X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=8bec08da0b168746535bd32c445b87207fe72f5e;hb=811b8d3cbaa790f59b7b107140b86248da16499b;hp=4543bfa1d9acba6e06c4dc3bbe3a91c309123404;hpb=8b1950055d51d4360e596446e5ac0f41008e357d;p=public-inbox.git

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 4543bfa1..8bec08da 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -9,25 +9,19 @@
 # are denoted by a negative NNTP article number.
 package PublicInbox::OverIdx;
 use strict;
-use warnings;
-use base qw(PublicInbox::Over);
+use v5.10.1;
+use parent qw(PublicInbox::Over);
 use IO::Handle;
 use DBI qw(:sql_types); # SQL_BLOB
 use PublicInbox::MID qw/id_compress mids_for_index references/;
 use PublicInbox::Smsg qw(subject_normalized);
 use Compress::Zlib qw(compress);
-use PublicInbox::Search;
 use Carp qw(croak);
 
 sub dbh_new {
 	my ($self) = @_;
 	my $dbh = $self->SUPER::dbh_new($self->{-no_fsync} ? 2 : 1);
 
-	# TRUNCATE reduces I/O compared to the default (DELETE)
-	# We do not use WAL since we're optimized for read-only ops,
-	# (and read-only requires SQLite 3.22.0 (2018-01-22)).
-	$dbh->do('PRAGMA journal_mode = TRUNCATE');
-
 	# 80000 pages (80MiB on SQLite <3.12.0, 320MiB on 3.12.0+)
 	# was found to be good in 2018 during the large LKML import
 	# at the time.  This ought to be configurable based on HW
@@ -190,23 +184,20 @@ sub resolve_mid_to_tid {
 	if (my $del = delete $self->{-ghosts_to_delete}) {
 		delete_by_num($self, $_) for @$del;
 	}
-	$tid // create_ghost($self, $mid);
-}
-
-sub create_ghost {
-	my ($self, $mid) = @_;
-	my $id = mid2id($self, $mid);
-	my $num = next_ghost_num($self);
-	$num < 0 or die "ghost num is non-negative: $num\n";
-	my $tid = next_tid($self);
-	my $dbh = $self->{dbh};
-	$dbh->prepare_cached(<<'')->execute($num, $tid);
+	$tid // do { # create a new ghost
+		my $id = mid2id($self, $mid);
+		my $num = next_ghost_num($self);
+		$num < 0 or die "ghost num is non-negative: $num\n";
+		$tid = next_tid($self);
+		my $dbh = $self->{dbh};
+		$dbh->prepare_cached(<<'')->execute($num, $tid);
 INSERT INTO over (num, tid) VALUES (?,?)
 
-	$dbh->prepare_cached(<<'')->execute($id, $num);
+		$dbh->prepare_cached(<<'')->execute($id, $num);
 INSERT INTO id2num (id, num) VALUES (?,?)
 
-	$tid;
+		$tid;
+	};
 }
 
 sub merge_threads {
@@ -270,6 +261,13 @@ sub subject_path ($) {
 	lc($subj);
 }
 
+sub ddd_for ($) {
+	my ($smsg) = @_;
+	my $dd = $smsg->to_doc_data;
+	utf8::encode($dd);
+	compress($dd);
+}
+
 sub add_overview {
 	my ($self, $eml, $smsg) = @_;
 	$smsg->{lines} = $eml->body_raw =~ tr!\n!\n!;
@@ -281,10 +279,7 @@ sub add_overview {
 		$xpath = subject_path($subj);
 		$xpath = id_compress($xpath);
 	}
-	my $dd = $smsg->to_doc_data;
-	utf8::encode($dd);
-	$dd = compress($dd);
-	add_over($self, [ @$smsg{qw(ts ds num)}, $mids, $refs, $xpath, $dd ]);
+	add_over($self, $smsg, $mids, $refs, $xpath, ddd_for($smsg));
 }
 
 sub _add_over {
@@ -311,10 +306,10 @@ sub _add_over {
 }
 
 sub add_over {
-	my ($self, $values) = @_;
-	my ($ts, $ds, $num, $mids, $refs, $xpath, $ddd) = @$values;
+	my ($self, $smsg, $mids, $refs, $xpath, $ddd) = @_;
 	my $old_tid;
 	my $vivified = 0;
+	my $num = $smsg->{num};
 
 	begin_lazy($self);
 	delete_by_num($self, $num, \$old_tid);
@@ -326,17 +321,17 @@ sub add_over {
 		$v > 1 and warn "BUG: vivified multiple ($v) ghosts for $mid\n";
 		$vivified += $v;
 	}
-	my $tid = $vivified ? $old_tid : link_refs($self, $refs, $old_tid);
-	my $sid = sid($self, $xpath);
+	$smsg->{tid} = $vivified ? $old_tid : link_refs($self, $refs, $old_tid);
+	$smsg->{sid} = sid($self, $xpath);
 	my $dbh = $self->{dbh};
 	my $sth = $dbh->prepare_cached(<<'');
 INSERT INTO over (num, tid, sid, ts, ds, ddd)
 VALUES (?,?,?,?,?,?)
 
-	my $n = 0;
-	my @v = ($num, $tid, $sid, $ts, $ds);
-	foreach (@v) { $sth->bind_param(++$n, $_) }
-	$sth->bind_param(++$n, $ddd, SQL_BLOB);
+	my $nc = 1;
+	$sth->bind_param($nc, $num);
+	$sth->bind_param(++$nc, $smsg->{$_}) for (qw(tid sid ts ds));
+	$sth->bind_param(++$nc, $ddd, SQL_BLOB);
 	$sth->execute;
 	$sth = $dbh->prepare_cached(<<'');
 INSERT INTO id2num (id, num) VALUES (?,?)
@@ -388,12 +383,12 @@ sub create_tables {
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS over (
-	num INTEGER NOT NULL,
-	tid INTEGER NOT NULL,
-	sid INTEGER,
-	ts INTEGER,
-	ds INTEGER,
-	ddd VARBINARY, /* doc-data-deflated */
+	num INTEGER 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)
 )
 
@@ -415,13 +410,13 @@ CREATE TABLE IF NOT EXISTS counter (
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS subject (
 	sid INTEGER PRIMARY KEY AUTOINCREMENT,
-	path VARCHAR(40) NOT NULL,
+	path VARCHAR(40) NOT NULL, /* SHA-1 of normalized subject */
 	UNIQUE (path)
 )
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS id2num (
-	id INTEGER NOT NULL,
+	id INTEGER NOT NULL, /* <=> msgid.id */
 	num INTEGER NOT NULL,
 	UNIQUE (id, num)
 )
@@ -432,7 +427,7 @@ CREATE TABLE IF NOT EXISTS id2num (
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS msgid (
-	id INTEGER PRIMARY KEY AUTOINCREMENT,
+	id INTEGER PRIMARY KEY AUTOINCREMENT, /* <=> id2num.id */
 	mid VARCHAR(244) NOT NULL,
 	UNIQUE (mid)
 )
@@ -448,7 +443,7 @@ sub commit_lazy {
 sub begin_lazy {
 	my ($self) = @_;
 	return if $self->{txn};
-	my $dbh = $self->connect or return;
+	my $dbh = $self->dbh or return;
 	$dbh->begin_work;
 	# $dbh->{Profile} = 2;
 	$self->{txn} = 1;
@@ -460,10 +455,10 @@ sub rollback_lazy {
 	$self->{dbh}->rollback;
 }
 
-sub disconnect {
+sub dbh_close {
 	my ($self) = @_;
 	die "in transaction" if $self->{txn};
-	$self->SUPER::disconnect;
+	$self->SUPER::dbh_close;
 }
 
 sub create {
@@ -474,8 +469,8 @@ sub create {
 		File::Path::mkpath(File::Basename::dirname($self->{filename}));
 	}
 	# create the DB:
-	PublicInbox::Over::connect($self);
-	$self->disconnect;
+	PublicInbox::Over::dbh($self);
+	$self->dbh_close;
 }
 
 sub rethread_prepare {
@@ -521,4 +516,119 @@ EOM
 	$pr->("I: rethread culled $total ghosts\n") if $pr && $total;
 }
 
+# used for cross-inbox search
+sub eidx_prep ($) {
+	my ($self) = @_;
+	$self->{-eidx_prep} //= do {
+		my $dbh = $self->dbh;
+		$dbh->do(<<"");
+INSERT OR IGNORE INTO counter (key) VALUES ('eidx_docid')
+
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS inboxes (
+	ibx_id INTEGER PRIMARY KEY AUTOINCREMENT,
+	eidx_key VARCHAR(255) NOT NULL, /* {newsgroup} // {inboxdir} */
+	UNIQUE (eidx_key)
+)
+
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS xref3 (
+	docid INTEGER NOT NULL, /* <=> over.num */
+	ibx_id INTEGER NOT NULL, /* <=> inboxes.ibx_id */
+	xnum INTEGER NOT NULL, /* NNTP article number in ibx */
+	oidbin VARBINARY NOT NULL, /* 20-byte SHA-1 or 32-byte SHA-256 */
+	UNIQUE (docid, ibx_id, xnum, oidbin)
+)
+
+	$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
+)
+
+		$dbh;
+	};
+}
+
+sub eidx_meta { # requires transaction
+	my ($self, $key, $val) = @_;
+
+	my $sql = 'SELECT val FROM eidx_meta WHERE key = ? LIMIT 1';
+	my $dbh = $self->{dbh};
+	defined($val) or return $dbh->selectrow_array($sql, undef, $key);
+
+	my $prev = $dbh->selectrow_array($sql, undef, $key);
+	if (defined $prev) {
+		$sql = 'UPDATE eidx_meta SET val = ? WHERE key = ?';
+		$dbh->do($sql, undef, $val, $key);
+	} else {
+		$sql = 'INSERT INTO eidx_meta (key,val) VALUES (?,?)';
+		$dbh->do($sql, undef, $key, $val);
+	}
+	$prev;
+}
+
+sub eidx_max {
+	my ($self) = @_;
+	get_counter($self->{dbh}, 'eidx_docid');
+}
+
+sub add_xref3 {
+	my ($self, $docid, $xnum, $oidhex, $eidx_key) = @_;
+	begin_lazy($self);
+	my $ibx_id = id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+	my $oidbin = pack('H*', $oidhex);
+	my $sth = $self->{dbh}->prepare_cached(<<'');
+INSERT OR IGNORE INTO xref3 (docid, ibx_id, xnum, oidbin) VALUES (?, ?, ?, ?)
+
+	$sth->bind_param(1, $docid);
+	$sth->bind_param(2, $ibx_id);
+	$sth->bind_param(3, $xnum);
+	$sth->bind_param(4, $oidbin, SQL_BLOB);
+	$sth->execute;
+}
+
+sub remove_xref3 {
+	my ($self, $docid, $oidhex, $eidx_key) = @_;
+	begin_lazy($self);
+	my $oidbin = pack('H*', $oidhex);
+	my $sth;
+	if (defined $eidx_key) {
+		my $ibx_id = id_for($self, 'inboxes', 'ibx_id',
+					eidx_key => $eidx_key);
+		$sth = $self->{dbh}->prepare_cached(<<'');
+DELETE FROM xref3 WHERE docid = ? AND ibx_id = ? AND oidbin = ?
+
+		$sth->bind_param(1, $docid);
+		$sth->bind_param(2, $ibx_id);
+		$sth->bind_param(3, $oidbin, SQL_BLOB);
+	} else {
+		$sth = $self->{dbh}->prepare_cached(<<'');
+DELETE FROM xref3 WHERE docid = ? AND oidbin = ?
+
+		$sth->bind_param(1, $docid);
+		$sth->bind_param(2, $oidbin, SQL_BLOB);
+	}
+	$sth->execute;
+}
+
+# for when an xref3 goes missing, this does NOT update {ts}
+sub update_blob {
+	my ($self, $smsg, $oidhex) = @_;
+	my $sth = $self->{dbh}->prepare(<<'');
+UPDATE over SET ddd = ? WHERE num = ?
+
+	$smsg->{blob} = $oidhex;
+	$sth->bind_param(1, ddd_for($smsg), SQL_BLOB);
+	$sth->bind_param(2, $smsg->{num});
+	$sth->execute;
+}
+
 1;