X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=95f4234c4b2b26cc2ca85ccd784a7d56b577db88;hb=0c8106d44f317175e122744b43407bf067183175;hp=18390602faada97021c0b774ac944550208ac70e;hpb=58e764d179131b0fba8590915e2528248be26329;p=public-inbox.git diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 18390602..95f4234c 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -1,6 +1,6 @@ # Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ -# based on notmuch, but with no concept of folders, files or flags +# based on notmuch, but with no concept of folders, files # # Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use # with the web and NNTP interfaces. This index maintains thread @@ -15,7 +15,7 @@ use PublicInbox::InboxWritable; use PublicInbox::MID qw(mids_for_index mids); use PublicInbox::MsgIter; use PublicInbox::IdxStack; -use Carp qw(croak); +use Carp qw(croak carp); use POSIX qw(strftime); use Time::Local qw(timegm); use PublicInbox::OverIdx; @@ -23,7 +23,7 @@ use PublicInbox::Spawn qw(spawn nodatacow_dir); use PublicInbox::Git qw(git_unquote); use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack - index_text term_generator add_val); + index_text term_generator add_val is_bad_blob); my $X = \%PublicInbox::Search::X; our ($DB_CREATE_OR_OPEN, $DB_OPEN); our $DB_NO_SYNC = 0; @@ -54,20 +54,16 @@ sub new { } } $ibx = PublicInbox::InboxWritable->new($ibx); - my $self = bless { - ibx => $ibx, - xpfx => $inboxdir, # for xpfx_init - -altid => $altid, - ibx_ver => $version, - indexlevel => $indexlevel, - }, $class; - $self->xpfx_init; + my $self = PublicInbox::Search->new($ibx); + bless $self, $class; + $self->{ibx} = $ibx; + $self->{-altid} = $altid; + $self->{indexlevel} = $indexlevel; $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium'; if ($ibx->{-skip_docdata}) { $self->{-set_skip_docdata_once} = 1; $self->{-skip_docdata} = 1; } - $ibx->umask_prepare; if ($version == 1) { $self->{lock_path} = "$inboxdir/ssoma.lock"; my $dir = $self->xdir; @@ -106,7 +102,6 @@ sub load_xapian_writable () { } eval 'require '.$X->{WritableDatabase} or die; *sortable_serialise = $xap.'::sortable_serialise'; - *sortable_unserialise = $xap.'::sortable_unserialise'; $DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()'); $DB_OPEN = eval($xap.'::DB_OPEN()'); my $ver = (eval($xap.'::major_version()') << 16) | @@ -352,8 +347,9 @@ sub index_ids ($$$$) { index_list_id($self, $doc, $hdr); } -sub add_xapian ($$$$) { +sub eml2doc ($$$;$) { my ($self, $eml, $smsg, $mids) = @_; + $mids //= mids_for_index($eml); my $doc = $X->{Document}->new; add_val($doc, PublicInbox::Search::TS(), $smsg->{ts}); my @ds = gmtime($smsg->{ds}); @@ -370,7 +366,7 @@ sub add_xapian ($$$$) { index_headers($self, $smsg); if (defined(my $eidx_key = $smsg->{eidx_key})) { - $doc->add_boolean_term('O'.$eidx_key); + $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.'; } msg_iter($eml, \&index_xapian, [ $self, $doc ]); index_ids($self, $doc, $eml, $mids); @@ -396,12 +392,18 @@ sub add_xapian ($$$$) { } } } + $doc; +} + +sub add_xapian ($$$$) { + my ($self, $eml, $smsg, $mids) = @_; + my $doc = eml2doc($self, $eml, $smsg, $mids); $self->{xdb}->replace_document($smsg->{num}, $doc); } sub _msgmap_init ($) { my ($self) = @_; - die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 1; + die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1; $self->{mm} //= eval { require PublicInbox::Msgmap; my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1; @@ -445,33 +447,33 @@ sub add_message { $smsg->{num}; } -sub _get_doc ($$$) { - my ($self, $docid, $oid) = @_; +sub _get_doc ($$) { + my ($self, $docid) = @_; my $doc = eval { $self->{xdb}->get_document($docid) }; $doc // do { warn "E: $@\n" if $@; - warn "E: #$docid $oid missing in Xapian\n"; + warn "E: #$docid missing in Xapian\n"; undef; } } sub add_eidx_info { - my ($self, $docid, $oid, $eidx_key, $eml) = @_; + my ($self, $docid, $eidx_key, $eml) = @_; begin_txn_lazy($self); - my $doc = _get_doc($self, $docid, $oid) or return; + my $doc = _get_doc($self, $docid) or return; term_generator($self)->set_document($doc); - $doc->add_boolean_term('O'.$eidx_key); + $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.'; index_list_id($self, $doc, $eml); $self->{xdb}->replace_document($docid, $doc); } sub remove_eidx_info { - my ($self, $docid, $oid, $eidx_key, $eml) = @_; + my ($self, $docid, $eidx_key, $eml) = @_; begin_txn_lazy($self); - my $doc = _get_doc($self, $docid, $oid) or return; + my $doc = _get_doc($self, $docid) or return; eval { $doc->remove_term('O'.$eidx_key) }; warn "W: ->remove_term O$eidx_key: $@\n" if $@; - for my $l ($eml->header_raw('List-Id')) { + for my $l ($eml ? $eml->header_raw('List-Id') : ()) { $l =~ /<([^>]+)>/ or next; my $lid = lc $1; eval { $doc->remove_term('G' . $lid) }; @@ -494,17 +496,53 @@ sub remove_eidx_info { $self->{xdb}->replace_document($docid, $doc); } -sub get_val ($$) { - my ($doc, $col) = @_; - sortable_unserialise($doc->get_value($col)); +sub set_keywords { + my ($self, $docid, @kw) = @_; + begin_txn_lazy($self); + my $doc = _get_doc($self, $docid) or return; + my %keep = map { $_ => 1 } @kw; + my %add = %keep; + my @rm; + my $end = $doc->termlist_end; + for (my $cur = $doc->termlist_begin; $cur != $end; $cur++) { + $cur->skip_to('K'); + last if $cur == $end; + my $kw = $cur->get_termname; + $kw =~ s/\AK//s or next; + $keep{$kw} ? delete($add{$kw}) : push(@rm, $kw); + } + return unless (scalar(@rm) + scalar(keys %add)); + $doc->remove_term('K'.$_) for @rm; + $doc->add_boolean_term('K'.$_) for (keys %add); + $self->{xdb}->replace_document($docid, $doc); +} + +sub add_keywords { + my ($self, $docid, @kw) = @_; + begin_txn_lazy($self); + my $doc = _get_doc($self, $docid) or return; + $doc->add_boolean_term('K'.$_) for @kw; + $self->{xdb}->replace_document($docid, $doc); +} + +sub remove_keywords { + my ($self, $docid, @kw) = @_; + begin_txn_lazy($self); + my $doc = _get_doc($self, $docid) or return; + my $replace; + eval { + $doc->remove_term('K'.$_); + $replace = 1 + } for @kw; + $self->{xdb}->replace_document($docid, $doc) if $replace; } sub smsg_from_doc ($) { my ($doc) = @_; my $data = $doc->get_data or return; my $smsg = bless {}, 'PublicInbox::Smsg'; - $smsg->{ts} = get_val($doc, PublicInbox::Search::TS()); - my $dt = get_val($doc, PublicInbox::Search::DT()); + $smsg->{ts} = int_val($doc, PublicInbox::Search::TS()); + my $dt = int_val($doc, PublicInbox::Search::DT()); my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt); $smsg->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy); $smsg->load_from_data($data); @@ -512,25 +550,19 @@ sub smsg_from_doc ($) { } sub xdb_remove { - my ($self, $oid, @removed) = @_; + my ($self, @docids) = @_; my $xdb = $self->{xdb} or return; - for my $num (@removed) { - my $doc = _get_doc($self, $num, $oid) or next; - my $smsg = smsg_from_doc($doc); - my $blob = $smsg->{blob}; # may be undef if --skip-docdata - if (!defined($blob) || $blob eq $oid) { - $xdb->delete_document($num); - } else { - warn "E: #$num $oid != $blob in Xapian\n"; - } + for my $docid (@docids) { + eval { $xdb->delete_document($docid) }; + warn "E: #$docid not in in Xapian? $@\n" if $@; } } -sub remove_by_oid { - my ($self, $oid, $num) = @_; - die "BUG: remove_by_oid is v2-only\n" if $self->{oidx}; +sub remove_by_docid { + my ($self, $num) = @_; + die "BUG: remove_by_docid is v2-only\n" if $self->{oidx}; $self->begin_txn_lazy; - xdb_remove($self, $oid, $num) if need_xapian($self); + xdb_remove($self, $num) if need_xapian($self); } sub index_git_blob_id { @@ -566,7 +598,7 @@ sub unindex_eml { } else { # just in case msgmap and over.sqlite3 become desynched: $self->{mm}->mid_delete($mids->[0]); } - xdb_remove($self, $oid, keys %tmp) if need_xapian($self); + xdb_remove($self, keys %tmp) if need_xapian($self); } sub index_mm { @@ -597,29 +629,46 @@ sub crlf_adjust ($) { } } +sub is_bad_blob ($$$$) { + my ($oid, $type, $size, $expect_oid) = @_; + if ($type ne 'blob') { + carp "W: $expect_oid is not a blob (type=$type)"; + return 1; + } + croak "BUG: $oid != $expect_oid" if $oid ne $expect_oid; + $size == 0 ? 1 : 0; # size == 0 means purged +} + sub index_both { # git->cat_async callback my ($bref, $oid, $type, $size, $sync) = @_; + return if is_bad_blob($oid, $type, $size, $sync->{oid}); my ($nr, $max) = @$sync{qw(nr max)}; ++$$nr; $$max -= $size; $size += crlf_adjust($$bref); my $smsg = bless { bytes => $size, blob => $oid }, 'PublicInbox::Smsg'; my $self = $sync->{sidx}; + local $self->{current_info} = "$self->{current_info}: $oid"; my $eml = PublicInbox::Eml->new($bref); $smsg->{num} = index_mm($self, $eml, $oid, $sync) or die "E: could not generate NNTP article number for $oid"; add_message($self, $eml, $smsg, $sync); + ++$self->{nidx}; my $cur_cmt = $sync->{cur_cmt} // die 'BUG: {cur_cmt} missing'; ${$sync->{latest_cmt}} = $cur_cmt; } sub unindex_both { # git->cat_async callback my ($bref, $oid, $type, $size, $sync) = @_; - unindex_eml($sync->{sidx}, $oid, PublicInbox::Eml->new($bref)); + return if is_bad_blob($oid, $type, $size, $sync->{oid}); + my $self = $sync->{sidx}; + local $self->{current_info} = "$self->{current_info}: $oid"; + unindex_eml($self, $oid, PublicInbox::Eml->new($bref)); # may be undef if leftover if (defined(my $cur_cmt = $sync->{cur_cmt})) { ${$sync->{latest_cmt}} = $cur_cmt; } + ++$self->{nidx}; } sub with_umask { @@ -632,10 +681,11 @@ sub index_sync { my ($self, $opt) = @_; delete $self->{lock_path} if $opt->{-skip_lock}; $self->with_umask(\&_index_sync, $self, $opt); - if ($opt->{reindex}) { + if ($opt->{reindex} && !$opt->{quit}) { my %again = %$opt; delete @again{qw(rethread reindex)}; index_sync($self, \%again); + $opt->{quit} = $again{quit}; # propagate to caller } } @@ -688,7 +738,7 @@ sub v1_checkpoint ($$;$) { if (my $pr = $sync->{-opt}->{-progress}) { $pr->("indexed $nr/$sync->{ntodo}\n") if $nr; } - if (!$stk) { # more to come + if (!$stk && !$sync->{quit}) { # more to come begin_txn_lazy($self); $self->{mm}->{dbh}->begin_work; } @@ -709,6 +759,7 @@ sub process_stack { if (my @leftovers = keys %{delete($sync->{D}) // {}}) { warn('W: unindexing '.scalar(@leftovers)." leftovers\n"); for my $oid (@leftovers) { + last if $sync->{quit}; $oid = unpack('H*', $oid); $git->cat_async($oid, \&unindex_both, $sync); } @@ -717,7 +768,8 @@ sub process_stack { $sync->{index_oid} = \&index_both; } while (my ($f, $at, $ct, $oid, $cur_cmt) = $stk->pop_rec) { - my $arg = { %$sync, cur_cmt => $cur_cmt }; + my $arg = { %$sync, cur_cmt => $cur_cmt, oid => $oid }; + last if $sync->{quit}; if ($f eq 'm') { $arg->{autime} = $at; $arg->{cotime} = $ct; @@ -731,7 +783,7 @@ sub process_stack { $git->cat_async($oid, \&unindex_both, $arg); } } - v1_checkpoint($self, $sync, $stk); + v1_checkpoint($self, $sync, $sync->{quit} ? undef : $stk); } sub log2stack ($$$) { @@ -841,15 +893,30 @@ sub reindex_from ($$) { ref($reindex) eq 'HASH' ? $reindex->{from} : ''; } +sub quit_cb ($) { + my ($sync) = @_; + sub { + # we set {-opt}->{quit} too, so ->index_sync callers + # can abort multi-inbox loops this way + $sync->{quit} = $sync->{-opt}->{quit} = 1; + warn "gracefully quitting\n"; + } +} + # indexes all unindexed messages (v1 only) sub _index_sync { my ($self, $opt) = @_; my $tip = $opt->{ref} || 'HEAD'; my $ibx = $self->{ibx}; + local $self->{current_info} = "$ibx->{inboxdir}"; $self->{batch_bytes} = $opt->{batch_size} // $BATCH_BYTES; $ibx->git->batch_prepare; my $pr = $opt->{-progress}; my $sync = { reindex => $opt->{reindex}, -opt => $opt, ibx => $ibx }; + my $quit = quit_cb($sync); + local $SIG{QUIT} = $quit; + local $SIG{INT} = $quit; + local $SIG{TERM} = $quit; my $xdb = $self->begin_txn_lazy; $self->{oidx}->rethread_prepare($opt); my $mm = _msgmap_init($self); @@ -870,7 +937,7 @@ sub _index_sync { my $stk = prepare_stack($sync, $range); $sync->{ntodo} = $stk ? $stk->num_records : 0; $pr->("$sync->{ntodo}\n") if $pr; # continue previous line - process_stack($self, $sync, $stk); + process_stack($self, $sync, $stk) if !$sync->{quit}; } sub DESTROY { @@ -918,6 +985,10 @@ sub set_metadata_once { sub _commit_txn { my ($self) = @_; + if (my $eidx = $self->{eidx}) { + $eidx->git->async_wait_all; + $eidx->{transact_bytes} = 0; + } if (my $xdb = $self->{xdb}) { set_metadata_once($self); $xdb->commit_transaction; @@ -953,4 +1024,25 @@ sub eidx_shard_new { $self; } +# ensure there's no stale Xapian docs by treating $over as canonical +sub over_check { + my ($self, $over) = @_; + begin_txn_lazy($self); + my $sth = $over->dbh->prepare(<<''); +SELECT COUNT(*) FROM over WHERE num = ? + + my $xdb = $self->{xdb}; + my $cur = $xdb->postlist_begin(''); + my $end = $xdb->postlist_end(''); + my $xdir = $self->xdir; + for (; $cur != $end; $cur++) { + my $docid = $cur->get_docid; + $sth->execute($docid); + my $x = $sth->fetchrow_array; + next if $x > 0; + warn "I: removing $xdir #$docid, not in `over'\n"; + $xdb->delete_document($docid); + } +} + 1;