package PublicInbox::SearchIdx;
use strict;
use warnings;
-use Fcntl qw(:flock :DEFAULT);
+use base qw(PublicInbox::Search PublicInbox::Lock);
use PublicInbox::MIME;
-use base qw(PublicInbox::Search);
use PublicInbox::MID qw/mid_clean id_compress mid_mime mids references/;
use PublicInbox::MsgIter;
use Carp qw(croak);
my ($self) = @_;
my $xdb = delete $self->{xdb} or croak 'not acquired';
$xdb->close;
- _lock_release($self) if $self->{creat};
+ $self->lock_release if $self->{creat};
undef;
}
my $flag = Search::Xapian::DB_OPEN;
if ($self->{creat}) {
require File::Path;
- _lock_acquire($self);
+ $self->lock_acquire;
File::Path::mkpath($dir);
$flag = Search::Xapian::DB_CREATE_OR_OPEN;
}
$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
}
-# we only acquire the flock if creating or reindexing;
-# PublicInbox::Import already has the lock on its own.
-sub _lock_acquire {
- my ($self) = @_;
- croak 'already locked' if $self->{lockfh};
- my $lock_path = $self->{lock_path} or return;
- sysopen(my $lockfh, $lock_path, O_WRONLY|O_CREAT) or
- die "failed to open lock $lock_path: $!\n";
- flock($lockfh, LOCK_EX) or die "lock failed: $!\n";
- $self->{lockfh} = $lockfh;
-}
-
-sub _lock_release {
- my ($self) = @_;
- return unless $self->{lock_path};
- my $lockfh = delete $self->{lockfh} or croak 'not locked';
- flock($lockfh, LOCK_UN) or die "unlock failed: $!\n";
- close $lockfh or die "close failed: $!\n";
-}
-
sub add_val ($$$) {
my ($doc, $col, $num) = @_;
$num = Search::Xapian::sortable_serialise($num);
}
sub add_message {
- my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
+ # mime = Email::MIME object
+ my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
my $doc_id;
my $mids = mids($mime->header_obj);
my $skel = $self->{skeleton};
# populates smsg->references for smsg->to_doc_data
my $refs = parse_references($smsg);
- my $data = $smsg->to_doc_data($blob);
+ $mid0 = $mids->[0] unless defined $mid0;
+ my $data = $smsg->to_doc_data($oid, $mid0);
foreach my $mid (@$mids) {
$tg->index_text($mid, 1, 'XM');
}
$doc_id;
}
-# returns deleted doc_id on success, undef on missing
+sub batch_do {
+ my ($self, $termval, $cb) = @_;
+ my $batch_size = 1000; # don't let @ids grow too large to avoid OOM
+ while (1) {
+ my ($head, $tail) = $self->find_doc_ids($termval);
+ return if $head == $tail;
+ my @ids;
+ for (; $head != $tail && @ids < $batch_size; $head->inc) {
+ push @ids, $head->get_docid;
+ }
+ $cb->(\@ids);
+ }
+}
+
sub remove_message {
my ($self, $mid) = @_;
my $db = $self->{xdb};
- my $doc_id;
+ my $called;
$mid = mid_clean($mid);
eval {
- my ($head, $tail) = $self->find_doc_ids('Q' . $mid);
- if ($head->equal($tail)) {
- warn "cannot remove non-existent <$mid>\n";
- }
- for (; $head != $tail; $head->inc) {
- my $docid = $head->get_docid;
- $db->delete_document($docid);
- }
+ batch_do($self, 'Q' . $mid, sub {
+ my ($ids) = @_;
+ $db->delete_document($_) for @$ids;
+ $called = 1;
+ });
};
-
if ($@) {
warn "failed to remove message <$mid>: $@\n";
- return undef;
+ } elsif (!$called) {
+ warn "cannot remove non-existent <$mid>\n";
}
- $doc_id;
+}
+
+# MID is a hint in V2
+sub remove_by_oid {
+ my ($self, $oid, $mid) = @_;
+ my $db = $self->{xdb};
+
+ # XXX careful, we cannot use batch_do here since we conditionally
+ # delete documents based on other factors, so we cannot call
+ # find_doc_ids twice.
+ my ($head, $tail) = $self->find_doc_ids('Q' . $mid);
+ return if $head == $tail;
+
+ # there is only ONE element in @delete unless we
+ # have bugs in our v2writable deduplication check
+ my @delete;
+ for (; $head != $tail; $head->inc) {
+ my $docid = $head->get_docid;
+ my $doc = $db->get_document($docid);
+ my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
+ $smsg->load_expand;
+ push(@delete, $docid) if $smsg->{blob} eq $oid;
+ }
+ $db->delete_document($_) foreach @delete;
+ scalar(@delete);
}
sub term_generator { # write-only
my ($self, $winner_tid, $loser_tid) = @_;
return if $winner_tid == $loser_tid;
my $db = $self->{xdb};
-
- my $batch_size = 1000; # don't let @ids grow too large to avoid OOM
- while (1) {
- my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
- return if $head == $tail;
- my @ids;
- for (; $head != $tail && @ids < $batch_size; $head->inc) {
- push @ids, $head->get_docid;
- }
- foreach my $docid (@ids) {
+ batch_do($self, 'G' . $loser_tid, sub {
+ my ($ids) = @_;
+ foreach my $docid (@$ids) {
my $doc = $db->get_document($docid);
$doc->remove_term('G' . $loser_tid);
$doc->add_boolean_term('G' . $winner_tid);
$db->replace_document($docid, $doc);
}
- }
+ });
}
sub _read_git_config_perm {
my ($self) = @_;
my @cmd = qw(config);
if ($self->{version} == 2) {
- push @cmd, "--file=$self->{mainrepo}/inbox-config";
+ push @cmd, "--file=$self->{mainrepo}/all.git/config";
}
my $fh = $self->{git}->popen(@cmd, 'core.sharedRepository');
local $/ = "\n";
$? == 0 or die ref($self)." pid:$pid exited with: $?";
}
+# triggers remove_by_oid in partition or skeleton
+sub remote_remove {
+ my ($self, $oid, $mid) = @_;
+ print { $self->{w} } "D $oid $mid\n" or
+ die "failed to write remove $!";
+}
+
1;