#
# Displays search results for the web interface
package PublicInbox::SearchView;
use strict;
use v5.10.1;
use List::Util qw(min max);
use URI::Escape qw(uri_unescape);
use PublicInbox::Smsg;
use PublicInbox::Hval qw(ascii_html obfuscate_addrs mid_href fmt_ts);
use PublicInbox::View;
use PublicInbox::WwwAtomStream;
use PublicInbox::WwwStream qw(html_oneshot);
use PublicInbox::SearchThread;
use PublicInbox::SearchQuery;
use PublicInbox::Search qw(mdocid);
my %rmap_inc;
sub mbox_results {
my ($ctx) = @_;
my $q = PublicInbox::SearchQuery->new($ctx->{qp});
if ($ctx->{env}->{'psgi.input'}->read(my $buf, 3)) {
$q->{t} = 1 if $buf =~ /\Ax=[^0]/;
}
require PublicInbox::Mbox;
$q->{x} eq 'm' ? PublicInbox::Mbox::mbox_all($ctx, $q) :
sres_top_html($ctx);
}
sub sres_top_html {
my ($ctx) = @_;
my $srch = $ctx->{-inbox}->search or
return PublicInbox::WWW::need($ctx, 'Search');
my $q = PublicInbox::SearchQuery->new($ctx->{qp});
my $x = $q->{x};
my $query = $q->{'q'};
my $o = $q->{o};
my $asc;
if ($o < 0) {
$asc = 1;
$o = -($o + 1); # so [-1] is the last element, like Perl lists
}
my $code = 200;
# double the limit for expanded views:
my $opts = {
limit => $q->{l},
offset => $o,
mset => 1,
relevance => $q->{r},
thread => $q->{t},
asc => $asc,
};
my ($mset, $total, $err, $html);
retry:
eval {
$mset = $srch->query($query, $opts);
$total = $mset->get_matches_estimated;
};
$err = $@;
ctx_prepare($q, $ctx);
if ($err) {
$code = 400;
$html = ''.err_txt($ctx, $err).' ';
} elsif ($total == 0) {
if (defined($ctx->{-uxs_retried})) {
# undo retry damage:
$q->{'q'} = $ctx->{-uxs_retried};
} elsif (index($q->{'q'}, '%') >= 0) {
$ctx->{-uxs_retried} = $q->{'q'};
$q->{'q'} = uri_unescape($q->{'q'});
goto retry;
}
$code = 404;
$html = "\n[No results found] ";
} else {
return adump($_[0], $mset, $q, $ctx) if $x eq 'A';
$ctx->{-html_tip} = search_nav_top($mset, $q, $ctx);
return mset_thread($ctx, $mset, $q) if $x eq 't';
mset_summary($ctx, $mset, $q); # appends to {-html_tip}
$html = '';
}
html_oneshot($ctx, $code);
}
# display non-nested search results similar to what users expect from
# regular WWW search engines:
sub mset_summary {
my ($ctx, $mset, $q) = @_;
my $total = $mset->get_matches_estimated;
my $pad = length("$total");
my $pfx = ' ' x $pad;
my $res = \($ctx->{-html_tip});
my $ibx = $ctx->{-inbox};
my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef;
my @nums = @{$ibx->search->mset_to_artnums($mset)};
my %num2msg = map { $_->{num} => $_ } @{$ibx->over->get_all(@nums)};
my ($min, $max);
foreach my $m ($mset->items) {
my $rank = sprintf("%${pad}d", $m->get_rank + 1);
my $pct = get_pct($m);
my $num = shift @nums;
my $smsg = delete($num2msg{$num}) or do {
eval {
$m = "$m $num expired\n";
$ctx->{env}->{'psgi.errors'}->print($m);
};
next;
};
$ctx->{-t_max} //= $smsg->{ts};
# only when sorting by relevance, ->items is always
# ordered descending:
$max //= $pct;
$min = $pct;
my $s = ascii_html($smsg->{subject});
my $f = ascii_html($smsg->{from_name});
if ($obfs_ibx) {
obfuscate_addrs($obfs_ibx, $s);
obfuscate_addrs($obfs_ibx, $f);
}
my $date = fmt_ts($smsg->{ds});
my $mid = mid_href($smsg->{mid});
$s = '(no subject)' if $s eq '';
$$res .= qq{$rank. }.
$s . " \n";
$$res .= "$pfx - by $f @ $date UTC [$pct%]\n\n";
}
if ($q->{r}) { # for descriptions in search_nav_bot
$q->{-min_pct} = $min;
$q->{-max_pct} = $max;
}
$$res .= search_nav_bot($mset, $q);
undef;
}
# shorten "/full/path/to/Foo/Bar.pm" to "Foo/Bar.pm" so error
# messages don't reveal FS layout info in case people use non-standard
# installation paths
sub path2inc ($) {
my $full = $_[0];
if (my $short = $rmap_inc{$full}) {
return $short;
} elsif (!scalar(keys %rmap_inc) && -e $full) {
%rmap_inc = map {; "$INC{$_}" => $_ } keys %INC;
# fall back to basename as last resort
$rmap_inc{$full} // (split('/', $full))[-1];
} else {
$full;
}
}
sub err_txt {
my ($ctx, $err) = @_;
my $u = $ctx->{-inbox}->base_url($ctx->{env}) . '_/text/help/';
$err =~ s/^\s*Exception:\s*//; # bad word to show users :P
$err =~ s!(\S+)!path2inc($1)!sge;
$err = ascii_html($err);
"\nBad query: $err \n" .
qq{See $u for help on using search};
}
sub search_nav_top {
my ($mset, $q, $ctx) = @_;
my $m = $q->qs_html(x => 'm', r => undef, t => undef);
my $rv = qq{};
}
sub search_nav_bot {
my ($mset, $q) = @_;
my $total = $mset->get_matches_estimated;
my $l = $q->{l};
my $rv = ' ';
my $o = $q->{o};
my $off = $o < 0 ? -($o + 1) : $o;
my $end = $off + $mset->size;
my $beg = $off + 1;
if ($beg <= $end) {
my $approx = $end == $total ? '' : '~';
$rv .= "Results $beg-$end of $approx$total";
} else {
$rv .= "No more results, only $total";
}
my ($next, $join, $prev, $nd, $pd);
if ($o >= 0) { # sort descending
my $n = $o + $l;
if ($n < $total) {
$next = $q->qs_html(o => $n, l => $l);
$nd = $q->{r} ? "[<= $q->{-min_pct}%]" : '(older)';
}
if ($o > 0) {
$join = $n < $total ? ' | ' : "\t";
my $p = $o - $l;
$prev = $q->qs_html(o => ($p > 0 ? $p : 0));
$pd = $q->{r} ? "[>= $q->{-max_pct}%]" : '(newer)';
}
} else { # o < 0, sort ascending
my $n = $o - $l;
if (-$n < $total) {
$next = $q->qs_html(o => $n, l => $l);
$nd = $q->{r} ? "[<= $q->{-min_pct}%]" : '(newer)';
}
if ($o < -1) {
$join = -$n < $total ? ' | ' : "\t";
my $p = $o + $l;
$prev = $q->qs_html(o => ($p < 0 ? $p : 0));
$pd = $q->{r} ? "[>= $q->{-max_pct}%]" : '(older)';
}
}
$rv .= qq{ next $nd } if $next;
$rv .= $join if $join;
$rv .= qq{prev $pd } if $prev;
my $rev = $q->qs_html(o => $o < 0 ? 0 : -1);
$rv .= qq{ | reverse };
}
sub sort_relevance {
[ sort {
(eval { $b->topmost->{pct} } // 0) <=>
(eval { $a->topmost->{pct} } // 0)
} @{$_[0]} ]
}
sub get_pct ($) {
# Capped at "99%" since "100%" takes an extra column in the
# thread skeleton view. says the value isn't
# very meaningful, anyways.
my $n = $_[0]->get_percent;
$n > 99 ? 99 : $n;
}
sub mset_thread {
my ($ctx, $mset, $q) = @_;
my $ibx = $ctx->{-inbox};
my $nshard = $ibx->search->{nshard} // 1;
my %pct = map { mdocid($nshard, $_) => get_pct($_) } $mset->items;
my $msgs = $ibx->over->get_all(keys %pct);
$_->{pct} = $pct{$_->{num}} for @$msgs;
my $r = $q->{r};
if ($r) { # for descriptions in search_nav_bot
my @pct = values %pct;
$q->{-min_pct} = min(@pct);
$q->{-max_pct} = max(@pct);
}
my $rootset = PublicInbox::SearchThread::thread($msgs,
$r ? \&sort_relevance : \&PublicInbox::View::sort_ds,
$ctx);
my $skel = search_nav_bot($mset, $q). "";
$ctx->{-upfx} = '';
$ctx->{anchor_idx} = 1;
$ctx->{cur_level} = 0;
$ctx->{skel} = \$skel;
$ctx->{mapping} = {};
$ctx->{searchview} = 1;
$ctx->{prev_attr} = '';
$ctx->{prev_level} = 0;
$ctx->{s_nr} = scalar(@$msgs).'+ results';
# reduce hash lookups in skel_dump
$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
PublicInbox::View::walk_thread($rootset, $ctx,
\&PublicInbox::View::pre_thread);
# link $INBOX_DIR/description text to "recent" view around
# the newest message in this result set:
$ctx->{-t_max} = max(map { delete $_->{ts} } @$msgs);
@$msgs = reverse @$msgs if $r;
$ctx->{msgs} = $msgs;
PublicInbox::WwwStream::aresponse($ctx, 200, \&mset_thread_i);
}
# callback for PublicInbox::WwwStream::getline
sub mset_thread_i {
my ($ctx, $eml) = @_;
$ctx->zmore($ctx->html_top) if exists $ctx->{-html_tip};
$eml and return PublicInbox::View::eml_entry($ctx, $eml);
my $smsg = shift @{$ctx->{msgs}} or
$ctx->zmore(${delete($ctx->{skel})});
$smsg;
}
sub ctx_prepare {
my ($q, $ctx) = @_;
my $qh = $q->{'q'};
utf8::decode($qh);
$qh = ascii_html($qh);
$ctx->{-q_value_html} = $qh;
$ctx->{-atom} = '?'.$q->qs_html(x => 'A', r => undef);
$ctx->{-title_html} = "$qh - search results";
my $extra = '';
$extra .= qq{ } if $q->{r};
if (my $x = $q->{x}) {
$x = ascii_html($x);
$extra .= qq{ };
}
$ctx->{-extra_form_html} = $extra;
}
sub adump {
my ($cb, $mset, $q, $ctx) = @_;
$ctx->{ids} = $ctx->{-inbox}->search->mset_to_artnums($mset);
$ctx->{search_query} = $q; # used by WwwAtomStream::atom_header
PublicInbox::WwwAtomStream->response($ctx, 200, \&adump_i);
}
# callback for PublicInbox::WwwAtomStream::getline
sub adump_i {
my ($ctx) = @_;
while (my $num = shift @{$ctx->{ids}}) {
my $smsg = eval { $ctx->{-inbox}->over->get_art($num) } or next;
return $smsg;
}
}
1;