-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# for XOVER, OVER in NNTP, and feeds/homepage/threads in PSGI
}
}
+sub ibx_id {
+ my ($self, $eidx_key) = @_;
+ id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+}
+
sub sid {
my ($self, $path) = @_;
return unless defined $path && $path ne '';
$$tid = $cur_tid;
} else { # rethreading, queue up dead ghosts
$$tid = next_tid($self);
- my $num = $smsg->{num};
- push(@{$self->{-ghosts_to_delete}}, $num) if $num < 0;
+ my $n = $smsg->{num};
+ if ($n > 0) {
+ $self->{dbh}->prepare_cached(<<'')->execute($$tid, $n);
+UPDATE over SET tid = ? WHERE num = ?
+
+ } elsif ($n < 0) {
+ push(@{$self->{-ghosts_to_delete}}, $n);
+ }
}
1;
}
$smsg->{lines} = $eml->body_raw =~ tr!\n!\n!;
my $mids = mids_for_index($eml);
my $refs = parse_references($smsg, $eml, $mids);
+ $mids->[0] //= $smsg->{mid} //= $eml->{-lei_fake_mid};
+ $smsg->{mid} //= '';
my $subj = $smsg->{subject};
my $xpath;
if ($subj ne '') {
}
} elsif ($n < 0) { # ghost
$$old_tid //= $cur_valid ? $cur_tid : next_tid($self);
- link_refs($self, $refs, $$old_tid);
+ $$old_tid = link_refs($self, $refs, $$old_tid);
delete_by_num($self, $n);
$$v++;
}
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS over (
- num INTEGER NOT NULL, /* NNTP article number == IMAP UID */
+ num INTEGER PRIMARY KEY NOT NULL, /* NNTP article number == IMAP UID */
tid INTEGER NOT NULL, /* THREADID (IMAP REFERENCES threading, JMAP) */
sid INTEGER, /* Subject ID (IMAP ORDEREDSUBJECT "threading") */
ts INTEGER, /* IMAP INTERNALDATE (Received: header, git commit time) */
ds INTEGER, /* RFC-2822 sent Date: header, git author time */
- ddd VARBINARY, /* doc-data-deflated (->to_doc_data, ->load_from_data) */
- UNIQUE (num)
+ ddd VARBINARY /* doc-data-deflated (->to_doc_data, ->load_from_data) */
)
$dbh->do('CREATE INDEX IF NOT EXISTS idx_tid ON over (tid)');
sub create {
my ($self) = @_;
- unless (-r $self->{filename}) {
+ my $fn = $self->{filename} // do {
+ Carp::confess('BUG: no {filename}') unless $self->{dbh};
+ return;
+ };
+ unless (-r $fn) {
require File::Path;
require File::Basename;
- File::Path::mkpath(File::Basename::dirname($self->{filename}));
+ File::Path::mkpath(File::Basename::dirname($fn));
}
# create the DB:
PublicInbox::Over::dbh($self);
$dbh->do('CREATE INDEX IF NOT EXISTS idx_docid ON xref3 (docid)');
+ # performance critical, this is not UNIQUE since we may need to
+ # tolerate some old bugs from indexing mirrors
+ $dbh->do('CREATE INDEX IF NOT EXISTS idx_nntp ON '.
+ 'xref3 (oidbin,xnum,ibx_id)');
+
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS eidx_meta (
key VARCHAR(255) PRIMARY KEY,
val VARCHAR(255) NOT NULL
)
+ # A queue of current docids which need reindexing.
+ # eidxq persists across aborted -extindex invocations
+ # Currently used for "-extindex --reindex" for Xapian
+ # data, but may be used in more places down the line.
+ $dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS eidxq (
+ docid INTEGER PRIMARY KEY NOT NULL
+)
+
$dbh;
};
}
sub add_xref3 {
my ($self, $docid, $xnum, $oidhex, $eidx_key) = @_;
begin_lazy($self);
- my $ibx_id = id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+ my $ibx_id = ibx_id($self, $eidx_key);
my $oidbin = pack('H*', $oidhex);
my $sth = $self->{dbh}->prepare_cached(<<'');
INSERT OR IGNORE INTO xref3 (docid, ibx_id, xnum, oidbin) VALUES (?, ?, ?, ?)
$sth->execute;
}
+# returns remaining reference count to $docid
sub remove_xref3 {
- my ($self, $docid, $oidhex, $eidx_key) = @_;
+ my ($self, $docid, $oidhex, $eidx_key, $rm_eidx_info) = @_;
begin_lazy($self);
my $oidbin = pack('H*', $oidhex);
- my $sth;
+ my ($sth, $ibx_id);
if (defined $eidx_key) {
- my $ibx_id = id_for($self, 'inboxes', 'ibx_id',
- eidx_key => $eidx_key);
+ $ibx_id = ibx_id($self, $eidx_key);
$sth = $self->{dbh}->prepare_cached(<<'');
DELETE FROM xref3 WHERE docid = ? AND ibx_id = ? AND oidbin = ?
$sth->bind_param(2, $oidbin, SQL_BLOB);
}
$sth->execute;
+ $sth = $self->{dbh}->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE docid = ?
+
+ $sth->execute($docid);
+ my $nr = $sth->fetchrow_array;
+ if ($nr == 0) {
+ delete_by_num($self, $docid);
+ } elsif (defined($ibx_id) && $rm_eidx_info) {
+ # if deduplication rules in ContentHash change, it's
+ # possible a docid can have multiple rows with the
+ # same ibx_id. This governs whether or not we call
+ # ->shard_remove_eidx_info in ExtSearchIdx.
+ $sth = $self->{dbh}->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE docid = ? AND ibx_id = ?
+
+ $sth->execute($docid, $ibx_id);
+ my $count = $sth->fetchrow_array;
+ $$rm_eidx_info = ($count == 0);
+ }
+ $nr;
}
# for when an xref3 goes missing, this does NOT update {ts}
$sth->execute;
}
+sub eidxq_add {
+ my ($self, $docid) = @_;
+ $self->dbh->prepare_cached(<<'')->execute($docid);
+INSERT OR IGNORE INTO eidxq (docid) VALUES (?)
+
+}
+
+sub eidxq_del {
+ my ($self, $docid) = @_;
+ $self->dbh->prepare_cached(<<'')->execute($docid);
+DELETE FROM eidxq WHERE docid = ?
+
+}
+
+sub blob_exists {
+ my ($self, $oidhex) = @_;
+ my $sth = $self->dbh->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE oidbin = ?
+
+ $sth->bind_param(1, pack('H*', $oidhex), SQL_BLOB);
+ $sth->execute;
+ $sth->fetchrow_array;
+}
+
1;