diff options
Diffstat (limited to 'lib/PublicInbox/SearchView.pm')
-rw-r--r-- | lib/PublicInbox/SearchView.pm | 326 |
1 files changed, 156 insertions, 170 deletions
diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm index 9b67b045..9919e25c 100644 --- a/lib/PublicInbox/SearchView.pm +++ b/lib/PublicInbox/SearchView.pm @@ -1,88 +1,96 @@ -# Copyright (C) 2015-2020 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> # # Displays search results for the web interface package PublicInbox::SearchView; use strict; -use warnings; -use URI::Escape qw(uri_unescape uri_escape); -use PublicInbox::SearchMsg; -use PublicInbox::Hval qw(ascii_html obfuscate_addrs mid_href); +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; -our $LIM = 200; +use PublicInbox::SearchQuery; +use PublicInbox::Search qw(get_pct); my %rmap_inc; -my $noop = sub {}; - sub mbox_results { my ($ctx) = @_; my $q = PublicInbox::SearchQuery->new($ctx->{qp}); - my $x = $q->{x}; + if ($ctx->{env}->{'psgi.input'}->read(my $buf, 3)) { + $q->{t} = 1 if $buf =~ /\Ax=[^0]/; + } require PublicInbox::Mbox; - return PublicInbox::Mbox::mbox_all($ctx, $q->{'q'}) if $x eq 'm'; - sres_top_html($ctx); + $q->{x} eq 'm' ? PublicInbox::Mbox::mbox_all($ctx, $q) : + sres_top_html($ctx); } sub sres_top_html { my ($ctx) = @_; - my $srch = $ctx->{-inbox}->search or + my $srch = $ctx->{srch} = $ctx->{ibx}->isrch or return PublicInbox::WWW::need($ctx, 'Search'); my $q = PublicInbox::SearchQuery->new($ctx->{qp}); - my $x = $q->{x}; - my $query = $q->{'q'}; - my $o = $q->{o}; + my $o = $q->{o} // 0; 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 = { + my $opt = { limit => $q->{l}, offset => $o, - mset => 1, relevance => $q->{r}, + threads => $q->{t}, asc => $asc, }; - my ($mset, $total, $err, $cb); -retry: - eval { - $mset = $srch->query($query, $opts); - $total = $mset->get_matches_estimated; - }; - $err = $@; + my $qs = $q->{'q'}; + $srch->query_approxidate($ctx->{ibx}->git, $qs); + sub { + $ctx->{wcb} = $_[0]; # PSGI server supplied write cb + $srch->async_mset($qs, $opt, \&sres_html_cb, $ctx, $opt, $q); + } +} + +sub sres_html_cb { # async_mset cb + my ($ctx, $opt, $q, $mset, $err) = @_; + my $code = 200; + my $total = $mset ? $mset->get_matches_estimated : undef; ctx_prepare($q, $ctx); + my ($res, $html); if ($err) { $code = 400; - $ctx->{-html_tip} = '<pre>'.err_txt($ctx, $err).'</pre><hr>'; - $cb = $noop; + $html = '<pre>'.err_txt($ctx, $err).'</pre><hr>'; } elsif ($total == 0) { - if (defined($ctx->{-uxs_retried})) { - # undo retry damage: + if (defined($ctx->{-uxs_retried})) { # undo retry damage: $q->{'q'} = $ctx->{-uxs_retried}; - } elsif (index($q->{'q'}, '%') >= 0) { + } elsif (index($q->{'q'}, '%') >= 0) { # retry unescaped $ctx->{-uxs_retried} = $q->{'q'}; - $q->{'q'} = uri_unescape($q->{'q'}); - goto retry; + my $qs = $q->{'q'} = uri_unescape($q->{'q'}); + $ctx->{srch}->query_approxidate($ctx->{ibx}->git, $qs); + return $ctx->{srch}->async_mset($qs, $opt, + \&sres_html_cb, $ctx, $opt, $q); } $code = 404; - $ctx->{-html_tip} = "<pre>\n[No results found]</pre><hr>"; - $cb = $noop; + $html = "<pre>\n[No results found]</pre><hr>"; + } elsif ($q->{x} eq 'A') { + $res = adump($mset, $q, $ctx); } else { - return adump($_[0], $mset, $q, $ctx) if $x eq 'A'; - $ctx->{-html_tip} = search_nav_top($mset, $q, $ctx); - if ($x eq 't') { - $cb = mset_thread($ctx, $mset, $q); + if ($q->{x} eq 't') { + $res = mset_thread($ctx, $mset, $q); } else { - $cb = mset_summary($ctx, $mset, $q); + mset_summary($ctx, $mset, $q); # appends to {-html_tip} + $html = ''; } } - PublicInbox::WwwStream->response($ctx, $code, $cb); + $res //= html_oneshot($ctx, $code, $html); + my $wcb = delete $ctx->{wcb}; + ref($res) eq 'CODE' ? $res->($wcb) : $wcb->($res); } # display non-nested search results similar to what users expect from @@ -94,35 +102,48 @@ sub mset_summary { my $pad = length("$total"); my $pfx = ' ' x $pad; my $res = \($ctx->{-html_tip}); - my $ibx = $ctx->{-inbox}; - my $srch = $ibx->search; + my $ibx = $ctx->{ibx}; my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef; + my @nums = @{$ibx->isrch->mset_to_artnums($mset)}; + my %num2msg = map { $_->{num} => $_ } @{$ibx->over->get_all(@nums)}; + my ($min, $max, %seen); + foreach my $m ($mset->items) { + my $num = shift @nums; + my $smsg = delete($num2msg{$num}) // do { + warn "$m $num expired\n"; + next; + }; + my $mid = $smsg->{mid}; + next if $seen{$mid}++; + $mid = mid_href($mid); + $ctx->{-t_max} //= $smsg->{ts}; my $rank = sprintf("%${pad}d", $m->get_rank + 1); my $pct = get_pct($m); - my $smsg = PublicInbox::SearchMsg::from_mitem($m, $srch); - unless ($smsg) { - eval { - $m = "$m ".$m->get_docid . " expired\n"; - $ctx->{env}->{'psgi.errors'}->print($m); - }; - next; - } + + # 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}); + my $f = ascii_html(delete $smsg->{from_name}); if ($obfs_ibx) { obfuscate_addrs($obfs_ibx, $s); obfuscate_addrs($obfs_ibx, $f); } - my $date = PublicInbox::View::fmt_ts($smsg->{ds}); - my $mid = mid_href($smsg->{mid}); + my $date = fmt_ts($smsg->{ds}); $s = '(no subject)' if $s eq ''; $$res .= qq{$rank. <b><a\nhref="$mid/">}. $s . "</a></b>\n"; $$res .= "$pfx - by $f @ $date UTC [$pct%]\n\n"; } - $$res .= search_nav_bot($mset, $q); - $noop; + if ($q->{r}) { # for descriptions in search_nav_bot + $q->{-min_pct} = $min; + $q->{-max_pct} = $max; + } + $$res .= search_nav_bot($ctx, $mset, $q); + undef; } # shorten "/full/path/to/Foo/Bar.pm" to "Foo/Bar.pm" so error @@ -143,7 +164,7 @@ sub path2inc ($) { sub err_txt { my ($ctx, $err) = @_; - my $u = $ctx->{-inbox}->base_url($ctx->{env}) . '_/text/help/'; + my $u = $ctx->{ibx}->base_url($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); @@ -153,8 +174,8 @@ sub err_txt { sub search_nav_top { my ($mset, $q, $ctx) = @_; - my $m = $q->qs_html(x => 'm', r => undef); - my $rv = qq{<form\naction="?$m"\nmethod="post"><pre>}; + my $m = $q->qs_html(x => 'm', r => undef, t => undef); + my $rv = qq{<form\nid=d\naction="?$m"\nmethod=post><pre>}; my $initial_q = $ctx->{-uxs_retried}; if (defined $initial_q) { my $rewritten = $q->{'q'}; @@ -179,21 +200,40 @@ sub search_nav_top { $rv .= '] view['; my $x = $q->{x}; - if ($x eq '') { - my $t = $q->qs_html(x => 't'); - $rv .= qq{<b>summary</b>|<a\nhref="?$t">nested</a>} - } elsif ($q->{x} eq 't') { + my $pfx = "\t\t\t"; + if ($x eq 't') { my $s = $q->qs_html(x => ''); $rv .= qq{<a\nhref="?$s">summary</a>|<b>nested</b>}; + $pfx = "thread overview <a\nhref=#t>below</a> | "; + } else { + my $t = $q->qs_html(x => 't'); + $rv .= qq{<b>summary</b>|<a\nhref="?$t">nested</a>} } my $A = $q->qs_html(x => 'A', r => undef); - $rv .= qq{|<a\nhref="?$A">Atom feed</a>]}; - $rv .= qq{\n\t\t\t\t\t\tdownload: }; - $rv .= qq{<input\ntype=submit\nvalue="mbox.gz"/></pre></form><pre>}; + $rv .= qq{|<a\nhref="?$A">Atom feed</a>]\n}; + $rv .= <<EOM if $x ne 't' && $q->{t}; +*** "t=1" collapses threads in summary, "full threads" requires mbox.gz *** +EOM + $rv .= <<EOM if $x eq 'm'; +*** "x=m" ignored for GET requests, use download buttons below *** +EOM + if ($ctx->{ibx}->isrch->has_threadid) { + $rv .= qq{${pfx}download mbox.gz: } . + # we set name=z w/o using it since it seems required for + # lynx (but works fine for w3m). + qq{<input\ntype=submit\nname=z\n} . + q{value="results only"/>} . + qq{|<input\ntype=submit\nname=x\n} . + q{value="full threads"/>}; + } else { # BOFH needs to --reindex + $rv .= qq{${pfx}download: } . + qq{<input\ntype=submit\nname=z\nvalue="mbox.gz"/>} + } + $rv .= qq{</pre></form><pre>}; } -sub search_nav_bot { - my ($mset, $q) = @_; +sub search_nav_bot { # also used by WwwListing for searching extindex miscidx + my ($ctx, $mset, $q) = @_; my $total = $mset->get_matches_estimated; my $l = $q->{l}; my $rv = '</pre><hr><pre id=t>'; @@ -203,77 +243,76 @@ sub search_nav_bot { my $beg = $off + 1; if ($beg <= $end) { - $rv .= "Results $beg-$end of $total"; - $rv .= ' (estimated)' if $end != $total; + my $approx = $end == $total ? '' : '~'; + $rv .= "Results $beg-$end of $approx$total"; } else { $rv .= "No more results, only $total"; } - my ($next, $join, $prev); + my ($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 ? '/' : ' '; + $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 ? '/' : ' '; + $join = -$n < $total ? ' | ' : "\t"; my $p = $o + $l; $prev = $q->qs_html(o => ($p < 0 ? $p : 0)); + $pd = $q->{r} ? "[>= $q->{-max_pct}%]" : '(older)'; } } - $rv .= qq{ <a\nhref="?$next"\nrel=next>next</a>} if $next; + $rv .= qq{ <a\nhref="?$next"\nrel=next>next $nd</a>} if $next; $rv .= $join if $join; - $rv .= qq{<a\nhref="?$prev"\nrel=prev>prev</a>} if $prev; + $rv .= qq{<a\nhref="?$prev"\nrel=prev>prev $pd</a>} if $prev; my $rev = $q->qs_html(o => $o < 0 ? 0 : -1); - $rv .= qq{ | <a\nhref="?$rev">reverse results</a></pre>}; + $rv .= qq{ | <a\nhref="?$rev">reverse</a>}; + exists($ctx->{ibx}) and + $rv .= q{ | options <a href=#d>above</a></pre>}; + $rv; } sub sort_relevance { - [ sort { - (eval { $b->topmost->{smsg}->{pct} } // 0) <=> - (eval { $a->topmost->{smsg}->{pct} } // 0) - } @{$_[0]} ] -} - -sub get_pct ($) { - # Capped at "99%" since "100%" takes an extra column in the - # thread skeleton view. <xapian/mset.h> says the value isn't - # very meaningful, anyways. - my $n = $_[0]->get_percent; - $n > 99 ? 99 : $n; -} - -sub load_msgs { - my ($mset) = @_; - [ map { - my $mi = $_; - my $smsg = PublicInbox::SearchMsg::from_mitem($mi); - $smsg->{pct} = get_pct($mi); - $smsg; - } ($mset->items) ] + @{$_[0]} = sort { + (eval { $b->topmost->{pct} } // 0) <=> + (eval { $a->topmost->{pct} } // 0) + } @{$_[0]}; } sub mset_thread { my ($ctx, $mset, $q) = @_; - my $msgs = $ctx->{-inbox}->search->retry_reopen(\&load_msgs, $mset); + my $ibx = $ctx->{ibx}; + my @pct = map { get_pct($_) } $mset->items; + my $msgs = $ibx->isrch->mset_to_smsg($ibx, $mset); + my $i = 0; + $_->{pct} = $pct[$i++] for @$msgs; my $r = $q->{r}; + if ($r) { # for descriptions in search_nav_bot + $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). "<pre>"; + my $skel = search_nav_bot($ctx, $mset, $q).'<pre>'. <<EOM; +-- pct% links below jump to the message on this page, permalinks otherwise -- +EOM $ctx->{-upfx} = ''; $ctx->{anchor_idx} = 1; $ctx->{cur_level} = 0; @@ -285,26 +324,27 @@ sub mset_thread { $ctx->{s_nr} = scalar(@$msgs).'+ results'; # reduce hash lookups in skel_dump - $ctx->{-obfuscate} = $ctx->{-inbox}->{obfuscate}; + $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 { $_->{ts} } @$msgs); + @$msgs = reverse @$msgs if $r; $ctx->{msgs} = $msgs; - \&mset_thread_i; + PublicInbox::WwwStream::aresponse($ctx, \&mset_thread_i); } # callback for PublicInbox::WwwStream::getline sub mset_thread_i { - my ($nr, $ctx) = @_; - my $msgs = $ctx->{msgs} or return; - while (my $smsg = pop @$msgs) { - $ctx->{-inbox}->smsg_mime($smsg) or next; - return PublicInbox::View::index_entry($smsg, $ctx, - scalar @$msgs); - } - my ($skel) = delete @$ctx{qw(skel msgs)}; - $$skel .= "\n</pre>"; + my ($ctx, $eml) = @_; + print { $ctx->zfh } $ctx->html_top if exists $ctx->{-html_tip}; + $eml and return PublicInbox::View::eml_entry($ctx, $eml); + my $smsg = shift @{$ctx->{msgs}} or + print { $ctx->zfh } ${delete($ctx->{skel})}; + $smsg; } sub ctx_prepare { @@ -325,73 +365,19 @@ sub ctx_prepare { } sub adump { - my ($cb, $mset, $q, $ctx) = @_; - $ctx->{items} = [ $mset->items ]; + my ($mset, $q, $ctx) = @_; + $ctx->{ids} = $ctx->{ibx}->isrch->mset_to_artnums($mset); $ctx->{search_query} = $q; # used by WwwAtomStream::atom_header - $ctx->{srch} = $ctx->{-inbox}->search; - PublicInbox::WwwAtomStream->response($ctx, 200, \&adump_i); + PublicInbox::WwwAtomStream->response($ctx, \&adump_i); } # callback for PublicInbox::WwwAtomStream::getline sub adump_i { my ($ctx) = @_; - while (my $mi = shift @{$ctx->{items}}) { - my $smsg = eval { - PublicInbox::SearchMsg::from_mitem($mi, $ctx->{srch}); - } or next; - $ctx->{-inbox}->smsg_mime($smsg) and return $smsg; - } -} - -package PublicInbox::SearchQuery; -use strict; -use warnings; -use URI::Escape qw(uri_escape); -use PublicInbox::MID qw(MID_ESC); - -sub new { - my ($class, $qp) = @_; - - my $r = $qp->{r}; - my ($l) = (($qp->{l} || '') =~ /([0-9]+)/); - $l = $LIM if !$l || $l > $LIM; - bless { - q => $qp->{'q'}, - x => $qp->{x} || '', - o => (($qp->{o} || '0') =~ /(-?[0-9]+)/), - l => $l, - r => (defined $r && $r ne '0'), - }, $class; -} - -sub qs_html { - my ($self, %over) = @_; - - if (keys %over) { - my $tmp = bless { %$self }, ref($self); - foreach my $k (keys %over) { - $tmp->{$k} = $over{$k}; - } - $self = $tmp; - } - - my $q = uri_escape($self->{'q'}, MID_ESC); - $q =~ s/%20/+/g; # improve URL readability - my $qs = "q=$q"; - - if (my $o = $self->{o}) { # ignore o == 0 - $qs .= "&o=$o"; - } - if (my $l = $self->{l}) { - $qs .= "&l=$l" unless $l == $LIM; - } - if (my $r = $self->{r}) { - $qs .= "&r"; - } - if (my $x = $self->{x}) { - $qs .= "&x=$x" if ($x eq 't' || $x eq 'A' || $x eq 'm'); + while (my $num = shift @{$ctx->{ids}}) { + my $smsg = eval { $ctx->{ibx}->over->get_art($num) } or next; + return $smsg; } - $qs; } 1; |