use PublicInbox::IdxStack;
use Carp qw(croak);
use POSIX qw(strftime);
+use Time::Local qw(timegm);
use PublicInbox::OverIdx;
-use PublicInbox::Spawn qw(spawn);
+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 nodatacow_dir);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size);
my $X = \%PublicInbox::Search::X;
my ($DB_CREATE_OR_OPEN, $DB_OPEN);
our $DB_NO_SYNC = 0;
-our $BATCH_BYTES = defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
- 0x7fffffff : 1_000_000;
+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");
}, $class;
$self->xpfx_init;
$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;
- $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
- $self->{over}->{-no_sync} = 1 if $ibx->{-no_sync};
- $self->{index_max_size} = $ibx->{index_max_size};
+ $self->{oidx} = PublicInbox::OverIdx->new("$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) |
1;
}
-sub nodatacow_dir ($) {
- my ($dir) = @_;
- opendir my $dh, $dir or die "opendir($dir): $!\n";
- PublicInbox::Spawn::set_nodatacow(fileno($dh));
-}
-
sub idx_acquire {
my ($self) = @_;
my $flag;
($is_shard && need_xapian($self)))) {
File::Path::mkpath($dir);
nodatacow_dir($dir);
+ $self->{-set_has_threadid_once} = 1;
}
}
return unless defined $flag;
- $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_sync};
+ $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_fsync};
my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
- if ($@) {
- die "Failed opening $dir: ", $@;
- }
+ croak "Failed opening $dir: $@" if $@;
$self->{xdb} = $xdb;
}
}
}
+sub index_list_id ($$$) {
+ my ($self, $doc, $hdr) = @_;
+ for my $l ($hdr->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->add_boolean_term('G' . $lid);
+ index_text($self, $lid, 1, 'XL'); # probabilistic
+ }
+}
+
sub index_ids ($$$$) {
my ($self, $doc, $hdr, $mids) = @_;
for my $mid (@$mids) {
}
}
$doc->add_boolean_term('Q' . $_) for @$mids;
- for my $l ($hdr->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = $1;
- $doc->add_boolean_term('G' . $lid);
- index_text($self, $lid, 1, 'XL'); # probabilistic
- }
+ index_list_id($self, $doc, $hdr);
}
sub add_xapian ($$$$) {
- my ($self, $mime, $smsg, $mids) = @_;
- my $hdr = $mime->header_obj;
+ my ($self, $eml, $smsg, $mids) = @_;
my $doc = $X->{Document}->new;
add_val($doc, PublicInbox::Search::TS(), $smsg->{ts});
my @ds = gmtime($smsg->{ds});
add_val($doc, PublicInbox::Search::DT(), $dt);
add_val($doc, PublicInbox::Search::BYTES(), $smsg->{bytes});
add_val($doc, PublicInbox::Search::UID(), $smsg->{num});
+ add_val($doc, PublicInbox::Search::THREADID, $smsg->{tid});
my $tg = term_generator($self);
$tg->set_document($doc);
index_headers($self, $smsg);
- msg_iter($mime, \&index_xapian, [ $self, $doc ]);
- index_ids($self, $doc, $hdr, $mids);
- $smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP
- PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids);
- my $data = $smsg->to_doc_data;
- $doc->set_data($data);
+ if (defined(my $eidx_key = $smsg->{eidx_key})) {
+ $doc->add_boolean_term('O'.$eidx_key);
+ $doc->add_boolean_term('P'.
+ "$eidx_key:$smsg->{num}:$smsg->{blob}");
+ }
+ msg_iter($eml, \&index_xapian, [ $self, $doc ]);
+ index_ids($self, $doc, $eml, $mids);
+
+ # by default, we maintain compatibility with v1.5.0 and earlier
+ # by writing to docdata.glass, users who never exect to downgrade can
+ # use --skip-docdata
+ if (!$self->{-skip_docdata}) {
+ # WWW doesn't need {to} or {cc}, only NNTP
+ $smsg->{to} = $smsg->{cc} = '';
+ PublicInbox::OverIdx::parse_references($smsg, $eml, $mids);
+ my $data = $smsg->to_doc_data;
+ $doc->set_data($data);
+ }
+
if (my $altid = $self->{-altid}) {
foreach my $alt (@$altid) {
my $pfx = $alt->{xprefix};
die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 1;
$self->{mm} //= eval {
require PublicInbox::Msgmap;
- my $rw = $self->{ibx}->{-no_sync} ? 2 : 1;
+ my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
};
}
sub add_message {
# mime = PublicInbox::Eml or Email::MIME object
my ($self, $mime, $smsg, $sync) = @_;
- my $hdr = $mime->header_obj;
- my $mids = mids_for_index($hdr);
+ my $mids = mids_for_index($mime);
$smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat
$smsg->{mid} //= $mids->[0]; # v1 compatibility
$smsg->{num} //= do { # v1
};
# v1 and tests only:
- $smsg->populate($hdr, $sync);
+ $smsg->populate($mime, $sync);
$smsg->{bytes} //= length($mime->as_string);
eval {
# 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, $oid) = @_;
+ my $doc = eval { $self->{xdb}->get_document($docid) };
+ $doc // do {
+ warn "E: $@\n" if $@;
+ warn "E: #$docid $oid missing in Xapian\n";
+ undef;
+ }
+}
+
+sub add_xref3 {
+ my ($self, $docid, $xnum, $oid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ term_generator($self)->set_document($doc);
+ $doc->add_boolean_term('O'.$eidx_key);
+ $doc->add_boolean_term('P'."$eidx_key:$xnum:$oid");
+ index_list_id($self, $doc, $eml);
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_xref3 {
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ my $xref3 = PublicInbox::Smsg::xref3(undef, $doc);
+ my %x3 = map { $_ => undef } @$xref3;
+ for (grep(/\A\Q$eidx_key\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
+ delete $x3{$_};
+ $doc->remove_term('P' . $_);
+ }
+ if (scalar(keys(%x3)) == 0) {
+ $self->{xdb}->delete_document($docid);
+ if (my $del_fh = $self->{del_fh}) { # TODO
+ print $del_fh $docid, "\n" or die "E: print $!";
+ }
+ } else {
+ if (!grep(/\A\Q$eidx_key\E:/, keys %x3)) {
+ $doc->remove_term('O'.$eidx_key);
+ }
+ for my $l ($eml->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->remove_term('G' . $lid);
+
+ # 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 $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) {
+ 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";
sub remove_by_oid {
my ($self, $oid, $num) = @_;
- die "BUG: remove_by_oid is v2-only\n" if $self->{over};
+ die "BUG: remove_by_oid is v2-only\n" if $self->{oidx};
$self->begin_txn_lazy;
xdb_remove($self, $oid, $num) if need_xapian($self);
}
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);
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]);
# called by public-inbox-index
sub index_sync {
- my ($self, $opts) = @_;
- delete $self->{lock_path} if $opts->{-skip_lock};
- $self->{ibx}->with_umask(\&_index_sync, $self, $opts);
- if ($opts->{reindex}) {
- my %again = %$opts;
+ my ($self, $opt) = @_;
+ delete $self->{lock_path} if $opt->{-skip_lock};
+ $self->{ibx}->with_umask(\&_index_sync, $self, $opt);
+ if ($opt->{reindex}) {
+ my %again = %$opt;
delete @again{qw(rethread reindex)};
index_sync($self, \%again);
}
sub check_size { # check_async cb for -index --max-size=...
my ($oid, $type, $size, $arg, $git) = @_;
(($type // '') eq 'blob') or die "E: bad $oid in $git->{git_dir}";
- if ($size <= $arg->{index_max_size}) {
+ if ($size <= $arg->{max_size}) {
$git->cat_async($oid, $arg->{index_oid}, $arg);
} else {
- warn "W: skipping $oid ($size > $arg->{index_max_size})\n";
+ warn "W: skipping $oid ($size > $arg->{max_size})\n";
}
}
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;
$self->{mm}->last_commit($newest);
}
} else {
- ${$sync->{max}} = $BATCH_BYTES;
+ ${$sync->{max}} = $self->{batch_bytes};
}
$self->{mm}->{dbh}->commit;
if ($newest && need_xapian($self)) {
- my $cur = $self->{xdb}->get_metadata('last_commit');
+ my $xdb = $self->{xdb};
+ my $cur = $xdb->get_metadata('last_commit');
if (need_update($self, $cur, $newest)) {
- $self->{xdb}->set_metadata('last_commit', $newest);
+ $xdb->set_metadata('last_commit', $newest);
+ }
+
+ # let SearchView know a full --reindex was done so it can
+ # generate ->has_threadid-dependent links
+ if ($sync->{reindex} && !ref($sync->{reindex})) {
+ my $n = $xdb->get_metadata('has_threadid');
+ $xdb->set_metadata('has_threadid', '1') if $n ne '1';
}
}
- $self->{over}->rethread_done($sync->{-opt}) if $newest; # all done
+ $self->{oidx}->rethread_done($sync->{-opt}) if $newest; # all done
commit_txn_lazy($self);
$self->{ibx}->git->cleanup;
my $nr = ${$sync->{nr}};
sub process_stack {
my ($self, $sync, $stk) = @_;
my $git = $self->{ibx}->git;
- my $max = $BATCH_BYTES;
+ my $max = $self->{batch_bytes};
my $nr = 0;
$sync->{nr} = \$nr;
$sync->{max} = \$max;
$git->cat_async($oid, \&unindex_both, $self);
}
}
- if ($sync->{index_max_size} = $self->{ibx}->{index_max_size}) {
+ if ($sync->{max_size} = $sync->{-opt}->{max_size}) {
$sync->{index_oid} = \&index_both;
}
while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
if ($f eq 'm') {
my $arg = { %$sync, autime => $at, cotime => $ct };
- if ($sync->{index_max_size}) {
+ if ($sync->{max_size}) {
$git->check_async($oid, \&check_size, $arg);
} else {
$git->cat_async($oid, \&index_both, $arg);
$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, $sync->{ibx});
}
# --is-ancestor requires git 1.8.0+
# indexes all unindexed messages (v1 only)
sub _index_sync {
- my ($self, $opts) = @_;
- my $tip = $opts->{ref} || 'HEAD';
- my $git = $self->{ibx}->git;
- $git->batch_prepare;
- my $pr = $opts->{-progress};
- my $sync = { reindex => $opts->{reindex}, -opt => $opts };
+ my ($self, $opt) = @_;
+ my $tip = $opt->{ref} || 'HEAD';
+ my $ibx = $self->{ibx};
+ $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 $xdb = $self->begin_txn_lazy;
- $self->{over}->rethread_prepare($opts);
+ $self->{oidx}->rethread_prepare($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);
$_[0]->{lockfh} = undef;
}
-# remote_* subs are only used by SearchIdxPart
-sub remote_commit {
- my ($self) = @_;
- if (my $w = $self->{w}) {
- print $w "commit\n" or die "failed to write commit: $!";
- } else {
- $self->commit_txn_lazy;
- }
-}
-
-sub remote_close {
- my ($self) = @_;
- if (my $w = delete $self->{w}) {
- my $pid = delete $self->{pid} or die "no process to wait on\n";
- print $w "close\n" or die "failed to write to pid:$pid: $!\n";
- close $w or die "failed to close pipe for pid:$pid: $!\n";
- waitpid($pid, 0) == $pid or die "remote process did not finish";
- $? == 0 or die ref($self)." pid:$pid exited with: $?";
- } else {
- die "transaction in progress $self\n" if $self->{txn};
- idx_release($self) if $self->{xdb};
- }
-}
-
-sub remote_remove {
- my ($self, $oid, $num) = @_;
- if (my $w = $self->{w}) {
- # triggers remove_by_oid in a shard
- print $w "D $oid $num\n" or die "failed to write remove $!";
- } else {
- $self->remove_by_oid($oid, $num);
- }
-}
-
sub _begin_txn {
my ($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;
$xdb;
# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
# This metadata is read by Admin::detect_indexlevel:
-sub set_indexlevel {
+sub set_metadata_once {
my ($self) = @_;
- if (!$self->{shard} && # undef or 0, not >0
- delete($self->{-set_indexlevel_once})) {
- my $xdb = $self->{xdb};
+ return if $self->{shard}; # only continue if undef or 0, not >0
+ my $xdb = $self->{xdb};
+
+ if (delete($self->{-set_has_threadid_once})) {
+ $xdb->set_metadata('has_threadid', '1');
+ }
+ if (delete($self->{-set_indexlevel_once})) {
my $level = $xdb->get_metadata('indexlevel');
if (!$level || $level ne 'medium') {
$xdb->set_metadata('indexlevel', 'medium');
}
}
+ if (delete($self->{-set_skip_docdata_once})) {
+ $xdb->get_metadata('skip_docdata') or
+ $xdb->set_metadata('skip_docdata', '1');
+ }
}
sub _commit_txn {
my ($self) = @_;
if (my $xdb = $self->{xdb}) {
- set_indexlevel($self);
+ 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 {
die "$$ $0 still in transaction\n" if $self->{txn};
}
+sub eidx_shard_new {
+ my ($class, $eidx, $shard) = @_;
+ my $self = bless {
+ 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;
+}
+
1;