use PublicInbox::IdxStack;
use Carp qw(croak);
use POSIX qw(strftime);
+use Time::Local qw(timegm);
use PublicInbox::OverIdx;
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);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack
+ index_text term_generator add_val);
my $X = \%PublicInbox::Search::X;
-my ($DB_CREATE_OR_OPEN, $DB_OPEN);
+our ($DB_CREATE_OR_OPEN, $DB_OPEN);
our $DB_NO_SYNC = 0;
our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : 1_000_000;
use constant DEBUG => !!$ENV{DEBUG};
my $xapianlevels = qr/\A(?:full|medium)\z/;
my $hex = '[a-f0-9]';
my $OID = $hex .'{40,}';
+our $INDEXLEVELS = qr/\A(?:full|medium|basic)\z/;
sub new {
my ($class, $ibx, $creat, $shard) = @_;
ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
- my $levels = qr/\A(?:full|medium|basic)\z/;
my $inboxdir = $ibx->{inboxdir};
my $version = $ibx->version;
my $indexlevel = 'full';
$altid = [ map { PublicInbox::AltId->new($ibx, $_); } @$altid ];
}
if ($ibx->{indexlevel}) {
- if ($ibx->{indexlevel} =~ $levels) {
+ if ($ibx->{indexlevel} =~ $INDEXLEVELS) {
$indexlevel = $ibx->{indexlevel};
} else {
die("Invalid indexlevel $ibx->{indexlevel}\n");
if ($version == 1) {
$self->{lock_path} = "$inboxdir/ssoma.lock";
my $dir = $self->xdir;
- $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
- $self->{over}->{-no_fsync} = 1 if $ibx->{-no_fsync};
+ $self->{oidx} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
+ $self->{oidx}->{-no_fsync} = 1 if $ibx->{-no_fsync};
} elsif ($version == 2) {
defined $shard or die "shard is required for v2\n";
# shard is a number
}
eval 'require '.$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) |
}
}
return unless defined $flag;
- $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_fsync};
+ $flag |= $DB_NO_SYNC if ($self->{ibx} // $self->{eidx})->{-no_fsync};
my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
- if ($@) {
- die "Failed opening $dir: ", $@;
- }
+ croak "Failed opening $dir: $@" if $@;
$self->{xdb} = $xdb;
}
$self->{term_generator} //= do {
my $tg = $X->{TermGenerator}->new;
- $tg->set_stemmer($self->stemmer);
+ $tg->set_stemmer(PublicInbox::Search::stemmer($self));
$tg;
}
}
}
}
+sub index_list_id ($$$) {
+ my ($self, $doc, $hdr) = @_;
+ for my $l ($hdr->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->add_boolean_term('G' . $lid);
+ index_text($self, $lid, 1, 'XL'); # probabilistic
+ }
+}
+
sub index_ids ($$$$) {
my ($self, $doc, $hdr, $mids) = @_;
for my $mid (@$mids) {
}
}
$doc->add_boolean_term('Q' . $_) for @$mids;
- for my $l ($hdr->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = $1;
- $doc->add_boolean_term('G' . $lid);
- index_text($self, $lid, 1, 'XL'); # probabilistic
- }
+ index_list_id($self, $doc, $hdr);
}
sub add_xapian ($$$$) {
$tg->set_document($doc);
index_headers($self, $smsg);
+ if (defined(my $eidx_key = $smsg->{eidx_key})) {
+ $doc->add_boolean_term('O'.$eidx_key);
+ }
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
# of the fields which exist in over.sqlite3. We may stop
# storing doc_data in Xapian sometime after we get multi-inbox
# search working.
- if (my $over = $self->{over}) { # v1 only
- $over->add_overview($mime, $smsg);
+ if (my $oidx = $self->{oidx}) { # v1 only
+ $oidx->add_overview($mime, $smsg);
}
if (need_xapian($self)) {
add_xapian($self, $mime, $smsg, $mids);
$smsg->{num};
}
+sub _get_doc ($$) {
+ my ($self, $docid) = @_;
+ my $doc = eval { $self->{xdb}->get_document($docid) };
+ $doc // do {
+ warn "E: $@\n" if $@;
+ warn "E: #$docid missing in Xapian\n";
+ undef;
+ }
+}
+
+sub add_eidx_info {
+ my ($self, $docid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid) or return;
+ term_generator($self)->set_document($doc);
+ $doc->add_boolean_term('O'.$eidx_key);
+ index_list_id($self, $doc, $eml);
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_eidx_info {
+ my ($self, $docid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ 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 ? $eml->header_raw('List-Id') : ()) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ eval { $doc->remove_term('G' . $lid) };
+ warn "W: ->remove_term G$lid: $@\n" if $@;
+
+ # nb: we don't remove the XL probabilistic terms
+ # since terms may overlap if cross-posted.
+ #
+ # IOW, a message which has both <foo.example.com>
+ # and <bar.example.com> would have overlapping
+ # "XLexample" and "XLcom" as terms and which we
+ # wouldn't know if they're safe to remove if we just
+ # unindex <foo.example.com> while preserving
+ # <bar.example.com>.
+ #
+ # In any case, this entire sub is will likely never
+ # be needed and users using the "l:" prefix are probably
+ # rarer.
+ }
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub get_val ($$) {
+ my ($doc, $col) = @_;
+ sortable_unserialise($doc->get_value($col));
+}
+
+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());
+ 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);
+ $smsg;
+}
+
sub xdb_remove {
- my ($self, $oid, @removed) = @_;
+ my ($self, @docids) = @_;
my $xdb = $self->{xdb} or return;
- for my $num (@removed) {
- my $doc = eval { $xdb->get_document($num) };
- unless ($doc) {
- warn "E: $@\n" if $@;
- warn "E: #$num $oid missing in Xapian\n";
- next;
- }
- my $smsg = bless {}, 'PublicInbox::Smsg';
- $smsg->load_expand($doc);
- my $blob = $smsg->{blob} // '(unset)';
- if ($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->{over};
+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 {
my $nr = 0;
my %tmp;
for my $mid (@$mids) {
- my @removed = eval { $self->{over}->remove_oid($oid, $mid) };
- if ($@) {
- warn "E: failed to remove <$mid> from overview: $@\n";
- } else {
- $nr += scalar @removed;
- $tmp{$_}++ for @removed;
- }
+ my @removed = $self->{oidx}->remove_oid($oid, $mid);
+ $nr += scalar @removed;
+ $tmp{$_}++ for @removed;
}
if (!$nr) {
- $mids = join('> <', @$mids);
- warn "W: <$mids> missing for removal from overview\n";
+ my $m = join('> <', @$mids);
+ warn "W: <$m> missing for removal from overview\n";
}
while (my ($num, $nr) = each %tmp) {
warn "BUG: $num appears >1 times ($nr) for $oid\n" if $nr != 1;
} 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 {
my $mids = mids($mime);
my $mm = $self->{mm};
if ($sync->{reindex}) {
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
for my $mid (@$mids) {
- my ($num, undef) = $over->num_mid0_for_oid($oid, $mid);
+ my ($num, undef) = $oidx->num_mid0_for_oid($oid, $mid);
return $num if defined $num;
}
$mm->num_for($mids->[0]) // $mm->mid_insert($mids->[0]);
$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);
+ 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, $self) = @_;
- unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
+ my ($bref, $oid, $type, $size, $sync) = @_;
+ unindex_eml($sync->{sidx}, $oid, PublicInbox::Eml->new($bref));
+ # may be undef if leftover
+ if (defined(my $cur_cmt = $sync->{cur_cmt})) {
+ ${$sync->{latest_cmt}} = $cur_cmt;
+ }
+}
+
+sub with_umask {
+ my $self = shift;
+ ($self->{ibx} // $self->{eidx})->with_umask(@_);
}
# called by public-inbox-index
sub index_sync {
my ($self, $opt) = @_;
delete $self->{lock_path} if $opt->{-skip_lock};
- $self->{ibx}->with_umask(\&_index_sync, $self, $opt);
- if ($opt->{reindex}) {
+ $self->with_umask(\&_index_sync, $self, $opt);
+ if ($opt->{reindex} && !$opt->{quit}) {
my %again = %$opt;
delete @again{qw(rethread reindex)};
index_sync($self, \%again);
+ $opt->{quit} = $again{quit}; # propagate to caller
}
}
sub v1_checkpoint ($$;$) {
my ($self, $sync, $stk) = @_;
- $self->{ibx}->git->check_async_wait;
- $self->{ibx}->git->cat_async_wait;
+ $self->{ibx}->git->async_wait_all;
- # latest_cmt may be undef
- my $newest = $stk ? $stk->{latest_cmt} : undef;
- if ($newest) {
+ # $newest may be undef
+ my $newest = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}};
+ if (defined($newest)) {
my $cur = $self->{mm}->last_commit || '';
if (need_update($self, $cur, $newest)) {
$self->{mm}->last_commit($newest);
}
- } else {
- ${$sync->{max}} = $self->{batch_bytes};
}
+ ${$sync->{max}} = $self->{batch_bytes};
$self->{mm}->{dbh}->commit;
- if ($newest && need_xapian($self)) {
- my $xdb = $self->{xdb};
+ my $xdb = need_xapian($self) ? $self->{xdb} : undef;
+ if ($newest && $xdb) {
my $cur = $xdb->get_metadata('last_commit');
if (need_update($self, $cur, $newest)) {
$xdb->set_metadata('last_commit', $newest);
}
-
+ }
+ if ($stk) { # all done if $stk is passed
# let SearchView know a full --reindex was done so it can
# generate ->has_threadid-dependent links
- if ($sync->{reindex} && !ref($sync->{reindex})) {
+ if ($xdb && $sync->{reindex} && !ref($sync->{reindex})) {
my $n = $xdb->get_metadata('has_threadid');
$xdb->set_metadata('has_threadid', '1') if $n ne '1';
}
+ $self->{oidx}->rethread_done($sync->{-opt}); # all done
}
-
- $self->{over}->rethread_done($sync->{-opt}) if $newest; # all done
commit_txn_lazy($self);
- $self->{ibx}->git->cleanup;
+ $sync->{ibx}->git->cleanup;
my $nr = ${$sync->{nr}};
idx_release($self, $nr);
# let another process do some work...
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);
$self->{mm}->{dbh}->begin_work;
}
# only for v1
sub process_stack {
my ($self, $sync, $stk) = @_;
- my $git = $self->{ibx}->git;
+ my $git = $sync->{ibx}->git;
my $max = $self->{batch_bytes};
my $nr = 0;
$sync->{nr} = \$nr;
$sync->{max} = \$max;
$sync->{sidx} = $self;
+ $sync->{latest_cmt} = \(my $latest_cmt);
$self->{mm}->{dbh}->begin_work;
if (my @leftovers = keys %{delete($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, $self);
+ $git->cat_async($oid, \&unindex_both, $sync);
}
}
if ($sync->{max_size} = $sync->{-opt}->{max_size}) {
$sync->{index_oid} = \&index_both;
}
- while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
+ while (my ($f, $at, $ct, $oid, $cur_cmt) = $stk->pop_rec) {
+ my $arg = { %$sync, cur_cmt => $cur_cmt };
+ last if $sync->{quit};
if ($f eq 'm') {
- my $arg = { %$sync, autime => $at, cotime => $ct };
+ $arg->{autime} = $at;
+ $arg->{cotime} = $ct;
if ($sync->{max_size}) {
$git->check_async($oid, \&check_size, $arg);
} else {
}
v1_checkpoint($self, $sync) if $max <= 0;
} elsif ($f eq 'd') {
- $git->cat_async($oid, \&unindex_both, $self);
+ $git->cat_async($oid, \&unindex_both, $arg);
}
}
- v1_checkpoint($self, $sync, $stk);
+ v1_checkpoint($self, $sync, $sync->{quit} ? undef : $stk);
}
-sub log2stack ($$$$) {
- my ($sync, $git, $range, $ibx) = @_;
+sub log2stack ($$$) {
+ my ($sync, $git, $range) = @_;
my $D = $sync->{D}; # OID_BIN => NR (if reindexing, undef otherwise)
my ($add, $del);
- if ($ibx->version == 1) {
+ if ($sync->{ibx}->version == 1) {
my $path = $hex.'{2}/'.$hex.'{38}';
$add = qr!\A:000000 100644 \S+ ($OID) A\t$path$!;
$del = qr!\A:100644 000000 ($OID) \S+ D\t$path$!;
my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
--no-notes --no-color --no-renames --no-abbrev),
$range);
- my ($at, $ct, $stk);
+ my ($at, $ct, $stk, $cmt);
while (<$fh>) {
+ return if $sync->{quit};
if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
- ($at, $ct) = ($1 + 0, $2 + 0);
- $stk //= PublicInbox::IdxStack->new($3);
+ ($at, $ct, $cmt) = ($1 + 0, $2 + 0, $3);
+ $stk //= PublicInbox::IdxStack->new($cmt);
} elsif (/$del/) {
my $oid = $1;
if ($D) { # reindex case
$D->{pack('H*', $oid)}++;
} else { # non-reindex case:
- $stk->push_rec('d', $at, $ct, $oid);
+ $stk->push_rec('d', $at, $ct, $oid, $cmt);
}
} elsif (/$add/) {
my $oid = $1;
my $oid_bin = pack('H*', $oid);
my $nr = --$D->{$oid_bin};
delete($D->{$oid_bin}) if $nr <= 0;
-
# nr < 0 (-1) means it never existed
- $stk->push_rec('m', $at, $ct, $oid) if $nr < 0;
- } else {
- $stk->push_rec('m', $at, $ct, $oid);
+ next if $nr >= 0;
}
+ $stk->push_rec('m', $at, $ct, $oid, $cmt);
}
}
close $fh or die "git log failed: \$?=$?";
$stk->read_prepare;
}
-sub prepare_stack ($$$) {
- my ($self, $sync, $range) = @_;
- my $git = $self->{ibx}->git;
+sub prepare_stack ($$) {
+ my ($sync, $range) = @_;
+ my $git = $sync->{ibx}->git;
if (index($range, '..') < 0) {
# don't show annoying git errors to users who run -index
return PublicInbox::IdxStack->new->read_prepare if $?;
}
$sync->{D} = $sync->{reindex} ? {} : undef; # OID_BIN => NR
- log2stack($sync, $git, $range, $self->{ibx});
+ log2stack($sync, $git, $range);
}
# --is-ancestor requires git 1.8.0+
ref($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 $git = $self->{ibx}->git;
+ my $ibx = $self->{ibx};
$self->{batch_bytes} = $opt->{batch_size} // $BATCH_BYTES;
- $git->batch_prepare;
+ $ibx->git->batch_prepare;
my $pr = $opt->{-progress};
- my $sync = { reindex => $opt->{reindex}, -opt => $opt };
+ 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;
- $self->{over}->rethread_prepare($opt);
+ $self->{oidx}->rethread_prepare($opt);
my $mm = _msgmap_init($self);
if ($sync->{reindex}) {
my $last = $mm->last_commit;
my $lx = reindex_from($sync->{reindex}, $last_commit);
my $range = $lx eq '' ? $tip : "$lx..$tip";
$pr->("counting changes\n\t$range ... ") if $pr;
- my $stk = prepare_stack($self, $sync, $range);
+ 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 {
sub _begin_txn {
my ($self) = @_;
my $xdb = $self->{xdb} || idx_acquire($self);
- $self->{over}->begin_lazy if $self->{over};
+ $self->{oidx}->begin_lazy if $self->{oidx};
$xdb->begin_transaction if $xdb;
$self->{txn} = 1;
$xdb;
sub begin_txn_lazy {
my ($self) = @_;
- $self->{ibx}->with_umask(\&_begin_txn, $self) if !$self->{txn};
+ $self->with_umask(\&_begin_txn, $self) if !$self->{txn};
}
# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
set_metadata_once($self);
$xdb->commit_transaction;
}
- $self->{over}->commit_lazy if $self->{over};
+ $self->{oidx}->commit_lazy if $self->{oidx};
}
sub commit_txn_lazy {
my ($self) = @_;
delete($self->{txn}) and
- $self->{ibx}->with_umask(\&_commit_txn, $self);
+ $self->with_umask(\&_commit_txn, $self);
}
sub worker_done {
die "$$ $0 still in transaction\n" if $self->{txn};
}
+sub eidx_shard_new {
+ my ($class, $eidx, $shard) = @_;
+ my $self = bless {
+ eidx => $eidx,
+ xpfx => $eidx->{xpfx},
+ indexlevel => $eidx->{indexlevel},
+ -skip_docdata => 1,
+ shard => $shard,
+ creat => 1,
+ }, $class;
+ $self->{-set_indexlevel_once} = 1 if $self->{indexlevel} eq 'medium';
+ $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;