
+$key be one of `all', `match=domain', or `404'
+EOF
+ $v = $default; # 'match=domain' or 'all'
+ goto again;
+ }
+}
+
+sub hide_key { 'www' }
-# TODO: +cgit
-my %VALID = (
- all => *list_all,
- 'match=domain' => *list_match_domain,
- 404 => *list_404,
-);
+sub add_misc_ibx { # MiscSearch->retry_reopen callback
+ my ($misc, $ctx, $re, $qs) = @_;
+ require PublicInbox::SearchQuery;
+ my $q = $ctx->{-sq} = PublicInbox::SearchQuery->new($ctx->{qp});
+ my $o = $q->{o};
+ my ($asc, $min, $max);
+ if ($o < 0) {
+ $asc = 1;
+ $o = -($o + 1); # so [-1] is the last element, like Perl lists
+ }
+ my $r = $q->{r};
+ my $opt = {
+ offset => $o,
+ asc => $asc,
+ relevance => $r,
+ limit => $q->{l}
+ };
+ $qs .= ' type:inbox';
-sub new {
- my ($class, $www) = @_;
- my $k = 'publicinbox.wwwListing';
- my $pi_config = $www->{pi_config};
- my $v = $pi_config->{lc($k)} // 404;
- bless {
- pi_config => $pi_config,
- style => $www->style("\0"),
- list_cb => $VALID{$v} || do {
- warn <<"";
-`$v' is not a valid value for `$k'
-$k be one of `all', `match=domain', or `404'
+ delete $ctx->{-list}; # reset if retried
+ my $pi_cfg = $ctx->{www}->{pi_cfg};
+ my $user_query = $q->{'q'} // '';
+ if ($user_query =~ /\S/) {
+ $qs = "( $qs ) AND ( $user_query )";
+ } else { # special case for ALL
+ $ctx->ibx_entry($pi_cfg->ALL // die('BUG: ->ALL expected'), {});
+ }
+ my $mset = $misc->mset($qs, $opt); # sorts by $MODIFIED (mtime)
+ my $hide_key = $ctx->hide_key;
- *list_404;
- },
- }, $class;
+ for my $mi ($mset->items) {
+ my $doc = $mi->get_document;
+ my ($eidx_key) = PublicInbox::Search::xap_terms('Q', $doc);
+ $eidx_key // next;
+ my $ibx = $pi_cfg->lookup_eidx_key($eidx_key) // next;
+ next if $ibx->{-hide}->{$hide_key};
+ grep(/$re/, @{$ibx->{url} // []}) or next;
+ $ctx->ibx_entry($ibx, $misc->doc2ibx_cache_ent($doc));
+ if ($r) { # for descriptions in search_nav_bot
+ my $pct = PublicInbox::Search::get_pct($mi);
+ # only when sorting by relevance, ->items is always
+ # ordered descending:
+ $max //= $pct;
+ $min = $pct;
+ }
+ }
+ if ($r) { # for descriptions in search_nav_bot
+ $q->{-min_pct} = $min;
+ $q->{-max_pct} = $max;
+ }
+ $ctx->{-mset} = $mset;
+ psgi_triple($ctx);
}
-sub ibx_entry {
- my ($mtime, $ibx, $env) = @_;
- my $ts = PublicInbox::View::fmt_ts($mtime);
- my $url = PublicInbox::Hval::prurl($env, $ibx->{url});
- my $tmp = <<"";
-* $ts - $url
- ${\$ibx->description}
+sub response {
+ my ($class, $ctx) = @_;
+ bless $ctx, $class;
+ my ($re, $qs) = $ctx->url_filter;
+ $re // return $ctx->psgi_triple;
+ if (my $ALL = $ctx->{www}->{pi_cfg}->ALL) { # fast path
+ # FIXME: test this in t/
+ $ALL->misc->reopen->retry_reopen(\&add_misc_ibx,
+ $ctx, $re, $qs);
+ } else { # slow path, no [extindex "all"] configured
+ my $iter = PublicInbox::ConfigIter->new($ctx->{www}->{pi_cfg},
+ \&list_match_i, $re, $ctx);
+ sub {
+ $ctx->{-wcb} = $_[0]; # HTTP server callback
+ $ctx->{env}->{'pi-httpd.async'} ?
+ $iter->event_step : $iter->each_section;
+ }
+ }
+}
+
+sub mset_footer ($$) {
+ my ($ctx, $mset) = @_;
+ # no footer if too few matches
+ return '' if $mset->get_matches_estimated == $mset->size;
+ require PublicInbox::SearchView;
+ PublicInbox::SearchView::search_nav_bot($mset, $ctx->{-sq});
+}
- if (defined(my $info_url = $ibx->{info_url})) {
- $tmp .= "\n$info_url";
+sub mset_nav_top {
+ my ($ctx, $mset) = @_;
+ my $q = $ctx->{-sq};
+ my $qh = $q->{'q'} // '';
+ utf8::decode($qh);
+ $qh = ascii_html($qh);
+ $qh = qq[\nvalue="$qh"] if $qh ne '';
+ my $rv = <<EOM;
+<form
+action="./"><pre><input
+name=q
+type=text$qh /><input
+type=submit
+value="locate inbox" /></pre></form><pre>
+EOM
+ chomp $rv;
+ if (defined($q->{'q'})) {
+ my $initial_q = $ctx->{-uxs_retried};
+ if (defined $initial_q) {
+ my $rewritten = $q->{'q'};
+ utf8::decode($initial_q);
+ utf8::decode($rewritten);
+ $initial_q = ascii_html($initial_q);
+ $rewritten = ascii_html($rewritten);
+ $rv .= " Warning: Initial query:\n <b>$initial_q</b>\n";
+ $rv .= " returned no results, used:\n";
+ $rv .= " <b>$rewritten</b>\n instead\n\n";
+ }
+ $rv .= 'Search results ordered by [';
+ if ($q->{r}) {
+ my $d = $q->qs_html(r => 0);
+ $rv .= qq{<a\nhref="?$d">updated</a>|<b>relevance</b>};
+ } else {
+ my $d = $q->qs_html(r => 1);
+ $rv .= qq{<b>updated</b>|<a\nhref="?$d">relevance</a>};
+ }
+ $rv .= ']';
}
- $tmp;
+ $rv .= qq{</pre>};
}
-# not really a stand-alone PSGI app, but maybe it could be...
-sub call {
- my ($self, $env) = @_;
- my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
- my $list = $self->{list_cb}->($self, $env);
+sub psgi_triple {
+ my ($ctx) = @_;
+ my $h = [ 'Content-Type', 'text/html; charset=UTF-8',
+ 'Content-Length', undef ];
+ my $gzf = gzf_maybe($h, $ctx->{env});
+ $gzf->zmore('<html><head><title>public-inbox listing</title>' .
+ $ctx->{www}->style('+/') .
+ '</head><body>');
my $code = 404;
- my $title = 'public-inbox';
- my $out = '';
- if (@$list) {
- # Swartzian transform since ->modified is expensive
- @$list = sort {
- $b->[0] <=> $a->[0]
- } map { [ $_->modified, $_ ] } @$list;
-
+ if (my $list = delete $ctx->{-list}) {
+ my $mset = delete $ctx->{-mset};
$code = 200;
- $title .= ' - listing';
- 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($tmp)).'</pre><hr>';
+ if ($mset) { # already sorted, so search bar:
+ $gzf->zmore(mset_nav_top($ctx, $mset));
+ } else { # sort config dump by ->modified
+ @$list = map { $_->[1] }
+ sort { $b->[0] <=> $a->[0] } @$list;
+ }
+ $gzf->zmore('<pre>');
+ $gzf->zmore(join("\n", @$list));
+ $gzf->zmore(mset_footer($ctx, $mset)) if $mset;
+ } elsif (my $mset = delete $ctx->{-mset}) {
+ $gzf->zmore(mset_nav_top($ctx, $mset));
+ $gzf->zmore('<pre>no matching inboxes');
+ $gzf->zmore(mset_footer($ctx, $mset));
+ } else {
+ $gzf->zmore('<pre>no inboxes, yet');
}
- $out = "<html><head><title>$title</title></head><body>" . $out;
- $out .= '<pre>'. PublicInbox::WwwStream::code_footer($env) .
- '</pre></body></html>';
- [ $code, $h, [ $out ] ]
+ my $out = $gzf->zflush('</pre></body></html>');
+ $h->[3] = length($out);
+ [ $code, $h, [ $out ] ];
}
1;