-# Copyright (C) 2019-2020 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 prurl fmt_ts);
-use PublicInbox::Linkify;
-use PublicInbox::View;
-use PublicInbox::Inbox;
+use v5.10.1;
+use PublicInbox::Hval qw(prurl fmt_ts ascii_html);
use PublicInbox::GzipFilter qw(gzf_maybe);
-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};
-}
+use PublicInbox::ConfigIter;
+use PublicInbox::WwwStream;
+use URI::Escape qw(uri_escape_utf8);
+use PublicInbox::MID qw(mid_escape);
-sub list_all ($$$) {
- my ($self, $env, $hide_key) = @_;
- my $list = [];
- $self->{pi_config}->each_inbox(\&list_all_i, [ $list, $hide_key ]);
- $list;
-}
-
-sub list_match_domain_i {
- my ($ibx, $arg) = @_;
- my ($list, $hide_key, $re) = @$arg;
- if (!$ibx->{-hide}->{$hide_key} && grep(/$re/, @{$ibx->{url}})) {
- push @$list, $ibx;
+sub ibx_entry {
+ my ($ctx, $ibx, $ce) = @_;
+ my $desc = ascii_html($ce->{description} //= $ibx->description);
+ my $ts = fmt_ts($ce->{-modified} //= $ibx->modified);
+ my ($url, $href);
+ if (scalar(@{$ibx->{url} // []})) {
+ $url = $href = ascii_html(prurl($ctx->{env}, $ibx->{url}));
+ } else {
+ $href = ascii_html(uri_escape_utf8($ibx->{name})) . '/';
+ $url = ascii_html($ibx->{name});
}
+ my $tmp = <<EOM;
+* $ts - <a\nhref="$href">$url</a>
+ $desc
+EOM
+ if (defined($url = $ibx->{infourl})) {
+ $url = ascii_html(prurl($ctx->{env}, $url));
+ $tmp .= qq( <a\nhref="$url">$url</a>\n);
+ }
+ push(@{$ctx->{-list}}, (scalar(@_) == 3 ? # $misc in use, already sorted
+ $tmp : [ $ce->{-modified}, $tmp ] ));
}
-sub list_match_domain ($$$) {
- my ($self, $env, $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 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'),
- }, $class;
-}
-
-sub ibx_entry {
- my ($mtime, $ibx, $env) = @_;
- my $ts = fmt_ts($mtime);
- my $url = prurl($env, $ibx->{url});
- my $tmp = <<"";
-* $ts - $url
- ${\$ibx->description}
-
- if (defined(my $info_url = $ibx->{infourl})) {
- $tmp .= ' ' . prurl($env, $info_url) . "\n";
+sub list_match_i { # ConfigIter callback
+ my ($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);
}
- $tmp;
}
-sub html ($$) {
- my ($env, $list) = @_;
- 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) {
- $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);
- my $l = PublicInbox::Linkify->new;
- $gzf->zmore($l->to_html($tmp));
+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 {
- $gzf->zmore('no inboxes, yet');
+ 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;
}
- my $out = $gzf->zflush('</pre><hr><pre>'.
- PublicInbox::WwwStream::code_footer($env) .
- '</pre></body></html>');
- $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);
+sub hide_key { 'www' }
+
+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
}
- 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";
+ my $r = $q->{r};
+ my $opt = {
+ offset => $o,
+ asc => $asc,
+ relevance => $r,
+ limit => $q->{l}
+ };
+ $qs .= ' type:inbox';
+
+ 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'), {});
}
- 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 $mset = $misc->mset($qs, $opt); # sorts by $MODIFIED (mtime)
+ my $hide_key = $ctx->hide_key;
+
+ 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);
+}
- 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
+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
+ if ($ctx->{qp}->{a} && # "search all inboxes"
+ $ctx->{qp}->{'q'}) {
+ my $u = 'all/?q='.mid_escape($ctx->{qp}->{'q'});
+ return [ 302, [ 'Location' => $u,
+ qw(Content-Type text/plain) ],
+ [ "Redirecting to $u\n" ] ];
+ }
+ # 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;
}
}
- $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, [], [] ];
+sub mset_footer ($$) {
+ my ($ctx, $mset) = @_;
+ # no footer if too few matches
+ return '' if $mset->get_matches_estimated == $mset->size;
+ require PublicInbox::SearchView;
+ PublicInbox::SearchView::search_nav_bot($ctx, $mset, $ctx->{-sq});
+}
- 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, $desc);
- }
+sub mset_nav_top {
+ my ($ctx, $mset) = @_;
+ my $q = $ctx->{-sq};
+ my $qh = $q->{'q'} // '';
+ if ($qh ne '') {
+ utf8::decode($qh);
+ $qh = qq[\nvalue="].ascii_html($qh).'"';
+ }
+ chop(my $rv = <<EOM);
+<form action="./"><pre><input name=q type=text$qh/><input
+type=submit value="locate inbox"/><input type=submit name=a
+value="search all inboxes"/></pre></form><pre>
+EOM
+ 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 {
- manifest_add($manifest, $ibx);
+ my $d = $q->qs_html(r => 1);
+ $rv .= qq{<b>updated</b>|<a\nhref="?$d">relevance</a>};
}
+ $rv .= ']';
}
- 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 ] ];
+ $rv .= qq{</pre>};
}
-# not really a stand-alone PSGI app, but maybe it could be...
-sub call {
- my ($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, $list);
+sub psgi_triple {
+ my ($ctx) = @_;
+ my $h = [ 'Content-Type', 'text/html; charset=UTF-8',
+ 'Content-Length', undef ];
+ my $gzf = gzf_maybe($h, $ctx->{env});
+ my $zfh = $gzf->zfh;
+ print $zfh '<html><head><title>public-inbox listing</title>',
+ $ctx->{www}->style('+/'),
+ '</head><body>';
+ my $code = 404;
+ if (my $list = delete $ctx->{-list}) {
+ my $mset = delete $ctx->{-mset};
+ $code = 200;
+ if ($mset) { # already sorted, so search bar:
+ print $zfh mset_nav_top($ctx, $mset);
+ } else { # sort config dump by ->modified
+ @$list = map { $_->[1] }
+ sort { $b->[0] <=> $a->[0] } @$list;
+ }
+ print $zfh '<pre>', join("\n", @$list); # big
+ print $zfh mset_footer($ctx, $mset) if $mset;
+ } elsif (my $mset = delete $ctx->{-mset}) {
+ print $zfh mset_nav_top($ctx, $mset),
+ '<pre>no matching inboxes',
+ mset_footer($ctx, $mset);
+ } else {
+ print $zfh '<pre>no inboxes, yet';
}
+ my $out = $gzf->zflush('</pre><hr><pre>'.
+qq(This is a listing of public inboxes, see the `mirror' link of each inbox
+for instructions on how to mirror all the data and code on this site.) .
+ '</pre></body></html>');
+ $h->[3] = length($out);
+ [ $code, $h, [ $out ] ];
}
1;